CN116543560A - Intelligent road condition prediction system and method based on deep learning - Google Patents
Intelligent road condition prediction system and method based on deep learning Download PDFInfo
- Publication number
- CN116543560A CN116543560A CN202310813105.8A CN202310813105A CN116543560A CN 116543560 A CN116543560 A CN 116543560A CN 202310813105 A CN202310813105 A CN 202310813105A CN 116543560 A CN116543560 A CN 116543560A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- prediction
- road condition
- model
- 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
Links
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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention relates to the field of road condition information, and discloses an intelligent road condition prediction system and method based on deep learning, wherein the system comprises the following steps: the central control module is used for editing and transmitting various control instructions and is used as a core central control end; the road condition acquisition module is used for acquiring traffic flow, speed, congestion degree, weather data and abnormal event data of a road section to be predicted; the preprocessing module is used for filtering the collected data, removing useless information and converting an adaptive format; the prediction model is trained by acquiring data such as traffic flow, speed and blocking degree, the data is acquired in a sectional mode, traffic data of different areas are comprehensively analyzed, further, the driving route and time are reasonably planned, the traffic efficiency is improved, the road congestion condition is reduced, more road condition rules are found, self-upgrading is continuously carried out, and road traffic facilities and public traffic states are improved while road network design is optimized.
Description
Technical Field
The invention relates to the technical field of road condition information, in particular to an intelligent road condition prediction system and method based on deep learning.
Background
The existing road condition prediction system and method have defects, such as:
1. the acquisition and statistics of various traffic data are relatively undefined, so that the training degree of a finally built prediction model is not high, the prediction result has quite limited, the collection process is relatively lengthy, the acquired data are easy to repeat and leak, and the analysis process is delayed;
2. in the process of data outflow and inflow, problematic data are difficult to find in time and correct, so that the problem data pollute the prediction model, and the prediction capability of the model is difficult to evaluate effectively.
Disclosure of Invention
Aiming at the defects existing in the prior art, the invention provides an intelligent road condition prediction system and method based on deep learning, which can effectively solve the problems in the prior art.
In order to achieve the above object, the present invention is realized by the following technical scheme,
the invention discloses an intelligent road condition prediction system based on deep learning, which comprises:
the central control module is used for editing and transmitting various control instructions and is used as a core central control end;
the road condition acquisition module is used for acquiring traffic flow, speed, congestion degree, weather data and abnormal event data of a road section to be predicted;
the preprocessing module is used for filtering the collected data, removing useless information and converting an adaptive format;
the data dividing module is used for dividing road sections to be predicted, and acquiring a plurality of road section intervals which are used as original data for model establishment and prediction;
the model unit is used as a prediction model and executes the prediction operation of the data after receiving the transferred data;
the model unit is provided with subordinate submodules, which comprise a target extraction module, a training module, a simulation prediction module and an output evaluation module, wherein:
the target extraction module is used for determining final input data and acquiring time states, weather states, traffic states and abnormal event parameters of each section in the current prediction period of the section to be predicted;
the training module is used for acquiring input data to form a sample pool, performing machine calculation and learning by key features to form an initial prediction model, and is continuously perfected;
the simulation prediction module is used for inputting new data into the sample pool in a staged manner, running an initial prediction model, predicting road conditions in a preset time in the future, outputting a prediction result, and automatically grabbing an actual observation value for feedback after the prediction is finished;
the output evaluation module is used for analyzing the difference between the actual observed value and the analog predicted value and evaluating the prediction accuracy;
the model analysis module is used for carrying out comprehensive statistics and analysis on the obtained original data and the predicted data, obtaining a predicted change index of a predicted model, carrying out real-time safety detection and monitoring, and carrying out early warning on the abnormal condition of the predicted change index;
the data storage module is used for storing all acquired data, trained model data and predicted data and uploading the data to the cloud end in real time;
and the correction unit is used for correcting and correcting the predicted result in real time and outputting the corrected predicted result.
Further, a user terminal is deployed on the central control module, an identity registration and login interface is provided, and after user identity information is verified, a prediction interaction interface is provided for a user, wherein the prediction interaction interface comprises: inputting query conditions, viewing predicted results and feeding back opinion inputs.
Furthermore, the threshold unit of the road section interval divided by the data dividing module is a route distance, and the setting process carries out equal-section or custom division according to the route length.
Furthermore, the central control module is in interactive connection with the road condition acquisition module through a wireless network, the road condition acquisition module is in interactive connection with the preprocessing module through the wireless network, the preprocessing module is in interactive connection with the data dividing module through the wireless network, the data dividing module is in interactive connection with the model unit and the correction unit through the wireless network, the model unit is in interactive connection with the model analysis module through the wireless network, the model analysis module is in interactive connection with the data storage module through the wireless network, and the data storage module is in interactive connection with the central control module through the wireless network.
Still further, the correction unit is provided with a subordinate sub-module, which comprises a real-time update module, a real-time inspection module and a correction module, wherein:
the real-time updating module is used for interfacing with a data source in the network in real time, receiving the latest road condition data in real time, integrating the latest road condition data with the existing data, and finishing updating;
the real-time inspection module is used for detecting the outflow and inflow states of the data in real time and judging whether the data state is abnormal or not;
the correction module is used for modifying or clearing the related parameters according to the updated data and the error report;
the real-time updating module and the real-time inspection module are in interactive connection with the correction module through a wireless network.
Furthermore, if the real-time inspection module judges that the data state is abnormal, the transmission of the upstream and the downstream is stopped, the feedback instruction is retransmitted to the transmitting node, the existing buffer is cleared, an error report is sent to the model, and if the data state is judged to be abnormal, the real-time inspection module continuously operates according to the preset setting.
Furthermore, the target extraction module is in interactive connection with the training module through a wireless network, the training module is in interactive connection with the simulation prediction module through the wireless network, and the simulation prediction module is in interactive connection with the output evaluation module through the wireless network.
An intelligent road condition prediction method based on deep learning comprises the following steps:
step 1: obtaining road data, carrying out format conversion, and then carrying out paragraph division of areas aiming at the converted data, wherein the division mode is divided by manual self-definition or programs according to attribute threshold values;
step 2: establishing a road condition prediction model, receiving the divided regional data, acquiring target characteristic data as a training sample, and putting the model into training;
step 3: when the model runs, capturing road condition information updated in real time, serving as corresponding change, marking the running abnormality, and reminding until correction actions are started and completed;
step 4: inputting actual road condition data to be predicted into a prediction model, running the prediction model, carrying out comprehensive evaluation analysis, and outputting an evaluation result;
step 5: and analyzing the performance of the prediction model according to the evaluation result, outputting a working report, and carrying out routine maintenance, upgrading and updating on each parameter of the system and the prediction model according to the working report.
Further, the performance of the prediction model in the step 5 is evaluated by mean absolute difference, and the calculation formula is as follows:
；
in the method, in the process of the invention,representing the predicted value; />Representing a true value; n represents the number of data; w represents the average absolute difference.
Still further, the parameters of the prediction model in step 5 include: an operating parameter, a receiving parameter and an output parameter.
Compared with the known public technology, the technical scheme provided by the invention has the following beneficial effects:
according to the invention, the prediction model is trained by acquiring data such as traffic flow, speed and blocking degree, the data is acquired in a sectional mode, the traffic data of different areas are comprehensively analyzed, the driving route and time are reasonably planned, the traffic efficiency is improved, the road congestion condition is reduced, more road condition rules are found, self-upgrading is continuously carried out, the road network design is optimized, meanwhile, the road traffic facilities are improved, and the public traffic state is improved.
According to the method, the query data in the inputted road condition data are identified and corrected in real time, so that risk data are reasonably avoided, a user can take corresponding measures in time, the safety of a predicted route is further ensured, and the safe trip is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is evident that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic diagram of a deep learning-based intelligent road condition prediction system;
FIG. 2 is a schematic flow chart of an intelligent road condition prediction method based on deep learning;
reference numerals in the figure respectively represent 1, a central control module; 2. the road condition acquisition module; 3. a preprocessing module; 4. a data dividing module; 5. a model unit; 51. a target extraction module; 52. a training module; 53. a simulation prediction module; 54. an output evaluation module; 6. a model analysis module; 7. a data storage module; 8. a correction unit; 81. a real-time updating module; 82. a real-time inspection module; 83. and a correction module.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the 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.
The invention is further described below with reference to examples.
Example 1: an intelligent road condition prediction system based on deep learning in this embodiment, as shown in fig. 1, includes:
the central control module 1 is used for editing and transmitting various control instructions and is used as a core central control end;
the road condition acquisition module 2 is used for acquiring traffic flow, speed, congestion degree, weather data and abnormal event data of a road section to be predicted;
the preprocessing module 3 is used for filtering the collected data, removing useless information and converting an adaptive format;
the data dividing module 4 is used for dividing road sections to be predicted to obtain a plurality of road section intervals which are used as original data for model establishment and prediction;
a model unit 5 that performs a prediction operation of the data after receiving the transferred data as a prediction model;
the model unit 5 is provided with subordinate submodules, which comprise a target extraction module 51, a training module 52, a simulation prediction module 53 and an output evaluation module 54, wherein:
the target extraction module 51 is configured to determine final input data, and obtain time status, weather status, traffic status and abnormal event parameters of each section in a current prediction period of the road section to be predicted;
the training module 52 is configured to acquire input data, form a sample pool, perform machine calculation and learning with key features, and form an initial prediction model, which is not always perfect;
the simulation prediction module 53 is configured to periodically input new data into the sample pool, run an initial prediction model, predict road conditions in a preset time in the future, output a prediction result, and automatically capture an actual observation value for feedback after the prediction is completed;
an output evaluation module 54 for analyzing the difference between the actual observed value and the simulated predicted value, and evaluating the prediction accuracy;
the model analysis module 6 is used for carrying out comprehensive statistics and analysis on the obtained original data and the predicted data, obtaining a predicted change index of a predicted model, carrying out real-time safety detection and monitoring, and carrying out early warning on the abnormal condition of the predicted change index;
the data storage module 7 is used for storing all acquired data, trained model data and predicted data and uploading the data at the cloud end in real time;
and a correction unit 8 for correcting and correcting the prediction result in real time and outputting the corrected prediction result.
The central control module 1 is provided with a user terminal and provides an identity registration and login interface, and after verifying user identity information, a prediction interaction interface is provided for a user, wherein the prediction interaction interface comprises: inputting query conditions, viewing predicted results and feeding back opinion inputs.
The threshold unit of the road section interval divided by the data dividing module 4 is a route distance, and the setting process carries out equal-section or custom division according to the route length.
As shown in fig. 1, the central control module 1 is interactively connected with the road condition obtaining module 2 through a wireless network, the road condition obtaining module 2 is interactively connected with the preprocessing module 3 through a wireless network, the preprocessing module 3 is interactively connected with the data dividing module 4 through a wireless network, the data dividing module 4 is interactively connected with the model unit 5 and the correction unit 8 through a wireless network, the model unit 5 is interactively connected with the model analysis module 6 through a wireless network, the model analysis module 6 is interactively connected with the data storage module 7 through a wireless network, the data storage module 7 is interactively connected with the central control module 1 through a wireless network, the target extracting module 51 is interactively connected with the training module 52 through a wireless network, the training module 52 is interactively connected with the simulation prediction module 53 through a wireless network, and the simulation prediction module 53 is interactively connected with the output evaluation module 54 through a wireless network.
In the embodiment, the central control module 1 is used for controlling the overall situation, the road condition acquisition module 2 is used for acquiring a large amount of road condition data, weather data and event data in a training stage, the preprocessing module 3 is used for carrying out format conversion on the original data, the data dividing module 4 is used for carrying out segmentation processing, the model unit 5 is started, the target extraction module 51 is used for extracting key targets in the original data, the training module 52 is used for constructing a training sample pool, the simulation prediction module 53 is used for constructing a prediction model, the simulation prediction model is started, the output evaluation module 54 is used for outputting road condition evaluation results along with continuous input of the data, the model analysis module 6 is used for evaluating the model performance, the data storage module 7 is used for storing all acquired and analyzed data, the correction unit 8 is started in an operation stage, the latest variation content of the acquired data is updated in real time through the real-time updating module 81, and the real-time inspection module 82 is used for detecting and correcting problem parameters in the analysis process in real time through the correction module 83.
Example 2: the embodiment also provides an intelligent road condition prediction method based on deep learning, as shown in fig. 2, comprising the following steps:
step 1: obtaining road data, carrying out format conversion, and then carrying out paragraph division of areas aiming at the converted data, wherein the division mode is divided by manual self-definition or programs according to attribute threshold values;
step 2: establishing a road condition prediction model, receiving the divided regional data, acquiring target characteristic data as a training sample, and putting the model into training;
step 3: when the model runs, capturing road condition information updated in real time, serving as corresponding change, marking the running abnormality, and reminding until correction actions are started and completed;
step 4: inputting actual road condition data to be predicted into a prediction model, running the prediction model, carrying out comprehensive evaluation analysis, and outputting an evaluation result;
step 5: and analyzing the performance of the prediction model according to the evaluation result, outputting a working report, and carrying out routine maintenance, upgrading and updating on each parameter of the system and the prediction model according to the working report.
The performance of the prediction model in the step 5 is evaluated through average absolute difference, and the calculation formula is as follows:
；
in the method, in the process of the invention,representing the predicted value; />Representing a true value; n represents the number of data; w represents the average absolute difference.
The parameters of the prediction model in the step 5 include: an operating parameter, a receiving parameter and an output parameter.
When the method is specifically implemented, the prediction model is trained by acquiring data such as traffic flow, speed and blocking degree, the data is acquired in a sectional mode, traffic data of different areas are comprehensively analyzed, driving routes and time are reasonably planned, traffic efficiency is improved, road congestion is reduced, more road condition rules are found, self-upgrading is continuously carried out, road network design is optimized, road traffic facilities are improved, public traffic states are improved, query data in inputted road condition data are recognized and corrected in real time, risk data are reasonably avoided, a user can take corresponding measures in time, the safety of the predicted routes is further guaranteed, and safe traveling is guaranteed.
Example 3: in this embodiment, as shown in fig. 1, the correction unit 8 is configured with subordinate sub-modules, including a real-time update module 81, a real-time inspection module 82, and a correction module 83, where:
the real-time updating module 81 is configured to interface with a data source in the network in real time, receive the latest road condition data in real time, integrate the latest road condition data with the existing data, and complete updating;
the real-time inspection module 82 is configured to detect the outflow and inflow states of data in real time, and determine whether the data state is abnormal;
a correction module 83 for modifying or clearing the parameters according to the updated data and the error report;
the real-time updating module 81 and the real-time inspection module 82 are interactively connected with the correction module 83 through a wireless network.
If the data status is determined to be abnormal, the real-time inspection module 82 stops the upstream and downstream transmission, feeds back the instruction to the sending node for retransmission, clears the existing buffer, sends an error report to the model, and if no abnormality is determined, continues to operate according to the preset setting.
In summary, the central control module 1 controls the overall situation, the road condition acquisition module 2 acquires a large amount of road condition data, weather data and event data in a training stage, the preprocessing module 3 performs format conversion on the original data, the data dividing module 4 performs segmentation processing, the model unit 5 is started, the target extraction module 51 extracts key targets in the original data, the training module 52 builds a training sample pool, the simulation prediction module 53 builds a prediction model, the simulation prediction module 53 starts training, the output evaluation module 54 outputs road condition evaluation results along with continuous input of the data, the model analysis module 6 evaluates the model performance, the data storage module 7 stores all acquired and analyzed data, the correction unit 8 is started in an operation stage, the real-time updating module 81 updates the latest fluctuation content of the acquired data in real time, the real-time inspection module 82 detects problem parameters in the analysis process in real time, and the correction module 83 performs correction;
the prediction model is trained by acquiring data such as traffic flow, speed and blocking degree, the data are acquired in a sectional mode, traffic data of different areas are comprehensively analyzed, then, driving routes and time are reasonably planned, traffic efficiency is improved, road congestion is reduced, more road condition rules are found, self-upgrading is continuously carried out, road network design is optimized, road traffic facilities are improved, public traffic states are improved, query data in the inputted road condition data are recognized and corrected in real time, risk data are reasonably avoided, a user can take corresponding measures in time, the safety of the predicted routes is further guaranteed, and safe traveling is guaranteed.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; while the invention has been described in detail with reference to the foregoing embodiments, it will be appreciated by those skilled in the art that variations may be made in the techniques described in the foregoing embodiments, or equivalents may be substituted for elements thereof; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An intelligent road condition prediction system based on deep learning is characterized by comprising:
the central control module (1) is used for editing and transmitting various control instructions and is used as a core central control end;
the road condition acquisition module (2) is used for acquiring traffic flow, speed, congestion degree, weather data and abnormal event data of a road section to be predicted;
the preprocessing module (3) is used for filtering the collected data, removing useless information and converting an adaptive format;
the data dividing module (4) is used for dividing road sections to be predicted to obtain a plurality of road section intervals which are used as original data for model establishment and prediction;
a model unit (5) that performs a prediction operation of the data after receiving the transferred data as a prediction model;
the model unit (5) is provided with a subordinate sub-module, which comprises a target extraction module (51), a training module (52), a simulation prediction module (53) and an output evaluation module (54), wherein:
the target extraction module (51) is used for determining final input data and acquiring time states, weather states, traffic states and abnormal event parameters of each section in the current prediction period of the section to be predicted;
the training module (52) is used for acquiring input data to form a sample pool, performing machine calculation and learning by key features to form an initial prediction model, and continuously perfecting;
the simulation prediction module (53) is used for inputting new data into the sample pool in a staged manner, running an initial prediction model, predicting road conditions in a preset time in the future, outputting a prediction result, and automatically grabbing an actual observation value for feedback after the prediction is finished;
an output evaluation module (54) for analyzing the difference between the actual observed value and the simulated predicted value, and evaluating the prediction accuracy;
the model analysis module (6) is used for carrying out comprehensive statistics and analysis on the obtained original data and the predicted data, obtaining a predicted change index of a predicted model, carrying out real-time safety detection and monitoring, and carrying out early warning on the condition of abnormal predicted change index;
the data storage module (7) is used for storing all acquired data, trained model data and predicted data and uploading the data at the cloud end in real time;
and the correction unit (8) is used for correcting and correcting the prediction result in real time and outputting the corrected prediction result.
2. The intelligent road condition prediction system based on deep learning according to claim 1, wherein the central control module (1) is configured with a user terminal, provides an identity registration and login interface, and provides a prediction interaction interface for a user after verifying user identity information, the prediction interaction interface comprises: inputting query conditions, viewing predicted results and feeding back opinion inputs.
3. The intelligent road condition prediction system based on deep learning according to claim 1, wherein the threshold unit of the road section interval divided by the data dividing module (4) is a route distance, and the setting process performs equal-section or custom division according to the route length.
4. The intelligent road condition prediction system based on deep learning according to claim 1, wherein the central control module (1) is in interactive connection with the road condition acquisition module (2) through a wireless network, the road condition acquisition module (2) is in interactive connection with the preprocessing module (3) through the wireless network, the preprocessing module (3) is in interactive connection with the data dividing module (4) through the wireless network, the data dividing module (4) is in interactive connection with the model unit (5) and the correction unit (8) through the wireless network, the model unit (5) is in interactive connection with the model analysis module (6) through the wireless network, the model analysis module (6) is in interactive connection with the data storage module (7) through the wireless network, and the data storage module (7) is in interactive connection with the central control module (1) through the wireless network.
5. The intelligent road condition prediction system based on deep learning according to claim 1, wherein the correction unit (8) is provided with subordinate submodules, including a real-time update module (81), a real-time patrol module (82) and a correction module (83), wherein:
the real-time updating module (81) is used for interfacing with a data source in the network in real time, receiving the latest road condition data in real time, integrating the latest road condition data with the existing data, and finishing updating;
the real-time inspection module (82) is used for detecting the outflow and inflow states of the data in real time and judging whether the data state is abnormal or not;
a correction module (83) for modifying or clearing the parameters involved in dependence on the updated data and the error report;
the real-time updating module (81) and the real-time inspection module (82) are in interactive connection with the correction module (83) through a wireless network.
6. The intelligent road condition prediction system based on deep learning according to claim 5, wherein the real-time inspection module (82) suspends the upstream and downstream transmission if the data status is determined to be abnormal, feeds back the instruction to the transmitting node for retransmission, clears the existing buffer, sends an error report to the model, and continuously operates according to the predetermined setting if no abnormality is determined.
7. The intelligent road condition prediction system based on deep learning according to claim 1, wherein the target extraction module (51) is interactively connected with the training module (52) through a wireless network, the training module (52) is interactively connected with the simulation prediction module (53) through a wireless network, and the simulation prediction module (53) is interactively connected with the output evaluation module (54) through a wireless network.
8. An intelligent road condition prediction method based on deep learning, which is an implementation method of the intelligent road condition prediction system based on deep learning as set forth in any one of claims 1 to 7, and is characterized by comprising the following steps:
step 1: obtaining road data, carrying out format conversion, and then carrying out paragraph division of areas aiming at the converted data, wherein the division mode is divided by manual self-definition or programs according to attribute threshold values;
step 2: establishing a road condition prediction model, receiving the divided regional data, acquiring target characteristic data as a training sample, and putting the model into training;
step 3: when the model runs, capturing road condition information updated in real time, serving as corresponding change, marking the running abnormality, and reminding until correction actions are started and completed;
step 4: inputting actual road condition data to be predicted into a prediction model, running the prediction model, carrying out comprehensive evaluation analysis, and outputting an evaluation result;
step 5: and analyzing the performance of the prediction model according to the evaluation result, outputting a working report, and carrying out routine maintenance, upgrading and updating on each parameter of the system and the prediction model according to the working report.
9. The intelligent road condition prediction method based on deep learning according to claim 8, wherein the performance of the prediction model in step 5 is evaluated by mean absolute difference, and the calculation formula is as follows:
；
in the method, in the process of the invention,representing the predicted value; />Representing a true value; n represents the number of data; w represents the average absolute difference.
10. The intelligent road condition prediction method based on deep learning according to claim 8, wherein the parameters of the prediction model in step 5 include: an operating parameter, a receiving parameter and an output parameter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310813105.8A CN116543560B (en) | 2023-07-05 | 2023-07-05 | Intelligent road condition prediction system and method based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310813105.8A CN116543560B (en) | 2023-07-05 | 2023-07-05 | Intelligent road condition prediction system and method based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116543560A true CN116543560A (en) | 2023-08-04 |
| CN116543560B CN116543560B (en) | 2023-09-22 |
Family
ID=87445607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310813105.8A Active CN116543560B (en) | 2023-07-05 | 2023-07-05 | Intelligent road condition prediction system and method based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116543560B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117131581A (en) * | 2023-10-26 | 2023-11-28 | 乘木科技(珠海)有限公司 | Digital twin urban road construction system and method |
| CN117152961A (en) * | 2023-09-20 | 2023-12-01 | 深圳市孪生云计算技术有限公司 | Wisdom road condition monitoring display system based on data analysis |
| CN117633489A (en) * | 2023-12-13 | 2024-03-01 | 智车信安(苏州)信息安全科技有限公司 | AI-based vehicle safety analysis method and system |
| CN117912255A (en) * | 2024-03-19 | 2024-04-19 | 河北鹏鹄信息科技有限公司 | Real-time intelligent driving global data acquisition highway monitoring system and monitoring method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517492A (en) * | 2019-08-27 | 2019-11-29 | 中国科学院自动化研究所 | Based on the traffic route recommended method of parallel integrated study, system, device |
| CN110555018A (en) * | 2019-07-29 | 2019-12-10 | 浙江工业大学 | traffic flow completion and prediction method |
| CN111292534A (en) * | 2020-02-13 | 2020-06-16 | 北京工业大学 | Traffic state estimation method based on clustering and deep sequence learning |
| CN113327418A (en) * | 2021-05-31 | 2021-08-31 | 同济大学 | Expressway congestion risk grading real-time prediction method |
| CN114493038A (en) * | 2022-02-17 | 2022-05-13 | 四川省生态环境科学研究院 | Traffic flow estimation method for all-time all-road network |
| CN114638428A (en) * | 2022-03-28 | 2022-06-17 | 智己汽车科技有限公司 | Traffic road condition prediction method and device and vehicle |
| US20220414450A1 (en) * | 2021-06-28 | 2022-12-29 | Mitsubishi Electric Research Laboratories, Inc. | Distributed Multi-Task Machine Learning for Traffic Prediction |
| US11620901B1 (en) * | 2022-06-02 | 2023-04-04 | Iteris, Inc. | Short-term traffic speed prediction and forecasting using machine learning analysis of spatiotemporal traffic speed dependencies in probe and weather data |
-
2023
- 2023-07-05 CN CN202310813105.8A patent/CN116543560B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110555018A (en) * | 2019-07-29 | 2019-12-10 | 浙江工业大学 | traffic flow completion and prediction method |
| CN110517492A (en) * | 2019-08-27 | 2019-11-29 | 中国科学院自动化研究所 | Based on the traffic route recommended method of parallel integrated study, system, device |
| CN111292534A (en) * | 2020-02-13 | 2020-06-16 | 北京工业大学 | Traffic state estimation method based on clustering and deep sequence learning |
| CN113327418A (en) * | 2021-05-31 | 2021-08-31 | 同济大学 | Expressway congestion risk grading real-time prediction method |
| US20220414450A1 (en) * | 2021-06-28 | 2022-12-29 | Mitsubishi Electric Research Laboratories, Inc. | Distributed Multi-Task Machine Learning for Traffic Prediction |
| CN114493038A (en) * | 2022-02-17 | 2022-05-13 | 四川省生态环境科学研究院 | Traffic flow estimation method for all-time all-road network |
| CN114638428A (en) * | 2022-03-28 | 2022-06-17 | 智己汽车科技有限公司 | Traffic road condition prediction method and device and vehicle |
| US11620901B1 (en) * | 2022-06-02 | 2023-04-04 | Iteris, Inc. | Short-term traffic speed prediction and forecasting using machine learning analysis of spatiotemporal traffic speed dependencies in probe and weather data |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117152961A (en) * | 2023-09-20 | 2023-12-01 | 深圳市孪生云计算技术有限公司 | Wisdom road condition monitoring display system based on data analysis |
| CN117131581A (en) * | 2023-10-26 | 2023-11-28 | 乘木科技(珠海)有限公司 | Digital twin urban road construction system and method |
| CN117131581B (en) * | 2023-10-26 | 2024-02-13 | 乘木科技(珠海)有限公司 | Digital twin urban road construction system and method |
| CN117633489A (en) * | 2023-12-13 | 2024-03-01 | 智车信安(苏州)信息安全科技有限公司 | AI-based vehicle safety analysis method and system |
| CN117912255A (en) * | 2024-03-19 | 2024-04-19 | 河北鹏鹄信息科技有限公司 | Real-time intelligent driving global data acquisition highway monitoring system and monitoring method |
| CN117912255B (en) * | 2024-03-19 | 2024-05-10 | 河北鹏鹄信息科技有限公司 | Real-time intelligent driving global data acquisition highway monitoring system and monitoring method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116543560B (en) | 2023-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116543560B (en) | Intelligent road condition prediction system and method based on deep learning | |
| CN109215347B (en) | Traffic data quality control method based on crowdsourcing trajectory data | |
| CN116153078B (en) | Road safety assessment method and device based on millimeter wave radar and storage medium | |
| CN108776452B (en) | Special equipment field maintenance monitoring method and system | |
| CN109598930B (en) | Automatic detect overhead closed system | |
| CN113269042B (en) | Intelligent traffic management method and system based on driving vehicle violation identification | |
| CN116721550B (en) | Traffic management system based on grid computing | |
| CN116631186B (en) | Expressway traffic accident risk assessment method and system based on dangerous driving event data | |
| CN108681717B (en) | Quality detection method for urban traffic video detection equipment | |
| CN114814877A (en) | Tunnel data acquisition method, equipment and medium based on inspection robot | |
| CN116168356A (en) | Vehicle damage judging method based on computer vision | |
| CN117558127A (en) | Computing task intelligent system under 5g edge computing environment | |
| CN117591857A (en) | Motor detection method based on deep learning | |
| CN106780164B (en) | Efficient bridge structure damage identification system | |
| CN117575349A (en) | Urban data model-based traffic influence evaluation method and system | |
| CN110728768A (en) | Switch operation and maintenance method and system | |
| CN117252851B (en) | Standard quality detection management platform based on image detection and identification | |
| CN116821620A (en) | Data analysis method based on electric bicycle charging pile | |
| CN117291872A (en) | Unmanned aerial vehicle line inspection defect content identification system and method | |
| CN106128105A (en) | A kind of traffic intersection pedestrian behavior monitoring system | |
| CN115493642A (en) | Road environment detection system of intelligent networked automobile | |
| CN115631184A (en) | Power transmission line fault analysis method, device, equipment and storage medium based on decision tree | |
| CN114202726A (en) | Power transmission line scene target detection method based on self-supervision learning | |
| CN111932877A (en) | Road section traffic abnormal state identification method based on license plate data | |
| CN109885018A (en) | A kind of management method of the expert think tank system towards mental package equipment |
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 |