CN110399973A - Method and apparatus for predicted position information - Google Patents
Method and apparatus for predicted position information Download PDFInfo
- Publication number
- CN110399973A CN110399973A CN201910671272.7A CN201910671272A CN110399973A CN 110399973 A CN110399973 A CN 110399973A CN 201910671272 A CN201910671272 A CN 201910671272A CN 110399973 A CN110399973 A CN 110399973A
- Authority
- CN
- China
- Prior art keywords
- station location
- location marker
- location information
- information
- time interval
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
Embodiment of the disclosure discloses the method and apparatus for predicted position information.This method can be applied to field of cloud calculation.One specific embodiment of this method includes: the location information sequence for obtaining object in historical time section, location information in location information sequence includes station location marker and time interval, and time interval is for characterizing residence time of the object at a upper position for the position that station location marker indicates；By location information sequence inputting to prediction network trained in advance, to predict that each predeterminated position of the object in preset predicted time section in predeterminated position identification sets identifies the probability at the position indicated respectively.The embodiment realizes the prediction to the position of object in preset predicted time section.
Description
Technical field
Embodiment of the disclosure is related to field of computer technology, and in particular to method and dress for predicted position information
It sets.
Background technique
With location technology, the fast development of sensor network, wireless communication technique, it is easy to be collected into mobile object
The position of (such as user, vehicle).In some application field (such as traffic controls, intelligent navigation for being related to moveable object
Deng), the position that look-ahead object occurs has biggish meaning in some scenes.For example, prediction object can be passed through
Position can assist the abnormal behaviour etc. of test object.
Therefore, be related to the application field of moveable object some, how look-ahead object may where position
It is one of primary study and problem to be solved with the time.Occur many predictions for being directed to mobile object location in the prior art
Method.For example, by extracting correlation rule from the recent historical position data of mobile object, and then establish Markov model
Or Hidden Markov Model etc..
Summary of the invention
Embodiment of the disclosure proposes the method and apparatus for predicted position information.
In a first aspect, embodiment of the disclosure provides a kind of method for predicted position information, this method comprises: obtaining
Take location information sequence of the object in historical time section, wherein the location information in location information sequence includes station location marker
And time interval, wherein station location marker is used to indicate the position where object, and time interval is for characterizing object in station location marker
Residence time at a upper position for the position of instruction；By location information sequence inputting to prediction network trained in advance, with
Prediction object appears in the mark of each predeterminated position in predeterminated position identification sets in preset predicted time section and indicates respectively
Position at probability, wherein prediction network includes Recognition with Recurrent Neural Network for extracting the characteristic information of location information sequence
With for predicting that each predeterminated position of the object in predicted time section in predeterminated position identification sets identifies according to characteristic information
The location information of the probability at position indicated respectively predicts network.
In some embodiments, location information prediction network is made of full articulamentum and output layer.
In some embodiments, predeterminated position identification sets obtain as follows: according to each position in predeterminable area
The distance between set, the corresponding station location marker in each position is clustered, at least one station location marker group is obtained；For
Station location marker group at least one station location marker group, chosen position mark is used as the station location marker group from the station location marker group
Identification information；Predeterminated position identification sets are formed by least one corresponding identification information of station location marker group.
In some embodiments, the time interval that the location information in location information sequence includes obtains as follows
It arrives: obtaining residence time of the object at a upper position for the position of the corresponding station location marker instruction of time interval；To stop
Time is normalized, to obtain corresponding time interval.
In some embodiments, station location marker includes latitude and longitude information.
Second aspect, embodiment of the disclosure provide a kind of device for predicted position information, which includes: to obtain
Unit is taken, is configured to obtain location information sequence of the object in historical time section, wherein the position in location information sequence
Information includes station location marker and time interval, wherein station location marker is used to indicate the position where object, and time interval is used for table
Levy residence time of the object at a upper position for the position that station location marker indicates；Predicting unit is configured to believe position
Sequence inputting is ceased to prediction network trained in advance, to predict that object appears in predeterminated position mark in preset predicted time section
Know the probability at the position that each predeterminated position mark concentrated indicates respectively, wherein prediction network includes for extracting position
The Recognition with Recurrent Neural Network of the characteristic information of information sequence and for according to characteristic information predict object in predicted time section pre-
If the location information prediction network of the probability at the position that each predeterminated position mark that station location marker is concentrated indicates respectively.
In some embodiments, location information prediction network is made of full articulamentum and output layer.
In some embodiments, predeterminated position identification sets obtain as follows: according to each position in predeterminable area
The distance between set, the corresponding station location marker in each position is clustered, at least one station location marker group is obtained；For
Station location marker group at least one station location marker group, chosen position mark is used as the station location marker group from the station location marker group
Identification information；Predeterminated position identification sets are formed by least one corresponding identification information of station location marker group.
In some embodiments, the time interval that the location information in location information sequence includes obtains as follows
It arrives: obtaining residence time of the object at a upper position for the position of the corresponding station location marker instruction of time interval；To stop
Time is normalized, to obtain corresponding time interval.
In some embodiments, station location marker includes latitude and longitude information.
The third aspect, embodiment of the disclosure provide a kind of server, which includes: one or more processing
Device；Storage device, for storing one or more programs；When one or more programs are executed by one or more processors, make
Obtain method of the one or more processors realization as described in implementation any in first aspect.
Fourth aspect, embodiment of the disclosure provide a kind of computer-readable medium, are stored thereon with computer program,
The method as described in implementation any in first aspect is realized when the computer program is executed by processor.
The method and apparatus for predicted position information that embodiment of the disclosure provides, using object in historical time section
The residence time that each position at interior place and object are located at various locations realizes to right in preset predicted time section
The prediction of the position of elephant.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the disclosure is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is that one embodiment of the disclosure can be applied to exemplary system architecture figure therein；
Fig. 2 is the flow chart according to one embodiment of the method for predicted position information of the disclosure；
Fig. 3 is the flow chart according to another embodiment of the method for predicted position information of the disclosure；
Fig. 4 is the signal of an application scenarios of the method according to an embodiment of the present disclosure for predicted position information
Figure；
Fig. 5 is the structural schematic diagram according to one embodiment of the device for predicted position information of the disclosure；
Fig. 6 is adapted for the structural schematic diagram for realizing the electronic equipment of embodiment of the disclosure.
Specific embodiment
The disclosure 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 related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to related invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the disclosure can phase
Mutually combination.The disclosure is described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
Fig. 1 is shown can the method for predicted position information using the disclosure or the dress for predicted position information
The exemplary architecture 100 for the embodiment set.
As shown in Figure 1, system architecture 100 may include terminal device 101,102,103, network 104 and server 105.
Network 104 between terminal device 101,102,103 and server 105 to provide the medium of communication link.Network 104 can be with
Including various connection types, such as wired, wireless communication link or fiber optic cables etc..
Terminal device 101,102,103 is interacted by network 104 with server 105, to receive or send message etc..Terminal
Various client applications can be installed in equipment 101,102,103.Such as the application of browser class, searching class application, map class
Using etc..
Terminal device 101,102,103 can be hardware, be also possible to software.When terminal device 101,102,103 is hard
When part, it can be various electronic equipments, including but not limited to smart phone, tablet computer, E-book reader, on knee portable
Computer and desktop computer etc..When terminal device 101,102,103 is software, above-mentioned cited electricity may be mounted at
In sub- equipment.Multiple softwares or software module may be implemented into (such as providing multiple softwares of Distributed Services or soft in it
Part module), single software or software module also may be implemented into.It is not specifically limited herein.
Server 105 can be to provide the server of various services, such as simultaneously according to the acquisition of terminal device 101,102,103
The position at place of the object of upload in historical time section and residence time in position predict object preset pre-
Survey the server of the position where in the period.
It should be noted that the position at place of the above-mentioned object in historical time section and the residence time in position
It can also be stored directly in the local of server 105, server 105 can directly extract the local object stored in history
Between place in section position and position residence time and handled, at this point it is possible to which terminal device is not present
101,102,103 and network 104).
It should be noted that the method provided by embodiment of the disclosure for predicted position information is generally by server
105 execute, and correspondingly, the device for predicted position information is generally positioned in server 105.
It may also be noted that terminal device 101,102,103 can also be based on place of the object in historical time section
Position and residence time in position, predict position of the object where in preset predicted time section.At this point, example
Server 105 and network 104 can be not present in property system architecture 100.
It should be noted that server 105 can be hardware, it is also possible to software.It, can when server 105 is hardware
To be implemented as the distributed server cluster that multiple servers form, individual server also may be implemented into.When server 105 is
When software, multiple softwares or software module may be implemented into (such as providing multiple softwares of Distributed Services or software mould
Block), single software or software module also may be implemented into.It is not specifically limited herein.
It should be understood that the number of terminal device, network and server in Fig. 1 is only schematical.According to realization need
It wants, can have any number of terminal device, network and server.
With continued reference to Fig. 2, it illustrates according to one embodiment of the method for predicted position information of the disclosure
Process 200.This for predicted position information method the following steps are included:
Step 201, location information sequence of the object in historical time section is obtained, wherein the position in location information sequence
Confidence breath includes station location marker and time interval.
In the present embodiment, object can refer to various transportable objects.For example, object can be people, vehicle, flight
Device etc..It can be moved just because of object, therefore, object may have evolution, i.e., be moved to from a position another
A position.
Wherein, station location marker can be used to indicate that the position where object.Station location marker, which can be, various can be used in marking
Know the information of position.For example, station location marker can be with the title etc. of position.Optionally, station location marker may include latitude and longitude information.
Optionally, station location marker is also possible to by pre-set character string of technical staff etc..
Wherein, time interval can be used for characterizing stop of the object at a upper position for the position that station location marker indicates
Time.Station location marker instruction position a upper position can refer to station location marker instruction position occur before, object institute
Position.For example, user is appearing in first position at the first time, then appears in the second position in the second time.
So first position can be considered as a upper position for first position, and the time difference between the second time is at the first time
It can be considered the corresponding time interval in the second position.
Wherein, historical time section can be configured by technical staff according to actual application scenarios.For example, historical time
Section can be 1 year etc. before current time.
It in the present embodiment, can for the executing subject (server 105 as shown in Figure 1) of the method for predicted position information
To obtain the object that terminal device acquires from the terminal device of communication connection (terminal device 101,102,103 as shown in Figure 1)
Location information sequence in historical time section.Certainly, above-mentioned executing subject can also be with acquisition target in historical time section
Location information sequence.At this point, above-mentioned executing subject can be directly from the local location information for obtaining object in historical time section
Sequence.
Step 202, by location information sequence inputting to prediction network trained in advance, to predict object in preset prediction
The probability present in position that each predeterminated position mark in period in predeterminated position identification sets indicates respectively.
In the present embodiment, predeterminated position identification sets can be made of the preassigned several station location markers of technical staff.
Optionally, the station location marker in predeterminated position identification sets can be by the corresponding station location marker group in each position in predeterminable area
At.Wherein, predeterminable area can be arranged by technical staff according to actual application demand.It should be appreciated that the object obtained
Each station location marker in the location information sequence in historical time section usually may belong to predeterminated position identification sets.
In the present embodiment, predicted time section can be arranged by technical staff according to actual application demand.For example, prediction
Period can be following one day or one week future etc. from current time.
In the present embodiment, prediction network may include Recognition with Recurrent Neural Network and location information prediction network.Wherein, it recycles
Neural network can be used for extracting the characteristic information of the location information sequence of input.Location information predicts that network can be according to circulation
The characteristic information prediction object that neural network is extracted appears in each in predeterminated position identification sets in preset predicted time section
The probability at position that a predeterminated position mark indicates respectively.
Wherein, Recognition with Recurrent Neural Network can use the structure of existing various Recognition with Recurrent Neural Network.For example, circulation nerve net
Network can be shot and long term memory network (Long Short-Term Memory networks, LSTM), gating cycle unit networks
(Gated Recurrent Unit networks, GRU), Recognition with Recurrent Neural Network (Stacked Recurrent Neural is stacked
Network, SRNN), bidirectional circulating neural network (bidirectional recurrent neural network, Bi-RNN)
Deng.The input of Recognition with Recurrent Neural Network can be location information sequence of the object in historical time section, and output can be extraction
The characteristic information of location information sequence.
Wherein, the input of location information prediction network can be the characteristic information that Recognition with Recurrent Neural Network exports, and output can be with
It is that each predeterminated position mark that object is appeared in preset predicted time section in predeterminated position identification sets indicates respectively
Probability at position.
Optionally, location information prediction network may include the output layer using default excitation function.Wherein, excitation function
It can be preset by technical staff.For example, excitation function can be using Softmax etc..
In the present embodiment, the prediction network of training can be based on the training sample obtained in advance in advance, and utilization is existing
Various training methods training obtain.Generally, training sample may include the location information sequence as the input of prediction network
Column, and the object of the desired output as prediction network appear in predeterminated position identification sets in preset predicted time section
The position that indicates respectively of each predeterminated position mark at probability.
It should be appreciated that can obtain training sample according to preset predicted time section, i.e. training sample usually should
Match with predicted time section.For example, preset predicted time section is one day following.At this point, training sample may include object
Location information sequence in preset historical time section.And object will appear in predeterminated position identification sets for one day in future
The probability at position that each predeterminated position mark indicates respectively.
Wherein, related technical personnel can construct initial predicted network to be trained according to actual application scenarios.Then,
Initial predicted network is trained based on training sample to obtain the prediction network of training completion.
It is alternatively possible to using location information sequence in training sample as the input of initial predicted network, by training sample
In object appeared in preset predicted time section each predeterminated position in predeterminated position identification sets mark indicate respectively
Position at desired output of the probability as initial predicted network, instructed based on gradient decline and back-propagation algorithm
Practice the prediction network completed.
It should be appreciated that the specific training method of prediction network can be adjusted flexibly.For example, it is also possible to first train
Recognition with Recurrent Neural Network, is then based on the Recognition with Recurrent Neural Network training location information prediction network of training completion, and then is trained
The prediction network of completion.
In some optional implementations of the present embodiment, the location information in above-mentioned location information sequence include when
Between be spaced and can obtain as follows: can first obtain object in the position of time interval corresponding station location marker instruction
Residence time at a upper position, then the residence time is normalized, to obtain corresponding time interval.
Wherein, normalization processing method can flexibly be chosen various normalization processing methods by technical staff.For example, can be with
First determine the maximum value and minimum value in each residence time obtained.It is illustrated using one of them residence time as example:
The difference of the residence time and the smallest residence time can first be determined as the first difference, then determine the residence time with most
The difference of big residence time can determine the quotient of the first difference and the second difference as the stop later as the second difference
Time corresponding time interval.
It should be appreciated that the time in location information sequence when network is predicted in training, in the training sample of use
Interval should also be the time interval obtained by normalized.Thus, it is possible to which accelerating gradient descent method solves optimal solution
Speed, to promote the training speed of prediction network.Meanwhile the time interval by obtaining after normalized can be to avoid
Excessive influence of the outlier (such as prominent value) on the output result of prediction network in corresponding each residence time, so as to
To promote the accuracy of the output result of prediction network.
In some optional implementations of the present embodiment, above-mentioned predeterminated position identification sets can obtain as follows
Arrive: step 1 carries out the corresponding station location marker in each position according to the distance between each position in predeterminable area
Cluster, obtains at least one station location marker group.Step 2, for the station location marker group at least one station location marker group, from this
Chosen position identifies the identification information as the station location marker group in station location marker group.Step 3, by least one station location marker
The corresponding identification information of group forms predeterminated position identification sets.
Wherein, specific clustering method can flexibly be chosen by technical staff according to actual application demand.Predeterminable area
It can be configured by technical staff according to actual application scenarios.Each position in each station location marker group obtained by cluster
Preset threshold can be less than by setting the distance between the position that mark indicates respectively.Wherein, preset threshold can be according to specifically answering
It is arranged with demand.
Wherein, for a station location marker group, it can use preset various methods chosen position from the station location marker group
Identify the identification information as the station location marker group.For example, each station location marker point in each position mark group can be determined first
Region determined by the position not indicated is as target area.Then chosen from station location marker group the position of corresponding instruction near
Identification information of the station location marker of the center in close-target region as the station location marker group.
In many cases, the number for the position for including in predeterminable area is very large.At this point it is possible to pass through above-mentioned
Method obtains predeterminated position identification sets.Obtained from each station location marker in predeterminated position identification sets position for indicating respectively
Total number be it is relatively small number of, so as to reduce prediction network training process in calculation amount, accelerate prediction network training
Speed.
The method provided by the above embodiment of the disclosure utilizes subjects history position and the stop in position
Time realizes the prediction to object future position.Meanwhile obtained predicted position also has temporal information, may be implemented
Prediction to the position at the place in the object following specific period, so as to promote the accuracy of prediction result.
With further reference to Fig. 3, it illustrates the processes 300 of another embodiment of the method for predicted position information.
This is used for the process 300 of the method for predicted position information, comprising the following steps:
Step 301, location information sequence of the object in historical time section is obtained, wherein the position in location information sequence
Confidence breath includes station location marker and time interval.
The specific implementation procedure of this step 301 can refer to the related description of the step 201 in Fig. 2 corresponding embodiment, In
This is repeated no more.
Step 302, by location information sequence inputting to prediction network trained in advance, to predict object in preset prediction
The probability present in position that each predeterminated position mark in period in predeterminated position identification sets indicates respectively, wherein
Prediction network includes Recognition with Recurrent Neural Network for extracting the characteristic information of location information sequence and for pre- according to characteristic information
It surveys general at the position that each predeterminated position mark of the object in predicted time section in predeterminated position identification sets indicates respectively
The location information of rate predicts network, wherein location information prediction network is made of full articulamentum and output layer.
In the present embodiment, the input of the full articulamentum of location information prediction network can be Recognition with Recurrent Neural Network output
Characteristic information, output can be the characteristic information of by transformation, default dimension.Location information predicts the defeated of the output layer of network
Enter the characteristic information by transformation, default dimension that can be full articulamentum output, output can be the object of prediction pre-
If predicted time section in it is general present in the position that indicates respectively of each predeterminated position mark in predeterminated position identification sets
Rate.
Wherein, location information prediction network full articulamentum can be used for Recognition with Recurrent Neural Network export characteristic information into
Row eigentransformation, with obtain default dimension, by transformed characteristic information, and then convenient for output layer carry out probabilistic forecasting,
And help to be promoted the accuracy of prediction result.
The specific of other contents in addition to the related content of location information prediction network in this step 302 executed
Journey can refer to the related description of the step 202 in Fig. 2 corresponding embodiment, and details are not described herein.
In some optional implementations of the present embodiment, the number for the full articulamentum that above-mentioned location information network includes
It can be configured by technical staff according to actual application demand.
In some optional implementations of the present embodiment, Recognition with Recurrent Neural Network is usually made of hidden layer.Wherein, it follows
The number for the hidden layer that ring neural network includes can be configured by technical staff according to actual application demand.For example, In
When Recognition with Recurrent Neural Network is based on LSTM building, Recognition with Recurrent Neural Network is formed according to by two or more LSTM layers.
Increase the number of hidden layer and/or increase the number of full articulamentum, the complexity of prediction network entirety can be increased,
So that the prediction result that output layer obtains has higher accuracy.
With continued reference to one that Fig. 4, Fig. 4 are according to the application scenarios of the method for predicted position information of the present embodiment
Schematic diagram 400.In the application scenarios of Fig. 4, the longitude and latitude for the position that user successively occurs in history 1 year can be obtained first
Degree is respectively L0, L1 ... LN.It is upper before at the corresponding position LN meanwhile user to be obtained respectively L0, L1 ...
Residence time at one position is respectively T0, T1 ... TN.I.e. user before at the corresponding position L0 upper one
Residence time at a position is T0, and the residence time at the corresponding position L0 is T1, and so on.Later, can by L0,
Each position residence time corresponding with a position thereon in L1 ... LN is considered as one group of location information, to obtain position
Information sequence 401.
Later, location information sequence 401 can be input to prediction network 402.As shown in the figure, prediction network 402 can
To include Recognition with Recurrent Neural Network 4021 and location information prediction network 4022.Wherein, Recognition with Recurrent Neural Network 4021 includes first hidden
Hide layer and the second hidden layer.Location information predicts that network 4022 includes full articulamentum and output layer.Specifically, position can be believed
Breath sequence 401 is input to the first hidden layer, and the characteristic information that the first hidden layer extracts is input to the second hidden layer, then will
Second hidden layer output characteristic information be input to full articulamentum, the default dimension for later exporting full articulamentum, through change
The characteristic information input to output layer changed obtains user and appears in longitude and latitude 1, longitude and latitude 2 ... longitude and latitude M point within next week
The probability at position not indicated is P1, P2 ... PM.
The scheme of the present embodiment description, can after obtaining the characteristic information of location information sequence using Recognition with Recurrent Neural Network
To carry out eigentransformation to location information sequence using full articulamentum, to increase the accuracy of the prediction result of final output.
With further reference to Fig. 5, as the realization to method shown in above-mentioned each figure, present disclose provides be used for prediction bits confidence
One embodiment of the device of breath, the Installation practice is corresponding with embodiment of the method shown in Fig. 2, which can specifically answer
For in various electronic equipments.
As shown in figure 5, the device 500 provided in this embodiment for predicted position information is including acquiring unit 501 and in advance
Survey unit 502.Wherein, acquiring unit 501 is configured to obtain location information sequence of the object in historical time section, wherein
Location information in location information sequence includes station location marker and time interval, wherein station location marker is for indicating object place
Position, time interval is for characterizing residence time of the object at a upper position for the position that station location marker indicates；Prediction
Unit 502 is configured to location information sequence inputting to prediction network trained in advance, to predict object in preset prediction
The probability present in position that each predeterminated position mark in period in predeterminated position identification sets indicates respectively, wherein
Prediction network includes Recognition with Recurrent Neural Network for extracting the characteristic information of location information sequence and for pre- according to characteristic information
It surveys general at the position that each predeterminated position mark of the object in predicted time section in predeterminated position identification sets indicates respectively
The location information of rate predicts network.
In the present embodiment, in the device 500 of predicted position information: the tool of acquiring unit 501 and predicting unit 502
Body processing and its brought technical effect can mutually speaking on somebody's behalf with reference to step 201 and the step 202 in Fig. 2 corresponding embodiment respectively
Bright, details are not described herein.
In some optional implementations of the present embodiment, location information predicts network by full articulamentum and output layer group
At.
In some optional implementations of the present embodiment, predeterminated position identification sets obtain as follows: according to
The distance between each position in predeterminable area clusters the corresponding station location marker in each position, obtains at least
One station location marker group；For the station location marker group at least one station location marker group, the chosen position from the station location marker group
Identify the identification information as the station location marker group；It is made of at least one corresponding identification information of station location marker group default
Station location marker collection.
In some optional implementations of the present embodiment, between the time that the location information in location information sequence includes
Every obtaining as follows: obtaining object at a upper position for the position of the corresponding station location marker instruction of time interval
Residence time；Residence time is normalized, to obtain corresponding time interval.
In some optional implementations of the present embodiment, station location marker includes latitude and longitude information.
The device provided by the above embodiment of the disclosure obtains position of the object in historical time section by acquiring unit
Information sequence, wherein the location information in location information sequence includes station location marker and time interval, wherein station location marker is used
Position where indicating object, time interval is for characterizing object at a upper position for the position that station location marker indicates
Residence time；Predicting unit by location information sequence inputting to prediction network trained in advance, to predict object preset pre-
The probability present in the position that each predeterminated position mark in the period in predeterminated position identification sets indicates respectively is surveyed,
In, prediction network includes Recognition with Recurrent Neural Network for extracting the characteristic information of location information sequence and for according to characteristic information
Predict that each predeterminated position of the object in predicted time section in predeterminated position identification sets identifies at the position indicated respectively
The location information of probability predicts network, to realize the accurate pre- of the position occurred in preset predicted time section for object
It surveys.
Below with reference to Fig. 6, it illustrates the electronic equipment that is suitable for being used to realize embodiment of the disclosure, (example is as shown in figure 1
Server) 600 structural schematic diagram.Server shown in Fig. 6 is only an example, should not be to the function of embodiment of the disclosure
Any restrictions can be brought with use scope.
As shown in fig. 6, electronic equipment 600 may include processing unit (such as central processing unit, graphics processor etc.)
601, random access can be loaded into according to the program being stored in read-only memory (ROM) 602 or from storage device 608
Program in memory (RAM) 603 and execute various movements appropriate and processing.In RAM 603, it is also stored with electronic equipment
Various programs and data needed for 600 operations.Processing unit 601, ROM 602 and RAM603 are connected with each other by bus 604.
Input/output (I/O) interface 605 is also connected to bus 604.
In general, following device can connect to I/O interface 605: including such as touch screen, touch tablet, keyboard, mouse, taking the photograph
As the input unit 606 of head, microphone, accelerometer, gyroscope etc.；Including such as liquid crystal display (LCD), loudspeaker, vibration
The output device 607 of dynamic device etc.；Storage device 608 including such as tape, hard disk etc.；And communication device 609.Communication device
609, which can permit electronic equipment 600, is wirelessly or non-wirelessly communicated with other equipment to exchange data.Although Fig. 6 shows tool
There is the electronic equipment 600 of various devices, it should be understood that being not required for implementing or having all devices shown.It can be with
Alternatively implement or have more or fewer devices.Each box shown in Fig. 6 can represent a device, can also root
According to needing to represent multiple devices.
Particularly, in accordance with an embodiment of the present disclosure, it may be implemented as computer above with reference to the process of flow chart description
Software program.For example, embodiment of the disclosure includes a kind of computer program product comprising be carried on computer-readable medium
On computer program, which includes the program code for method shown in execution flow chart.In such reality
It applies in example, which can be downloaded and installed from network by communication device 609, or from storage device 608
It is mounted, or is mounted from ROM 602.When the computer program is executed by processing unit 601, the implementation of the disclosure is executed
The above-mentioned function of being limited in the method for example.
It is situated between it should be noted that computer-readable medium described in embodiment of the disclosure can be computer-readable signal
Matter or computer readable storage medium either the two any combination.Computer readable storage medium for example can be with
System, device or the device of --- but being not limited to --- electricity, magnetic, optical, electromagnetic, infrared ray or semiconductor, or it is any more than
Combination.The more specific example of computer readable storage medium can include but is not limited to: have one or more conducting wires
Electrical connection, portable computer diskette, hard disk, random access storage device (RAM), read-only memory (ROM), erasable type are programmable
Read-only memory (EPROM or flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), light storage device, magnetic are deposited
Memory device or above-mentioned any appropriate combination.In embodiment of the disclosure, computer readable storage medium, which can be, appoints
What include or the tangible medium of storage program that the program can be commanded execution system, device or device use or and its
It is used in combination.And in embodiment of the disclosure, computer-readable signal media may include in a base band or as carrier wave
The data-signal that a part is propagated, wherein carrying computer-readable program code.The data-signal of this propagation can be adopted
With diversified forms, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal is situated between
Matter can also be any computer-readable medium other than computer readable storage medium, which can be with
It sends, propagate or transmits for by the use of instruction execution system, device or device or program in connection.Meter
The program code for including on calculation machine readable medium can transmit with any suitable medium, including but not limited to: electric wire, optical cable,
RF (radio frequency) etc. or above-mentioned any appropriate combination.
Above-mentioned computer-readable medium can be included in above-mentioned server；It is also possible to individualism, and without
It is incorporated in the server.Above-mentioned computer-readable medium carries one or more program, when said one or multiple journeys
When sequence is executed by the server, so that the server: obtaining location information sequence of the object in historical time section, wherein position
Setting the location information in information sequence includes station location marker and time interval, wherein station location marker is used to indicate where object
Position, time interval is for characterizing residence time of the object at a upper position for the position that station location marker indicates；By position
Information sequence is input to prediction network trained in advance, to predict that object appears in predeterminated position in preset predicted time section
The probability at position that each predeterminated position mark in identification sets indicates respectively, wherein prediction network includes for extracting position
Set the characteristic information of information sequence Recognition with Recurrent Neural Network and for according to characteristic information predict object in predicted time section
The location information prediction network for the probability at position that each predeterminated position mark in predeterminated position identification sets indicates respectively.
The behaviour for executing embodiment of the disclosure can be write with one or more programming languages or combinations thereof
The computer program code of work, described program design language include object oriented program language-such as Java,
Smalltalk, C++ further include conventional procedural programming language-such as " C " language or similar program design language
Speech.Program code can be executed fully on the user computer, partly be executed on the user computer, as an independence
Software package execute, part on the user computer part execute on the remote computer or completely in remote computer or
It is executed on server.In situations involving remote computers, remote computer can pass through the network of any kind --- packet
Include local area network (LAN) or wide area network (WAN) --- it is connected to subscriber computer, or, it may be connected to outer computer (such as
It is connected using ISP by internet).
Flow chart and block diagram in attached drawing are illustrated according to the system of the various embodiments of the disclosure, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of the module, program segment or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are actually
It can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it to infuse
Meaning, the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart can be with holding
The dedicated hardware based system of functions or operations as defined in row is realized, or can use specialized hardware and computer instruction
Combination realize.
Being described in unit involved in embodiment of the disclosure can be realized by way of software, can also be passed through
The mode of hardware is realized.Described unit also can be set in the processor, for example, can be described as: a kind of processor
Including acquiring unit and predicting unit.Wherein, the title of these units is not constituted to the unit itself under certain conditions
It limits, for example, acquiring unit is also described as " obtaining the unit of location information sequence of the object in historical time section ".
Above description is only the preferred embodiment of the disclosure and the explanation to institute's application technology principle.Those skilled in the art
Member it should be appreciated that embodiment of the disclosure involved in invention scope, however it is not limited to the specific combination of above-mentioned technical characteristic and
At technical solution, while should also cover do not depart from foregoing invention design in the case where, by above-mentioned technical characteristic or its be equal
Feature carries out any combination and other technical solutions for being formed.Such as disclosed in features described above and embodiment of the disclosure (but
It is not limited to) technical characteristic with similar functions is replaced mutually and the technical solution that is formed.
Claims (12)
1. a kind of method for predicted position information, comprising:
Obtain location information sequence of the object in historical time section, wherein the location information packet in the location information sequence
Include station location marker and time interval, wherein station location marker is used to indicate the position where the object, and time interval is for characterizing
Residence time of the object at a upper position for the position that station location marker indicates；
By the location information sequence inputting to prediction network trained in advance, to predict the object in preset predicted time
The probability present in position that each predeterminated position mark in section in predeterminated position identification sets indicates respectively, wherein described
Prediction network includes Recognition with Recurrent Neural Network for extracting the characteristic information of the location information sequence and for according to the spy
Each predeterminated position mark of the object described in sign information prediction in predicted time section in predeterminated position identification sets indicates respectively
Position at probability location information predict network.
2. according to the method described in claim 1, wherein, the location information prediction network is by full articulamentum and output layer group
At.
3. according to the method described in claim 1, wherein, the predeterminated position identification sets obtain as follows:
According to the distance between each position in predeterminable area, the corresponding station location marker in each position is clustered,
Obtain at least one station location marker group；
For the station location marker group at least one described station location marker group, chosen position identifies conduct from the station location marker group
The identification information of the station location marker group；
The predeterminated position identification sets are formed by least one described corresponding identification information of station location marker group.
4. according to the method described in claim 1, wherein, the time interval that the location information in the location information sequence includes
It obtains as follows:
When obtaining stop of the object at a upper position for the position of the corresponding station location marker instruction of the time interval
Between；
The residence time is normalized, to obtain corresponding time interval.
5. method described in one of -4 according to claim 1, wherein the station location marker includes latitude and longitude information.
6. a kind of device for predicted position information, comprising:
Acquiring unit is configured to obtain location information sequence of the object in historical time section, wherein the location information sequence
Location information in column includes station location marker and time interval, wherein and station location marker is used to indicate position where the object,
Time interval is for characterizing residence time of the object at a upper position for the position that station location marker indicates；
Predicting unit is configured to the location information sequence inputting to prediction network trained in advance, described right to predict
The position indicated respectively is identified as appearing in each predeterminated position in predeterminated position identification sets in preset predicted time section
The probability at place, wherein the prediction network includes the circulation nerve net for extracting the characteristic information of the location information sequence
Network and for predicting that the object is each pre- in predeterminated position identification sets in predicted time section according to the characteristic information
If the location information of the probability at the position that station location marker indicates respectively predicts network.
7. device according to claim 6, wherein the location information prediction network is by full articulamentum and output layer group
At.
8. device according to claim 6, wherein the predeterminated position identification sets obtain as follows:
According to the distance between each position in predeterminable area, the corresponding station location marker in each position is clustered,
Obtain at least one station location marker group；
For the station location marker group at least one described station location marker group, chosen position identifies conduct from the station location marker group
The identification information of the station location marker group；
The predeterminated position identification sets are formed by least one described corresponding identification information of station location marker group.
9. device according to claim 6, wherein the time interval that the location information in the location information sequence includes
It obtains as follows:
When obtaining stop of the object at a upper position for the position of the corresponding station location marker instruction of the time interval
Between；
The residence time is normalized, to obtain corresponding time interval.
10. the device according to one of claim 6-9, wherein the station location marker includes latitude and longitude information.
11. a kind of server, comprising:
One or more processors；
Storage device is stored thereon with one or more programs；
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
Now such as method as claimed in any one of claims 1 to 5.
12. a kind of computer-readable medium, is stored thereon with computer program, wherein the realization when program is executed by processor
Such as method as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910671272.7A CN110399973A (en) | 2019-07-24 | 2019-07-24 | Method and apparatus for predicted position information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910671272.7A CN110399973A (en) | 2019-07-24 | 2019-07-24 | Method and apparatus for predicted position information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110399973A true CN110399973A (en) | 2019-11-01 |
Family
ID=68324914
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910671272.7A Pending CN110399973A (en) | 2019-07-24 | 2019-07-24 | Method and apparatus for predicted position information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110399973A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488984A (en) * | 2020-04-03 | 2020-08-04 | 中国科学院计算技术研究所 | Method for training trajectory prediction model and trajectory prediction method |
-
2019
- 2019-07-24 CN CN201910671272.7A patent/CN110399973A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111488984A (en) * | 2020-04-03 | 2020-08-04 | 中国科学院计算技术研究所 | Method for training trajectory prediction model and trajectory prediction method |
| CN111488984B (en) * | 2020-04-03 | 2023-07-21 | 中国科学院计算技术研究所 | Method for training track prediction model and track prediction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108154196B (en) | Method and apparatus for exporting image | |
| CN110110811A (en) | Method and apparatus for training pattern, the method and apparatus for predictive information | |
| CN109145781A (en) | Method and apparatus for handling image | |
| CN110288049A (en) | Method and apparatus for generating image recognition model | |
| CN107908789A (en) | Method and apparatus for generating information | |
| US11093857B2 (en) | Method and apparatus for generating information | |
| CN109740018A (en) | Method and apparatus for generating video tab model | |
| CN108830837A (en) | A kind of method and apparatus for detecting ladle corrosion defect | |
| CN109815365A (en) | Method and apparatus for handling video | |
| CN109902446A (en) | Method and apparatus for generating information prediction model | |
| CN109145828A (en) | Method and apparatus for generating video classification detection model | |
| CN109829432A (en) | Method and apparatus for generating information | |
| CN109766418A (en) | Method and apparatus for output information | |
| US10772035B2 (en) | Method and apparatus for generating information | |
| CN110009059A (en) | Method and apparatus for generating model | |
| CN109947989A (en) | Method and apparatus for handling video | |
| CN110263748A (en) | Method and apparatus for sending information | |
| CN110457476A (en) | Method and apparatus for generating disaggregated model | |
| US20220414689A1 (en) | Method and apparatus for training path representation model | |
| CN109242043A (en) | Method and apparatus for generating information prediction model | |
| CN108182472A (en) | For generating the method and apparatus of information | |
| CN110427915A (en) | Method and apparatus for output information | |
| CN110070076A (en) | Method and apparatus for choosing trained sample | |
| CN114550053A (en) | Traffic accident responsibility determination method, device, computer equipment and storage medium | |
| CN110008926A (en) | The method and apparatus at age for identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |