CN106448199A - Traffic control method based on text mining - Google Patents

Abstract

The present invention provides a traffic control method based on text mining, comprising: step 100, obtaining text information of traffic control; step 200, determining the radiation range of the intersection; step 300, determining keywords within the radiation range of the intersection ; Step 400, counting the occurrence frequency and times of the keywords; Step 500, predicting the degree of congestion at the intersection; Step 600, adjusting the traffic control information at the intersection; Step 700, determining the current round of traffic control adjustment cycle. According to the text information related to traffic control within a certain period of time, the present invention can analyze the possible congestion degree of the designated crossroads for a period of time in the future, and adjust the traffic control information of the designated crossroads based on the congestion degree, so as to avoid traffic congestion and improve people's travel quality , Conducive to building a low-carbon society.

Description

A Traffic Control Method Based on Text Mining

technical field

The invention relates to the field of traffic control, in particular to a traffic control method based on text mining.

Background technique

In recent years, the United Kingdom, Australia, Europe and the United States have established traffic control systems in certain cities. In these systems, most of them are equipped with magnetic loop detectors near each intersection, and the control devices or staff at each intersection input traffic control parameters into the microprocessor through communication networks such as telephone lines, cables, and closed-circuit television lines. , centralized control with a small computer.

At present, there are some self-developed urban traffic control and management systems in China, but there is still a big gap in overall performance compared with similar systems abroad, and they are only used in some small and medium-sized cities. Most of the transportation systems introduced by domestic cities, especially big cities, are imported SCOOT and SCATS systems. Because the traffic flow in our country is a mixed traffic flow, which is very different from the traffic flow in foreign countries, the effect of foreign traffic control systems in China is not satisfactory. Compared with foreign countries, my country's current traffic situation is still relatively backward, mainly manifested in:

(1) The structure of urban roads is unreasonable, and the spatial structure of most urban roads belongs to the plane traffic state, forming the characteristics of "mixed traffic of people and vehicles, mixed driving of fast and slow vehicles". The proportion of main and secondary arterial roads and branch lines is out of balance, and the connection relationship is disordered, making it difficult for arterial roads to perform their functions. In terms of road area, the road area ratio of domestic cities is lower than that of large cities of the same size in the world.

(2) The traffic structure is unbalanced. Domestic urban traffic is mainly composed of various motor vehicles, non-motor vehicles and pedestrians, forming a special ternary mixed traffic structure.

(3) The technical level of traffic management is low, and traffic accidents are frequent. At present, China's urban traffic problems present two typical phenomena: poor management and disorder; and no scientific, reasonable and effective urban traffic monitoring system. The consequences of this are getting worse. The road network traffic capacity is significantly lower than the design requirements and has large fluctuations, unpredictable travel time, high incidence of traffic accidents, deteriorating traffic environment, and easy fatigue of travelers.

Contents of the invention

The present invention provides a kind of traffic control method based on text mining for solving the above-mentioned problem, it is characterized in that, comprises the following steps:

Step 100, obtaining traffic control text information;

Step 200, determine the radiation range of the intersection;

Step 300, determining keywords within the radiation range of the intersection;

Step 400, counting the occurrence frequency and times of the keywords;

Step 500, predicting the congestion degree of the intersection;

Step 600, adjusting the traffic control information of the intersection;

Step 700, determine the period of the current round of traffic control adjustment.

According to the text information related to traffic control within a certain period of time, the present invention can analyze the possible congestion degree of the designated crossroads for a period of time in the future, and adjust the traffic control information of the designated crossroads based on the congestion degree, so as to avoid traffic congestion and improve people's travel quality , Conducive to building a low-carbon society.

detailed description

In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. example. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

Embodiment 1 of the present invention discloses a traffic control method based on text mining, which is characterized in that it includes the following steps:

Step 100, obtaining traffic control text information;

Step 200, determine the radiation range of the intersection;

Step 300, determining keywords within the radiation range of the intersection;

Step 400, counting the occurrence frequency and times of the keywords;

Step 500, calculating the congestion degree of the intersection;

Step 600, adjusting the traffic control information of the intersection;

Step 700, determine the period of the current round of traffic control adjustment.

Embodiment 2 of the present invention discloses a traffic control method based on text mining, which is characterized in that it includes the following steps:

Step 100, obtaining traffic control text information;

The method for acquiring traffic control text information in step 100 includes but not limited to capturing short message information, capturing map software information and capturing Internet information.

Step 200, determine the radiation range of the intersection;

The step 200 further includes:

Step 220, determining two road grades passing through the intersection;

The road class division standard among the present invention is: urban road class divides expressway, trunk road, secondary trunk road, branch road four grades, and the red line width control of each level: expressway is not less than 40 meters, trunk road 30-40 meters, secondary road The main road is 25-40 meters, and the branch road is 12-25 meters.

(According to the "Code for Design of Urban Road Engineering" (CJJ37-2012), there is no mandatory requirement for the width of the red line of the road, but only the requirements for the width of the road, the composition of the cross section and the minimum width of each functional zone)

The first-class road is an expressway, with a value of 1: the urban road has a central divider, has more than four motor vehicle lanes, all or part of which adopts a three-dimensional intersection and controls access, and is a road for cars to travel at a relatively high speed. Also known as the car lane. The designed driving speed of the expressway is 60-80km/h.

Secondary roads are main roads, with a value of 2: arterial roads connecting various urban districts, mainly for traffic functions. The designed driving speed of the trunk road is 40-60km/h.

The third-class road is a secondary trunk road, with a value of 3: it assumes the role of traffic collection and distribution between the trunk road and each sub-district, and also has service functions. The design speed of secondary trunk road is 40km/h.

The fourth-level road is a branch road, and the value is 4: the connection line between the secondary trunk road and the Jiefang Road (community road), which is mainly used for service functions. The design speed of the branch road is 30km/h.

Step 240, determining the number of lanes of the two roads passing through the intersection;

Step 260, determine the number of large buildings between the intersection and adjacent intersections, the large buildings in the present invention refer to:

Housing construction projects with more than 25 floors (including, the same below); structures or building projects with a height of more than 100 meters; housing construction projects with a single building area of more than 30,000 square meters;

Housing construction projects with a single span of more than 30 meters; residential complex or building group projects with a construction area of more than 100,000 square meters; housing construction projects with a single construction and safety contract value of more than 100 million yuan;

Soft ground treatment projects with a depth of more than 15 meters and a single project contract value of more than 10 million yuan; foundation and foundation projects with a single pile bearing load of more than 6,000 kN and a single project contract value of more than 10 million yuan; depths of more than 11 meters and a single project contract value Deep and large foundation pit protection and earthwork engineering with a contract value of 10 million yuan; steel structure projects with a steel structure weight of more than 1,000 tons and a steel structure building area of more than 20,000 square meters; grid structure weight of more than 300 tons, and grid structure Grid projects with a construction area of more than 5,000 square meters and a side length of more than 70 meters;

Step 280, calculate the radiation range of the intersection according to the road properties, the number of lanes and the population, the formula for calculating the radiation range is:

Where Rad is the radiation range of the intersection, L ₁ and L ₂ are the first and second road levels passing through the intersection respectively, N ₁ and N ₂ are the first road passing through the intersection and the number of lanes of the second road, N _c is the number of large buildings around the intersection, α and β are the weight coefficients of the first and second roads passing through the intersection respectively, and α, β∈ [0,1], and α+β=1, λ is the radiation range coefficient, which can be adjusted according to the size of the city, preferably 5.

Generally speaking, the smaller the value of the road level passing through an intersection, the more important the intersection is. The more lanes passing through an intersection, the more important the intersection is. If there are more large buildings around the intersection , indicating that the intersection is more important. Therefore, the radiation range calculation formula of the present invention can reflect the influence and importance of different parameters on the radiation range, and the use of the radiation range coefficient can make the formula applicable to cities of different scales, further expanding its practicability.

Step 300, determine keywords within the radiation range of the intersection, the keywords in step 300 include but not limited to address, street name, house number, building name, unit name, performance name, game name.

Step 400, counting the occurrence frequency and times of the keywords;

The step 400 further includes:

Step 420, extracting keywords in the text information;

Step 440, counting the total number of occurrences of each keyword in the text information;

Step 450, calculate the total number of occurrences N of all keywords in the text information

Where w _i is the total number of occurrences of the i-th keyword, and n is the number of keywords;

Step 460, calculate the actual number W _i of occurrences of the i-th keyword in the text information,

Where w _j is the total number of occurrences of the j-th keyword, r _ij is the similarity coefficient between the j-th keyword and the i-th keyword, r _ij ∈ [0,1], i, j ∈ [1, n ], the calculation method of the similarity degree coefficient can use the cosine algorithm based on the space vector;

The so-called real number of keyword occurrences is because a place name may have different expressions, and different keywords may be strongly related. For example, "State Intellectual Property Office" and "State Intellectual Property Office" can be regarded as the same keyword, It is also strongly related to the address "No. 6, Xitucheng Road". The similarity coefficient is a measure to describe the relationship between keywords. The similarity coefficient between unrelated keywords is 0, and the similarity coefficient between the full name and the abbreviation of the keyword is 1.

Step 470, calculate the occurrence frequency f _i of the i-th keyword

Wherein Δt is the time period of the keywords in the statistical text information;

Step 480, calculating the popularity h of the intersection according to the number and frequency of keyword occurrences

Wherein W _k is the real number of occurrences of the kth keyword in the radiation range of the intersection, f _k is the frequency of occurrence of the kth keyword in the radiation range of the intersection, and n _rad is the radiation of the intersection The number of keywords in the range, γ is the adjustment coefficient, γ∈[0,1].

Step 500, predicting the congestion degree of the intersection, the specific method is:

Step 600, adjust the traffic control information of the intersection, the specific method is:

Given the first threshold T, if the congestion degree is greater than the first threshold, an early warning message will be broadcast to all cars in the city, prompting that there may be congestion at the intersection, and reminding citizens to adjust their travel routes;

Step 700, determine the cycle of the current round of traffic control adjustment, and the length of the adjustment cycle is preferably 30 minutes.

Other similarities with the method will not be repeated here, please refer to the method description section for details.

According to the text information related to traffic control within a certain period of time, the embodiment of the present invention can analyze the possible congestion degree of the designated crossroads for a period of time in the future, and adjust the traffic control information of the designated crossroads according to the congestion degree, so as to avoid causing traffic congestion and improve people's The quality of travel is conducive to building a low-carbon society.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still be Modifications are made to the technical solutions described in the foregoing embodiments, or equivalent replacements are made to some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims (4)

1. a traffic control method based on text mining, is characterized in that, comprises the following steps: Step 100, obtaining traffic control text information; Step 200, determine the radiation range of the intersection; Step 300, determining keywords within the radiation range of the intersection; Step 400, counting the occurrence frequency and times of the keywords; Step 500, predicting the congestion degree of the intersection; Step 600, adjusting the traffic control information of the intersection; Step 700, determine the period of the current round of traffic control adjustment. 2. The traffic control method based on text mining according to claim 1, characterized in that, the method for obtaining the text information of traffic control in the step 100 includes but not limited to grabbing short message information, grabbing map software information and grabbing Get Internet information. 3. the traffic control method based on text mining according to claim 1, is characterized in that, described step 200 further comprises: Step 220, determining two road grades passing through the intersection; Step 240, determining the number of lanes of the two roads passing through the intersection; Step 260, determining the number of large buildings between the intersection and adjacent intersections; Step 280, calculate the radiation range of the intersection according to the road properties, the number of lanes and the population, the formula for calculating the radiation range is: $\mathrm{<span\; class="notranslate">\; R</span>}\mathrm{<span\; class="notranslate">\; a</span>}\mathrm{<span\; class="notranslate">\; d</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; \&lambda;</span>}<span\; class="notranslate">\; *</span>{\mathrm{<span\; class="notranslate">\; e</span>}}^{\frac{\mathrm{<span\; class="notranslate">\; ln</span>}{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; ln</span>}{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}{{\mathrm{<span\; class="notranslate">\; \&alpha;L</span>}}_{\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; +</span>{\mathrm{<span\; class="notranslate">\; \&beta;\; L</span>}}_{\mathrm{<span\; class="notranslate">\; 2</span>}}}}<span\; class="notranslate">\; *</span>\sqrt{{\mathrm{<span\; class="notranslate">\; N</span>}}_{\mathrm{<span\; class="notranslate">\; c</span>}}<span\; class="notranslate">\; +</span>\mathrm{<span\; class="notranslate">\; 1</span>}}<span\; class="notranslate">\; ;</span>$ Where Rad is the radiation range of the intersection, L ₁ and L ₂ are the first and second road levels passing through the intersection respectively, N ₁ and N ₂ are the first road passing through the intersection and the number of lanes of the second road, N _c is the number of large buildings around the intersection, α and β are the weight coefficients of the first and second roads passing through the intersection respectively, and α, β∈ [0,1], and α+β=1, λ is the radiation range coefficient. 4. The traffic control method based on text mining according to claim 1, wherein the keywords in the step 300 include but not limited to address, street name, house number, building name, unit name, performance name , the game name.