CN116703008B - Traffic volume prediction method, equipment and medium for newly built highway - Google Patents
Traffic volume prediction method, equipment and medium for newly built highway Download PDFInfo
- Publication number
- CN116703008B CN116703008B CN202310961919.6A CN202310961919A CN116703008B CN 116703008 B CN116703008 B CN 116703008B CN 202310961919 A CN202310961919 A CN 202310961919A CN 116703008 B CN116703008 B CN 116703008B
- Authority
- CN
- China
- Prior art keywords
- influence
- data
- traffic
- predicted
- road
- 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
- 238000000034 method Methods 0.000 title claims abstract description 46
- 239000011159 matrix material Substances 0.000 claims abstract description 64
- 238000013439 planning Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 238000003066 decision tree Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a traffic volume prediction method, equipment and medium for a newly built highway, and belongs to the technical field of traffic control systems. The method determines an influence set corresponding to each traffic cell based on a first position sequence of a planned newly-built road and a second position sequence of each traffic cell. Based on historical OD data corresponding to the influence set as input, carrying out OD prediction through a preset long-short-term memory network LSTM model to obtain predicted OD data. And determining a corresponding influence adjusting range according to the historical OD data and the predicted OD data corresponding to the influence set. Based on the influence set, the influence adjusting range and the historical OD data, a predicted OD matrix corresponding to the planned new road is generated, and the predicted OD matrix is sent to the corresponding user terminal. The method solves the problem that the current OD prediction model is difficult to give an accurate OD prediction result when the road network topology structure is difficult to change.
Description
Technical Field
The application relates to the technical field of traffic control systems, in particular to a traffic volume prediction method, traffic volume prediction equipment and traffic volume prediction media for a newly built highway.
Background
Traffic volume (OD) prediction is an important issue in traffic planning and management, aiming at predicting the travel demands and traffic flows between the various nodes of the traffic network.
Currently, there are conventional OD prediction models such as linear regression, machine learning models, hybrid models, etc. for OD prediction of road networks. However, it is difficult to give accurate OD prediction results when the topology of the road network changes.
Disclosure of Invention
The embodiment of the application provides a traffic volume prediction method, equipment and medium for a newly built highway, which are used for solving the problem that an accurate OD prediction result is difficult to give when the current OD prediction model is difficult to change a road network topology structure so as to improve the use experience of a user on the OD prediction model.
In one aspect, the embodiment of the application provides a traffic volume prediction method for a newly built highway, which comprises the following steps:
acquiring a first position sequence for planning a newly-built road and a second position sequence of each corresponding traffic cell; the corresponding traffic cells are traffic areas within a preset range of the planned newly-built highway;
determining an influence set corresponding to each traffic cell based on the first position sequence and the second position sequence; the influence set at least comprises traffic cells screened according to preset rules and corresponding influence thereof; the preset rule comprises a distance threshold value used for screening the traffic cells;
based on historical OD data corresponding to the influence set as input, carrying out OD prediction through a preset long-short-term memory network LSTM model to obtain predicted OD data;
determining a corresponding influence adjustment range according to the historical OD data and the predicted OD data corresponding to the influence set;
and generating a prediction OD matrix corresponding to the planned new road based on the influence set, the influence adjusting range and the historical OD data, and sending the prediction OD matrix to a corresponding user terminal.
In one implementation manner of the present application, determining the set of influence corresponding to each traffic cell based on the first location sequence and the second location sequence specifically includes:
determining shortest paths from the traffic cell to at least two highway endpoints of the planned new highway respectively according to the first position sequence and the second position sequence so as to generate a travel distance set;
comparing the shortest path in the travel distance set with the distance threshold;
and according to the comparison result, matching a piecewise function corresponding to the comparison result in an influence model, and determining the influence of the traffic cells based on the matched piecewise function so as to generate the influence set corresponding to each traffic cell.
In one implementation of the present application, the method further includes:
acquiring road information of the planned new road; wherein the road information includes at least one or more of: road class, road length, regional population density, regional road network density;
and calculating the distance threshold according to the road information and a preset weight list.
In one implementation manner of the present application, determining a corresponding influence adjustment range according to the historical OD data and the predicted OD data corresponding to the influence set specifically includes:
determining each traffic cell corresponding to the influence set;
according to the historical OD data and the predicted OD data, generating an OD pair list of each traffic cell according to a preset sequence;
calculating the difference value between the predicted OD data and the historical OD data in the OD pair corresponding to each traffic cell in the OD pair list;
and taking the sum value of the difference values corresponding to the traffic cells as the influence adjusting range.
In one implementation manner of the present application, based on the influence set, the influence adjustment range and the historical OD data, a predicted OD matrix corresponding to the planned new road is generated, and the predicted OD matrix is sent to a corresponding user terminal, which specifically includes:
summing the influence of the influence sets corresponding to the traffic cells to obtain influence sum values;
and determining an influence pending weight according to the ratio of the influence in each influence set to the influence sum value, generating a predicted OD matrix corresponding to the planned newly-built road according to the influence pending weight, the influence adjusting range and the historical OD data, and sending the predicted OD matrix to a corresponding user terminal.
In one implementation manner of the present application, according to the pending weight of the influence, the adjusting range of the influence, and the historical OD data, a predicted OD matrix corresponding to the planned new road is generated, and the predicted OD matrix is sent to a corresponding user terminal, which specifically includes:
generating a pending weight binary group of the influence pending weight of each reachable traffic cell; the reachable traffic cells are paths which exist in pairs through the planned new road;
calculating the binary group weight sum value of each undetermined weight binary group and the undetermined weight sum value of each influence undetermined weight;
and taking the ratio of the weight sum value of the binary group to the undetermined weight sum value as the influence weights of the two traffic cells corresponding to the undetermined weight binary group, generating a prediction OD matrix corresponding to the planned newly-built road according to the influence weights, the influence adjusting range and the historical OD data, and sending the prediction OD matrix to the corresponding user terminal.
In one implementation manner of the present application, according to the influence weight, the influence adjustment range and the historical OD data, a predicted OD matrix corresponding to the planned new road is generated, and the predicted OD matrix is sent to a corresponding user terminal, which specifically includes:
calculating a product value of the influence weight and the influence adjustment range;
determining corresponding predicted newly-built road OD data according to the sum of the product value and the historical OD data of the two corresponding traffic cells;
and adding each piece of predicted newly-built road OD data to a predicted OD matrix so as to send the predicted OD matrix to a corresponding user terminal.
In one implementation manner of the present application, based on the historical OD data corresponding to the influence set as input, the OD prediction is performed by a preset long-short-term memory network LSTM model, and before the predicted OD data is obtained, the method further includes:
according to the year sequence, a plurality of historical OD data samples are obtained;
and respectively inputting the historical OD data samples of adjacent years of the same starting point region and the same destination region in the historical OD data samples into the LSTM model to train the LSTM model until the output accuracy of the LSTM model reaches a preset threshold value, so as to obtain the trained LSTM model.
On the other hand, the embodiment of the application also provides traffic volume prediction equipment for a newly built highway, which comprises the following steps:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to:
acquiring a first position sequence for planning a newly-built road and a second position sequence of each corresponding traffic cell; the corresponding traffic cells are traffic areas within a preset range of the planned newly-built highway;
determining an influence set corresponding to each traffic cell based on the first position sequence and the second position sequence; the influence set at least comprises traffic cells screened according to preset rules and corresponding influence thereof; the preset rule comprises a distance threshold value used for screening the traffic cells;
based on historical OD data corresponding to the influence set as input, carrying out OD prediction through a preset long-short-term memory network LSTM model to obtain predicted OD data;
determining a corresponding influence adjustment range according to the historical OD data and the predicted OD data corresponding to the influence set;
and generating a prediction OD matrix corresponding to the planned new road based on the influence set, the influence adjusting range and the historical OD data, and sending the prediction OD matrix to a corresponding user terminal.
In still another aspect, an embodiment of the present application further provides a traffic volume prediction method for a newly built highway, in which a non-volatile computer storage medium storing computer executable instructions is stored, the computer executable instructions being configured to:
acquiring a first position sequence for planning a newly-built road and a second position sequence of each corresponding traffic cell; the corresponding traffic cells are traffic areas within a preset range of the planned newly-built highway;
determining an influence set corresponding to each traffic cell based on the first position sequence and the second position sequence; the influence set at least comprises traffic cells screened according to preset rules and corresponding influence thereof; the preset rule comprises a distance threshold value used for screening the traffic cells;
based on historical OD data corresponding to the influence set as input, carrying out OD prediction through a preset long-short-term memory network LSTM model to obtain predicted OD data;
determining a corresponding influence adjustment range according to the historical OD data and the predicted OD data corresponding to the influence set;
and generating a prediction OD matrix corresponding to the planned new road based on the influence set, the influence adjusting range and the historical OD data, and sending the prediction OD matrix to a corresponding user terminal.
The beneficial effects that can be produced by the present application include, but are not limited to:
according to the technical scheme, planning of a newly built road can be considered, and prediction of the OD matrix can be performed, namely, under the condition that the road network topology result is changed, accurate prediction of the OD matrix can be performed. Meanwhile, the influence and influence regulation range of a newly built road on a traffic cell are planned, the predicted OD data obtained by LSTM are secondarily distributed, influence factors are added to the finally obtained predicted OD matrix, and the predicted OD matrix is comprehensively and comprehensively generated, so that an accurate OD prediction result is given. And the OD matrix is accurately predicted, so that the use experience of a user on an OD prediction model can be improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a schematic flow chart of a traffic volume prediction method for a newly built highway according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a traffic volume prediction device for a newly built highway according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
OD prediction is an important issue in traffic planning and management, and research is aimed at predicting travel demands and traffic flows between various nodes of a traffic network. Current OD prediction model studies have been largely developed from the following:
traditional model: traditional OD prediction models are mainly based on methods such as linear regression, generalized linear hybrid models and the like, which require manual feature extraction and have weaker processing power for high-dimensional data.
Machine learning model: machine learning models include neural networks, support vector machines, decision trees, etc., which can automatically extract features and learn relationships between features, with better performance and processing power than traditional models.
Mixing model: the hybrid model is a combined model which combines a traditional model and a machine learning model and realizes OD prediction through combination of a shared weight logistic regression and Long-short-term memory network (Long-Short Term Memory, LSTM) and gradient lifting tree (Gradient Boosting Decision Tree, GBDT).
The existing defects can not be predicted under the condition of changing the road network topology structure, and the existing OD prediction model can also generate larger deviation when the road attribute is changed greatly.
Based on the above, the embodiment of the application provides a traffic volume prediction method, equipment and medium for a newly built road, which are used for solving the problem that an accurate OD prediction result is difficult to give when the road network topology structure is difficult to change in the current OD prediction model, so as to improve the use experience of a user on the OD prediction model. .
Various embodiments of the present application are described in detail below with reference to the attached drawing figures.
The embodiment of the application provides a traffic volume prediction method for a newly built highway, as shown in fig. 1, the method can comprise the following steps of S101-S105:
s101, the server acquires a first position sequence for planning a newly-built road and a second position sequence of each corresponding traffic cell.
The corresponding traffic cells are traffic areas within a preset range of planning a newly built highway.
Planning a new road refers to planning a new road by a government or planning a new road, the first position sequence comprises space position coordinates and range of planning the new road, and position coordinates of each intersection of an entrance of the new road are also included, for example, the first position sequence is [ a, b, c, d, …, n ], if a represents planning a starting position of the new road, b represents planning an ending position of the new road, c represents a first entrance or sink of the new road from a point, d represents a second entrance or sink of the new road, and the intersection, … …, n represents an nth entrance or sink of the new road, and the intersection, wherein n is a natural number.
The second position sequence refers to the space position coordinates of the traffic cell in the vicinity of the planned new road, and may include the area boundary coordinates of the traffic cell. The traffic cell refers to a traffic analysis area preset by a user, the influence area is a research range of traffic influence analysis or is called an analysis area, and some travel distribution methods further divide the analysis area into traffic subareas, so that travel distribution prediction aims at calculating travel distribution quantity between a land project and each subarea.
The first position sequence and the second position sequence may be obtained by a server climbing from the internet, or may be obtained by a user being stored in a database connected to the server in advance and the server being obtained automatically.
It should be noted that, the server is merely an example as an execution subject of the traffic volume prediction method for the newly built highway, and the execution subject is not limited to the server, for example, a server cluster, or the like, and may be an execution subject, which is not particularly limited in the present application.
S102, the server determines an influence set corresponding to each traffic cell based on the first position sequence and the second position sequence.
The influence set at least comprises traffic cells screened according to preset rules and corresponding influence thereof. The preset rules include a distance threshold for screening traffic cells.
In the embodiment of the application, the server determines the impact set corresponding to each traffic cell based on the first position sequence and the second position sequence, and specifically comprises the following steps:
and the server determines the shortest paths from the traffic cell to at least two road endpoints of the planned new road respectively according to the first position sequence and the second position sequence so as to generate a travel distance set. And comparing the shortest path in the travel distance set with a distance threshold. And according to the comparison result, matching a piecewise function corresponding to the comparison result in the influence model, and determining the influence of the traffic cells based on the matched piecewise function so as to generate an influence set corresponding to each traffic cell.
At least two intersections or entrances to traffic cells are planned for the newly built highway, and in the embodiment of the application, the newly built highway is used as a highway endpoint. The server may calculate the shortest path from the traffic cell to the highway endpoint according to the obtained first position sequence and the second position sequence, where the second position sequence adopted by the server may be the shortest path from the central region coordinate point of the traffic cell to the highway endpoint, and the shortest path may be the distance calculated by using a euclidean distance calculation formula, or the distance between the two may be calculated by using other distance calculation algorithms, which is not limited in this application. The calculated distance result can be crawled after the calculation is performed by using the existing map software, for example, the calculated distance is calculated by a hundred-degree map and a high-altitude map.
After calculating the shortest path from the traffic cell to the two highway endpoints, the server can obtain the unique shortest path to the highway endpoints by the following formula:
wherein ,representing traffic cell +.>Respectively arrive at the planned new road->Is>，/>Is (are) shortest path->Is the shortest path to the only nearest highway endpoint.
Will beAdded to the travel distance set and according to +.>Distance threshold->Is determined by comparing the size of the (a) and (b)>Corresponding piecewise function for calculating +.>Influence of corresponding traffic cells.
In addition, the determination of the distance threshold also needs to obtain the road information for planning the newly built road by the server. Wherein the road information includes at least one or more of the following: road class, road length, regional population density, regional road network density. And calculating a distance threshold according to the road information and the preset weight list.
The calculation of the distance threshold may be a threshold set by the user, for example, the generation of the distance threshold needs to refer to parameters such as road grade, road length, regional population density, regional road network density, etc., the user may set a weight for each parameter and add the weight to the weight list, and the server calculates the distance threshold according to the sum of products of each weight and the corresponding parameter in the weight list.
The piecewise function calculation formula of the influence model is as follows:
wherein the influence model is as described aboveDistance threshold->Can be understood as whether the traffic cell is within the distance threshold range for planning the newly built road, if it is ()>Less than or equal to the distance threshold), the influence can be calculated if not (++)>Greater than the distance threshold) is not capable of calculating the impact. In summary, only traffic cells within the range of the distance threshold can be calculated through the influence model, so that the OD matrix of the traffic cells can be predicted, and traffic cells with too far distances cannot be used for predicting the OD matrix, so that the prediction error of the OD matrix is reduced.
And S103, the server performs OD prediction through a preset long-short-term memory network LSTM model based on historical OD data corresponding to the influence set as input to obtain predicted OD data.
In the embodiment of the application, based on the historical OD data corresponding to the influence set as input, the OD prediction is performed through a preset long-short-term memory network LSTM model, and before the predicted OD data is obtained, the method further comprises the steps of:
and the server acquires a plurality of historical OD data samples according to the year sequence. And respectively inputting historical OD data samples of adjacent years of the same starting point region and the same destination region in each historical OD data sample into the LSTM model to train the LSTM model until the output accuracy of the LSTM model reaches a preset threshold value, and obtaining the trained LSTM model.
The server can climb the historical OD data samples through the Internet, or acquire the historical OD data samples preset by the user, and arrange the historical OD data samples according to the year sequence. The historical OD data sample starting point area and destination point area can correspond to the traffic cells of the planned newly-built road, the starting point area can be obtained to be any traffic cell, and the destination point area is another traffic cell which is easy to reach the starting point area. And taking the historical OD data sample as a model training sample, inputting the model training sample into an LSTM model to be trained, performing a model training process, and calculating the accuracy of an output result of the LSTM model in the training process so as to judge whether the LSTM model is trained according to the accuracy of the result.
S104, the server determines a corresponding influence adjustment range according to the historical OD data and the predicted OD data corresponding to the influence set.
In the embodiment of the application, the corresponding influence adjusting range is determined according to the historical OD data and the predicted OD data corresponding to the influence set, and the method specifically comprises the following steps:
and the server determines each traffic cell corresponding to the influence set, and generates an OD pair list of each traffic cell according to the historical OD data and the predicted OD data and a preset sequence. And calculating the OD pairs corresponding to each traffic cell in the OD pair list, and predicting the difference value between the OD data and the historical OD data. And taking the sum value of the difference values corresponding to the traffic cells as an influence adjusting range.
Each influence set is formed by planning influence of a newly built road on each traffic cell, and one traffic cell uniquely corresponds to one influence set. In the actual use process, the traffic cell may not have an influence set, and the traffic cell is determined through the influence set, so that the calculation of the OD matrix can be ensured not to have errors.
For example, cell 1 to cell 2:2023 traffic volume 100, predicted 2024 traffic volume 150; cell 1 to cell 3:2023 traffic 150, predicted 2024 traffic 200; … …; cellTo cell->:2023 traffic volume 100, and 2024 traffic volume 150 is predicted. Wherein->，/>Belonging to the set of all cells within the distance threshold of planning a new road.
The server may calculate the difference between the predicted year and the current year, i.e. 2024 traffic (predicted OD data) minus 2023 traffic (historical OD data), e.g. cell 1 to cell 2, as 150-100=50. The server can calculate the difference value of the OD to the data of each traffic cell to another traffic cell according to the sequence along the planned newly-built road. Then, the server sums the difference values of the traffic cells within the distance threshold range of the planned new road to obtain an influence adjusting range。
S105, the server generates a prediction OD matrix corresponding to the planned new road based on the influence set, the influence adjustment range and the historical OD data, and sends the prediction OD matrix to the corresponding user terminal.
In the embodiment of the application, based on the influence set, the influence adjusting range and the historical OD data, a predicted OD matrix corresponding to a planned new road is generated, and the predicted OD matrix is sent to a corresponding user terminal, which specifically comprises the following steps:
and the server performs summation operation on the influence of the influence sets corresponding to the traffic cells to obtain influence and value. And determining the influence pending weight according to the ratio of the influence to the influence sum value in each influence set, generating a predicted OD matrix corresponding to the planned newly-built road according to the influence pending weight, the influence adjusting range and the historical OD data, and sending the predicted OD matrix to the corresponding user terminal.
After the influence sets are obtained, the server can calculate influence and values in the influence sets corresponding to all traffic cells within the range of the distance threshold, and then independently calculate the ratio of the influence of each traffic cell to the influence and values, so that the ratio is used as the influence pending weight. The influence pending weight calculation formula is as follows:
wherein ,is->Influence of individual traffic cells pending weights, +.>Is the influence and value.
The server then generates a pending weight tuple of the impact pending weights for each traffic cell that is reachable. The reachable traffic cells are two-by-two paths of each traffic cell, and the paths of the traffic cells pass through a planned new road. And calculating the weight sum value of the binary groups of each undetermined weight binary group and the undetermined weight sum value of each influence undetermined weight. And taking the ratio of the binary group weight sum value to the undetermined weight sum value as the influence weights of the two traffic cells corresponding to the undetermined weight binary group so as to generate a prediction OD matrix corresponding to the planned newly-built road according to the influence weights, the influence adjusting range and the historical OD data, and sending the prediction OD matrix to the corresponding user terminal.
The undetermined weight binary groups are composed of the influence undetermined weights of two traffic cells which can reach along the planned new road, the server can respectively calculate the sum value of the two influence undetermined weights in each undetermined weight binary group, can also calculate the sum value of the influence undetermined weights corresponding to all traffic cells, and then calculates the influence weights. The specific calculation is as follows:
wherein ,refers to->Traffic cells and->Influence weight between individual traffic cells, < ->And (5) undetermining the sum of the weights for the influence forces corresponding to all the traffic cells.
The server will then also calculate the product value of the impact weight and the impact adjustment range. And determining corresponding predicted newly-built road OD data according to the sum of the product value and the historical OD data of the two corresponding traffic cells. And adding each predicted newly-built road OD data to the predicted OD matrix to send the predicted OD matrix to the corresponding user terminal.
In other words, the server can predict OD data according to the influence weight, the influence adjustment range and the history OD matrix obtained by the above calculation, and the specific calculation formula is as follows:
wherein ,is->Traffic cells to->Predicted OD data for predicted year of individual traffic cell,/->Is->Traffic cells to->Historical OD data for individual traffic cells.
After obtaining the predicted OD data between each traffic cell, the server may sort all traffic partitions by rows (starting point area) and columns (destination area), and generate a predicted OD matrix by using the OD data as an element. And sent to a user terminal responsible for controlling the traffic system, such as terminal equipment of logistics enterprises and traffic management departments, such as mobile phones, computers, etc., which is not particularly limited in the application.
According to the technical scheme, planning of a newly built road can be considered, and prediction of the OD matrix can be performed, namely, under the condition that the road network topology result is changed, accurate prediction of the OD matrix can be performed. Meanwhile, the influence and influence regulation range of a newly built road on a traffic cell are planned, the predicted OD data obtained by LSTM are secondarily distributed, influence factors are added to the finally obtained predicted OD matrix, and the predicted OD matrix is comprehensively and comprehensively generated, so that an accurate OD prediction result is given. And the OD matrix is accurately predicted, so that the use experience of a user on an OD prediction model can be improved.
Fig. 2 is a schematic structural diagram of a traffic volume prediction device for a newly built highway according to an embodiment of the present application, where, as shown in fig. 2, the device includes:
at least one processor; and a memory communicatively coupled to the at least one processor. Wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to enable the at least one processor to:
and acquiring a first position sequence for planning a newly-built road and a second position sequence of each corresponding traffic cell. The corresponding traffic cells are traffic areas within a preset range of a planned new road. And determining an influence set corresponding to each traffic cell based on the first position sequence and the second position sequence. The influence set at least comprises traffic cells screened according to preset rules and corresponding influence thereof. The preset rules include a distance threshold for screening traffic cells. Based on historical OD data corresponding to the influence set as input, carrying out OD prediction through a preset long-short-term memory network LSTM model to obtain predicted OD data. And determining a corresponding influence adjusting range according to the historical OD data and the predicted OD data corresponding to the influence set. Based on the influence set, the influence adjusting range and the historical OD data, a predicted OD matrix corresponding to the planned new road is generated, and the predicted OD matrix is sent to the corresponding user terminal.
The embodiment of the application also provides a non-volatile computer storage medium for the traffic volume prediction method of the newly built highway, which stores computer executable instructions, wherein the computer executable instructions are set as follows:
and acquiring a first position sequence for planning a newly-built road and a second position sequence of each corresponding traffic cell. The corresponding traffic cells are traffic areas within a preset range of a planned new road. And determining an influence set corresponding to each traffic cell based on the first position sequence and the second position sequence. The influence set at least comprises traffic cells screened according to preset rules and corresponding influence thereof. The preset rules include a distance threshold for screening traffic cells. Based on historical OD data corresponding to the influence set as input, carrying out OD prediction through a preset long-short-term memory network LSTM model to obtain predicted OD data. And determining a corresponding influence adjusting range according to the historical OD data and the predicted OD data corresponding to the influence set. Based on the influence set, the influence adjusting range and the historical OD data, a predicted OD matrix corresponding to the planned new road is generated, and the predicted OD matrix is sent to the corresponding user terminal.
The embodiments of the present application are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for the apparatus, medium embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
The device, medium and method provided by the embodiment of the application are in one-to-one correspondence, so that the device and medium also have similar beneficial technical effects as the corresponding method, and the beneficial technical effects of the device and medium are not repeated here because the beneficial technical effects of the method are described in detail above.
It should also be noted that 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 foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (5)
1. A traffic volume prediction method for a newly built highway, the method comprising:
acquiring a first position sequence for planning a newly-built road and a second position sequence of each corresponding traffic cell; the corresponding traffic cells are traffic areas within a preset range of the planned newly-built highway;
determining an influence set corresponding to each traffic cell based on the first position sequence and the second position sequence; the influence set at least comprises traffic cells screened according to preset rules and corresponding influence thereof; the preset rule comprises a distance threshold value used for screening the traffic cells;
based on historical OD data corresponding to the influence set as input, carrying out OD prediction through a preset long-short-term memory network LSTM model to obtain predicted OD data;
determining a corresponding influence adjustment range according to the historical OD data and the predicted OD data corresponding to the influence set;
generating a prediction OD matrix corresponding to the planned new road based on the influence set, the influence adjusting range and the historical OD data, and sending the prediction OD matrix to a corresponding user terminal;
the determining, based on the first location sequence and the second location sequence, an impact set corresponding to each traffic cell specifically includes:
determining shortest paths from the traffic cell to at least two highway endpoints of the planned new highway respectively according to the first position sequence and the second position sequence so as to generate a travel distance set;
comparing the shortest path in the travel distance set with the distance threshold;
according to the comparison result, matching a piecewise function corresponding to the comparison result in an influence model, and determining influence of the traffic cells based on the matched piecewise function so as to generate the influence set corresponding to each traffic cell;
the determining a corresponding influence adjusting range according to the historical OD data and the predicted OD data corresponding to the influence set specifically includes:
determining each traffic cell corresponding to the influence set;
according to the historical OD data and the predicted OD data, generating an OD pair list of each traffic cell according to a preset sequence;
calculating the difference value between the predicted OD data and the historical OD data in the OD pair corresponding to each traffic cell in the OD pair list;
taking the sum of the difference values corresponding to the traffic cells as the influence adjusting range;
based on the influence set, the influence adjustment range and the historical OD data, a predicted OD matrix corresponding to the planned new road is generated, and the predicted OD matrix is sent to a corresponding user terminal, which specifically includes:
summing the influence of the influence sets corresponding to the traffic cells to obtain influence sum values;
determining an influence pending weight according to the ratio of the influence in each influence set to the influence sum value, generating a predicted OD matrix corresponding to the planned newly-built road according to the influence pending weight, the influence adjusting range and the historical OD data, and sending the predicted OD matrix to a corresponding user terminal;
according to the pending weight of the influence, the adjusting range of the influence and the historical OD data, a predicted OD matrix corresponding to the planned newly-built road is generated, and the predicted OD matrix is sent to a corresponding user terminal, and the method specifically comprises the following steps:
generating a pending weight binary group of the influence pending weight of each reachable traffic cell; the reachable traffic cells are paths which exist in pairs through the planned new road;
calculating the binary group weight sum value of each undetermined weight binary group and the undetermined weight sum value of each influence undetermined weight;
the ratio of the weight sum value of the binary group to the undetermined weight sum value is used as the influence weights of the two traffic cells corresponding to the undetermined weight binary group, so that a predicted OD matrix corresponding to the planned newly-built road is generated according to the influence weights, the influence adjusting range and the historical OD data, and the predicted OD matrix is sent to a corresponding user terminal;
according to the influence weight, the influence adjusting range and the historical OD data, a predicted OD matrix corresponding to the planned newly-built road is generated, and the predicted OD matrix is sent to a corresponding user terminal, which specifically comprises:
calculating a product value of the influence weight and the influence adjustment range;
determining corresponding predicted newly-built road OD data according to the sum of the product value and the historical OD data of the two corresponding traffic cells;
adding each piece of predicted newly-built road OD data to a predicted OD matrix so as to send the predicted OD matrix to a corresponding user terminal;
the piecewise function calculation formula of the influence model is as follows:
wherein ,is traffic district->Shortest path to the only nearest road end of the planned new road,/->Is a distance threshold.
2. The traffic volume prediction method for a newly built highway according to claim 1, further comprising:
acquiring road information of the planned new road; wherein the road information includes at least one or more of: road class, road length, regional population density, regional road network density;
and calculating the distance threshold according to the road information and a preset weight list.
3. The traffic volume prediction method for a newly built highway according to claim 1, wherein the method further comprises, based on the historical OD data corresponding to the influence set as input, performing OD prediction through a preset long-short-term memory network LSTM model, and before obtaining the predicted OD data:
according to the year sequence, a plurality of historical OD data samples are obtained;
and respectively inputting the historical OD data samples of adjacent years of the same starting point region and the same destination region in the historical OD data samples into the LSTM model to train the LSTM model until the output accuracy of the LSTM model reaches a preset threshold value, so as to obtain the trained LSTM model.
4. A traffic volume prediction apparatus for a newly built road, the apparatus comprising:
at least one processor; the method comprises the steps of,
a memory communicatively coupled to the at least one processor; wherein,
the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a traffic volume prediction method for a newly created highway as claimed in any one of the preceding claims 1-3.
5. A non-volatile computer storage medium storing computer executable instructions for a traffic volume prediction method for a newly created road, characterized in that the computer executable instructions are capable of executing a traffic volume prediction method for a newly created road as claimed in any one of the preceding claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310961919.6A CN116703008B (en) | 2023-08-02 | 2023-08-02 | Traffic volume prediction method, equipment and medium for newly built highway |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310961919.6A CN116703008B (en) | 2023-08-02 | 2023-08-02 | Traffic volume prediction method, equipment and medium for newly built highway |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116703008A CN116703008A (en) | 2023-09-05 |
| CN116703008B true CN116703008B (en) | 2023-10-31 |
Family
ID=87824221
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310961919.6A Active CN116703008B (en) | 2023-08-02 | 2023-08-02 | Traffic volume prediction method, equipment and medium for newly built highway |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116703008B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118313697B (en) * | 2024-06-06 | 2024-10-01 | 山东高速股份有限公司 | Method and equipment for evaluating local highway toughness under closing condition of toll station |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007128121A (en) * | 2005-11-01 | 2007-05-24 | Tadataka Iida | Method for precisely estimating congested traffic volume generated by zone and od traffic amount |
| CN104183119A (en) * | 2014-08-19 | 2014-12-03 | 中山大学 | Real-time traffic flow distribution prediction system based on road section OD backstepping |
| CN105096614A (en) * | 2015-09-23 | 2015-11-25 | 南京遒涯信息技术有限公司 | Newly established crossing traffic flow prediction method based on generating type deep belief network |
| KR101638368B1 (en) * | 2015-01-02 | 2016-07-11 | 경희대학교 산학협력단 | Prediction System And Method of Urban Traffic Flow Using Multifactor Pattern Recognition Model |
| KR101742042B1 (en) * | 2016-11-15 | 2017-05-31 | 한국과학기술정보연구원 | Apparatus and method for traffic flow prediction |
| CN107967532A (en) * | 2017-10-30 | 2018-04-27 | 厦门大学 | The Forecast of Urban Traffic Flow Forecasting Methodology of integration region vigor |
| CN108345987A (en) * | 2018-01-22 | 2018-07-31 | 东南大学 | A kind of road infrastructure construction project influences evaluation DSS and method |
| CN109447352A (en) * | 2018-10-31 | 2019-03-08 | 东南大学 | A kind of anti-combined method pushed away of bus trip OD matrix |
| JP2019220048A (en) * | 2018-06-22 | 2019-12-26 | 株式会社日立製作所 | Traffic flow prediction device and traffic flow prediction system |
| CN111242491A (en) * | 2020-01-16 | 2020-06-05 | 厦门大学 | Medical big data visualization analysis method, medium, equipment and system |
| CN112489420A (en) * | 2020-11-17 | 2021-03-12 | 中国科学院深圳先进技术研究院 | Road traffic state prediction method, system, terminal and storage medium |
| CN112907969A (en) * | 2021-02-02 | 2021-06-04 | 中国科学院计算技术研究所 | Method and system for predicting road traffic flow |
| CN113298301A (en) * | 2021-05-17 | 2021-08-24 | 东南大学 | Urban service facility evaluation and optimization method based on crowd digital portrait |
| CN113496314A (en) * | 2021-09-07 | 2021-10-12 | 南京感动科技有限公司 | Method for predicting road traffic flow by neural network model |
| WO2022077767A1 (en) * | 2020-10-16 | 2022-04-21 | 深圳先进技术研究院 | Traffic flow prediction method and apparatus, computer device, and readable storage medium |
| CN116052435A (en) * | 2023-03-06 | 2023-05-02 | 广州市交通规划研究院有限公司 | Urban road congestion influence range definition and road influence calculation method |
| CN116434531A (en) * | 2022-12-15 | 2023-07-14 | 上海交通大学 | Short-time traffic flow prediction method based on Conv1D-LSTM model |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7395151B2 (en) * | 2004-02-24 | 2008-07-01 | O'neill Dennis M | System and method for knowledge-based emergency response |
| US10395520B2 (en) * | 2016-12-19 | 2019-08-27 | Here Global B.V. | Method and apparatus for constructing a traffic model |
| CN111489553B (en) * | 2020-04-26 | 2022-02-25 | 百度在线网络技术（北京）有限公司 | Route planning method, device, equipment and computer storage medium |
-
2023
- 2023-08-02 CN CN202310961919.6A patent/CN116703008B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007128121A (en) * | 2005-11-01 | 2007-05-24 | Tadataka Iida | Method for precisely estimating congested traffic volume generated by zone and od traffic amount |
| CN104183119A (en) * | 2014-08-19 | 2014-12-03 | 中山大学 | Real-time traffic flow distribution prediction system based on road section OD backstepping |
| KR101638368B1 (en) * | 2015-01-02 | 2016-07-11 | 경희대학교 산학협력단 | Prediction System And Method of Urban Traffic Flow Using Multifactor Pattern Recognition Model |
| CN105096614A (en) * | 2015-09-23 | 2015-11-25 | 南京遒涯信息技术有限公司 | Newly established crossing traffic flow prediction method based on generating type deep belief network |
| KR101742042B1 (en) * | 2016-11-15 | 2017-05-31 | 한국과학기술정보연구원 | Apparatus and method for traffic flow prediction |
| CN107967532A (en) * | 2017-10-30 | 2018-04-27 | 厦门大学 | The Forecast of Urban Traffic Flow Forecasting Methodology of integration region vigor |
| CN108345987A (en) * | 2018-01-22 | 2018-07-31 | 东南大学 | A kind of road infrastructure construction project influences evaluation DSS and method |
| JP2019220048A (en) * | 2018-06-22 | 2019-12-26 | 株式会社日立製作所 | Traffic flow prediction device and traffic flow prediction system |
| CN109447352A (en) * | 2018-10-31 | 2019-03-08 | 东南大学 | A kind of anti-combined method pushed away of bus trip OD matrix |
| CN111242491A (en) * | 2020-01-16 | 2020-06-05 | 厦门大学 | Medical big data visualization analysis method, medium, equipment and system |
| WO2022077767A1 (en) * | 2020-10-16 | 2022-04-21 | 深圳先进技术研究院 | Traffic flow prediction method and apparatus, computer device, and readable storage medium |
| CN112489420A (en) * | 2020-11-17 | 2021-03-12 | 中国科学院深圳先进技术研究院 | Road traffic state prediction method, system, terminal and storage medium |
| CN112907969A (en) * | 2021-02-02 | 2021-06-04 | 中国科学院计算技术研究所 | Method and system for predicting road traffic flow |
| CN113298301A (en) * | 2021-05-17 | 2021-08-24 | 东南大学 | Urban service facility evaluation and optimization method based on crowd digital portrait |
| CN113496314A (en) * | 2021-09-07 | 2021-10-12 | 南京感动科技有限公司 | Method for predicting road traffic flow by neural network model |
| CN116434531A (en) * | 2022-12-15 | 2023-07-14 | 上海交通大学 | Short-time traffic flow prediction method based on Conv1D-LSTM model |
| CN116052435A (en) * | 2023-03-06 | 2023-05-02 | 广州市交通规划研究院有限公司 | Urban road congestion influence range definition and road influence calculation method |
Non-Patent Citations (4)
| Title |
|---|
| Short-Term Traffic Flow Intensity Prediction Based on CHS-LSTM;Zhao Lei等;《Arabian Journal For Science And Engineering》;第45卷(第12期);第10845-10857页 * |
| 位置服务应用中设施重选址问题研究;蔡洋;《中国优秀硕士学位论文全文数据库 (信息科技辑)》(第2期);第I138-46页 * |
| 区域路网新建公路转移交通量预测方法研究;朱从坤, 冯焕焕;苏州科技学院学报(工程技术版)(第04期);第46-49页 * |
| 基于多因素耦合改进的LSTM道路交通流量预测方法及应用;吴恩泽等;《运输经理世界》(第33期);第68-70页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116703008A (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108846517B (en) | Integration method for predicating quantile probabilistic short-term power load | |
| CN111260118A (en) | Vehicle networking traffic flow prediction method based on quantum particle swarm optimization strategy | |
| CN116703008B (en) | Traffic volume prediction method, equipment and medium for newly built highway | |
| Allignol et al. | A new framework for solving en route conflicts | |
| CN111523778A (en) | Power grid operation safety assessment method based on particle swarm algorithm and gradient lifting tree | |
| CN104091216A (en) | Traffic information predication method based on fruit fly optimization least-squares support vector machine | |
| CN108021686A (en) | A kind of method of public bus network and road network in Rapid matching electronic map | |
| CN108204944A (en) | The Buried Pipeline rate prediction method of LSSVM based on APSO optimizations | |
| CN114510072A (en) | Multi-unmanned aerial vehicle path planning method, terminal and medium based on evolution migration optimization | |
| CN104732067A (en) | Industrial process modeling forecasting method oriented at flow object | |
| CN118071215B (en) | Engineering index analysis processing system and method | |
| CN116307927A (en) | Life circle planning rationality evaluation method and system based on people stream prediction | |
| Lai et al. | Bus arrival time prediction using wavelet neural network trained by improved particle swarm optimization | |
| Jiang et al. | Research on method of trajectory prediction in aircraft flight based on aircraft performance and historical track data | |
| CN113639757B (en) | Map matching method and system based on bidirectional scoring model and backtracking correction mechanism | |
| Blazquez et al. | An instance-specific parameter tuning approach using fuzzy logic for a post-processing topological map-matching algorithm | |
| CN115691140B (en) | Analysis and prediction method for space-time distribution of automobile charging demand | |
| CN116680969A (en) | Filler evaluation parameter prediction method and device for PSO-BP algorithm | |
| CN111191941A (en) | Method for solving SEVM model problem based on artificial bee colony algorithm | |
| CN115527365A (en) | Urban trip activity prediction method and device based on artificial neural network | |
| CN105427581B (en) | traffic simulation method and system based on floating car data | |
| CN111832791B (en) | Gas station prediction method based on machine learning logistic regression | |
| CN117787520B (en) | Hydraulic engineering inspection method, system and storage medium based on quality improvement and synergy model | |
| CN118378103B (en) | Geographic information system data matching management method based on artificial intelligence | |
| EP4177865A1 (en) | Method for determining a flight plan |
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 |