CN118052347A - Travel time estimation method and system based on travel track sequence of floating car - Google Patents
Travel time estimation method and system based on travel track sequence of floating car Download PDFInfo
- Publication number
- CN118052347A CN118052347A CN202410451045.4A CN202410451045A CN118052347A CN 118052347 A CN118052347 A CN 118052347A CN 202410451045 A CN202410451045 A CN 202410451045A CN 118052347 A CN118052347 A CN 118052347A
- Authority
- CN
- China
- Prior art keywords
- travel
- travel track
- floating car
- floating
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013528 artificial neural network Methods 0.000 claims abstract description 46
- 238000012549 training Methods 0.000 claims description 49
- 238000005070 sampling Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 11
- 238000007781 pre-processing Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000012795 verification Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 description 11
- 238000004590 computer program Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 229910021389 graphene Inorganic materials 0.000 description 1
- 238000011065 in-situ storage Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a travel time estimation method and a travel time estimation system based on a travel track sequence of a floating car, which relate to the technical field of data prediction, acquire travel tracks of the floating car under various travel time conditions, enable track data to be diversified, sample the travel tracks of the floating car, generate a sampled travel track sequence set of the floating car, sample various travel track sequences and travel duration, combine the various travel track sequences of the floating car and external environment conditions of the various travel track sequences of the floating car, train a deep neural network by using combined sequence data, and generate a prediction model to predict the travel duration. Due to the diversity of the track data, the prediction model is constructed by applying the diversity track data, so that the prediction accuracy can be very high even facing complex and diverse traffic modes.
Description
Technical Field
The invention relates to the field of data prediction, in particular to a travel time estimation method and system based on a plurality of travel track sequences of a floating car.
Background
With the vigorous development of Chinese economy, people's travel demands have increased greatly, and travel time estimation is a vital task for various applications involving road traffic movement, such as route planning, navigation, and car calling. As urban population and road construction increase, travelers need to know the expected travel time of their journey in advance. However, accurate estimation of travel time is a challenge due to the complex road network and implicit information. Therefore, it is necessary to develop a transportation time model that can process route-rich spatio-temporal information and effectively simulate various factors affecting travel time. The nature of travel time estimation is an approximately linear regression problem, and the traditional travel time estimation method fits the relationship between travel and time through a statistical method, so that time-varying characteristics or emergency situations in traffic operation are difficult to characterize, and accurate results are obtained.
In recent years, with the rapid development of computer science, a method for estimating travel time using a deep neural network technique has been widely proposed by many researchers. The deep neural network-based approach formally represents road network segments in the physical world as mathematically structured vectors while preserving the original information as much as possible by minimizing prediction errors. The regression problem of travel time estimation using deep neural network-based models is very suitable and reliable and has played an important role in traffic field applications represented by map navigation. However, although the conventional deep neural network structure achieves a certain effect, the prediction accuracy is not ideal in the face of complex and diverse traffic modes.
Disclosure of Invention
The invention aims to provide a travel time estimation method and system based on a travel track sequence of a floating car, which can solve the problem of low prediction precision when a traditional deep neural network structure faces to complex and diverse traffic modes.
In order to achieve the above object, the present invention provides the following.
In a first aspect, the application provides a travel time estimation method based on a travel track sequence of a floating car, which comprises the following steps.
Acquiring travel tracks of the floating car under various travel time conditions; the travel time conditions comprise travel starting and stopping points, travel distance, travel time and travel duration.
Sampling the travel track of each floating car to obtain a sampled travel track sequence set of the floating car; each sampled floating car travel track sequence in the sampled floating car travel track sequence set comprises an adjacent road section index sequence after the floating car travel track is mapped to a road network, a basic attribute sequence of an adjacent road section after the floating car travel track is mapped to the road network, a GPS point sequence after the floating car travel track is mapped to the road network and the travel duration of the corresponding floating car travel track.
And training a deep neural network according to the sampled travel track sequence set of the floating car to obtain a prediction model.
And estimating travel time by using the prediction model.
In a second aspect, the application provides a travel time estimation system based on a travel track sequence of a floating car, which comprises the following modules.
The data acquisition module is used for acquiring travel tracks of the floating car under various travel time conditions; the travel time conditions comprise travel starting and stopping points, travel distance, travel time and travel duration.
The data sampling module is used for sampling travel tracks of each floating car to obtain a sampled travel track sequence set of the floating car; each sampled floating car travel track sequence in the sampled floating car travel track sequence set comprises an adjacent road section index sequence after the floating car travel track is mapped to a road network, a basic attribute sequence of an adjacent road section after the floating car travel track is mapped to the road network, a GPS point sequence after the floating car travel track is mapped to the road network and the travel duration of the corresponding floating car travel track.
And the model training module is used for training the deep neural network according to the sampled travel track sequence set of the floating car to obtain a prediction model.
And the data prediction module is used for estimating the travel time by utilizing the prediction model.
According to the specific embodiments provided by the invention, the following technical effects are disclosed.
The invention provides a travel time estimation method and a travel time estimation system based on a travel track sequence of a floating car, which are used for acquiring travel tracks of the floating car under various travel time conditions so as to enable track data to be diversified, and meanwhile, sampling the travel tracks of the floating car to generate a sampled travel track sequence set of the floating car, so that various travel track sequences and travel duration are sampled to train a deep neural network, and a prediction model is generated to predict the travel duration. Due to the diversity of the track data, the prediction model is constructed by applying the diversity track data, so that the prediction accuracy can be very high even facing complex and diverse traffic modes.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a travel time estimation method based on a travel track sequence of a floating car according to embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of a predictive model construction process according to embodiment 1 of the present invention;
FIG. 3 is a schematic diagram of a computer sequence prediction model constructed based on a deep neural network according to embodiment 1 of the present invention;
Fig. 4 is a block diagram of a travel time estimation system based on a travel track sequence of a floating car according to embodiment 2 of the present invention;
fig. 5 is an internal structure diagram of a computer device according to embodiment 6 of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention aims to provide a travel time estimation method and a travel time estimation system based on a travel track sequence of a floating car, and aims to construct a travel duration prediction model based on diversified track data by combining travel durations of travel tracks of the floating car, and the prediction model can have high prediction precision even facing complex and diversified traffic modes.
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Example 1
As shown in fig. 1, the present embodiment provides a travel time estimation method based on a travel track sequence of a floating car, which includes the following steps.
Step 101: acquiring travel tracks of the floating car under various travel time conditions; the travel time conditions comprise travel starting and stopping points, travel distance, travel time and travel duration.
The travel track of the floating car under various travel time conditions specifically comprises: the floating cars of different starting and stopping points, different travel distances, different travel times and different travel durations contain a sequence of GPS points of time slice information.
Step 102: sampling the travel track of each floating car to obtain a sampled travel track sequence set of the floating car; each sampled floating car travel track sequence in the sampled floating car travel track sequence set comprises an adjacent road section index sequence after the floating car travel track is mapped to a road network, a basic attribute sequence of an adjacent road section after the floating car travel track is mapped to the road network, a GPS point sequence after the floating car travel track is mapped to the road network and the travel duration of the corresponding floating car travel track. The duration of the stroke is a discrete value that is not negative.
The basic attributes mainly comprise: the type of road segment, the length of the road segment in the track (i.e. the distance from the start of the track to the road segment), etc. (denoted as）。
Since each road segment has a specific basic attribute, the basic attribute of the i-th road segment can be expressed as a list (denoted as）。
The basic attribute sequence in the track is the sequence of basic attribute components of all road segments in the track (recorded as）。
In order to ensure the accuracy of the travel track, before executing step 102 "sample the travel track of each floating car", the method specifically includes.
And carrying out data preprocessing on each travel track of the floating car, removing travel track abnormal data in the travel track of the floating car, and generating a preprocessed travel track of the floating car.
The specific data preprocessing is divided into two steps: (1) And screening the travel track of each floating car, removing abnormal data of abnormal travel in the travel track of the floating car, and generating the screened travel track of the floating car.
The track of the floating car is mainly taxi data, so that the taxi comprises actions such as waiting in situ, no-load passenger searching and the like, and the track has the actions, but the track is required to be the track under the condition that the floating car-mounted passenger normally runs, so that abnormal trip abnormal data refers to the track under the condition of no passenger carrying.
(2) And cleaning the travel track of the floating car screened in the previous step, removing travel track abnormal data exceeding a preset range in the travel track of the floating car screened, and generating the travel track of the floating car cleaned.
After the track data under the condition of not carrying passengers are screened out, some abnormal data still exist and cannot be removed, for example, the track travel time is too long and is more than 3600s, the track length is too short and is less than 1000m, and the average track speed is too high and is more than 100km/h or too low and is less than 15km/h. So abnormal data exceeding the preset range refers to data exceeding the above specific range (the range is defined manually), and such data does not empirically conform to the actual travel situation of the floating car and should be rejected.
Step 103: and training a deep neural network according to the sampled travel track sequence set of the floating car to obtain a prediction model (namely, a computer sequence prediction model in the corresponding figure 1).
As shown in fig. 2 and 3, step 103 specifically includes.
(1) Setting super parameters of the deep neural network with different numerical combinations; the super parameters comprise the number of training rounds, the learning rate and the data volume of each training.
(2) And dividing the sampled travel track sequence set (tensor) of the floating car into a training set and a verification set.
(3) And carrying out partial blurring processing on adjacent road section indexes in the sampled travel track sequence of the floating car in the training set to obtain a blurred travel track sequence of the floating car.
(4) And training the deep neural network by using the sampled travel track sequence of the floating vehicle and the fuzzy travel track sequence of the floating vehicle in the training set according to the numerical combination of each super parameter.
(5) Calculating damage errors by using the predicted value and the corresponding real value output by the deep neural network to adjust the parameters of the deep neural network model until the parameters of the neural network model converge or the current iteration number reaches the preset training round number, so as to obtain a plurality of trained deep neural networks; the predicted value output by the deep neural network comprises a travel duration predicted value corresponding to the sampled travel track sequence of the floating car in the training set, a travel duration predicted value corresponding to the blurred travel track sequence of the floating car and a predicted value of the blurred adjacent road section index.
As shown in fig. 3, the depth neural network includes an encoder and a decoder, after the sampled travel track sequence of the floating car and the blurred travel track sequence in the training set are input to the encoder, a road section representation vector is obtained, a predicted value of a road section index of the blurred process is predicted, the sampled travel track sequence aggregate road section representation vector is input to the decoder, and the decoder obtains a journey duration estimated value. Wherein the loss function 1: the main objective of the function is to calculate the error between the predicted value and the true value of the road segment index of the fuzzy process (e.g. manually masked) in the travel track; the loss function 1 is a cross entropy loss function commonly used in classification tasks. Loss function 2: the main objective of this function is to calculate the error between the predicted value and the true value of the travel duration of the travel trajectory, the loss function 2 is a SmoothL <1> loss function, which is in the form of a square error (L2) at a specific threshold, and is in the form of an absolute error (L1) outside the threshold, smoothL <1> is less sensitive to outliers than L2, while its convergence speed is more stable and faster than L1. In the training stage, two loss functions are combined into a whole loss function in a weighted addition mode, in the training stage, model parameters of the deep neural network are adjusted by using loss errors calculated by the two loss functions, fuzzy processing is introduced in the training stage, loss errors between predicted values of corresponding road section indexes and original road section true values are calculated, and the deep neural network can learn association relations between adjacent indexes in a road section index sequence better, so that the accuracy of the follow-up predicted journey duration of the deep neural network is improved.
(6) And selecting an optimal model in each trained deep neural network as the prediction model.
As an optional implementation manner, selecting an optimal prediction model from the prediction models, verifying different prediction models by using the sampled travel track sequence set of the floating vehicle in the verification set, determining the optimal prediction model, and recording super parameters and model parameters corresponding to the optimal prediction model.
Step 104: and estimating travel time by using the prediction model. Specifically included are.
(1) And acquiring a travel track of the floating car to be predicted under any travel time condition which does not contain the travel duration.
(2) And sampling the travel track of the floating car to be predicted, and generating a sampled travel track sequence set of the floating car to be predicted.
(3) And inputting the sampled floating car travel track sequence set (tensor) to be predicted into the prediction model, and predicting the travel duration of the floating car travel track to be predicted.
In this embodiment, the travel track of the floating car under various travel time conditions is obtained, so that track data has diversity, meanwhile, the travel track of the floating car is sampled, and a sampled travel track sequence set of the floating car is generated, so that various travel track sequences and travel duration are sampled, the travel track sequences of multiple floating car types and external environmental conditions thereof are combined, and then the combined sequence data is utilized to train the deep neural network, so that a prediction model is generated to predict the travel duration. Due to the diversity of the track data, the prediction model is constructed by applying the diversity track data, so that the prediction model can have high prediction precision even facing complex and diverse traffic modes.
Example 2
As shown in fig. 4, the present embodiment provides a travel time estimation system based on a travel track sequence of a floating car, which includes the following modules.
The data acquisition module 100 is used for acquiring travel tracks of the floating car under various travel time conditions; the travel time conditions comprise travel starting and stopping points, travel distance, travel time and travel duration.
The data sampling module 200 is configured to sample the travel track of each floating vehicle, so as to obtain a sampled travel track sequence set of the floating vehicle; each sampled floating car travel track sequence in the sampled floating car travel track sequence set comprises an adjacent road section index sequence after the floating car travel track is mapped to a road network, a basic attribute sequence of an adjacent road section after the floating car travel track is mapped to the road network, a GPS point sequence after the floating car travel track is mapped to the road network and the travel duration of the corresponding floating car travel track.
The model training module 300 is configured to train the deep neural network according to the sampled travel track sequence set of the floating car, so as to obtain a prediction model.
A data prediction module 400 for estimating travel time using the prediction model.
As an alternative embodiment, the system further comprises.
A data preprocessing module; the data preprocessing module is used for preprocessing the data of each travel track of the floating car, removing travel track abnormal data in the travel track of the floating car and generating a preprocessed travel track of the floating car.
The model training module specifically comprises the following components.
The super parameter selection unit is used for setting super parameters of the deep neural network with different numerical combinations; the super parameters comprise the number of training rounds, the learning rate and the data volume of each training.
The data set dividing unit is used for dividing the sampled travel track sequence set of the floating car into a training set and a verification set.
And the adjacent road section index blurring unit is used for carrying out partial blurring processing on the adjacent road section indexes in the sampled travel track sequence of the floating vehicle in the training set to obtain a blurred travel track sequence of the floating vehicle.
The network training updating unit is used for training the deep neural network by utilizing the sampled travel track sequence of the floating vehicle and the fuzzy travel track sequence of the floating vehicle in the training set for each numerical combination of the super parameters; calculating a loss error by using the predicted value and the corresponding true value output by the deep neural network to adjust the parameters of the deep neural network model until the parameters of the deep neural network model converge or the current iteration number reaches the preset training round number, so as to obtain a plurality of trained deep neural networks; the predicted value output by the deep neural network comprises a travel duration predicted value corresponding to the sampled travel track sequence of the floating car in the training set, a travel duration predicted value corresponding to the blurred travel track sequence of the floating car and a predicted value of the blurred adjacent road section index.
And the optimal model determining unit is used for selecting an optimal model in each trained deep neural network as the prediction model.
Example 3
A computer apparatus, comprising: the memory, the processor, and a computer program stored on the memory and executable on the processor, the processor executing the computer program to implement the steps of a travel time estimation method based on a floating car travel track sequence in embodiment 1.
Example 4
A computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a travel time estimation method based on a sequence of travel trajectories of floating vehicles in embodiment 1.
Example 5
A computer program product comprising a computer program which when executed by a processor implements the steps of a travel time estimation method based on a sequence of travel tracks of a floating car of embodiment 1.
Example 6
A computer device, which may be a database, may have an internal structure as shown in fig. 5. The computer device includes a processor, a memory, an Input/Output interface (I/O) and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store the pending transactions. The input/output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a travel time estimation method based on a floating car travel track sequence in embodiment 1.
It should be noted that, the object information (including, but not limited to, object device information, object personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) related to the present invention are both information and data authorized by the object or sufficiently authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related countries and regions.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, database, or other medium used in embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory (ReRAM), magneto-resistive random access Memory (Magnetoresistive Random Access Memory, MRAM), ferroelectric Memory (Ferroelectric Random Access Memory, FRAM), phase change Memory (PHASE CHANGE Memory, PCM), graphene Memory, and the like. Volatile memory can include random access memory (Random Access Memory, RAM) or external cache memory, and the like. By way of illustration, and not limitation, RAM can be in the form of a variety of forms, such as Static Random access memory (Static Random access memory AccessMemory, SRAM) or dynamic Random access memory (Dynamic Random Access Memory, DRAM), and the like. The databases referred to in the embodiments provided herein may include at least one of a relational database and a non-relational database. The non-relational database may include, but is not limited to, a blockchain-based distributed database, and the like. The processor referred to in the embodiments provided in the present invention may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic unit, a data processing logic unit based on quantum computing, or the like, but is not limited thereto.
The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The principles and embodiments of the present invention have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present invention and the core ideas thereof; also, it is within the scope of the present invention to be modified by those of ordinary skill in the art in light of the present teachings. In view of the foregoing, this description should not be construed as limiting the invention.
Claims (8)
1. The travel time estimation method based on the travel track sequence of the floating car is characterized by comprising the following steps of:
acquiring travel tracks of the floating car under various travel time conditions; the travel time conditions comprise travel starting and stopping points, travel distance, travel time and travel duration;
Sampling the travel track of each floating car to obtain a sampled travel track sequence set of the floating car; each sampled floating vehicle travel track sequence in the sampled floating vehicle travel track sequence set comprises an adjacent road section index sequence after the floating vehicle travel track is mapped to a road network, a basic attribute sequence of an adjacent road section after the floating vehicle travel track is mapped to the road network, a GPS point sequence after the floating vehicle travel track is mapped to the road network and the travel duration of the corresponding floating vehicle travel track;
training a deep neural network according to the sampled travel track sequence set of the floating car to obtain a prediction model;
and estimating travel time by using the prediction model.
2. The travel time estimation method based on a travel track sequence of a floating car according to claim 1, wherein before performing the step of "sampling each travel track of the floating car", specifically comprising:
and carrying out data preprocessing on each travel track of the floating car, removing travel track abnormal data in the travel track of the floating car, and generating a preprocessed travel track of the floating car.
3. The travel time estimation method based on the travel track sequence of the floating car according to claim 1, wherein the training of the deep neural network according to the sampled travel track sequence set to obtain the prediction model specifically comprises the following steps:
setting super parameters of the deep neural network with different numerical combinations; the super parameters comprise the number of training rounds, the learning rate and the data volume of each training;
dividing the sampled travel track sequence set of the floating vehicle into a training set and a verification set;
Carrying out partial blurring processing on adjacent road section indexes in the sampled travel track sequence of the floating car in the training set to obtain a blurred travel track sequence of the floating car;
Training the deep neural network by using the sampled travel track sequence of the floating vehicle and the fuzzy travel track sequence of the floating vehicle in the training set according to the numerical combination of each super parameter;
Calculating damage errors by using the predicted value and the corresponding real value output by the deep neural network to adjust the parameters of the deep neural network model until the parameters of the deep neural network model converge or the current iteration number reaches the preset training round number, so as to obtain a plurality of trained deep neural networks; the predicted value output by the deep neural network comprises a travel duration predicted value corresponding to the sampled travel track sequence of the floating car in the training set, a travel duration predicted value corresponding to the blurred travel track sequence of the floating car and a predicted value of a blurred adjacent road section index;
And selecting an optimal model in each trained deep neural network as the prediction model.
4. The travel time estimation method based on a travel track sequence of a floating car according to claim 3, wherein an optimal model in each trained deep neural network is selected as the prediction model, and specifically comprises:
And verifying different trained deep neural networks by using the sampled travel track sequence of the floating car in the verification set, and determining an optimal model as the prediction model.
5. The travel time estimation method based on the travel track sequence of the floating car according to claim 1, wherein the travel time estimation is performed by using the prediction model, and specifically comprises the following steps:
acquiring a travel track of the floating car to be predicted under any travel time condition which does not contain travel duration;
Sampling the travel track of the floating car to be predicted, and generating a sampled travel track sequence set of the floating car to be predicted;
and inputting the sampled travel track sequence set of the floating vehicle to be predicted into the prediction model, and predicting the travel duration of the travel track of the floating vehicle to be predicted.
6. Travel time estimation system based on floating car travel track sequence, characterized by comprising:
The data acquisition module is used for acquiring travel tracks of the floating car under various travel time conditions; the travel time conditions comprise travel starting and stopping points, travel distance, travel time and travel duration;
The data sampling module is used for sampling travel tracks of each floating car to obtain a sampled travel track sequence set of the floating car; each sampled floating vehicle travel track sequence in the sampled floating vehicle travel track sequence set comprises an adjacent road section index sequence after the floating vehicle travel track is mapped to a road network, a basic attribute sequence of an adjacent road section after the floating vehicle travel track is mapped to the road network, a GPS point sequence after the floating vehicle travel track is mapped to the road network and the travel duration of the corresponding floating vehicle travel track;
The model training module is used for training the deep neural network according to the sampled travel track sequence set of the floating car to obtain a prediction model;
And the data prediction module is used for estimating the travel time by utilizing the prediction model.
7. The travel time estimation system based on a floating car travel track sequence of claim 6, further comprising: a data preprocessing module; the data preprocessing module is used for preprocessing the data of each travel track of the floating car, removing travel track abnormal data in the travel track of the floating car and generating a preprocessed travel track of the floating car.
8. The travel time estimation system based on a travel track sequence of a floating car of claim 7, wherein the model training module specifically comprises:
The super parameter selection unit is used for setting super parameters of the deep neural network with different numerical combinations; the super parameters comprise the number of training rounds, the learning rate and the data volume of each training;
The data set dividing unit is used for dividing the sampled travel track sequence set of the floating car into a training set and a verification set;
The adjacent road section index blurring unit is used for carrying out partial blurring processing on the adjacent road section indexes in the sampled travel track sequence of the floating vehicle in the training set to obtain a blurred travel track sequence of the floating vehicle;
The network training updating unit is used for training the deep neural network by utilizing the sampled travel track sequence of the floating vehicle and the fuzzy travel track sequence of the floating vehicle in the training set for each numerical combination of the super parameters; calculating damage errors by using the predicted value and the corresponding real value output by the deep neural network to adjust the parameters of the deep neural network model until the parameters of the deep neural network model converge or the current iteration number reaches the preset training round number, so as to obtain a plurality of trained deep neural networks; the predicted value output by the deep neural network comprises a travel duration predicted value corresponding to the sampled travel track sequence of the floating car in the training set, a travel duration predicted value corresponding to the blurred travel track sequence of the floating car and a predicted value of a blurred adjacent road section index;
and the optimal model determining unit is used for selecting an optimal model in each trained deep neural network as the prediction model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410451045.4A CN118052347A (en) | 2024-04-16 | 2024-04-16 | Travel time estimation method and system based on travel track sequence of floating car |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410451045.4A CN118052347A (en) | 2024-04-16 | 2024-04-16 | Travel time estimation method and system based on travel track sequence of floating car |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118052347A true CN118052347A (en) | 2024-05-17 |
Family
ID=91046949
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410451045.4A Pending CN118052347A (en) | 2024-04-16 | 2024-04-16 | Travel time estimation method and system based on travel track sequence of floating car |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118052347A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020120389A1 (en) * | 2001-02-23 | 2002-08-29 | Hitachi, Ltd. | Method of presuming traffic conditions by using floating car data and system for presuming and presenting traffic conditions by using floating data |
| CN104574967A (en) * | 2015-01-14 | 2015-04-29 | 合肥革绿信息科技有限公司 | City large-area road network traffic sensing method based on plough satellite |
| CN106940930A (en) * | 2016-11-01 | 2017-07-11 | 深圳市城市交通规划设计研究中心有限公司 | Motorway journeys time prediction system and Forecasting Methodology |
| CN109410575A (en) * | 2018-10-29 | 2019-03-01 | 北京航空航天大学 | A kind of road network trend prediction method based on capsule network and the long Memory Neural Networks in short-term of nested type |
| US20190156662A1 (en) * | 2016-12-09 | 2019-05-23 | Dalian University Of Technology | A method for estimating road travel time based on built environment and low-frequency floating car data |
| CN111710160A (en) * | 2020-06-01 | 2020-09-25 | 北方工业大学 | Travel time prediction method based on floating car data |
| CN112017436A (en) * | 2020-09-09 | 2020-12-01 | 中国科学院自动化研究所 | Method and system for predicting urban traffic travel time |
| CN113052206A (en) * | 2021-03-04 | 2021-06-29 | 武汉理工大学 | Road travel time prediction method and device based on floating car data |
| CN114202120A (en) * | 2021-12-13 | 2022-03-18 | 中国电子科技集团公司第十五研究所 | Urban traffic travel time prediction method aiming at multi-source heterogeneous data |
-
2024
- 2024-04-16 CN CN202410451045.4A patent/CN118052347A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020120389A1 (en) * | 2001-02-23 | 2002-08-29 | Hitachi, Ltd. | Method of presuming traffic conditions by using floating car data and system for presuming and presenting traffic conditions by using floating data |
| CN104574967A (en) * | 2015-01-14 | 2015-04-29 | 合肥革绿信息科技有限公司 | City large-area road network traffic sensing method based on plough satellite |
| CN106940930A (en) * | 2016-11-01 | 2017-07-11 | 深圳市城市交通规划设计研究中心有限公司 | Motorway journeys time prediction system and Forecasting Methodology |
| US20190156662A1 (en) * | 2016-12-09 | 2019-05-23 | Dalian University Of Technology | A method for estimating road travel time based on built environment and low-frequency floating car data |
| CN109410575A (en) * | 2018-10-29 | 2019-03-01 | 北京航空航天大学 | A kind of road network trend prediction method based on capsule network and the long Memory Neural Networks in short-term of nested type |
| CN111710160A (en) * | 2020-06-01 | 2020-09-25 | 北方工业大学 | Travel time prediction method based on floating car data |
| CN112017436A (en) * | 2020-09-09 | 2020-12-01 | 中国科学院自动化研究所 | Method and system for predicting urban traffic travel time |
| CN113052206A (en) * | 2021-03-04 | 2021-06-29 | 武汉理工大学 | Road travel time prediction method and device based on floating car data |
| CN114202120A (en) * | 2021-12-13 | 2022-03-18 | 中国电子科技集团公司第十五研究所 | Urban traffic travel time prediction method aiming at multi-source heterogeneous data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tian | Approach for short-term traffic flow prediction based on empirical mode decomposition and combination model fusion | |
| CN114973677A (en) | Method and apparatus for determining estimated time of arrival | |
| CN113792929B (en) | Traffic flow prediction method, electronic device and storage medium | |
| CN110956341B (en) | Parking lot flow prediction method and device, electronic equipment and storage medium | |
| CN112633602B (en) | Traffic congestion index prediction method and device based on GIS map information | |
| CN113159403B (en) | Intersection pedestrian track prediction method and device | |
| CN116342657B (en) | TCN-GRU ship track prediction method, system, equipment and medium based on coding-decoding structure | |
| CN111461426A (en) | High-precision travel time length prediction method based on deep learning | |
| CN114881339A (en) | Vehicle trajectory prediction method, system, computer device, and storage medium | |
| CN113449905A (en) | Traffic jam early warning method based on gated cyclic unit neural network | |
| CN114360239A (en) | Traffic prediction method and system for multilayer space-time traffic knowledge map reconstruction | |
| CN112529284A (en) | Private car residence time prediction method, device and medium based on neural network | |
| CN116415200A (en) | Abnormal vehicle track abnormality detection method and system based on deep learning | |
| CN110264725B (en) | Method and device for determining road section flow | |
| CN115204755B (en) | Service area access rate measuring method and device, electronic equipment and readable storage medium | |
| CN111160594B (en) | Method and device for estimating arrival time and storage medium | |
| CN116778715A (en) | Multi-factor intelligent prediction method for high-speed traffic flow | |
| CN118052347A (en) | Travel time estimation method and system based on travel track sequence of floating car | |
| CN114724414B (en) | Method and device for determining urban air traffic sharing rate, electronic equipment and medium | |
| CN116080681A (en) | Zhou Chehang identification and track prediction method based on cyclic convolutional neural network | |
| CN115700628A (en) | Traffic flow prediction method and system containing missing data | |
| CN114722704A (en) | Wheel wear prediction network model training method and device | |
| CN114492544A (en) | Model training method and device and traffic incident occurrence probability evaluation method and device | |
| CN114281808A (en) | Traffic big data cleaning method, device, equipment and readable storage medium | |
| CN116542528B (en) | Traffic demand satisfaction analysis method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |