CN115050187A - Public opinion knowledge graph-based digital urban traffic management method - Google Patents

Public opinion knowledge graph-based digital urban traffic management method Download PDF

Info

Publication number
CN115050187A
CN115050187A CN202210966105.7A CN202210966105A CN115050187A CN 115050187 A CN115050187 A CN 115050187A CN 202210966105 A CN202210966105 A CN 202210966105A CN 115050187 A CN115050187 A CN 115050187A
Authority
CN
China
Prior art keywords
public
opinion
data
traffic
public transport
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
Application number
CN202210966105.7A
Other languages
Chinese (zh)
Other versions
CN115050187B (en
Inventor
申永生
陈冲杰
叶晓华
陈卫锋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou City Brain Co ltd
Original Assignee
Hangzhou City Brain Co ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou City Brain Co ltd filed Critical Hangzhou City Brain Co ltd
Priority to CN202210966105.7A priority Critical patent/CN115050187B/en
Publication of CN115050187A publication Critical patent/CN115050187A/en
Application granted granted Critical
Publication of CN115050187B publication Critical patent/CN115050187B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
    • 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
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Theoretical Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention discloses a public opinion knowledge graph-based digital urban traffic control method. In order to overcome the defects that the prior art only manages and controls urban traffic in a short time and lacks long-time urban traffic planning and management. The invention comprises the following steps: s1: obtaining multi-dimensional historical public transport opinion information of different cities, and constructing a public transport opinion knowledge map; s2: dividing a city into a plurality of control areas, collecting public traffic opinion data of each control area in real time, and identifying and processing categories; s3: when the processing category is real-time management and control, determining the specific position and specific event of the abnormality according to the public traffic opinion data, and associating and executing corresponding traffic management and control operation; s4: and when the processing category is long-term planning, determining a specific event according to the public traffic opinion data, matching a planning processing scheme and feeding back. The urban traffic is managed and controlled in real time and suggested for long-term planning based on the knowledge map, collected public sentiment information is fully utilized, and the urban traffic management level is improved.

Description

Public opinion knowledge graph-based digital urban traffic management method
Technical Field
The invention relates to the field of urban management, in particular to a public opinion knowledge graph-based digital urban traffic management method.
Background
With the accelerated transformation of economic society, the rapid population increase, resource shortage and ecological environment deterioration become serious problems in the process of urbanization, and the sustainable development of large and medium cities becomes one of the key points of attention of human society. The construction of the digital city becomes a brand new city development concept and practice path.
The knowledge graph is an effective means for processing big data of a digital city. Along with the continuous development of novel digital city construction, the demand of people on data application is continuously improved, the data generated by citizen life and operation of various industries is explosively increased, data sources cover the internet, city-level internet of things, social networks, enterprise data operator data, space-time data and the like, a city-level big data center is formed, and reasonable allocation of resources is realized by using big data technologies such as intelligent perception, distributed storage, data mining, real-time dynamic visualization and the like.
Urban traffic as an indispensable link to "digital cities", there are various kinds of information-based traffic management systems, such as: checking traffic management information based on geographic information, including checking police force (personnel, vehicles and equipment) online and distribution conditions; analyzing traffic data based on geographic information, wherein the traffic data comprises road traffic flow statistics, average speed of each road section, traffic flow density, congestion degree analysis display and the like; the two-dimensional map is linked with video monitoring, intelligent analysis of videos is combined, vehicle illegal behavior recognition, positioning, monitoring and checking are carried out, and the map and the videos are linked through manual switching operation; and distributing an authority type index interface, and distributing visual interfaces to traffic managers in different levels according to the authority. The general information traffic management system only has feedback processing on the current or real-time traffic condition, and lacks the development planning management on the long-term urban traffic.
For example, a "traffic operation management system based on traffic management knowledge graph" disclosed in chinese patent literature, which is publication No. CN110442731A, the system setup includes the following steps; s1, the system constructs a plurality of core service display board modules based on an index model system, and each core service display board module is provided with index parameters; s2: establishing a uniform service data description standard model by a traffic management KPI index system model library; s3: the system rapidly positions the positions of the service operation signs or abnormal signs and related conditions according to the traffic management service index knowledge graph; s4: the system establishes a management cockpit module based on a traffic management knowledge graph; s5: and establishing a physical sign thematic module, indexes and desktop thematic configuration.
The scheme has control on the current urban traffic in a short time, but lacks planning and management on the urban traffic for a long time.
Disclosure of Invention
The invention mainly solves the problem that the prior art lacks the long-term planning and control of urban traffic according to the acquired information; the method is characterized in that according to information such as traffic public sentiment collected in real time, urban traffic is managed and controlled in real time and suggested for long-term planning based on the knowledge map, the collected information is fully utilized, and the urban traffic management level is improved.
The technical problem of the invention is mainly solved by the following technical scheme:
a public opinion knowledge graph-based digital urban traffic management method comprises the following steps:
s1: obtaining multi-dimensional historical public transport opinion information of different cities, and constructing a public transport opinion knowledge map;
s2: dividing a city into a plurality of control areas, collecting public transport opinion data of each control area in real time, and identifying the processing category of the collected public transport opinion data as real-time control, no processing or long-term planning according to a public transport opinion knowledge map;
s3: when the processing category is real-time management and control, determining the specific position and specific event of the abnormality according to the public traffic opinion data, and associating and executing corresponding traffic management and control operation;
s4: and when the processing category is long-term planning, determining a specific event according to the public traffic opinion data, matching a planning processing scheme and feeding back.
The public transport opinion management method based on the knowledge map is used for constructing the public transport opinion map based on historical public transport opinion data, carrying out real-time management and control and long-term planning suggestion on urban traffic based on the knowledge map through real-time collected public transport opinion information, fully utilizing the collected information and improving the urban traffic management level. Public sentiment information is fully utilized, and guidance and suggestions are provided for the management of urban traffic.
Preferably, the dimension of the traffic history public opinion information comprises the place, the time, the object, the event keyword, the property and the influence. Public opinion information is extracted from multiple dimensions, namely the public opinion information extraction method can be used for constructing a public opinion knowledge graph and can facilitate subsequent targeted processing of the public opinion information. And mutual verification is facilitated.
Preferably, the step S2 includes the following steps:
s201: dividing each city into a plurality of control areas according to the location distribution of historical public transport opinion information;
s202: collecting public traffic sentiment data and live traffic data by each control area at a set sampling frequency;
s203: and judging the processing type of the public transport opinion data based on the public transport opinion knowledge graph according to the acquired public transport opinion data, and verifying the public transport opinion data by combining with the traffic live data.
The public transport opinion data in different areas are collected and processed in a partitioning mode, and the efficiency and accuracy of information processing are improved.
Preferably, the process of dividing the control area includes:
based on the city map, expressing all public traffic opinion information on the city map in a marking mode according to the minimum location position in the location dimension; the size of the mark is a traffic influence range in influence dimensionality in the public transport opinion information;
determining path nodes after traversing all the public transport opinion information; selecting a least marked coverage area on the urban map, clustering the coverage area, and determining a plurality of path nodes;
and sequentially selecting node paths between the adjacent path nodes by taking the minimum mark coverage range between the adjacent path nodes as a path range and taking the shortest distance in the path range as a node path to form a closed control area.
And different areas are divided, and grid management is performed, so that the efficiency of urban traffic management is improved.
Preferably, each control area collects traffic public opinion data at a set public opinion sampling frequency, and adjusts the live collecting frequency according to the collected and fed back traffic live data:
Figure 722521DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 150091DEST_PATH_IMAGE002
a live acquisition frequency for an ith time period;
Figure 946009DEST_PATH_IMAGE003
a set minimum live acquisition frequency;
Figure 197736DEST_PATH_IMAGE004
setting a vehicle speed difference coefficient;
Figure 875842DEST_PATH_IMAGE005
setting a vehicle speed difference value for the minimum;
Figure 107104DEST_PATH_IMAGE006
the adjacent vehicle speed difference coefficients are obtained;
Figure 491949DEST_PATH_IMAGE007
is the minimum adjacent vehicle speed difference;
Figure 416042DEST_PATH_IMAGE008
real-time vehicle speed of the current lane;
Figure 581444DEST_PATH_IMAGE009
setting a vehicle speed for the current lane;
Figure 616396DEST_PATH_IMAGE010
real-time vehicle speed for adjacent lanes;
[. is a rounding calculation;
Figure 855748DEST_PATH_IMAGE011
adjusting unit values for live acquisition frequencies;
Figure 950743DEST_PATH_IMAGE012
wherein the content of the first and second substances,
Figure 806703DEST_PATH_IMAGE013
is a set maximum live acquisition frequency;
Figure 176505DEST_PATH_IMAGE014
a first adjustment level;
Figure 300056DEST_PATH_IMAGE015
is the second adjustment level.
According to the speed difference between the vehicle speed and the set vehicle speed, the common problem of urban traffic can be reflected, such as congestion at the peak of the morning and evening, influence of severe weather on driving, road maintenance and the like; the larger the speed difference is, the more serious the above problem is, and the acquisition frequency needs to be increased so as not to miss important information. The reasons such as whether the current lane has an accident or not can be reflected according to the adjacent vehicle speed difference, if the adjacent vehicle speed difference is larger, the possibility that the current lane has the accident is higher, and the acquisition frequency needs to be increased so as to avoid missing important information. The real-time traffic condition is used for adjusting the live acquisition frequency of different areas, so that important traffic information is not missed, excessive useless information is not generated, and resource waste is avoided.
Preferably, each control area collects traffic live data at a set live collection frequency, and public opinion sampling frequency is adjusted according to the live collection frequency:
Figure 300373DEST_PATH_IMAGE016
wherein, the first and the second end of the pipe are connected with each other,
Figure 378051DEST_PATH_IMAGE017
public opinion collection frequency in the ith time period;
Figure 817122DEST_PATH_IMAGE018
the set minimum public sentiment collection frequency is set;
Figure 296645DEST_PATH_IMAGE019
is a set frequency interval;
Figure 467864DEST_PATH_IMAGE020
adjusting a unit value for public opinion acquisition frequency;
Figure 32837DEST_PATH_IMAGE021
wherein the content of the first and second substances,
Figure 744441DEST_PATH_IMAGE022
the method comprises the steps of setting maximum public opinion collection frequency;
Figure 344050DEST_PATH_IMAGE023
is the third adjustment level.
The public opinion collecting frequency is increased according to real-time road conditions, the public opinion collection is combined with real-time road conditions, the public opinion collecting efficiency is improved, and important public transport opinions are not missed.
Preferably, the collected public transportation opinion data comprises official public opinion data and non-official public opinion data. Official data and unofficial data have different public credibility and are used as an index for judging the truth of public sentiment.
Preferably, clustering the collected public transport opinion data according to dimensions respectively to form public opinion data clusters on the dimensions;
taking a cluster from each dimension, and performing intersection to obtain a group of same public transport opinion data sets;
traversing all clusters, and obtaining a plurality of identical public transport opinion data sets after arrangement and combination;
and respectively matching the public transport opinion data in the same public transport opinion data set with the public transport opinion knowledge map to obtain corresponding processing categories.
And clustering different reports of the same event, and mutually checking the matching result of the knowledge graph.
Preferably, historical public opinion data matched through the public opinion knowledge graph and acquired live traffic data are checked, whether the historical public opinion data and the acquired live traffic data are identical events is judged, if yes, a corresponding matching result is executed, and otherwise, the historical public opinion data and the acquired live traffic data are matched through the public opinion knowledge graph again after feedback;
if the processing types of the public transport opinion data matching in the same public transport opinion data set are different, taking the matching result of official public opinion data as a final result;
if there is no public opinion data, the final result is the result of most processing categories.
And the reliability of the matching result is improved.
Preferably, a historical planning scheme is matched based on a public opinion knowledge graph through event keywords in the public opinion data;
judging whether the planning scheme exists in a traffic construction planning list of the city, and if so, reordering the importance of the planning scheme in the traffic construction planning list; otherwise, the planning scheme is fed back to the corresponding personnel for planning suggestion.
Preferably, the calculation process of the importance of the planning scheme is as follows:
Figure 686170DEST_PATH_IMAGE024
wherein the content of the first and second substances,
Figure 242834DEST_PATH_IMAGE025
importance of the kth planning scenario;
Figure 758129DEST_PATH_IMAGE026
the influence coefficient is determined by public sentiment information browsing amount, and is obtained by looking up a table according to the public sentiment information browsing amount, and different browsing amounts correspond to different influence coefficients;
Figure 212244DEST_PATH_IMAGE027
reporting times for public opinion information;
Figure 725265DEST_PATH_IMAGE028
the range coefficient for spreading the public transport opinion information is obtained by looking up a table, and different spreading ranges correspond to different range coefficients. The spreading range of the public transport opinion information is determined by the distance between the public transport opinion information publishing place and the event correlation place;
Figure 264830DEST_PATH_IMAGE029
the number of times of matching to the kth planning scheme;
Figure 583816DEST_PATH_IMAGE030
cost coefficients for the kth planning scenario;
Figure 626859DEST_PATH_IMAGE031
the time coefficient for the kth planning scenario.
And calculating the importance of the planning through multiple dimensions, and providing a reference suggestion for the construction planning of urban traffic.
Preferably, when the collected public transport opinion data lack partial dimension information, data restoration is carried out; if the missing dimension is time, directly ending; and if the missing dimension is an event keyword, rejecting the public transport opinion data.
Preferably, the data recovery process is as follows:
a1: matching the public transport opinion data lacking partial dimensionality with the public opinion knowledge map, judging whether a corresponding processing category can be obtained, if so, ending, otherwise, entering the step A2;
a2: and respectively arranging and combining the clusters on other dimensions to form an intersection to obtain a plurality of public opinion data sets.
A3: judging whether other public transport opinion data exist in a public opinion data set where public transport opinion data lacking dimensionality is located; if yes, go to step A4, otherwise, go to step A5;
a4: judging whether other complete public transport opinion data are identical in data of missing dimension, if so, repairing the data as the data of missing dimension, otherwise, entering the step A4;
a5: and traversing the historical public transport opinion information, matching, and selecting the historical public transport opinion information with the highest similarity as a repairing object for repairing the data of the corresponding dimensionality.
The invention has the beneficial effects that:
1. the public transport opinion management method based on the knowledge map is used for constructing the public opinion knowledge map based on historical public transport opinion data, carrying out real-time management and control and long-term planning suggestion on urban transport through the real-time collected public transport opinion information based on the knowledge map, fully utilizing the collected information and improving the urban transport management level.
2. Public sentiment information is fully utilized, and guidance and suggestions are provided for the management of urban traffic.
3. The public transport opinion data in different areas are collected and processed in a partitioning mode, and the efficiency and accuracy of information processing are improved.
4. The general problem of urban traffic can be reflected according to the speed difference between the vehicle speed and the set vehicle speed, and the reasons of whether the current lane has accidents or not can be reflected according to the adjacent vehicle speed difference. The real-time traffic condition is used for adjusting the live acquisition frequency of different areas, so that important traffic information is not missed, excessive useless information is not generated, and resource waste is avoided.
5. The public opinion collecting frequency is increased according to real-time road conditions, the public opinion collection is combined with real-time road conditions, the public opinion collecting efficiency is improved, and important public transport opinions are not missed.
Drawings
Fig. 1 is a flow chart of an urban traffic control method of the invention.
Fig. 2 is a schematic diagram of a public transport opinion knowledge graph according to the present invention.
Fig. 3 is a schematic diagram of the management area division according to the present invention.
Detailed Description
The technical scheme of the invention is further specifically described by the following embodiments and the accompanying drawings.
Example (b):
the public opinion knowledge graph-based digital urban traffic management method of the embodiment is shown as a figure 1 and comprises the following steps of:
s1: obtaining multi-dimensional historical public transport opinion information of different cities, and constructing a public transport opinion knowledge map.
One feature in historical public transport opinion information is used as a dimension, and the historical public transport opinion information comprises features such as places, time, objects, event keywords, properties, influence and the like.
The place comprises a public transport opinion information publishing place and an event correlation place; and characteristic vocabularies such as city names, street names, addresses, landmark buildings and the like are used as screening dimensions. And dividing the set of the public transport opinion information by taking the city name as a unit according to the subordinate relation of the place name associated with the event.
The time dimension comprises public transport opinion information publishing time and event correlation time mentioned in the public transport opinion information.
The object dimension is the subject of the event occurrence, including private cars, public transportation, roads, individuals, and the like.
The event keywords are selected event vocabularies related to traffic, such as car accidents, rear-end collisions, congestion, typhoons, heavy snow, heavy rain and the like.
The characters are emotional attitudes of people on various public transport opinion information, including positive, non-concerned, negative and the like.
The influence is the range of spreading public transport opinion information and the traffic influence range caused by events.
And mutually correlating all dimension information in the same historical public transportation opinion information, and correlating and mapping events in the historical public transportation opinion information with corresponding traffic control decisions.
The public transportation opinion knowledge graph shown in fig. 2 is constructed based on historical public transportation opinion information and traffic control decision, and the specific process of constructing the knowledge graph is not repeated in this embodiment.
S2: the method comprises the steps of dividing a city into a plurality of control areas, collecting public transport opinion data of each control area in real time, and identifying the processing category of the collected public transport opinion data as real-time control, no processing or long-term planning according to a public transport opinion knowledge map.
S201: and dividing each city into a plurality of control areas according to the location distribution of the historical public transport opinion information.
In the embodiment, as shown in fig. 3, on the basis of a city map, each piece of public transportation information is represented on the city map in a mark form according to the smallest location position in the location dimension. The size of the mark is the traffic influence range in the influence dimension in the public transport opinion information.
And determining path nodes after traversing all public transport opinion information. And selecting the coverage area of the least marks on the city map, clustering the coverage area, and determining a plurality of path nodes. In this embodiment, a K-means clustering algorithm is used to cluster the coverage area.
And sequentially selecting node paths between the adjacent path nodes by taking the minimum mark coverage range between the adjacent path nodes as a path range and taking the shortest distance in the path range as a node path to form a closed control area.
S202: and each control area respectively collects public traffic sentiment data and live traffic data at a set sampling frequency.
And each control area respectively collects the public traffic sentiment data at a set public sentiment sampling frequency and collects the live traffic data at a set live collecting frequency.
Adjusting the live acquisition frequency according to the traffic live data acquired and fed back:
Figure 576360DEST_PATH_IMAGE032
wherein, the first and the second end of the pipe are connected with each other,
Figure 337643DEST_PATH_IMAGE002
the live acquisition frequency for the ith time period.
Figure 460320DEST_PATH_IMAGE003
Is the set minimum live acquisition frequency.
Figure 357868DEST_PATH_IMAGE004
Setting a vehicle speed difference coefficient; a weighting coefficient for a vehicle speed difference between an actual vehicle speed and a set vehicle speed; and (4) presetting.
Figure 976806DEST_PATH_IMAGE005
The vehicle speed difference is set to the minimum. Is set by human.
Figure 287702DEST_PATH_IMAGE033
The coefficients of adjacent vehicle speed differences; weighting coefficients of the difference between the actual speed of the current lane and the speed of the adjacent lane; and (4) presetting.
Figure 151753DEST_PATH_IMAGE007
Is the minimum adjacent vehicle speed difference. Is set by human.
Figure 903808DEST_PATH_IMAGE034
And the real-time speed of the current lane is obtained.
Figure 460691DEST_PATH_IMAGE009
And setting the speed of the current lane, namely the speed limit of the lane.
Figure 993304DEST_PATH_IMAGE010
The real-time speed of the adjacent lane.
And [. cndot. ] is a rounding calculation.
Figure 395466DEST_PATH_IMAGE011
The unit value is adjusted for the live acquisition frequency.
Figure 267607DEST_PATH_IMAGE035
Wherein the content of the first and second substances,
Figure 995392DEST_PATH_IMAGE013
is the set maximum live acquisition frequency.
Figure 749721DEST_PATH_IMAGE014
A first adjustment level;
Figure 955575DEST_PATH_IMAGE015
is the second adjustment level. The first adjustment level and the second adjustment level divide the live sampling frequency into a plurality of adjustment levels in an interval of the maximum sampling frequency and the minimum sampling frequency. In the present embodiment, 5 adjustment levels are divided, i.e.
Figure 446337DEST_PATH_IMAGE036
。
According to the speed difference between the vehicle speed and the set vehicle speed, the common problem of urban traffic can be reflected, such as congestion at the peak of the morning and evening, influence of severe weather on driving, road maintenance and the like; the larger the speed difference is, the more serious the above problem is, and the acquisition frequency needs to be increased so as not to miss important information.
The reasons such as whether the current lane has an accident or not can be reflected according to the adjacent vehicle speed difference, if the adjacent vehicle speed difference is larger, the possibility that the current lane has the accident is higher, and the acquisition frequency needs to be increased so as to avoid missing important information.
The real-time traffic condition is used for adjusting the live acquisition frequency of different areas, so that important traffic information is not missed, excessive useless information is not generated, and resource waste is avoided.
Adjusting public opinion sampling frequency according to live acquisition frequency:
Figure 79443DEST_PATH_IMAGE037
wherein, the first and the second end of the pipe are connected with each other,
Figure 586648DEST_PATH_IMAGE017
and the public sentiment collection frequency is the public sentiment collection frequency of the ith time period.
Figure 596192DEST_PATH_IMAGE018
The set minimum public sentiment collection frequency is set.
Figure 177346DEST_PATH_IMAGE038
Is a set frequency interval.
Figure 246934DEST_PATH_IMAGE020
Adjusting unit value for public sentiment collection frequency.
Figure 975855DEST_PATH_IMAGE039
Wherein the content of the first and second substances,
Figure 789090DEST_PATH_IMAGE040
the set maximum public sentiment collection frequency is obtained.
Figure 490330DEST_PATH_IMAGE023
To the third adjustment level, in this embodiment,
Figure 465239DEST_PATH_IMAGE023
and taking 5.
The public opinion collecting frequency is increased according to real-time road conditions, the public opinion collection is combined with real-time road conditions, the public opinion collecting efficiency is improved, and important public transport opinions are not missed.
S203: and judging the processing type of the public transport opinion data based on the public transport opinion knowledge graph according to the acquired public transport opinion data, and verifying the public transport opinion data by combining with the traffic live data.
The collected public transportation opinion data comprises official public opinion data and non-official public opinion data.
And clustering the collected public transport opinion data according to the dimensions to form public opinion data clusters on the dimensions.
Taking a cluster from each dimension, and performing intersection to obtain a group of same public transport opinion data sets; and traversing all the clusters, and obtaining a plurality of identical public transport opinion data sets after arrangement and combination. In the embodiment, the same public transportation opinion data set is the same public transportation event opinion published on different platforms according to law.
For example, the collected public transportation opinion data a1, a2, A3, B, C1, C2, D1, D2, D3, D4, and the like;
if A1, A2 and A3 are the same public transport opinion data set; c1 and C2 are a group of same public transport opinion data sets; d1, D2, D3 and D4 are a group of same public transport opinion data sets;
then, the public transport opinion data clusters of the place dimension { A1A 2A 3G H }, { C1C 2E R }, { D1D 2D 3D 4G K }, … …
Time-dimension traffic public opinion data clustering { A1A 2A 3E H }, { C1C 2B R }, { D1D 2D 3D 4G H }, … …
Traffic public opinion data clustering of object dimensions { A1A 2A 3H C1}, { C1C 2A 1A 2R }, { D1D 2D 3D 4B K }, … …
Traffic public opinion data clustering of event keyword dimension { A1A 2A 3A 4D 1}, { C1C 2A 2R }, { D1D 2D 3D 4C 3H }, … …
Public transport opinion data clustering of property dimension { A1A 2A 3E K }, { C1C 2C 3R }, { D1D 2D 3D 4H V }, … … }
Public transport opinion data clustering of influence dimension { A1A 2A 3R E }, { C1C 2J K }, { D1D 2D 3D 4A 1C 2}, … …
And sequentially intersecting to obtain the same public traffic opinion data set.
And respectively matching the public transport opinion data in the same public transport opinion data set with the public transport opinion knowledge map to obtain corresponding processing categories.
The treatment categories include real-time administration, no treatment required, or long-term planning.
And checking historical public opinion data matched through the public opinion knowledge graph and the acquired live traffic data, judging whether the historical public opinion data and the acquired live traffic data are the same event, if so, executing a corresponding matching result, and otherwise, feeding back and then matching through the public opinion knowledge graph again.
In the embodiment, for example, for the conditions related to traffic accidents, unexpected conditions, and the like, the real-time management and control categories are matched; for public transport opinions caused by inelegant force factors such as severe weather, the classes are matched without processing; and for public traffic opinions such as morning and evening peak congestion, long-term planning is matched.
And if the processing types of the public transport opinion data matching in the same public transport opinion data set are different, taking the matching result of the official public opinion data as a final result.
If there is no official public opinion data, the result of most processing categories is used as the final result.
When the collected public transport opinion data lack partial dimension information, data restoration is carried out. If the missing dimension is time, the process is ended directly. And if the missing dimension is an event keyword, rejecting the public transport opinion data.
A1: and matching the public transport opinion data lacking partial dimensionality with the public opinion knowledge map, judging whether a corresponding processing category can be obtained, if so, ending, otherwise, entering the step A2.
A2: and respectively arranging and combining the clusters on other dimensions to form an intersection to obtain a plurality of public opinion data sets.
A3: judging whether other public transport opinion data exist in a public opinion data set where public transport opinion data lacking dimensionality is located; if so, go to step A4, otherwise, go to step A5.
A4: and judging whether the other complete public transport opinion data are the same in the missing dimension, if so, repairing the data serving as the missing dimension data, and otherwise, entering the step A4.
A5: and traversing the historical public transport opinion information, matching, and selecting the historical public transport opinion information with the highest similarity as a repairing object for repairing the data of the corresponding dimensionality.
S3: and when the processing category is real-time management and control, determining the specific position and specific event of the abnormality according to the public traffic opinion data, and associating and executing corresponding traffic management and control operation.
And matching historical traffic control means including but not limited to closing roads, limiting roads, setting temporary traffic lights and the like by the event keywords in the traffic public opinion data based on the public opinion knowledge map.
And taking the most specific place as an abnormal position according to the place dimension in the public transport opinion data.
And sending the abnormal position and the traffic control means to corresponding staff for execution.
And associating the corresponding traffic public opinion data with the corresponding traffic control operation and updating the public opinion knowledge map.
S4: and when the processing category is long-term planning, determining a specific event according to the public traffic opinion data, matching a planning processing scheme and feeding back.
And matching a historical planning scheme based on a public opinion knowledge graph through event keywords in the public opinion data.
Judging whether the planning scheme exists in a traffic construction planning list of the city, and if so, reordering the importance of the planning scheme in the traffic construction planning list; otherwise, the planning scheme is fed back to the corresponding personnel for planning suggestion.
The calculation process of the importance of the planning scheme comprises the following steps:
Figure 947036DEST_PATH_IMAGE041
wherein the content of the first and second substances,
Figure 796918DEST_PATH_IMAGE025
the importance of the kth planning scenario.
Figure 618244DEST_PATH_IMAGE026
The influence coefficient is determined by public sentiment information browsing amount, and is obtained by looking up a table according to the public sentiment information browsing amount, and different browsing amounts correspond to different influence coefficients.
Figure 498475DEST_PATH_IMAGE027
The number of times of public opinion information reporting is shown.
Figure 405251DEST_PATH_IMAGE042
The range coefficient for spreading the public transport opinion information is obtained by looking up a table, and different spreading ranges correspond to different range coefficients. The range of spreading the public transportation opinion information is determined by the distance between the public transportation opinion information publishing place and the incident correlation place.
Figure 357027DEST_PATH_IMAGE043
The number of times to match to the kth plan.
Figure 767280DEST_PATH_IMAGE030
For the kth plannerThe cost factor of the case.
Figure 349571DEST_PATH_IMAGE044
The time coefficient for the kth planning scenario.
And feeding back the planning scheme with the re-ordered importance to related personnel for planning suggestion.
It should be understood that the examples are for illustrative purposes only and are not intended to limit the scope of the present invention. Further, it should be understood that various changes or modifications of the present invention may be made by those skilled in the art after reading the teaching of the present invention, and such equivalents may fall within the scope of the present invention as defined in the appended claims.

Claims (13)

1. A public opinion knowledge graph-based digital urban traffic management method is characterized by comprising the following steps:
s1: obtaining multi-dimensional historical public transport opinion information of different cities, and constructing a public transport opinion knowledge map;
s2: dividing a city into a plurality of control areas, collecting public transport opinion data of each control area in real time, and identifying the processing category of the collected public transport opinion data as real-time control, no processing or long-term planning according to a public transport opinion knowledge map;
s3: when the processing category is real-time management and control, determining the specific position and specific event of the abnormality according to the public traffic opinion data, and associating and executing corresponding traffic management and control operation;
s4: and when the processing category is long-term planning, determining a specific event according to the public traffic opinion data, matching a planning processing scheme and feeding back.
2. The method as claimed in claim 1, wherein the dimensions of the traffic history public opinion information include location, time, object, event keyword, nature and influence.
3. The public opinion knowledge graph-based digital urban traffic control method according to claim 1, wherein the step S2 comprises the steps of:
s201: dividing each city into a plurality of control areas according to the location distribution of historical public transport opinion information;
s202: collecting public traffic sentiment data and live traffic data by each control area at a set sampling frequency;
s203: and judging the processing type of the public transport opinion data based on the public transport opinion knowledge graph according to the acquired public transport opinion data, and verifying the public transport opinion data by combining with the traffic live data.
4. The public opinion knowledge graph-based digital urban traffic governance method according to claim 1 or 3, wherein the management and control area division process is as follows:
based on a city map, representing the public traffic opinion information on the city map in a marking mode according to the minimum location position in the location dimension; the size of the mark is a traffic influence range in influence dimensionality in public traffic opinion information;
determining path nodes after traversing all public transport opinion information; selecting a least marked coverage area on the urban map, clustering the coverage area, and determining a plurality of path nodes;
and sequentially selecting node paths between the nodes of each adjacent path by taking the minimum mark coverage range between the nodes of the adjacent paths as a path range and taking the shortest distance in the path range as a node path to form a closed control area.
5. A public opinion knowledge graph-based digital urban traffic control method according to claim 1 or 3, wherein each control area collects traffic public opinion data at a set public opinion sampling frequency, and adjusts the live collecting frequency according to the collected and fed back traffic live data:
Figure 105862DEST_PATH_IMAGE001
wherein the content of the first and second substances,
Figure 491844DEST_PATH_IMAGE002
a live acquisition frequency for an ith time period;
Figure 740423DEST_PATH_IMAGE003
is a set minimum live acquisition frequency;
Figure 604473DEST_PATH_IMAGE004
setting a vehicle speed difference coefficient;
Figure 386222DEST_PATH_IMAGE005
setting a vehicle speed difference value for the minimum;
Figure 677526DEST_PATH_IMAGE006
the coefficients of adjacent vehicle speed differences;
Figure 413401DEST_PATH_IMAGE007
is the minimum adjacent vehicle speed difference;
Figure 815564DEST_PATH_IMAGE008
real-time vehicle speed of the current lane;
Figure 953284DEST_PATH_IMAGE009
setting a vehicle speed for the current lane;
Figure 212227DEST_PATH_IMAGE010
real-time vehicle speed for adjacent lanes;
[. is a rounding calculation;
Figure 435398DEST_PATH_IMAGE011
adjusting unit values for live acquisition frequencies;
Figure 641251DEST_PATH_IMAGE012
wherein the content of the first and second substances,
Figure 633478DEST_PATH_IMAGE013
is a set maximum live acquisition frequency;
Figure 765120DEST_PATH_IMAGE014
a first adjustment level;
Figure 475587DEST_PATH_IMAGE015
is the second adjustment level.
6. The digital urban traffic control method based on public opinion knowledge graph according to claim 5, wherein each control area respectively collects traffic live data at a set live collection frequency, and adjusts public opinion sampling frequency according to the live collection frequency:
Figure 219552DEST_PATH_IMAGE016
wherein the content of the first and second substances,
Figure 331865DEST_PATH_IMAGE017
public opinion collection frequency in the ith time period;
Figure 932610DEST_PATH_IMAGE018
the set minimum public sentiment collection frequency is set;
Figure 130373DEST_PATH_IMAGE019
is a set frequency interval;
Figure 412450DEST_PATH_IMAGE020
adjusting a unit value for public opinion acquisition frequency;
Figure 379269DEST_PATH_IMAGE021
wherein the content of the first and second substances,
Figure 619758DEST_PATH_IMAGE022
the method comprises the steps of setting maximum public opinion collection frequency;
Figure DEST_PATH_IMAGE023
is the third adjustment level.
7. A public opinion knowledge graph-based digital urban traffic control method according to claim 1, 3 or 6, wherein the collected public opinion data includes official public opinion data and non-official public opinion data.
8. The method as claimed in claim 7, wherein the collected public transportation data are clustered according to dimensions to form public transportation data clusters in each dimension;
taking a cluster from each dimension, and performing intersection to obtain a group of same public transport opinion data sets;
traversing all clusters, and obtaining a plurality of same public transport opinion data sets after arrangement and combination;
and respectively matching the public transport opinion data in the same public transport opinion data set with the public transport opinion knowledge map to obtain corresponding processing categories.
9. The method as claimed in claim 1, wherein the historical public opinion data matched with the public opinion knowledge map and the collected live traffic data are checked to determine whether the historical public opinion data and the collected live traffic data are the same event, if yes, the corresponding matching result is executed, otherwise, the public opinion knowledge map is matched again after feedback;
if the processing types of the public transport opinion data matching in the same public transport opinion data set are different, taking the matching result of official public opinion data as a final result;
if there is no official public opinion data, the result of most processing categories is used as the final result.
10. The method for digital urban traffic control based on public opinion knowledge graph according to claim 1, wherein a historical planning scheme is matched based on public opinion knowledge graph through event keywords in traffic public opinion data;
judging whether the planning scheme exists in a traffic construction planning list of the city, and if so, reordering the importance of the planning scheme in the traffic construction planning list; otherwise, the planning scheme is fed back to the corresponding personnel for planning suggestion.
11. The public opinion knowledge graph-based digital urban traffic control method according to claim 10, wherein the calculation process of the importance of the planning scheme is as follows:
Figure 809211DEST_PATH_IMAGE024
wherein the content of the first and second substances,
Figure 894979DEST_PATH_IMAGE025
importance of the kth planning scenario;
Figure 716304DEST_PATH_IMAGE026
the influence coefficient is determined by public sentiment information browsing amount, and is obtained by looking up a table according to the public sentiment information browsing amount, and different browsing amounts correspond to different influence coefficients;
Figure 127694DEST_PATH_IMAGE027
reporting times for public opinion information;
Figure 831208DEST_PATH_IMAGE028
obtaining the range coefficient of spreading public transport opinion information by looking up a table, wherein different spreading ranges correspond to different range coefficients; the spreading range of the public transport opinion information is determined by the distance between the public transport opinion information publishing place and the event correlation place;
Figure 455087DEST_PATH_IMAGE029
the number of times of matching to the kth planning scheme;
Figure 396499DEST_PATH_IMAGE030
cost coefficients for the kth planning scenario;
Figure 978790DEST_PATH_IMAGE031
the time coefficient for the kth planning scenario.
12. A public opinion knowledge graph-based digital urban traffic control method according to claim 1, 3, 6 or 8, characterized in that when the collected public opinion data lacks information of partial dimension, data recovery is performed; if the missing dimension is time, directly ending; and if the missing dimension is an event keyword, rejecting the public transport opinion data.
13. The public opinion knowledge graph-based digital urban traffic control method according to claim 12, wherein the data restoration process is as follows:
a1: matching the public transport opinion data lacking partial dimensionality with the public opinion knowledge map, judging whether a corresponding processing category can be obtained, if so, ending, otherwise, entering the step A2;
a2: respectively arranging and combining the clusters on other dimensions to form an intersection to obtain a plurality of public opinion data sets;
a3: judging whether other public transportation opinion data exist in a public opinion data set where the public transportation opinion data lacking dimensionality is located; if yes, go to step A4, otherwise, go to step A5;
a4: judging whether other complete public transport opinion data are identical in data of missing dimension, if so, repairing the data as the data of missing dimension, otherwise, entering the step A4;
a5: and traversing the historical public transport opinion information, matching, and selecting the historical public transport opinion information with the highest similarity as a repairing object for repairing the data of the corresponding dimensionality.
CN202210966105.7A 2022-08-12 2022-08-12 Public opinion knowledge graph-based digital urban traffic management method Active CN115050187B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210966105.7A CN115050187B (en) 2022-08-12 2022-08-12 Public opinion knowledge graph-based digital urban traffic management method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210966105.7A CN115050187B (en) 2022-08-12 2022-08-12 Public opinion knowledge graph-based digital urban traffic management method

Publications (2)

Publication Number Publication Date
CN115050187A true CN115050187A (en) 2022-09-13
CN115050187B CN115050187B (en) 2022-11-01

Family

ID=83167000

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210966105.7A Active CN115050187B (en) 2022-08-12 2022-08-12 Public opinion knowledge graph-based digital urban traffic management method

Country Status (1)

Country Link
CN (1) CN115050187B (en)

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
US20170124464A1 (en) * 2015-10-28 2017-05-04 Fractal Industries, Inc. Rapid predictive analysis of very large data sets using the distributed computational graph
CN107203641A (en) * 2017-06-19 2017-09-26 北京易华录信息技术股份有限公司 A kind of method of the collection of Internet traffic public feelings information and processing
CN107742418A (en) * 2017-09-29 2018-02-27 东南大学 A kind of urban expressway traffic congestion status and stifled point position automatic identifying method
CN110413784A (en) * 2019-07-23 2019-11-05 国家计算机网络与信息安全管理中心 The public sentiment association analysis method and system of knowledge based map
CN110533212A (en) * 2019-07-04 2019-12-03 西安理工大学 Urban waterlogging public sentiment monitoring and pre-alarming method based on big data
CN111914096A (en) * 2020-07-06 2020-11-10 同济大学 Public transport passenger satisfaction evaluation method and system based on public opinion knowledge graph
CN112749239A (en) * 2021-01-20 2021-05-04 青岛海信网络科技股份有限公司 Event map construction method and device and computing equipment
CN114153965A (en) * 2021-12-08 2022-03-08 深圳市网联安瑞网络科技有限公司 Content and map combined public opinion event recommendation method, system and terminal
US20220084051A1 (en) * 2020-09-11 2022-03-17 Changxin Memory Technologies, Inc. System and method for processing public sentiment, computer storage medium and electronic device

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170124464A1 (en) * 2015-10-28 2017-05-04 Fractal Industries, Inc. Rapid predictive analysis of very large data sets using the distributed computational graph
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
CN107203641A (en) * 2017-06-19 2017-09-26 北京易华录信息技术股份有限公司 A kind of method of the collection of Internet traffic public feelings information and processing
CN107742418A (en) * 2017-09-29 2018-02-27 东南大学 A kind of urban expressway traffic congestion status and stifled point position automatic identifying method
CN110533212A (en) * 2019-07-04 2019-12-03 西安理工大学 Urban waterlogging public sentiment monitoring and pre-alarming method based on big data
CN110413784A (en) * 2019-07-23 2019-11-05 国家计算机网络与信息安全管理中心 The public sentiment association analysis method and system of knowledge based map
CN111914096A (en) * 2020-07-06 2020-11-10 同济大学 Public transport passenger satisfaction evaluation method and system based on public opinion knowledge graph
US20220084051A1 (en) * 2020-09-11 2022-03-17 Changxin Memory Technologies, Inc. System and method for processing public sentiment, computer storage medium and electronic device
CN112749239A (en) * 2021-01-20 2021-05-04 青岛海信网络科技股份有限公司 Event map construction method and device and computing equipment
CN114153965A (en) * 2021-12-08 2022-03-08 深圳市网联安瑞网络科技有限公司 Content and map combined public opinion event recommendation method, system and terminal

Also Published As

Publication number Publication date
CN115050187B (en) 2022-11-01

Similar Documents

Publication Publication Date Title
CN108109382B (en) Congestion point, congestion line and congestion area discovery method based on composite network
CN108364467B (en) Road condition information prediction method based on improved decision tree algorithm
CN110705747A (en) Intelligent public transport cloud brain system based on big data
CN102521965B (en) Effect evaluation method of traffic demand management measures based on identification data of license plates
CN108648445B (en) Dynamic traffic situation prediction method based on traffic big data
CN110555544B (en) Traffic demand estimation method based on GPS navigation data
CN106844527B (en) Road surface disease identification and management decision-making method and system based on internet big data
CN113269347B (en) College express network node flow prediction method based on random forest
CN116797055A (en) Urban road planning method and system based on Internet of things
CN108806257B (en) Method for identifying congested areas and congested road sections
US20220319323A1 (en) Method for identifying road risk based on networked vehicle-mounted adas
CN115050187B (en) Public opinion knowledge graph-based digital urban traffic management method
CN113256978A (en) Method and system for diagnosing urban congestion area and storage medium
CN116013084A (en) Traffic management and control scene determining method and device, electronic equipment and storage medium
CN113284340B (en) Road traffic safety grading system
CN105608315A (en) Quantitative evaluation method and system of safety service level of bus stop
Adrees et al. A proposed framework for using GIS to enhance traffic safety in Sudan: a case study
CN111785024B (en) Urban vehicle working condition construction method based on regions and time domains
CN114139984A (en) Urban traffic accident risk prediction method based on flow and accident collaborative perception
CN114398413A (en) Intelligent analysis method, equipment and storage medium for road inspection
Tran et al. Transportation analytics with fuzzy logic and regression
Zenina et al. Transport travel demand simulation model development for mixed-use building
Sun et al. Identification of recurrent congestion in main trunk road based on grid and analysis on influencing factors
CN110246075B (en) Smart city monitoring bayonet layout method
CN115035722B (en) Road safety risk prediction method based on combination of space-time characteristics and social media

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