CN111488984A - Method for training trajectory prediction model and trajectory prediction method - Google Patents

Method for training trajectory prediction model and trajectory prediction method Download PDF

Info

Publication number
CN111488984A
CN111488984A CN202010259417.5A CN202010259417A CN111488984A CN 111488984 A CN111488984 A CN 111488984A CN 202010259417 A CN202010259417 A CN 202010259417A CN 111488984 A CN111488984 A CN 111488984A
Authority
CN
China
Prior art keywords
term
track
time
data
short
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.)
Granted
Application number
CN202010259417.5A
Other languages
Chinese (zh)
Other versions
CN111488984B (en
Inventor
钱塘文
徐勇军
王飞
王佳楷
孙涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Guoke Yidao Technology Co ltd
Original Assignee
Institute of Computing Technology of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Institute of Computing Technology of CAS filed Critical Institute of Computing Technology of CAS
Priority to CN202010259417.5A priority Critical patent/CN111488984B/en
Publication of CN111488984A publication Critical patent/CN111488984A/en
Application granted granted Critical
Publication of CN111488984B publication Critical patent/CN111488984B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Biophysics (AREA)
  • Evolutionary Computation (AREA)
  • Biomedical Technology (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • Remote Sensing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The embodiment of the invention provides a track prediction method, which comprises the steps of carrying out track prediction by using a track prediction model obtained by a method for training a track prediction model according to real-time track data of a user to obtain a track prediction result, dividing space-time track data into recent track data, short-term historical data and long-term historical data, capturing a long-term space-time relation of each track point in the long-term historical data by using a coding model of a first multi-head attention machine system network, capturing a short-term space-time relation of each track point in the short-term historical data by using a cyclic neural network coding model, adjusting the short-term space-time relation by using a coding model of a second multi-head attention machine system network according to the similarity of the long-term space-time relation and the short-term space-time relation, realizing the global dependence of historical tracks, training a decoding model of a third multi-head attention machine system network by using the recent track data and the adjusted short-term space-time relation as the, the accuracy of the track prediction is improved.

Description

Method for training trajectory prediction model and trajectory prediction method
Technical Field
The invention relates to the technical field of information, in particular to the field of space-time trajectory prediction, and more particularly relates to a method for training a trajectory prediction model and a trajectory prediction method.
Background
Location prediction is a basic technology based on location services, and the popularization of the application of a positioning sensor and a positioning means can obtain a large amount of track data. Location prediction based on historical trajectory data for location services has become a hotspot of current research. The current common methods for location prediction are based on both patterns and models.
The pattern-based method extracts a trajectory pattern, such as a frequent pattern and a sequential pattern, from the historical trajectory, and predicts a next location using the extracted pattern. Although pattern methods are also common, finding a meaningful pattern is not an easy task and requires human intervention to determine if it is a meaningful pattern.
Model-based methods can achieve better performance than pattern-based methods, and common model-based methods include:
hidden Markov model based methods model the user's historical trajectory using a hidden Markov model and then use the model to predict the next possible location.
The method based on the recurrent neural network model can obtain good effect in the modeling of the sequence neural network by using the recurrent neural network, but the basic constraint of the sequence calculation still exists, and long-term context information cannot be well captured.
The current method has the problem of overlarge search domain, the distance between adjacent point coordinates is certain to be close due to the limitation of physical world factors, and if the former point is in China and the next point is not in the United states or Europe according to the common sampling time interval. Analysis of the results of mispredictions of existing methods has revealed that there are a large number of such points that break through physical limitations.
Because in the existing method, the same model is generally adopted to process the trajectory data of all the periods, such as a recurrent neural network model. The recurrent neural network model can well capture short-term context information, but cannot well capture long-term context information, global dependence of historical trajectories is difficult to realize, and accuracy of trajectory prediction is low.
Disclosure of Invention
It is therefore an object of the present invention to overcome the above-mentioned drawbacks of the prior art and to provide a method for training a trajectory prediction model and a trajectory prediction method.
The purpose of the invention is realized by the following technical scheme:
according to a first aspect of the present invention, there is provided a method for training a trajectory prediction model, the method comprising:
a1, acquiring space-time trajectory data of trajectory segments containing a plurality of targets represented by dense vectors, and cutting the trajectory data into near-term trajectory data, short-term history data and long-term history data from near to far according to time;
a2, training a coding model of the first multi-head attention mechanism network by using long-term historical data to capture the long-term spatiotemporal relation of each track point in the long-term historical data;
a3, training a recurrent neural network coding model by using short-term historical data to capture the short-term space-time relation of each track point in the short-term historical data;
a4, training a coding model of a second multi-head attention mechanism network by using the long-term space-time relationship and the short-term space-time relationship to adjust the short-term space-time relationship according to the similarity of the long-term space-time relationship and the short-term space-time relationship, so as to obtain the adjusted short-term space-time relationship;
a5, training a decoding model of a third multi-head attention mechanism network by using the recent track data and the adjusted short-term space-time relation to obtain the track prediction model.
In some embodiments of the present invention, the step a1 includes:
a11, acquiring space-time trajectory data of a plurality of targets represented by sparse vectors from a database and preprocessing the space-time trajectory data to obtain a plurality of trajectory segments;
a12, performing data mapping on the plurality of track segments to map sparse vectors to dense vectors, and obtaining space-time track data of the track segments containing a plurality of targets represented by the dense vectors;
and A13, cutting the space-time trajectory data of the trajectory segment containing a plurality of targets represented by dense vectors into recent trajectory data, short-term historical data and long-term historical data from near to far according to preset cutting rules and time.
In some embodiments of the present invention, the step a11 includes:
a111, acquiring space-time trajectory data of a plurality of targets represented by sparse vectors from a database, wherein each target comprises one or more trajectory segments;
a112, preprocessing the acquired space-time trajectory data of a plurality of targets represented by sparse vectors, comprising:
a1121, cutting track segments of two adjacent track points with a time difference larger than or equal to a preset time threshold value from between the two adjacent track points so as to cut the track segments into two or more track segments;
a1122, deleting track segments containing track points, the number of which is less than a first preset number of points;
and A1123, deleting the target with the segment number of the track segment less than the preset segment number.
Preferably, the preset time threshold is 72 hours, the number of the first preset points is 5, and the number of the preset segments is 5.
In some embodiments of the present invention, the step a13 includes:
a131, presetting three time intervals, namely in a first time node, between the first time node and a second time node and before the second time node from track recording data, and respectively taking track sections belonging to the three time intervals as recent track data, short-term historical data and long-term historical data, wherein the values of the first time node and the second time node are set by a user according to needs;
a132, cutting a plurality of track segments represented by dense vectors to cut the track segments spanning any time interval into two segments from two adjacent track points belonging to the two intervals;
and A133, cutting the track segment containing the track points in the short-term historical data, the number of which is greater than the second preset point number, into two segments from the track point of the track segment located at the second preset point number and the next track point of the track segment, and deleting the track segment, the number of which is less than the first preset point number, of the track points after the cutting.
Preferably, the number of the second preset points is 20.
Preferably, in the step a2, the long-term history data is used as a query, a key and a value to be input into a coding model of the first multi-head attention mechanism network so as to capture the long-term spatiotemporal relationship of each track point according to the context information of each track point in the long-term history data;
in the step A3, inputting the short-term historical data into a recurrent neural network to capture the short-term spatiotemporal relationship of each track point according to the context information of each track point in the short-term historical data;
in the step a4, inputting the long-term spatiotemporal relationship as a query and the short-term spatiotemporal relationship as a key and a value into a coding model of the second multi-head attention mechanism network to adjust the short-term spatiotemporal relationship according to the similarity of the long-term spatiotemporal relationship and the short-term spatiotemporal relationship, so as to obtain an adjusted short-term spatiotemporal relationship;
in step a5, the decoding model of the third multi-headed attention system network includes a multi-headed attention system model with a mask and a normal multi-headed attention system model, the multi-headed attention system model with the mask is input with the near-term trajectory data as the query, the key, and the value to capture the near-term spatiotemporal relationship of each trajectory point according to the context information of each trajectory point in the near-term history data, and the near-term spatiotemporal relationship as the query, the adjusted short-term spatiotemporal relationship as the key, and the adjusted short-term spatiotemporal relationship is input into the normal multi-headed attention system model to train the decoding model of the third multi-headed attention system network.
According to a second aspect of the present invention, there is provided a trajectory prediction method including:
according to the real-time trajectory data of the user, the trajectory prediction model obtained by the method for training the trajectory prediction model according to the first aspect is used for performing trajectory prediction, and a trajectory prediction result is obtained.
In some embodiments of the invention, the trajectory prediction method comprises:
b1, acquiring real-time trajectory data expressed by sparse vectors of the user and performing data mapping on the real-time trajectory data to map the sparse vectors to dense vectors to obtain the real-time trajectory data expressed by the dense vectors of the user;
b2, inputting the real-time track data expressed by dense vectors of the user as query, key and value into a multi-head attention mechanism model with a mask of a track prediction model to obtain a decoding result;
b3, inputting the decoding result into a full-link layer of a track prediction model to obtain predicted probability values of a plurality of candidate points of the user at the next moment;
and B4, acquiring the candidate point with the maximum probability value as the predicted track point of the user at the next moment, and outputting the candidate point as a track prediction result.
According to a third aspect of the present invention, there is provided an electronic apparatus comprising:
one or more processors; and
a memory, wherein the memory is to store one or more executable instructions;
the one or more processors are configured to perform the steps of the method as described in the first aspect or the second aspect via execution of the one or more executable instructions.
According to a fourth aspect of the present invention, there is provided a computer readable storage medium having embodied thereon a computer program executable by a processor to perform the steps of the method according to the first or second aspect.
Compared with the prior art, the invention has the advantages that:
the method divides space-time trajectory data into near-term trajectory data, short-term historical data and long-term historical data, captures the long-term space-time relationship of each trajectory point in the long-term historical data by using a coding model of a first multi-head attention machine network, captures the short-term space-time relationship of each trajectory point in the short-term historical data by using a cyclic neural network coding model, adjusts the short-term space-time relationship according to the similarity of the long-term space-time relationship and the short-term space-time relationship by using a coding model of a second multi-head attention machine network to obtain the adjusted short-term space-time relationship, realizes the global dependency of historical trajectories, trains a decoding model of the third multi-head attention machine network by using the near-term trajectory data and the adjusted short-term space-time relationship, and uses the decoding model as a trajectory prediction model, thereby improving the accuracy of.
Drawings
Embodiments of the invention are further described below with reference to the accompanying drawings, in which:
FIG. 1 is a schematic flow chart of a conventional trajectory prediction method;
fig. 2 is a flowchart illustrating a method for training a trajectory prediction model according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail by embodiments with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As mentioned in the background section, in the prior art method, the trajectory data of all the time periods are usually processed by using the same model, such as a recurrent neural network model, see fig. 1, which shows a prior art trajectory prediction method, including: k1, acquiring space-time trajectory data from the database and preprocessing the space-time trajectory data to obtain a plurality of trajectory segments; k2, performing data mapping on the plurality of track segments to map the sparse vectors to the dense vectors, and obtaining a plurality of track segments represented by the dense vectors; k3, cutting a plurality of track segments represented by dense vectors into recent track data and long-term track data; k4, training a recurrent neural network model by using the recent track data and the long-term track data; k5, carrying out trajectory prediction by using the trained recurrent neural network model according to the real-time trajectory data of the user to obtain a trajectory prediction result. In the existing track prediction method, a recurrent neural network model can well capture short-term context information, but cannot well capture long-term context information, so that global dependence of historical tracks is difficult to realize, and the accuracy of track prediction is low. Therefore, the method divides the space-time trajectory data into the recent trajectory data, the short-term historical data and the long-term historical data, captures the long-term space-time relationship of each trajectory point in the long-term historical data by using the coding model of the first multi-head attention mechanism network, captures the short-term space-time relationship of each trajectory point in the short-term historical data by using the cyclic neural network coding model, adjusts the short-term space-time relationship according to the similarity of the long-term space-time relationship and the short-term space-time relationship by using the coding model of the second multi-head attention mechanism network to obtain the adjusted short-term space-time relationship, realizes the global dependency of the historical trajectory, trains the decoding model of the third multi-head attention mechanism network by using the recent trajectory data and the adjusted short-term space-time relationship, and then uses the decoding model as a trajectory prediction model, thereby improving the.
According to an embodiment of the present invention, as shown in fig. 2, there is provided a method for training a trajectory prediction model, including:
a1, acquiring space-time trajectory data of trajectory segments containing a plurality of targets represented by dense vectors, and cutting the trajectory data into near-term trajectory data, short-term history data and long-term history data from near to far according to time;
a2, training a coding model of the first multi-head attention mechanism network by using long-term historical data to capture the long-term spatiotemporal relation of each track point in the long-term historical data;
a3, training a recurrent neural network coding model by using short-term historical data to capture the short-term space-time relation of each track point in the short-term historical data;
a4, training a coding model of the second multi-head attention mechanism network by using the long-term space-time relationship and the short-term space-time relationship to adjust the short-term space-time relationship according to the similarity of the long-term space-time relationship and the short-term space-time relationship to obtain the adjusted short-term space-time relationship;
and A5, training a decoding model of the third multi-head attention mechanism network by using the recent track data and the adjusted short-term space-time relation to obtain a track prediction model.
For a better understanding of the present invention, each step is described in detail below with reference to specific examples.
In step a1, spatiotemporal trajectory data of trajectory segments containing a plurality of targets represented by dense vectors is acquired and cut from near to far into near-term trajectory data, short-term history data, and long-term history data according to time.
Preferably, step a1 includes:
a11, acquiring space-time trajectory data of a plurality of targets represented by sparse vectors from a database and preprocessing the space-time trajectory data to obtain a plurality of trajectory segments;
a12, performing data mapping on the plurality of track segments to map the sparse vectors to the dense vectors, and obtaining space-time track data of the track segments containing a plurality of targets represented by the dense vectors;
and A13, cutting the space-time trajectory data of the trajectory segment containing a plurality of targets represented by dense vectors into recent trajectory data, short-term historical data and long-term historical data from near to far according to preset cutting rules and time.
Preferably, step a11 includes:
a111, acquiring space-time trajectory data of a plurality of targets represented by sparse vectors from a database, wherein each target comprises one or more trajectory segments;
a112, preprocessing the acquired space-time trajectory data of a plurality of targets represented by sparse vectors, comprising:
a1121, cutting track segments of two adjacent track points with a time difference larger than or equal to a preset time threshold value from between the two adjacent track points so as to cut the track segments into two or more track segments;
a1122, deleting track segments containing track points, the number of which is less than a first preset number of points;
and A1123, deleting the target with the segment number of the track segment less than the preset segment number.
Preferably, in step A12, a Word2Vec model, an E L Mo model, a GPT model or a BERT model is used for data mapping of a plurality of track segments, a sparse vector is generally defined by representing a Word by a very long vector, the length of the vector is the size n of a dictionary, the components of the vector are only 1, and the positions of the rest are all 0.1 corresponding to the indexes of the Word in the dictionary.
Preferably, the value range of the preset time threshold is 24-80 hours. The value range of the first preset points is 5-8. The value range of the preset number of the sections is 3-7 sections. For example, the preset time threshold is 72 hours, the first preset number of points is 5, and the preset number of segments is 5 segments. If two adjacent track points in a track segment have a time interval of 75 hours and more than 72 hours, the track segment is divided into two segments from the interval between the two adjacent track points. After finding out all adjacent track points with the time difference exceeding 72 hours and completing cutting, identifying the point number contained in each track segment, deleting the track segments with the point number less than 5, and after deleting the track segments with the point number less than 5, identifying the number of the track segments of each target, and deleting the targets with the segment number less than 5 of the track segments contained. The technical scheme of the preferred embodiment can at least realize the following beneficial technical effects: the interference of some trace points with overlarge interval time on subsequent analysis is avoided; track segments with the number of track points smaller than the first preset point number and targets with the number of segments for deleting track segments smaller than the preset segment number can be eliminated, track segments with small information quantity and difficult capture of effective characteristics and targets can be eliminated, and effectiveness of follow-up track prediction is improved.
Preferably, step a13 includes:
a131, presetting three time intervals, namely in a first time node, between the first time node and a second time node and before the second time node since the track recording data, and respectively taking track sections belonging to the three time intervals as recent track data, short-term historical data and long-term historical data;
a132, cutting a plurality of track segments represented by dense vectors to cut the track segments spanning any time interval into two segments from two adjacent track points belonging to the two intervals;
and A133, cutting the track segment containing the track points in the short-term historical data, the number of which is greater than the second preset point number, into two segments from the track point of the track segment located at the second preset point number and the next track point of the track segment, and deleting the track segment, the number of which is less than the first preset point number, of the track points after the cutting.
Preferably, the values of the first time node and the second time node are set by a user according to needs. For example, the first time node is set as 3 days, the second time node is set as 9 days, which corresponds to three preset time intervals, namely within 3 days, between 3 and 9 days and before 9 days, and the track sections within 3 days, between 3 and 9 days and before 9 days are respectively used as the recent track data, the short-term history data and the long-term history data. Suppose that the track segments after one target cut respectively represent ST1,ST2,…,STkI.e. k track segments in total, and cutting and dividing the track segments according to the time interval, and obtaining long-term historyData is ST1,ST2,…,STk-4(ii) a Short term historical data of STk-3,STk-2,STk-1(ii) a Recent trajectory data is STk. The technical scheme of the preferred embodiment can at least realize the following beneficial technical effects: the space-time trajectory data is divided into three time intervals, so that corresponding space-time relations are captured respectively according to the short-term historical data and the long-term historical data, global dependence on historical trajectories is formed, and prediction is accurate.
Preferably, the second predetermined number of dots is 20. The technical scheme of the preferred embodiment can at least realize the following beneficial technical effects: because the short-term historical data is followed by capturing the space-time relationship among the track points by the cyclic neural network coding model, the cyclic neural network coding model is an autoregressive model, and when the number of the track points contained in a single track segment exceeds 20, the cyclic neural network coding model cannot well obtain the space-time relationship among the track points with longer distance, the track segment in the short-term historical data with the track points exceeding 20 is cut, so that the cyclic neural network coding model can well analyze the space-time relationship among the track points, and the accuracy of track prediction is improved.
Preferably, the database is for example an in-memory database redis, a distributed database hive or a relational database MySQ L.
In step A2, a coding model of the first multi-headed attention mechanism network is trained with long-term historical data to capture long-term spatiotemporal relationships of trace points in the long-term historical data.
Preferably, the long-term history data is input as a query, key, and value into a coding model of the first multi-headed attention mechanism network to capture long-term spatiotemporal relationships of the respective trace points according to context information of the respective trace points in the long-term history data. The long-term spatiotemporal relationship is a first vector matrix formed by weights of all track points in each vector dimension in long-term historical data. For the convenience of understanding, the form of the vector matrix of the present invention is described below by the schematic vector matrix of table 1, and the following second, third and fourth vector matrices are also in this form, and the vector dimensions of the first, second, third and fourth vector matrices are all the same, so they will not be separately illustrated in the following. The vector dimension can be set by a user according to the data quantity of the space-time trajectory data according to needs. In general, the vector dimensions are set to 450-550. Preferably, the vector dimension is set to 500.
TABLE 1 exemplary vector matrix
Figure BDA0002438729830000091
The vector dimension in table 1 is n-dimension, where n-dimension corresponds to n in X1n and X2n in table 1, and indicates that the vector corresponding to a track point includes n components. X11, X12, X13, X14, … …, X1n corresponding to the track point 1 and X21, X22, X23, X24, … …, X2n corresponding to the track point 2 are only symbols representing respective vectors in the invention for simplification. Each component is actually represented as a real or floating-point number. For example, vectors X11, X12, X13, X14, and X1n may be floating point numbers in the form of-2.0122, -0.5094, -0.5750, -2.6393, -0.0634, respectively.
According to one example of the present invention, the working principle of the coding model of the first multi-headed attention mechanism network is:
Figure BDA0002438729830000092
in the formula 1, the first and second groups of the compound,
i represents the ith layer model;
TE is the abbreviation of the Transformer Encoder model (transform Encoder), and is called TE model in the following abbreviation;
Figure BDA0002438729830000093
is the output of the TE model at the ith layer;
l N is short for linear Normalization (L initial Normalization), which is a Normalization method;
Figure BDA0002438729830000101
is the hidden state of the TE model at the ith layer;
FFN is an abbreviation of Feed-forward neural network (Feed-forward network);
equation 1 is illustrated below:
the coding model of the multi-head attention mechanism network is a multi-layer model, i is greater than or equal to 1.
The input to each layer is
Figure BDA0002438729830000102
(hidden state of ith layer), the output is
Figure BDA0002438729830000103
(output result of ith layer);
the specific data processing flow corresponding to the formula is as follows:
1. hiding state of ith layer
Figure BDA0002438729830000104
An afferent feedforward neural network FFN, with the purpose of causing the active feature to be activated;
2. feeding forward the result of the neural network
Figure BDA0002438729830000105
And
Figure BDA0002438729830000106
adding, in order to ensure that information is not lost due to the increase of the track length when the information is transmitted in the network;
3. adding the result
Figure BDA0002438729830000107
Normalization L N was performed in order to eliminate dimensional effects between data;
4. output of
Figure BDA0002438729830000108
I.e. equal to
Figure BDA0002438729830000109
In the formula 1, the first and second groups of the compound,
Figure BDA00024387298300001010
wherein the content of the first and second substances,
Figure BDA00024387298300001011
representing the output of the TE model at the i-1 layer;
MA is short for multi-head attention mechanism network (multi-head attention mechanism)1Indicating that it corresponds to a first multi-headed attention mechanism network, hereinafter abbreviated as MA1A network;
equation 2 is illustrated below:
equation 2 describes the process flow for obtaining the hidden state of the i-th layer, the input is
Figure BDA00024387298300001012
(output result of layer i-1), the output is
Figure BDA00024387298300001013
(hidden state of ith layer) as follows:
1. output results of the i-1 th layer
Figure BDA00024387298300001014
Afferent MA1In the network, the purpose is to obtain
Figure BDA00024387298300001015
Internal association of (2);
2. mixing MA1Results of the network
Figure BDA00024387298300001016
And
Figure BDA00024387298300001017
the purpose of the addition is to ensure that information is not lost due to the increase of the track length when the information is transmitted in the networkLosing;
3. adding the result
Figure BDA00024387298300001018
Normalization L N was performed in order to eliminate dimensional effects between data;
4. output of
Figure BDA00024387298300001019
Namely, it is
Figure BDA00024387298300001020
In formula 2, when i is 1,
Figure BDA00024387298300001021
wherein the content of the first and second substances,
Figure BDA0002438729830000111
representing the hidden state of the TE model at the layer 1;
MA1(x1,x1,x1) Is MA1The network requires three elements as inputs, namely query Q, key K and value V, x1The long-term historical data is input into a coding model of the first multi-head attention mechanism network as query, key and value;
equation 3 is illustrated below:
equation 3 describes the process flow for the layer 1 hidden state, where the input is long-term history data x1The output is
Figure BDA0002438729830000112
The specific process is as follows:
1. long-term history data x1Afferent MA1In the network, the purpose is to obtain the internal relation between long-term historical tracks x;
2. attention finding of multiple heads MA1(x1,x1,x1) And x1The purpose of the addition is to make the information not to be transferred in the network because of the track lengthIncrease in time and loss of information;
3. adding the result x1+MA1(x1,x1,x1) Normalization L N was performed in order to eliminate dimensional effects between data;
4. output of
Figure BDA0002438729830000113
I.e. equal to L N (x)1+MA(x1,x1,x1))。
To better illustrate the MA network, it is further illustrated by its formula below. The MA network is a novel neural network model, and its formula is:
MA(Q,K,V)＝Concat(head1,head2,…,head8)WOformula 4;
in the formula 4, the first and second groups of the compound,
q represents a query (query), which is one of the inputs to the Multi-head;
k represents a key (key) which is one of the inputs of the Multi-head;
v represents a value (value), which is one of the inputs to the Multi-head;
head1,head2,…,head8respectively representing the result of each Attention;
o represents an output;
WOa weight matrix representing the output;
the idea corresponding to equation 4 is:
MA(Q,K,V)＝Concat(head1,head2,…,head8)WOmeans that 8 Attention-processed (Attention) results are connected by a splicing operation (Concat) and then multiplied by the output weight matrix WOAnd the obtained result is the result of the MA network.
The specific processing flow of the MA network is as follows:
1. the result head of 8 attentions1,head2,…,head8After splicing (concat), multiplying by the output weight matrix WOThe aim is to focus on the information of different subspaces simultaneously;
2. output MA (Q, K, V), i.e. Concat (head)1,head2,…,head8)WO；
In the formula 4, the first and second groups of the compound,
Figure BDA0002438729830000121
wherein j is a positive integer less than or equal to 8, headjRepresenting head1,head2,…,head8One of (a);
Figure BDA0002438729830000122
representing a weight matrix for input Q in the jth head;
Figure BDA0002438729830000123
representing a weight matrix for input K in the jth head;
Figure BDA0002438729830000124
representing a weight matrix for input K in the jth head;
equation 5 is illustrated below:
equation 5 describes the specific flow of attention processing, and the input is abbreviated as Q, K, V (actually the last equation)
Figure BDA0002438729830000125
As input), the output is Attention (Q, K, V).
In the formula 5, the first and second groups,
Figure BDA0002438729830000126
wherein, Attention (Q, K, V) represents the result of Attention processing (Attention), and then Q, K, V are inputs, respectively;
softmax represents a general method for calculating scores and classifying in a neural network;
KTa transpose matrix representing K;
dkrepresenting a threshold for reducing errors due to data imbalance;
the method comprises the following specific steps:
1. multiplying the transposed matrixes of Q and K to obtain QKTIn order to calculate Q, K the relationship between;
2. will QKTIs divided by
Figure BDA0002438729830000127
The purpose is to reduce the error caused by data unbalance;
3. will be provided with
Figure BDA0002438729830000128
Performing softmax calculation to obtain a score between 0 and 1, wherein the purpose is to obtain probability;
4. will be provided with
Figure BDA0002438729830000129
Multiplying with V in order to calculate the relationship between Q, K, V;
5. output Attention (Q, K, V), i.e.
Figure BDA00024387298300001210
In step A3, the recurrent neural network coding model is trained with the short-term historical data to capture the short-term spatiotemporal relationship of the trace points in the short-term historical data.
Preferably, the short-term historical data is input into the recurrent neural network to capture the short-term spatiotemporal relationship of each trace point according to the context information of each trace point in the short-term historical data. And the short-term space-time relation is a second vector matrix formed by the track points in the short-term historical data relative to the weights of the vector dimensions.
According to one example of the present invention, the working principle of the recurrent neural network coding model is:
Figure BDA0002438729830000131
in the formula 7, the first and second groups,
l E represents a recurrent neural network coding model (L STM Encoder), L STM represents a long-Short Term Memory network model (L ong Short-Term Memory), which is a relatively general model of recurrent neural networks;
Figure BDA0002438729830000132
the output of the L E module representing the ith layer;
Figure BDA0002438729830000133
a hidden layer state of L E module representing the ith layer;
FFN denotes a feed-forward neural network;
equation 7 is illustrated below:
the cyclic neural network coding model is a multilayer model, namely i is greater than or equal to 1. It should be noted that the number of layers of the cyclic neural network coding model is consistent with that of the multi-head attention mechanism network coding model;
the input to each layer is
Figure BDA0002438729830000134
(hidden state of ith layer), the output is
Figure BDA0002438729830000135
(output result of ith layer);
the specific data processing flow corresponding to formula 7 is:
1. hiding state of ith layer
Figure BDA0002438729830000136
An afferent feedforward neural network FFN, with the purpose of causing the active feature to be activated;
2. feeding forward the result of the neural network
Figure BDA0002438729830000137
And
Figure BDA0002438729830000138
is added in order toWhen information is transmitted in the network, information loss caused by the increase of the track length can be avoided;
3. adding the result
Figure BDA0002438729830000139
Normalization L N was performed in order to eliminate dimensional effects between data;
4. output of
Figure BDA00024387298300001310
I.e. equal to
Figure BDA00024387298300001311
In the formula 7, the first and second groups,
Figure BDA00024387298300001312
wherein the content of the first and second substances,
Figure BDA00024387298300001313
the output of the L E module at level i-1;
Figure BDA0002438729830000141
to represent
Figure BDA0002438729830000142
Is the input to L STM;
equation 8 is illustrated below:
equation 8 describes the process flow for obtaining the hidden state of the i-th layer, the input is
Figure BDA0002438729830000143
(output result of layer i-1), the output is
Figure BDA0002438729830000144
(hidden state of ith layer) as follows:
1. output results of the i-1 th layer
Figure BDA0002438729830000145
In the afferent recurrent neural network L STM, the purpose is to acquire
Figure BDA0002438729830000146
The timing relationship of (1);
2. combining the results of the recurrent neural network
Figure BDA0002438729830000147
And
Figure BDA0002438729830000148
adding, in order to ensure that information is not lost due to the increase of the track length when the information is transmitted in the network;
3. adding the result
Figure BDA0002438729830000149
Normalization L N was performed in order to eliminate dimensional effects between data;
4. output of
Figure BDA00024387298300001410
Namely, it is
Figure BDA00024387298300001411
Wherein, when i is equal to 1,
Figure BDA00024387298300001412
Figure BDA00024387298300001413
represents the hidden layer state of layer 1L E module;
x2representing input trajectory data, x2Is short-term historical data;
equation 9 is illustrated below:
equation 9 describes the process flow for the layer 1 hidden state, where the input is the short-term history trace x2The output is
Figure BDA00024387298300001414
The specific process is as follows:
1. will short-term history track x2In the afferent recurrent neural network L STM, the purpose is to obtain a short-term historical trajectory x2The timing relationship of (1);
2. l STM (x) of the result of the recurrent neural network2) And x2Adding, in order to ensure that information is not lost due to the increase of the track length when the information is transmitted in the network;
3. adding the result x2+LSTM(x2) Normalization L N was performed in order to eliminate dimensional effects between data;
4. output of
Figure BDA00024387298300001415
I.e. equal to L N (x)2+LSTM(x2))。
Preferably, the recurrent neural network is a neural network model. The traditional recurrent neural network formula is:
ht＝fw(concat(ht-1,xt) Equation 10;
wherein h istRepresenting the hidden layer state at the t-th moment; x is the number oftAn input representing a time t; f. ofwRepresenting a function of the parameter w, expanded specifically to fw(x)＝tanh(wx)。
In step a4, the coding model of the second multi-headed attention mechanism network is trained with the long-term spatiotemporal relationship and the short-term spatiotemporal relationship to adjust the short-term spatiotemporal relationship according to the similarity of the long-term spatiotemporal relationship and the short-term spatiotemporal relationship to obtain an adjusted short-term spatiotemporal relationship.
Preferably, the long-term spatiotemporal relationship is used as a query, and the short-term spatiotemporal relationship is used as a key and a value to be input into a coding model of the second multi-head attention mechanism network so as to adjust the short-term spatiotemporal relationship according to the similarity of the long-term spatiotemporal relationship and the short-term spatiotemporal relationship, and obtain the adjusted short-term spatiotemporal relationship. The adjusted short-term space-time relationship is a third vector matrix formed by adjusting the similarity of the long-term space-time relationship and the short-term space-time relationship of the weights of the track points relative to the vector dimensions in the short-term historical data. The technical scheme of the embodiment can at least realize the following beneficial technical effects: according to the invention, the short-term spatio-temporal relationship can be adjusted according to the similarity of the long-term spatio-temporal relationship and the short-term spatio-temporal relationship to obtain the adjusted short-term spatio-temporal relationship, so that the global dependence of a historical track is realized, and after the processing of the step, in the score of the final candidate point, compared with the score of the candidate point output by other models, the probability of the partial candidate point far away from the 'true value' is reduced, and the probability of the partial candidate point close to the 'true value' is improved, wherein the 'true value' refers to: and the position point is really located at the next moment, so that the accuracy of the track prediction is improved.
Preferably, the short-term spatiotemporal relationship is adjusted according to the similarity between the long-term spatiotemporal relationship and the short-term spatiotemporal relationship, and the adjusted short-term spatiotemporal relationship is obtained by a multi-head attention mechanism network, and the working principle is as follows:
Figure BDA0002438729830000151
wherein, MA2Indicating that it corresponds to a second multi-headed attention mechanism network, hereinafter abbreviated as MA2A network;
OCArepresenting the adjusted short-term spatiotemporal relationship;
n represents the model of the Nth layer, and the number of layers of the model is N layers (6 layers) in total;
equation 11 is illustrated below:
in equation 11, the long-term spatiotemporal relationship
Figure BDA0002438729830000152
Short term spatiotemporal relationships
Figure BDA0002438729830000153
And short term spatiotemporal relationships
Figure BDA0002438729830000154
Respectively as queriesQ, bond K and value V into MA2In the network, the relation between the query Q, the key K and the value V can be calculated, so that the adjustment effect is achieved.
In step a5, a decoding model of the third multi-headed attention mechanism network is trained using the recent trajectory data and the adjusted short-term spatiotemporal relationship to obtain a trajectory prediction model. Namely, the decoding model of the third multi-head attention mechanism network is trained by using the recent track data and the adjusted short-term space-time relation and then is used as a track prediction model.
Preferably, the decoding model of the third multi-head attention system network includes a multi-head attention system model with a mask and a normal multi-head attention system model, the near-term trajectory data is used as a query, a key and a value and is input into the multi-head attention system model with the mask to capture the near-term spatiotemporal relationship of each trajectory point according to the context information of each trajectory point in the near-term historical data, the near-term spatiotemporal relationship is used as a query, and the adjusted short-term spatiotemporal relationship is input into the normal multi-head attention system model as a key and a value to train the decoding model of the third multi-head attention system network. And the recent space-time relationship is a fourth vector matrix formed by the weights of the track points in the recent track data relative to the vector dimensions.
According to an example of the present invention, the operation principle of training the decoding model of the third multi-headed attention mechanism network is:
Figure BDA0002438729830000161
wherein the content of the first and second substances,
Figure BDA0002438729830000162
represents the output of an i-th layer Decoder (Decoder);
Figure BDA0002438729830000163
represents a hidden layer state of an i-th layer Decoder (Decoder);
FFN denotes a feed-forward neural network;
equation 12 is illustrated below:
the decoding model of the third multi-head attention mechanism network is a multi-layer model, i is greater than or equal to 1. It should be noted that, for a multi-head attention mechanism network, the number of coding model layers is consistent with that of decoding model layers, and is 6;
in equation 12, the input for each layer is
Figure BDA0002438729830000164
(hidden state of ith layer), the output is
Figure BDA0002438729830000165
(output result of ith layer);
the specific data processing flow corresponding to formula 12 is:
1. hiding state of ith layer
Figure BDA0002438729830000166
An afferent feedforward neural network FFN, with the purpose of causing the active feature to be activated;
2. feeding forward the result of the neural network
Figure BDA0002438729830000167
And
Figure BDA0002438729830000168
adding, in order to ensure that information is not lost due to the increase of the track length when the information is transmitted in the network;
3. adding the result
Figure BDA0002438729830000169
Normalization L N was performed in order to eliminate dimensional effects between data;
4. output of
Figure BDA00024387298300001610
I.e. equal to
Figure BDA00024387298300001611
In the formula 12, the first and second groups of the formula,
Figure BDA00024387298300001612
wherein the content of the first and second substances,
Figure BDA00024387298300001613
represents an input layer state of an i-th layer Decoder (Decoder);
OCArepresenting the adjusted short-term spatiotemporal relationship;
Figure BDA00024387298300001614
a normal multi-head attention mechanism model representing a decoding model of the third multi-head attention mechanism network
Figure BDA00024387298300001615
OCA、OCAMaking the result produced by input Q, K, V;
the formula is illustrated below:
the formula describes the process flow of obtaining the hidden state of the i-th layer, and the input is
Figure BDA0002438729830000171
(i-th level hidden state) and adjusted short-term spatio-temporal relationship OCAThe output is
Figure BDA0002438729830000172
(hidden state of ith layer) as follows:
1. hiding the ith layer from the state
Figure BDA0002438729830000173
With adjusted short-term spatiotemporal relationship OCAAfferent MA3In the network, the purpose is to obtain the internal relation between the two;
2. will result in a plurality of attention
Figure BDA0002438729830000174
And
Figure BDA0002438729830000175
adding, in order to ensure that information is not lost due to the increase of the track length when the information is transmitted in the network;
3. adding the result
Figure BDA0002438729830000176
Normalization L N was performed in order to eliminate dimensional effects between data;
4. output of
Figure BDA0002438729830000177
Namely, it is
Figure BDA0002438729830000178
In the formula 13, the first and second groups,
Figure BDA0002438729830000179
wherein the content of the first and second substances,
Figure BDA00024387298300001710
represents the output of an i-1 layer Decoder (Decoder);
Figure BDA00024387298300001711
a masked multi-head attention mechanism model representing a decoding model of the third multi-head attention mechanism network;
equation 14 is illustrated below:
the formula describes the process flow of obtaining the i-th level hidden state, and the input is
Figure BDA00024387298300001712
(output result of layer i-1), the output is
Figure BDA00024387298300001713
(secondary hidden state of ith layer), specifically as follows:
1. output results of the i-1 th layer
Figure BDA00024387298300001714
Multi-head attention mechanism MMA with mask3In order to obtain
Figure BDA00024387298300001715
Internal association of (2);
2. multiple attention results with masks
Figure BDA00024387298300001716
And
Figure BDA00024387298300001717
adding, in order to ensure that information is not lost due to the increase of the track length when the information is transmitted in the network;
3. adding the result
Figure BDA00024387298300001718
Normalization L N was performed in order to eliminate dimensional effects between data;
4. output of
Figure BDA00024387298300001719
Namely, it is
Figure BDA00024387298300001720
Wherein, when i is equal to 1,
Figure BDA00024387298300001721
in the formula 15, the first step is,
x3is recent trajectory data;
Figure BDA00024387298300001722
the formula describes the processing flow of the 1 st level hidden state, and the input is recent track data x3The output is
Figure BDA00024387298300001723
The specific process is as follows:
1. the recent track data x3As MMA3Model Q, K and V afferent to multi-head attention mechanism MMA with mask3In order to obtain recent trajectory data x3Inter-relation between
2. MMA-results of multiple attention with masks3(x3,x3,x3) And x3The purpose of the addition is to enable information to be transmitted in the network without loss of information due to increase of track length
3. Adding the result x3+MMA3(x3,x3,x3) Normalization L N was performed in order to eliminate dimensional effects between data;
4. output of
Figure BDA0002438729830000181
I.e. equal to L N (x)3+MMA3(x3,x3,x3))。
According to an embodiment of the present invention, there is provided a trajectory prediction method including: according to the real-time trajectory data of the user, the trajectory prediction model obtained by the method for training the trajectory prediction model in the previous embodiment is used for performing trajectory prediction, and a trajectory prediction result is obtained.
Preferably, the trajectory prediction method includes:
b1, acquiring real-time trajectory data expressed by sparse vectors of the user and performing data mapping on the real-time trajectory data to map the sparse vectors to dense vectors to obtain the real-time trajectory data expressed by the dense vectors of the user;
b2, inputting the real-time track data expressed by dense vectors of the user as query, key and value into a multi-head attention mechanism model with a mask of the track prediction model to obtain a decoding result;
b3, inputting the decoding result into the full-link layer of the track prediction model to obtain the predicted probability values of a plurality of candidate points of the user at the next moment;
and B4, acquiring the candidate point with the maximum probability value as the predicted track point of the user at the next moment, and outputting the candidate point as a track prediction result.
Preferably, the candidate point is a collective term for all the location points where the next location point of the target may appear. Assuming that there are m location points, the scores of the first m candidate points are consistent, and after the processing of the method of the present invention, the scores (probability values) of the m candidates are different, and the higher the probability value is, the higher the probability that the next location point of the target is the location point is.
According to an embodiment of the present invention, there is provided an electronic apparatus including: one or more processors; and a memory, wherein the memory is to store one or more executable instructions; the one or more processors are configured to perform the steps of the methods described in the foregoing embodiments via execution of one or more executable instructions.
It should be noted that, although the steps are described in a specific order, the steps are not necessarily performed in the specific order, and in fact, some of the steps may be performed concurrently or even in a changed order as long as the required functions are achieved.
The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.
The computer readable storage medium may be a tangible device that retains and stores instructions for use by an instruction execution device. The computer readable storage medium may include, for example, but is not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing.
Having described embodiments of the present invention, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims (11)

1. A method for training a trajectory prediction model, the method comprising:
a1, acquiring space-time trajectory data of trajectory segments containing a plurality of targets represented by dense vectors, and cutting the trajectory data into near-term trajectory data, short-term history data and long-term history data from near to far according to time;
a2, training a coding model of the first multi-head attention mechanism network by using long-term historical data to capture the long-term spatiotemporal relation of each track point in the long-term historical data;
a3, training a recurrent neural network coding model by using short-term historical data to capture the short-term space-time relation of each track point in the short-term historical data;
a4, training a coding model of a second multi-head attention mechanism network by using the long-term space-time relationship and the short-term space-time relationship to adjust the short-term space-time relationship according to the similarity of the long-term space-time relationship and the short-term space-time relationship, so as to obtain the adjusted short-term space-time relationship;
a5, training a decoding model of a third multi-head attention mechanism network by using the recent track data and the adjusted short-term space-time relation to obtain the track prediction model.
2. The method for training a trajectory prediction model according to claim 1, wherein the step a1 includes:
a11, acquiring space-time trajectory data of a plurality of targets represented by sparse vectors from a database and preprocessing the space-time trajectory data to obtain a plurality of trajectory segments;
a12, performing data mapping on the plurality of track segments to map sparse vectors to dense vectors, and obtaining space-time track data of the track segments containing a plurality of targets represented by the dense vectors;
and A13, cutting the space-time trajectory data of the trajectory segment containing a plurality of targets represented by dense vectors into recent trajectory data, short-term historical data and long-term historical data from near to far according to preset cutting rules and time.
3. The method for training a trajectory prediction model according to claim 2, wherein the step a11 includes:
a111, acquiring space-time trajectory data of a plurality of targets represented by sparse vectors from a database, wherein each target comprises one or more trajectory segments;
a112, preprocessing the acquired space-time trajectory data of a plurality of targets represented by sparse vectors, comprising:
a1121, cutting track segments of two adjacent track points with a time difference larger than or equal to a preset time threshold value from between the two adjacent track points so as to cut the track segments into two or more track segments;
a1122, deleting track segments containing track points, the number of which is less than a first preset number of points;
and A1123, deleting the target with the segment number of the track segment less than the preset segment number.
4. The method of claim 3, wherein the predetermined time threshold is 72 hours, the first predetermined number of points is 5, and the predetermined number of segments is 5 segments.
5. The method for training a trajectory prediction model according to claim 2, wherein the step a13 includes:
a131, presetting three time intervals, namely in a first time node, between the first time node and a second time node and before the second time node from track recording data, and respectively taking track sections belonging to the three time intervals as recent track data, short-term historical data and long-term historical data, wherein the values of the first time node and the second time node are set by a user according to needs;
a132, cutting a plurality of track segments represented by dense vectors to cut the track segments spanning any time interval into two segments from two adjacent track points belonging to the two intervals;
and A133, cutting the track segment containing the track points in the short-term historical data, the number of which is greater than the second preset point number, into two segments from the track point of the track segment located at the second preset point number and the next track point of the track segment, and deleting the track segment, the number of which is less than the first preset point number, of the track points after the cutting.
6. The method of training a trajectory prediction model according to claim 5, wherein the second predetermined number of points is 20.
7. The method for training a trajectory prediction model according to any one of claims 1 to 6,
in the step a2, inputting the long-term history data as query, key and value into a coding model of the first multi-head attention mechanism network to capture the long-term spatiotemporal relationship of each trace point according to the context information of each trace point in the long-term history data;
in the step A3, inputting the short-term historical data into a recurrent neural network to capture the short-term spatiotemporal relationship of each track point according to the context information of each track point in the short-term historical data;
in the step a4, inputting the long-term spatiotemporal relationship as a query and the short-term spatiotemporal relationship as a key and a value into a coding model of the second multi-head attention mechanism network to adjust the short-term spatiotemporal relationship according to the similarity of the long-term spatiotemporal relationship and the short-term spatiotemporal relationship, so as to obtain an adjusted short-term spatiotemporal relationship;
in step a5, the decoding model of the third multi-headed attention system network includes a multi-headed attention system model with a mask and a normal multi-headed attention system model, the multi-headed attention system model with the mask is input with the near-term trajectory data as the query, the key, and the value to capture the near-term spatiotemporal relationship of each trajectory point according to the context information of each trajectory point in the near-term history data, and the near-term spatiotemporal relationship as the query, the adjusted short-term spatiotemporal relationship as the key, and the adjusted short-term spatiotemporal relationship is input into the normal multi-headed attention system model to train the decoding model of the third multi-headed attention system network.
8. A trajectory prediction method, characterized in that the trajectory prediction method comprises:
according to the real-time trajectory data of the user, performing trajectory prediction by using the trajectory prediction model obtained by the method for training the trajectory prediction model according to any one of claims 1 to 7 to obtain a trajectory prediction result.
9. The trajectory prediction method according to claim 8, characterized in that the trajectory prediction method comprises:
b1, acquiring real-time trajectory data expressed by sparse vectors of the user and performing data mapping on the real-time trajectory data to map the sparse vectors to dense vectors to obtain the real-time trajectory data expressed by the dense vectors of the user;
b2, inputting the real-time track data expressed by dense vectors of the user as query, key and value into a multi-head attention mechanism model with a mask of a track prediction model to obtain a decoding result;
b3, inputting the decoding result into a full-link layer of a track prediction model to obtain predicted probability values of a plurality of candidate points of the user at the next moment;
and B4, acquiring the candidate point with the maximum probability value as the predicted track point of the user at the next moment, and outputting the candidate point as a track prediction result.
10. An electronic device, comprising:
one or more processors; and
a memory, wherein the memory is to store one or more executable instructions;
the one or more processors are configured to perform the steps of the method of any one of claims 1-7, and 8-9 via execution of the one or more executable instructions.
11. A computer-readable storage medium having embodied thereon a computer program, the computer program being executable by a processor to perform the steps of the method of any one of claims 1 to 7, and 8 to 9.
CN202010259417.5A 2020-04-03 2020-04-03 Method for training track prediction model and track prediction method Active CN111488984B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010259417.5A CN111488984B (en) 2020-04-03 2020-04-03 Method for training track prediction model and track prediction method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010259417.5A CN111488984B (en) 2020-04-03 2020-04-03 Method for training track prediction model and track prediction method

Publications (2)

Publication Number Publication Date
CN111488984A true CN111488984A (en) 2020-08-04
CN111488984B CN111488984B (en) 2023-07-21

Family

ID=71797728

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010259417.5A Active CN111488984B (en) 2020-04-03 2020-04-03 Method for training track prediction model and track prediction method

Country Status (1)

Country Link
CN (1) CN111488984B (en)

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111982144A (en) * 2020-08-20 2020-11-24 北京百度网讯科技有限公司 Navigation method, navigation device, electronic equipment and computer readable medium
CN112529294A (en) * 2020-12-09 2021-03-19 中国科学院深圳先进技术研究院 Training method, medium and equipment for individual random trip destination prediction model
CN112634328A (en) * 2020-12-24 2021-04-09 电子科技大学长三角研究院(衢州) Method for predicting pedestrian track based on self-centering star chart and attention mechanism
CN112766339A (en) * 2021-01-11 2021-05-07 中国科学院计算技术研究所 Trajectory recognition model training method and trajectory recognition method
CN112885079A (en) * 2021-01-11 2021-06-01 成都语动未来科技有限公司 Vehicle track prediction method based on global attention and state sharing
CN113127591A (en) * 2021-04-13 2021-07-16 河海大学 Position prediction method based on Transformer and LSTM
CN113504527A (en) * 2021-09-13 2021-10-15 北京海兰信数据科技股份有限公司 Radar target prediction processing method and system
CN113537459A (en) * 2021-06-28 2021-10-22 淮阴工学院 Method for predicting humiture of drug storage room
CN113554060A (en) * 2021-06-24 2021-10-26 福建师范大学 DTW-fused LSTM neural network trajectory prediction method
CN114842681A (en) * 2022-07-04 2022-08-02 中国电子科技集团公司第二十八研究所 Airport scene flight path prediction method based on multi-head attention mechanism
CN116743635A (en) * 2023-08-14 2023-09-12 北京大学深圳研究生院 Network prediction and regulation method and network regulation system
CN116807458A (en) * 2023-07-04 2023-09-29 中原工学院 Human gait track prediction method based on attention mechanism
CN116956098A (en) * 2023-09-21 2023-10-27 四川吉利学院 Long-tail track prediction method based on perception distributed comparison learning framework
CN117216614A (en) * 2023-09-22 2023-12-12 哈尔滨工业大学 Track characterization mining method based on space-time information extraction

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107480784A (en) * 2017-06-28 2017-12-15 青岛科技大学 A kind of mobile phone signaling data pedestrian traffic trajectory predictions method based on deep learning
US20180374359A1 (en) * 2017-06-22 2018-12-27 Bakhi.com Times Technology (Beijing) Co., Ltd. Evaluation framework for predicted trajectories in autonomous driving vehicle traffic prediction
CN110163439A (en) * 2019-05-24 2019-08-23 长安大学 A kind of city size taxi trajectory predictions method based on attention mechanism
CN110210604A (en) * 2019-05-21 2019-09-06 北京邮电大学 A kind of terminal device movement pattern method and device
CN110399973A (en) * 2019-07-24 2019-11-01 北京百度网讯科技有限公司 Method and apparatus for predicted position information
US20190349287A1 (en) * 2018-05-10 2019-11-14 Dell Products L. P. System and method to learn and prescribe optimal network path for sdn
CN110928993A (en) * 2019-11-26 2020-03-27 重庆邮电大学 User position prediction method and system based on deep cycle neural network

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180374359A1 (en) * 2017-06-22 2018-12-27 Bakhi.com Times Technology (Beijing) Co., Ltd. Evaluation framework for predicted trajectories in autonomous driving vehicle traffic prediction
CN107480784A (en) * 2017-06-28 2017-12-15 青岛科技大学 A kind of mobile phone signaling data pedestrian traffic trajectory predictions method based on deep learning
US20190349287A1 (en) * 2018-05-10 2019-11-14 Dell Products L. P. System and method to learn and prescribe optimal network path for sdn
CN110210604A (en) * 2019-05-21 2019-09-06 北京邮电大学 A kind of terminal device movement pattern method and device
CN110163439A (en) * 2019-05-24 2019-08-23 长安大学 A kind of city size taxi trajectory predictions method based on attention mechanism
CN110399973A (en) * 2019-07-24 2019-11-01 北京百度网讯科技有限公司 Method and apparatus for predicted position information
CN110928993A (en) * 2019-11-26 2020-03-27 重庆邮电大学 User position prediction method and system based on deep cycle neural network

Non-Patent Citations (9)

* Cited by examiner, † Cited by third party
Title
ASHISH VASWANI等: "Attention Is All You Need" *
JEAN MERCAT等: "Multi-Head Attention for Multi-Modal Joint Vehicle Motion Forecasting" *
JIE FENG等: "DeepMove: Predicting Human Mobility with Attentional Recurrent Networks" *
JUN ZENG等: "A Next Location Predicting Approach Based on a Recurrent Neural Network and Self-attention" *
QIANG LIU等: "Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts" *
SEONG HYEON PARK等: "Sequence-to-Sequence Prediction of Vehicle Trajectory via LSTM Encoder-Decoder Architecture" *
TANGWEN QIAN等: "CABIN: A Novel Cooperative Attention Based Location Prediction Network Using Internal-External Trajectory Dependencies" *
YONGHUI WU等: "Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation" *
石庆研;岳聚财;韩萍;王文青;: "基于LSTM-ARIMA模型的短期航班飞行轨迹预测" *

Cited By (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111982144A (en) * 2020-08-20 2020-11-24 北京百度网讯科技有限公司 Navigation method, navigation device, electronic equipment and computer readable medium
CN112529294B (en) * 2020-12-09 2023-04-14 中国科学院深圳先进技术研究院 Training method, medium and equipment for individual random trip destination prediction model
CN112529294A (en) * 2020-12-09 2021-03-19 中国科学院深圳先进技术研究院 Training method, medium and equipment for individual random trip destination prediction model
CN112634328A (en) * 2020-12-24 2021-04-09 电子科技大学长三角研究院(衢州) Method for predicting pedestrian track based on self-centering star chart and attention mechanism
CN112634328B (en) * 2020-12-24 2022-11-08 电子科技大学长三角研究院(衢州) Method for predicting pedestrian track based on self-centering star chart and attention mechanism
CN112766339A (en) * 2021-01-11 2021-05-07 中国科学院计算技术研究所 Trajectory recognition model training method and trajectory recognition method
CN112885079A (en) * 2021-01-11 2021-06-01 成都语动未来科技有限公司 Vehicle track prediction method based on global attention and state sharing
CN113127591A (en) * 2021-04-13 2021-07-16 河海大学 Position prediction method based on Transformer and LSTM
CN113127591B (en) * 2021-04-13 2022-09-23 河海大学 Position prediction method based on Transformer and LSTM
CN113554060B (en) * 2021-06-24 2023-06-20 福建师范大学 LSTM neural network track prediction method integrating DTW
CN113554060A (en) * 2021-06-24 2021-10-26 福建师范大学 DTW-fused LSTM neural network trajectory prediction method
CN113537459A (en) * 2021-06-28 2021-10-22 淮阴工学院 Method for predicting humiture of drug storage room
CN113537459B (en) * 2021-06-28 2024-04-26 淮阴工学院 Drug warehouse temperature and humidity prediction method
CN113504527A (en) * 2021-09-13 2021-10-15 北京海兰信数据科技股份有限公司 Radar target prediction processing method and system
CN113504527B (en) * 2021-09-13 2021-12-14 北京海兰信数据科技股份有限公司 Radar target prediction processing method and system
CN114842681A (en) * 2022-07-04 2022-08-02 中国电子科技集团公司第二十八研究所 Airport scene flight path prediction method based on multi-head attention mechanism
CN116807458A (en) * 2023-07-04 2023-09-29 中原工学院 Human gait track prediction method based on attention mechanism
CN116743635B (en) * 2023-08-14 2023-11-07 北京大学深圳研究生院 Network prediction and regulation method and network regulation system
CN116743635A (en) * 2023-08-14 2023-09-12 北京大学深圳研究生院 Network prediction and regulation method and network regulation system
CN116956098A (en) * 2023-09-21 2023-10-27 四川吉利学院 Long-tail track prediction method based on perception distributed comparison learning framework
CN117216614A (en) * 2023-09-22 2023-12-12 哈尔滨工业大学 Track characterization mining method based on space-time information extraction
CN117216614B (en) * 2023-09-22 2024-03-08 哈尔滨工业大学 Track characterization mining method based on space-time information extraction

Also Published As

Publication number Publication date
CN111488984B (en) 2023-07-21

Similar Documents

Publication Publication Date Title
CN111488984A (en) Method for training trajectory prediction model and trajectory prediction method
US11568000B2 (en) System and method for automatic task-oriented dialog system
AU2019204399B2 (en) A neural dialog state tracker for spoken dialog systems using dynamic memory networks
CN108629288B (en) Gesture recognition model training method, gesture recognition method and system
CN107871014A (en) A kind of big data cross-module state search method and system based on depth integration Hash
CN110945515A (en) Intent and slot detection for digital assistants
CN109190544B (en) Human identity recognition method based on sequence depth image
CN112541944B (en) Probability twin target tracking method and system based on conditional variational encoder
CN110766041A (en) Deep learning-based pest detection method
WO2023115598A1 (en) Planar cascade steady flow prediction method based on generative adversarial network
CN109858454B (en) Adaptive kernel correlation filtering tracking method based on dual models
CN115042798A (en) Traffic participant future trajectory prediction method and system, and storage medium
CN111722306A (en) Typhoon landing intensity prediction method and system based on TCN network model
CN115471771A (en) Video time sequence action positioning method based on semantic level time sequence correlation modeling
CN116229519A (en) Knowledge distillation-based two-dimensional human body posture estimation method
Bermingham et al. Mining place-matching patterns from spatio-temporal trajectories using complex real-world places
CN115271063A (en) Inter-class similarity knowledge distillation method and model based on feature prototype projection
CN114547347A (en) Time sequence knowledge graph completion method, device and equipment based on convolutional neural network
CN114529552A (en) Remote sensing image building segmentation method based on geometric contour vertex prediction
Lin et al. Domestic activities clustering from audio recordings using convolutional capsule autoencoder network
CN112766339A (en) Trajectory recognition model training method and trajectory recognition method
Ma et al. PPDTSA: Privacy-preserving deep transformation self-attention framework for object detection
US20050025242A1 (en) Sequential motion pattern representation
CN116503399A (en) Insulator pollution flashover detection method based on YOLO-AFPS
CN114663839B (en) Method and system for re-identifying blocked pedestrians

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20240305

Address after: 518133, 7th Floor, Building 8, Qiugu, Meisheng Huigu Science and Technology Park, No. 83 Dabao Road, Shanghe Community, Xin'an Street, Bao'an District, Shenzhen City, Guangdong Province

Patentee after: SHENZHEN GUOKE YIDAO TECHNOLOGY Co.,Ltd.

Country or region after: China

Address before: 100190 No. 6 South Road, Zhongguancun Academy of Sciences, Beijing, Haidian District

Patentee before: Institute of Computing Technology, Chinese Academy of Sciences

Country or region before: China

TR01 Transfer of patent right