CN105674995B - A kind of method and device obtaining commuting route based on user's trip track - Google Patents
A kind of method and device obtaining commuting route based on user's trip track Download PDFInfo
- Publication number
- CN105674995B CN105674995B CN201511029772.9A CN201511029772A CN105674995B CN 105674995 B CN105674995 B CN 105674995B CN 201511029772 A CN201511029772 A CN 201511029772A CN 105674995 B CN105674995 B CN 105674995B
- Authority
- CN
- China
- Prior art keywords
- commuting
- section
- way
- track
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000004891 communication Methods 0.000 claims description 54
- 241000209094 Oryza Species 0.000 claims description 35
- 235000007164 Oryza sativa Nutrition 0.000 claims description 35
- 235000009566 rice Nutrition 0.000 claims description 35
- 238000010801 machine learning Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims 1
- 241000208340 Araliaceae Species 0.000 description 4
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 4
- 235000003140 Panax quinquefolius Nutrition 0.000 description 4
- 235000008434 ginseng Nutrition 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 2
- 238000012790 confirmation Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0261—Targeted advertisements based on user location
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Automation & Control Theory (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Navigation (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of method and devices that commuting route is obtained based on user's trip track.The method for obtaining commuting route based on user's trip track includes: the history trip track data for obtaining unknown commuting route user；Determine home location, company position and the commuting of the unknown commuting route user by way of section according to history trip track data；The commuting route of the unknown commuting route user is determined by way of section and history trip track data according to the home location, company position, commuting.The technical solution of the embodiment of the present invention provides a kind of method obtained with the higher commuting route of the practical route matching degree that commutes of user.
Description
Technical field
The present invention relates to intelligent identification technology field more particularly to a kind of commuting route is obtained based on user track of going on a journey
Method and device.
Background technique
It is used in vehicle business all kinds of, for example in the business such as windward driving or share-car, the commuting demand of user occupies critically important
The market share.Before pushing commuting vehicle order to user, according to order traffic path and the practical traffic path of user is needed
Decide whether to push order to user with degree.However, user will not be allowed to provide complete commuting in existing accreditation process
Route, a portion user can provide home address and CompanyAddress.Another part user will not usually provide home address
And CompanyAddress.In order to better meet the commuting demand of user, before push commutes order, need to obtain user on and off duty
Commute route.
The prior art does not provide the method that can obtain user's commuting route on and off duty automatically and accurately, so that user
Practical commuting route and the commuting route differences of order push are very big, so that the commuting order of push is not able to satisfy the reality of user
It needs.
Summary of the invention
In view of this, the embodiment of the present invention provides a kind of method and dress for obtaining commuting route based on user's trip track
It sets, to improve the accuracy for determining the practical route that commutes of user.
In a first aspect, the embodiment of the invention provides a kind of method for obtaining commuting route based on user's trip track, institute
The method of stating includes:
Obtain the history trip track data of unknown commuting route user；
According to the history go on a journey track data determine the unknown commuting home location of route user, company position and
Commuting is by way of section；
It is gone on a journey described in track data determination according to the home location, company position, commuting by way of section and the history
The commuting route of unknown commuting route user.
Second aspect, the embodiment of the invention also provides it is a kind of based on user go on a journey track obtain commuting route device,
Described device includes:
Data acquisition module, for obtaining the history trip track data of unknown commuting route user；
Critical data determining module, for determining the unknown commuting route user according to history trip track data
Home location, company position and commuting by way of section；
Commute route determination module, is used for according to the home location, company position, commuting by way of section and the history
Trip track data determines the commuting route of the unknown commuting route user.
The method and device provided in an embodiment of the present invention that commuting route is obtained based on user's trip track, utilizes user's
History trip track data obtains the commuting route of user, so that the commuting route and the actual commuting route of user that obtain coincide
Degree is more preferable, matching degree is higher, and the commuting route that will acquire is improved and pushed with vehicle class application program to user as order route
The success rate of order.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, of the invention other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is a kind of process for method that commuting route is obtained based on user's trip track that the embodiment of the present invention one provides
Figure；
Fig. 2 is the flow chart of the method for the processing history trip track data that the embodiment of the present invention one provides；
Fig. 3 is a kind of process of method that commuting route is obtained based on user's trip track provided by Embodiment 2 of the present invention
Figure；
Fig. 4 is a kind of process for method that commuting route is obtained based on user's trip track that the embodiment of the present invention three provides
Figure；
Fig. 5 is a kind of process for method that commuting route is obtained based on user's trip track that the embodiment of the present invention four provides
Figure；
Fig. 6 is that the track street that is not connected to that the embodiment of the present invention four provides is connected to schematic diagram；
Fig. 7 is a kind of process for method that commuting route is obtained based on user's trip track that the embodiment of the present invention five provides
Figure；
Fig. 8 is a kind of structure for device that commuting route is obtained based on user's trip track that the embodiment of the present invention six provides
Figure.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
In description, only some but not all contents related to the present invention are shown in the drawings.
Embodiment one
Fig. 1 is a kind of process for method that commuting route is obtained based on user's trip track that the embodiment of the present invention one provides
Figure.The present embodiment is applicable to the case where wanting to obtain the commuting route of unknown commuting route user.The route that commutes is usually to use
Route between the family and company at family, or it can be appreciated that be user on the road that some period (several months) frequently uses
Line.This method can be executed by obtaining the device of commuting route based on user's trip track, and wherein the device can be by software
And/or hardware is realized, the device usually it is configurable in the server.It is provided in this embodiment to be gone on a journey based on user with reference to Fig. 1
The method that track obtains commuting route can specifically include as follows:
S110, the history trip track data for obtaining unknown commuting route user.
Wherein, history trip track data is the user's history position acquired by internet or each application client
The data that information summarizes.For example, user carries out the position data of self poisoning using shopping client, map client is used
The navigation routine etc. to navigate is held, can be used as history trip track data；User fills out when internet carries out Account Registration
The position data write.It obtains history trip track data and can be and obtain unknown commuting route user within a preset time interval
History trip track data obtains history trip track data of the unknown commuting route user in default trip number, tool
The prefixed time interval of body and default trip number can be defined according to the actual situation.
S120, track data of being gone on a journey according to the history determine the home location of the unknown commuting route user, company
Position and commuting are by way of section.
Illustratively, home location is the position of the user's residence directly or indirectly obtained by history trip track data
Information, preferably in map a coordinate points；Company position is directly or indirectly obtained by history trip track data
The location information of user company, preferably in map a coordinate points.For the route that user frequently uses, house position
Setting actually is two endpoints for frequently using route with company position.For having for the user of specific rule of life, frequency
Numerous possible more than one of the route used, then home location and company position can also be with more than one.Commuting is logical by way of section
The location information by commuting route that history trip track data directly or indirectly obtains is crossed, two preferably in map
Section between crossing, or be the smallest section vector units in electronic map, each unknown commuting route user can have
Multiple commutings are by way of section.
S130, it is determined according to the home location, company position, commuting by way of section and history trip track data
The commuting route of the unknown commuting route user.
Illustratively, commuting route determination mode, which can be, obtains home location and company in history trip track data
Whole communication paths between position determine the big route of probability as commuting route according to setting strategy from communication path.
The method that commuting route is obtained based on user's trip track that the embodiment of the present invention one provides, it is unknown logical by utilizing
The history trip track data of diligent route user determines the home location, company position and commuting way of unknown commuting route user
It through section, and then determines the commuting route of unknown commuting route user, determining commuting route is used as with vehicle class application program
Order route improve the success rate of push order so that the practical commuting route matching degree of order route and user are high.
In the above-mentioned technical solutions, living for the unknown commuting route user is determined according to history trip track data
Residence position, company position and commuting preferably are carried out following method by way of section, referring to fig. 2, comprising:
S121, history trip track data is divided into path locus data and non-rice habitats track data.
Specifically, path locus data are the position data set in history trip track data on road, can characterize
The path of unknown commuting route user trip.Non-rice habitats track data is to remove path locus in history trip track data
Remaining outer position data set can characterize position of the unknown commuting route user in building or on the non-rice habitats such as open space
Confidence breath.So-called road, the section concept as in electronic map.
S122, determine the commuting of the unknown commuting route user by way of section according to the path locus data.
Illustratively, each commuting of unknown commuting route user can be determined by way of section by path locus data.Really
Determine mode and can be to be identified using commuting by way of section identifier, wherein commuting by way of section identifier is to utilize engineering
Learning system model obtains the commuting of known commuting route user by way of section and non-commuting by way of section training.Method of determination
Can also be the travel time according to path locus data, be chosen at the work hours section and/or quitting time section by way of section
As commuting by way of section.
S123, home location and the company position that the unknown commuting route user is determined according to the non-rice habitats track data
It sets.
Illustratively, home location and the company position of unknown commuting route user can be determined by non-rice habitats track data
It sets.Method of determination, which can be, obtains home location and company position that unknown commuting route user provides.Method of determination can also be with
To be identified using location indentifier, wherein location indentifier be using machine learning system model to known home location and
What home location cluster, company position cluster and the inoperative position cluster of company position user was trained, wherein the house position
Setting cluster, company position cluster and inoperative position cluster is by the non-rice habitats track data to known home location and company position user
Cluster obtains.The region that section intensively occurs between method of determination can also be acquisition user at work, will be in the most close of shopping centre
Integrate position mark as company position, obtains the user region that section intensively occurs on one's own time, it will be in the most intensive of residential block
Position mark is home location.
Embodiment two
The present embodiment provides a kind of side that commuting route is obtained based on user's trip track based on above-described embodiment
Method.Fig. 3 is a kind of flow chart of method that commuting route is obtained based on user's trip track provided by Embodiment 2 of the present invention.Ginseng
Fig. 3 is examined, the method provided in an embodiment of the present invention for obtaining commuting route based on user's trip track may include as follows:
S210, the history trip track data for obtaining unknown commuting route user.
S220, history trip track data is divided into path locus data and non-rice habitats track data.
S230, determine the commuting of the unknown commuting route user by way of section according to the path locus data.
S240, the non-rice habitats track data is clustered, obtains 1 clusters.
Specifically, can be clustered with clustering algorithm to the non-rice habitats track data, clustering algorithm can be segmentation
Method (such as: Kmeans) is based on density clustering algorithm (such as: dbscan), is based on Grid Clustering Algorithm (such as: wavecluster)
Deng.Available 1 clusters after cluster, each cluster include the location data of certain amount or certain density, and
The quantity or density for the position data for including between each point cluster can be different.
S250, each described cluster is identified using location indentifier, with determine home location cluster, company position cluster and
Inoperative position cluster, and determine home location and company position, the location indentifier is using machine learning system model to
Know what the home location cluster, company position cluster and inoperative position cluster of home location and company position user were trained,
Described in home location cluster, company position cluster and inoperative position cluster be by the non-of known home location and company position user
Path locus data clusters obtain.
Illustratively, before being identified using location indentifier to each described cluster, it is thus necessary to determine that location indentifier, really
Determine step to specifically include: obtaining a certain number of known home locations and the history trip track data of company position user, it will
Each history trip track data uses clustering algorithm according to whether path locus data and non-rice habitats track data are divided on road
Each non-rice habitats track data is clustered, multiple tracing point clusters are obtained, the point cluster comprising home location is labeled as house position
(home) cluster is set, the point cluster comprising company position is labeled as company position (company) cluster, the point cluster of remaining position is labeled as
Inoperative position (useless) cluster.Using obtained each cluster as the training data of location indentifier, machine learning system model is utilized
Location indentifier is trained according to preset attribute, confirms location indentifier.Wherein preset attribute is can to determine user position
The attribute of confidence breath, can set manually, and can also be determined based on model training.Preset attribute can go out in each cluster for user
Show each WLAN (Wireless in the ratio, user's ratio that daytime and night occur in each cluster, each cluster of number of days
Fidelity, wifi) probability calculation that occurs the wifi entropy, the ratio that occurs in cluster each period in one day of user that come out
At least one of number that example, user occur in cluster etc..
After determining location indentifier, identified using each point cluster of the location indentifier to unknown commuting route user,
Determine home location cluster, company position cluster and inoperative position cluster.The center point coordinate of home location cluster is denoted as unknown commuting road
The center point coordinate of company position cluster is denoted as the company position of unknown commuting route user by the home location of line user.
S260, it is determined according to the home location, company position, commuting by way of section and history trip track data
The commuting route of the unknown commuting route user.
It is provided by Embodiment 2 of the present invention it is a kind of gone on a journey the method that track obtains commuting route based on user, by will be unknown
The history trip track data of commuting route user is divided into path locus data and non-rice habitats track data, according to path locus number
It commutes according to determining by way of section, non-rice habitats track data is clustered and identified using clustering algorithm and location indentifier, really
The home location and company position for determining user, further according to home location, company position and commuting by way of section in history trip rail
The commuting route of unknown commuting route user is determined in mark data.This method can accurately determine unknown commuting route user's
Home location and company position, and then commuting route is accurately determined, so that the commuting route determined and the actual commuting of user
Route matching degree is higher.
Embodiment three
The present embodiment provides a kind of side that commuting route is obtained based on user's trip track based on above-described embodiment
Method.Fig. 4 is a kind of flow chart for method that commuting route is obtained based on user's trip track that the embodiment of the present invention three provides.Ginseng
Fig. 4 is examined, the method provided in an embodiment of the present invention for obtaining commuting route based on user's trip track may include as follows:
S310, the history trip track data for obtaining unknown commuting route user.
S320, history trip track data is divided into path locus data and non-rice habitats track data.
S330, determine the commuting of the unknown commuting route user by way of section according to the path locus data.
S340, the home location provided in the non-rice habitats track data by the unknown commuting route user and public affairs are obtained
Take charge of position.
Illustratively, home location and company position can be prompts unknown commuting route user to provide house in registration
Position and company position, or motivate unknown commuting route user to provide home location and company using the method rewarded with compensation
Position.Unknown commuting route user can directly acquire home location and company position after providing home location and company position.
S350, it is determined according to the home location, company position, commuting by way of section and history trip track data
The commuting route of the unknown commuting route user.
The method for obtaining commuting route based on user's trip track that the embodiment of the present invention three provides, obtains unknown commuting road
The home location and company position that line user provides, and commuted according to path locus data acquisition by way of section, pass through house position
Set, company position, commuting by way of section history trip track data in determine it is unknown commuting route user commuting route.It should
The step of method can directly acquire the home location and company position of unknown commuting route user, simplify commuting route determination,
Make determining commuting route and actual commuting route matching degree higher simultaneously, raising is pushed with vehicle class application program to user
The success rate of commuting order.
Example IV
The present embodiment provides a kind of side that commuting route is obtained based on user's trip track based on above-described embodiment
Method.Fig. 5 is a kind of flow chart for method that commuting route is obtained based on user's trip track that the embodiment of the present invention four provides.Ginseng
Fig. 5 is examined, the method provided in an embodiment of the present invention for obtaining commuting route based on user's trip track may include as follows:
S410, the history trip track data for obtaining unknown commuting route user.
S420, history trip track data is divided into path locus data and non-rice habitats track data.
S430, the path locus data are divided as unit of street, obtains whole track streets, is denoted as rail
Mark street set.
Illustratively, path locus data are divided, can is to be divided as unit of street, or with
Preset length is that unit is divided, and is preferably divided as unit of street.The street is one between two crossings
Section street.After path locus data are divided as unit of street, track street set is obtained.
S440, each track street in the set of the track street is identified by way of section identifier using commuting,
The commuting for obtaining unknown commuting route user is identified as the probability to commute by way of section by way of section and each track street
Value, the commuting are to the commuting of known commuting route user using machine learning system model by way of road by way of section identifier
What section and non-commuting were obtained by way of section training.
Illustratively, a commuting is by way of the corresponding track street in section.Using commuting by way of section identifier to institute
State track street set in each track street identified before, first to determine commuting by way of section identifier, determine step
It specifically includes: obtaining the track street set of the known commuting route user of certain amount, each track street for the route that commutes is marked
Commuting is denoted as by way of section, remaining track street sign is non-commuting by way of section.By obtained each commuting by way of section and
Each non-training data to commute by way of section as commuting by way of section identifier, using machine learning system model according to default
Attribute is trained commuting by way of section identifier, and confirmation commuting is by way of section identifier.Wherein preset attribute be can be true
User's commuting is determined by way of the attribute in section, can be set manually, and can also be determined based on model training.Preset attribute can be use
The number of days and user trajectory street set of number of days, appearance that family track street set occurs occur minimum number of days ratio,
Ratio and number that daytime and night occur, the track street of daytime and night frequency of occurrence and the user be integrated into daytime and
There is at least one of the ratio of minimum number, the ratio that each period occurs in one day and number etc. in night.
In confirmation commuting after the identifier of section, using commuting by way of section identifier to unknown commuting route user's
Track street set is identified that the commuting for obtaining unknown commuting route user is identified by way of section and each track street
For the probability value by way of section that commutes.For example, it is R that track street, which is identified as commuting by way of the probability value in section, known
Not Wei non-probability value of the commuting by way of section be r, then R+r=1.Preferably, when track street is identified as commuting by way of section
Probability value be greater than preset value when, by the track street be identified as commuting by way of section, the size of preset value can be according to reality
Situation is set.
S450, home location and the company position that the unknown commuting route user is determined according to the non-rice habitats track data
It sets.
S460, it is determined according to the home location, company position, commuting by way of section and history trip track data
The commuting route of the unknown commuting route user.
What the embodiment of the present invention four provided is gone on a journey the method that track obtains commuting route based on user, by by unknown commuting
The history trip track data of route user is divided into path locus data and non-rice habitats track data, is known using commuting by way of section
Commuting in other device identification path locus data determines the home location and public affairs of user using non-rice habitats track data by way of section
Position is taken charge of, and then determines the commuting route of unknown commuting route user.This method can accurately determine that unknown commuting route is used
The commuting at family is by way of section, so that finally determining commuting route and the actual commuting route matching degree of user is higher, improves and uses
Vehicle class application program pushes the success rate of commuting order to user.
Technical solution in the embodiment of the present invention preferably can be according to the home location, company position, commuting
Before the commuting route that section and history trip track data determine the unknown commuting route user, further includes:
Examine the history trip track data connection situation；Be not connected to track street if having, by it is described be not connected to track street with
It is not connected to the smallest track street in track street described in distance in the history trip track data to be connected, connected path is denoted as
It is new that track street is added, and the new commuting that track street is added is by way of the commuting way that section probability value is adjacent both ends track street
Half through section probability value sum.
There is the case where not being connected to other track streets in track street even in history trip track data.It at this time will not
Connection track street is connected with not being connected to the smallest track street of track street distance value, and connected path is on road, quilt
It is denoted as new addition track street route.Fig. 6 is that the track street that is not connected to that the embodiment of the present invention four provides is connected to schematic diagram.Such as figure
Shown in 6, it is not connected to track street 601 in history trip track data, distance is not connected to the smallest track street in track street 601
Road 602 will not be connected to track street 601 and be connected with track street 602, be denoted as new addition track street 603.Wherein, new to be added
The commuting in track street 603 is not connected to track by way of the calculation method of section probability value, preferably adjacent both ends track street
Half of the commuting in street 601 and track street 602 by way of section probability value sum.
Embodiment five
The present embodiment provides a kind of side that commuting route is obtained based on user's trip track based on above-described embodiment
Method.Fig. 7 is a kind of flow chart for method that commuting route is obtained based on user's trip track that the embodiment of the present invention five provides.Ginseng
Fig. 7 is examined, the method provided in an embodiment of the present invention for obtaining commuting route based on user's trip track may include as follows:
S510, the history trip track data for obtaining unknown commuting route user.
S520, track data of being gone on a journey according to the history determine the home location of the unknown commuting route user, company
Position and commuting are by way of section.
S530, it is commuted based on described by way of section, determines home location and institute described in the history trip track data
State the communication path between company position.
Illustratively, whole communication paths in history trip track data between home location and company position are obtained,
Wherein communication path is at least through a commuting by way of section, and in the coconnected trajectory path of road.
Preferably, the probability value N number of commuting from high to low of the unknown commuting route user is obtained by way of section,
N is at least 2；N number of commuting is calculated by way of each subset of the corresponding set in section, each subset includes described at least one
Commuting is by way of section；Determine the corresponding most short communication path of each subset, the most short communication path is in the home location
The whole for including between the company position and by way of the subset commuting is by way of section.
Illustratively, the highest commuting of N number of probability value is obtained by way of section, and wherein N is at least 2, and is the bigger the better.It obtains
N number of commuting be denoted as commuting by way of section and gather by way of section, calculate commuting by way of section and gather corresponding each subset, every height
It concentrates comprising at least one commuting by way of section, determines the corresponding all connections of subset each between home location and company position
Path, each communication path include that the whole in corresponding subset commutes by way of section, it is preferred that determine each subset whole access
Most short communication path in diameter.Such as N, when taking 3, commuting is respectively the highest section 1 of probability value, section 2 and section by way of section
3.Then commuting is (section 1) by way of section set (section 1, section 2, section 3) corresponding subset, (section 2), (section 3),
(section 1, section 2), (section 1, section, 3), (section 2, section 3), (section 1, section 2, section 3).In home location and public affairs
Communication path between department position by way of (section 1) has 5, and the communication path of the shortest distance is taken to be denoted as most short communication path 1,
Communication path between home location and company position by way of (section 2) has 3, takes the communication path of the shortest distance to be denoted as most short
Communication path 2, and so on, most short communication path 1 is finally obtained to most short communication path 7.
S540, it is commuted based on described by way of the probability value in section, calculates the commuting route probability value of the communication path.
Illustratively, confirm that the commuting in each track street of unknown commuting route user, can after the probability value in section
The commuting route probability value of each communication path is calculated by way of section probability value by commuting.Calculate the commuting route probability of communication path
The method of value, preferably each track street in acquisition communication path is probability value of the commuting by way of section, by each probability value phase
Multiply the commuting route probability value as the communication path.For example, including 6 tracks street, each track street in 1 communication path
Probability value of the commuting by way of section be respectively 0.23,0.51,0.24,0.78,0.65,0.71, each probability value is multiplied to obtain
0.01013387544, then the commuting route probability value of the communication path is 0.01013387544.
S550, the commuting route that the unknown commuting route user is determined according to the commuting route probability value.
Illustratively, after the commuting route probability value for calculating each communication path, the maximum communication path conduct of probability value is taken
The commuting route of unknown commuting route user.If most probable value corresponds at least two communication paths, most probable value pair is taken
Commuting route of the shortest communication path of total path as unknown commuting route user in the communication path answered.For example, calculating 8
The probability value of communication path is respectively 0.0145,0.756,0.207,0.0597,0.0147,0.0451,0.0023,0.367, then
Take 0.756 corresponding communication path as the commuting route of unknown commuting route user.If the probability value difference of 8 communication paths
It is 0.0145,0.756,0.207,0.0597,0.756,0.0147,0.0023,0.367, there is the probability value of two communication paths
It is 0.756, the total path of first communication path is 3.4 kilometers, and the total path of Article 2 communication path is 3.1 kilometers, then takes
Commuting route of the Article 2 communication path as unknown commuting route user.
The method that commuting route is obtained based on user's trip track that the embodiment of the present invention five provides, it is unknown logical by obtaining
The history trip track data of diligent route user determine home location, company position and commuting by way of section, according to commuting by way of
Section and its probability value determine communication path and its probability value between home location and company position, and then determine not
Know the commuting route of commuting route user.The commuting route for the unknown commuting route user that this method determines and practical commuting route
Matching degree is higher, and push order can be improved as the order route pushed with vehicle class application program in the commuting route that will acquire
Success rate.
Embodiment six
Fig. 8 is a kind of structure for device that commuting route is obtained based on user's trip track that the embodiment of the present invention six provides
Figure.The present embodiment is applicable to the case where wanting to obtain the commuting route of unknown commuting route user.With reference to Fig. 8, the present embodiment
The device for obtaining commuting route based on user's trip track provided can specifically include as follows:
Data acquisition module 801, for obtaining the history trip track data of unknown commuting route user；
Critical data determining module 802, for determining the unknown commuting route according to history trip track data
Home location, company position and the commuting of user is by way of section；
Commute route determination module 803, for according to the home location, company position, commuting by way of section and described
History trip track data determines the commuting route of the unknown commuting route user.
Further, the critical data determining module 802 may include:
Data divide submodule, for history trip track data to be divided into path locus data and non-rice habitats track
Data；
Commuting determines submodule by way of section, for determining that the unknown commuting route is used according to the path locus data
The commuting at family is by way of section；
Position determination submodule, for determining living for the unknown commuting route user according to the non-rice habitats track data
Residence position and company position.
Preferably, the position determination submodule may include:
Data clusters unit obtains 1 clusters for clustering to the non-rice habitats track data；
Point cluster determination unit, for being identified using location indentifier to each described cluster, with determine home location cluster,
Company position cluster and inoperative position cluster, and determine home location and company position, the location indentifier is to utilize machine learning
System model instructs the home location cluster, company position cluster and inoperative position cluster of known home location and company position user
It gets, wherein the home location cluster, company position cluster and inoperative position cluster are by known home location and company
The non-rice habitats track data of position user clusters to obtain.
Preferably, the position determination submodule specifically can be used for:
The home location provided in the non-rice habitats track data by the unknown commuting route user and company position are provided
It sets.
Further, the commuting determines that submodule may include: by way of section
Track street determination unit obtains whole for dividing the path locus data as unit of street
Track street, be denoted as track street set；
Commuting is by way of section determination unit, for utilizing commuting by way of section identifier in the set of the track street
Each track street is identified that the commuting for obtaining unknown commuting route user is identified as by way of section and each track street
It commutes by way of the probability value in section, the commuting is using machine learning system model to known commuting road by way of section identifier
The commuting of diameter user is obtained by way of section and non-commuting by way of section training.
Further, the commuting route determination module 803 may include:
Communication path determines submodule, for, by way of section, determining the history trip track data based on the commuting
Described in communication path between home location and the company position；
Probability value computational submodule, for, by way of the probability value in section, calculating the communication path based on the commuting
Commute route probability value；
Commute route determination submodule, for determining the unknown commuting route user according to the commuting route probability value
Commuting route.
Preferably, the communication path determines that submodule may include:
Commuting is by way of section acquiring unit, for obtaining the probability value of the unknown commuting route user from high to low
N number of commuting by way of section, N is at least 2；
Subset determing unit, for calculating each subset of N number of commuting by way of the corresponding set in section, each subset
Comprising commuting described at least one by way of section；
Most short communication path determination unit, for determining the corresponding most short communication path of each subset, the most short company
The whole that path includes between the home location and the company position and by way of the subset commuting is by way of road
Section.
Further, described device can also include:
Detection module, for examining the history trip track data connection situation；
If adjacent modules are not connected to track street and history trip for described be not connected to track street for having
It is not connected to the smallest track street in track street in track data described in distance to be connected, connected path is denoted as new addition track street
Road, and the new commuting that track street is added by way of the commuting that section probability value is adjacent both ends track street by way of section probability value
The half of sum.
The device that commuting route is obtained based on user's trip track that the embodiment of the present invention six provides, it is any in fact with the present invention
It applies the method that commuting route is obtained based on user's trip track provided by example and belongs to same inventive concept, the present invention times can be performed
The method for obtaining commuting route based on user's trip track provided by embodiment of anticipating is had execution and is obtained based on user's trip track
Take the corresponding functional module of method and beneficial effect of commuting route.The not technical detail of detailed description in the present embodiment, can
The method that commuting route is obtained based on user's trip track provided referring to any embodiment of that present invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (16)
1. a kind of method for obtaining commuting route based on user's trip track characterized by comprising
Obtain the history trip track data of unknown commuting route user；
Home location, company position and the commuting of the unknown commuting route user are determined according to history trip track data
By way of section；
According to the home location, company position, commuting by way of section and the history trip track data determine it is described unknown
The commuting route of commuting route user；
The home location of the unknown commuting route user is determined according to history trip track data and company position includes:
History trip track data is divided into path locus data and non-rice habitats track data；
The home location and company position of the unknown commuting route user are determined according to the non-rice habitats track data；
Wherein, the home location and company position packet of the unknown commuting route user are determined according to the non-rice habitats track data
It includes:
The non-rice habitats track data is clustered, 1 clusters are obtained；
Each described cluster is identified using location indentifier, to determine home location cluster, company position cluster and inoperative position
Cluster, and determine home location and company position.
2. the method according to claim 1, wherein according to the history go on a journey track data determine commuting by way of
Section includes:
Determine the commuting of the unknown commuting route user by way of section according to the path locus data.
3. the method according to claim 1, wherein the location indentifier is to utilize machine learning system model
The home location cluster, company position cluster and inoperative position cluster of known home location and company position user are trained to obtain
, wherein the home location cluster, company position cluster and inoperative position cluster are by known home location and company position use
The non-rice habitats track data at family clusters to obtain.
4. the method according to claim 1, wherein being determined according to the non-rice habitats track data described unknown logical
The home location and company position of diligent route user include:
The home location and company position provided in the non-rice habitats track data by the unknown commuting route user is provided.
5. according to the method described in claim 2, it is characterized in that, determining the unknown commuting according to the path locus data
The commuting of route user includes: by way of section
The path locus data are divided as unit of street, obtain whole track streets, are denoted as track street collection
It closes；
Each track street in the set of the track street is identified by way of section identifier using commuting, is obtained unknown logical
The commuting of diligent route user is identified as the probability value to commute by way of section, the commuting by way of section and each track street
It is to the commuting of known commuting route user using machine learning system model by way of section and non-commuting by way of section identifier
By way of section, training is obtained.
6. according to the method described in claim 5, it is characterized in that, according to the home location, company position, commuting by way of road
Section and history trip track data determine that the commuting route of the unknown commuting route user includes:
Based on the commuting by way of section, home location and the company position described in the history trip track data are determined
Between communication path；
Based on the commuting by way of the probability value in section, the commuting route probability value of the communication path is calculated；
The commuting route of the unknown commuting route user is determined according to the commuting route probability value.
7. according to the method described in claim 6, it is characterized in that, determining that the history goes out by way of section based on the commuting
Communication path between home location described in row track data and the company position includes:
The N number of commuting of the probability value of the unknown commuting route user from high to low is obtained by way of section, N is at least 2；
N number of commuting is calculated by way of each subset of the corresponding set in section, each subset includes at least one described commuting
By way of section；
Determine the corresponding most short communication path of each subset, the most short communication path is in the home location and the company
The whole for including between position and by way of the subset commuting is by way of section.
8. according to the method described in claim 5, it is characterized in that, according to the home location, company position, commuting by way of road
Section and history trip track data determine before the commuting route of the unknown commuting route user, further includes:
Examine the history trip track data connection situation；
It is not connected to track street if having, is not connected to described in track street and history trip track data described in distance
It is not connected to the smallest track street in track street to be connected, connected path is denoted as new addition track street, and new addition track street
The commuting in road is by way of the commuting that section probability value is adjacent both ends track street by way of the half of section probability value sum.
9. a kind of device for obtaining commuting route based on user's trip track characterized by comprising
Data acquisition module, for obtaining the history trip track data of unknown commuting route user；
Critical data determining module, for determining living for the unknown commuting route user according to history trip track data
Residence position, company position and commuting are by way of section；
Commute route determination module, for being gone on a journey according to the home location, company position, commuting by way of section and the history
Track data determines the commuting route of the unknown commuting route user；
The critical data determining module includes:
Data divide submodule, for history trip track data to be divided into path locus data and non-rice habitats track number
According to；
Position determination submodule, for determining the house position of the unknown commuting route user according to the non-rice habitats track data
It sets and company position；
Wherein, the position determination submodule includes:
Data clusters unit obtains 1 clusters for clustering to the non-rice habitats track data；
Point cluster determination unit, for being identified using location indentifier to each described cluster, to determine home location cluster, company
Position cluster and inoperative position cluster, and determine home location and company position.
10. device according to claim 9, which is characterized in that the critical data determining module includes:
Commuting determines submodule by way of section, for determining the unknown commuting route user's according to the path locus data
Commuting is by way of section.
11. device according to claim 9, which is characterized in that the location indentifier is to utilize machine learning system mould
Type is trained to obtain to the home location cluster, company position cluster and inoperative position cluster of known home location and company position user
, wherein the home location cluster, company position cluster and inoperative position cluster are by known home location and company position use
The non-rice habitats track data at family clusters to obtain.
12. device according to claim 10, which is characterized in that the position determination submodule is specifically used for:
The home location and company position provided in the non-rice habitats track data by the unknown commuting route user is provided.
13. device according to claim 10, which is characterized in that the commuting determines that submodule includes: by way of section
Track street determination unit obtains whole rails for dividing the path locus data as unit of street
Mark street is denoted as track street set；
Commuting is by way of section determination unit, for utilizing commuting by way of section identifier to each rail in the set of the track street
Mark street is identified that the commuting for obtaining unknown commuting route user is identified as commuting by way of section and each track street
Probability value by way of section, the commuting are to be used using machine learning system model known commuting path by way of section identifier
The commuting at family is obtained by way of section and non-commuting by way of section training.
14. device according to claim 13, which is characterized in that the commuting route determination module includes:
Communication path determines submodule, for, by way of section, determining institute in the history trip track data based on the commuting
State the communication path between home location and the company position；
Probability value computational submodule, for, by way of the probability value in section, calculating the commuting of the communication path based on the commuting
Route probability value；
Commute route determination submodule, for determining that the unknown commuting route user's is logical according to the commuting route probability value
Diligent route.
15. device according to claim 14, which is characterized in that the communication path determines that submodule includes:
Commuting is by way of section acquiring unit, for obtaining the N of the probability value of the unknown commuting route user from high to low
By way of section, N is at least 2 for a commuting；
Subset determing unit, for calculating N number of commuting by way of each subset of the corresponding set in section, each subset includes
At least one described commuting is by way of section；
Most short communication path determination unit, for determining the corresponding most short communication path of each subset, the most short access
The whole that diameter includes between the home location and the company position and by way of the subset commuting is by way of section.
16. device according to claim 13, which is characterized in that further include:
Inspection module, for examining the history trip track data connection situation；
If adjacent modules are not connected to track street and history trip track for described be not connected to track street for having
The smallest track street in track street is not connected in data described in distance to be connected, connected path is denoted as new addition track street,
And the new commuting that track street is added by way of the commuting that section probability value is adjacent both ends track street by way of section probability value and
Half.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511029772.9A CN105674995B (en) | 2015-12-31 | 2015-12-31 | A kind of method and device obtaining commuting route based on user's trip track |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511029772.9A CN105674995B (en) | 2015-12-31 | 2015-12-31 | A kind of method and device obtaining commuting route based on user's trip track |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105674995A CN105674995A (en) | 2016-06-15 |
| CN105674995B true CN105674995B (en) | 2019-03-08 |
Family
ID=56298342
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511029772.9A Active CN105674995B (en) | 2015-12-31 | 2015-12-31 | A kind of method and device obtaining commuting route based on user's trip track |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105674995B (en) |
Families Citing this family (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106289291A (en) * | 2016-07-26 | 2017-01-04 | 北京奇虎科技有限公司 | The recommendation method and apparatus of navigation way |
| CN107798648A (en) * | 2016-09-07 | 2018-03-13 | 北京嘀嘀无限科技发展有限公司 | A kind of potential passenger of regular bus excavates processing method and server |
| US10355788B2 (en) * | 2017-01-06 | 2019-07-16 | Uber Technologies, Inc. | Method and system for ultrasonic proximity service |
| CN106931974B (en) * | 2017-03-29 | 2020-04-03 | 清华大学 | A method for calculating personal commuting distance based on mobile terminal GPS positioning data records |
| CN107277103A (en) * | 2017-04-27 | 2017-10-20 | 华晓燕 | It is a kind of based on the commuting service system accurately pushed and implementation method |
| CN107038858B (en) * | 2017-05-25 | 2019-05-28 | 厦门大学 | Commute private car dynamic share-car recommended method |
| CN108848463B (en) * | 2018-06-29 | 2019-09-24 | 百度在线网络技术（北京）有限公司 | Commute route determination method and apparatus |
| CN108960736A (en) * | 2018-07-13 | 2018-12-07 | 北京百度网讯科技有限公司 | For sending the method and device of information |
| CN109256029B (en) * | 2018-09-12 | 2021-09-03 | 广州小鹏汽车科技有限公司 | Automatic setting method and device for location attribute |
| CN110751531A (en) * | 2018-11-13 | 2020-02-04 | 北京嘀嘀无限科技发展有限公司 | Track identification method and device and electronic equipment |
| CN109495856B (en) * | 2018-12-18 | 2021-08-10 | 成都方未科技有限公司 | Mobile phone user type marking method based on big data |
| CN109726874A (en) * | 2019-01-18 | 2019-05-07 | 创新奇智(北京)科技有限公司 | Travel route planing method, calculates equipment and storage medium at device |
| CN109919357B (en) * | 2019-01-30 | 2021-01-22 | 创新先进技术有限公司 | Data determination method, device, equipment and medium |
| CN111696343B (en) * | 2019-03-12 | 2022-04-05 | 北京嘀嘀无限科技发展有限公司 | Track data processing method and device |
| CN109948070B (en) * | 2019-03-13 | 2022-08-09 | 深圳市同行者科技有限公司 | Method for analyzing and determining positions of home and company, storage medium and terminal |
| CN111721306B (en) * | 2019-03-20 | 2022-07-05 | 北京嘀嘀无限科技发展有限公司 | Road matching method and device, electronic equipment and readable storage medium |
| CN111832788B (en) * | 2019-04-23 | 2024-03-29 | 北京嘀嘀无限科技发展有限公司 | Service information generation method, device, computer equipment and storage medium |
| CN110111054A (en) * | 2019-05-09 | 2019-08-09 | 上汽安吉物流股份有限公司 | Spell the generation method and device, computer-readable medium and logistics system of single network model |
| CN112235778B (en) * | 2019-06-26 | 2022-06-14 | 中国移动通信集团湖南有限公司 | Group Member Determination Method and Server |
| CN113190769B (en) * | 2021-05-08 | 2023-09-19 | 北京百度网讯科技有限公司 | Communication characteristic data determining method, device, electronic equipment and storage medium |
| CN113704373B (en) * | 2021-08-19 | 2023-12-05 | 国家计算机网络与信息安全管理中心 | User identification method, device and storage medium based on movement track data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103389100A (en) * | 2013-08-02 | 2013-11-13 | 上海梦擎信息科技有限公司 | System for freely navigating real-time road condition |
| CN103542848A (en) * | 2012-07-17 | 2014-01-29 | 株式会社电装 | Destination recommendation system and destination recommendation method |
| CN103697901A (en) * | 2013-12-25 | 2014-04-02 | 沈阳美行科技有限公司 | Solving method for automatic guidance patterns of vehicle navigation |
| CN104102719A (en) * | 2014-07-18 | 2014-10-15 | 百度在线网络技术（北京）有限公司 | Track information pushing method and device |
| CN104165634A (en) * | 2014-07-28 | 2014-11-26 | 广州视源电子科技股份有限公司 | Path planning method based on user use habit |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8892350B2 (en) * | 2011-12-16 | 2014-11-18 | Toyoda Jidosha Kabushiki Kaisha | Journey learning system |
-
2015
- 2015-12-31 CN CN201511029772.9A patent/CN105674995B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103542848A (en) * | 2012-07-17 | 2014-01-29 | 株式会社电装 | Destination recommendation system and destination recommendation method |
| CN103389100A (en) * | 2013-08-02 | 2013-11-13 | 上海梦擎信息科技有限公司 | System for freely navigating real-time road condition |
| CN103697901A (en) * | 2013-12-25 | 2014-04-02 | 沈阳美行科技有限公司 | Solving method for automatic guidance patterns of vehicle navigation |
| CN104102719A (en) * | 2014-07-18 | 2014-10-15 | 百度在线网络技术（北京）有限公司 | Track information pushing method and device |
| CN104165634A (en) * | 2014-07-28 | 2014-11-26 | 广州视源电子科技股份有限公司 | Path planning method based on user use habit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105674995A (en) | 2016-06-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105674995B (en) | A kind of method and device obtaining commuting route based on user's trip track | |
| Hsueh et al. | Map matching for low-sampling-rate GPS trajectories by exploring real-time moving directions | |
| Yu et al. | Deep learning-based traffic safety solution for a mixture of autonomous and manual vehicles in a 5G-enabled intelligent transportation system | |
| CN108170793B (en) | Vehicle semantic track data-based dwell point analysis method and system | |
| Bovy et al. | Stochastic route choice set generation: behavioral and probabilistic foundations | |
| EP3327575B1 (en) | Information distribution apparatus and method | |
| Lai et al. | Urban traffic Coulomb’s law: A new approach for taxi route recommendation | |
| US10885897B2 (en) | Information providing device and information providing system | |
| Wang et al. | Surrogate mobile sensing | |
| CN110472999B (en) | Passenger flow mode analysis method and device based on subway and shared bicycle data | |
| CN106503714A (en) | A kind of method that urban function region is recognized based on interest point data | |
| Guo et al. | Transportation mode recognition with deep forest based on GPS data | |
| Liu et al. | Balanced traffic routing: Design, implementation, and evaluation | |
| CN114896420B (en) | Parking lot recommendation method and recommendation device, target vehicle, and storage medium | |
| CN109523186A (en) | Urban area partitioning method and device | |
| CN113079463A (en) | Tourist attraction tourist travel activity identification method based on mobile phone signaling data | |
| CN104121917B (en) | A kind of method and apparatus of automatic discovery newly building bridge | |
| CN116972860A (en) | Yaw recognition method and device, electronic equipment and storage medium | |
| Hu et al. | A novel method for the detection of road intersections and traffic rules using big floating car data | |
| D'Andrea et al. | Path clustering based on a novel dissimilarity function for ride-sharing recommenders | |
| CN106323318B (en) | The processing method and processing device of the transit time of guidance path | |
| Liu et al. | Using trajectory data to explore roadway characterization for bikeshare network | |
| CN116434532B (en) | Intersection track prediction method and device based on strategy intention | |
| Meister et al. | Descriptive route choice analysis of cyclists in Zurich | |
| CN106940189B (en) | Classical line acquisition method and device in navigation system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |