CN114677839B - Customized travel intelligent transportation system based on big data and control method thereof - Google Patents
Customized travel intelligent transportation system based on big data and control method thereof Download PDFInfo
- Publication number
- CN114677839B CN114677839B CN202210595131.3A CN202210595131A CN114677839B CN 114677839 B CN114677839 B CN 114677839B CN 202210595131 A CN202210595131 A CN 202210595131A CN 114677839 B CN114677839 B CN 114677839B
- Authority
- CN
- China
- Prior art keywords
- traffic
- information
- travel
- customized
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- 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
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Abstract
The invention relates to a customized travel intelligent transportation system based on big data and a control method thereof, wherein the control method comprises the steps of receiving a customized transportation request sent by a user through a mobile terminal; determining whether a customized traffic request of a user is received, and if so, requesting a traffic customization module to give a customized travel suggestion; and carrying out travel based on the returned travel suggestions. Under the support of big data, the intelligent traffic control is carried out in a quantitative calculation mode from three angles of a traffic prediction model, a prediction label and customized traffic, so that the traffic transportation efficiency and the intelligent degree are improved.
Description
Technical Field
The invention belongs to the field of intelligent transportation, and particularly relates to a customized travel intelligent transportation system based on big data and a control method thereof.
Background
Urban traffic is a dynamic, open and comprehensive huge system, and with the continuous improvement of the levels of urbanization and motorization, traffic congestion becomes a troublesome problem commonly faced by various major cities in the world. The supply and demand relationship is complex, and the generation, evolution and dissipation of traffic jam are more complex processes. With the continuous development of traffic navigation technology, path planning and intelligent travel are gradually favored by people. The intelligent traffic system is developed in many areas, and is an effective and novel method for relieving urban traffic pressure and reducing environmental pollution at present. The real-time and accurate traffic prediction can provide traffic guidance for the traveling of citizens, provide timely decision support for the management of traffic departments, and is the key for ensuring the efficient operation of a traffic system. The traffic jam degree is comprehensively and objectively measured, the traffic jam situation is accurately mastered in real time, deep analysis is performed, large data resources are fully utilized to scientifically support traffic guidance, and the method is an important basis and precondition for researching traffic intellectualization.
At present, products such as navigation and the like which can provide travel suggestions are often used for calculating approximate time or other indexes of each travel path according to historical traffic data of each travel path after various feasible travel paths are planned, and then are provided for a user to select. In research in the field of traffic flow prediction, various prediction models and prediction methods have been developed. In this case, then, accurate traffic flow prediction is a prerequisite and key to its implementation for intelligent transportation. However, it is known that the current traffic prediction method still has many problems. Traffic forecasts tend to be substantially accurate and may fail for a number of unknown reasons. On the other hand, the traffic intelligence management is completely dependent on the traditional prediction mechanism, and obviously has inherent defects. How to carry out efficient intelligent traffic management from the innate and the acquired, namely fundamentally, is a problem to be solved;
under the support of big data, the intelligent traffic control is carried out from three angles of a traffic prediction model, a prediction label and customized traffic through a quantitative calculation mode, and the traffic transportation efficiency is improved.
Disclosure of Invention
In order to solve the above problems in the prior art, the present invention provides a big data customized travel intelligent transportation system and a control method thereof, wherein the system comprises: the system comprises a mobile terminal and an intelligent traffic module;
the intelligent transportation module includes: the system comprises a traffic prediction module, a traffic customization module, an interface module, an intelligent calculation module and a label calculation module;
the mobile terminal is used for enabling a user to send a customized traffic request to the intelligent traffic module and receive an intelligent traffic suggestion returned by the intelligent traffic module;
the intelligent traffic module is used for receiving a traffic customization request sent by a user, acquiring traffic prediction information and traffic customization information, obtaining an intelligent traffic suggestion through the intelligent calculation module, and returning the obtained intelligent traffic suggestion to the mobile terminal;
the interface module is used for receiving a customized traffic request sent by a user, analyzing the customized traffic request and sending the analyzed customized traffic request information to the intelligent calculation module, the traffic prediction module and the traffic customization module; the interface module is also used for submitting personal information for registration login through the mobile terminal by a user, and sending the submitted personal information to the intelligent transportation module for storage;
the analyzing the customized traffic request specifically comprises: acquiring user information and travel sub-conditions in the customized traffic request; the travel sub-conditions comprise request time, travel time information, transportation mode information, route information, a departure place and/or a destination;
the label calculation module is used for calculating label information of the customized traffic request based on the analyzed customized traffic request; sending the label information to a traffic prediction module;
the calculating of the tag information of the customized traffic request specifically includes: calculating to obtain label information based on the time information; extracting a basic label in the time information; extracting a conventional special label in the time information; extracting a hidden special label in the time information; and using a basic label, a conventional special label and a hidden special label as label information of the customized traffic request; wherein: the hidden special label is information which changes along with time;
the method for extracting the hidden special label in the time information specifically comprises the following steps:
step SUB _ A1, obtaining search result information of travel time through search based on travel time information; the search is internet search, question and answer search and news search;
step SUB _ A2, extracting an event information set from the search result information;
a step SUB _ A3, determining an unprocessed event from the event information set, and determining whether the unprocessed event is a valid event; if so, return to step SUB _ A3; otherwise, taking the unprocessed event as a current event and entering the next step;
a step SUB _ A4 of acquiring first historical trip information with the same event type based on the current event information, judging a first influence degree of the current event information on the first historical trip information, and when the first influence degree is greater than a preset influence degree, taking the event information as an extracted hidden special label; otherwise, when the first influence degree is smaller than or equal to a preset influence degree, determining the extracted hidden special label based on the combination of events;
the event-based merging determination of the extracted hidden special tags specifically includes: forming an event binary group by the current event and each non-current event in the event set; calculating a second influence degree of each event binary group on second historical trip information, wherein: the second historical trip information is the first historical trip information related to two events in the event binary group; when more than one second influence degree is larger than a preset influence degree, selecting the event binary group corresponding to the largest second influence degree as the extracted hidden special label; when the current time does not exist, entering the next step;
calculating a first influence degree of the current event information on the first historical travel information, specifically: calculating a first degree of influence IDG based on the following formula;
wherein:
the prediction accuracy of the traffic prediction module in the ith historical travel information in the first historical travel information is shown, and the RPR is the preset accuracy; n is the number of pieces of historical travel information in the first historical travel information;
the calculating of the second degree of influence of each event binary group on the second historical travel information specifically includes: similarly, the formula (1) and the formula (2) are adopted to calculate a second degree of influence of the event binary group on the second historical travel information aiming at the historical travel information of the second binary event in the event binary group existing in the first historical travel record at the same time, namely the second historical travel information;
step SUB _ A5, judging whether all events are processed, if yes, ending, otherwise, returning to step SUB _ A3;
the label calculation module is also used for taking the hidden special label as a newly added input parameter of the traffic prediction module; training and updating the traffic prediction module based on the sample data containing the newly added input parameters;
the traffic prediction module is used for predicting traffic conditions based on the first traffic prediction model and giving out conventional travel suggestions based on prediction results; the first traffic prediction model predicts traffic conditions based on the basic label and the conventional special label;
the traffic prediction module also comprises a second traffic prediction model, when new input parameters are generated, the traffic prediction model creates a backup of the first traffic prediction model as the second traffic prediction model, performs new training on the second traffic prediction model based on the new input parameters, and replaces the first traffic prediction model with the second traffic prediction model when the training of the second traffic prediction model meets a target value;
the traffic customizing module is used for giving a customized travel suggestion corresponding to the customized traffic request;
the intelligent calculation module is used for determining whether to accept the customized traffic request of the user, and if so, requesting the traffic customization module to give a customized travel suggestion as an intelligent traffic suggestion; and if not, requesting the traffic prediction module to give a conventional travel suggestion as an intelligent traffic suggestion.
Further, the intelligent transportation module is built on a big data platform.
Furthermore, the number of the mobile terminals is one or more.
Further, the interface module is used for providing a graphical user interface for the mobile terminal when receiving access of the mobile terminal, and forming an intelligent traffic request after collecting the customized traffic information written by the mobile terminal.
Further, the interface module is also used for analyzing the customized traffic request and sending the analyzed customized traffic request information to the intelligent calculation module, the traffic prediction module and the traffic customization module.
A big data-based customized travel intelligent traffic control method based on the system is characterized by comprising the following steps:
step S1: receiving a traffic customizing request sent by a user through a mobile terminal;
step S2: determining whether a customized traffic request of a user is accepted, and if so, requesting a traffic customization module to give a customized travel suggestion; if not, requesting the traffic prediction module to give a conventional travel suggestion;
step S3: and the user goes out based on the returned travel advice.
Further, the user sends the customized traffic request in a wireless manner.
A processor is used for running a program, wherein the program runs to execute the big data-based customized travel intelligent transportation control method.
A computer-readable storage medium comprising a program which, when run on a computer, causes the computer to execute the big-data based customized travel intelligent transportation control method.
An execution device, comprising a processor coupled to a memory, wherein the memory stores program instructions, and wherein the program instructions stored in the memory when executed by the processor implement the big data based customized travel intelligent transportation control method.
The beneficial effects of the invention include:
(1) a customized trip and a mode of combining the customized trip with traffic prediction are provided, and fusion is performed based on quantitative calculation, so that the traffic transportation efficiency is greatly improved; (2) the prediction model can dynamically change along with the internal rule of traffic change by discovering and enabling the dynamic label, and the special label is hidden, so that the failure condition of the traffic prediction model can be avoided; (3) a dynamically extensible traffic prediction module and a rapid thermal update mechanism are designed so that the traffic prediction model can keep follow-up updates as time progresses and time changes.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, and are not to be considered limiting of the invention, in which:
FIG. 1 is a schematic structural diagram of a big data-based customized travel intelligent transportation system of the present invention;
fig. 2 is a schematic diagram of a customized travel intelligent traffic control method based on big data according to the present invention.
Detailed Description
The invention will be described in detail with reference to the drawings and specific embodiments, wherein the exemplary embodiments and the description are only for the purpose of illustrating the invention, and are not to be construed as limiting the invention
As shown in fig. 1, the present invention provides a customized travel intelligent transportation system based on big data, and the system includes: the system comprises a mobile terminal and an intelligent traffic module;
the intelligent transportation module includes: the system comprises a traffic prediction module, a traffic customization module, an interface module, an intelligent calculation module and a label calculation module;
the mobile terminal is used for enabling a user to send a customized traffic request to the intelligent traffic module and receive an intelligent traffic suggestion returned by the intelligent traffic module;
intelligent traffic recommendations include traffic plans and their predicted times, such as: in the time range A, taking the vehicle B to walk on the route C, and consuming 1 hour;
the intelligent traffic module is used for receiving a traffic customization request sent by a user, acquiring traffic prediction information and traffic customization information, obtaining an intelligent traffic suggestion through the intelligent calculation module, and returning the obtained intelligent traffic suggestion to the mobile terminal;
preferably: the intelligent traffic module is constructed on a big data platform;
preferably: one or more mobile terminals are provided;
the interface module is used for receiving a customized traffic request sent by a user, analyzing the customized traffic request and sending the analyzed customized traffic request information to the intelligent computing module, the traffic prediction module and the traffic customization module; the interface module is also used for submitting personal information for registration login through the mobile terminal by a user, and sending the submitted personal information to the intelligent transportation module for storage;
preferably, the following components: the interface module is used for providing a graphical user interface to the mobile terminal when receiving the access of the mobile terminal, and forming an intelligent traffic request after collecting the customized traffic information written by the mobile terminal;
the analyzing the customized traffic request specifically comprises: acquiring user information and travel sub-conditions in the customized traffic request; wherein: the travel sub-conditions comprise sub-conditions such as request time, travel time information, transportation mode information, route information, departure place and/or destination and the like; these sub-conditions are alternative, for example: driving can be replaced by taxi taking, public transportation and the like; the extension of time through the time range is also replaceable; the customized traffic request is a customized request for traffic resources, which is made by a user based on the travel demand of the user; the corresponding customized travel suggestion is a travel suggestion based on traffic resource reservation and customized use given by aiming at the customized traffic request;
preferably: sorting the travel sub-conditions according to replaceability; alternative rankings are default rankings, or may be user-specified; alternatives to the sub-conditions are to meet general user requirements, such as: the bicycle can be replaced by walking, and the walking mode can be realized by most people, so that the replaceability is very strong; when the number of the alternative options is more, the replaceability is strong; otherwise, the number of replaceable options is small, and the range is narrow, so that the replaceability is weak;
the label calculation module is used for calculating label information of the customized traffic request based on the analyzed customized traffic request; sending the label information to a traffic prediction module;
the calculating of the tag information of the customized traffic request specifically includes: calculating to obtain label information based on the time information; extracting basic labels of year, month, day and the like in the time information; conventional special labels in extraction time, such as: holidays, workdays, peak hours; extracting hidden special labels in the time information, such as study days, examination days, curtain opening, extremely cold weather, rainstorm, subway opening days and the like; and using the basic label, the conventional special label and the hidden special label as the label information of the customized traffic request; hiding a special label is information that may change over time, for example: the information such as the study date is not a fixed time, but has a non-negligible influence on the traffic; the hidden special label can also change along with the change of time, and is information which is not considered in the conventional traffic prediction;
the method for extracting the hidden special label in the time information specifically comprises the following steps:
step SUB _ A1, obtaining search result information of travel time through search based on travel time information; the search is various search channels such as internet search, question and answer search, news search and the like;
preferably: the search is a search around route information;
step SUB _ A2, extracting an event information set from the search result information; for example: subway opening, rainstorm reduction, elastic work advice, peak shifting travel advice and the like;
a step SUB _ A3, determining an unprocessed event from the event information set, and determining whether the unprocessed event is a valid event; if yes, returning to the step SUB _ A3, otherwise, taking the unprocessed event as the current event and entering the next step;
preferably; before executing the step, preprocessing the event information set to delete meaningless events in the event information set;
the determining whether the event is a valid event specifically includes: determining whether the event information is an input parameter of a first traffic prediction model in a current traffic prediction module;
step SUB _ A4, acquiring first historical trip information with the same event type based on the current event information, judging a first influence degree of the current event information on the first historical trip information, and taking the event information as an extracted hidden special label when the first influence degree is greater than a preset influence degree; otherwise, entering the next step;
here, it can be understood that the first historical travel information is travel information historically related to the current event, and at this time, the historical travel information may be determined by means of searching because the historical travel information fails to be labeled for the current event, for example: when the event is a study day, searching historical study days and corresponding historical travel information thereof as first historical travel information;
alternatively: when the first influence degree is less than or equal to a preset influence degree, determining the extracted hidden special label based on the combination of events;
the event-based merging determination of the extracted hidden special tags specifically includes: forming an event binary group by the current event and each non-current event in the event set; calculating a second degree of influence of each event binary group on second historical travel information, wherein: the second historical trip information is the first historical trip information related to two events in the event binary group; when more than one second influence degree is larger than a preset influence degree, selecting the event binary group corresponding to the largest second influence degree as the extracted hidden special label; when the current time does not exist, entering the next step;
alternatively: selecting an event binary group with the influence degree larger than a second preset influence degree as the extracted hidden special label;
preferably: the first preset influence degree and the second preset influence degree are preset values;
preferably: the label calculation module is also used for taking the hidden special label as a newly added input parameter of the traffic prediction module; training and updating the traffic prediction module based on the sample data containing the newly added input parameters; for the event binary group, the event description can be a new event type as a new event description, and the event description is a new added input parameter; for example: monday and study day; through superposition of event combination in a binary mode, multiple types of newly discovered events are finally integrated into a new representative event type, for example, the event type is Monday, the day of the study and the vicinity of school, and the newly discovered events are finally used as credible input parameters to influence the accuracy of a traffic prediction model; of course, these hidden special tags may be included in the regular special tags as time progresses, and may also be annihilated as time progresses;
calculating a first influence degree of the current event information on the first historical travel information, specifically: calculating a first degree of influence IDG based on the following formula;
wherein:
the prediction accuracy of the traffic prediction module in the ith historical travel information in the first historical travel information is shown, and the RPR is the preset accuracy; n is the number of the historical trip information in the first historical trip information;
preferably: the prediction accuracy is the prediction aiming at the traffic jam index;
the calculating of the second degree of influence of each event binary group on the second historical travel information specifically includes: similarly, the formula (1) and the formula (2) are adopted to calculate a second degree of influence of the event binary group on the second historical travel information aiming at the historical travel information of the second binary event in the event binary group existing in the first historical travel record at the same time, namely the second historical travel information;
step SUB _ A5, judging whether all events are processed, if yes, ending, otherwise, returning to step SUB _ A3;
most of the existing traffic prediction models can perform continuous prediction based on time, and the prediction is accurate in most cases, but in many cases, because the hidden information behind the time is not found timely, the general meaning represented by the time is only considered but is not accurate, the invention finds the hidden special label in the time information and performs historical information verification through deep extraction of the time information, thereby improving the possible prediction accuracy;
the traffic prediction module is used for predicting traffic conditions based on the first traffic prediction model and giving travel suggestions based on prediction results;
preferably: the first traffic prediction model predicts traffic conditions based on the basic labels and the conventional special labels;
preferably: the first traffic prediction model is a neural network-based traffic prediction model; the method is also a commonly adopted prediction model for the current traffic prediction;
the traffic prediction module also comprises a second traffic prediction model, when newly added input parameters occur, the traffic prediction model establishes a backup of the current first traffic prediction model as the second traffic prediction model, performs new training on the second traffic prediction model based on the newly added input parameters, and replaces the first traffic prediction model with the second traffic prediction model when the training of the second traffic prediction model meets a target value; in such a way, the dynamic expansion and the rapid hot update of the traffic prediction module are supported, so that the traffic prediction model can be continuously updated along with the time progress, and the social development and the information progress are met;
preferably, the following components: the newly added input parameters are input parameters given by the label calculation module; these input parameters will change constantly with time;
preferably: the first traffic prediction model is dynamically extensible, and specifically comprises: the input parameters of the traffic prediction model are set in a plurality of units, and part of the input parameters in the plurality of units are reserved data units and are set as default values when not used; when the newly added input parameters are generated, the newly added input parameters correspond to the reserved data elements, and the traffic prediction model is trained on the basis of sample data containing the newly added input parameters;
preferably: the newly added data input layer performs input processing on the newly added input parameters, so that the newly added input parameters meet the parameter input format and the characteristic extraction mode reserved by the first traffic prediction model;
the traffic customizing module is used for giving a customized travel suggestion corresponding to the customized traffic request; the method specifically comprises the following steps: determining the customized travel suggestion closest to the customized traffic request based on the traffic saturation and the given customized travel suggestions; that is, the customized traffic request is based on the principle of first-come first-order customization, and the travel advice given can increase the traffic saturation; of course, alternatively, the closest customized travel suggestion is determined by taking the user information in the customized traffic request into consideration and the priority of the user as well; the travel advice given by the traffic customization module is based on accurate customization information, and as long as people travel according to the customized travel advice, and the customization system has enough usage amount, the travel advice can be guaranteed by 100%, so that inaccuracy caused by prediction is overcome to the degree of the past, the maximum execution efficiency is exerted by combining the traffic customization module and the prediction system, and the influence of human factors on the intelligent traffic system is avoided;
alternatively: determining a congestion degree based on the saturation degree, and determining a customized travel suggestion under the condition that the congestion degree meets a target value;
preferably: the congestion degree is additionally severe congestion, moderate congestion, light congestion, unblocked and very unblocked;
the determining of the customized travel advice closest to the customized transportation request specifically comprises the following steps:
step SUB _ C1, taking the travel suggestion completely meeting the current customized traffic request as an initial travel suggestion, and setting the current travel suggestion to be equal to the initial travel suggestion;
step SUB _ C2, judging whether the traffic saturation allows the current travel suggestion, and if so, taking the current travel suggestion as the closest customized travel suggestion; otherwise, entering the next step;
step SUB _ C3, selecting an un-replaced travel SUB-condition with the strongest replaceability, judging whether all the travel SUB-conditions are completely replaced, if not, selecting an approximate travel SUB-condition to replace the current travel SUB-condition to form a current travel suggestion, and returning to the step SUB _ C2; if so, the customization fails;
when one travel sub-condition has a plurality of alternative options, a plurality of current travel suggestions may be formed, and one of the current travel suggestions may be selected as a customized travel suggestion output;
the intelligent computing module is used for determining whether to accept the customized traffic request of the user, and if so, requesting the traffic customization module to give a customized travel suggestion; if not, requesting the traffic prediction module to give a conventional travel suggestion;
preferably: the traffic request prediction module gives a travel suggestion, and the travel suggestion specifically comprises the following steps: giving a travel suggestion through a traffic prediction model, calculating the influence degree of the hidden special label on the travel suggestion, adjusting the travel suggestion based on the influence degree, and giving the adjusted travel suggestion;
the method comprises the following steps of calculating the influence degree of the hidden special label on the travel suggestion, specifically: calculating the influence degree of the hidden special label on the first historical travel information or the second historical travel information, and adjusting a travel suggestion based on the influence degree;
for example: hiding the special label to change the congestion degree from smooth to severe congestion, namely, the congestion degree is improved by 2 levels, and then, the travel suggestion given by the traffic prediction module is adjusted based on the rule; of course, the adjustment mode can also be the adjustment of a traffic mode and the like, and when the congestion degree is obviously improved, the recommended travel advice is necessarily adjusted;
the determining whether to accept the customized traffic request of the user specifically includes: if the customized traffic request can be met under the condition of ensuring the accuracy of the travel suggestion, the customized traffic request of the user is accepted; otherwise, not accepting; for example: if the travel suggestion is obtained completely according to the travel sub-conditions given in the request, and the accuracy of the travel suggestion meets the requirement, the travel suggestion is accepted; the accuracy here may be determined based on the judgment of the traffic congestion index, the travel route duration of the travel advice, and the like, or may be determined based on the degree to which the travel sub-conditions are replaced;
alternatively: the determining whether to accept the customized traffic request of the user specifically includes: determining whether to receive a customized traffic request of a user based on the registered amount of the customized traffic system; when the registration amount exceeds a preset value, the following steps are received, for example: over 90% of users use the customized transportation mode, and the customized mode is credible and feasible;
the step of determining whether to accept the customized traffic request of the user specifically comprises the following steps:
step SUB _ B1, extracting travel time information, traffic mode information and route information in the customized traffic request;
a step SUB _ B2 of determining a customization quantity related to said travel time and route; determining a predicted trip amount based on the trip time and route;
alternatively: the step SUB _ B2 specifically includes: determining the number of the traffic customization requests on the day as a customization amount; determining the predicted trip amount on the current day as the predicted trip amount;
preferably: determining a predicted traffic volume based on a first traffic prediction model;
step SUB _ B3, comparing the customized traffic volume CNM with the predicted traffic volume PNM, and receiving the customized traffic request of the user when the difference value ratio (PNM-CNM)/PNM is within a preset range; otherwise, not accept;
if the user does not accept the travel advice, the travel advice guarantee rate or the accuracy rate of the travel advice is lower than the accuracy rate of the customized travel mode close to 100%; certainly, on the premise of corresponding traffic rule guarantee, hardware setting guarantee and customization credit degree setting, the accuracy of the traffic request customization can be further improved;
alternatively, the step SUB _ B3 specifically includes: comparing the customized quantity CNM with the predicted traffic quantity PNM, and if the customized index (CNM/PNM) CPR + (1-CNM/PNM) ToTPR is greater than the customized index threshold (CPR + ToTPR)/2, receiving the customized traffic request of the user; otherwise, not accept;
wherein: CPR is the accuracy of the custom traffic module; for example: the accuracy rate of the customized traffic is considered to be 100% when each given travel suggestion can meet the non-congestion target, and the totrp is the accuracy rate of the traffic prediction module, which depends on the prediction accuracy rate of the first traffic prediction model;
based on the same inventive concept, the invention also provides a big data customized travel intelligent traffic control method, which comprises the following steps:
step S1: receiving a traffic customization request sent by a user through a mobile terminal;
step S2: determining whether a customized traffic request of a user is accepted, and if so, requesting a traffic customization module to give a customized travel suggestion; if not, requesting the traffic prediction module to give a conventional travel suggestion;
step S3: the user goes out based on the returned travel advice;
the terms "data processing apparatus", "data processing system", "user equipment" or "computing device" encompass all kinds of apparatus, devices and machines for processing data, including by way of example a programmable processor, a computer, a system on a chip, or a plurality or combination of the above. The apparatus can comprise special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit). The apparatus can include, in addition to hardware, code that creates an execution environment for the computer program, e.g., code that constitutes processor firmware, a protocol stack, a database management system, an operating system, a cross-platform execution environment, a virtual machine, or a combination of one or more of the above. The apparatus and execution environment may implement a variety of different computing model infrastructures, such as web services, distributed computing, and grid computing infrastructures.
A computer program (also known as a program, software application, script, or code) can be written in any form of programming language, including compiled or interpreted languages, declarative or procedural languages, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. The computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, subroutines, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers that are located at one site or distributed across multiple sites and interconnected by a communication network.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (10)
1. A big data-based customized travel intelligent transportation system, which is characterized by comprising: the system comprises a mobile terminal and an intelligent traffic module;
the intelligent transportation module includes: the system comprises a traffic prediction module, a traffic customization module, an interface module, an intelligent calculation module and a label calculation module;
the mobile terminal is used for enabling a user to send a customized traffic request to the intelligent traffic module and receive an intelligent traffic suggestion returned by the intelligent traffic module;
the intelligent traffic module is used for receiving a traffic customization request sent by a user, acquiring traffic prediction information and traffic customization information, obtaining an intelligent traffic suggestion through the intelligent calculation module, and returning the obtained intelligent traffic suggestion to the mobile terminal;
the interface module is used for receiving a customized traffic request sent by a user, analyzing the customized traffic request and sending the analyzed customized traffic request information to the intelligent calculation module, the traffic prediction module and the traffic customization module; the interface module is also used for submitting personal information for registration login through the mobile terminal by a user, and sending the submitted personal information to the intelligent transportation module for storage;
the analyzing the customized traffic request specifically comprises: acquiring user information and travel sub-conditions in the customized traffic request; the travel sub-conditions comprise request time, travel time information, traffic mode information, route information, a departure place and a destination;
the label calculation module is used for calculating label information of the customized traffic request based on the analyzed customized traffic request; sending the label information to a traffic prediction module;
the calculating of the tag information of the customized traffic request specifically includes: calculating to obtain label information based on the time information; extracting a basic label in the time information; extracting a conventional special label in the time information; the basic labels include year, month, day; conventional special labels include holidays, workdays, peak hours; extracting a hidden special label in the time information; and using a basic label, a conventional special label and a hidden special label as label information of the customized traffic request; wherein: the hidden special label is information which changes along with the change of time;
the method for extracting the hidden special label in the time information specifically comprises the following steps:
step SUB _ A1, obtaining search result information of travel time through search based on travel time information; the search is internet search, question and answer search and news search;
step SUB _ A2, extracting an event information set from the search result information;
a step SUB _ A3, determining an unprocessed event from the event information set, and determining whether the unprocessed event is a valid event; if yes, go back to step SUB _ A3; otherwise, taking the unprocessed event as a current event and entering the next step;
the determining whether the event is a valid event specifically includes: determining whether the event information is an input parameter of a first traffic prediction model in a current traffic prediction module;
step SUB _ A4, acquiring first historical trip information with the same event based on the current event information, judging a first influence degree of the current event information on the first historical trip information, and taking the event information as an extracted hidden special label when the first influence degree is greater than a preset influence degree; otherwise, when the first influence degree is smaller than or equal to a preset influence degree, determining the extracted hidden special label based on the combination of events;
the event-based merging determination of the extracted hidden special tags specifically includes: forming an event binary group by the current event and each non-current event in the event set; calculating a second degree of influence of each event binary group on second historical travel information, wherein: the second historical trip information is the first historical trip information related to two events in the event binary group; when more than one second influence degree is larger than a preset influence degree, selecting the event binary group corresponding to the largest second influence degree as the extracted hidden special label; when the current time does not exist, entering the next step;
calculating a first influence degree of the current event information on the first historical travel information, specifically: calculating a first degree of influence IDG based on the following formula;
wherein:
the prediction accuracy of the traffic prediction module in the ith historical travel information in the first historical travel information is shown, and the RPR is the preset accuracy; n is the number of pieces of historical travel information in the first historical travel information;
the calculating of the second degree of influence of each event binary group on the second historical travel information specifically includes: similarly, the formula (1) and the formula (2) are adopted to calculate a second degree of influence of the event binary group on the second historical travel information aiming at the historical travel information of the second binary event in the event binary group existing in the first historical travel record at the same time, namely the second historical travel information;
step SUB _ A5, judging whether all events are processed, if yes, ending, otherwise, returning to step SUB _ A3;
the label calculation module is also used for taking the hidden special label as a newly added input parameter of the traffic prediction module; training and updating the traffic prediction module based on the sample data containing the newly added input parameters;
the traffic prediction module is used for predicting traffic conditions based on the first traffic prediction model and giving out conventional travel suggestions based on prediction results; the first traffic prediction model predicts traffic conditions based on the basic labels and the conventional special labels;
the traffic prediction module also comprises a second traffic prediction model, when new input parameters are generated, the traffic prediction model creates a backup of the first traffic prediction model as the second traffic prediction model, performs new training on the second traffic prediction model based on the new input parameters, and replaces the first traffic prediction model with the second traffic prediction model when the training of the second traffic prediction model meets a target value;
the traffic customizing module is used for giving a customized travel suggestion corresponding to the customized traffic request;
the intelligent calculation module is used for determining whether to accept the customized traffic request of the user, and if so, requesting the traffic customization module to give a customized travel suggestion as an intelligent traffic suggestion; and if not, requesting the traffic prediction module to give a conventional travel suggestion as an intelligent traffic suggestion.
2. The big data based customized travel intelligent transportation system according to claim 1, wherein the intelligent transportation module is built on a big data platform.
3. The big data-based customized travel intelligent transportation system according to claim 2, wherein the number of the mobile terminals is one or more.
4. The big data-based customized travel intelligent transportation system according to claim 3, wherein the interface module is configured to provide a graphical user interface to the mobile terminal when receiving access from the mobile terminal, and form an intelligent transportation request after collecting customized transportation information written by the mobile terminal.
5. The big data-based customized travel intelligent transportation system according to claim 4, wherein the interface module is further configured to parse the customized transportation request and send the parsed customized transportation request information to the intelligent calculation module, the transportation prediction module and the transportation customization module.
6. A big data based customized travel intelligent transportation control method based on the big data based customized travel intelligent transportation system according to any one of claims 1-5, characterized by comprising the following steps:
step S1: receiving a traffic customizing request sent by a user through a mobile terminal;
step S2: determining whether a customized traffic request of a user is accepted, and if so, requesting a traffic customization module to give a customized travel suggestion; if not, requesting the traffic prediction module to give a conventional travel suggestion;
step S3: and the user goes out based on the returned travel advice.
7. The big data-based customized travel intelligent traffic control method according to claim 6, wherein the user sends the customized traffic request in a wireless manner.
8. A processor, characterized in that the processor is used for running a program, wherein the program is run to execute the big data based customized travel intelligent transportation control method according to any one of claims 6 to 7.
9. A computer-readable storage medium characterized by comprising a program which, when run on a computer, causes the computer to execute the big-data based customized travel intelligent traffic control method according to any one of claims 6-7.
10. An execution device, characterized in that it comprises a processor coupled with a memory, said memory storing program instructions, which when executed by said processor, implement the big data based customized travel intelligent transportation control method according to any one of claims 6 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210595131.3A CN114677839B (en) | 2022-05-29 | 2022-05-29 | Customized travel intelligent transportation system based on big data and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210595131.3A CN114677839B (en) | 2022-05-29 | 2022-05-29 | Customized travel intelligent transportation system based on big data and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114677839A CN114677839A (en) | 2022-06-28 |
| CN114677839B true CN114677839B (en) | 2022-08-16 |
Family
ID=82079278
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210595131.3A Active CN114677839B (en) | 2022-05-29 | 2022-05-29 | Customized travel intelligent transportation system based on big data and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114677839B (en) |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005149430A (en) * | 2003-11-20 | 2005-06-09 | Meipull Co Ltd | Historical touring guide system |
| US7831532B2 (en) * | 2004-11-16 | 2010-11-09 | Microsoft Corporation | Precomputation and transmission of time-dependent information for varying or uncertain receipt times |
| CN103236163B (en) * | 2013-04-28 | 2015-01-07 | 北京航空航天大学 | Traffic jam avoiding prompting system based on collective intelligence network |
| CN107331183A (en) * | 2017-07-14 | 2017-11-07 | 广州大正新材料科技有限公司 | Based on shared safe intelligent transportation method of servicing and system |
| CN110763248A (en) * | 2019-10-23 | 2020-02-07 | 北京市天元网络技术股份有限公司 | Travel route reservation and customization method, system, medium and equipment |
| CN111275965B (en) * | 2020-01-20 | 2021-02-05 | 交通运输部科学研究院 | Real-time traffic simulation analysis system and method based on internet big data |
| CN112665604A (en) * | 2020-12-31 | 2021-04-16 | 重庆文理学院 | Intelligent vehicle guiding platform |
| CN113570096A (en) * | 2021-08-04 | 2021-10-29 | 李镇 | Intelligent trip method and device based on big data |
-
2022
- 2022-05-29 CN CN202210595131.3A patent/CN114677839B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114677839A (en) | 2022-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mehmood et al. | Smart infrastructure and applications | |
| CN104121908B (en) | A kind of method and system of delay path planning | |
| CN112581106B (en) | Government affair event automatic order dispatching method fusing grid semantics of handling organization | |
| CN113570867B (en) | Urban traffic state prediction method, device, equipment and readable storage medium | |
| CN111524353A (en) | Method for traffic text data for speed prediction and travel planning | |
| CN109410576A (en) | Road condition analyzing method, apparatus, storage medium and the system of multisource data fusion | |
| Xiong et al. | An integrated and personalized traveler information and incentive scheme for energy efficient mobility systems | |
| Petrik et al. | Uncertainty analysis of an activity-based microsimulation model for Singapore | |
| CN114677839B (en) | Customized travel intelligent transportation system based on big data and control method thereof | |
| Raskar et al. | Modified fuzzy-based smart barricade movement for traffic management system | |
| Silva et al. | Solving a capacitated waste collection problem using an open-source tool | |
| Lin et al. | Insights into Travel Pattern Analysis and Demand Prediction: A Data-Driven Approach in Bike-Sharing Systems | |
| Liao et al. | Multi-modal sequence to sequence learning with content attention for hotspot traffic speed prediction | |
| CN116108970A (en) | Smart city sharing bicycle putting and operation area planning method and Internet of things system | |
| Buyvol et al. | Mobility and road safety improvement by optimizing smart city infrastructure parameters: a case study | |
| Hu et al. | Temporal-spatial prediction of trip demand using neural networks and points of interest | |
| Pozdnukov et al. | Demand Forecasting and Activity-based Mobility Modelling from Cell Phone Data | |
| Shan et al. | A novel personalized dynamic route recommendation approach based on pearson similarity coefficient in cooperative vehicle-infrastructure systems | |
| Li et al. | Research and application of the Beijing road traffic prediction system | |
| Pavleski et al. | In-Depth Evaluation of Reinforcement Learning Based Adaptive Traffic Signal Control Using TSCLAB | |
| CN114895982B (en) | Application calling method, system, equipment and storage medium based on user information | |
| Benmessaoud et al. | Neural Network Feature-Based System for Real-Time Road Condition Prediction | |
| Chang et al. | Driver compliance model under dynamic travel information with ATIS | |
| Mishima et al. | Is Adding More Modalities Better in a Multimodal Spatio-temporal Prediction Scenario? A Case Study on Japan Air Quality | |
| Wang et al. | A Rush-Hour Vehicles Scheduling Strategy in Online Car-Sharing System Based on Urban Trajectory Data Analysis |
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 |