CN111860920B - Travel time prediction method and device - Google Patents
Travel time prediction method and device Download PDFInfo
- Publication number
- CN111860920B CN111860920B CN201910356006.5A CN201910356006A CN111860920B CN 111860920 B CN111860920 B CN 111860920B CN 201910356006 A CN201910356006 A CN 201910356006A CN 111860920 B CN111860920 B CN 111860920B
- Authority
- CN
- China
- Prior art keywords
- traffic data
- historical
- historical traffic
- probability value
- neural network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a travel time prediction method and a travel time prediction device. The method comprises the following steps: acquiring historical traffic data sets of N batches of a target road section, wherein the historical traffic data sets of each batch comprise recorded historical traffic data of a preset time period, and the historical traffic data at least comprise: average historical travel time; taking the historical passing data sets of N batches as input of a convolutional neural network, and obtaining at least one probability value set through the convolutional neural network, wherein the number of probability values in the probability value set is N; for a set of probability values, each probability value in the set of probability values is multiplied by its corresponding N average historical travel times in the historical traffic data and the sum of the products is determined as the predicted travel time. By adopting the technical scheme provided by the invention, the travel time of the road section can be accurately predicted, so that the accuracy of the ETA of the navigation route is ensured.
Description
Technical Field
The invention relates to the technical field of data mining, in particular to a travel time prediction method and device.
Background
Navigation is a core function of map navigation applications. Typically, a map navigation application provides multiple navigation routes from the same start point to the same end point for selection by a user, and the predicted Arrival time (ETA) is one of the parameters of great interest when the user selects a navigation route. The accuracy of ETA prediction of a navigation route is critical to accurately predicting the travel time of the navigation route, but since the ETA for a user to select the navigation route must be determined before the user travels and the traffic condition of the road affecting the accuracy of the travel time prediction changes in real time, how to accurately predict the travel time of the navigation route before the user does not travel is a problem that needs to be solved and optimized by those skilled in the art.
Disclosure of Invention
The invention aims to provide a technical scheme capable of accurately predicting travel time.
In order to achieve the above objective, an embodiment of the present invention provides a method for predicting travel time, including the following steps:
Acquiring historical traffic data sets of N batches of a target road section, wherein the historical traffic data sets of each batch comprise recorded historical traffic data of a preset time period, and the historical traffic data at least comprise: average historical travel time;
Taking the historical passing data sets of N batches as input of a convolutional neural network, and obtaining at least one probability value set through the convolutional neural network, wherein the number of probability values in the probability value set is N;
for a set of probability values, each probability value in the set of probability values is multiplied by its corresponding N average historical travel times in the historical traffic data and the sum of the products is determined as the predicted travel time.
The embodiment of the invention also provides a device for predicting the travel time, which comprises the following modules:
the system comprises a sample determining module, a target road section processing module and a data processing module, wherein the sample determining module is used for acquiring N batches of historical traffic data sets of the target road section, each batch of historical traffic data sets comprises recorded historical traffic data of a preset time period, and the historical traffic data at least comprises: average historical travel time;
The sample learning module is used for taking the historical passing data sets of N batches as input of a convolutional neural network, and obtaining at least one probability value set through the convolutional neural network, wherein the number of probability values in the probability value set is N;
A prediction module for multiplying each probability value in a probability value group with its corresponding N average historical travel times in the historical traffic data and determining the sum of the products as a predicted travel time for the probability value group.
The embodiment of the invention also provides electronic equipment, which comprises:
a storage device;
One or more processors;
Wherein the storage device is configured to store one or more programs that, when executed by the one or more processors, cause the one or more processors to implement a method of predicting travel time as described above.
The embodiment of the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed, runs a method of predicting travel time as described above.
Compared with the prior art, the technical scheme of the invention can predict the travel time by adopting the historical passing data recorded in the past, a probability value group is obtained by using the convolutional neural network in the prediction process, the probability value in the probability value group is used as a weight to obtain a prediction result, and the influence of abnormal data on the prediction result is reduced, so that the predicted travel time is more accurate.
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 required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a travel time prediction method according to an embodiment of the present invention.
Fig. 2 is a diagram of three input channels used in a Convolutional Neural Network (CNN) model.
FIG. 3 is a schematic diagram showing the comparison of the effect of the method according to the embodiment of the present invention with the conventional historical average method.
Detailed Description
In order to facilitate an understanding and a complete description of the technical solutions of the present invention by a person skilled in the art, reference is made to the accompanying drawings, it being evident that the embodiments described are only some, but not all, of the embodiments of the present invention. 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.
Example 1
Referring to the flowchart of fig. 1, a method for predicting travel time according to an embodiment of the present invention includes the following steps:
Step S10, acquiring N batches of historical traffic data sets of the target road section, where each batch of historical traffic data set includes recorded historical traffic data of a preset time period, and the historical traffic data at least includes: average historical travel time.
In the embodiment of the present invention, N is a positive integer, the preset time period may be preset M days in one embodiment, and the value range of M may be an integer less than or equal to 7 and greater than or equal to 1. Specific values of N and M can be set by those skilled in the art according to actual needs. For example, a set of 12 batches of historical traffic data for the target road segment is obtained, each set includes recorded historical traffic data for 7 days (i.e., N is 12 and M is 7), and the technical solution provided by the present invention is only illustrated for clarity, and should not be considered as any limitation of the present invention. It should be noted that, in daily life, each day is named from monday to sunday, so when n=12 and m is 7, the foregoing example may also be described as acquiring a history traffic data set of 12 weeks of the target road section, and in order to make the prediction result more accurate, the history traffic data set of the last 12 weeks of the target road section may be acquired in specific implementation. As another example, 10 batches of historical traffic data sets of the target road section are obtained, and each batch of historical traffic data sets comprises recorded historical traffic data for 5 days, which can be monday to friday or 5 days arbitrarily selected, so long as the selection criteria of each batch are consistent.
In another preferred embodiment of the invention, the historical traffic data may also include a standard deviation of historical traffic flow and/or average historical travel time.
Further, based on different predicted demands, for example, the travel time of the target link is predicted by day or the travel time of the target link is predicted at different times per day, the predicted demands need to be considered for recording when recording the historical traffic data. When the travel time of the target road section needs to be predicted according to different times per day, for example, the travel time is predicted every X minutes (for example, 60 minutes, 30 minutes, 10 minutes, etc.), the historical traffic data of each day of the target road section is recorded, and the historical traffic data and the corresponding recording time are recorded every X minutes. That is, the history traffic data of each batch is the history traffic data recorded every day at a preset time interval and the corresponding recording time according to a preset M days. The preset time interval can be set arbitrarily according to actual needs.
And S20, taking the historical passing data sets of N batches as input of a convolutional neural network, and obtaining at least one probability value set through the convolutional neural network, wherein the number of probability values in the probability value set is N.
The embodiment of the invention adopts a Convolutional Neural Network (CNN). CNN is a classical pattern recognition algorithm, and is different from the traditional artificial neural network in that CNN uses convolution to replace matrix multiplication in the traditional neural network, and is aided with the principle of local visual field in human vision, so that CNN becomes the first learning algorithm for actually and successfully training a multi-layer network structure, and is generally used for image recognition. The invention refers to the application of CNN in image recognition, the obtained historical traffic data of N batches of target road sections are treated as image data, and the historical average travel time, the historical traffic flow and the variance of the historical average travel time which are included in the historical traffic data are treated as data of three channels of one pixel point of an image. Specifically, the historical traffic data is used as input of a convolutional neural network, characteristic extraction is carried out through convolutional layer, nonlinear activation layer and pooling (Pooling) operation of the convolutional neural network, and at least one probability value group is output through a full connection layer.
Continuing the previous example, N is 12, m is 7, and each day records historical traffic data every 30 minutes, then the historical traffic data sets of N batches are input into the convolutional neural network as follows:
Inputting historical traffic data of 8 am on monday into a convolutional neural network to obtain 12 weights of 8 am on monday; the historical traffic data of 8:30 of Monday am is input into a convolutional neural network to obtain 8 of Monday am: a weight of 12 of 30, and so on until the last historical traffic data recorded on sunday has been processed. In the invention, N average historical travel times, N standard deviations of the average historical travel times and N historical vehicle flows corresponding to the same recording time on the same day in N batches of historical traffic data sets are used as one group of input of a convolutional neural network, so that a corresponding probability value group is obtained.
Step S30, for a probability value group, multiplying each probability value in the probability value group with its corresponding N average historical travel times in the historical traffic data and determining the sum of the products as the predicted travel time.
Continuing the previous example, multiplying and summing the 12 probability values of 8 am on monday and the 12 average historical travel times of 8 am on monday respectively to obtain a prediction result of the travel time of 8 am on monday.
In essence, the historical average method and the exponential smoothing method are specific examples of weighted average, so that the coupled model has more complete expression capability and can completely cover the traditional prediction methods, and the influence surface is improved from 10% to 100%.
Fig. 3 shows the result of the method of the present invention compared to the method of the historical average. Referring to fig. 3 (a), it can be seen that an outlier appears in the average travel time in the fifth week, and the weight given to the fifth week by the prediction model of the present invention is approximately 0, so that the outlier is accurately filtered; as can be seen from fig. 3 (b), when the average travel time for the 12 week feature interval is relatively average, the predictive model of the present invention will tend to assign higher weights to the last few weeks, consistent with our intuitive experience; as can be seen from fig. 3 (c), since the average travel time in the characteristic interval of the first weeks is shorter, the continuous congestion occurs in the last weeks, the historical average SP is obviously smaller, and the weight assigned to the first weeks by the prediction model of the present invention is approaching 0, so that the calculated SP is more consistent with expectations; fig. 3 (d) is similar to fig. 3 (c), except that the historical average SP is larger.
In addition, the vehicle travel time is only one application scene of the invention, and the invention can also analyze the business district passenger flow. Therefore, qualitatively, the invention can be used for processing any statistical data with extremely strong or weak correlation between data from the time sequence. The invention is a preferred solution if the correlation between the data is weak from the time dimension.
Example two
The second embodiment of the invention provides a travel time prediction device, which is characterized by comprising the following modules:
the system comprises a sample determining module, a target road section processing module and a data processing module, wherein the sample determining module is used for acquiring N batches of historical traffic data sets of the target road section, each batch of historical traffic data sets comprises recorded historical traffic data of a preset time period, and the historical traffic data at least comprises: average historical travel time;
The sample learning module is used for taking the historical passing data sets of N batches as input of a convolutional neural network, and obtaining at least one probability value set through the convolutional neural network, wherein the number of probability values in the probability value set is N;
A prediction module for multiplying each probability value in a probability value group with its corresponding N average historical travel times in the historical traffic data and determining the sum of the products as a predicted travel time for the probability value group.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described apparatus, modules and units may refer to corresponding procedures of the foregoing method embodiments, and are not repeated herein.
The embodiment of the invention also discloses an electronic device, which comprises a storage device and one or more processors, wherein the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the method as in the embodiment.
The embodiment of the invention also discloses a computer readable storage medium, on which a computer program is stored, which when executed, implements the method as in the first embodiment.
According to the technical scheme disclosed by the invention, the thought of an attention mechanism (attention) is consulted, a method of combining pattern recognition and weighted average is adopted, and the weighted probability of 12 average points of history in input information is predicted, so that future values are directly predicted, the prediction model provided by the invention has stronger expression capability and interpretability, and meanwhile, the problems that the influence surface is insufficient and abnormal points cannot be automatically recognized due to the simple use of the pattern recognition model can be overcome.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods, apparatus and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart and block diagrams may represent a module, segment, or portion of code, which comprises one or more computer-executable instructions for implementing the logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. It will also be noted that each block or combination of blocks in the block diagrams and flowchart illustrations, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments, provided to enable any person skilled in the art to make or use the present invention, is provided for illustration only and not for limitation. Other variations or modifications of the various aspects of the invention will be apparent to those of skill in the art, and are within the scope of the invention.
Claims (13)
1. A method for predicting travel time, comprising the steps of:
Acquiring historical traffic data sets of N batches of a target road section, wherein the historical traffic data sets of each batch comprise recorded historical traffic data of a preset time period, and the historical traffic data at least comprise: average historical travel time;
Taking the historical passing data sets of N batches as input of a convolutional neural network, and obtaining at least one probability value set through the convolutional neural network, wherein the number of probability values in the probability value set is N;
for a set of probability values, each probability value in the set of probability values is multiplied by its corresponding N average historical travel times in the historical traffic data and the sum of the products is determined as the predicted travel time.
2. The method according to claim 1, wherein the obtaining at least one probability value set by using the N batches of historical traffic data sets as inputs to a convolutional neural network, comprises:
and taking the N batches of historical passing data sets as input of the convolutional neural network, extracting features through a convolutional layer, a nonlinear activation layer and pooling operation of the convolutional neural network, and outputting at least one probability value set through a full connection layer of the convolutional neural network.
3. The method of claim 1, wherein the historical traffic data further comprises a standard deviation of average historical travel time and/or historical traffic flow.
4. A method according to claim 3, characterized in that N average historical travel times, standard deviations of N average historical travel times and N historical traffic flows corresponding to the same recording time on the same day in the N batches of historical traffic data sets are taken as a set of inputs of a convolutional neural network, a corresponding set of probability value sets is obtained, each probability value in the probability value sets is multiplied by N average historical travel times, and the sum of the products is determined as the predicted travel time of the target road section on the same recording time on the same day.
5. The method according to any one of claims 1 to 4, wherein the predetermined period of time is a predetermined period of M days, M being a variable parameter ranging from an integer of 7 or less to 1 or more;
the historical traffic data set of each batch comprises recorded historical traffic data of a preset time period, and specifically comprises the following steps: the historical traffic data set for each batch includes recorded M days of historical traffic data.
6. The method according to claim 5, characterized in that the method comprises:
Recording historical traffic data of the target road section and corresponding recording time in each day according to a preset time interval;
the historical traffic data set of each batch comprises recorded historical traffic data of a preset time period for road conditions, and specifically comprises the following steps:
the historical traffic data of each batch is recorded according to preset time intervals every day according to preset M days and corresponding recording time.
7. A travel time prediction apparatus, comprising:
the system comprises a sample determining module, a target road section processing module and a data processing module, wherein the sample determining module is used for acquiring N batches of historical traffic data sets of the target road section, each batch of historical traffic data sets comprises recorded historical traffic data of a preset time period, and the historical traffic data at least comprises: average historical travel time;
The sample learning module is used for taking the historical passing data sets of N batches as input of a convolutional neural network, and obtaining at least one probability value set through the convolutional neural network, wherein the number of probability values in the probability value set is N;
A prediction module for multiplying each probability value in a probability value group with its corresponding N average historical travel times in the historical traffic data and determining the sum of the products as a predicted travel time for the probability value group.
8. The apparatus of claim 7, wherein the sample learning module is specifically configured to:
and taking the N batches of historical passing data sets as input of the convolutional neural network, extracting features through a convolutional layer, a nonlinear activation layer and pooling operation of the convolutional neural network, and outputting at least one probability value set through a full connection layer of the convolutional neural network.
9. The apparatus of claim 7, wherein the historical traffic data further comprises a standard deviation of average historical travel times and/or historical traffic flow;
the sample learning module is specifically configured to: and taking N average historical travel times, N standard deviations of the average historical travel times and N historical vehicle flows corresponding to the same recording time on the same day in the N batches of historical traffic data sets as one group of inputs of a convolutional neural network to obtain a corresponding probability value set, multiplying each probability value in the probability value set by the N average historical travel times, and determining the sum of the products as the predicted travel time of the target road section on the same recording time on the same day.
10. The device according to any one of claims 7 to 9, wherein the predetermined period of time is a predetermined period of M days, M being a variable parameter ranging from an integer of 7 or less to 1 or more;
the historical traffic data set of each batch comprises recorded historical traffic data of a preset time period, and specifically comprises the following steps: the historical traffic data set for each batch includes recorded M days of historical traffic data.
11. The apparatus as recited in claim 10, further comprising:
The recording module is used for recording the historical traffic data of the target road section and the corresponding recording time according to a preset time interval every day;
the historical traffic data set of each batch comprises recorded historical traffic data of a preset time period for road conditions, and specifically comprises the following steps:
the historical traffic data of each batch is recorded according to preset time intervals every day according to preset M days and corresponding recording time.
12. An electronic device, the device comprising:
a storage device;
One or more processors;
Wherein the storage means is for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement the method of predicting travel time of any one of claims 1-6.
13. A computer readable storage medium having stored thereon a computer program which, when executed, runs the method of predicting travel time according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910356006.5A CN111860920B (en) | 2019-04-29 | 2019-04-29 | Travel time prediction method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910356006.5A CN111860920B (en) | 2019-04-29 | 2019-04-29 | Travel time prediction method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111860920A CN111860920A (en) | 2020-10-30 |
| CN111860920B true CN111860920B (en) | 2024-10-01 |
Family
ID=72966146
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910356006.5A Active CN111860920B (en) | 2019-04-29 | 2019-04-29 | Travel time prediction method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111860920B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114822061B (en) * | 2022-03-30 | 2023-11-28 | 阿里巴巴（中国）有限公司 | Arrival time estimation method, arrival time estimation device, electronic equipment and computer program product |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101320442A (en) * | 2007-06-05 | 2008-12-10 | 上海博拉软件有限公司 | Method for implementing real-time cargo tracing and monitoring based on logistics management platform |
| CN103903430A (en) * | 2014-04-14 | 2014-07-02 | 东南大学 | Dynamic fusion type travel time predicting method with multi-source and isomorphic data adopted |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107085943B (en) * | 2015-12-23 | 2020-06-30 | 青岛海信网络科技股份有限公司 | Short-term prediction method and system for road travel time |
-
2019
- 2019-04-29 CN CN201910356006.5A patent/CN111860920B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101320442A (en) * | 2007-06-05 | 2008-12-10 | 上海博拉软件有限公司 | Method for implementing real-time cargo tracing and monitoring based on logistics management platform |
| CN103903430A (en) * | 2014-04-14 | 2014-07-02 | 东南大学 | Dynamic fusion type travel time predicting method with multi-source and isomorphic data adopted |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111860920A (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rangapuram et al. | Deep state space models for time series forecasting | |
| CN112419710B (en) | Traffic congestion data prediction method, traffic congestion data prediction device, computer equipment and storage medium | |
| US8160981B2 (en) | Event-based anticipation systems, methods and computer program products for associative memories wherein times of future events occurring are predicted | |
| CN112242060B (en) | Traffic flow prediction method and apparatus, computer device, and readable storage medium | |
| CN111429006A (en) | Financial risk index prediction model construction method and device and risk situation prediction method and device | |
| CN108898831B (en) | Road section condition evaluation method and system based on road high-definition checkpoint data | |
| CN103747523A (en) | User position predicating system and method based on wireless network | |
| KR20200052806A (en) | Operating method of deep learning based climate change prediction system | |
| Das et al. | A probabilistic approach for weather forecast using spatio-temporal inter-relationships among climate variables | |
| Wirthmüller et al. | Predicting the time until a vehicle changes the lane using LSTM-based recurrent neural networks | |
| CN110263733A (en) | Image processing method, nomination appraisal procedure and relevant apparatus | |
| CN117474365B (en) | Intelligent police service method and system based on artificial intelligence technology | |
| CN111798482A (en) | Target tracking method and device | |
| WO2022165602A1 (en) | Method, system and computer readable medium for probabilistic spatiotemporal forecasting | |
| CN111860920B (en) | Travel time prediction method and device | |
| CN108877224A (en) | A kind of Short-time Traffic Flow Forecasting Methods carrying out Estimating Confidence Interval | |
| CN114399901B (en) | Method and equipment for controlling traffic system | |
| CN117875521B (en) | Real-time railway passenger flow prediction method, system, medium and electronic equipment | |
| CN119226948A (en) | Data prediction method, device, electronic device and storage medium | |
| CN106228029B (en) | Crowdsourcing-based quantitative problem solving method and device | |
| CN112116167A (en) | Data processing method, data processing apparatus, storage medium, and electronic device | |
| Kuhail et al. | Parking availability forecasting model | |
| Wu et al. | Traffic flow prediction using optimal autoregressive moving average with exogenous input-based predictors | |
| JP6668227B2 (en) | Spatio-temporal prediction model learning device, spatio-temporal prediction device, method, and program | |
| CN117081942A (en) | Network traffic prediction method, device, equipment and medium |
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 |