CN111552772A - Real-time traffic road condition text data and traffic volume combined visual analysis method - Google Patents
Real-time traffic road condition text data and traffic volume combined visual analysis method Download PDFInfo
- Publication number
- CN111552772A CN111552772A CN202010322466.9A CN202010322466A CN111552772A CN 111552772 A CN111552772 A CN 111552772A CN 202010322466 A CN202010322466 A CN 202010322466A CN 111552772 A CN111552772 A CN 111552772A
- Authority
- CN
- China
- Prior art keywords
- traffic
- road
- time
- text
- view
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000000007 visual effect Effects 0.000 title claims abstract description 22
- 238000004458 analytical method Methods 0.000 title claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 26
- 230000011218 segmentation Effects 0.000 claims abstract description 13
- 238000010586 diagram Methods 0.000 claims description 22
- 238000013527 convolutional neural network Methods 0.000 claims description 20
- 230000008859 change Effects 0.000 claims description 18
- 241000699666 Mus <mouse, genus> Species 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 7
- 241000239290 Araneae Species 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- NQBKFULMFQMZBE-UHFFFAOYSA-N n-bz-3-benzanthronylpyrazolanthron Chemical compound C12=CC=CC(C(=O)C=3C4=CC=CC=3)=C2C4=NN1C1=CC=C2C3=C1C1=CC=CC=C1C(=O)C3=CC=C2 NQBKFULMFQMZBE-UHFFFAOYSA-N 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 235000014347 soups Nutrition 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 235000010627 Phaseolus vulgaris Nutrition 0.000 claims description 3
- 244000046052 Phaseolus vulgaris Species 0.000 claims description 3
- NNBFNNNWANBMTI-UHFFFAOYSA-M brilliant green Chemical compound OS([O-])(=O)=O.C1=CC(N(CC)CC)=CC=C1C(C=1C=CC=CC=1)=C1C=CC(=[N+](CC)CC)C=C1 NNBFNNNWANBMTI-UHFFFAOYSA-M 0.000 claims description 3
- 230000009193 crawling Effects 0.000 claims description 3
- 230000002045 lasting effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000011160 research Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000012800 visualization Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Instructional Devices (AREA)
Abstract
The invention belongs to the technical field of visualization and visual analysis, and particularly relates to a visual analysis method for combining real-time traffic road condition text data with traffic volume, which comprises the following steps: firstly, a network crawler program is compiled by Python to obtain traffic-related unstructured text information in a social media website, and unstructured text information data are converted into structured information data by Chinese word segmentation, part of speech tagging and entity naming identification methods; and then, the structured information data is visually displayed in a map base view, a traffic event view, a flow thermodynamic view, a theme river map view and a road flow data view. The invention can quickly acquire the traffic information published in the current social media, and further excavate the information behind the event by a visual technical means, thereby providing more visual experience for users, and simultaneously providing stronger data analysis capability for relevant management departments in cities so as to improve the decision efficiency of traffic management of the users.
Description
Technical Field
The invention belongs to the technical field of text data mining, data analysis, visualization and visual analysis, and particularly relates to a visual analysis method for combining real-time traffic road condition text data with traffic volume.
Background
Along with the development of the urbanization process, urban traffic is more convenient, and meanwhile, a series of traffic traveling problems such as traffic jam, traffic accidents and the like are increasingly highlighted. Many cities are expanding roads and building new roads, but the development of new roads is limited for urban traffic resources, and the key to solve the problem of traffic congestion is not how to build more roads, but how to reasonably utilize limited traffic resources and improve the efficiency of urban road networks. With the development of new technologies such as a big data technology, artificial intelligence, visualization and visual analysis at present, how to analyze road conditions by using the latest technologies has a very high strategic significance for promoting the development process of urbanization by deeply mining hundreds of millions of urban traffic data, optimizing the construction of traffic infrastructure, reasonably planning the traffic trip of people and the like, and shows very important informatization value. The social media can generate massive information every day, and the information is not short of many media information about urban traffic road conditions, but at present, the information is not sufficient and effective to deeply mine the data value behind the information. By combining real-time traffic road condition information, visual analysis technology and interactive operation mode and graphical analysis results thereof can provide convenience for users to analyze the value law behind data, and the mode also gets great attention in the field of intelligent traffic. The traffic events hidden in the traffic data can be mined by utilizing a visual analysis technology, the occurrence process, reasons and influences of the traffic events are understood, and management decisions can be made by management personnel conveniently at proper time. In addition, in a plurality of traffic events, non-traffic direct factors such as road maintenance notice, traffic accident reports and the like also exist, and the non-traffic direct factors truly reflect the actual situation of road traffic and can obviously influence the traffic flow. The traffic information is utilized, and the orderly operation of urban traffic order can be effectively assisted, so that the traffic pressure of large cities is relieved.
Disclosure of Invention
In order to solve the technical problems in the prior art, the invention provides a visual analysis method for combining real-time traffic road condition text data with traffic volume, which has the following specific technical scheme:
a real-time traffic road condition text data combined traffic volume visual analysis method comprises the following steps:
step 1: utilizing Python to write a web crawler program to obtain traffic-related unstructured text information in a social media website, and converting unstructured text information data into structured information data through Chinese word segmentation, part of speech tagging and entity naming identification methods;
step 2: and the structured information data is visually displayed in a map base view, a traffic event view, a flow thermodynamic view, a theme river map view and a road flow data view.
Further, the information-based structural data comprises traffic text data and road historical flow data.
Further, the specific content of step 1 is as follows:
step 1.1: creating a script project by using a script crawler frame based on Pyron, defining a self-definition class inheriting from a Spider class provided by a Spider, setting a name and a request, configuring a captured microblog link, capturing logic and a function for defining and processing a crawling result, acquiring real-time traffic road condition microblog information published by all bloggers under a traffic road condition topic from the microblog link, capturing related webpage content from a traffic intersection information block of a traffic website in real time, finishing initialization of a Beautiful Soup object through a Beautiful Soup library of Pyron, analyzing and acquiring content in an HTML format, extracting a title, publishing time and text of a traffic text through a traversal document tree, and primarily removing non-traffic related value information according to a keyword matching method;
step 1.2: secondly classifying the categories of the texts by using a character-level convolutional neural network Char-CNN model, training the character-level convolutional neural network Char-CNN model before classifying the texts by using the character-level convolutional neural network Char-CNN model for the first time, screening out text contents with classification results as traffic from output results, classifying the text contents into five event types of road construction, accident congestion, public traffic regulation, large activities and other events according to characteristic vocabularies appearing in the texts, and eliminating text information which is related to the traffic and has no influence on the road by using a keyword matching method;
step 1.3: the method comprises the steps of using a Chinese word segmentation frame based on a perceptron in a Python Chinese word segmentation component HanLP to segment words, establishing a self-defined dictionary on the basis of an internal word bank, setting stop words to remove words without any contribution to text information, screening words and corresponding part-of-speech labels of word segmentation results, and finally storing original text of the text, extracted time words, extracted place words and event types into a file.
Further, the custom dictionary comprises traffic terms, road names of target areas and time words.
Further, the traffic event view is obtained by: displaying the processed single traffic text record in the form of time, place and start information in a character mode; drawing different event type icons for the five types of event types, setting a carousel effect, slowly switching contents from bottom to top, hiding a first line of a data table when data are updated, moving other traffic message records upwards by one line, adding new contents to the last line, and flashing for 2.5 seconds; carrying out color coding on the background of the content of each traffic message according to the occurrence time of the traffic text, and reflecting the change of the occurrence time of the event along with the time through the gradual change of the color; simultaneously, event type icons appear at corresponding time longitude and latitude positions of the map basic view, and when the event type icons appear, the event type icons are subjected to primary zooming-in and zooming-out transformation, namely, when the event type icons appear, the icons are firstly zoomed in to be 1.5 times of the size of the original set icons, and are zoomed in to be the size of the original set icons after lasting for 2 seconds; when the mouse is hovered in the text area, the carousel is paused through the message, the text full-text content in the focus cell area of the mouse is displayed, meanwhile, the corresponding road is highlighted and displayed in the map basic view, when the mouse leaves the text area, the highlight road information on the map is cleared, and the carousel is continued.
Further, the map base view mode is as follows: the map basic view uses an open source JavaScript map library leaf, and is used for displaying map details of a target research area; setting the map layer style of a map in a self-defined manner, wherein the map layer style is used for visualizing the occurrence of traffic events, traffic flow and traffic volume information; and a road information button, a thermodynamic diagram starting button and a traffic volume display button are arranged at the upper left corner of the map view, and a sliding bar is arranged at the upper right corner of the map view and used for selecting a display time interval.
Furthermore, the map basic view is independently displayed and is matched with the visualization layer for superposing other views for supporting linkage analysis.
Further, the flow thermodynamic diagram is in the following manner: setting a time selector at the upper right of a map basic view, selecting corresponding time, selecting a thermodynamic diagram of average traffic flow on a road within 5 minutes at the time moment by taking 5 minutes as a minimum scale unit, carrying out color coding on the traffic flow through a color range from weak green to orange red by the thermodynamic diagram, wherein a hexadecimal color code of the weak green is #98FB98, an RGB color value is 152, 251 and 152, and the coded current traffic flow on the road is at a lower level compared with the highest value of the global road traffic flow; the orange-red hexadecimal color code is # FF4500, the RGB color value is 255, 69, 0, and the coded current road traffic flow is in a higher value state compared with the current global road traffic flow maximum value; the intermediate state between the light green and the light red indicates the degree of the road traffic flow according to the change of the color, and the value represented by the intermediate state is higher as the intermediate state is closer to the light red color, and the value represented by the intermediate state is lower as the intermediate state is closer to the light green color.
Further, the mode of the theme river chart view is as follows: each point of the theme river graph view is the degree of the traffic incident at the current moment on the traffic, the x axis represents a time axis, the y axis represents the degree, the degree is represented by the percentage of the difference value between the speed of the road vehicle at the current moment and the historical average value on the road in the next week, along with the generation of the traffic incident, corresponding data points are added in the theme river graph in the direction corresponding to the x axis in real time, the time axis is updated according to the lapse of time, data points in the corresponding moment are continuously added according to the change of the speed of the road, the refreshing is carried out every five minutes, the increase of the data points and the theme river graph are completed, meanwhile, the river which is not subjected to the change of the speed of the road more than 20 percent within more than half an hour is judged; each river is coded in a different color.
Further, the road flow data view mode is as follows: the road flow data view is mainly displayed on the map basic view, color coding is carried out on the speed of the road, meanwhile, the selection of the road is supported, an information card is displayed after the road is selected, the head of the information card displays the name of the road, the lower part of the information card comprises a parallel coordinate system diagram and an annular thermodynamic diagram, and the first-dimension coordinate of the parallel coordinate system diagram displays the degree of the selected road, namely the quantity of the road connected with the road section is displayed; the second-dimension coordinate shows the length of the selected road, the distance unit is kilometers, the third-dimension coordinate shows the road classification of the road, and the express way, the main road, the secondary road and the branch way are classified according to the urban road grade, and correspond to four values of 1, 2, 3 and 4 in sequence; a small grid of each ring of the annular thermodynamic diagram represents a half hour, a whole circle is divided into 24 scale units by 360 degrees, each unit corresponds to an hour, the inner layer and the outer layer respectively represent color mapping of traffic speeds of the first half hour and the second half hour in the corresponding hour, the speed values are represented from high to low in the color mapping and are represented as emerald green, hexadecimal color codes are # aaff7f to sweetened bean paste red, and the hexadecimal color codes are represented as gradual change representations of # dd4f 58.
Has the advantages that:
the visual analysis method combining the text data of the real-time traffic road condition with the traffic volume supports the joint analysis of various data types, can quickly acquire the traffic information published in the current social media, can further mine the information behind the events through visual technical means, provides more visual experience for users, and simultaneously provides stronger data analysis capability for relevant management departments in cities so as to enhance the decision efficiency of traffic management of the users.
Drawings
FIG. 1 is a view of a visual analysis system of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings and embodiments.
As shown in fig. 1, a visual analysis method for real-time traffic road condition text data combined with traffic volume includes the following steps:
step 1: utilizing Python to write a web crawler program to obtain traffic-related unstructured text information in a social media website, and converting unstructured text information data into structured information data through Chinese word segmentation, part of speech tagging and entity naming identification methods;
step 2: the structured information data are visually displayed in a map basic view, a traffic event view, a flow thermodynamic view, a theme river view and a road flow data view; wherein the information-based structure data comprises traffic text data and road historical flow data.
The specific content of step 1 is as follows:
step 1.1: creating a script project by using a script crawler frame based on Pyron, defining a self-definition class inheriting from a Spider class provided by a Spider, setting a name and a request, configuring a captured microblog link, capturing logic and a function for defining and processing a crawling result, acquiring real-time traffic road condition microblog information published by all bloggers under a traffic road condition topic from the microblog link, capturing related webpage content from a traffic intersection information block of a traffic website in real time, completing initialization of a Beautiful Soup object through a Beautiful Soup library of Pyron, analyzing the acquired content in an HTML format, extracting a title, publishing time and text content of a traffic text through traversing a document, and primarily removing non-traffic related value information according to a keyword matching method;
step 1.2: the method comprises the following steps of performing secondary classification on the category of a text by using a character-level convolutional neural network Char-CNN model, training the character-level convolutional neural network Char-CNN model before performing classification on the text by using the character-level convolutional neural network Char-CNN model for the first time, wherein the total number of data sets for training and testing is 6000 news data, 3000 traffic texts and 3000 non-traffic news are included, and the data sets are classified by 8: 2 into two subsets of a training set and a test set, namely 2400 pieces of traffic data and 2400 pieces of non-traffic data for training, 600 pieces of traffic data and 600 pieces of non-traffic data for testing, 128 neurons of a full connecting layer of the character-level convolutional neural network model, 64 convolutional kernels, a learning rate of 1e-4, 32 training batches, 200 total iteration rounds, a Char-CNN model for classifying subsequent texts, screening out a classification result from output results as traffic text content, and is divided into five event types of road construction, accident congestion, public traffic adjustment, large-scale activities and other events according to the characteristic vocabularies appearing in the text, meanwhile, text information which belongs to traffic correlation and has no influence on roads is eliminated by using a keyword matching method again;
step 1.3: the method comprises the steps of using a Chinese word segmentation frame based on a perceptron in a Python Chinese word segmentation component HanLP to segment words, establishing a self-defined dictionary on the basis of an internal word bank, wherein the self-defined dictionary comprises traffic terms, road names and time words of a target area, setting stop words to remove words which do not contribute to text information, screening words and corresponding part-of-speech labels of word segmentation results, and finally extracting original text texts of the texts, the time words, place words and event types and storing the results into files.
The map base view mode is as follows: the map basic view uses an open source JavaScript map library leaf, and is used for displaying map details of a target research area; setting the map layer style of a map in a self-defined manner, wherein the map layer style is used for visualizing the occurrence of traffic events, traffic flow and traffic volume information; setting a road information button at the upper left corner of the map view, enabling a thermodynamic diagram button and a traffic volume display button, and setting a sliding bar at the upper right corner for selecting a display time interval; and the map basic view is independently displayed and is matched with the visual layer of the other views to be superposed for supporting linkage analysis.
The traffic event view is in the following manner: displaying the processed single traffic text record in the form of time, place and start information in a character mode; drawing different event type icons for the five types of event types, setting a carousel effect, slowly switching contents from bottom to top, hiding a first line of a data table when data are updated, moving all traffic message records upwards by one line, adding new contents to the last line, and flashing for 2.5 seconds; carrying out color coding on the background of the content of each traffic message according to the occurrence time of the traffic text, and reflecting the change of the occurrence time of the event along with the time through the gradual change of the color; simultaneously, event type icons appear at corresponding time longitude and latitude positions of the map basic view, and when the event type icons appear, the event type icons are subjected to primary zooming-in and zooming-out transformation, namely, when the event type icons appear, the icons are firstly zoomed in to be 1.5 times of the size of the original set icons, and are zoomed in to be the size of the original set icons after lasting for 2 seconds; in addition, when the mouse is hovered in the text area, the carousel is paused through the message, the text full-text content of the focus cell area of the mouse is displayed, meanwhile, the corresponding road is highlighted and displayed in the map basic view, when the mouse leaves the text area, the highlighted road information on the map is cleared, and the carousel is continued.
The flow thermodynamic view mode is as follows: setting a time selector at the upper right of a map basic view, selecting corresponding time, selecting a thermodynamic diagram of average traffic flow on a road within 5 minutes at the time moment by taking 5 minutes as a minimum scale unit, carrying out color coding on the traffic flow through a color range from weak green to orange red by the thermodynamic diagram, wherein a hexadecimal color code of the weak green is #98FB98, an RGB color value is 152, 251 and 152, and the coded current traffic flow on the road is at a lower level compared with the highest value of the global road traffic flow; the orange-red hexadecimal color code is # FF4500, the RGB color value is 255, 69, 0, and the coded current road traffic flow is in a higher value state compared with the current global road traffic flow maximum value; the intermediate state between the light green and the light red indicates the degree of the road traffic flow according to the change of the color, and the value represented by the intermediate state is higher as the intermediate state is closer to the light red color, and the value represented by the intermediate state is lower as the intermediate state is closer to the light green color.
The mode of the theme river flow graph view is as follows: each point of the theme river graph view is the degree of the traffic incident at the current moment on the traffic, the x axis represents a time axis, the y axis represents the degree, the degree is represented by the percentage of the difference value between the speed of the road vehicle at the current moment and the historical average value on the road in the next week, along with the generation of the traffic incident, corresponding data points are added in the theme river graph in the direction corresponding to the x axis in real time, the time axis is updated according to the lapse of time, data points in the corresponding moment are continuously added according to the change of the speed of the road, the refreshing is carried out every five minutes, the increase of the data points and the theme river graph are completed, meanwhile, the river which is not subjected to the change of the speed of the road more than 20 percent within more than half an hour is judged; each river is coded in a different color.
The road flow data view mode is as follows: the road flow data view is mainly displayed on the map basic view, color coding is carried out on the speed of the road, meanwhile, the selection of the road is supported, an information card is displayed after the road is selected, the head of the information card displays the name of the road, the lower part of the information card comprises a parallel coordinate system diagram and an annular thermodynamic diagram, and the first-dimension coordinate of the parallel coordinate system diagram displays the degree of the selected road, namely the quantity of the road connected with the road section is displayed; the second-dimension coordinate shows the length of the selected road, the distance unit is kilometers, the third-dimension coordinate shows the road classification of the road, and the express way, the main road, the secondary road and the branch way are classified according to the urban road grade, and correspond to four values of 1, 2, 3 and 4 in sequence; a small grid of each ring of the annular thermodynamic diagram represents a half hour, a whole circle is divided into 24 scale units by 360 degrees, each unit corresponds to an hour, the inner layer and the outer layer respectively represent color mapping of traffic speeds of the first half hour and the second half hour in the corresponding hour, the speed values are represented from high to low in the color mapping and are represented as emerald green, hexadecimal color codes are # aaff7f to sweetened bean paste red, and the hexadecimal color codes are represented as gradual change representations of # dd4f 58.
Claims (10)
1. A real-time traffic road condition text data combined traffic volume visual analysis method is characterized by comprising the following steps:
step 1: utilizing Python to write a web crawler program to obtain traffic-related unstructured text information in a social media website, and converting unstructured text information data into structured information data through Chinese word segmentation, part of speech tagging and entity naming identification methods;
step 2: and the structured information data is visually displayed in a map base view, a traffic event view, a flow thermodynamic view, a theme river map view and a road flow data view.
2. The method as claimed in claim 1, wherein the structured data includes traffic text data and historical traffic data.
3. The method as claimed in claim 2, wherein the step 1 comprises the following steps:
step 1.1: creating a script project by using a script crawler frame based on Pyron, defining a self-definition class inheriting from a Spider class provided by a Spider, setting a name and a request, configuring a captured microblog link, capturing logic and a function for defining and processing a crawling result, acquiring real-time traffic road condition microblog information published by all bloggers under a traffic road condition topic from the microblog link, capturing related webpage content from a traffic intersection information block of a traffic website in real time, finishing initialization of a Beautiful Soup object through a Beautiful Soup library of Pyron, analyzing and acquiring content in an HTML format, extracting a title, publishing time and text of a traffic text through a traversal document tree, and primarily removing non-traffic related value information according to a keyword matching method;
step 1.2: secondly classifying the categories of the texts by using a character-level convolutional neural network Char-CNN model, training the character-level convolutional neural network Char-CNN model before classifying the texts by using the character-level convolutional neural network Char-CNN model for the first time, screening out text contents with classification results as traffic from output results, classifying the text contents into five event types of road construction, accident congestion, public traffic regulation, large activities and other events according to characteristic vocabularies appearing in the texts, and eliminating text information which is related to the traffic and has no influence on the road by using a keyword matching method;
step 1.3: the method comprises the steps of using a Chinese word segmentation frame based on a perceptron in a Python Chinese word segmentation component HanLP to segment words, establishing a self-defined dictionary on the basis of an internal word bank, setting stop words to remove words without any contribution to text information, screening words and corresponding part-of-speech labels of word segmentation results, and finally storing original text of the text, extracted time words, extracted place words and event types into a file.
4. The method as claimed in claim 3, wherein the customized dictionary comprises traffic terms, road names of target areas and time words.
5. The method as claimed in claim 3, wherein the traffic event view is obtained by combining text data of real-time traffic road conditions with traffic volume in a manner of: displaying the processed single traffic text record in the form of time, place and start information in a character mode; drawing different event type icons for the five types of event types, setting a carousel effect, slowly switching contents from bottom to top, hiding a first line of a data table when data are updated, moving other traffic message records upwards by one line, adding new contents to the last line, and flashing for 2.5 seconds; carrying out color coding on the background of the content of each traffic message according to the occurrence time of the traffic text, and reflecting the change of the occurrence time of the event along with the time through the gradual change of the color; simultaneously, event type icons appear at corresponding time longitude and latitude positions of the map basic view, and when the event type icons appear, the event type icons are subjected to primary zooming-in and zooming-out transformation, namely, when the event type icons appear, the icons are firstly zoomed in to be 1.5 times of the size of the original set icons, and are zoomed in to be the size of the original set icons after lasting for 2 seconds; when the mouse is hovered in the text area, the carousel is paused through the message, the text full-text content in the focus cell area of the mouse is displayed, meanwhile, the corresponding road is highlighted and displayed in the map basic view, when the mouse leaves the text area, the highlight road information on the map is cleared, and the carousel is continued.
6. The method as claimed in claim 1, wherein the map base view is obtained by combining text data of real-time traffic road conditions with traffic volume: the map basic view uses an open source JavaScript map library leaf, and is used for displaying map details of a target research area; setting the map layer style of a map in a self-defined manner, wherein the map layer style is used for visualizing the occurrence of traffic events, traffic flow and traffic volume information; and a road information button, a thermodynamic diagram starting button and a traffic volume display button are arranged at the upper left corner of the map view, and a sliding bar is arranged at the upper right corner of the map view and used for selecting a display time interval.
7. The method as claimed in claim 1 or 6, wherein the map base view is displayed separately and the visual layer of the other views is superimposed to support linkage analysis.
8. The method as claimed in claim 1, wherein the traffic thermal view is obtained by combining text data of real-time traffic road conditions with traffic volume, and the method comprises: setting a time selector at the upper right of a map basic view, selecting corresponding time, selecting a thermodynamic diagram of average traffic flow on a road within 5 minutes at the time moment by taking 5 minutes as a minimum scale unit, carrying out color coding on the traffic flow through a color range from weak green to orange red by the thermodynamic diagram, wherein a hexadecimal color code of the weak green is #98FB98, an RGB color value is 152, 251 and 152, and the coded current traffic flow on the road is at a lower level compared with the highest value of the global road traffic flow; the orange-red hexadecimal color code is # FF4500, the RGB color value is 255, 69, 0, and the coded current road traffic flow is in a higher value state compared with the current global road traffic flow maximum value; the intermediate state between the light green and the light red indicates the degree of the road traffic flow according to the change of the color, and the value represented by the intermediate state is higher as the intermediate state is closer to the light red color, and the value represented by the intermediate state is lower as the intermediate state is closer to the light green color.
9. The visual analysis method of real-time traffic road condition text data combined with traffic volume according to claim 1, wherein the mode of the view of the theme river map is as follows: each point of the theme river graph view is the degree of the traffic incident at the current moment on the traffic, the x axis represents a time axis, the y axis represents the degree, the degree is represented by the percentage of the difference value between the speed of the road vehicle at the current moment and the historical average value on the road in the next week, along with the generation of the traffic incident, corresponding data points are added in the theme river graph in the direction corresponding to the x axis in real time, the time axis is updated according to the lapse of time, data points in the corresponding moment are continuously added according to the change of the speed of the road, the refreshing is carried out every five minutes, the increase of the data points and the theme river graph are completed, meanwhile, the river which is not subjected to the change of the speed of the road more than 20 percent within more than half an hour is judged; each river is coded in a different color.
10. The method as claimed in claim 1, wherein the road traffic data view is in a form of: the road flow data view is mainly displayed on the map basic view, color coding is carried out on the speed of the road, meanwhile, the selection of the road is supported, an information card is displayed after the road is selected, the head of the information card displays the name of the road, the lower part of the information card comprises a parallel coordinate system diagram and an annular thermodynamic diagram, and the first-dimension coordinate of the parallel coordinate system diagram displays the degree of the selected road, namely the quantity of the road connected with the road section is displayed; the second-dimension coordinate shows the length of the selected road, the distance unit is kilometers, the third-dimension coordinate shows the road classification of the road, and the express way, the main road, the secondary road and the branch way are classified according to the urban road grade, and correspond to four values of 1, 2, 3 and 4 in sequence; a small grid of each ring of the annular thermodynamic diagram represents a half hour, a whole circle is divided into 24 scale units by 360 degrees, each unit corresponds to an hour, the inner layer and the outer layer respectively represent color mapping of traffic speeds of the first half hour and the second half hour in the corresponding hour, the speed values are represented from high to low in the color mapping and are represented as emerald green, hexadecimal color codes are # aaff7f to sweetened bean paste red, and the hexadecimal color codes are represented as gradual change representations of # dd4f 58.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010322466.9A CN111552772A (en) | 2020-04-22 | 2020-04-22 | Real-time traffic road condition text data and traffic volume combined visual analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010322466.9A CN111552772A (en) | 2020-04-22 | 2020-04-22 | Real-time traffic road condition text data and traffic volume combined visual analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111552772A true CN111552772A (en) | 2020-08-18 |
Family
ID=72005888
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010322466.9A Pending CN111552772A (en) | 2020-04-22 | 2020-04-22 | Real-time traffic road condition text data and traffic volume combined visual analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111552772A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966941A (en) * | 2021-03-09 | 2021-06-15 | 宁波工程学院 | Accident black spot identification method and system based on traffic accident big data |
| CN113112790A (en) * | 2021-03-09 | 2021-07-13 | 华东师范大学 | Urban road operation situation monitoring method combined with knowledge graph |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236163A (en) * | 2013-04-28 | 2013-08-07 | 北京航空航天大学 | Traffic jam avoiding prompting system based on collective intelligence network |
| CN105512166A (en) * | 2015-10-30 | 2016-04-20 | 青岛智能产业技术研究院 | Traffic parallel method with mapping between microblog public sentiments and city road conditions |
| CN110555568A (en) * | 2019-09-12 | 2019-12-10 | 重庆交通大学 | Road traffic running state real-time perception method based on social network information |
-
2020
- 2020-04-22 CN CN202010322466.9A patent/CN111552772A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236163A (en) * | 2013-04-28 | 2013-08-07 | 北京航空航天大学 | Traffic jam avoiding prompting system based on collective intelligence network |
| CN105512166A (en) * | 2015-10-30 | 2016-04-20 | 青岛智能产业技术研究院 | Traffic parallel method with mapping between microblog public sentiments and city road conditions |
| CN110555568A (en) * | 2019-09-12 | 2019-12-10 | 重庆交通大学 | Road traffic running state real-time perception method based on social network information |
Non-Patent Citations (3)
| Title |
|---|
| 吴向平等: "面向出租车出行规律的预测式可视分析方法", 《计算机辅助设计与图形学学报》 * |
| 周志光等: "多维时空数据协同可视分析方法", 《计算机辅助设计与图形学学报》 * |
| 王锴: "智能交通管理平台在视频专网中的应用", 《中国公共安全》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112966941A (en) * | 2021-03-09 | 2021-06-15 | 宁波工程学院 | Accident black spot identification method and system based on traffic accident big data |
| CN113112790A (en) * | 2021-03-09 | 2021-07-13 | 华东师范大学 | Urban road operation situation monitoring method combined with knowledge graph |
| CN112966941B (en) * | 2021-03-09 | 2024-04-19 | 宁波工程学院 | Accident black spot identification method and system based on traffic accident big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Souza et al. | City Information Modelling as a support decision tool for planning and management of cities: A systematic literature review and bibliometric analysis | |
| Wang et al. | Unsupervised machine learning in urban studies: A systematic review of applications | |
| CN111768618B (en) | Traffic jam state propagation prediction and early warning system and method based on city portrait | |
| CN103390039B (en) | Urban disaster thematic map real-time generating method based on network information | |
| Bachechi et al. | Big data analytics and visualization in traffic monitoring | |
| CN106096623A (en) | A kind of crime identifies and Forecasting Methodology | |
| CN108710625A (en) | A kind of special topic knowledge automatic mining system and method | |
| Minaei | Evolution, density and completeness of OpenStreetMap road networks in developing countries: The case of Iran | |
| Liao et al. | Applying crowdsourcing techniques in urban planning: A bibliometric analysis of research and practice prospects | |
| CN101814076A (en) | Visualizing information and information correlation analysis system and establishing method | |
| CN111552772A (en) | Real-time traffic road condition text data and traffic volume combined visual analysis method | |
| Zhang et al. | Using street view images to identify road noise barriers with ensemble classification model and geospatial analysis | |
| Dong et al. | Notice of violation of IEEE publication principles: Data augmented design: Urban planning and design in the new data environment | |
| CN112069327A (en) | Knowledge graph construction method and system for teaching resources of online education classroom | |
| Li et al. | Fusing taxi trajectories and RS images to build road map via DCNN | |
| CN113868492A (en) | Visual OD (origin-destination) analysis method based on electric police and checkpoint data and application | |
| Xu et al. | Application of training data affects success in broad-scale local climate zone mapping | |
| Chen et al. | Data visualization in smart grid and low‐carbon energy systems: A review | |
| Li et al. | Human perception evaluation system for urban streetscapes based on computer vision algorithms with attention mechanisms | |
| AlSukhayri et al. | Leveraging the saudi linked open government data: A framework and potential benefits | |
| Wang et al. | Intelligent traffic analytics: From monitoring to controlling | |
| Hu et al. | Urban landscape information atlas and model system based on remote sensing images | |
| Xu et al. | New data, integrated methods and multiple applications: a review of urban studies based on street view images | |
| Jégou et al. | Proposals for the use of graphical models in urban climatic maps | |
| Niu et al. | Knowledge evolution in transit-oriented development: a comparative bibliometric analysis of International versus Chinese publications |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200818 |