CN108537691A - A kind of region visit intelligent management system and method - Google Patents
A kind of region visit intelligent management system and method Download PDFInfo
- Publication number
- CN108537691A CN108537691A CN201810588847.4A CN201810588847A CN108537691A CN 108537691 A CN108537691 A CN 108537691A CN 201810588847 A CN201810588847 A CN 201810588847A CN 108537691 A CN108537691 A CN 108537691A
- Authority
- CN
- China
- Prior art keywords
- data
- user
- passenger flow
- intensity
- travel path
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000009826 distribution Methods 0.000 claims abstract description 118
- 238000005457 optimization Methods 0.000 claims abstract description 70
- 238000004458 analytical method Methods 0.000 claims abstract description 50
- 230000002452 interceptive effect Effects 0.000 claims abstract description 35
- 230000006399 behavior Effects 0.000 claims description 31
- 230000006870 function Effects 0.000 claims description 30
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 10
- 230000003542 behavioural effect Effects 0.000 claims description 7
- 239000004744 fabric Substances 0.000 claims description 6
- 230000006698 induction Effects 0.000 claims description 5
- 230000003993 interaction Effects 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 238000013135 deep learning Methods 0.000 claims description 2
- 238000007726 management method Methods 0.000 description 34
- 238000010586 diagram Methods 0.000 description 7
- 238000005259 measurement Methods 0.000 description 7
- 238000000605 extraction Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000009825 accumulation Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000002948 stochastic simulation Methods 0.000 description 4
- 238000012790 confirmation Methods 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000013019 agitation Methods 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000005315 distribution function Methods 0.000 description 1
- 238000013467 fragmentation Methods 0.000 description 1
- 238000006062 fragmentation reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008929 regeneration Effects 0.000 description 1
- 238000011069 regeneration method Methods 0.000 description 1
- 230000002040 relaxant effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/14—Travel agencies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention proposes a kind of region visit intelligent management system and method, the system includes user interactive module, information acquisition module, data memory module, forecast analysis module and warning module, the system and method are based on the calculating and analysis for generating data to visit region, it makes prediction to the intensity of passenger flow distribution in visit region, the optimization travel path for making the estimated distribution characteristics of intensity of passenger flow level off to Optimum distribution feature is selected from travel path set, the optimization travel path is pushed to user, and it is provided to the user based on the optimization travel path and sells the management service bought including travel path reservation and admission ticket.Intelligent management system proposed by the present invention and method will can go sight-seeing tourist of the resources configuration optimization to corresponding visit demand in advance, alleviated from source using technological means or even solves the problems, such as that visit resource dispensing is unbalanced in region, greatly mitigate the government pressure in visit region, while so that the visit of tourist is experienced and being increased dramatically.
Description
Technical field
The present invention relates to smart travel and tourist's intelligent management service technology field, more particularly to a kind of gone sight-seeing to region is gone
System and method to carry out intelligent management.
Background technology
Smart travel is typically referred to Information and Communication Technology integrated application in travel industry, in Tourist Experience, tourism
The many aspects such as management, travel industry development bring the industry transformation process of more preferably effect and higher efficiency.Mobile Internet,
The development of the Information and Communication Technology such as GIS, Internet of Things, cloud computing platform, virtual reality and augmented reality is drawn in numerous areas
Play huge change agitation.Different industries are most significant in this technological change to be benefited, and comes from the resource updates speed of raising
Degree, makes people be expected to grasp real-time resource status, can be directed to real-time requirement and carry out more efficient supply configuration, to make not
It mutually matched with the relationship between resource, be connected and hinder, into internal value-added benign cycle.
In tourist industry, new technological means be in it is gradually universal during, people show in tourist resources, tourism
Information interchange, passenger flow analysing, speech guide, tourist are interactive, admission ticket is sold and buys management etc. and be made that many positive trials.Example
Such as, intelligent video camera head of the placement with " number identification " function at hinge is shunted in the entrance at scenic spot and important tourist, to scape
The intensity of passenger flow of each region and passenger flow direction monitor and estimate in real time in area, can assist in manager and grasp in scenic spot
Trip distribution dynamic contributes to the safety management at scenic spot, including timely water conservancy diversion to avoid tread event generation etc..
But in the development of wisdom, tourist industry is at present still in initial stage.It is tasted in spite of a large amount of new technological means
Examination expansion application in different ways in tourist industry, but their application direction is all more single, is presented in entire industry disconnected
Point form, in the form of fragmentation, decentralized, disordering based on, between each other without formed organically contact, there is no very well
Ground incorporates among industry situation, does not more touch the deep problems of tourism industry resources allocative efficiency.
This aspect is
Data information fail adequately to be analyzed and utilized, be not based on data resource and develop feasible science, the money of rule
Source optimization dispensing method.The imbalance of resource dispensing will produce many adverse consequences, such as in visit region, popularity is high
It is often overstaffed to go sight-seeing sight spot, is not only easy to cause safety problem, is less useful for the resource and Regenerated energy at protection sight spot itself
Power；On the other hand, the low visit sight spot of popularity usually be nobody shows any interest in, and cannot play the effect that its elasticity accommodates, or even therefore
Ignored in maintenance, is equally unfavorable for the protection and utilization at this kind of sight spot.
It solves the above problems from whole angle although still lacking as long as the several years has been developed in smart travel, in industry
Effective technology scheme, fail predictably that unbalanced visit sight spot resource and the diversified visit demand of tourist is mutual
Adaptation is got up.
Invention content
In order to solve the resource optimization matching problem in tourism industry, the development of smart travel is promoted into in-depth, the present invention
A kind of region visit intelligent management system and method are herein proposed, the system and method will go sight-seeing the visit sight spot in region
It is converted into overall data resource, and is regular feature by distribution shifts of all tourists in different sight spots, is swum by analyzing
The a variety of data informations look in region construct a kind of proactive guiding system using the analyzing and predicting method of big data
And method, so that tourist's distribution at different sight spots in region is tended to be more balanced.It, can be right in advance by the system and method
It goes sight-seeing resource and carries out reasonable distribution, alleviate from source and even solve the problems, such as that sight spot resource dispensing is unbalanced in region, greatly
Mitigate the government pressure in visit region, simultaneously because the equalization distribution of sight spot resource, also will bring tourist to go sight-seeing the big of experience
Width is promoted.
A kind of region visit intelligent management system proposed by the present invention includes user interactive module, information acquisition module and number
According to memory module, which is characterized in that the system also includes forecast analysis modules, wherein
The user interactive module is used to complete the function that interacts with user, and the function of the interaction includes,
Collect the visit demand of user；Based on the analysis result of the forecast analysis module, the prediction is pushed to user
The optimization travel path of analysis module output；And management clothes are provided to the user based on the optimization travel path confirmed through user
Business, the management service include that travel path reservation and admission ticket are sold and bought；
For described information acquisition module for acquiring real time data, the real time data includes user characteristic data, Yong Huhang
For data and visit region in intensity of passenger flow real-time estimation data, and by the intensity of passenger flow real-time estimation data export to
The data memory module；
For storing data, the data of storage include the travel path collection in excursion district domain to the data memory module
It closes data, is the preset weighted data of focus and intensity of passenger flow threshold data in visit region, the user characteristic data, described
User behavior data, the intensity of passenger flow real-time estimation data and user characteristics historical data, user behavior historical data and
Intensity of passenger flow historical data；
The forecast analysis module includes optimization computing module and prediction recommending module, wherein
The optimization computing module is obtained by the comprehensive analysis to data in the data memory module in visit region
The Optimum distribution feature of intensity of passenger flow, wherein the data for analysis include the intensity of passenger flow historical data, user spy
Levy historical data, the preset weight and intensity of passenger flow threshold data of the user behavior historical data and the focus；
The prediction recommending module obtains one timing of future by the comprehensive analysis to data in the data memory module
The estimated distribution characteristics of intensity of passenger flow in section, and the estimated distribution for making the intensity of passenger flow is selected from the travel path set
Feature levels off to the optimization travel path of the Optimum distribution feature, and the optimization travel path is exported to the user and is interacted
Module, wherein the data for analysis include the user characteristics real time data, the user behavior real time data, the user
Characteristic history data, the user behavior historical data, the intensity of passenger flow real-time estimation data, the travel path set number
According to this and the preset weighted data and intensity of passenger flow threshold data of the focus.
According to one preferred embodiment of the present invention, the system also includes warning module, the warning module is used for described
The estimated distribution characteristics of intensity of passenger flow and the intensity of passenger flow real-time estimation data are monitored, pre- when the intensity of passenger flow
When the peak value of score cloth or the intensity of passenger flow real-time estimation data exceed the intensity of passenger flow threshold value of focus, send out respectively
The Real-time Alarm signal that passenger flow has transfinited the Caution And Warning signal or passenger flow that transfinite.
According to one preferred embodiment of the present invention, the optimization computing module further includes user characteristics classification submodule and visit
Route classification submodule, user characteristics classification submodule by the analysis to data in the data memory module, to
Family set carries out the classification of feature based；The travel path classifies submodule based on to data in the data memory module
Travel path set is divided into according to the classification that user characteristics classification submodule is made and meets respective classes by analysis
The travel path subclass of user characteristics, the classification of user's set and the travel path subclass are for predicting recommending module
It uses.
According to one preferred embodiment of the present invention, wherein the optimization computing module and/or the prediction recommending module are to institute
It includes statistical induction method and machine learning method to state the method that the data in data memory module are analyzed.
According to one preferred embodiment of the present invention, wherein the machine learning method include regression algorithm, it is clustering algorithm, artificial
Neural network algorithm, deep learning algorithm and nitrification enhancement.
According to one preferred embodiment of the present invention, the Optimum distribution feature and the prediction distribution be characterized as characteristic function or
Characteristic parameter.
According to one preferred embodiment of the present invention, the Optimum distribution feature and the prediction distribution feature include visit region
Global characteristics and focus local feature.
Region visit intelligent management includes the following steps：
Information collection step, is acquired real time data, and the real time data includes user characteristic data, user behavior
Intensity of passenger flow real-time estimation data in data and visit region；
Visit area data is stored in data memory module by data storing steps, and the data include excursion district domain
Travel path collective data, visit region in focus preset weight and intensity of passenger flow threshold data, the user characteristics
Data, the user behavior data, the intensity of passenger flow real-time estimation data and user characteristics historical data, user behavior
Historical data and intensity of passenger flow historical data；
Forecast analysis step, the forecast analysis step include optimization calculating step and predict recommendation step, wherein
The optimization calculates step by analyzing the data in the data memory module, show that visit region middle reaches visitor is close
The Optimum distribution feature of degree, wherein it includes that the intensity of passenger flow historical data, the user characteristics are gone through that the optimization, which calculates data,
The preset weighted data and intensity of passenger flow threshold data of history data, the user behavior historical data and the focus；
The prediction recommendation step obtains visitor in following certain period by analyzing the data in the data memory module
The estimated distribution characteristics of current density, and selection makes the estimated distribution characteristics of the intensity of passenger flow become from the travel path set
Be bordering on the optimization travel path of the Optimum distribution feature, wherein the prediction recommending data include the user characteristic data,
The user behavior data, the user characteristics historical data, the user behavior historical data, the intensity of passenger flow are estimated in real time
Count according to, the preset weighted data and intensity of passenger flow threshold data of the travel path collective data and the focus；
User's interactive step, for completing the function that is interacted with user, the function of the interaction includes,
Collect the visit demand of user；Based on the analysis result of the forecast analysis module, the prediction is pushed to user
The optimization travel path of analysis module output；And management clothes are provided to the user based on the optimization travel path confirmed through user
Business, the management service include that travel path reservation and admission ticket are sold and bought.
According to one preferred embodiment of the present invention, this method further includes warning step, and the warning step is close to the passenger flow
The estimated distribution characteristics and the intensity of passenger flow real-time estimation data of degree are monitored, when the estimated distribution of the intensity of passenger flow
Peak value or the intensity of passenger flow real-time estimation data exceed focus the intensity of passenger flow threshold value when, send out respectively passenger flow will
The Real-time Alarm signal that the Caution And Warning signal or passenger flow to transfinite has transfinited.
According to one preferred embodiment of the present invention, the optimization calculates step and/or the prediction recommendation step to the number
What is calculated and analyzed according to the data in memory module includes statistical induction method and machine learning method.
Region visit intelligent management system proposed by the present invention and method, by the abundant profit for generating data to visit region
It is analyzed, the tourist resources gone sight-seeing in region can be linked to each other with comprehensive, integration is the orderly information of a tissue
Body, and by the methods of the statistical induction in data analysis, differentiate the connection between the visit behavior of a large amount of tourists and tourist resources
It is rule.This contact rule be used to formulate the objective measure standard of tourist resources optimization distribution, and further combined with data
Prediction technique in analysis just carries out tending to distribute rationally at the beginning of the visit behavior of tourist generates to the travel path of tourist
Guiding.A large amount of tourists are gone sight-seeing with this make the best use of the situation of process makes the dispensing optimization of tourist resources in Tour region weigh mark
Standard can not only mitigate the government pressure in visit region from source, can more tourist resources be made to be utilized effectively, be conducive to travel
The protection and regeneration of resource are conducive to the visit experience for greatly improving tourist.
Description of the drawings
Fig. 1 is the system architecture block diagram of the embodiment of the present invention one；
Fig. 2 is the specific function structure chart of system of the embodiment of the present invention one；
Fig. 3 is the system architecture block diagram of the embodiment of the present invention two；
Fig. 4 is the specific function structure chart of system of the embodiment of the present invention two；
Fig. 5 is the method flow Organization Chart of the embodiment of the present invention three；
Fig. 6 is that the method for the embodiment of the present invention three predicts recommendation step particular flow sheet；
Fig. 7 is the function schematic diagram that the embodiment of the present invention three uses；
Fig. 8 is the Function Fitting schematic diagram that the embodiment of the present invention three uses；
Specific implementation mode
To make the objectives, technical solutions, and advantages of the present invention clearer, right in the following with reference to the drawings and specific embodiments
The present invention is described in detail.
It should be noted that in term of the invention in use, " focus " indicates that tourist concentrates small in visit region
Range areas, such as sight spot, place of interest, narrow and unique crossing, concentrate relaxing area etc..In some embodiments, " concern
Point " can be reduced to refer to sight spot or place of interest, be used with sight spot or place of interest intercommunication.
Embodiment one
Fig. 1 is the system architecture block diagram of the embodiment of the present invention one.As shown in Figure 1, the system include user interactive module 1,
Predict recommending module 21, optimization computing module 22, data memory module 3, information acquisition module 5 and warning module 4.Wherein predict
Recommending module 21 and optimization computing module 22 collectively form forecast analysis module (not shown).
User interactive module 1 is completed to carry out the various functions of information exchange with user, including in use information acquisition module 5
The acquisition mode of setting acquires user's characteristic information, such as proposes the phases such as number, age, visiting time, visit demand to user
The problem of pass, and the answer feedback of user is collected to information acquisition module 5；Further include that will predict the optimization that recommending module 21 exports
Travel path recommends user, user confirm travel path after, according to the confirmation message of user provide to the user path reservation,
Admission ticket sells buy Deng interactive services；Further comprise that the relevant interactive function of other management services, for example, user's progress path are led
Boat and/or time limit remind, early warning diffluent information are pushed to user, is pushed to user and goes sight-seeing relevent information information etc..
Information acquisition module 5 using a variety of known ways to user information data, visit region Trip distribution data etc. with
The data of time change are acquired in real time, further include optionally the real-time preprocessing functions of data such as intensity of passenger flow distribution estimation；
And by the data collected or by pretreated data output in real time to data memory module 3.
Data memory module 3 is for storing all types of data caused by visit region.Such as including information acquisition module 5
The real time data of input further includes the characteristic information data for going sight-seeing each focus in region, goes sight-seeing the travel path set number in region
According to and user's history data and intensity of passenger flow distribution historical data etc..
Optimization computing module 22 is under the jurisdiction of forecast analysis module, includes above-mentioned non-reality for analyzing data memory module 3
When data Various types of data, the regularization feature of intensity of passenger flow distribution, and comprehensive institute is calculated by the methods of clustering, being fitted
It states distribution characteristics and goes sight-seeing the information data in region, obtain Optimal Distribution form of the intensity of passenger flow in visit region；Further include
User is collected based on more complete historical data and carries out tagsort, and travel path set is carried out corresponding to user characteristics
The classification of classification.
Prediction recommending module 21 is also under the jurisdiction of forecast analysis module, by preengaging superposition, stochastic simulation or machine learning
The methods of analysis calculating is carried out to the Various types of data in data memory module 3, estimate the passenger flow of visit region following a period of time
Density Distribution, and based on the real time data in data memory module 3, to meeting the visit road in the travel path subclass of demand
Diameter is assessed, and must be sent as an envoy to and be estimated intensity of passenger flow distribution closest to the visit road of Optimal Distribution form in optimization computing module 22
Diameter, in this, as optimization travel path, output to user interactive module confirms for user.
Warning module 4 is to the visit region Trip distribution real time data and prediction recommending module 21 in information acquisition module
In intensity of passenger flow distribution estimated data be monitored, when the former exceed focus intensity of passenger flow threshold value when send out Real-time Alarm
Information sends out Caution And Warning information when the latter exceeds the intensity of passenger flow threshold value of focus；The warning information is supplied to visit
Regional managers and/or tourist use, and assist the shunting guiding work for avoiding peak passenger flow.
Above-mentioned module and its between relationship constitute the present invention region visit intelligent management system embodiment one base
This framework.
Fig. 2 is the specific function structure chart of system of the embodiment of the present invention one.As shown in Fig. 2, system, which includes user, interacts mould
Block 1100, prediction recommending module 1210, optimization computing module 1220, information acquisition module 1300, data memory module 1500 with
And warning module 1400.
Wherein, user interactive module 1100 includes user oriented interactive interface 1101 and management service submodule 1102.
User oriented interactive interface 1101 interacts under the scenes such as such as booking, inquiry, navigation and early warning with user, according to
The acquisition mode set in information acquisition module acquires characteristic information input by user for example, by modes such as question and answer, including works as
Number, age, visiting time, visit demand of preceding user etc., and recommendation paths are presented to the user for confirming；It provides to the user
The interactive services such as navigation and early warning, sight spot introduction；The information of reception enters data memory module by information acquisition module
1500.The reserve route that management service submodule 1102 receives user confirms as a result, providing corresponding management clothes to the user accordingly
Business, including provides the visit region admission ticket of period corresponding to reserve route, admission ticket containing papery, electronic entrance ticket or get tickets electronics according to
According to, and collect corresponding expense etc..
Information acquisition module 1300 includes user information acquisition submodule 1301, user characteristics Q＆A (i.e. question and answer) submodule
1302 and intensity of passenger flow in real time acquisition with estimation submodule 1303.User information acquires submodule 1301 by user oriented
Interactive interface 1101 collects the characteristic informations such as visit demand input by user and reserve route confirms, practical travel path, looks into
The behavioural informations such as inquiry, navigation needs, and it is exported respectively to data memory module 1500.User characteristics Q＆A submodules 1302
The relevant issues of user characteristics and behavior are set, are called for user oriented interactive interface 1101.Intensity of passenger flow in real time acquisition with
Estimate that submodule 1303 utilizes prior art means, such as intelligent video camera head, GPS positioning mode, acquisition in real time and/or estimation are each
The intensity of passenger flow distribution situation of focus exports the real-time estimation situation that the intensity of passenger flow is distributed to data memory module
1500。
Data memory module 1500 includes that User Information Database 1510, visit area information database 1520 and passenger flow are close
Spend distributed data base 1530.Wherein, the data that User Information Database 1510 stores include that user information acquires submodule 1301
The active user's characteristic 1511 and active user's behavioral data 1513 that acquire and input in real time, and accumulation user characteristics
Historical data 1512 and user behavior historical data 1514.The data for going sight-seeing 1520 storage of area information database include excursion district
The preset weighted data 1521 of focus, focus intensity of passenger flow threshold data 1522 and travel path collective data in domain
1523.The data that intensity of passenger flow distributed data base 1530 stores include that intensity of passenger flow acquisition in real time is inputted with estimation submodule 1303
Intensity of passenger flow distribution real time data 1531 and accumulation intensity of passenger flow distribution history data 1532.
It includes user characteristics grader 1221, travel path grader 1222 and optimal passenger flow to optimize computing module 1220
Density Distribution computational submodule 1223.
Wherein, user characteristics grader 1221 carries out user complete or collected works to be based on different spies using historical use data as foundation
The cluster of sign, for example, by clustering algorithm generate based on different visit durations, different interest preferences, different age brackets,
The cluster classification of different visit purposes and different visit attributes (tourist group, individual traveler's visit, family go on a tour) etc..
Travel path grader 1222 is based on travel path collective data 1523, according to user characteristics grader 1221
Travel path set, the travel path for meeting the user characteristics accordingly clustered is divided into according to different characteristic by the cluster classification made
Subclass；Meet 2 hours, 3 hours, 4 hours, 5 hours, 6 hours for example, by total visit duration being divided into travel path set
Five travel path subclass, or for example go on a tour by tourist group, lovers, friend goes on a tour, respect the aged people go on a tour, parent-offspring goes on a tour will go sight-seeing road
Diameter set, which is divided into, meets five travel path subclass of above-mentioned category feature, etc..
Optimal intensity of passenger flow distribution computational submodule 1223 is by the methods of Function Fitting, machine learning to intensity of passenger flow point
Cloth historical data 1532 is analyzed, and the regularization feature of intensity of passenger flow distribution, and the comprehensive regularization feature is calculated
With visit zone information data, such as the preset weighted data 1521 of focus and focus intensity of passenger flow threshold data 1522, really
Surely visit region intensity of passenger flow Optimum distribution feature φ daily in different visit seasons0。
Predict that recommending module 1210 includes user characteristics extraction and matched sub-block 1211, intensity of passenger flow distribution optimization submodule
Submodule 1213 is estimated in block 1212 and intensity of passenger flow distribution.
Wherein, with matched sub-block 1211 by reading active user's characteristic 1511, extraction is worked as user characteristics extraction
The feature of preceding user simultaneously classifies to user, then chooses in travel path grader 1222 and belongs to the visit road accordingly classified
Diameter, as the travel path subclass with active user's characteristic matching.The corresponding classification can be single classification, can also be
The intersection of a variety of classification.
Intensity of passenger flow distribution estimates submodule 1213 and carries out analysis calculating to the Various types of data in data memory module 1500,
The intensity of passenger flow that visit region following a period of time is estimated using the methods of reservation superposition, stochastic simulation or machine learning is distributed,
Such as historical data is preengage according to the day in user behavior historical data 1514, the superposition of reservation intensity of passenger flow distribution is carried out,
Feature φ is estimated to obtain the intensity of passenger flow distribution under this day current reservation number statem0。
Intensity of passenger flow distribution optimization submodule 1212 extracts user characteristics to be met with what is chosen in matched sub-block 1211
Each travel path in the travel path subclass of current demand is assessed, and spy is estimated in the increment intensity of passenger flow that must send as an envoy to distribution
Levy φxIt is distributed intensity of passenger flow Optimum distribution feature φ in computational submodule 1223 closest to optimal intensity of passenger flow0Travel path
P0, as optimize travel path, and the path and its corresponding visit information are pushed to user oriented interactive interface 1101 and supplied
User confirms.One of the mode of the assessment, such as the tourist by traversing active user's number m are closed by above-mentioned subsets of paths
In each path when, distribution phi is estimated to each place of interest intensity of passenger flowm0After generating different increments, the increment of each place of interest
Distribution characteristics φxWith Optimum distribution feature φ0The path P of gap minimum0, travel path as an optimization.Specific implementation is shown
Example can be found in the detailed description to intelligent management in embodiment three.
Warning module 1400, which includes passenger flow, transfinites Caution And Warning submodule 1401 and passenger flow transfinites Real-time Alarm submodule
1402.Wherein, the passenger flow Caution And Warning submodule 1401 that transfinites estimates the excursion district that submodule 1213 estimates to intensity of passenger flow distribution
Domain future a period of time intensity of passenger flow distribution peaks information be monitored, when estimate peak value be more than focus intensity of passenger flow threshold
When value, forecast warning message is sent out to manager and/or tourist, assists shunting management in advance；Passenger flow transfinites Real-time Alarm submodule
Block 1402 is monitored intensity of passenger flow distribution real time data 1531, when real-time intensity of passenger flow is more than the intensity of passenger flow threshold of focus
When value, real-time alerting information is sent out to manager and/or tourist, assists shunting management in real time.
By the structure of above-mentioned specific module, the region visit intelligent management system of the embodiment of the present invention one can be abundant
On the basis of multiple types of data, the intensity of passenger flow distribution to going sight-seeing region, which is made, meets estimating for objective law,
And optimization travel path is selected for tourist in a manner of the measurement for meeting objective standard, make a large amount of tourists via optimization travel path
Guiding is intended to more balancedly be distributed in visit region, is more preferably adapted between visit resource and tourist demand to realize
State.
Embodiment two
Fig. 3 is the system architecture block diagram of the embodiment of the present invention two.Compared with embodiment one, embodiment two reduces early warning mould
Block is suitble to include planning and guiding towards wide area tourist resources, such as the overall arrangement of provincial tourist resources, or transprovincially travels
The occasions insensitive to large-scale tourist attraction threshold value such as the planning recommendation in path.In this case, term " focus " can be with
Refer to residence time more long place, such as scenic spot, special dining room etc. with visit value.In addition, embodiment two is equally
It is suitble to include using as service planning system in the region of sight spot.
As shown in figure 3, the system architecture of embodiment two includes user interactive module 201, prediction recommending module 2021, optimization
Computing module 2022, data memory module 203, information acquisition module 205.Wherein prediction recommending module 2021 and optimization calculates mould
Block 2022 collectively forms forecast analysis module (not shown).
Similar to embodiment one, in the system architecture of embodiment two, user interactive module 201 is completed to carry out letter with user
The various functions of interaction are ceased, including the acquisition mode acquisition user's characteristic information being arranged in use information acquisition module 205, such as
The related problem such as number, age, visiting time, visit demand is proposed to user, and collects the answer feedback of user to information
Acquisition module 205；Further include that will predict that the optimization travel path that recommending module 2021 exports recommends user, confirms in user and swim
It lookes at behind path, path reservation is provided to the user according to the confirmation message of user, admission ticket is sold and the interactive services such as buys；Further comprise it
The relevant interactive function of his management service, for example, user carry out path navigation and/or the time limit reminds, pushes visit phase to user
Close information etc..
Information acquisition module 205 is using a variety of known ways to user information data, visit region Trip distribution data etc.
The data changed over time are acquired in real time, further include optionally that the data such as intensity of passenger flow distribution estimation pre-process work(in real time
Energy；And by the data collected or by pretreated data output in real time to data memory module 203.
Data memory module 203 is for storing all types of data caused by visit region.Such as including information collection mould
The real time data that block 205 inputs further includes the characteristic information data for going sight-seeing each focus in region, goes sight-seeing the travel path collection in region
Close the historical data etc. of data and user's history data and intensity of passenger flow distribution.
Optimization computing module 2022 is under the jurisdiction of forecast analysis module, includes above-mentioned for analyzing data memory module 203
The regularization feature of intensity of passenger flow distribution is calculated by the methods of clustering, being fitted in the Various types of data of non-real-time data, and comprehensive
It closes the distribution characteristics and goes sight-seeing the information data in region, obtain Optimal Distribution form of the intensity of passenger flow in visit region；Also
Progress tagsort is collected to user including being based on more complete historical data, and travel path set is carried out corresponding to user
The classification of feature classification.
Prediction recommending module 2021 is also under the jurisdiction of forecast analysis module, by preengaging superposition, stochastic simulation or engineering
The methods of habit carries out analysis calculating to the Various types of data in data memory module 203, estimates visit region following a period of time
Intensity of passenger flow is distributed, and based on the real time data in data memory module 203, to meeting in the travel path subclass of demand
Travel path is assessed, and must be sent as an envoy to and be estimated intensity of passenger flow distribution closest to Optimal Distribution form in optimization computing module 2022
Travel path, in this, as optimization travel path, output to user interactive module for user confirm.
Above-mentioned module and its between relationship constitute the present invention region visit intelligent management system embodiment two base
This framework.
Fig. 4 is the specific function structure chart of system of the embodiment of the present invention two.As shown in figure 4, system, which includes user, interacts mould
Block 2100, prediction recommending module 2210, optimization computing module 2220, information acquisition module 2300 and data memory module
2500。
Wherein, user interactive module 2100 includes user oriented interactive interface 2101 and management service submodule 2102.
User oriented interactive interface 2101 interacts under the scenes such as such as booking, inquiry, navigation and early warning with user, according to
The acquisition mode set in information acquisition module acquires characteristic information input by user for example, by modes such as question and answer, including works as
Number, age, visiting time, visit demand of preceding user etc., and recommendation paths are presented to the user for confirming；It provides to the user
The interactive services such as navigation and sight spot introduction；The information of reception enters data memory module 2500 by information acquisition module.Pipe
Reason Attendant sub-module 2102 receives the reserve route confirmation of user as a result, providing corresponding management service to the user accordingly, including
The visit region admission ticket of period corresponding to reserve route, admission ticket containing papery, electronic entrance ticket or electronics foundation of getting tickets are provided, and is collected
Corresponding expense etc..
Information acquisition module 2300 includes user information acquisition submodule 2301, user characteristics Q＆A (i.e. question and answer) submodule
2302 and intensity of passenger flow in real time acquisition with estimation submodule 2303.User information acquires submodule 2301 by user oriented
Interactive interface 2101 collects the characteristic informations such as visit demand input by user and reserve route confirms, practical travel path, looks into
The behavioural informations such as inquiry, navigation needs, and it is exported respectively to data memory module 2500.User characteristics Q＆A submodules 2302
The relevant issues of user characteristics and behavior are set, are called for user oriented interactive interface 2101.Intensity of passenger flow in real time acquisition with
Estimate that submodule 2303 utilizes prior art means, such as intelligent video camera head, GPS positioning mode, acquisition in real time and/or estimation are each
The intensity of passenger flow distribution situation of focus exports the real-time estimation situation that the intensity of passenger flow is distributed to data memory module
2500。
Data memory module 2500 includes that User Information Database 2510, visit area information database 2520 and passenger flow are close
Spend distributed data base 2530.Wherein, the data that User Information Database 2510 stores include that user information acquires submodule 2301
The active user's characteristic 2511 and active user's behavioral data 2513 of input, and accumulation user characteristics historical data
2512 and user behavior historical data 2514.The data for going sight-seeing 2520 storage of area information database include the pass in the domain of excursion district
The preset weighted data 2521 of note point, focus intensity of passenger flow threshold data 2522 and travel path collective data 2523.Passenger flow
The data that Density Distribution database 2530 stores include that intensity of passenger flow acquires and estimates that the passenger flow that submodule 2303 inputs is close in real time
Degree distribution real time data 2531 and the intensity of passenger flow distribution history data 2532 of accumulation.
It includes user characteristics grader 2221, travel path grader 2222 and optimal passenger flow to optimize computing module 2220
Density Distribution computational submodule 2223.
Wherein, user characteristics grader 2221 carries out user complete or collected works to be based on different spies using historical use data as foundation
The cluster of sign, for example, by clustering algorithm generate based on different visit durations, different interest preferences, different age brackets,
The cluster classification of different visit purposes and different visit attributes (tourist group, individual traveler's visit, family go on a tour) etc..
Travel path grader 2222 is based on travel path collective data 2523, according to user characteristics grader 2221
Travel path set, the travel path for meeting the user characteristics accordingly clustered is divided into according to different characteristic by the cluster classification made
Subclass；Meet 2 hours, 3 hours, 4 hours, 5 hours, 6 hours for example, by total visit duration being divided into travel path set
Five travel path subclass, or for example go on a tour by tourist group, lovers, friend goes on a tour, respect the aged people go on a tour, parent-offspring goes on a tour will go sight-seeing road
Diameter set, which is divided into, meets five travel path subclass of above-mentioned category feature, etc..
Optimal intensity of passenger flow distribution computational submodule 2223 is by the methods of Function Fitting, machine learning to intensity of passenger flow point
Cloth historical data 2532 is analyzed, and the regularization feature of intensity of passenger flow distribution, and the comprehensive regularization feature is calculated
With visit zone information data, such as the preset weighted data 2521 of focus and focus intensity of passenger flow threshold data 2522, really
Surely visit region intensity of passenger flow Optimum distribution feature φ daily in different visit seasons0。
Predict that recommending module 2210 includes user characteristics extraction and matched sub-block 2211, intensity of passenger flow distribution optimization submodule
Submodule 2213 is estimated in block 2212 and intensity of passenger flow distribution.
Wherein, with matched sub-block 2211 by reading active user's characteristic 2511, extraction is worked as user characteristics extraction
The feature of preceding user simultaneously classifies to user, then chooses in travel path grader 2222 and belongs to the visit road accordingly classified
Diameter, as the travel path subclass with active user's characteristic matching.The corresponding classification can be single classification, can also be
The intersection of a variety of classification.
Intensity of passenger flow distribution estimates submodule 2213 and carries out analysis calculating to the Various types of data in data memory module 203,
The intensity of passenger flow that visit region following a period of time is estimated using the methods of reservation superposition, stochastic simulation or machine learning is distributed,
Such as historical data is preengage according to the day in user behavior historical data 2514, the superposition of reservation intensity of passenger flow distribution is carried out,
Feature φ is estimated to obtain the intensity of passenger flow distribution under this day current reservation number statem0。
Intensity of passenger flow distribution optimization submodule 2212 extracts user characteristics to be met with what is chosen in matched sub-block 2211
Each travel path in the travel path subclass of current demand is assessed, and spy is estimated in the increment intensity of passenger flow that must send as an envoy to distribution
Levy φxIt is distributed intensity of passenger flow Optimum distribution feature φ in computational submodule 2223 closest to optimal intensity of passenger flow0Travel path
P0, as optimize travel path, and the path and its corresponding visit information are pushed to user oriented interactive interface 2101 and supplied
User confirms.One of the mode of the assessment, such as the tourist by traversing active user's number m are closed by above-mentioned subsets of paths
In each path when, distribution phi is estimated to each place of interest intensity of passenger flowm0After generating different increments, the increment of each place of interest
Distribution characteristics φxWith Optimum distribution feature φ0The path P of gap minimum0, travel path as an optimization.Specific implementation is shown
Example can be found in the detailed description to intelligent management in embodiment three.
By the structure of above-mentioned specific module, the region visit intelligent management system of the embodiment of the present invention two can be fully sharp
With multiple types of data, make a large amount of tourists via the guiding of optimization travel path, is intended to more balancedly divide in visit region
Cloth, to realize better adaptation state between visit resource and tourist demand.
Embodiment three
Fig. 5 is that intelligent management process structure figure is gone sight-seeing in the region of the embodiment of the present invention three.As shown in figure 5, this method
Process structure it is as follows.
Step 001, visit area information database is established, wherein the feature comprising focus in visit region and visit road
The feature of diameter, the feature of focus is such as including numbering, average visiting time, intensity of passenger flow threshold value, preset weight；Go sight-seeing road
The feature of diameter such as include by focus and focus between travelling route spent by time.
One simply example is to go sight-seeing area information with the scenic spot of 5 places of interest (being focus in this instance)
Data in database include：
Each place of interest ViNumber N=[1,2,3,4,5]；
Each place of interest ViAverage visiting time be set as vector T=[10,15,10,30,15] (unit：Minute)；
Each place of interest ViThe intensity of passenger flow threshold value that can be accommodated simultaneously is respectively ρTH=[200,200,300,500,150]
(unit：People/point)；
Consider popularity and protection (sets popularity：V4>V3>V1>V2=V5；Protection：V4>V5>V2>V1=
V3), preset weight is Θ=[3,4,2,5,5]；For preset weight for example for shunting, i.e., preset weight is higher herein, and shunting is excellent
First grade is higher；
If each place of interest ViThe minimum sampling step length Δ T of intensity of passenger flow distribution function is 1 minute.
Each path can be expressed as the passenger flow being distributed in the intensity of passenger flow of each related place of interest in special time period
Increment, such as：
Pj=[10,0,30,0,90]
It indicates, if there is m tourists are since t moment, along the j-th strip path to advance, then entering visit region 10 will divide
After clock reach the 1st place of interest, be the 1st place of interest intensity of passenger flow at the t+10 moment, bring 10 minutes m people's increments；30
The 3rd place of interest of arrival after minute is the 3rd place of interest at the t+30 moment, brings 10 minutes m people's increments；It is arrived after 90 minutes
It is the 5th place of interest at the t+90 moment up to the 5th place of interest, brings 15 minutes m people's increments.It is exemplary purpose herein, it will
Time is reduced to average, but the option for taking other expression ways is not precluded.
Step 002, using the intensity of passenger flow distributed data of historical accumulation, intensity of passenger flow distributed data base is established.
Step 003 is that optimization calculates step.
The step including the use of the analysis to intensity of passenger flow distribution history data, establishes intensity of passenger flow historical rethinking first
Rule model.
Herein only as example, made using common normal distribution (Gaussian Profile) function as shown in Figure 7 of art of mathematics
Data fitting is carried out for basic function, however not excluded that takes the option of other modes analysis of history data.For example, it is also possible to using machine
Device learning method is analyzed and is fitted to data.
Herein by taking two kinds of rule models as an example：Focus partial model and visit region block mold.
Focus partial model is a kind of model for weighing each focus optimum state.Herein only as an example, setting every
A focus intensity of passenger flow model is the superposition of two normal distributions, as shown in Function Fitting schematic diagram in Fig. 8.After fitting,
Two Normal Distribution Characteristics functions are obtained, respectively there is peak value ρiM1、ρiM2With halfwidth TiHW1、TiHW2.Due to ρiM1>ρiM2, TiHW1
<TiHW2, herein to put it more simply, selecting more crucial TiHW1And/or ρiM1Feature φ is weighed as an optimization0。
Visit region block mold is then a kind of model of optimum state that weighing visit region entirety, using when each
Between put the inhomogeneities of Trip distribution between each focus as measurement index.Herein only as example, such as by each pass
The difference of the instantaneous intensity of passenger flow and mean value of noting point is multiplied by what the normalization root mean square of institute's value after preset weight changed over time
Curve S (t), the measurement index as inhomogeneities rule.
Then, it will assess and determine in this step optimum state feature.
In focus partial model, using the optimum state of each place of interest as standard, the optimum state of i-th of place of interest
Parameter is：
φi0=[TigHW1,ρigM1]
φi0Determination it is related to preset weight and intensity of passenger flow threshold value.The higher focus of preset weight, optimal halfwidth
It is bigger, for example, 2.2 hours；The bigger focus of intensity of passenger flow threshold value, optimal peak value are higher.Except initial stage is preset
Outside, the numerical value of optimal halfwidth and/or optimal peak value will be also advanced optimized by more multidata rollback and verification.Optimal shape
The measurement of state is not limited thereto, such as in the case where calculation power is had a surplus, it is also an option that the matched curve conduct by optimization
The modes such as optimum state function.
In going sight-seeing region block mold, using the scenic spot entirety uniformity as measurement standard, such as full excursion district can be obtained
The optimum state parameter in domain is：
φ0=Sg
Wherein in order to which simplification example illustrates, by φ0It is taken as the inhomogeneities curve S by optimization0(t) peak value Sg, but simultaneously
It is not excluded for other standards setting means, for example, by using the inhomogeneities curve S by optimization0(t) itself is as optimum state letter
The modes such as number.
In addition, in this step also user's history number will be based on by user characteristics grader and travel path grader
According to travel path collective data, the classification by feature carried out to user and travel path, is formed mutual with different user feature
Corresponding travel path subclass.
For example, a kind of mode classification characterized by visiting time is：There are 2 hours 3, paths in set of paths, 3 is small
When 3, path, 4 hours 5, paths, 5 hours 8, paths, 6 hours 6, paths, 7 hours 5, paths, totally 6 subsets of paths
It closes；
In another example another mode classification characterized by user property is：It is suitble to 2, the path of tourist group user, fits
8, the path of domestic consumer is closed, 5, the path containing old man user is suitble to, is suitble to 7, the path of parent-offspring user, is suitble to lovers' trip
6, the path of objective user, totally 5 subsets of paths conjunctions；It optionally, will be regarding different needs and further directed to the feature of different user
Adjust preset weight matrix Θg。
User opens interactive interface in step 004.Then, by the trip by interactive interface to user in step 005
The characteristics such as demand of looking at are collected, and analyze the type belonging to the user accordingly, and thereby determine that the affiliated type of suitable user
Travel path subclass.
Next, by the prediction recommendation step particular flow sheet of the embodiment of the present invention three with reference to shown in figure 6, prediction is recommended
Step 006 is described in detail.The detailed process is given for example only, however not excluded that the choosing of said function is completed using other modes
.
As shown in fig. 6, in prediction recommendation step, 1001 steps are carried out first, establish the initial predicted curve of intensity of passenger flow.
In 1001 steps, for preceding M user, such as M=100, as preceding 100 users, in suitable user
Recommendation paths are provided in the travel path subclass of affiliated type at random to determine for user.By these paths in each place of interest
The upper volume of the flow of passengers by zero of intensity of passenger flow distribution adds up, formed each place of interest intensity of passenger flow initially estimate curve f (i, t,
100), wherein i numbers for place of interest, and t is the time；
Next in 1002 steps, new user sends out interaction request after M users, then since the user
Implement the prediction that optimization is weighed to recommend.
First, 1003 steps are executed, 5 current rod densities of 5 place of interest intensity of passenger flow is obtained and estimates curve f (i, t, m0)
As basis, wherein t is time, m0Currently to have preengage number, m0>100, i be 1 to 5；
Next, 1004 steps are executed, according to m0The suitable user determined in the demand obtaining step 005 of+1 user
The travel path subclass of affiliated type, such as select visiting time for 3 hours 3 paths；
In step 1005, using the feature vector of 3 paths as increment, it is added to each related place of interest
Density prediction curve f (i, t, m0) on, form three groups of new increment density prediction curve f (j, i, t, m1), wherein j indicates road
Diameter is numbered, and j is 1 to 3, m1Indicate to increase after active user it is total preengage number, wherein every group of curve represent one it is possible
Path.
In step 1006, will judge in three groups of curves, in every curve f (j, i, t, m1) occur described in step 1005
In the period of increment, whether numerical value exceeds the 95% of the place of interest intensity of passenger flow threshold value after increment, and described 95% is
The strick precaution range beyond intensity of passenger flow threshold value, the visual actual state of concrete numerical value is avoided to be modified；
If all there is one or more incremental rate curve for exceeding 95% in three groups of curves, i.e., all paths all may
Cause the passenger flow peak of one or more places of interest to transfinite, then recommend to extend visiting time or change date of visit, is then return to
Above-mentioned 1003 step；
If all incremental rate curves of only one group curve all without departing from 95%, enter 1010 steps, by the paths
Path is recommended to user as an optimization；
When in the group more than one group of curve all incremental rate curves all without departing from 95% when, execute 1007 steps, weigh user
The concurrent quantity of request.
When the number of concurrent of user's request is few, such as only one user files a request, then may be selected to execute step 1009, by
A place of interest optimizes measurement.As an example, showing that a kind of halfwidth of simplification weighs step herein：
1, increment distribution curve f (j, i, t, the m for each place of interest that this group of path is related to1) carry out as shown in Figure 8
Double normal distributions fitting, obtain fitting after halfwidth parameter TjiHW1, the as estimated distribution characteristics φ of thisix；Wherein i
Each place of interest number being related to for j-th strip path；
2, halfwidth T after digital simulationjiHW1With optimal halfwidth TigHW1Difference Δ TjiHW1, to (i.e. j-th strip in jth group
Path) all places of interest for being related to, by above-mentioned difference Δ TjiHW1Utilize preset weight θiRoot mean square normalization after being weighted,
As critical parameter kj；
3, more different groups of above-mentioned critical parameter kj, wherein parameter kjMinimum path can make estimated distribution characteristics most
Level off to Optimal Distribution feature, thus as preferred path P0。
When the number of concurrent of user's request is more, such as 10 or more users file a request simultaneously, then select to execute step
1008, carry out global optimization measurement.As an example, showing that a kind of peak value of simplification weighs step herein：
1, place of interest density curve that other are not directed to increment is added in increment distribution curve group, forms 3 groups of overall situations and increases
Measure distribution curve f (j, i, t, m1), wherein i is 1 to 5, i.e. every group of overall situation increment distribution curve includes that 5 local regularity distributions are bent
Line；
2, the weighting inhomogeneities curve S of every group of overall situation increment distribution curve is calculatedj(t), wherein j is 1 to 3：
3, as simplification example, 3 weighting inhomogeneities curve S are obtained respectivelyj(t) the peak value M on entire timelinej,
Estimated distribution characteristics φ as thisx；Calculate peak value MjWith SgDifference, the path of difference minimum can make estimated distribution special
Sign most levels off to Optimal Distribution feature, thus as preferred path P0。
It is computed as described above to obtain preferred path P0Afterwards, 1010 steps are executed, recommend the preferred path to user, to complete
At prediction recommendation step 006.
Then, referring again to the flow chart of Fig. 5, step 007 is executed, visit preferred path is confirmed by user, is then based on
Visit preferred path provides a user the management service in step 008, such as the reservation of preferred path, admission ticket are sold and bought, and leads to
Cross other interactive information of step 009 acquisition user, such as the reasons why confirming preferred path.
During the visit of user, the behavioral data of user is acquired and is stored by step 010, such as specifically
Travelling route etc., corresponding data feeds back to prediction recommendation step, the reference frame as intensity of passenger flow prediction distribution curve.
Meanwhile prediction and real-time passenger flow are monitored by step 012, forecast is sent out when the intensity of passenger flow transfinites
Warning information or Real-time Alarm information.
In addition optionally, every some cycles, such as one week, step 011 is executed, based on newer historical data to model
Carry out the optimizations update such as retraining, newer model and individual features calculate step 003 for optimization and use, make model self by
More multidata training, which has, more accurately describes and estimates ability.
Region visit intelligent management system proposed by the present invention and method, a variety of data that visit region is generated into
Row adequately analysis and utilization more profoundly dissect and illustrate visit region for regional managers and tourist goes sight-seeing the spy of behavior
Sign and rule.By the utilization to this objective law, system and method proposed by the present invention can help tourist in visit
More preferably tour is obtained when preceding or visit, the mismatch problems between visit resource and tourist's visit behavior are effectively relieved.Profit
With the management system and method for the present invention, the utilization ratio of visit resource and the visit experience of tourist can be promoted simultaneously, is assisted
The efficient management in region is gone sight-seeing, the utilization of resources in visit region is promoted to enter benign cycle.
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution, improvement and etc. done should be included within the scope of protection of the invention.
Claims (10)
1. intelligent management system is gone sight-seeing in a kind of region, the system comprises user interactive module, information acquisition module and data to deposit
Store up module, which is characterized in that the system also includes forecast analysis modules, wherein
The user interactive module is used to complete the function that interacts with user, and the function of being interacted with user includes,
Collect the visit demand of user；Based on the analysis result of the forecast analysis module, the forecast analysis is pushed to user
The optimization travel path of module output；And management service is provided to the user based on the optimization travel path confirmed through user, institute
It includes that travel path reservation and admission ticket are sold and bought to state management service；
For described information acquisition module for acquiring real time data, the real time data includes user characteristic data, user behavior number
According to this and the intensity of passenger flow real-time estimation data in visit region, and the intensity of passenger flow real-time estimation data are exported to described
Data memory module；
For storing data, the data of storage include the travel path set number in excursion district domain to the data memory module
According to, visit region in focus preset weighted data and intensity of passenger flow threshold data, the user characteristic data, the user
Behavioral data, the intensity of passenger flow real-time estimation data and user characteristics historical data, user behavior historical data and passenger flow
Density historical data；
The forecast analysis module includes optimization computing module and prediction recommending module, wherein
The optimization computing module obtains passenger flow in visit region by the comprehensive analysis to data in the data memory module
The Optimum distribution feature of density is gone through wherein the data for analysis include the intensity of passenger flow historical data, the user characteristics
The preset weight and intensity of passenger flow threshold data of history data, the user behavior historical data and the focus；
The prediction recommending module is obtained by the comprehensive analysis to data in the data memory module in following certain period
The estimated distribution characteristics of intensity of passenger flow, and the estimated distribution characteristics for making the intensity of passenger flow is selected from the travel path set
It levels off to the optimization travel path of the Optimum distribution feature, the optimization travel path is exported to the user and interacts mould
Block, wherein the data for analysis include the user characteristic data, the user behavior data, the user characteristics history number
According to, the user behavior historical data, the intensity of passenger flow real-time estimation data, the travel path collective data and described
The preset weighted data and intensity of passenger flow threshold data of focus.
2. intelligent management system is gone sight-seeing in region as described in claim 1, wherein the system also includes warning module, it is described pre-
Alert module is used to be monitored the estimated distribution characteristics of the intensity of passenger flow and the intensity of passenger flow real-time estimation data, when
The passenger flow of the peak value of the estimated distribution of the intensity of passenger flow or the intensity of passenger flow real-time estimation data beyond focus is close
When spending threshold value, the Real-time Alarm signal that passenger flow has transfinited the Caution And Warning signal or passenger flow that transfinite is sent out respectively.
3. intelligent management system is gone sight-seeing in region as described in claim 1, wherein the optimization computing module further includes user spy
Sign classification submodule and travel path classification submodule, the user characteristics classification submodule pass through to the data memory module
The classification for carrying out feature based is gathered user in the analysis of middle data；The travel path classification submodule is based on to the number
Travel path set is drawn according to the classification that user characteristics classification submodule is made according to the analysis of data in memory module
It is divided into the travel path subclass for the user characteristics for meeting respective classes, the classification of user's set and travel path
Set is used for prediction recommending module.
4. intelligent management system is gone sight-seeing in region as described in claim 1, wherein the optimization computing module and/or the prediction
The method that recommending module analyzes the data in the data memory module includes statistical induction method and machine learning side
Method.
5. intelligent management system is gone sight-seeing in region as claimed in claim 4, wherein the machine learning method include regression algorithm,
Clustering algorithm, artificial neural network algorithm, deep learning algorithm and nitrification enhancement.
6. intelligent management system is gone sight-seeing in region as described in claim 1, wherein the Optimum distribution feature and the prediction point
Cloth feature is characterized function or characteristic parameter.
7. intelligent management system is gone sight-seeing in region as described in claim 1, wherein the Optimum distribution feature and the prediction point
Cloth feature includes visit region global characteristics and focus local feature.
8. intelligent management is gone sight-seeing in a kind of region, which is characterized in that the described method comprises the following steps：
Information collection step, is acquired real time data, and the real time data includes user characteristic data, user behavior data
With the intensity of passenger flow real-time estimation data in visit region；
Data storing steps store data in data memory module, and the data include the travel path collection in excursion district domain
It closes data, is the preset weighted data of focus and intensity of passenger flow threshold data in visit region, the user characteristic data, described
User behavior data, the intensity of passenger flow real-time estimation data and user characteristics historical data, user behavior historical data and
Intensity of passenger flow historical data；
Forecast analysis step, the forecast analysis step include optimization calculating step and predict recommendation step, wherein
The optimization calculates step by analyzing the data in the data memory module, obtains visit region middle reaches visitor's density
Optimum distribution feature, wherein for analysis data include the intensity of passenger flow historical data, the user characteristics historical data,
The preset weight and intensity of passenger flow threshold data of the user behavior historical data and the focus；
The prediction recommendation step show that passenger flow is close in following certain period by analyzing the data in the data memory module
The estimated distribution characteristics of degree, and selection makes the estimated distribution characteristics of the intensity of passenger flow level off to from the travel path set
The optimization travel path of the Optimum distribution feature, wherein the data for analysis include the user characteristic data, the use
Family behavioral data, the user characteristics historical data, the user behavior historical data, the intensity of passenger flow real-time estimation number
According to, the preset weighted data and intensity of passenger flow threshold data of the travel path collective data and the focus；
User's interactive step, for completing the function that is interacted with user, the function of the interaction includes,
Collect the visit demand of user；Based on the analysis result of the forecast analysis module, the forecast analysis is pushed to user
The optimization travel path of module output；And management service is provided to the user based on the optimization travel path confirmed through user, institute
It includes that travel path reservation and admission ticket are sold and bought to state management service.
9. intelligent management is gone sight-seeing in region as claimed in claim 8, wherein the method further includes warning step, described pre-
Alert step is monitored the estimated distribution characteristics of the intensity of passenger flow and the intensity of passenger flow real-time estimation data, when described
The peak value of the estimated distribution of intensity of passenger flow or the intensity of passenger flow real-time estimation data exceed the intensity of passenger flow threshold of focus
When value, the Real-time Alarm signal that passenger flow has transfinited the Caution And Warning signal or passenger flow that transfinite is sent out respectively.
10. intelligent management is gone sight-seeing in region as claimed in claim 8, wherein optimization calculating step and/or described pre-
It includes statistical induction method and machine to survey the method that recommendation step is calculated and analyzed to the data in the data memory module
Device learning method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810588847.4A CN108537691A (en) | 2018-06-08 | 2018-06-08 | A kind of region visit intelligent management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810588847.4A CN108537691A (en) | 2018-06-08 | 2018-06-08 | A kind of region visit intelligent management system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108537691A true CN108537691A (en) | 2018-09-14 |
Family
ID=63470549
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810588847.4A Pending CN108537691A (en) | 2018-06-08 | 2018-06-08 | A kind of region visit intelligent management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108537691A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272501A (en) * | 2018-09-27 | 2019-01-25 | 深圳春沐源控股有限公司 | Scenic spot information statistical method, system and storage medium |
| CN109784550A (en) * | 2018-12-29 | 2019-05-21 | 广州慧睿思通信息科技有限公司 | A kind of schedule planning system and method based on intelligent sensing equipment |
| CN110297964A (en) * | 2019-03-28 | 2019-10-01 | 特斯联（北京）科技有限公司 | A kind of tourist attractions recommended method and device based on big data analysis |
| CN110955740A (en) * | 2019-10-30 | 2020-04-03 | 重庆特斯联智慧科技股份有限公司 | Tourism resource scheduling method and system based on path big data |
| CN111581547A (en) * | 2020-06-04 | 2020-08-25 | 浙江商汤科技开发有限公司 | Tour information pushing method and device, electronic equipment and storage medium |
| CN112419567A (en) * | 2020-11-09 | 2021-02-26 | 成都中科大旗软件股份有限公司 | Comprehensive management system based on text and travel fusion |
| CN112422654A (en) * | 2020-11-06 | 2021-02-26 | 周欢 | User management method based on intelligent endowment |
| CN113361665A (en) * | 2021-08-11 | 2021-09-07 | 成都理工大学 | Highland mountain tourism safety risk early warning method based on reinforcement learning |
| TWI801718B (en) * | 2020-02-25 | 2023-05-11 | 瑞軒科技股份有限公司 | Intelligent interactive display device, intelligent interactive display system and interactive display method thereof |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103994771A (en) * | 2014-05-06 | 2014-08-20 | 长沙地大物泊网络科技有限公司 | Scenic region intelligent navigation application system and using method thereof |
| CN104036352A (en) * | 2014-06-09 | 2014-09-10 | 陕西师范大学 | Space-time regulation and emergency guidance system and method for scenic spot tourists |
| CN106447084A (en) * | 2016-08-22 | 2017-02-22 | 北京易游华成科技有限公司 | Path planning device, method and system |
| CN206100067U (en) * | 2016-08-22 | 2017-04-12 | 北京易游华成科技有限公司 | Passenger flow volume monitoring device and system |
| CN107133277A (en) * | 2017-04-12 | 2017-09-05 | 浙江大学 | Recommend method in a kind of tourist attractions based on Dynamic Theme model and matrix decomposition |
| CN107230330A (en) * | 2017-07-12 | 2017-10-03 | 东南大学 | A kind of tourist communications management system based on big data |
-
2018
- 2018-06-08 CN CN201810588847.4A patent/CN108537691A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103994771A (en) * | 2014-05-06 | 2014-08-20 | 长沙地大物泊网络科技有限公司 | Scenic region intelligent navigation application system and using method thereof |
| CN104036352A (en) * | 2014-06-09 | 2014-09-10 | 陕西师范大学 | Space-time regulation and emergency guidance system and method for scenic spot tourists |
| CN106447084A (en) * | 2016-08-22 | 2017-02-22 | 北京易游华成科技有限公司 | Path planning device, method and system |
| CN206100067U (en) * | 2016-08-22 | 2017-04-12 | 北京易游华成科技有限公司 | Passenger flow volume monitoring device and system |
| CN107133277A (en) * | 2017-04-12 | 2017-09-05 | 浙江大学 | Recommend method in a kind of tourist attractions based on Dynamic Theme model and matrix decomposition |
| CN107230330A (en) * | 2017-07-12 | 2017-10-03 | 东南大学 | A kind of tourist communications management system based on big data |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272501B (en) * | 2018-09-27 | 2022-11-11 | 深圳春沐源控股有限公司 | Scenic spot information statistical method, system and storage medium |
| CN109272501A (en) * | 2018-09-27 | 2019-01-25 | 深圳春沐源控股有限公司 | Scenic spot information statistical method, system and storage medium |
| CN109784550A (en) * | 2018-12-29 | 2019-05-21 | 广州慧睿思通信息科技有限公司 | A kind of schedule planning system and method based on intelligent sensing equipment |
| CN110297964A (en) * | 2019-03-28 | 2019-10-01 | 特斯联（北京）科技有限公司 | A kind of tourist attractions recommended method and device based on big data analysis |
| CN110955740A (en) * | 2019-10-30 | 2020-04-03 | 重庆特斯联智慧科技股份有限公司 | Tourism resource scheduling method and system based on path big data |
| CN110955740B (en) * | 2019-10-30 | 2020-12-18 | 重庆特斯联智慧科技股份有限公司 | Tourism resource scheduling method and system based on path big data |
| TWI801718B (en) * | 2020-02-25 | 2023-05-11 | 瑞軒科技股份有限公司 | Intelligent interactive display device, intelligent interactive display system and interactive display method thereof |
| CN111581547A (en) * | 2020-06-04 | 2020-08-25 | 浙江商汤科技开发有限公司 | Tour information pushing method and device, electronic equipment and storage medium |
| CN111581547B (en) * | 2020-06-04 | 2023-12-15 | 浙江商汤科技开发有限公司 | Tour information pushing method and device, electronic equipment and storage medium |
| CN112422654A (en) * | 2020-11-06 | 2021-02-26 | 周欢 | User management method based on intelligent endowment |
| CN112422654B (en) * | 2020-11-06 | 2022-07-26 | 东莞市中展实业投资有限公司 | User management method based on intelligent old age care |
| CN112419567A (en) * | 2020-11-09 | 2021-02-26 | 成都中科大旗软件股份有限公司 | Comprehensive management system based on text and travel fusion |
| US11625803B2 (en) | 2021-08-11 | 2023-04-11 | Chengdu University Of Technology | High land tourism safety risk warning method based on reinforcement learning |
| CN113361665B (en) * | 2021-08-11 | 2021-11-16 | 成都理工大学 | Highland mountain tourism safety risk early warning method based on reinforcement learning |
| CN113361665A (en) * | 2021-08-11 | 2021-09-07 | 成都理工大学 | Highland mountain tourism safety risk early warning method based on reinforcement learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108537691A (en) | A kind of region visit intelligent management system and method | |
| Xu et al. | A VIKOR-based approach for assessing the service performance of electric vehicle sharing programs: A case study in Beijing | |
| Xu et al. | A hybrid machine learning model for demand prediction of edge-computing-based bike-sharing system using Internet of Things | |
| Qin et al. | Reinforcement learning for ridesharing: An extended survey | |
| CN105405293B (en) | A kind of road travel time short term prediction method and system | |
| CN109872535A (en) | A kind of current prediction technique of wisdom traffic, device and server | |
| CN106448132A (en) | Conventional public traffic service index real-time evaluation system and method | |
| Lin et al. | A spatial-temporal hybrid model for short-term traffic prediction | |
| CN107392389A (en) | Taxi dispatching processing method based on ARIMA models | |
| CN109741626A (en) | Parking situation prediction technique, dispatching method and system | |
| Lin et al. | Intelligent bus operation optimization by integrating cases and data driven based on business chain and enhanced quantum genetic algorithm | |
| CN102903038A (en) | Method and system for small object logistics distribution based on user track | |
| Kong et al. | The method and application of big data mining for mobile trajectory of taxi based on MapReduce | |
| Pfaffenbichler | The strategic, dynamic and integrated urban land use and transport model MARS (Metropolitan Activity Relocation Simulator) | |
| Wang et al. | Has the healthy city pilot policy improved urban health development performance in China? Evidence from a quasi-natural experiment | |
| Kamel et al. | A modelling platform for optimizing time-dependent transit fares in large-scale multimodal networks | |
| Xu et al. | A taxi dispatch system based on prediction of demand and destination | |
| Yang et al. | Dynamic Origin‐Destination Matrix Estimation Based on Urban Rail Transit AFC Data: Deep Optimization Framework with Forward Passing and Backpropagation Techniques | |
| Lin et al. | Insights into Travel Pattern Analysis and Demand Prediction: A Data-Driven Approach in Bike-Sharing Systems | |
| Qiu et al. | RPSBPT: A route planning scheme with best profit for taxi | |
| Wang et al. | DeepFM-Based taxi pick-up area recommendation | |
| Zhu et al. | Analysis of human resource allocation model for tourism industry based on improved BP neural network | |
| CN109859087A (en) | A kind of intelligent Community soft environment configuration system and method surpassing brain using city | |
| Ghandeharioun et al. | Real-time ridesharing operations for on-demand capacitated systems considering dynamic travel time information | |
| Ning et al. | A catfish effect based team recommendation system |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180914 |