CN106096000A - A kind of user based on mobile Internet travel optimization recommend method and system - Google Patents
A kind of user based on mobile Internet travel optimization recommend method and system Download PDFInfo
- Publication number
- CN106096000A CN106096000A CN201610458701.9A CN201610458701A CN106096000A CN 106096000 A CN106096000 A CN 106096000A CN 201610458701 A CN201610458701 A CN 201610458701A CN 106096000 A CN106096000 A CN 106096000A
- Authority
- CN
- China
- Prior art keywords
- user
- travel
- matrix
- trip
- optimization
- 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
- 238000005457 optimization Methods 0.000 title claims abstract description 46
- 238000012546 transfer Methods 0.000 claims abstract description 25
- 238000013461 design Methods 0.000 claims abstract description 9
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 238000011156 evaluation Methods 0.000 claims abstract description 6
- 239000011159 matrix material Substances 0.000 claims description 77
- 230000032683 aging Effects 0.000 claims description 8
- 238000005303 weighing Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 11
- 239000000203 mixture Substances 0.000 description 11
- 238000011160 research Methods 0.000 description 10
- 230000000875 corresponding effect Effects 0.000 description 8
- 230000006399 behavior Effects 0.000 description 7
- 230000033001 locomotion Effects 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000001149 cognitive effect Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000002452 interceptive effect Effects 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000003786 synthesis reaction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 239000002912 waste gas Substances 0.000 description 2
- 206010068052 Mosaicism Diseases 0.000 description 1
- 210000003484 anatomy Anatomy 0.000 description 1
- 238000000429 assembly Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008713 feedback mechanism Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000006116 polymerization reaction Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 210000003765 sex chromosome Anatomy 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- General Business, Economics & Management (AREA)
- Strategic Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
A kind of user based on mobile Internet travel optimization recommend method, its comprise the steps: S1, confirm user travel consider factor, described factor include go on a journey choosing period of time, travel route choice, Passenger Traveling Choice, transfer select;S2, according to above-mentioned factor build user's travel solutions tensor operation model;S3, the result of calculation of the tensor operation model of user's travel solutions is added Candidate Recommendation scheme, and carry out candidate scheme score value calculating;S4, the score value of the Candidate Recommendation scheme of acquisition is supplied to user carrying out experiencing and obtain user's feedback result to experiencing, the trip scheme recommended user based on every evaluation index carries out score value ranking, thus obtains final suggested design for user's selection.The present invention also provides for a kind of user based on mobile Internet and travels optimization commending system.
Description
Technical field
The present invention relates to mobile Internet tourism route recommended technology field, particularly to a kind of based on mobile Internet
User travel optimization recommend method and system.
Background technology
Mobile Internet platform based on current popular, the research of the recommendation method carrying out user's travel mode be one new
Emerging research field, the research field related to includes based on mobile Internet platform, user's real time position dynamically change prison
Surveying, User Activity position and the Changing Pattern of scope, the regular course of User Activity defines the recommendation with optimal route, and user lives
All technical fields being correlated with user's travel mode recommendation that mobile interchange is online such as dynamic space-time rule design.By to this
The research of a little advanced technologies, the present invention proposes a set of in urban life, and mankind's travel solutions optimization scheme is recommended
Research system.This system can be good at solving the choosing period of time of mankind's travelling, Path selection corresponding to period, mode of transportation
Select the problem of logical relation between transfer.Thus reach to recommend the purpose of optimum travel solutions to user.I.e. user
Optional, optimum period, optimum period corresponding optimal path, the optimal vehicles under the optimum period select and transfer.
User is being considered under safety, convenience, ageing and economy, travel solutions can be made the wisest choosing
Select.
The main study subject that these fields relate to, key technology and actual application value specifically include that
Travel mode study in sparse gps data: Yu Zheng et al. uses the method for monitoring learning from user
The openness data passed are inferred the mode of user's travelling automatically.In this article discuss travel mode include walking, drive, public transport
Three models, and do Context-aware computing based on certain travel mode.Paper uses segmentation flex point technology and based on condition
The post-processing algorithm of probability, and set up deduction model with this, and by the prediction of experimental verification travel mode and different travel mode
The accuracy of transfer.
Geographical location marker in digital picture: Kentaro Toyama et al. proposes a kind of novel end-to-end system
For capturing the map location metadata in digital picture.In this article, three challenge that they solve include: 1, exist
The method identifying location tags on photo;2, the data structure of a kind of image operating band location tags is proposed;3, display and
Browse the user interface of band position mark photo.And having write a kind of software for automatically creating appropriate situation map should
Use instrument.
The anatomy of position history and modeling: Ramaswamy Hariharan et al. proposes the number of a series of strict difinition
It is used for analyzing and generating position history according to structure and algorithm.Literary composition have employed non-Markovian and two kinds of methods of Markov to
The position history at family carries out probability modeling.And with the results show the value of these data structures and position history probability
The possible application of model.
The study of multi-user's critical positions and Motion prediction: Danile Ashbrook et al. utilizes position situation to user not
The action come creates forecast model, and establishes a kind of system, when this system collects considerably long one on different scale automatically
Gps data in Duan also converts them into significant positional information.These positional informationes can be used a series of alone
The application that family and collaborative multi-user participate in.
Destination in potential track infers: John Krumm et al. utilizes driving history and the driving behavior number of driver
According to setting up model, and often driven stretch by him and predict where car may be left by he.The driver driving of research in this article
Behavior includes destination's type, driving efficiency and journey time.In addition to the destination accessed before considering, model utilizes one
Open modeling method considers that user accesses tera incognita based on data trend and the similarity of location context attribute.Analyze
Most assemblies be fused for generating probability purpose map by Bayesian inference.
It is a kind of for learning that low level sensor infers that high-level user behavior: Donald J.Patterson et al. proposes
Practise the Bayesian model of urban subscriber's mobile behavior.Meanwhile, they propose a kind of non-supervisory unified model, and this model can
Simulating user's current behavior pattern, this behavioral pattern is just as their track route at ordinary times.This model uses particle
Wave filter and expectation-maximization algorithm are implemented.This model makes about bus routes and bus station's information by addition is more
Infer that accuracy is improved.
Personalized map: Lin Liao et al. proposes a kind of auxiliary cognitive information technological system, and this system can learn often
Individual user customization personalized map and infer their daily routines and situation of movement.For the different behavior situations of user, should
System can use discriminant and production model.A kind of discriminant relation Markov Network can be used to extract different location and mark
Remember them.A kind of production dynamic bayesian network can be used to learn the use that traffic route, deduction target and real-time report are potential
Family mistake.They pay close attention to the basic structure of model and have briefly inquired into deduction and learning art.Experiment display, this system can be accurately
Extract and marking terrain, it was predicted that ownership goal and identify the situation made mistakes of user, as user has taken bus wrong.
The study of itinerary and deduction: Lin Liao et al. describes a kind of level Markov model, this model energy
User's daily routines situation is inferred by community in urban areas.In order to reduce between coarseness GPS sensor measured value and high-level information
Gap, the destination of such as user and motion mode, model use abstract conception many levels.In order to reach more effective
Inferred results, they use Rao-Blackwellized particle filter in the many levels of model hierarchy structure.Bus
Bus stop and these location points of parking lot are the points that user frequently changes action modes, need not manually mark training set data
In the case of just can from gps data daily record learning to.And how upper and lower by user historical data with description of test
User Activity is having to explicitly modeled by literary composition situation, accurately to detect new behavior and user error (such as taking wrong bus).Finally,
Having inquired into one in literary composition and be called the application of " Opportunity Knocks ", this application uses the technology in literary composition to go to help cognition to have
The people with disability of defect uses public transport safely.
Segmentation and the probabilistic model of labelled sequence data: John Lafferty et al. proposes probability random field model, it
It is a kind of sequence data to be split and the framework of labelling for setting up probabilistic model.Conditional random fields is at hidden markov mould
Type the most grammatically provides some advantages for alleviation this kind of work of strong independence assumption with random.Conditional random fields also is able to avoid
The fundamental shortcomings of big entropy Markov model and other differentiated Markov model based on Directed Graph Model.It literary composition is bar
Part random field proposes iterative parameter algorithm for estimating, and compares hidden markov model in synthesis and natural language data
Performance with maximum entropy Markov model.
Webpage search with GIS-Geographic Information System: integrated currently having caused of the Webpage search of band geography information attracts the attention of millions of people.
Existing many positions web page search system makes user search the web page contents of ad-hoc location.In the text, Taro Tezuka et al. refers to
Go out this kind of integrated still rest in more shallow level.The most most of web page search system are the most only in local page
Hold and map interface is chained up.They are the extensions of common independent GIS-Geographic Information System, are employed for a kind of sing on web
C-S framework.In this article, extracting, Knowledge Discovery and present aspect, inquire into the Web search for band GIS tightened up integrated
Method.And describe the implementation of support " integrated must exceed simple map-hyperlink framework " this viewpoint.
Space-time RSS navigates: Yih-Farn Chen et al. proposes a kind of new space-time browser technology, and this technology can be with
A kind of mode timely, personalized and automatic provides the user the RSS that assembles and navigate and extends the ability of content.Especially, Wen Zhong
Introduce a kind of system being referred to as GeoTracker, represent that for geographical space being adapted to assist in user with time representation quickly finds
Relevant renewal.In the course of the work, they provide a kind of support RSS feeds intelligence polymerization and travel to desktop and mobile terminal
Middleware engine on equipment.Literary composition have studied this system two data sets (2006World Cup Soccer and
Breaking news items) on homing capability.Also illustrate that these technology video on YouTube and Google simultaneously
The application of Search Results strengthens a user in his location based on own geographical interest and the ability that browses.Finally, they
The location estimating ability of GeoTracker is carried out with the machine learning techniques using natural language processing/information retrieval community
Experiment is compared.Although the algorithm in literary composition is simple, but it possesses higher recall rate.
Sports science and exploration system: Rainer Wasinger et al. describes a kind of for sports science and based on shifting
The intimate pocket PC product completed of dynamic multimode interaction platform.This Platform Designing is out to support indoor and room in order to easier
Outer navigation task, and use the combination of several module to show input and the output of user.And 2D/3D figure and synthesis voice are used
Show information useful on circuit and position, and the fusion input coming from embedded speech and gesture recognition engine all considers
Arrive the mutual of user.
Mobile-Ipv6 based on context multiplayer: Keith Mitchell et al. describes one in the text and is called
Many people moving game prototype of Real Tournament, this palm machine game adds a series of sensor for strengthening true generation
Mobile interactive function in boundary's environment.Then current method is assessed for real-time, interactive, found the framework in literary composition more
It is suitable for wireless environment and based on point-to-point method.For providing support to extensibility, low latency, soft real-time Mobile solution, should
Method provides adaptability, shares state and coherency mechanism.
Navigation is controlled: Steven Strachan et al. is mobile global alignment system and MP3 player by audible feedback
Function combine, for pocket palm machine, to generate a kind of palm system.This system can be anti-by the music persistently adapted to
The destination that user thinks is guided in feedback to them.Literary composition illustrates and how to do audio frequency and show and can be subject to from the degree of depth of control theory
Benefit.Such as, it was predicted that display browse element, and the uncertain or appropriate display of fuzzy factors.The probability interpretation energy of navigation task
Enough it is summarized in other Mobile solution depending on context.This is the hand-held that first item is based entirely on location aware
The example of music player, is discussed in detail the use scene of this system in literary composition.
The Mobile solution framework of geographical space Web: Rainer Simon et al. proposes a kind of mobile network architecture, this
Structure utilizes the geographical sky on the Internet by Interactive innovation pattern on smart mobile phone and palm PC and the new type of user interface
Between content.Discussing current development procedure in literary composition, they relate to building mobile geographical space W eb application and obtaining framework needs
Three technical prerequisite: based on visualization and view field space querying operation, the environmental model of a 2.5D and
A kind of form of the unique display data interaction for geospatial queries result.Therefore, they propose as a kind of coupling
Cut-set power space model based on XML candidate, and illustrate a kind of prototype realize process.
Location-based movable cognitive: the human activities such as Lin Liao are cognitive and pass through to build and expansion relation Markov
Network defines a kind of overall framework.Using the movable cognitive example from position data, they illustrate their model
The various feature comprising temporal information and the spatial information extracted from geographical data bank and global restriction can be represented, such as a people
Family and the number of job site.They develop a efficiently deduction and learning art of based on MCMC.Utilize by many people
The GPS location data collected, the moving position of the accurate labelling user of this technology energy.Additionally, by utilize priori extract from
The method of other people low volume data training high-quality model is feasible.
In existing city, movement locus and the mobility law study of the mankind go deep into, it is impossible to in urban life
Energy resource consumption and waste gas discharge are optimized, it is impossible to reach the purpose protecting environment.
Summary of the invention
In view of this, the present invention propose a kind of user based on mobile Internet travel optimization recommend method.
A kind of user based on mobile Internet travel optimization recommend method, it comprises the steps:
S1, confirm user travel consider factor, described factor include go on a journey choosing period of time, travel route choice, trip
Mode selects, changes to selection;
S2, according to above-mentioned factor build user's travel solutions tensor operation model;
S3, the result of calculation of the tensor operation model of user's travel solutions is added Candidate Recommendation scheme, and carry out candidate
Scheme score value calculates;
S4, the score value of the Candidate Recommendation scheme of acquisition is supplied to user carries out experiencing and obtain user's feedback to experiencing
As a result, the trip scheme recommended user based on every evaluation index carries out score value ranking, thus obtains final suggested design
Select for user.
Travel in optimization recommendation method user based on mobile Internet of the present invention, in described step S1:
The module that selection mode selects includes safety coefficient S, convenience C, transfer relation T, economy E;S is used for weighing
Amount user selects the safe coefficient of line mode, and span is 0~10, and S value is the lowest, shows that this kind of trip mode is uneasy
Entirely;C for representing the convenience degree of user's travel mode, T for represent user to the selection of hourage and demand, E is used for
Represent user's requirement to travelling Financial cost.
Travel in optimization recommendation method user based on mobile Internet of the present invention, in described step S2:
The tensor operation model of user's travel solutions is as follows:
Rm=U*W*M*C*T, in formula, RmRepresenting the optimization travel mode that user selects, travel mode the most to be recommended, U represents
User, W represents alternative travel mode, and M represents travelling module, and T represents transfer relation.
Travel in optimization recommendation method user based on mobile Internet of the present invention,
The incidence relation matrix of user and travel mode is as follows:
Wherein MU×WRepresenting matrix title, the ranks relation of U-W representing matrix, Pij(i=1...n, j=1...m) represents
User UiSelect travel mode WjProbability.
Travel in optimization recommendation method user based on mobile Internet of the present invention,
Travel mode is as follows with the incidence relation matrix of module:
Wherein MW×MRepresenting matrix title, the ranks relation of W-M representing matrix, PiS,PiC,PiT,PiE(i=1...m) represent
User UiSelect travel mode Wi(i=1...m) the safety of corresponding trip mode, convenience, ageing and economical
Property.
Travel in optimization recommendation method user based on mobile Internet of the present invention,
User is as follows with the incidence relation matrix of convenience:
Wherein this incidence relation matrix is Boolean matrix, wherein, MU-CRepresenting matrix title, C-C represents the ranks of this matrix
Relation;CabTransfer relation whether is there is, if there is its value is 1, otherwise between the travel mode of (a, b=1...m) expression user
It is 0.
Travel in optimization recommendation method user based on mobile Internet of the present invention,
User is as follows with the incidence relation matrix of transfer relation:
Wherein this relational matrix is numeric type incidence relation matrix, wherein, MU-TRepresenting matrix title, U-T represents this matrix
Ranks relation, UTij(i=1...n, j=1...m) represents in historical data, user UiSelect period TjDuring for most preferably going on a journey
The probability of section.
Travel in optimization recommendation method user based on mobile Internet of the present invention,
In described step S3:
The incidence relation matrix of the trip route that the trip period is corresponding with this period is as follows:
Wherein this incidence relation matrix is numerical relation matrix, wherein, MT-PRepresenting matrix title, T-P represents this matrix
Ranks relation, TPij(i=1...n, j=1...m) represents that user is selecting trip period Ti(i=1...n) and this period institute right
The trip route Pa answeredj(j=1...m) time, the score of the travel route choice scheme drawn;Score value is the highest, shows this period
This path is selected more to easily become optimum trip scheme.
Travel in optimization recommendation method user based on mobile Internet of the present invention,
In described step S4:
User is as follows with the incidence relation matrix of optimization travel solutions:
Wherein this incidence relation matrix is numerical relation matrix, wherein, MU-RRepresenting matrix title, U-R represents this matrix
Ranks relation, Sij(i=1...n, j=1...m) represents user UiSelect optimization travel solutions RjFor optimal trip scheme
Score, score value is the highest, more easily becomes the trip scheme that user is alternative.
The present invention also provides for a kind of user based on mobile Internet and travels optimization commending system, and it includes as placed an order
Unit:
Factor determines unit, the factor considered for confirming user to travel, and described factor includes go on a journey choosing period of time, trip
Path selection, Passenger Traveling Choice, transfer select;
Unit set up by model, for building the tensor operation model of user's travel solutions according to above-mentioned factor;
Candidate scheme determines unit, pushes away for the result of calculation of the tensor operation model of user's travel solutions is added candidate
Recommend scheme, and carry out candidate scheme score value calculating;
Optimal case determines unit, experiences for the score value of the Candidate Recommendation scheme of acquisition is supplied to user and obtains
Taking the family feedback result to experiencing, the trip scheme recommended user based on every evaluation index carries out score value ranking, thus
Obtain final suggested design to select for user.
The user based on mobile Internet that implementing the present invention provides optimization of travelling recommends method and system and existing skill
Art compares the analysis having the advantages that by a large number of users travel histories data, therefrom extract user's trip time
Section and at the vehicles of this period user's choice for traveling, and the user side of trip that user's trip route of correspondence is constituted
Case.By structure trip scheme set is estimated from safety, convenience, ageing and economy isometry index respectively
After, calculate the final score of each scheme.The most finally assert, it is recommended that the score of scheme is the highest, the easiest candidate becomes
The user optimized goes on a journey scheme, and obtains the selection of user.By the excavation of the historical data to User Activity, existed by user
The feature of travelling in city, needs to select the appropriate vehicles according to certain space-time rule, and selects trip for user
Travel routes corresponding to the row period carries out candidate's optimization, and to reach to evade specific time period and section, burst occurs in road traffic
The purpose that property is congested.It addition, rational user travels, recommendation can also reduce the energy resource consumption in urban life and waste gas discharge,
Thus reach environment is carried out the purpose of protective effect.Meanwhile, the travelling of user relates to mankind's rule of life in city, right
The development in future city and planning serve predictable enthusiasm reference role.
Accompanying drawing explanation
Fig. 1 is that the user based on mobile Internet of embodiment of the present invention optimization of travelling recommends the chain of command of method
Figure;
Fig. 2 is that the user of the embodiment of the present invention travels recommendation method operational flowchart;
Fig. 3 is embodiment of the present invention user's travel mode selected metric standard drawing;
Fig. 4 is that the user based on mobile Internet of the embodiment of the present invention travels optimization commending system structured flowchart.
Detailed description of the invention
Invention proposes a kind of user based on mobile Internet and travels recommendation method.User travelling need consider because of
Element includes: user goes on a journey the selection of period, the selection of user's trip mode, and trip mode through (or needing transfer) is used
Whether family have selected optimization action path, the feedback of optimization path and assessment etc..They subordinations are used in mobile Internet
Family travelling recommendation method research system under, its chain of command as shown in Figure 1:
User is travelled recommendation from trip choosing period of time method, travel route choice by method system described in Fig. 1 respectively
Method, Passenger Traveling Choice method and transfer four aspects of system of selection are summarized, and then provide travelling optimum path planning
Recommended models, the research method to this model sets up feedback mechanism afterwards, and whether optimization is estimated to recommendation paths.
Research system based on user's travel mode recommendation method that Fig. 1 is given, was carried out each stage in this system
Refinement, can show that user travels the computational methods of suggested design, as in figure 2 it is shown, include that the period that user goes on a journey calculates, user goes out
The path computing of row, user occur that way choice calculates and the transfer of user's trip mode calculates.By these projects are entered
After row calculates, can the tensor operation model of structuring user's travel solutions, complete the tensor operation of projects.Its result of calculation is entered
Enter Candidate Recommendation scheme, calculate with the score value of pending candidate scheme.After the score value calculating Candidate Recommendation scheme, it is provided that
Candidate scheme is experienced to user.Remain user to experiencing after result provides feedback result, based on every evaluation index pair
The trip scheme that user recommends carries out score value ranking, thus obtains final suggested design and recommend user's selection.
Passenger Traveling Choice: active user's alternative major travel mode of travelling in city includes: aircraft, train
(high ferro), steamer, automobile, subway, bicycle and walking.It is known that various travel modes are in time span and spatial extent
On be respectively arranged with its pluses and minuses, how preferably matching and utilize their advantage, evading its shortcoming is a challenge being worth studying
Sex chromosome mosaicism.Such as, intercity travelling, aircraft is shorter for hourage than alternate manner, but airplane needs transfer, airport one
As be arranged on outskirts of a town, therefore its convenience non-optimal.When city is close together, though high ferro slightly below aircraft hourage, but
High ferro station is located in city, and convenience is higher than aircraft.Here it is most of passengers increasingly favor in the reason of high travel iron.Thus
Understanding, the needs that select of trip mode consider some questions as shown in Figure 3, and they are also measure user travelling optimizations simultaneously
The important indicator recommended.
Safety: it is the factor of user's overriding concern.If travel mode is dangerous, user is can never be alternative
's.In patent of the present invention, carry out measure user by safety coefficient S and select the safe coefficient of line mode.The value model of safety coefficient
Enclosing is 0~10, and safety coefficient is the lowest, shows that this kind of trip mode is the most dangerous.Being worth explanation, the safety of trip mode is
One relative concept, the most definitely.The tolerance of user's safety is affected by a lot of accidentalia, in the research of this patent
In all this kind of accidentalia is got rid of.
Convenience: be designated C.Refer to the convenience degree of user's travel mode.If user is close to railway station, Ta Menkao
Consider city this factor congested, generally will not select the airline traveling far away from suburb.Therefore, convenience is that measure user is to travelling
The important measurement index that mode selects.During weighing convenience, need to consider the real time position L that user is presently inR,
By calculating LRWith convenience just can be quantified and measure by the distance taken between trip vehicles website.According to walking
Or private car (the privately owned vehicles such as bicycle, motorcycle), its site distance is from ignoring.It addition, the real-time friendship in city
Path condition is also the key factor considered.Such as, although sometimes site distance may be slightly less than airport from railway station, but by
Too block up to the traffic in this section of path, railway station in user's real time position, and airport be preferable on the contrary in countryside road conditions,
Now the convenience on airport is on the contrary higher than railway station.
Ageing: to be designated T.Refer to user to the selection of hourage and demand.User is before ensureing safety
Put, the travel mode that hourage is relatively short can be selected.Such as, originally it is first from user's real time position to railway station private car
Choosing, but certain period traffic extreme difference, user apart from interior, uses bicycle to be better than on ageing on the contrary to railway station suitably
Private car.
Economy: be designated E.Refer to user's requirement to travelling Financial cost.Ensureing user's touring safety
Under premise, user generally favors in the higher travel mode of cost performance.
Can select to set up tensor model as shown in Equation 1 to user's travel mode based on above-mentioned module.
Rm=U*W*M*C*T (1)
In formula 1, RmRepresenting the optimization travel mode (travel mode the most to be recommended) that user selects, U represents user, W table
Showing alternative travel mode, M represents travelling module, and T represents transfer relation.U, W, M and T correspond respectively to user,
Travel mode, metric and the incidence relation matrix whether changed to.Its matrix is as shown in formula 2 to formula 4.
Wherein, the M in formula (2)U×WRepresenting matrix title, the ranks relation of U-W representing matrix.Pij(i=1...n, j
=1...m) represent user UiSelect travel mode WjProbability.
Wherein, the M in formula (3)W×MRepresenting matrix title, the ranks relation of W-M representing matrix.PiS,PiC,PiT,PiE(i
=1...m) represent that user selects travel mode W respectivelyi(i=1...m) safety of the trip mode corresponding to, convenience,
Ageing and economy (between 0~10, score value height shows the quality of travel mode to its score value optional).
Transfer select: due to user travelling during in order to promote the indices of travel mode, meet the trip of self
Row demand, they would generally select certain transfer manner to be optimized travel mode.Formula (4) gives user transfer
Relational matrix.
It can be seen that this relational matrix is Boolean matrix from formula (4).Wherein, MU-CRepresenting matrix title, C-C represents
The ranks relation of this matrix.CabTransfer relation whether is there is, if existing between the travel mode of (a, b=1...m) expression user
Its value is 1, is otherwise 0.
Trip choosing period of time: the go on a journey selection of period of user can be that the trip of user provides a lot of convenient.User is selecting
During same section of travel routes, due to the difference on trip choosing period of time, also result in the difference in travelling metric.In order to
Solve this problem, provide the incidence matrix of user's choice for traveling, as shown in Equation 5.
It can be seen that this relational matrix is numeric type incidence relation matrix from formula (5).Wherein, MU-TRepresenting matrix name
Claiming, U-T represents the ranks relation of this matrix.UTij(i=1...n, j=1...m) represents in historical data, user UiDuring selection
Section TjProbability for the optimal period of going on a journey.
After the calculating to formula (1)-formula (5), can be that user calculates optimized travel mode.
Travel route choice: user, before travel in addition to selecting the trip period optimized, optimizes at this choosing period of time
Trip route also it is critical that.Even if it is true that in non-peak period on and off duty, different sections is due to accident
Generation, real-time road can be caused prior uncertain impact equally.By the analysis to user's historical data, can be right
Accident-prone road section carries out feature extraction and mark, when user selects specific time period, carries out user in trip scheme propelling movement
Avoid the propelling movement to these sections as far as possible.Here, the relational matrix such as formula (6) providing user's travel route choice is shown.
It can be seen that this relational matrix is numerical relation matrix from formula (6).Wherein, MT-PRepresenting matrix title, T-P
Represent the ranks relation of this matrix.TPij(i=1...n, j=1...m) represents that user is selecting trip period Ti(i=1...n)
With the trip route Pa corresponding to this periodj(j=1...m) time, the score of the travel route choice scheme drawn.Score value is more
Height, shows that this path of this choosing period of time more easily becomes optimum trip scheme.
After user is by selecting trip choosing period of time, travel route choice and transfer, different users can distinguish
Show that they in different periods desired optimization user's trip mode and change to trip mode, thus realize user when trip
Between and optimized choice spatially.
User's travel solutions feedback and assessment: be worth explanation, the recommendation results of the user's optimization trip calculated
After recommending user, only could push as final optimization trip mode obtaining customer acceptance.Therefore, for
The recommendation results calculated is estimated, provides the suggested design assessment square of user feedback result shown in formula (7)
Battle array.
It can be seen that this relational matrix is numerical relation matrix from formula (7).Wherein, MU-RRepresenting matrix title, U-R
Represent the ranks relation of this matrix.Sij(i=1...n, j=1...m) represents user UiSelect optimization travel solutions RjFor
The score of good trip scheme.Score value is the highest, more easily becomes the trip scheme that user is alternative.
The content that this patent is studied, through the analysis to a large number of users travel histories data, therefrom extracts user's trip
Period and at the vehicles of this period user's choice for traveling, and the user side of trip that user's trip route of correspondence is constituted
Case.By structure trip scheme set is estimated from safety, convenience, ageing and economy isometry index respectively
After, calculate the final score of each scheme.The most finally assert, it is recommended that the score of scheme is the highest, the easiest candidate becomes
The user optimized goes on a journey scheme, and obtains the selection of user.
It is understood that for the person of ordinary skill of the art, can conceive according to the technology of the present invention and do
Go out other various corresponding changes and deformation, and all these change all should belong to the protection model of the claims in the present invention with deformation
Enclose.
Claims (10)
1. a user based on mobile Internet optimization of travelling recommends method, it is characterised in that it comprises the steps:
S1, confirm user travel consider factor, described factor include go on a journey choosing period of time, travel route choice, trip mode
Select, transfer selects;
S2, according to above-mentioned factor build user's travel solutions tensor operation model;
S3, the result of calculation of the tensor operation model of user's travel solutions is added Candidate Recommendation scheme, and carry out candidate scheme
Score value calculates;
S4, the score value of the Candidate Recommendation scheme of acquisition is supplied to user carries out experiencing and obtain user's feedback knot to experiencing
Really, the trip scheme recommended user based on every evaluation index carries out score value ranking, thus obtains final suggested design and supply
User selects.
2. user based on mobile Internet as claimed in claim 1 optimization of travelling recommends method, it is characterised in that described
In step S1:
The module that selection mode selects includes safety coefficient S, convenience C, transfer relation T, economy E;S is used for weighing use
The safe coefficient of line mode is selected at family, and span is 0~10, and S value is the lowest, shows that this kind of trip mode is the most dangerous;C uses
In representing the convenience degree of user's travel mode, T for represent user to the selection of hourage and demand, E is used for representing use
The family requirement to travelling Financial cost.
3. user based on mobile Internet as claimed in claim 2 optimization of travelling recommends method, it is characterised in that described
In step S2:
The tensor operation model of user's travel solutions is as follows:
Rm=U*W*M*C*T, in formula, RmRepresenting the optimization travel mode that user selects, travel mode the most to be recommended, U represents use
Family, W represents alternative travel mode, and M represents travelling module, and T represents transfer relation.
4. user based on mobile Internet as claimed in claim 3 optimization of travelling recommends method, it is characterised in that
The incidence relation matrix of user and travel mode is as follows:
Wherein MU×WRepresenting matrix title, the ranks relation of U-W representing matrix, Pij(i=1...n, j=1...m) represents user Ui
Select travel mode WjProbability.
5. user based on mobile Internet as claimed in claim 4 optimization of travelling recommends method, it is characterised in that
Travel mode is as follows with the incidence relation matrix of module:
Wherein MW×MRepresenting matrix title, the ranks relation of W-M representing matrix, PiS,PiC,PiT,PiE(i=1...m) user is represented
UiSelect travel mode Wi(i=1...m) the safety of corresponding trip mode, convenience, ageing and economy.
6. user based on mobile Internet as claimed in claim 5 optimization of travelling recommends method, it is characterised in that
User is as follows with the incidence relation matrix of convenience:
Wherein this incidence relation matrix is Boolean matrix, wherein, MU-CRepresenting matrix title, C-C represents that the ranks of this matrix close
System;CabWhether there is transfer relation between the travel mode of (a, b=1...m) expression user, if there is its value is 1, be otherwise
0。
7. user based on mobile Internet as claimed in claim 6 optimization of travelling recommends method, it is characterised in that
User is as follows with the incidence relation matrix of transfer relation:
Wherein this relational matrix is numeric type incidence relation matrix, wherein, MU-TRepresenting matrix title, U-T represents the row of this matrix
Row relation, UTij(i=1...n, j=1...m) represents in historical data, user UiSelect period TjFor the optimal trip period
Probability.
8. user based on mobile Internet as claimed in claim 7 optimization of travelling recommends method, it is characterised in that
In described step S3:
The incidence relation matrix of the trip route that the trip period is corresponding with this period is as follows:
Wherein this incidence relation matrix is numerical relation matrix, wherein, MT-PRepresenting matrix title, T-P represents the ranks of this matrix
Relation, TPij(i=1...n, j=1...m) represents that user is selecting trip period Ti(i=1...n) and corresponding to this period
Trip route Paj(j=1...m) time, the score of the travel route choice scheme drawn;Score value is the highest, shows this choosing period of time
This path more easily becomes optimum trip scheme.
9. user based on mobile Internet as claimed in claim 8 optimization of travelling recommends method, it is characterised in that
In described step S4:
User is as follows with the incidence relation matrix of optimization travel solutions:
Wherein this incidence relation matrix is numerical relation matrix, wherein, MU-RRepresenting matrix title, U-R represents the ranks of this matrix
Relation, Sij(i=1...n, j=1...m) represents user UiSelect optimization travel solutions RjFor the score of optimal scheme of going on a journey,
Score value is the highest, more easily becomes the trip scheme that user is alternative.
10. a user based on mobile Internet travels optimization commending system, it is characterised in that it includes such as lower unit:
Factor determines unit, the factor considered for confirming user to travel, and described factor includes go on a journey choosing period of time, trip route
Selection, Passenger Traveling Choice, transfer select;
Unit set up by model, for building the tensor operation model of user's travel solutions according to above-mentioned factor;
Candidate scheme determines unit, for the result of calculation of the tensor operation model of user's travel solutions is added Candidate Recommendation side
Case, and carry out candidate scheme score value calculating;
Optimal case determines unit, carries out experiencing and obtaining use for the score value of the Candidate Recommendation scheme of acquisition is supplied to user
The family feedback result to experiencing, the trip scheme recommended user based on every evaluation index carries out score value ranking, thus obtains
Final suggested design selects for user.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610458701.9A CN106096000A (en) | 2016-06-22 | 2016-06-22 | A kind of user based on mobile Internet travel optimization recommend method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610458701.9A CN106096000A (en) | 2016-06-22 | 2016-06-22 | A kind of user based on mobile Internet travel optimization recommend method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106096000A true CN106096000A (en) | 2016-11-09 |
Family
ID=57239051
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610458701.9A Pending CN106096000A (en) | 2016-06-22 | 2016-06-22 | A kind of user based on mobile Internet travel optimization recommend method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106096000A (en) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106679683A (en) * | 2016-11-26 | 2017-05-17 | 上海亿账通互联网科技有限公司 | Method and device of acquiring travel information |
CN107356261A (en) * | 2017-06-14 | 2017-11-17 | 广东欧珀移动通信有限公司 | Air navigation aid and Related product |
CN108775904A (en) * | 2018-08-20 | 2018-11-09 | 蔚来汽车有限公司 | For the air navigation aid of charged area in parking lot |
CN108829744A (en) * | 2018-05-24 | 2018-11-16 | 湖北文理学院 | A kind of travel mode recommended method based on situation element and user preference |
CN109829588A (en) * | 2019-02-13 | 2019-05-31 | 苏州大学 | Tensor trajectory path planing method based on context |
CN110222894A (en) * | 2019-06-06 | 2019-09-10 | 阿里巴巴集团控股有限公司 | Advertisement placement method, device and equipment |
CN110573837A (en) * | 2017-06-30 | 2019-12-13 | Oppo广东移动通信有限公司 | Navigation method, navigation device, storage medium and server |
CN110785626A (en) * | 2017-06-30 | 2020-02-11 | Oppo广东移动通信有限公司 | Travel mode recommendation method and device, storage medium and terminal |
CN111201421A (en) * | 2017-10-12 | 2020-05-26 | 北京嘀嘀无限科技发展有限公司 | System and method for determining optimal transport service type in online-to-offline service |
CN112669603A (en) * | 2020-12-17 | 2021-04-16 | 广东南方通信建设有限公司 | Urban traffic cooperation method and device based on big data |
WO2021261987A1 (en) * | 2020-06-22 | 2021-12-30 | Mimos Berhad | System and method for providing destination recommendation to travelers |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104331404A (en) * | 2013-07-22 | 2015-02-04 | 中国科学院深圳先进技术研究院 | A user behavior predicting method and device based on net surfing data of a user's cell phone |
CN104331411A (en) * | 2014-09-19 | 2015-02-04 | 华为技术有限公司 | Item recommendation method and item recommendation device |
CN105550950A (en) * | 2015-11-20 | 2016-05-04 | 广东工业大学 | Location-based service travel recommendation method |
CN105653535A (en) * | 2014-11-13 | 2016-06-08 | 中国科学院沈阳计算技术研究所有限公司 | Media resource recommendation method |
-
2016
- 2016-06-22 CN CN201610458701.9A patent/CN106096000A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104331404A (en) * | 2013-07-22 | 2015-02-04 | 中国科学院深圳先进技术研究院 | A user behavior predicting method and device based on net surfing data of a user's cell phone |
CN104331411A (en) * | 2014-09-19 | 2015-02-04 | 华为技术有限公司 | Item recommendation method and item recommendation device |
CN105653535A (en) * | 2014-11-13 | 2016-06-08 | 中国科学院沈阳计算技术研究所有限公司 | Media resource recommendation method |
CN105550950A (en) * | 2015-11-20 | 2016-05-04 | 广东工业大学 | Location-based service travel recommendation method |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018095145A1 (en) * | 2016-11-26 | 2018-05-31 | 上海壹账通金融科技有限公司 | Method and device for acquiring travel information, and computer readable storage medium |
CN106679683B (en) * | 2016-11-26 | 2018-06-29 | 深圳壹账通智能科技有限公司 | Obtain the method and device of trip information |
CN106679683A (en) * | 2016-11-26 | 2017-05-17 | 上海亿账通互联网科技有限公司 | Method and device of acquiring travel information |
CN107356261A (en) * | 2017-06-14 | 2017-11-17 | 广东欧珀移动通信有限公司 | Air navigation aid and Related product |
US11274932B2 (en) | 2017-06-14 | 2022-03-15 | Guangdong Oppo Mobile Telecommunications Corp., Ltd. | Navigation method, navigation device, and storage medium |
CN110573837B (en) * | 2017-06-30 | 2023-10-27 | Oppo广东移动通信有限公司 | Navigation method, navigation device, storage medium and server |
CN110573837A (en) * | 2017-06-30 | 2019-12-13 | Oppo广东移动通信有限公司 | Navigation method, navigation device, storage medium and server |
CN110785626A (en) * | 2017-06-30 | 2020-02-11 | Oppo广东移动通信有限公司 | Travel mode recommendation method and device, storage medium and terminal |
CN111201421A (en) * | 2017-10-12 | 2020-05-26 | 北京嘀嘀无限科技发展有限公司 | System and method for determining optimal transport service type in online-to-offline service |
US11290547B2 (en) | 2017-10-12 | 2022-03-29 | Beijing Didi Infinity Technology And Development Co., Ltd. | Systems and methods for determining an optimal transportation service type in an online to offline service |
CN108829744B (en) * | 2018-05-24 | 2021-07-06 | 湖北文理学院 | Travel mode recommendation method based on situation elements and user preferences |
CN108829744A (en) * | 2018-05-24 | 2018-11-16 | 湖北文理学院 | A kind of travel mode recommended method based on situation element and user preference |
CN108775904A (en) * | 2018-08-20 | 2018-11-09 | 蔚来汽车有限公司 | For the air navigation aid of charged area in parking lot |
CN109829588A (en) * | 2019-02-13 | 2019-05-31 | 苏州大学 | Tensor trajectory path planing method based on context |
CN110222894A (en) * | 2019-06-06 | 2019-09-10 | 阿里巴巴集团控股有限公司 | Advertisement placement method, device and equipment |
WO2021261987A1 (en) * | 2020-06-22 | 2021-12-30 | Mimos Berhad | System and method for providing destination recommendation to travelers |
CN112669603A (en) * | 2020-12-17 | 2021-04-16 | 广东南方通信建设有限公司 | Urban traffic cooperation method and device based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106096000A (en) | A kind of user based on mobile Internet travel optimization recommend method and system | |
Yuan et al. | A survey of traffic prediction: from spatio-temporal data to intelligent transportation | |
Aghili | Complete solution for the time fractional diffusion problem with mixed boundary conditions by operational method | |
Selvi et al. | Application of modified wavelet and homotopy perturbation methods to nonlinear oscillation problems | |
Alvarez-Garcia et al. | Trip destination prediction based on past GPS log using a Hidden Markov Model | |
Jiang et al. | Boundary value problems for fractional differential equation with causal operators | |
Wu et al. | Analysis of fractional factor system for data transmission in SDN | |
Basavanagoud et al. | () Connectivity Index of Graphs | |
Pappalardo et al. | Future directions in human mobility science | |
Liu et al. | Modeling the interaction coupling of multi-view spatiotemporal contexts for destination prediction | |
Cui et al. | Deep integration of health information service system and data mining analysis technology | |
Koca et al. | A new approach for nuclear family model with fractional order Caputo derivative | |
Gandarias et al. | Conservation laws for a Boussinesq equation. | |
Voit et al. | Predicting the separation of time scales in a heteroclinic network | |
Kırdar et al. | A design proposal of integrated smart mobility application for travel behavior change towards sustainable mobility | |
Hendawi et al. | A vision for micro and macro location aware services | |
Shiralashetti et al. | Modified wavelet full-approximation scheme for the numerical solution of nonlinear volterra integral and integro-differential equations | |
Wu et al. | Application of experience economy and recommendation algorithm in tourism reuse of industrial wasteland | |
Arnesen et al. | A forward Markov model for predicting bicycle speed | |
Zuo et al. | Incorporating low-stress bicycling connectivity into expanded transit service coverage | |
Sun et al. | Mobile technology and studies on transport behavior: A literature analysis, integrated research model, and future research agenda | |
Gurevich | On classes of infinite loaded graphs with randomly deleted edges | |
Guan et al. | The teaching of sports science of track and field-based on nonlinear mathematical equations | |
Yao et al. | Predicting mobile users' next location using the semantically enriched geo-embedding model and the multilayer attention mechanism | |
Şahin | Dichromatic polynomial for graph of a (2, n)-torus knot |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161109 |