JP2020035091A - Traffic situation prediction device - Google Patents

Abstract

To suppress an increase of a calculation amount required for constructing a prediction model while improving prediction accuracy of a traffic demand in the future.SOLUTION: A traffic state prediction device 100 comprises a learning population data acquisition unit 111 for acquiring learning population data; a traffic amount data acquisition unit 113 for acquiring traffic amount data in each time zone; a usable time zone extraction unit 115 for determining whether or not a traffic amount in each time zone included in the traffic amount data in each time zone is identical to a traffic demand indicating the number of vehicles having tried to pass through a prediction object road in a corresponding time zone, and extracting only a traffic amount in the time zone that is identical thereto as learning traffic amount data during construction of a prediction model; a traffic demand prediction model unit 117 for constructing a traffic demand prediction model, on the basis of the learning traffic amount data and population data for every group; and a traffic demand prediction unit 119 for predicting the traffic demand of the prediction object road, on the basis of the traffic demand prediction model and the population data for every group.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a traffic condition prediction device.

  As used herein, "traffic capacity" is the ability of a road to have structural capacity, such as how many vehicles each road can pass within a given period of time. As used herein, "traffic volume" is the number of vehicles that have actually passed a certain road within a certain period, as measured by a road sensor such as a camera or a sensor installed on the road. As used herein, "traffic demand" is the number of vehicles attempting to pass a certain road within a certain period.

  There is a known technology that acquires traffic data such as traffic volume and required time, and predicts future traffic conditions (traffic demand, required transit time, occurrence of traffic congestion, etc.) at a desired point based on the acquired traffic data. I have. As a method of predicting a traffic situation, there is a method of predicting a future traffic situation from accumulated past traffic data and current traffic data by a statistical processing method such as pattern matching or machine learning. According to the technology described in Patent Document 1, the characteristics of the fluctuation of the traffic volume at a specific date and time and place are statistically analyzed from the accumulated past traffic data, and the traffic volume is calculated based on the obtained characteristics and the current traffic volume. Regression models predict future traffic volumes. In the technology described in Patent Document 2, a traffic congestion prediction model is created based on past traffic congestion data, and current traffic data is input to the traffic congestion prediction model to predict traffic congestion.

JP-A-11-160454 JP 2004-272408 A

  If traffic demand exceeds traffic capacity on a certain road during a certain period of time, vehicles will stay and traffic congestion will occur, and traffic volume and traffic demand will not match (traffic volume will be less than traffic demand) The traffic demand cannot be grasped from the traffic volume. For example, if a traffic demand of 3,000 [vehicles / hour] occurs on a road having a traffic capacity of 2,000 [vehicles / hour] (2,000 vehicles can be passed per hour), the traffic volume becomes 2,000 [vehicles / hour], which does not match the traffic demand. Traffic data, such as traffic volume measured by road sensors, is data on vehicles that have actually passed the road, so if traffic demand exceeds traffic capacity and the upper limit of traffic volume is limited by traffic capacity, It is not possible to know how much traffic demand was in the time zone. Vehicles staying due to the traffic demand exceeding the traffic capacity will pass through the road in a time zone after the time when the traffic originally intended to pass, which will affect future traffic volume, required time, and continuation of traffic congestion. Furthermore, if traffic demand exceeding the traffic capacity continues during that time, the effect will continue even later. For this reason, when predicting the future traffic volume, required time, and traffic congestion from only the traffic data, there is a possibility that the prediction error may be large especially on a road where the traffic volume is large and the traffic demand exceeding the traffic capacity frequently occurs.

  For example, in the method described in Patent Literature 1, the future traffic volume is predicted based on the traffic volume measured by the road sensor. However, the traffic volume is only predicted, and the traffic demand exceeds the traffic capacity. Has not been able to predict traffic demand. In addition, since there are many factors that affect traffic demand, required time, and traffic congestion, there is a concern that the prediction result may differ from the actual result due to unexpected factors in the conventional prediction method. For example, in the method described in Patent Literature 2, a congestion prediction model is created using data of a vehicle that is already in a traveling state as past traffic data. Vehicles that affect traffic on the target road are not considered. For this reason, when predicting traffic demand, required time, and traffic congestion only from past traffic data, the longer the time from the current time to the predicted time is, the longer the vehicle that is not currently in the traveling state but is in the traveling state at the predicted time is For this reason, the prediction error may increase.

  On the other hand, if these prediction models are constructed in consideration of traffic demand, required time, and various factors that affect traffic congestion, prediction errors can be reduced and prediction accuracy can be improved. However, in this case, the amount of calculation required to construct the prediction model may increase dramatically.

  The present invention has been made in view of the above circumstances, and has as its object to improve the prediction accuracy of future traffic demand and to suppress an increase in the amount of calculation required for constructing a prediction model.

  A traffic situation prediction device according to one aspect of the present invention includes a population data acquisition unit that acquires population data of a plurality of groups classified according to a position and an attribute of a person, and a number of vehicles that have passed a prediction target road. A time zone traffic volume data acquisition unit that acquires hourly traffic volume data indicating a certain traffic volume for each time zone, and a traffic volume of each time zone included in the hourly traffic volume data, in a corresponding time zone. Use to judge whether the traffic demand matches the traffic demand indicating the number of vehicles trying to pass through the road to be predicted, and extract only the traffic volume in the matching time zone as learning traffic data when constructing the prediction model A time zone extraction unit, and a traffic demand prediction model construction unit that constructs a traffic demand prediction model that predicts traffic demand using the population data as an explanatory variable based on the learning traffic data and the population data for each group. Based on the population data and the traffic demand forecasting model for each group, and a traffic demand prediction unit for predicting a traffic demand to be predicted road.

  In the traffic condition prediction device according to one aspect of the present invention, a traffic demand prediction model is constructed based on traffic volume data and population data by, for example, machine learning. By using the population data, a traffic demand prediction model can be constructed in consideration of various factors of the increase and decrease of the traffic demand. For example, the population data correlates to the number of cars that are not currently in a running state but will be in a running state at the predicted time. By acquiring the factors of traffic demand increase / decrease, which are difficult to obtain from traffic volume data, from population data and constructing a traffic demand prediction model, traffic demand prediction models can be used with high accuracy. You can make predictions. Here, for example, when the traffic demand exceeding the traffic capacity occurs, the vehicle stays and the traffic congestion occurs, and the traffic volume becomes smaller than the traffic demand. Therefore, it is necessary to accurately grasp the traffic demand from the traffic volume. Can not. Therefore, when a traffic demand prediction model is simply constructed from traffic volume data, there is a possibility that traffic demand cannot be predicted with high accuracy. In this regard, in the traffic situation prediction device according to one aspect of the present invention, the traffic volume and the traffic demand are compared, and only the traffic volume in a time zone where both coincide with each other is used for the prediction model construction. That is, for example, when a traffic demand exceeding the traffic demand occurs on the prediction target road and there is a time zone in which the traffic volume does not match the traffic demand, the traffic volume data in the time zone in which the traffic volume does not match is excluded. Thus, a traffic demand forecast model that more accurately reflects the relationship between population and traffic demand is constructed. By using the traffic demand prediction model, it is possible to predict the traffic demand exceeding the traffic capacity with high accuracy by extrapolation based on the population. In addition, since the traffic demand prediction model is constructed by excluding a part of the traffic volume data, the amount of calculation required for constructing the traffic demand prediction model can be suppressed. As described above, according to the traffic condition prediction device according to one aspect of the present invention, it is possible to improve the prediction accuracy of traffic demand and to suppress an increase in the amount of calculation required for constructing a traffic demand prediction model.

  The traffic demand prediction model construction unit may construct a traffic demand prediction model by selecting population data of a group having a high degree of contribution to traffic demand on the road to be predicted. Thus, the accuracy of the traffic demand prediction can be ensured, and the population data used for constructing the traffic demand forecast model can be limited, thereby suppressing an increase in the amount of calculation required for constructing the traffic demand forecast model.

  The traffic condition prediction device described above includes a required time data obtaining unit that obtains required time data for each time zone indicating the required time of a vehicle that has passed the target road for each time zone, and a traffic demand prediction result obtained by the traffic demand prediction unit. And a traffic demand prediction unit for constructing a travel time prediction model for predicting the travel time for each time zone using the traffic demand prediction result as an explanatory variable, based on the travel time data for each time zone. A required time prediction unit for predicting the required time for each time zone when passing through the road to be predicted based on the predicted traffic demand prediction result used for predicting the required time for each time zone and the required time prediction model And may be further provided. For example, a vehicle that has stayed due to a traffic demand exceeding the traffic capacity during a certain period passes through the road in a time zone after the time zone originally intended to pass. In this case, the required time of the vehicle may not be properly predicted. In this regard, in the traffic condition prediction device according to one aspect of the present invention, the required time prediction model is constructed based on the required time for each time zone and the prediction result of the traffic demand. The required time can be predicted in consideration of the influence. That is, according to the traffic situation prediction device according to one aspect of the present invention, the accuracy of the required time prediction can be improved.

  The above-described traffic condition prediction device may further include a traffic congestion prediction unit that predicts traffic congestion based on a prediction result of the required time for each time zone by the required time prediction unit. By predicting traffic congestion based on the above-described highly accurate required time prediction result, the accuracy of traffic congestion prediction can be improved.

  The above-described traffic condition prediction device includes a speed data acquisition unit that acquires hourly speed data indicating the speed of a vehicle that has passed through the prediction target road for each time zone, and a traffic accident and traffic regulation status on the prediction target road. A traffic abnormal data acquisition unit that acquires hourly traffic abnormal data indicated for each zone, and wherein the use time zone extracting unit considers at least one of hourly speed data and hourly traffic abnormal data. Then, it may be determined whether the traffic volume in each time zone included in the hourly traffic volume data matches the traffic demand in the corresponding time zone. If the traffic demand exceeds the traffic capacity, it is considered that the speed of the vehicle decreases due to congestion. When a traffic accident or a traffic regulation occurs, the traffic volume is considered to change irregularly. As described above, the speed data and the traffic abnormality data for each time zone are closely related to the traffic volume and the traffic demand situation. Therefore, when determining whether or not the traffic volume matches the traffic demand, By considering the speed data and the traffic abnormality data, the coincidence between the traffic volume and the traffic demand can be determined with high accuracy.

  ADVANTAGE OF THE INVENTION According to this invention, the prediction accuracy of future traffic demand can be improved and increase of the calculation amount required for construction of a prediction model can be suppressed.

It is a figure for explaining the function of the traffic situation prediction device concerning one embodiment. It is a figure showing the example of composition of population data. It is a figure showing an example of a traffic congestion prediction result. 4 is a flowchart illustrating a process executed by the traffic situation prediction device according to the embodiment, and more specifically, a flowchart illustrating a process of constructing a traffic demand prediction model. 4 is a flowchart illustrating a process executed by the traffic condition prediction device according to the embodiment, and more specifically, a flowchart illustrating a traffic demand prediction process. 5 is a flowchart illustrating a process executed by the traffic condition prediction device according to the embodiment, and more specifically, a flowchart illustrating a process of constructing a required time prediction model. 3 is a flowchart illustrating a process executed by the traffic condition prediction device according to the embodiment, specifically, a flowchart illustrating a required time prediction process and a traffic congestion prediction process. It is a figure showing composition of hardware of a traffic situation prediction device concerning one embodiment.

  Hereinafter, an embodiment of a traffic situation prediction device according to the present invention will be described in detail with reference to the drawings. In the description of the drawings, the same elements will be denoted by the same reference symbols, without redundant description.

  FIG. 1 is a diagram for explaining functions of the traffic situation prediction device 100 according to the present embodiment. The traffic condition prediction device 100 creates (constructs) a traffic demand prediction model used for prediction of traffic demand based on learning traffic volume data and population data. The traffic situation prediction device 100 predicts traffic demand using population data as input, using the created traffic demand prediction model.

  In addition, the traffic condition prediction device 100 creates a required time prediction model used for predicting the required time based on the data in which the predicted traffic demand is accumulated for learning and the required time data. The traffic condition prediction device 100 predicts the required time based on the created required time prediction model and the traffic demand predicted using the population data as input. Then, the traffic condition prediction device 100 predicts traffic congestion from the required time further predicted from the traffic demand predicted by inputting the population data.

  As shown in FIG. 1, the traffic situation prediction device 100 includes a learning population data acquisition unit 111, a learning population data storage unit 112, a traffic volume data acquisition unit 113, a traffic volume data storage unit 114, a speed Data acquisition unit 128, speed data storage unit 129, traffic abnormality data acquisition unit 130, traffic abnormality data storage unit 131, use time zone extraction unit 115, learning traffic volume data storage unit 116, traffic demand prediction A model construction unit 117, a traffic demand prediction model storage unit 118, a prediction population data acquisition unit 110, a traffic demand prediction unit 119, a learning traffic demand prediction result storage unit 120, a required time data acquisition unit 121, The required time data storage unit 122, the required time prediction model construction unit 123, the required time prediction model storage unit 124, the prediction traffic demand prediction result acquisition unit 125, It includes a required time prediction unit 126, a traffic jam prediction unit 127, a.

  The learning population data acquisition unit 111 acquires population data of a plurality of groups classified according to the position and attribute of a person. The learning population data acquisition unit 111 acquires learning population data (learning population data) used for constructing a traffic demand prediction model from outside the traffic situation prediction device 100. The learning population data acquisition unit 111 acquires learning population data sampled within a predetermined sampling period as original data used for traffic congestion prediction. The learning population data is, for example, past population data of the whole country recorded in an external database, and is divided into a plurality of groups classified according to the sampling time, the position of the person, and the attribute of the person. In the present embodiment, the learning population data acquisition unit 111 acquires only the learning population data sampled at noon every day. The learning population data acquisition unit 111 inputs the learning population data to the learning population data storage unit 112. The learning population data storage unit 112 stores (stores) the learning population data.

  The population data is data indicating how many people existed in a certain area at a certain time. In the present embodiment, the population data is divided into a plurality of groups classified according to the sampling time, the position of the person (for example, a local mesh, etc.), and the attributes of the person (for example, gender, age, place of residence, etc.). The population belonging to each is shown. The sampling time is the time at which the data was sampled. The position and attribute of a person are the position and attribute of a data sampling target (sample target). For example, the population data is generated from periodically sampled position information of the mobile terminal and registration information on the attribute of the user of the mobile terminal stored in an external database or the like. In the present embodiment, as shown in FIG. 2, the population data includes items of “time”, “location identification number”, “sex”, “age”, “place of residence”, and “population”. .

  "Time" indicates the date and time when the data was sampled. The "position identification number" indicates a number for identifying the position of the sampling target person. For example, “JIS X 0410 area mesh code” is used as the “position identification number”. As the “position identification number”, a regional mesh code such as a secondary mesh, a tertiary mesh, or a half regional mesh may be used, or a prefecture code or a municipal code of the place of residence may be used. You may. In the present embodiment, since a half area mesh is used as the “position identification number”, the position identification numbers are classified into about 1.5 million types.

  “Gender” indicates the gender of the sampling target person. The “age” indicates the age group of the sampling target. In the present embodiment, “age” is 20 years old or less, 21 to 25 years, 26 to 30 years, 31 to 35 years, 36 to 40 years, 41 to 45 years, 46 to 50 years, 51 to 55 years, 56 years It is classified into 13 types: -60 years old, 61-65 years old, 66-70 years old, 71-75 years old, 76 years old and over. “Residence” indicates the residence of the sampling target. For the “living place”, a regional mesh code such as a secondary mesh, a tertiary mesh, or a half regional mesh may be used, or a prefecture code or a municipal code of the residential place may be used. Is also good. In the present embodiment, municipal codes classified into about 2,000 are used as the “living place”.

  In the present embodiment, the population data is divided into a plurality of groups according to “position identification number” corresponding to the position of a person and “sex”, “age”, and “place of residence” corresponding to the attribute of the person. being classified. For this reason, the population data can be classified into groups of about 1.5 million × 2 × 13 × about 2000. That is, the space in which the combination of the position of the person and the attribute is a variable has theoretically about 80 billion dimensions.

  The traffic volume data acquisition unit 113 acquires hourly traffic volume data indicating the traffic volume, which is the number of vehicles passing through the prediction target road, for each time zone. The traffic data acquisition unit 113 acquires traffic data from outside the traffic condition prediction device 100. The traffic volume data acquisition unit 113 acquires traffic volume data at a traffic demand prediction position sampled within a predetermined sampling period as original data used for traffic demand prediction. The traffic volume data indicates, for example, a traffic volume in the past traffic volume data recorded in an external database according to the traffic demand prediction position at which the traffic demand is predicted. The traffic data acquisition unit 113 inputs traffic data to the traffic data storage unit 114. The traffic data storage unit 114 stores (stores) traffic data.

  The traffic volume data is data indicating the number of vehicles (traffic volume) passing according to the position. For example, the traffic volume data is measured at regular sampling intervals using a vehicle sensor installed on the road, and the traffic volume information is calculated. It is stored in advance in an external database to be managed. For example, the traffic volume data includes items of “time” and “traffic volume” for each section (so-called link) in which a road (for example, a main road in the whole country) is divided in advance. In the present embodiment, the above-described section (position) that has been divided in advance is set as a prediction target (prediction target road). “Time” indicates the date and time at the start of the sampling period. The “traffic volume” indicates the traffic volume at the target position during the sampling period. In this embodiment, the traffic data is sampled at intervals of 10 minutes.

  The speed data acquisition unit 128 acquires hourly speed data indicating the speed of the vehicle that has passed the prediction target road for each time zone. The speed data acquisition unit 128 acquires speed data used for extracting traffic data for learning from outside the traffic condition prediction device 100. The speed data acquisition unit 128 acquires speed data at the traffic demand prediction position sampled within a predetermined sampling period. The speed data indicates, for example, a speed corresponding to a traffic demand prediction position at which traffic demand is predicted among past speed data recorded in an external database. The speed data acquisition unit 128 inputs the speed data to the speed data storage unit 129. The speed data storage unit 129 stores (stores) speed data.

  The speed data is data indicating the speed of the vehicle in accordance with the position, for example, measured at regular sampling intervals using a vehicle sensor installed on the road, and stored in advance in an external database that manages the speed information. Have been. For example, the speed data uses, for each sampling period, the average of the speeds of the vehicles that have passed the target position during that period. For example, speed data includes items of “time” and “speed”. “Time” indicates the date and time of the start of the sampling period. In “speed”, the speed of the vehicle during the sampling period is displayed. The speed need not be the average speed of the vehicle during the sampling period, but may be a maximum speed, a minimum speed, a median speed, or the like. In the present embodiment, the speed data is sampled at intervals of 5 minutes.

  The traffic abnormality data acquisition unit 130 acquires hourly traffic abnormality data indicating a traffic accident and a traffic regulation situation on the prediction target road for each time zone. The traffic abnormal data acquisition unit 130 acquires traffic abnormal data used for extracting learning traffic volume data from outside the traffic situation prediction device 100. The traffic abnormality data acquisition unit 130 acquires traffic abnormality data at a traffic demand prediction position sampled within a predetermined sampling period. The traffic anomaly data indicates, for example, the presence or absence of a traffic anomaly corresponding to a traffic demand prediction position at which traffic demand is predicted, among past traffic anomaly data recorded in an external database. The traffic abnormal data acquisition unit 130 inputs the traffic abnormal data to the traffic abnormal data storage unit 131. The traffic abnormality data storage unit 131 stores (stores) traffic abnormality data.

  The traffic abnormality data is data indicating a traffic abnormality corresponding to a position, and is stored in an external database for managing traffic abnormality information in advance. The traffic abnormality is an event that can affect the traffic situation at the target position due to a traffic accident, road construction, traffic regulation, or the like. For example, the traffic abnormality data includes items of “time” and “traffic abnormality”. “Time” indicates the date and time of the start of a period delimited by a certain time interval. "Traffic anomaly" indicates the presence or absence of an anomaly in the target position during the period. The format of the traffic abnormality data is not limited to the above-described format, and may be, for example, data that exists only at the time of occurrence of the traffic abnormality.

  The use time zone extraction unit 115 determines whether the traffic volume of each time zone included in the hourly traffic volume data matches the traffic demand indicating the number of vehicles that tried to pass through the prediction target road in the corresponding time zone. Is determined, and only the traffic volume in the coincident time zone is extracted as learning traffic volume data at the time of constructing the prediction model. The use time zone extraction unit 115 refers to the traffic volume data storage unit 114, the speed data storage unit 129, and the traffic abnormality data storage unit 131, and determines, for each position, the time zone in which the traffic volume and the traffic demand are determined to match. Extract traffic volume data. As described above, the use time zone extraction unit 115 considers the time zone-specific speed data and the time zone-specific traffic abnormality data, and determines whether the traffic volume of each time zone included in the time zone-specific traffic volume data corresponds to the corresponding time zone. It is determined whether the traffic demand is the same as that of the belt.

  Hereinafter, an example will be described in which the usage time zone extraction unit 115 determines whether or not the traffic volume and the traffic demand match for the traffic volume data at a certain traffic demand predicted position using the speed data and the traffic abnormality data. I do. When a traffic demand that exceeds the traffic capacity of the target position occurs, the speed of the target position decreases due to congestion. In addition, when lane reduction, speed regulation, and the like occur due to traffic abnormalities, the traffic volume changes irregularly, so it cannot be determined whether the traffic volume matches traffic demand. The use time zone extraction unit 115 determines whether the speed at a certain time at the predicted position is lower than a predetermined speed threshold using the speed data. As a result of the determination, if the speed is below the threshold value, congestion has occurred at the target position, it is determined that the traffic volume and the traffic demand do not match, and the traffic volume data at the target time is excluded. The speed threshold is a parameter and can be arbitrarily changed by the user. The threshold value of the speed is set to 70 [km / hour] on a highway, for example. Further, the use time zone extracting unit 115 excludes the traffic volume data at the time when the traffic abnormality has occurred, using the traffic abnormality data. The use time zone extraction unit 115 inputs the traffic volume data at the time not excluded to the learning traffic volume data storage unit 116. The learning traffic data storage unit 116 stores (stores) the traffic data at times not excluded. It should be noted that the exclusion of traffic volume data performed by the use time zone extraction unit 115 is not limited to the method using the speed data and the traffic abnormality data described above. For example, only one of the speed data and the traffic abnormality data may be used, or the traffic congestion data may be used.

  The traffic demand prediction model construction unit 117 constructs a traffic demand prediction model that predicts traffic demand using population data as an explanatory variable, based on learning traffic data and learning population data (population data for each group). The traffic demand prediction model construction unit 117 refers to the learning population data storage unit 112 and the learning traffic volume data storage unit 116, and predicts a regression equation (traffic demand prediction model) used for prediction of traffic demand for each position. To build. The traffic demand prediction model construction unit 117 constructs a traffic demand prediction model by Elastic Net regression using learning population data as explanatory variables and learning traffic volume data as target variables. The traffic demand prediction model construction unit 117 constructs a traffic demand prediction model using a plurality of sets of sampling periods, with learning population data and learning traffic volume data indicating information on the same day as one set. The regression used in the traffic demand prediction model construction unit 117 is not limited to Elastic Net regression. Instead of Elastic Net regression, for example, Lasso regression, Ridge regression, etc. may be used. Also, variable selection by logistic regression, dimensional compression by PLS regression, PCA, etc., linear regression, neural network, or the like may be combined. In the present embodiment, a model is constructed in which the population at noon for each day and the traffic volume data in 5-minute units in the afternoon on the same day are set as one set, and a model for predicting the traffic demand in 5-minute units in the afternoon on the same day from the population at noon. The traffic demand prediction model construction unit 117 inputs the traffic demand prediction model to the traffic demand prediction model storage unit 118. The traffic demand prediction model storage unit 118 stores (stores) the traffic demand prediction model.

  The traffic demand prediction model construction unit 117 may construct a traffic demand prediction model by preferentially selecting population data of a group having a high degree of contribution to traffic demand on the prediction target road. Whether or not the contribution is high is determined by, for example, a regression coefficient, a correlation coefficient, a weight in a neural network, or the like.

  The prediction population data acquisition unit 110 acquires prediction population data used for prediction of traffic demand from outside the traffic condition prediction device 100. The prediction population data is population data at a predetermined date and time determined in advance, and is, for example, the latest population data among the population data that can be obtained, the population data at a predetermined time on the current day, and the like. In the present embodiment, the prediction population data acquisition unit 110 acquires population data sampled at noon of the day on which traffic demand prediction is performed.

  The traffic demand prediction unit 119 predicts the traffic demand of the road to be predicted based on the population data for prediction (population data for each group) and the traffic demand prediction model. The traffic demand prediction unit 119 predicts a traffic demand using the traffic demand prediction model stored in the traffic demand prediction model storage unit 118 and the prediction population data acquired by the prediction population data acquisition unit 110. In the present embodiment, the traffic demand prediction unit 119 receives prediction population data as input, and uses the traffic demand prediction model acquired from the traffic demand prediction model storage unit 118 to determine the traffic demand prediction position in the traffic demand prediction time zone. The traffic demand prediction result is output to the outside of the traffic situation prediction device 100. In addition, the traffic demand prediction unit 119 inputs the traffic demand prediction result to the learning traffic demand prediction result storage unit 120 and the prediction traffic demand prediction result acquisition unit 125. The learning traffic demand prediction result storage unit 120 stores (stores) the traffic demand prediction result as learning data for constructing a required time prediction model.

  The required time data obtaining unit 121 obtains required time data for each time zone indicating the required time of the vehicle that has passed the prediction target road for each time zone. The required time data acquisition unit 121 acquires required time data from outside the traffic condition prediction device 100. The required time data obtaining unit 121 obtains required time data at the required time predicted position sampled within a predetermined sampling period as original data used for the required time prediction. The required time data indicates, for example, a required time corresponding to a required time predicted position for predicting a required time among past required time data recorded in an external database. The required time data acquisition unit 121 inputs the required time data to the required time data storage unit 122. The required time data storage unit 122 stores (stores) required time data.

  The required time data is data indicating the required time required to pass from the entrance to the exit of the target position, is measured for each predetermined sampling period, and is stored in advance in an external database that manages the required time information. . For example, the required time data includes items of “time” and “required time” for each position. "Time" indicates the date and time when the vehicle arrived at the entrance of the target position. In the “time required”, the length of time required for the vehicle arriving at the entrance at the target position to reach the exit at the target position is displayed. In the present embodiment, the required time data is sampled at intervals of 30 minutes.

  The required time prediction model construction unit 123 uses the traffic demand prediction result by the traffic demand prediction unit 119 and the required time data by time zone to predict the required time by time zone using the predicted result of traffic demand as an explanatory variable. Build a time prediction model. The required time prediction model construction unit 123 refers to the learning traffic demand prediction result storage unit 120 and the required time data storage unit 122 and, for each position, a prediction regression equation used for predicting the required time (required time prediction model). To build. The required time prediction model construction unit 123 constructs a required time prediction model by Elastic Net regression using the learning traffic demand prediction result as an explanatory variable and the required time data as an objective variable. The required time prediction model constructing unit 123 constructs a required time prediction model using a plurality of sets of sampling periods, with one set of learning traffic demand prediction results indicating information on the same day and required time data. The regression used in the required time prediction model construction unit 123 is not limited to Elastic Net regression. Instead of Elastic Net regression, for example, Lasso regression, Ridge regression, etc. may be used. Also, variable selection by logistic regression, dimensional compression by PLS regression, PCA, etc., linear regression, neural network, or the like may be combined. In the present embodiment, the traffic demand forecast result in the unit of 5 minutes in the afternoon and the required time data in the unit of 30 minutes in the afternoon of the same day are set as one set, and the required time in the unit of 30 minutes is calculated from the traffic demand forecast result in the unit of 5 minutes. Build predictive models. The required time prediction model construction unit 123 inputs the required time prediction model to the required time prediction model storage unit 124. The required time prediction model storage unit 124 stores (stores) the required time prediction model.

  The prediction traffic demand prediction result acquisition unit 125 acquires the prediction traffic demand prediction result used for the prediction of the required time from the traffic demand prediction unit 119. The traffic demand forecasting result for prediction is a traffic demand forecasting result at a predetermined date and time determined in advance. For example, the traffic demand forecasting result is obtained by using the latest population data among the available population data, the population data at the predetermined time of the day, and the like. It is a traffic demand prediction result predicted by the prediction unit 119. In the present embodiment, the traffic demand prediction result acquiring unit 125 for prediction uses the population at noon of the day for which the required time is to be predicted, and the traffic demand prediction unit 119 predicts the traffic demand prediction in the unit of 5 minutes in the afternoon of the day. Get the result.

  The required time prediction unit 126 passes through the road to be predicted based on the traffic demand prediction result for prediction used by the traffic demand prediction unit 119 and used for predicting the required time for each time zone, and the required time prediction model. Predict the required time for each time zone. The required time prediction unit 126 uses the required time prediction model stored in the required time prediction model storage unit 124 and the predicted traffic demand prediction result obtained by the predicted traffic demand prediction result acquisition unit 125 to calculate the required time. Predict. In the present embodiment, the required time prediction unit 126 receives the predicted traffic demand prediction result as an input, and uses the required time prediction model acquired from the required time prediction model storage unit 124 to calculate the required time in the required time prediction time zone. Outputs the estimated time required for the location.

  The traffic congestion prediction unit 127 predicts traffic congestion based on the prediction result of the required time for each time zone by the required time prediction unit 126. In this embodiment, for each day, at the position of the traffic congestion prediction target, from the result of the required time prediction in the unit of 30 minutes in the afternoon of the same day, “no traffic congestion”, “congestion start time”, “congestion end time” in the afternoon of the same day ”And“ peak time of traffic jam ”. The traffic jam required time threshold Tj at which the traffic jam is determined to be occurring at the position of the traffic jam prediction target is determined by using the speed v determined to be the traffic jam and the length m of the position of the traffic jam prediction target at the traffic jam required time threshold: Tj = m / v is obtained. The speed v determined to be a traffic jam is a parameter, and can be arbitrarily set by the user. For example, 40 [km / hour] is set on an expressway. In the case where at least one required time prediction result exceeding Tj is present in the required time prediction results in the unit of 30 minutes in the afternoon of the traffic congestion prediction target day at the position of the traffic congestion prediction target predicted by the required time prediction unit 126, It is determined that there is traffic congestion, and if there is no traffic congestion, it is determined that there is no traffic congestion.

  When it is determined that there is a traffic jam, the traffic jam prediction unit 127 predicts the start time of the traffic jam, the end time of the traffic jam, and the peak time of the traffic jam. In this embodiment, the time at which the required time of the required time prediction result in the afternoon of the traffic congestion prediction target position in the unit of 30 minutes exceeds the traffic congestion required time threshold Tj for the traffic congestion prediction target day is regarded as the traffic congestion start time. Next, the time at which the required time last transitions from a state in which the required time exceeds the traffic congestion time threshold Tj to a state in which the required time is lower than the threshold is set as the end time of the congestion. Next, the time when the required time is the largest is set as the peak time of the traffic jam. FIG. 3A shows an output example of a prediction result from the traffic congestion prediction unit 127 when it is determined that there is congestion. For example, as shown in FIG. 3A, for the item of “congestion occurrence”, a value indicating “congestion” is output, and “start time”, “end time”, and “congestion peak time” are output. , Output the derived results. The above is an example of the embodiment, and the determination of the congestion start time, the congestion end time, and the peak time of the congestion are not limited to the above. For example, on a road where traffic congestion repeatedly occurs and ends many times in the afternoon, it is assumed that the traffic congestion has occurred many times instead of once, and not only at the time when the traffic congestion time threshold Tj is exceeded for the first time, but also Each time it exceeds, the start time may be considered as another traffic jam.

  When it is determined that there is no traffic congestion, the traffic congestion prediction unit 127 does not predict the “start time”, the “end time”, and the “congestion peak time”. FIG. 3B shows an output example of a prediction result from the traffic congestion prediction unit 127 when it is determined that there is no congestion. For example, as shown in FIG. 3B, a value indicating “no traffic congestion” is output for the item “occurrence of traffic congestion”, and “start time”, “end time”, And the item of “congestion peak time” is NULL.

  Next, a process executed by the traffic situation prediction device 100 will be described with reference to FIGS. FIG. 4 is a flowchart illustrating a construction process of a traffic demand prediction model. FIG. 5 is a flowchart showing the traffic demand prediction processing. FIG. 6 is a flowchart showing a process of constructing a required time prediction model. FIG. 7 is a flowchart showing the required time prediction processing and the traffic congestion prediction processing.

  As shown in FIG. 4, in the traffic demand prediction model construction processing, first, various data are acquired from outside the traffic situation prediction device 100 (step S1). Specifically, the learning population data acquiring unit 111 acquires the learning population data, the traffic volume data acquiring unit 113 acquires the hourly traffic volume data, and the speed data acquiring unit 128 acquires the hourly speed data. The traffic abnormality data acquiring unit 130 acquires the traffic abnormality data by time zone.

  Subsequently, the usage time zone is extracted by the usage time zone extraction unit 115 (step S2). Specifically, the usage time zone extraction unit 115 determines, for the traffic volume of each time zone included in the hourly traffic volume data, the traffic demand indicating the number of vehicles that have attempted to pass through the prediction target road in the corresponding time zone. Is determined, and only the traffic volume in the matching time zone is extracted as the learning traffic volume data at the time of constructing the prediction model. The use time zone extraction unit 115 considers the time zone-specific speed data and the time zone-specific traffic abnormality data, and determines that the traffic volume of each time zone included in the time zone-specific traffic volume data is the traffic demand of the corresponding time zone. It is determined whether or not they match.

  Subsequently, the traffic demand prediction model construction unit 117 constructs a traffic demand prediction model (step S3). Specifically, the traffic demand forecasting model construction unit 117 creates a traffic demand forecasting model that forecasts traffic demand using population data as an explanatory variable based on learning traffic data and learning population data (population data for each group). To construct. Then, the constructed traffic demand prediction model is stored by the traffic demand prediction model storage unit 118 (step S4).

  As shown in FIG. 5, in the traffic demand prediction processing, first, the population data for prediction is acquired from outside the traffic condition prediction device 100 by the population data acquisition unit for prediction 110 (step S11). Subsequently, traffic demand is predicted by the traffic demand prediction unit 119 (step S12). Specifically, the traffic demand prediction unit 119 predicts the traffic demand on the road to be predicted based on the population data for prediction (population data for each group) and the traffic demand prediction model (step S12). Then, the traffic demand prediction unit 119 outputs the prediction result to the outside, and the traffic demand prediction result storage unit 120 for learning stores the traffic demand prediction result (step S13).

  As shown in FIG. 6, in the required time prediction model construction processing, first, the required time data obtaining unit 121 obtains required time data for each time zone from outside the traffic condition prediction device 100 (step S21). Subsequently, the required time prediction model construction unit 123 constructs a required time prediction model (step S22). Specifically, the required time prediction model construction unit 123 uses the traffic demand prediction result as an explanatory variable based on the traffic demand prediction result by the traffic demand prediction unit 119 and the required time data for each time zone to determine the required time for each time zone. Build a required time prediction model that predicts time. Then, the constructed required time prediction model is stored by the required time prediction model storage unit 124 (step S23).

  As shown in FIG. 7, in the required time prediction processing and the traffic congestion prediction processing, first, the required time is predicted by the required time prediction unit 126 (step S31). Specifically, the required time prediction unit 126 performs a prediction based on a traffic demand prediction result for prediction used by the traffic demand prediction unit 119 and used for predicting the required time for each time zone, and a required time prediction model. Predict the required time for each time zone when passing through the target road. Subsequently, traffic congestion is predicted by the traffic congestion prediction unit 127 (step S32). Specifically, the traffic congestion prediction unit 127 predicts traffic congestion based on the prediction result of the required time for each time zone by the required time prediction unit 126. Then, the traffic congestion prediction unit 127 outputs the traffic congestion prediction result to the outside (step S33).

  Next, the operation and effect of the traffic situation prediction device 100 will be described.

The traffic situation prediction device 100 includes a learning population data acquisition unit 111 that acquires a plurality of groups of learning population data classified according to the positions and attributes of people, and the number of vehicles that have passed the prediction target road. A traffic volume data acquiring unit 113 for acquiring hourly traffic volume data indicating the traffic volume for each time zone; and a traffic volume for each time zone included in the hourly traffic volume data, a prediction target road in the corresponding time zone. Use time zone extraction to judge whether the traffic demand matches the traffic demand indicating the number of vehicles trying to pass through, and extract only the traffic volume in the matching time zone as learning traffic volume data when constructing the prediction model A traffic demand forecasting model for constructing a traffic demand forecasting model for forecasting traffic demand using population data as an explanatory variable based on the learning traffic volume data and population data for each group; Includes a built unit 117, based on population data and traffic demand forecasting model for each group, the traffic demand prediction unit 119 for predicting a traffic demand prediction target roads, a.
In the traffic condition prediction device 100 described above, a traffic demand prediction model is constructed by, for example, machine learning based on the traffic volume data and the population data. By using the population data, a traffic demand prediction model can be constructed in consideration of various factors of the increase and decrease of the traffic demand. For example, the population data correlates to the number of cars that are not currently in a running state but will be in a running state at the predicted time. Such a traffic demand increase / decrease factor, which is difficult to obtain from traffic volume data, is obtained from population data and a traffic demand prediction model is constructed. By using the traffic demand prediction model, traffic demand prediction is performed with high accuracy. It can be performed. Here, for example, when the traffic demand exceeds the traffic capacity, the vehicle stays and the traffic congestion occurs, and the traffic volume becomes smaller than the traffic demand. Can not. Therefore, when a traffic demand prediction model is simply constructed from traffic volume data, there is a possibility that traffic demand cannot be predicted with high accuracy. In this regard, in the traffic situation prediction device 100, the traffic volume and the traffic demand are compared, and only the traffic volume in a time zone in which both coincide is used for the construction of the prediction model. That is, for example, when there is a time zone where the traffic demand exceeds the traffic demand on the prediction target road and the traffic volume does not match the traffic demand, the traffic volume data of the time zone where the traffic volume does not match is excluded. Thus, a traffic demand forecast model that more accurately reflects the relationship between population and traffic demand is constructed. By using the traffic demand prediction model, it is possible to predict the traffic demand exceeding the traffic capacity with high accuracy by extrapolation based on the population. In addition, since the traffic demand prediction model is constructed by excluding a part of the traffic volume data, the amount of calculation required for constructing the traffic demand prediction model can be suppressed. As described above, according to the traffic situation prediction device 100, it is possible to improve the prediction accuracy of traffic demand and to suppress an increase in the amount of calculation required for constructing a traffic demand prediction model.

  The traffic demand prediction model construction unit 117 may construct a traffic demand prediction model by selecting population data of a group having a high degree of contribution to traffic demand on the prediction target road. Thus, the accuracy of the traffic demand prediction can be ensured, and the population data used for constructing the traffic demand forecast model can be limited, thereby suppressing an increase in the amount of calculation required for constructing the traffic demand forecast model.

  The above-described traffic condition prediction device 100 includes a required time data acquisition unit 121 that acquires required time data for each time zone indicating the required time of a vehicle that has passed the prediction target road for each time zone, and a traffic demand prediction unit 119 that performs traffic demand prediction. A required time prediction model constructing unit 123 that constructs a required time prediction model for predicting required time per time zone using the predicted result of traffic demand as an explanatory variable based on the prediction result of Based on the traffic demand prediction result for prediction used for predicting the required time for each time zone predicted by the prediction unit 119 and the required time prediction model, the required time for each time zone when passing through the road to be predicted is predicted. And a required time prediction unit 126. For example, a vehicle that has stayed due to a traffic demand exceeding the traffic capacity during a certain period passes through the road in a time zone after the time zone originally intended to pass. In this case, the required time of the vehicle may not be properly predicted. In this regard, in the traffic condition prediction device 100, the required time prediction model is constructed based on the required time for each time zone and the prediction result of the traffic demand. Time can be predicted. That is, according to the traffic condition prediction device 100, the accuracy of the required time prediction can be improved.

  The above-described traffic condition prediction device 100 further includes a traffic congestion prediction unit 127 that predicts traffic congestion based on the prediction result of the required time for each time zone by the required time prediction unit 126. By predicting traffic congestion based on the above-described highly accurate required time prediction result, the accuracy of traffic congestion prediction can be improved.

  The above-described traffic condition prediction device 100 includes a speed data acquisition unit 128 that acquires hourly speed data indicating the speed of a vehicle passing through the prediction target road for each time zone, and a traffic accident and traffic regulation condition on the prediction target road. And a traffic abnormal data acquisition unit 130 that acquires traffic abnormal data by time period for each of the time periods, wherein the use time band extracting unit 115 includes at least one of speed data by time period and traffic abnormal data by time period. In consideration of either of these, it is determined whether the traffic volume in each time zone included in the hourly traffic volume data matches the traffic demand in the corresponding time zone. If the traffic demand exceeds the traffic capacity, it is considered that the speed of the vehicle decreases due to congestion. When a traffic accident or a traffic regulation occurs, the traffic volume is considered to change irregularly. As described above, the speed data and the traffic abnormality data for each time zone are closely related to the traffic volume and the traffic demand situation. Therefore, when determining whether or not the traffic volume matches the traffic demand, By considering the speed data and the traffic abnormality data, the coincidence between the traffic volume and the traffic demand can be determined with high accuracy.

  Finally, a hardware configuration of the traffic condition prediction device 100 will be described with reference to FIG. The above-described traffic condition prediction device 100 may be physically configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

  In the following description, the term “apparatus” can be read as a circuit, a device, a unit, or the like. The hardware configuration of the traffic situation prediction device 100 may be configured to include one or more devices illustrated in the drawing, or may be configured to exclude some devices.

  Each function of the traffic condition prediction device 100 is configured such that the processor 1001 performs an operation by reading predetermined software (program) on hardware such as the processor 1001 and the memory 1002, and performs communication by the communication device 1004 and communication between the memory 1002 and the memory 1002. This is realized by controlling reading and / or writing of data in the storage 1003.

  The processor 1001 controls the entire computer by operating an operating system, for example. The processor 1001 may be configured by a central processing unit (CPU) including an interface with a peripheral device, a control device, an arithmetic device, a register, and the like. For example, the control function of the traffic demand prediction unit 119 and the like of the traffic situation prediction device 100 may be realized by the processor 1001.

  In addition, the processor 1001 reads a program (program code), a software module, and data from the storage 1003 and / or the communication device 1004 to the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least a part of the operation described in the above embodiment is used. For example, the control functions of the traffic demand prediction unit 119 and the like of the traffic condition prediction device 100 may be realized by a control program stored in the memory 1002 and operated by the processor 1001, and the other function blocks may be similarly realized. Is also good. Although it has been described that the various processes described above are executed by one processor 1001, the processes may be executed simultaneously or sequentially by two or more processors 1001. Processor 1001 may be implemented with one or more chips. Note that the program may be transmitted from a network via a telecommunication line.

  The memory 1002 is a computer-readable recording medium, and includes, for example, at least one of a ROM (Read Only Memory), an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), and a RAM (Random Access Memory). May be done. The memory 1002 may be called a register, a cache, a main memory (main storage device), or the like. The memory 1002 can store a program (program code), a software module, and the like that can be executed to execute the wireless communication method according to one embodiment of the present invention.

  The storage 1003 is a computer-readable recording medium such as an optical disk such as a CD-ROM (Compact Disc ROM), a hard disk drive, a flexible disk, and a magneto-optical disk (eg, a compact disk, a digital versatile disk, a Blu-ray). (Registered trademark) disk), a smart card, a flash memory (for example, a card, a stick, a key drive), a floppy (registered trademark) disk, and a magnetic strip. The storage 1003 may be called an auxiliary storage device. The storage medium described above may be, for example, a database including the memory 1002 and / or the storage 1003, a server, or any other suitable medium.

  The communication device 1004 is hardware (transmission / reception device) for performing communication between computers via a wired and / or wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, or the like.

  The input device 1005 is an input device that receives an external input (for example, a keyboard, a mouse, a microphone, a switch, a button, a sensor, and the like). The output device 1006 is an output device that performs output to the outside (for example, a display, a speaker, an LED lamp, and the like). Note that the input device 1005 and the output device 1006 may have an integrated configuration (for example, a touch panel).

  Each device such as the processor 1001 and the memory 1002 is connected by a bus 1007 for communicating information. The bus 1007 may be configured by a single bus, or may be configured by a different bus between the devices.

  The traffic condition prediction device 100 includes hardware such as a microprocessor, a digital signal processor (DSP), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array). The hardware may implement some or all of the functional blocks. For example, the processor 1001 may be implemented by at least one of these hardware.

  Although the present embodiment has been described in detail above, it is obvious to those skilled in the art that the present embodiment is not limited to the embodiment described in this specification. This embodiment can be implemented as a modified or changed embodiment without departing from the spirit and scope of the present invention defined by the description of the claims. Therefore, the description in this specification is for the purpose of illustration and description, and does not have any restrictive meaning to the present embodiment.

  Each aspect / embodiment described in this specification includes LTE (Long Term Evolution), LTE-A (LTE-Advanced), SUPER 3G, IMT-Advanced, 4G, 5G, FRA (Future Radio Access), W-CDMA. (Registered trademark), GSM (registered trademark), CDMA2000, Ultra Mobile Broad-band (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, UWB (Ultra-Wide) Band), Bluetooth (registered trademark), and other suitable systems, and / or an extended next-generation system based on these systems.

  The processing procedure, sequence, flowchart, and the like of each aspect / embodiment described in this specification may be interchanged as long as there is no inconsistency. For example, the methods described herein present elements of various steps in a sample order, and are not limited to the specific order presented.

  The input and output information and the like may be stored in a specific place (for example, a memory) or may be managed by a management table. Information that is input and output can be overwritten, updated, or added. The output information or the like may be deleted. The input information or the like may be transmitted to another device.

  The determination may be made based on a value (0 or 1) represented by one bit, a Boolean value (Boolean: true or false), or a comparison of numerical values (for example, a predetermined value). Value).

  Each aspect / embodiment described in this specification may be used alone, may be used in combination, or may be switched as the execution goes on. Further, the notification of the predetermined information (for example, the notification of “X”) is not limited to being explicitly performed, and is performed implicitly (for example, not performing the notification of the predetermined information). Is also good.

  Software, regardless of whether it is called software, firmware, middleware, microcode, a hardware description language, or any other name, instructions, instruction sets, codes, code segments, program codes, programs, subprograms, software modules , Applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, and the like.

  In addition, software, instructions, and the like may be transmitted and received via a transmission medium. For example, if the software uses a wired technology such as coaxial cable, fiber optic cable, twisted pair and digital subscriber line (DSL) and / or a wireless technology such as infrared, wireless and microwave, the website, server, or other When transmitted from a remote source, these wired and / or wireless technologies are included within the definition of transmission medium.

  The information, signals, etc. described herein may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc., that can be referred to throughout the above description are not limited to voltages, currents, electromagnetic waves, magnetic or magnetic particles, optical or photons, or any of these. May be represented by a combination of

  Note that terms described in this specification and / or terms necessary for understanding this specification may be replaced with terms having the same or similar meanings.

  Further, the information, parameters, and the like described in this specification may be represented by an absolute value, may be represented by a relative value from a predetermined value, or may be represented by another corresponding information. .

  The user terminal may be a mobile communication terminal, a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile subscriber station, an access terminal, It may also be called a mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable term.

  The terms "determining" and "determining" as used herein may encompass a wide variety of operations. "Determining", "determining" means, for example, calculating, computing, processing, deriving, investigating, looking up (e.g., a table, database or another Searching in a data structure), and ascertaining may be regarded as “determined” or “determined”. Also, “determining” and “deciding” include receiving (eg, receiving information), transmitting (eg, transmitting information), input (input), output (output), and access. (accessing) (for example, accessing data in a memory) may be regarded as “determined” or “determined”. In addition, `` judgment '' and `` decision '' means that resolving, selecting, selecting, establishing, establishing, comparing, etc. are considered as `` judgment '' and `` decided ''. May be included. In other words, “judgment” and “decision” may include deeming any operation as “judgment” and “determined”.

  The phrase "based on" as used herein does not mean "based solely on" unless stated otherwise. In other words, the phrase "based on" means both "based only on" and "based at least on."

  Where the designations "first," "second," and the like, are used herein, any reference to the element does not generally limit the quantity or order of the element. These designations may be used herein as a convenient way to distinguish between two or more elements. Thus, a reference to a first and second element does not mean that only two elements may be employed therein, or that the first element must somehow precede the second element.

  As long as “include”, “including”, and variations thereof, are used in the present description or claims, these terms are equivalent to the term “comprising” It is intended to be comprehensive. Further, it is intended that the term "or", as used herein or in the claims, not be the exclusive OR.

  In this specification, a plurality of devices is also included unless the context or the technology clearly indicates that only one device exists.

  Throughout this disclosure, the singular encompasses the plural unless the context clearly dictates otherwise.

  100: Traffic condition prediction device, 111: Learning population data acquisition unit, 113: Traffic volume data acquisition unit, 114: Traffic volume data storage unit, 115: Usage time zone extraction unit, 117: Traffic demand prediction model construction unit, 119 ··· Traffic demand prediction unit, 121 · Required time data acquisition unit, 123 · · · Required time prediction model construction unit, 126 · · · Required time prediction unit, 127 · Traffic congestion prediction unit, 128 · Speed data acquisition unit, 130 · Traffic abnormal data acquisition Department.

Claims (5)

A population data acquisition unit that acquires population data of a plurality of groups classified according to the position and attribute of a person;
A time zone traffic volume data acquisition unit that acquires hourly traffic volume data indicating a traffic volume, which is the number of vehicles passing through the prediction target road, for each time zone;
It is determined whether or not the traffic volume of each time zone included in the traffic volume data for each time zone matches the traffic demand indicating the number of vehicles attempting to pass through the road to be predicted in the corresponding time zone. A use time zone extraction unit that extracts only the traffic volume in the time zone that is being used as learning traffic volume data when constructing the prediction model;
Based on the learning traffic data and the population data for each group, a traffic demand prediction model construction unit that constructs a traffic demand prediction model that predicts traffic demand using population data as an explanatory variable,
A traffic condition prediction device comprising: a traffic demand prediction unit that predicts traffic demand of the road to be predicted based on the population data and the traffic demand prediction model for each of the groups.   The traffic condition prediction device according to claim 1, wherein the traffic demand prediction model construction unit selects the population data of a group having a high contribution to traffic demand on the road to be predicted and constructs the traffic demand prediction model. A required time data acquisition unit that acquires required time data by time zone indicating the required time of the vehicle that has passed through the prediction target road for each time zone,
Based on the traffic demand prediction result by the traffic demand prediction unit and the time zone-based required time data, a required time prediction model for predicting the required time by time zone using the predicted result of the traffic demand as an explanatory variable is constructed. Required time prediction model construction unit,
The traffic demand prediction result, which is predicted by the traffic demand prediction unit and used for predicting the required time for each time zone, and the time when passing through the prediction target road based on the required time prediction model. The traffic condition prediction device according to claim 1, further comprising a required time prediction unit that predicts a required time for each zone.   The traffic condition prediction device according to claim 3, further comprising a traffic congestion prediction unit that predicts traffic congestion based on a prediction result of the required time for each time zone by the required time prediction unit. A speed data acquisition unit that acquires hourly speed data indicating the speed of the vehicle that has passed through the prediction target road for each time zone,
A traffic abnormality data acquisition unit that acquires hourly traffic abnormality data indicating a traffic accident or traffic regulation situation on the prediction target road for each time zone,
The use time zone extraction unit considers at least one of the time zone-specific speed data and the time zone-specific traffic abnormal data, and the traffic volume of each time zone included in the time zone-specific traffic volume data is: The traffic condition prediction device according to any one of claims 1 to 4, wherein it is determined whether the traffic demand matches the traffic demand in a corresponding time zone.

Images