CN116128274A - Data analysis system and method - Google Patents
Data analysis system and method Download PDFInfo
- Publication number
- CN116128274A CN116128274A CN202111333788.4A CN202111333788A CN116128274A CN 116128274 A CN116128274 A CN 116128274A CN 202111333788 A CN202111333788 A CN 202111333788A CN 116128274 A CN116128274 A CN 116128274A
- Authority
- CN
- China
- Prior art keywords
- data
- target
- information
- passenger
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000007405 data analysis Methods 0.000 title claims abstract description 157
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013523 data management Methods 0.000 claims abstract description 46
- 238000004458 analytical method Methods 0.000 claims abstract description 21
- 230000014759 maintenance of location Effects 0.000 claims description 42
- 238000012545 processing Methods 0.000 claims description 18
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 5
- 238000005070 sampling Methods 0.000 description 9
- 210000002569 neuron Anatomy 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004451 qualitative analysis Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005206 flow analysis Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010224 classification analysis Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000014616 translation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a data analysis system and a data analysis method. Wherein, this system includes: the target server acquires a structured data set, wherein each structured data in the structured data set corresponds to each risk point in the target road network one by one, and the structured data comprises passenger flow data information of the corresponding risk point; the data access module is used for accessing the structured data set transmitted by the target server and sending the structured data set to the data management module; the data management module selects target historical data from each structured data, transmits the target historical data to the data analysis module, receives a data analysis result fed back by the data analysis module, and sends the data analysis result to the display module; the data analysis module is used for analyzing each target historical data to obtain a data analysis result; and the display module displays the data analysis result. The method and the device solve the technical problems that the acquired passenger flow data is lack of effective analysis and auxiliary decision information cannot be provided for scheduling staff in the related technology.
Description
Technical Field
The application relates to the technical field of traffic networks, in particular to a data analysis system and a data analysis method.
Background
With the formation of urban rail transit network operation patterns, the scale of station passenger flows is continuously increased, and under emergency conditions, safety accidents such as trampling and the like are extremely easy to occur, so that the risk of large passenger flows cannot be ignored. In the related art, the existing urban rail transit video monitoring system is generally utilized to collect and count passenger flow data of key areas such as a platform, a station hall, a channel and an entrance of a station, so that the detection of the risk of large passenger flow in the key areas of the station is completed, decision assistance is provided for dispatching personnel to give a dispatching command, and the pre-warning and emergency processing capability of subway personnel on the large passenger flow is improved.
However, the existing detection systems for subway passenger flows are mostly focused on the data acquisition directions of face recognition, behavior recognition, density, calculation of the number of people and the like, and tend to quantitative analysis of data statistics, but the qualitative analysis of the trend, feature extraction and classification of the passenger flows along with the time is less, so that visual and clear intelligent decision auxiliary information cannot be provided for the dispatcher.
In view of the above problems, no effective solution has been proposed at present.
Disclosure of Invention
The embodiment of the application provides a data analysis system and a data analysis method, which at least solve the technical problems that the acquired passenger flow data is lack of effective analysis and auxiliary decision information cannot be provided for a dispatcher in the related technology.
According to one aspect of the embodiments of the present application, there is provided a data analysis system comprising: the target server is used for acquiring a structured data set, each structured data in the structured data set corresponds to each risk point in the target road network one by one, and the structured data at least comprises: passenger flow data information of the risk points corresponding to the structured data; the data access module is used for accessing the structured data set transmitted by the target server and sending the structured data set to the data management module; the data management module is used for selecting target historical data from each piece of structured data and transmitting the target historical data to the data analysis module; receiving a data analysis result fed back by the data analysis module, and sending the data analysis result to a display module; the data analysis module is configured to analyze each of the target historical data to obtain the data analysis result, where the data analysis result at least includes: passenger density information, channel count information, congestion duration information and passenger retention state information of each risk point; and the display module is used for displaying the data analysis result.
Optionally, the target server includes: the road network center analysis server is used for acquiring a first customer stream video acquired by acquisition equipment at a preset first type of risk point in the target road network, and analyzing the first customer stream video to obtain the structured data corresponding to the first type of risk point; and each line analysis server is used for acquiring a second passenger flow video acquired by acquisition equipment at a second type risk point in a line corresponding to the line analysis server in the target road network, and analyzing the second passenger flow video to obtain the structured data corresponding to the second type risk point.
Optionally, the structured data includes: passenger flow data type information and the passenger flow data information, wherein the passenger flow data information at least comprises: passenger number information, lane count information; the source information and the acquisition time period of the structured data, wherein the source information comprises: risk point location identification information of the risk point location corresponding to the structured data, the risk point location identification information including: and acquiring equipment identification information of the equipment at the risk point.
Optionally, for any one of the structured data in the structured data set, the data management module is configured to select, according to an acquisition time period of the structured data, the target historical data with a preset duration from the structured data, and transmit the target historical data to the data analysis module.
Optionally, the data analysis module includes a plurality of data analysis submodules, configured to analyze the target historical data to obtain the data analysis result, where the plurality of data analysis submodules at least includes: a first data analysis sub-module for determining the passenger density information, a second data analysis sub-module for determining the channel count information, a third data analysis sub-module for determining the congestion duration information, and a fourth data analysis sub-module for determining the passenger stay status information.
Optionally, for any one of the target historical data, the first data analysis submodule is configured to determine passenger density data of the risk points corresponding to the target historical data according to the passenger number information in the target historical data and a first point table pre-stored parameter of the collecting device corresponding to the target historical data, and order the passenger density data of all the risk points to obtain a passenger density ranking, where the first point table pre-stored parameter includes: area information of the risk point location corresponding to the target history data; for any one of the target historical data, the second data analysis submodule is configured to determine channel count data of the risk points corresponding to the target historical data according to the channel count information in the target historical data and a second point table pre-stored parameter of the acquisition device corresponding to the target historical data, and order the channel count data of all the risk points to obtain a channel count ranking, where the second point table pre-stored parameter includes: acquisition time information of the acquisition equipment corresponding to the target historical data; for any one of the target historical data, the third data analysis submodule is used for carrying out binarization processing on the passenger flow data information in the target historical data according to a preset threshold value, determining the maximum duration that the passenger flow data information in the target historical data continuously exceeds the preset threshold value according to the binarization processing result, obtaining congestion duration data of the risk points corresponding to the target historical data, and sequencing the congestion duration data of all the risk points to obtain a congestion duration ranking; for any one of the target historical data, the fourth data analysis submodule is used for selecting a preset number of data subsets from the target historical data, inputting the preset number of data subsets into a pre-trained neural network model respectively to obtain a preset number of passenger detention state results respectively, and carrying out weighted average calculation on the preset number of passenger detention state results to obtain the passenger detention state of the risk point position corresponding to the target historical data, wherein the neural network model is used for analyzing the passenger detention state according to the input data.
Optionally, the system further comprises: a database module, the database module comprising: a first sub-database for storing the structured data set; the second sub-database is used for storing the data analysis result, wherein the data analysis result at least comprises the following components: the passenger density data, the channel count data, the congestion duration data, the passenger retention state, the passenger density ranking, the channel count ranking and the congestion duration ranking which are classified according to the risk point location identification information corresponding to the target historical data.
Optionally, the display module is further configured to respond to a selection instruction of a target object, obtain, by using the data management module, target structured data, target passenger density data, target channel count data, target congestion duration data, and target passenger retention state corresponding to a target risk point location corresponding to the selection instruction, and display the target structured data, the target passenger density data, the target channel count data, the target congestion duration data, and the target passenger retention state.
According to another aspect of the embodiments of the present application, there is also provided a data analysis method, including: the method comprises the steps of obtaining a structured data set through a target server, wherein each structured data in the structured data set corresponds to each risk point in a target road network one by one, and the structured data at least comprises: passenger flow data information of the risk points corresponding to the structured data; the structured data set transmitted by the target server is accessed through a data access module, and the structured data set is sent to a data management module; selecting target historical data from each structured data through the data management module, and transmitting the target historical data to a data analysis module; analyzing each target historical data through the data analysis module to obtain the data analysis result, and feeding back the data analysis result to the data management module, wherein the data analysis result at least comprises: passenger density information, channel count information, congestion duration information and passenger retention state information of each risk point; the data analysis result is sent to a display module through the data management module; and displaying the data analysis result through the display module.
According to another aspect of the embodiments of the present application, there is further provided a nonvolatile storage medium, where the nonvolatile storage medium includes a stored program, and when the program runs, the device where the nonvolatile storage medium is controlled to execute the data analysis method described above.
In the embodiment of the application, a data analysis system for traffic network passenger flow analysis is provided, in the system, a target server is used for obtaining structured data corresponding to each risk point in a target road network one by one to obtain a structured data set, and the structured data at least comprises passenger flow data information of the corresponding risk point; the data access module is used for accessing the structured data set and sending the structured data set to the data management module; the data management module is used for selecting target historical data from each structured data, transmitting the target historical data to the data analysis module, receiving a data analysis result fed back by the data analysis module, and transmitting the data analysis result to the display module; the data analysis module is used for analyzing each target historical data to obtain a data analysis result; and the display module is used for displaying the data analysis result. The method comprises the steps of summarizing structured data of risk points of each line, carrying out data statistics, feature extraction and qualitative analysis on target historical data in a preset time period, obtaining passenger density information, channel count information, congestion duration information, passenger retention state information and the like of each risk point, displaying the passenger density information, the channel count information, the congestion duration information, the passenger retention state information and the like, and providing decision assistance for a command and dispatch system, so that the technical problem that collected passenger flow data is lack of effective analysis in the related technology and auxiliary decision information cannot be provided for a dispatcher is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute an undue limitation to the application. In the drawings:
FIG. 1 is a schematic diagram of a data analysis system according to an embodiment of the present application;
FIG. 2 is a schematic diagram of another data analysis system according to an embodiment of the present application;
FIG. 3 is a schematic flow chart of an algorithm for determining congestion duration according to an embodiment of the present application;
FIG. 4 is a schematic illustration of a neural network model for determining a passenger retention state according to an embodiment of the present application;
fig. 5 is a flow chart of a data analysis method according to an embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will be made in detail and with reference to the accompanying drawings in the embodiments of the present application, it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that embodiments of the present application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
For a better understanding of the embodiments of the present application, some nouns or translations of terms that appear during the description of the embodiments of the present application are explained as follows:
risk point location: areas marked in traffic networks, where traffic accidents are likely to occur, such as platforms, channels, entrances and exits of stations with large passenger flows.
Example 1
FIG. 1 is a schematic structural diagram of an alternative data analysis system according to an embodiment of the present application, as shown in FIG. 1, where the data analysis system at least includes: a target server 10, a data access module 11, a data management module 12, a data analysis module 13 and a display module 14, wherein:
the target server 10 is configured to obtain a structured data set, where each structured data in the structured data set corresponds to each risk point in the target road network one by one, and the structured data at least includes: passenger flow data information of risk points corresponding to the structured data.
The data access module 11 is configured to access the structured data set transmitted by the target server, and send the structured data set to the data management module.
A data management module 12 for selecting target history data from each structured data, and transmitting the target history data to the data analysis module; and receiving the data analysis result fed back by the data analysis module, and sending the data analysis result to the display module.
The data analysis module 13 is configured to analyze each target history data to obtain a data analysis result, where the data analysis result at least includes: passenger density information, channel count information, congestion duration information and passenger retention state information of each risk point.
And the display module 14 is used for displaying the data analysis result.
In some optional embodiments of the present application, the data analysis system further includes a database module for storing data. Fig. 2 is a schematic structural diagram of another alternative data analysis system according to an embodiment of the present application, in which the target server 10 includes a road network center analysis server 100 running on the road network center side and a plurality of line analysis servers 101 running on the respective line sub-station sides for collecting structured data; the data access module 11, the data management module 12, the data analysis module 13, the display module 14 and the database module 15 may be modules in a data analysis device running on the road network center side, and are used for processing and analyzing the structured data transmitted by the target server 10, so as to provide auxiliary decision information for the dispatcher. Wherein the database module 15 comprises a first sub-database 150 for storing structured data sets and a second sub-database 151 for storing data analysis results.
The specific functions and interaction processes of the modules in the system are described below.
The road network center analysis server 100 is operated at the road network center side, and is used for acquiring a first customer stream video acquired by an acquisition device at a preset first type risk point in the target road network, and analyzing the first customer stream video to obtain structured data corresponding to the first type risk point.
For example, a road network center of a certain city presets 580 risk points for the road network of the whole city, wherein the risk points are first-class risk points, and an acquisition device at each risk point acquires a passenger flow video of the point in real time and uploads the passenger flow video to a road network center analysis server, wherein the acquisition device can be an existing video monitoring device at the risk point or a channel counting device. And after analyzing the passenger flow video, the road network center analysis server generates structured data corresponding to the risk point location.
The plurality of line analysis servers 101 are operated at each line sub-station side of the line network, wherein any line analysis server is used for acquiring second passenger flow videos acquired by acquisition equipment at second type risk points in a line corresponding to the line analysis server in the target line network, and analyzing the second passenger flow videos to obtain structured data corresponding to the second type risk points.
For example, a line monitored by a line substation is provided with a plurality of risk points, wherein the risk points are the second type of risk points, the acquisition equipment at each risk point acquires the passenger flow video of the point in real time, the passenger flow video is uploaded to a line analysis server corresponding to the line substation, and after the line analysis server analyzes the passenger flow video, structured data corresponding to the risk point is generated.
Generally, the structured data at least includes passenger flow data type information and specific passenger flow data information corresponding to each type, such as passenger number information and channel count information; optionally, the structured data further includes: source information and an acquisition time period of the structured data, wherein the source information comprises: risk point location identification information of a risk point location corresponding to the structured data, the risk point location identification information including: device identification information of the acquisition device at the risk point. For example, the source of the structured data can be directly identified by the device ID of the collecting device, or can be identified by the station name corresponding to the risk point location, or can be identified by the server ID, and the user can determine the source according to his own preference.
After the target server 10 obtains the structured data set, it is accessed through the data access module 11, and the structured data set is sent to the data management module 12.
For any structured data in the structured data set, the data management module 12 may first read passenger flow data information, risk point location identification information, and an acquisition time period in the structured data, store the passenger flow data information, the risk point location identification information, the acquisition time period, and the like in the first sub-database 150 according to the risk point location identification information, then select target historical data with a preset duration from the structured data according to the acquisition time period of the structured data, and transmit the target historical data to the data analysis module 13. The preset duration is set by the user according to actual requirements, such as 10 minutes, 15 minutes, and the like.
The data analysis module 13 includes a plurality of data analysis sub-modules, which are configured to analyze the target historical data to obtain a data analysis result, where the plurality of data analysis sub-modules at least includes: a first data analysis sub-module 130 for determining passenger density information, a second data analysis sub-module 131 for determining channel count information, a third data analysis sub-module 132 for determining congestion duration information, and a fourth data analysis sub-module 133 for determining passenger stay status information.
The first data analysis sub-module 130 is configured to run a first data processing algorithm for determining passenger density information, where for any target historical data, the first data processing algorithm determines passenger density data of risk points corresponding to the target historical data according to passenger number information in the target historical data and a first point table pre-stored parameter of an acquisition device corresponding to the target historical data, and sorts passenger density data of all risk points to obtain passenger density ranks, where the first point table pre-stored parameter includes: area information of the risk point location corresponding to the target history data.
For example, the number of passengers in the target historical data corresponding to a certain risk point is 100 (the number may be the average number of passengers within a preset time period or the maximum number), and the area of the first point table of the corresponding acquisition device in the prestored parameters is 100m 2 The passenger density data of the risk point can be calculated to be 100/100=1 person/m 2 The method comprises the steps of carrying out a first treatment on the surface of the And after the passenger density data of all the risk points are calculated, sorting the passenger density data to obtain passenger density ranking.
The first data analysis sub-module 130 feeds back the passenger density data and passenger density ranks of all risk points to the data management module 12, and the data management module 12 stores the passenger density data in the second sub-database 151 according to the classification of the risk point identification information, and simultaneously stores the passenger density ranks in the second sub-database 151.
The second data analysis sub-module 131 runs a second data processing algorithm for determining channel count information, and for any target historical data, the second data processing algorithm determines channel count data of risk points corresponding to the target historical data according to the channel count information in the target historical data and a second point table pre-stored parameter of the acquisition device corresponding to the target historical data, and sorts the channel count data of all risk points to obtain a channel count ranking, wherein the second point table pre-stored parameter includes: acquisition time information of the acquisition device corresponding to the target history data.
For example, the channel count information in the target historical data corresponding to a certain risk point location is 50 people (the number can be the average number of channel counts in a preset duration or the maximum number), and the time in the second point table pre-stored parameter of the corresponding acquisition device is 2 minutes (i.e. the data acquisition period is 2 minutes), so that the channel count data of the risk point location can be calculated to be 50/2=25 people/minute; after the channel counting data of all the risk points are obtained through calculation, sorting is carried out on the channel counting data to obtain the channel counting ranking.
The second data analysis sub-module 131 feeds back the channel count data and the channel count ranking of all risk points to the data management module 12, and the data management module 12 stores each channel count data into the second sub-database 151 according to the risk point identification information in a classified manner, and simultaneously stores the channel count ranking into the second sub-database 151.
The third data analysis sub-module 132 runs a third data processing algorithm for determining congestion duration information, and for any target historical data, the third data processing algorithm performs binarization processing on the passenger flow data information in the target historical data according to a preset threshold value, determines the maximum duration of the passenger flow data information in the target historical data continuously exceeding the preset threshold value according to the binarization processing result, obtains congestion duration data of risk points corresponding to the target historical data, and sorts the congestion duration data of all risk points to obtain congestion duration ranking.
Fig. 3 shows an alternative algorithm flow for determining congestion duration data, as shown in the figure, after target historical data in a certain sampling duration is obtained, binarizing passenger flow volume of each sampling (i.e. n=1, 2, …, N in the figure) according to a preset threshold, where n=sampling duration (e.g. 15 minutes) x sampling frequency (e.g. 10 times per minute), assuming that the preset threshold is 100 people, and when the passenger flow volume of the first sampling exceeds 100 people, it is denoted as D (1) =1; when the passenger flow volume of the second sampling does not exceed 100 persons, the passenger flow volume is marked as D (2) =0; d (1) to D (N) are determined in sequence, and then the D (N) is processed according to the algorithm flow in the figure. Wherein i represents the time length of the ith passenger flow continuously exceeding a preset threshold (for preventing sampling errors, the continuous super-threshold state allows intermittent sampling intervals once), i.e. the congestion occurs at the ith time, T (i) represents the time length of the congestion occurs at the ith time, and the maximum value T in T (i) max As congestion duration data for the risk point. It should be noted that, here, the sample duration is 15 minutes, and the sample frequency is 10 times per minute, so that the user can set the sample duration and the sample frequency by himself in practical application.
After the congestion duration data of all the risk points are obtained through calculation, the congestion duration data are ranked, the third data analysis sub-module 132 feeds back the congestion duration data and the congestion duration ranking of all the risk points to the data management module 12, and the data management module 12 stores the congestion duration data into the second sub-database 151 in a classified manner according to the risk point identification information, and simultaneously stores the congestion duration ranking into the second sub-database 151.
The fourth data analysis sub-module 133 is configured to run a fourth data processing algorithm for determining the passenger retention state information, where for any target historical data, the fourth data processing algorithm selects a preset number of data subsets from the target historical data, inputs the preset number of data subsets into a pre-trained neural network model respectively to obtain a preset number of passenger retention state results respectively, and performs weighted average calculation on the preset number of passenger retention state results to obtain a passenger retention state of a risk point corresponding to the target historical data, where the neural network model is configured to analyze the passenger retention state according to the input data.
Wherein fig. 4 shows an alternative fully connected BP neural network model in which: the input layer is 50 neurons, the first hidden layer designs 100 hidden neurons, the second hidden layer designs 50 hidden neurons, the classification layer designs 10 neurons, and three classification analysis is carried out, wherein the three classification mainly comprises: no passenger retention, little passenger retention and serious passenger retention. During training, three sample sets of no passenger retention, little passenger retention and serious passenger retention can be respectively obtained for training the model, so that the model can analyze the passenger retention state according to the input data. Typically, the output result is a ten-bit boolean number, e.g., output result 0000000001 represents category one: the passenger is not detained, and output 0000000010 indicates category two: the passengers are in a small amount, and the output result 0000000100 indicates the category three: the passengers are seriously detained. In the later stage, the congestion index average value is calculated, and the Boolean number result can be further converted into decimal 0, 1 and 2, namely 0 indicates no retention of passengers, 1 indicates a small retention of passengers, and 2 indicates a serious retention of passengers, but the dimension of input data is consistent with the number of neurons of an input layer, and the number of bits of the output Boolean number result is consistent with the number of neurons of a classification layer.
For example, if the number of preset dislocation weighted groups (i.e. the preset number) is 5, the fourth data processing algorithm may select 90 data before and after the target time point from the target historical data, and make the dislocation into 5 groups of data (50 sampling data in each group), that is, 5 data subsets, and input the 5 data subsets into the neural network model respectively to obtain 5 passenger retention state results respectively, as shown in table 1, which are 0,1,2,2,1 respectively, and perform weighted average calculation to obtain a final result 1.2, and determine that the passenger retention degree index of the target time point of the risk point is 1.2.
TABLE 1
After obtaining the passenger retention state information of all risk points, the fourth data analysis sub-module 133 feeds back the passenger retention state information of all risk points to the data management module 12, and the data management module 12 stores the passenger retention state information into the second sub-database 151 according to the risk point identification information.
And the display module 14 is used for displaying the data analysis result.
The display module 14 is typically a UI display interface, and may display passenger density ranks, channel count ranks, congestion duration ranks, passenger retention status information, and the like obtained by the above analysis, and may also display historical data, road network risk point statistics, weather hydrologic information, VMS video, and the like.
As can be seen from the above, in the database module 15, the first sub-database 150 stores a structured data set, where each structured data is stored according to the corresponding risk point identification information, and the second sub-database 151 stores a data analysis result, where the data analysis result at least includes: passenger density data, channel count data, congestion duration data, passenger retention status, and passenger density ranking, channel count ranking and congestion duration ranking which are classified according to risk point location identification information corresponding to the target historical data.
Accordingly, presentation module 14 may also obtain, by data management module 12, target structured data, target passenger density data, target lane count data, target congestion duration data, target passenger stay state corresponding to the target risk point corresponding to the selection instruction in response to the selection instruction of the target object, and present the target structured data, target passenger density data, target lane count data, target congestion duration data, and target passenger stay state.
For example, after a user selects a certain risk point location on the UI, the data management module searches the first sub-database for the target structured data corresponding to the risk point location identification information, searches the second sub-database for the target passenger density data, the target channel count data, the target congestion duration data, and the target passenger retention state corresponding to the risk point location identification information, and displays the target passenger density data, the target channel count data, the target congestion duration data, and the target passenger retention state to the user on the UI to provide decision assistance.
In the data analysis system for traffic network passenger flow analysis provided by the embodiment of the application, the target server is used for obtaining structured data corresponding to each risk point in the target road network one by one to obtain a structured data set, and the structured data at least comprises passenger flow data information of the corresponding risk point; the data access module is used for accessing the structured data set and sending the structured data set to the data management module; the data management module is used for selecting target historical data from each structured data, transmitting the target historical data to the data analysis module, receiving a data analysis result fed back by the data analysis module, and transmitting the data analysis result to the display module; the data analysis module is used for analyzing each target historical data to obtain a data analysis result; and the display module is used for displaying the data analysis result. The method comprises the steps of summarizing structured data of risk points of each line, carrying out data statistics, feature extraction and qualitative analysis on target historical data in a preset time period, obtaining passenger density information, channel count information, congestion duration information, passenger retention state information and the like of each risk point, displaying the passenger density information, the channel count information, the congestion duration information, the passenger retention state information and the like, and providing decision assistance for a command and dispatch system, so that the technical problem that collected passenger flow data is lack of effective analysis in the related technology and auxiliary decision information cannot be provided for a dispatcher is solved.
Example 2
On the basis of the data analysis system provided in embodiment 1, the embodiments of the present application provide an embodiment of a data analysis method, it should be noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different from that herein.
Fig. 5 is a flow chart of an alternative data analysis method according to an embodiment of the present application, as shown in fig. 5, the method at least includes steps S502-S512, where:
step S502, a structured data set is obtained through a target server, each structured data in the structured data set corresponds to each risk point in a target road network one by one, and the structured data at least comprises: passenger flow data information of risk points corresponding to the structured data;
step S504, accessing the structured data set transmitted by the target server through the data access module, and sending the structured data set to the data management module;
step S506, selecting target historical data from each structured data through the data management module, and transmitting the target historical data to the data analysis module;
Step S508, analyzing each target historical data through the data analysis module to obtain a data analysis result, and feeding back the data analysis result to the data management module, wherein the data analysis result at least comprises: passenger density information, channel count information, congestion duration information and passenger retention state information of each risk point;
step S510, the data analysis result is sent to the display module through the data management module;
step S512, the data analysis result is displayed through the display module.
It should be noted that, each step in the data analysis method in the embodiment of the present application corresponds to a function executed by each module in the data analysis system in embodiment 1, and since detailed description has been made in embodiment 1, details not shown in part in this embodiment may refer to embodiment 1, and will not be repeated here.
Example 3
According to an embodiment of the present application, there is also provided a nonvolatile storage medium including a stored program, wherein the device in which the nonvolatile storage medium is controlled to execute the data analysis method in embodiment 2 when the program runs.
Optionally, the program controls the device in which the nonvolatile storage medium is located to execute the following steps when running: the method comprises the steps that a structured data set is obtained through a target server, each structured data in the structured data set corresponds to each risk point in a target road network one by one, and the structured data at least comprises: passenger flow data information of risk points corresponding to the structured data; accessing a structured data set transmitted by a target server through a data access module, and sending the structured data set to a data management module; selecting target historical data from each structured data through the data management module, and transmitting the target historical data to the data analysis module; analyzing each target historical data through a data analysis module to obtain a data analysis result, and feeding the data analysis result back to a data management module, wherein the data analysis result at least comprises: passenger density information, channel count information, congestion duration information and passenger retention state information of each risk point; the data analysis result is sent to the display module through the data management module; and displaying the data analysis result through a display module.
The foregoing embodiment numbers of the present application are merely for describing, and do not represent advantages or disadvantages of the embodiments.
In the foregoing embodiments of the present application, the descriptions of the embodiments are emphasized, and for a portion of this disclosure that is not described in detail in this embodiment, reference is made to the related descriptions of other embodiments.
In the several embodiments provided in the present application, it should be understood that the disclosed technology content may be implemented in other manners. The above-described embodiments of the apparatus are merely exemplary, and the division of units may be a logic function division, and there may be another division manner in actual implementation, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interfaces, units or modules, or may be in electrical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution, in the form of a software product stored in a storage medium, including several instructions to cause a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely a preferred embodiment of the present application and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present application and are intended to be comprehended within the scope of the present application.
Claims (10)
1. A data analysis system, comprising:
the target server is used for acquiring a structured data set, each structured data in the structured data set corresponds to each risk point in the target road network one by one, and the structured data at least comprises: passenger flow data information of the risk points corresponding to the structured data;
the data access module is used for accessing the structured data set transmitted by the target server and sending the structured data set to the data management module;
the data management module is used for selecting target historical data from each piece of structured data and transmitting the target historical data to the data analysis module; receiving a data analysis result fed back by the data analysis module, and sending the data analysis result to a display module;
the data analysis module is configured to analyze each of the target historical data to obtain the data analysis result, where the data analysis result at least includes: passenger density information, channel count information, congestion duration information and passenger retention state information of each risk point;
And the display module is used for displaying the data analysis result.
2. The system of claim 1, wherein the target server comprises:
the road network center analysis server is used for acquiring a first customer stream video acquired by acquisition equipment at a preset first type of risk point in the target road network, and analyzing the first customer stream video to obtain the structured data corresponding to the first type of risk point;
and each line analysis server is used for acquiring a second passenger flow video acquired by acquisition equipment at a second type risk point in a line corresponding to the line analysis server in the target road network, and analyzing the second passenger flow video to obtain the structured data corresponding to the second type risk point.
3. The system of claim 1, wherein the structured data comprises:
passenger flow data type information and the passenger flow data information, wherein the passenger flow data information at least comprises: passenger number information, lane count information;
the source information and the acquisition time period of the structured data, wherein the source information comprises: risk point location identification information of the risk point location corresponding to the structured data, the risk point location identification information including: and acquiring equipment identification information of the equipment at the risk point.
4. The system of claim 3, wherein the system further comprises a controller configured to control the controller,
for any one of the structured data sets, the data management module is configured to select the target historical data with a preset duration from the structured data according to the collection time period of the structured data, and transmit the target historical data to the data analysis module.
5. The system of claim 4, wherein the system further comprises a controller configured to control the controller,
the data analysis module comprises a plurality of data analysis submodules, which are used for analyzing the target historical data to obtain the data analysis result, wherein the plurality of data analysis submodules at least comprise: a first data analysis sub-module for determining the passenger density information, a second data analysis sub-module for determining the channel count information, a third data analysis sub-module for determining the congestion duration information, and a fourth data analysis sub-module for determining the passenger stay status information.
6. The system of claim 5, wherein the system further comprises a controller configured to control the controller,
for any one of the target historical data, the first data analysis sub-module is configured to determine passenger density data of the risk points corresponding to the target historical data according to the passenger number information in the target historical data and a first point table pre-stored parameter of the collecting device corresponding to the target historical data, and order the passenger density data of all the risk points to obtain a passenger density ranking, where the first point table pre-stored parameter includes: area information of the risk point location corresponding to the target history data;
For any one of the target historical data, the second data analysis submodule is configured to determine channel count data of the risk points corresponding to the target historical data according to the channel count information in the target historical data and a second point table pre-stored parameter of the acquisition device corresponding to the target historical data, and order the channel count data of all the risk points to obtain a channel count ranking, where the second point table pre-stored parameter includes: acquisition time information of the acquisition equipment corresponding to the target historical data;
for any one of the target historical data, the third data analysis submodule is used for carrying out binarization processing on the passenger flow data information in the target historical data according to a preset threshold value, determining the maximum duration that the passenger flow data information in the target historical data continuously exceeds the preset threshold value according to the binarization processing result, obtaining congestion duration data of the risk points corresponding to the target historical data, and sequencing the congestion duration data of all the risk points to obtain a congestion duration ranking;
for any one of the target historical data, the fourth data analysis submodule is used for selecting a preset number of data subsets from the target historical data, inputting the preset number of data subsets into a pre-trained neural network model respectively to obtain a preset number of passenger detention state results respectively, and carrying out weighted average calculation on the preset number of passenger detention state results to obtain the passenger detention state of the risk point position corresponding to the target historical data, wherein the neural network model is used for analyzing the passenger detention state according to the input data.
7. The system of claim 6, wherein the system further comprises: a database module, the database module comprising:
a first sub-database for storing the structured data set;
the second sub-database is used for storing the data analysis result, wherein the data analysis result at least comprises the following components: the passenger density data, the channel count data, the congestion duration data, the passenger retention state, the passenger density ranking, the channel count ranking and the congestion duration ranking which are classified according to the risk point location identification information corresponding to the target historical data.
8. The system of claim 1, wherein the system further comprises a controller configured to control the controller,
the display module is further configured to respond to a selection instruction of a target object, obtain, through the data management module, target structured data, target passenger density data, target channel count data, target congestion duration data, and target passenger retention state corresponding to a target risk point location corresponding to the selection instruction, and display the target structured data, the target passenger density data, the target channel count data, the target congestion duration data, and the target passenger retention state.
9. A data analysis method applied to the data analysis system according to any one of claims 1 to 8, comprising:
the method comprises the steps of obtaining a structured data set through a target server, wherein each structured data in the structured data set corresponds to each risk point in a target road network one by one, and the structured data at least comprises: passenger flow data information of the risk points corresponding to the structured data;
the structured data set transmitted by the target server is accessed through a data access module, and the structured data set is sent to a data management module;
selecting target historical data from each structured data through the data management module, and transmitting the target historical data to a data analysis module;
analyzing each target historical data through the data analysis module to obtain the data analysis result, and feeding back the data analysis result to the data management module, wherein the data analysis result at least comprises: passenger density information, channel count information, congestion duration information and passenger retention state information of each risk point;
The data analysis result is sent to a display module through the data management module;
and displaying the data analysis result through the display module.
10. A non-volatile storage medium, characterized in that the non-volatile storage medium comprises a stored program, wherein the program, when run, controls a device in which the non-volatile storage medium is located to perform the data analysis method of claim 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111333788.4A CN116128274B (en) | 2021-11-11 | 2021-11-11 | Data analysis system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111333788.4A CN116128274B (en) | 2021-11-11 | 2021-11-11 | Data analysis system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116128274A true CN116128274A (en) | 2023-05-16 |
| CN116128274B CN116128274B (en) | 2023-09-26 |
Family
ID=86299541
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111333788.4A Active CN116128274B (en) | 2021-11-11 | 2021-11-11 | Data analysis system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116128274B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140115710A1 (en) * | 2012-10-19 | 2014-04-24 | Pearson Education, Inc. | Privacy Server for Protecting Personally Identifiable Information |
| CN105279572A (en) * | 2015-09-16 | 2016-01-27 | 北京城建设计发展集团股份有限公司 | City track traffic passenger flow density index calculating and releasing system |
| CN109033718A (en) * | 2018-09-07 | 2018-12-18 | 哈尔滨工业大学 | A kind of dynamic emergency evacuation method of city rail traffic route failure |
| CN109858670A (en) * | 2018-12-24 | 2019-06-07 | 哈尔滨工业大学 | A kind of rail traffic station large passenger flow real time early warning method |
| US20200097815A1 (en) * | 2018-09-21 | 2020-03-26 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for predicting passenger flow |
| KR102145549B1 (en) * | 2019-12-02 | 2020-08-18 | 주식회사 페르미 | Communication system and method for providing emergency rescue service |
| CN112365092A (en) * | 2020-12-01 | 2021-02-12 | 北京交通大学 | Urban rail transit road network large passenger flow risk self-adaptive pre-warning system |
| CN112949080A (en) * | 2021-03-22 | 2021-06-11 | 中铁信(北京)网络技术研究院有限公司 | Urban rail transit station simulation system and method based on dynamic driving |
-
2021
- 2021-11-11 CN CN202111333788.4A patent/CN116128274B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140115710A1 (en) * | 2012-10-19 | 2014-04-24 | Pearson Education, Inc. | Privacy Server for Protecting Personally Identifiable Information |
| CN105279572A (en) * | 2015-09-16 | 2016-01-27 | 北京城建设计发展集团股份有限公司 | City track traffic passenger flow density index calculating and releasing system |
| CN109033718A (en) * | 2018-09-07 | 2018-12-18 | 哈尔滨工业大学 | A kind of dynamic emergency evacuation method of city rail traffic route failure |
| US20200097815A1 (en) * | 2018-09-21 | 2020-03-26 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for predicting passenger flow |
| CN109858670A (en) * | 2018-12-24 | 2019-06-07 | 哈尔滨工业大学 | A kind of rail traffic station large passenger flow real time early warning method |
| KR102145549B1 (en) * | 2019-12-02 | 2020-08-18 | 주식회사 페르미 | Communication system and method for providing emergency rescue service |
| CN112365092A (en) * | 2020-12-01 | 2021-02-12 | 北京交通大学 | Urban rail transit road network large passenger flow risk self-adaptive pre-warning system |
| CN112949080A (en) * | 2021-03-22 | 2021-06-11 | 中铁信(北京)网络技术研究院有限公司 | Urban rail transit station simulation system and method based on dynamic driving |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116128274B (en) | 2023-09-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108242149B (en) | Big data analysis method based on traffic data | |
| CN114390079B (en) | Smart city public place management method and Internet of things system | |
| CN104091070B (en) | Rail transit fault diagnosis method and system based on time series analysis | |
| CN113160602B (en) | Intelligent bus dispatching simulation system | |
| CN107992786A (en) | A kind of people streams in public places amount statistical method and system based on face | |
| CN115272037B (en) | Smart city based on Internet of things regional public security management early warning method and system | |
| CN116308960B (en) | Intelligent park property prevention and control management system based on data analysis and implementation method thereof | |
| CN116504076A (en) | Expressway traffic flow prediction method based on ETC portal data | |
| CN108289203A (en) | A kind of video monitoring system for rail traffic | |
| CN111488803A (en) | Airport target behavior understanding system integrating target detection and target tracking | |
| CN107992958A (en) | Population super-limit prewarning method based on ARMA | |
| CN114048882B (en) | Railway fault handling operation and maintenance decision suggestion method | |
| Liu et al. | Forecast and early warning of regional bus passenger flow based on machine learning | |
| CN110781873A (en) | Driver fatigue grade identification method based on bimodal feature fusion | |
| CN113160604A (en) | Bus management method and system based on artificial intelligence | |
| CN114819418B (en) | Station passenger flow control method, device, equipment and readable storage medium | |
| CN116128274B (en) | Data analysis system and method | |
| CN111144706A (en) | Method for grading and classifying network taxi appointment drivers | |
| CN109409563B (en) | Method, system and storage medium for analyzing real-time number of people in public transport operation vehicle | |
| CN113435867B (en) | Smart city operation method, system and readable storage medium | |
| CN113487073B (en) | Edge technology-based process control system energy consumption management method and system | |
| CN113298350A (en) | Artificial intelligence-based bus comprehensive supervision and service system | |
| CN112365092A (en) | Urban rail transit road network large passenger flow risk self-adaptive pre-warning system | |
| CN112488568A (en) | Method for evaluating large passenger flow operation risk of subway station and application thereof | |
| CN117334042B (en) | Intelligent traffic management system and method based on artificial intelligence |
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 |