JP6816591B2 - Information provision system, information provision method, and program - Google Patents

Description

The present invention relates to an information providing system, an information providing method, and a program, and in particular, an information providing system, an information providing method, and a program for providing information on the availability of a parking lot of a facility installed on a road. Regarding.

A system for guiding the congestion status of service facilities such as service areas and parking areas is known on motorways such as expressways and toll roads. For example, in Patent Document 1, based on the parking lot information of each service facility on the expressway, which is broadcast by FM (Frequency Modulation) multiplex broadcasting, the recent congestion of the parking lot of the service facility in front of the vehicle in the traveling direction A navigation device that presents the situation is disclosed.

As a related technique, Patent Document 2 discloses a technique for changing the reservation when the estimated time of arrival is changed after the reservation of the parking lot. Patent Document 3 discloses a technique for estimating the arrival time at a destination based on a deceleration factor located in each area. Patent Document 4 discloses a technique for estimating the time required to reach a destination based on the driver's preferred driving speed. Further, as another related technique, Non-Patent Document 1 and Non-Patent Document 2 disclose a heterogeneous mixture learning technique for generating a prediction model for each group having the same pattern and regularity of data. ..

Japanese Patent No. 6054273 Japanese Unexamined Patent Publication No. 2006-172061 Japanese Unexamined Patent Publication No. 2009-210513 Japanese Unexamined Patent Publication No. 2002-31285

Ryohei Fujimaki, Satoshi Morinaga, "State-of-the-art Data Mining in the Big Data Era", NEC Technical Report, Vol.65, No.2, 2012, p.81-85 Riki Eto, et al., "Fully-Automatic Bayesian Piecewise Sparse Linear Models", Proceedings of the 17th International Conference on Artificial Intelligence and Statistics (AISTATS), 2014, p.238-246

The technique described in Patent Document 1 described above presents a recent congestion situation of a parking lot of a service facility. However, the congestion status of service facilities changes from moment to moment due to the congestion status of roads and other factors. Therefore, even if the parking lot of the service facility is not congested at this time, there is a possibility that the vehicle cannot be parked due to the congestion when the vehicle arrives at the service facility. In this case, even if the congestion status is presented, the user cannot effectively utilize the presented congestion status when making a usage plan for the service facility, for example, a break or a meal after several hours. ..

An object of the present invention is to provide an information providing system, an information providing method, and a program capable of solving the above-mentioned problems and presenting accurate information on the availability of parking lots installed along a road.

The information providing system according to one aspect of the present invention is installed so as to be able to enter and exit along the road, which exists in the traveling direction of the target vehicle on the road, based on the traffic condition at each point on the road. A vehicle that requires the use of the parking lot at the predicted arrival time based on the arrival time prediction means for predicting the arrival time of the target vehicle to the parking lot and the traffic condition at each point on the road. Based on the demand forecasting means for predicting the demand, which is the number of vehicles, and the predicted demand, the vacancy status of the parking lot at the predicted arrival time is determined, and parking information including the determination result of the vacancy status is generated. The parking information generating means for outputting to the target vehicle is provided.

The information providing method in one aspect of the present invention is installed so as to be accessible to and from the road along the road existing in the traveling direction of the target vehicle on the road based on the traffic condition at each point on the road. Predict the arrival time of the target vehicle to the parking lot, and predict the demand for the number of vehicles that need to use the parking lot at the predicted arrival time based on the traffic conditions at each point on the road. Then, based on the predicted demand, the vacancy status of the parking lot at the predicted arrival time is determined, parking information including the determination result of the vacancy status is generated, and the parking information is output to the target vehicle.

The information providing method in one aspect of the present invention allows the computer to enter and exit the road along the road, which exists in the traveling direction of the target vehicle on the road, based on the traffic condition at each point on the road. It is the number of vehicles that need to use the parking lot at the predicted arrival time based on the traffic conditions at each point on the road by predicting the arrival time of the target vehicle to the parking lot installed in. Processing that predicts demand, determines the vacancy status of the parking lot at the predicted arrival time based on the predicted demand, generates parking information including the determination result of the vacancy status, and outputs it to the target vehicle. To execute.

The effect of the present invention is to be able to present accurate information on the availability of parking lots installed along the road.

It is a figure which shows the example of the road in 1st Embodiment. It is a block diagram which shows the structure of 1st Embodiment. It is a figure which shows the example of the traffic state information in 1st Embodiment. It is a figure which shows the example of the traffic prediction model in 1st Embodiment. It is a figure which shows the example of the facility information in 1st Embodiment. It is a figure which shows the example of the demand information in 1st Embodiment. It is a figure which shows the example of the traffic prediction model in 1st Embodiment. It is a block diagram which shows the structure of the parking information providing apparatus 100 realized by the computer in 1st Embodiment. It is a flowchart which shows the learning process in 1st Embodiment. It is a flowchart which shows the parking information provision processing in 1st Embodiment. It is a figure which shows the example of the parking information request in 1st Embodiment. It is a figure which shows the example of the prediction result of the arrival time in 1st Embodiment. It is a figure which shows the example of the demand prediction result and the determination result of the availability of a parking lot in the 1st Embodiment. It is a figure which shows the example of the parking information in 1st Embodiment. It is a figure which shows the calculation example of the waiting time in 1st Embodiment. It is a figure which shows another example of parking information in 1st Embodiment. It is a block diagram which shows the characteristic structure of 1st Embodiment. It is a block diagram which shows the structure of the 2nd Embodiment. It is a figure which shows the example of the reservation information in the 2nd Embodiment. It is a figure which shows the example of the allocation information in 2nd Embodiment. It is a flowchart which shows parking information provision and reservation processing in 2nd Embodiment. It is a figure which shows the example of the demand prediction result, the determination result of the availability of a parking lot, and the determination result of whether or not a parking lot can be reserved in the second embodiment. It is a figure which shows the example of the parking information in 2nd Embodiment. It is a flowchart which shows the reservation control processing in 2nd Embodiment.

The embodiment for carrying out the invention will be described in detail with reference to the drawings. In each drawing and each embodiment described in the specification, the same reference numerals are given to the same components, and the description thereof will be omitted as appropriate.

(First Embodiment)
The first embodiment will be described.

First, the road and the traffic condition in the first embodiment will be described.

FIG. 1 is a diagram showing an example of a road in the first embodiment. In the first embodiment, the road is a road for automobiles such as a highway and a toll road. Along the road, service facilities such as service areas and parking areas for providing various services to drivers and passengers of vehicles using the road (hereinafter, also referred to as road users) (hereinafter, simply referred to as road users). , Also referred to as facility) will be installed. At each service facility, a parking lot is set up to park the vehicles of users who stop by the facility. The parking lot will be provided with an entrance from the road and an exit to the road so that access to and from the road is possible.

In the example of FIG. 1, the service facility Si (i is an integer from 1 to M, M is the number of service facilities) is installed on the road.

Further, in the first embodiment, the value of the index indicating the traffic condition is measured at a plurality of points on the road. Flow velocity, speed, and vehicle density are used as indicators. The flow velocity indicates, for example, the number of vehicles passing through the point (number of passing vehicles) per unit time. The speed indicates, for example, the average of the speeds of a plurality of vehicles at a point. The vehicle density indicates, for example, the ratio of each vehicle spatially occupying a predetermined section including a point (space occupancy) or the ratio of each vehicle occupying a point temporally (time occupancy). .. It is known that there is a correlation between flow velocity, velocity, and vehicle density, and that any of these indicators can be used to infer other indicators.

In the example of FIG. 1, the values of these indexes are measured at each of the points Xj (j is an integer from 1 to N and N is the number of points).

In FIG. 1, the road is a road having a single route for simplification, but the road is not limited to this, and the road may form a road network by branching or merging.

First, the configuration of the first embodiment will be described. FIG. 2 is a block diagram showing the configuration of the first embodiment. Referring to FIG. 2, the information providing system 1 includes a parking information providing device 100 and a terminal device 200. The terminal device 200 is, for example, a navigation terminal mounted on a vehicle, a smartphone or a mobile phone of a user in the vehicle, or the like. The parking information providing device 100 and the terminal device 200 are connected by a network or the like.

The parking information providing device 100 includes a road information storage unit 111, a traffic state storage unit 112, a traffic prediction model learning unit 113, a traffic prediction model storage unit 114, a facility information storage unit 115, a demand information storage unit 116, and a demand prediction model learning unit. 117 and demand forecast model storage unit 118 are included. The parking information providing device 100 further includes a request receiving unit 119, an arrival time forecasting unit 120, a demand forecasting unit 121, and a parking information generating unit 122.

The road information storage unit 111 stores road information indicating a road map, each point, and the position of each service facility.

The traffic state storage unit 112 stores the traffic state information. The traffic condition information shows the history of the measured values of the traffic condition at each point on the road. Traffic conditions are collected, for example, by a traffic condition collector (not shown). The traffic condition collecting device collects traffic conditions at predetermined collection intervals from sensors installed at each point on the road, for example.

FIG. 3 is a diagram showing an example of traffic condition information in the first embodiment. In the example of FIG. 3, the traffic conditions (flow rate, speed, and vehicle density) at each point Xj on the road of FIG. 1 are collected.

The traffic prediction model learning unit 113 generates (learns) a traffic prediction model based on the traffic state information stored in the traffic state storage unit 112. The traffic prediction model is a model for predicting the traffic condition of a prediction target point based on the traffic condition of each point. The traffic prediction model learning unit 113 generates a traffic prediction model by using, for example, a machine learning technique. In this case, the traffic prediction model may be generated by using the heterogeneous mixture learning technique disclosed in Non-Patent Documents 1 and 2. Further, the traffic prediction model may be a general time series model such as a linear regression model, an autoregressive model, or an autoregressive moving average model. The traffic prediction model is generated for one or more of the above-mentioned indicators (flow velocity, speed, vehicle density) representing the traffic condition.

In the first embodiment, as a traffic prediction model, for example, the vehicle density at the current time of each point is set in the explanatory variable, and the vehicle density at the prediction target time of the prediction target point is set in the objective variable. Use a linear function.

Here, D _j (t) is the vehicle density at the current time t at the point Xj. Further, _{Dest_k} (t + T) is a predicted value of the vehicle density at time t + T at the point Xk (k is an integer from 1 to N). α _jk is a coefficient indicating the magnitude of the relationship between the vehicle density D _j (t) at the point Xj and the vehicle density D _k (t + T) at the point Xk.

FIG. 4 is a diagram showing an example of a traffic prediction model according to the first embodiment. In the example of FIG. 4, the prediction target time is 0.5 hours later (T = 0.5h (hour)), 1.0 hour later (T = 1.0h), and 1.5 hours later (T) for each point. = 1.5h), 2.0 hours later (T = 2.0h), ... A traffic prediction model is generated.

As the traffic prediction model, not only a linear function such as the equation 1 may be used, but an arbitrary function in which the traffic state at each point is set as an explanatory variable may be used. Further, a plurality of traffic prediction models may be generated for the same prediction target point and prediction target time. In this case, even if these traffic prediction models are used properly for each situation related to the prediction target time and the prediction target point, such as the weather of the prediction target point at the prediction target time, the presence or absence of surrounding events, the day of the week and the time zone of the prediction target time, etc. Good. In addition, variables representing these situations may be included in the explanatory variables.

The traffic prediction model storage unit 114 stores the traffic prediction model generated by the traffic prediction model learning unit 113.

The facility information storage unit 115 stores facility information. The facility information indicates the type of each service facility, the function related to the service provided by each service facility (hereinafter, also referred to as the service function), and the number of parking lots of each service facility (total number of parking slots).

FIG. 5 is a diagram showing an example of facility information in the first embodiment. In the example of FIG. 5, the presence or absence of a toilet, a shop, a restaurant, and a gas station is set as a service function of each service facility. Further, as the service function provided by each service facility, the presence or absence of other functions such as a dog run and accommodation facilities may be set.

The demand information storage unit 116 stores the demand information. The demand information shows the history of measured values of parking lot demand at each service facility. The demand for a parking lot is the number of vehicles that need to use the parking lot (hereinafter, also referred to as the number of vehicles required to use the parking lot). For example, the number of vehicles parked in each parking lot of the parking lot and the said number of vehicles. It is obtained from the total value of the number of vehicles waiting to be parked in the parking lot. The demand for the parking lot is collected, for example, by a demand collecting device (not shown). The demand collection device collects measured values of the number of parked vehicles and parking waiting vehicles at predetermined collection intervals from sensors installed in each parking frame or passage in the parking lot, for example, and the parking lot. Calculate the demand for. In addition, the demand collection device collects the measured values of the number of vehicles passing through the entrance and exit from the sensors installed at the entrance and exit of the parking lot, and calculates the demand for the parking lot from the difference between them. You may.

FIG. 6 is a diagram showing an example of demand information in the first embodiment. In the example of FIG. 6, the demand (number of vehicles required to use) of the parking lot at each service facility Si on the road of FIG. 1 is collected.

The demand forecast model learning unit 117 generates (learns) a demand forecast model based on the traffic state information stored in the traffic state storage unit 112 and the demand information stored in the demand information storage unit 116. The demand forecast model is a model for forecasting the demand for parking lots of service facilities based on the traffic conditions at each point. The demand forecast model learning unit 117 generates a demand forecast model by using, for example, a machine learning technique. In this case, the demand forecast model may be generated by using the heterogeneous mixture learning technique disclosed in Non-Patent Documents 1 and 2. Further, the demand forecast model may be a general time series model such as a linear regression model, an autoregressive model, or an autoregressive moving average model.

In the first embodiment, as the demand forecast model, for example, the vehicle density at the current time of each point is set in the explanatory variable, and the demand (number of vehicles requested to use) at the forecast target time of the forecast target facility is set in the objective variable. Use a linear function like the two equations.

Here, _{Rest_i} (t + T) is a predicted value of the demand at time t + T in the parking lot of the service facility Si. β _ji is a coefficient indicating the magnitude of the relationship between the vehicle density D _j (t) at the point Xj and the demand R _i (t + T) for the parking lot of the service facility Si.

FIG. 7 is a diagram showing an example of a traffic prediction model in the first embodiment. In the example of FIG. 7, for each service facility, the forecast target time is 0.5 hours later (T = 0.5h (hour)), 1.0 hour later (T = 1.0h), and 1.5 hours later (T = 1.0h). T = 1.5h), 2.0 hours later (T = 2.0h), ..., A demand forecast model is generated.

As the demand forecast model, not only a linear function such as Equation 2 but also an arbitrary function in which the traffic state at each point is set as an explanatory variable may be used. Further, a plurality of demand forecast models may be generated for the same forecast target facility and forecast target time. In this case, these demand forecast models may be used properly according to the forecast target time and the situation related to the forecast target facility, such as the weather of the forecast target facility at the forecast target time, the day and time zone of the forecast target time, and the like. In addition, variables representing these situations may be included in the explanatory variables. Further, variables representing the presence or absence of various service functions of the facility to be predicted and variables representing the number of parking lots of the facility may be included in the explanatory variables.

The demand forecast model storage unit 118 stores the demand forecast model generated by the demand forecast model learning unit 117.

The request receiving unit 119 receives a parking information request for requesting parking information from the terminal device 200 of the vehicle on the road. Parking information is information indicating the availability of parking lots of service facilities.

The arrival time prediction unit 120 uses the traffic prediction model stored in the traffic prediction model storage unit 114 to enter the parking lot of each service facility of the vehicle from which the parking information request is transmitted (hereinafter, also referred to as a target vehicle). Predict the arrival time.

The demand forecasting unit 121 uses the demand forecasting model stored in the demand forecasting model storage unit 118 to use the demand forecasting model to arrive at the parking lot of each service facility at the predicted arrival time (hereinafter, also referred to as the predicted arrival time). Forecast the demand for.

The parking information generation unit 122 determines the availability of the parking lot at the predicted arrival time of each service facility at the parking lot based on the demand predicted by the demand forecasting unit 121 (hereinafter, also referred to as the predicted demand). The parking information generation unit 122 generates parking information including a determination result of the availability of the parking lot and outputs (transmits) it to the terminal device 200 of the target vehicle.

The parking information providing device 100 may be a computer that includes a CPU (Central Processing Unit) and a storage medium that stores a program, and operates by control based on the program.

FIG. 8 is a block diagram showing a configuration of a parking information providing device 100 realized by a computer in the first embodiment.

Referring to FIG. 8, the parking information providing device 100 includes a CPU 101, a storage device 102 (storage medium), an input / output device 103, and a communication device 104. The CPU 101 is a program instruction (Instruction) for realizing the traffic forecast model learning unit 113, the demand forecast model learning unit 117, the request reception unit 119, the arrival time prediction unit 120, the demand forecast unit 121, and the parking information generation unit 122. To execute. The storage device 102 is, for example, a hard disk, a memory, or the like, and includes a road information storage unit 111, a traffic state storage unit 112, a traffic prediction model storage unit 114, a facility information storage unit 115, a demand information storage unit 116, and a demand prediction model. Stores the data of the storage unit 118. The input / output device 103 is, for example, a keyboard, a display, or the like, and receives a learning execution instruction from an administrator or the like. The communication device 104 receives the parking information request from the terminal device 200 and transmits the parking information to the terminal device 200.

Further, a part or all of each component of the parking information providing device 100 may be realized by a general-purpose or dedicated circuitry, a processor, or a combination thereof. These circuits and processors may be composed of a single chip, or may be composed of a plurality of chips connected via a bus. Further, a part or all of the parking information providing device 100 may be realized by a combination of the above-mentioned circuit or the like and a program.

When a part or all of each component of the parking information providing device 100 is realized by a plurality of information processing devices and circuits, the plurality of information processing devices and circuits may be centrally arranged. It may be distributed. For example, the information processing device, the circuit, and the like may be realized as a form in which each of the client and server system, the cloud computing system, and the like is connected via a communication network.

Next, the operation of the first embodiment will be described.

<Learning process>
First, the learning process will be described.

FIG. 9 is a flowchart showing the learning process in the first embodiment.

Here, the road information regarding the road of FIG. 1, the traffic condition information of FIG. 3, and the demand information of FIG. 6 are stored in the road information storage unit 111, the traffic condition storage unit 112, and the demand information storage unit 116, respectively. Suppose there is.

First, the traffic prediction model learning unit 113 of the parking information providing device 100 generates (learns) a traffic prediction model based on the history of traffic conditions at each point (step S101). The traffic prediction model learning unit 113 stores the generated traffic prediction model in the traffic prediction model storage unit 114.

For example, the traffic prediction model learning unit 113 generates a traffic prediction model represented by the equation 1 as shown in FIG. 4 based on the traffic condition information of FIG.

Next, the demand forecast model learning unit 117 generates (learns) a demand forecast model based on the history of traffic conditions at each point and the history of demand for parking lots of each service facility (step S102). The demand forecast model learning unit 117 stores the generated demand forecast model in the demand forecast model storage unit 118.

For example, the traffic forecast model learning unit 113 generates a demand forecast model represented by the equation 2 as shown in FIG. 7 based on the traffic condition information of FIG. 3 and the demand information of FIG.

<Parking information provision processing>
Next, the parking information providing process will be described.

Here, the traffic forecast model of FIG. 4, the facility information of FIG. 5, and the demand forecast model of FIG. 7 are transferred to the traffic forecast model storage unit 114, the facility information storage unit 115, and the demand forecast model storage unit 118, respectively. Suppose it is saved.

FIG. 10 is a flowchart showing the parking information providing process in the first embodiment.

First, the terminal device 200 of the vehicle (target vehicle) transmits a parking information request to the parking information providing device 100 (step S251). Here, the parking information request includes the identifier of the vehicle and the requirements of the service facility for which the parking information should be provided. As the requirement conditions, for example, various service functions provided by the service facility and the required time from the current location to the parking lot are set.

FIG. 11 is a diagram showing an example of a parking information request in the first embodiment. For example, the terminal device 200 of the vehicle "CAR1" traveling at the point "X1" transmits a parking information request as shown in FIG. 11 at the time "09:00".

The request receiving unit 119 of the parking information providing device 100 receives the parking information request (step 201). Based on the road information and the facility information, the parking information generation unit 122 selects a service facility that satisfies the service function specified in the required condition among the service facilities existing in front of the target vehicle in the traveling direction on the road. Extract (step S202).

For example, the parking information generation unit 122 satisfies the condition of the service function of FIG. 11 among the service facilities "S1" to "Sm" existing in the traveling direction of the target vehicle "CAR1" based on the facility information of FIG. The service facilities "S2", "S4", and "S6" are extracted.

The parking information generation unit 122 instructs the arrival time prediction unit 120 to predict the arrival time of each service facility extracted in step S202 to the parking lot. The arrival time prediction unit 120 predicts the arrival time at the parking lot of each service facility by using the traffic prediction model (step S203).

Here, the arrival time prediction unit 120 applies the measured value of the vehicle density at the current time of each point to each traffic prediction model, predicts the vehicle density at each prediction target time at each point, and obtains the predicted vehicle density. Based on this, the speed at each prediction target time at each point is predicted. The arrival time prediction unit 120 divides the road from the current location of the target vehicle to each service facility at the prediction target points of each traffic prediction model. The arrival time prediction unit 120 predicts the arrival time at the parking lot of each service facility by summing the predicted travel time values calculated from the speed prediction values of the divided sections. Here, as the predicted value of the speed of each section, the predicted value of the speed of the point at the arrival time at the starting point of the section is used.

If the arrival time prediction unit 120 can predict the arrival time of each service facility at the parking lot, the traffic such as using a preset average speed or average required time between the current location of the target vehicle and each service facility, etc. The arrival time may be predicted by a method other than the method using the prediction model.

FIG. 12 is a diagram showing an example of a prediction result of the arrival time in the first embodiment. For example, the arrival time prediction unit 120 predicts the arrival time of the service facilities “S2”, “S4”, and “S6” to the parking lot as shown in FIG. 12 by using each traffic prediction model of FIG.

Based on the estimated arrival time, the parking information generation unit 122 extracts the service facility that satisfies the required time specified in the requirement condition from the service facilities extracted in step S202 (step S204).

For example, the parking information generation unit 122 has the service facility “S2”, which satisfies the condition of the required time of FIG. 11 among the service facilities “S2”, “S4”, and “S6” based on the estimated arrival time of FIG. Extract "S4".

The parking information generation unit 122 instructs the demand forecasting unit 121 to forecast the demand of each service facility extracted in step S204. The demand forecasting unit 121 predicts the demand of the parking lot at the predicted arrival time of each service facility to the parking lot by using the demand forecasting model (step S205).

Here, the demand forecasting unit 121 applies the measured value of the vehicle density at the current time of each point to the demand forecasting model corresponding to the predicted arrival time, and predicts the demand at the predicted arrival time to the parking lot of each service facility. To do.

FIG. 13 is a diagram showing an example of a demand prediction result and a parking lot availability determination result in the first embodiment. For example, the arrival time forecasting unit 120 uses the demand forecasting model corresponding to the predicted arrival time to the parking lot of each service facility “S2” and “S4” among the demand forecasting models of FIG. 7, and demand (usage request). The number of vehicles) is predicted as shown in FIG.

The parking information generation unit 122 determines the availability of the parking lot at the predicted arrival time based on the predicted demand for the parking lot of each service facility extracted in step S204 (step S206). Here, the parking information generation unit 122 determines that the vacancy status is "vacant" when the number of vehicles requested to be used indicated by the predicted demand is less than the number of accommodations in the parking lot indicated by the facility information.

For example, the parking information generation unit 122 determines the availability of parking lots of the service facilities "S2" and "S4" as shown in FIG. 13 based on the number of parking lots accommodated in the facility information of FIG.

The parking information generation unit 122 generates parking information including a determination result of the availability of the parking lot (step S207). The parking information generation unit 122 transmits the generated parking information to the terminal device 200 of the target vehicle (step S208).

FIG. 14 is a diagram showing an example of parking information in the first embodiment. In the parking information of FIG. 14, the judgment result (predicted vacancy status) of the vacancy status of the parking lots of the service facilities "S2" and "S4" is "full" (no vacancy) and "vacant" (vacant), respectively. It is shown. For example, the parking information generation unit 122 generates parking information as shown in FIG. 14 and transmits it to the target vehicle “CAR1”.

When the terminal device 200 of the target vehicle receives the parking information (step S252), the terminal device 200 presents (displays) the parking information to the user (step S253).

For example, the terminal device 200 of the target vehicle "CAR1" presents the parking information of FIG. 14 to the user.

The parking information generation unit 122 may include the waiting time from the estimated arrival time of the parking lot of the service facility whose vacancy status is determined to be "no vacancy" in step S206 in the parking information. In this case, for example, the parking information generation unit 122 causes the demand forecasting unit 121 to predict the demand for the parking lot at each time after the predicted arrival time by using the demand forecasting model. Then, the parking information generation unit 122 calculates the waiting time by determining the time when the number of vehicles requested to be used indicated by the predicted demand is less than the number of vehicles accommodated in the parking lot as the time when parking is possible.

FIG. 15 is a diagram showing a calculation example of the waiting time in the first embodiment. For example, the parking information generation unit 122 calculates the waiting time “1.0 h” for the service facility “S2” by using the number of vehicles requested to use after the estimated arrival time “10:00” as shown in FIG. ..

The parking information generation unit 122 may calculate the waiting time by another method as long as the waiting time from the estimated arrival time of the parking lot can be calculated. For example, the parking information generation unit 122 predicts the number of waiting vehicles by subtracting the number of vehicles accommodated in the parking lot from the number of vehicles requested to be used indicated by the predicted demand at the estimated arrival time, and based on the predicted number of waiting vehicles. The waiting time may be calculated. In this case, the waiting time is calculated, for example, by multiplying the predicted number of waiting vehicles and the average parking time.

FIG. 16 is a diagram showing another example of parking information in the first embodiment. In the parking information of FIG. 16, the waiting time is shown for the service facility “S2” whose vacancy status is “no vacancy”. For example, the parking information generation unit 122 generates parking information including a waiting time as shown in FIG. 16 and transmits it to the target vehicle “CAR1”.

As described above, the operation of the first embodiment is completed.

Next, the characteristic configuration of the first embodiment will be described.

FIG. 17 is a block diagram showing a characteristic configuration of the first embodiment. Referring to FIG. 17, the information providing system 1 includes an arrival time forecasting unit 120, a demand forecasting unit 121, and a parking information generating unit 122. The arrival time prediction unit 120 predicts the arrival time of the target vehicle on the road to the parking lot of the facility on the road based on the traffic condition at each point on the road. The demand forecasting unit 121 predicts the demand, which is the number of vehicles that require the use of the parking lot of the facility at the predicted arrival time, based on the traffic condition at each point on the road. The parking information generation unit 122 determines the vacancy status of the parking lot of the facility at the predicted arrival time based on the predicted demand, generates parking information including the determination result of the vacancy status, and outputs the parking information to the target vehicle.

Next, the effect of the first embodiment will be described.

According to the first embodiment, accurate information on the availability of parking lots installed along the road can be presented. The reason is that the parking information generation unit 122 determines the availability of the parking lot at the predicted arrival time based on the predicted demand of the parking lot at the predicted arrival time of the target vehicle to the parking lot, and obtains the parking information including the judgment result. This is to generate. As a result, the user can grasp the accurate availability at the time of arrival at the parking lot of the service facility, etc. from the presented parking information, so that the parking information can be used to make a usage plan of the service facility, etc. Can be used effectively.

Further, according to the first embodiment, even when the vacancy status of the parking lot is "no vacancy", whether the user should use the service facility or the like having the parking lot after waiting for the vacancy of the parking lot. Can be judged. The reason is that the parking information generation unit 122 predicts the waiting time from the predicted arrival time of the parking lot when the determination result of the vacancy status of the parking lot is "no vacancy", and determines the predicted waiting time. This is to generate parking information including.

In the first embodiment, a case where the parking lot to be determined for availability is a parking lot of a service facility such as a service area or a parking area installed along a road for automobiles has been described as an example. However, the parking lot is not limited to this, and the parking lot to be determined for availability may be any parking lot such as a parking lot of a commercial facility, a leisure facility, or a public facility as long as it is a parking lot installed along the road.

Further, in the first embodiment, the parking information generation unit 122 determines "no vacancy" or "vacancy" as the vacancy status of the parking lot. Not limited to this, the parking information generation unit 122 may determine the degree of congestion as the availability of the parking lot. In this case, the parking information generation unit 122 determines, for example, "vacant (congested)" if the predicted demand for the parking lot is less than the number of cars accommodated in the parking lot and the predicted demand is equal to or higher than the predetermined congestion determination threshold value. If it is less than the congestion determination threshold value of, it may be determined that there is a vacancy (no congestion).

(Second Embodiment)
Next, the second embodiment will be described. The second embodiment differs from the first embodiment in that the parking lot is reserved based on the predicted demand for the parking lot of the service facility.

It is desirable for the user to be able to reserve a parking lot in the parking lot in order to park more reliably even if the parking lot is vacant at the estimated arrival time. On the other hand, for a business operator operating a service facility, if a parking lot is reserved when the parking lot is crowded, vehicles other than the reserved vehicle will reserve the parking lot during the reserved parking time. It cannot be used, and the operational efficiency of the parking lot is reduced.

Therefore, in the second embodiment, when the vacant state of the parking lot is "vacant" (the predicted demand is less than the capacity of the parking lot), the parking information providing device 100 is not congested (the parking lot is not congested). When the predicted demand is less than the predetermined reservation determination threshold value), the parking lot reservation is accepted from the terminal device 200.

In the second embodiment, reservations are made for the number of parking slots equal to or less than the maximum number of reservations among all the parking slots (parking slots for the main number of parking lots) of the service facility. The parking slot for reservation is not fixed, and at the reservation start time, the parking slot in which the vehicle is not detected (not parked) is assigned to the reserved vehicle. Vehicles that have not been reserved can park in the parking lot that is not assigned to the reserved vehicle.

First, the configuration of the second embodiment will be described. FIG. 18 is a block diagram showing the configuration of the second embodiment. Referring to FIG. 18, the information providing system 1 in the second embodiment includes the components of the information providing system 1 in the first embodiment (FIG. 2), the parking frame control device 300, the vehicle sensor 400, and the like. And the display device 500 is included. The parking frame control device 300 is arranged for each service facility. The vehicle sensor 400 and the display device 500 are arranged for each parking frame of the parking lot of each service facility. The parking information providing device 100 and the parking frame control device 300 are connected by a network or the like. Further, the parking frame control device 300, the vehicle sensor 400, and the display device 500 are also connected by a network or the like.

Further, the parking information providing device 100 in the second embodiment is a component of the parking information providing device 100 in the first embodiment (FIG. 2), and further, a reservation management unit 124 and a reservation information storage unit 123. including.

The parking information generation unit 122 determines whether or not the parking lot can be reserved, in addition to determining the availability at the estimated time of arrival at the parking lot. The parking information generation unit 122 generates parking information including a determination result of the availability of the parking lot and a determination result of whether or not the reservation is possible, and outputs the parking information to the terminal device 200 of the target vehicle.

The request receiving unit 119 receives a reservation request for a reservable parking lot in the parking information in addition to the parking information request from the terminal device 200.

The reservation information storage unit 123 stores the reservation information. The reservation information indicates the reservation status of the parking lot of each service facility.

FIG. 19 is a diagram showing an example of reservation information in the second embodiment. In the reservation information of FIG. 19, the identifier of the reserved vehicle (hereinafter, also referred to as the reserved vehicle), the reservation start time, and the reservation end time are associated with the reservation status of the parking lot of each service facility. In addition, the reservation information further includes the number of reservations at each time.

The reservation management unit 124 reserves the parking lot (updates the reservation information) in response to the reservation request from the terminal device 200 of the target vehicle. Further, the reservation management unit 124 transmits a parking frame control request to the parking frame control device 300 of the service facility based on the reservation information.

The parking frame control device 300 includes an allocation information storage unit 311 and a control unit 312.

The allocation information storage unit 311 stores the allocation information. The allocation information indicates the allocation status of the parking space for the reserved vehicle.

FIG. 20 is a diagram showing an example of allocation information in the second embodiment. In the allocation information of FIG. 20, the identifier of the parking frame, the identifier of the reserved vehicle to which the parking frame is assigned, the reservation start time, and the reservation end time are associated with each other.

When the control unit 312 receives the parking frame control request, the parking allocation to the reserved vehicle is based on the vehicle detection status acquired from the vehicle sensor 400 of each parking frame and the allocation information stored in the allocation information storage unit 311. Determine the frame. The control unit 312 causes the determined parking frame display device 500 to display that the parking frame is reserved (allocated to the reserved vehicle).

The vehicle sensor 400 is, for example, an optical sensor that detects whether or not a vehicle is parked in a parking frame.

The display device 500 is, for example, an electric lamp such as an LED (Light Emitting Diode) or an incandescent light bulb, and displays so that the user can identify that the parking frame is reserved. Further, the display device 500 may be a display device. When the display device 500 is an electric lamp, one or more electric lamps may be installed along the parking frame, or may be installed on the road surface in the parking frame or in the upper space of the parking frame. When the display device 500 is a display device, the display device may be installed along the parking frame, or may be installed on the road surface in the parking frame or in the upper space of the parking frame.

Next, the operation of the second embodiment will be described.

<Parking information provision and reservation processing>
First, parking information provision and reservation processing will be described.

Here, the traffic forecast model of FIG. 4, the facility information of FIG. 5, and the demand forecast model of FIG. 7 are transferred to the traffic forecast model storage unit 114, the facility information storage unit 115, and the demand forecast model storage unit 118, respectively. Suppose it is saved. Further, it is assumed that the reservation information (before update) in FIG. 19 and the allocation information (before update) in FIG. 20 are stored in the reservation information storage unit 123 and the allocation information storage unit 311, respectively.

FIG. 21 is a flowchart showing parking information provision and reservation processing in the second embodiment.

Here, the process from the transmission of the parking information request to the determination of the availability of the parking lot (S351, steps S301 to S306) is the same as the parking information providing process (S251, steps S201 to S206) in the first embodiment. ..

For example, the terminal device 200 of the vehicle "CAR1" traveling at the point "X1" transmits a parking information request as shown in FIG. 11 at the time "09:00". The arrival time prediction unit 120 uses each traffic prediction model of FIG. 4 to predict the arrival time of the service facilities “S2”, “S4”, and “S6” at the parking lot as shown in FIG.

FIG. 22 is a diagram showing an example of a demand prediction result, a parking lot availability determination result, and a parking lot reservation availability determination result in the second embodiment.

The arrival time forecasting unit 120 uses the demand forecasting model corresponding to the predicted arrival time to the parking lot of each service facility "S2" and "S4" among the demand forecasting models of FIG. 7, and demand (number of vehicles requested to be used). ) Is predicted as shown in FIG. The parking information generation unit 122 determines the availability of parking lots of the service facilities "S2" and "S4" as shown in FIG. 22 based on the number of parking lots accommodated in the facility information of FIG.

Next, the parking information generation unit 122 extracts the service facility whose vacancy status determination result is "vacant" from the service facilities extracted in step S304 (step S307).

The parking information generation unit 122 determines whether or not the parking lot of each service facility extracted in step S307 can be reserved at the predicted arrival time based on the predicted demand and the reservation information (step S308).

Here, in the parking information generation unit 122, for example, the number of vehicles requested to be used indicated by the predicted demand is less than the predetermined reservation determination threshold value, and each of the reservation information is from the predicted arrival time to the elapsed parking time. If the number of reservations at the time is less than the predetermined maximum number of reservations, it is determined that reservations are possible. For the reservation determination threshold and the maximum number of reservations, a value equal to or less than the number of cars accommodated in the parking lot (ratio to the number of cars accommodated, etc.) is used. Further, as the parking time, for example, a predetermined reserved time is used. As the parking time, the average parking time or the required parking time obtained from the target vehicle in advance may be used.

For example, it is assumed that the reservation determination threshold is "90%" of the parking lot capacity, the maximum reservation number is "10%" of the parking lot capacity, and the reservation time is "0.5h". In this case, the parking information generation unit 122 uses the number of parking lots accommodated in the facility information of FIG. 5 and the reservation information (before update) of FIG. 19 to obtain the parking lots of the service facilities "S2" and "S4". Whether or not a reservation can be made is determined as shown in FIG.

The parking information generation unit 122 generates parking information including the availability of the parking lot and the determination result of whether or not the parking lot can be reserved (step S309). The parking information generation unit 122 transmits the generated parking information to the terminal device 200 of the target vehicle (step S310).

FIG. 23 is a diagram showing an example of parking information in the second embodiment. In the parking information of FIG. 22, the determination result (predicted vacancy status) of the vacancy status of the parking lots of the service facilities "S2" and "S4" is indicated by "vacant vehicles" (vacant). Further, the determination results of whether or not the parking lots of the service facilities "S2" and "S4" can be reserved are indicated by "impossible" and "possible", respectively. Further, for the service facility "S4" capable of reserving a parking lot, a button (reservation button) for instructing transmission of a reservation request is displayed. For example, the parking information generation unit 122 generates parking information as shown in FIG. 23 and transmits it to the terminal device 200 of the target vehicle “CAR1”.

When the terminal device 200 of the target vehicle receives the parking information (step S352), the terminal device 200 presents (displays) the parking information to the user (step S353).

For example, the terminal device 200 of the target vehicle "CAR1" presents the parking information of FIG. 23 to the user.

When the user inputs a reservation request transmission instruction, the terminal device 200 transmits the reservation request to the parking information providing device 100 (step S354). Here, the reservation request includes the identifier of the target vehicle and the identifier of the service facility that reserves the parking lot.

For example, when the reservation button for the service facility "S4" is pressed in the parking information of FIG. 23, the terminal device 200 of the target vehicle "CAR1" sets the target vehicle identifier "CAR1" and the service facility identifier "S4". The reservation request including the reservation is transmitted to the parking information providing device 100.

The request receiving unit 119 of the parking information providing device 100 receives the reservation request from the terminal device 200 (step 311).

The reservation management unit 124 updates the reservation information in response to the reservation request received from the terminal device 200 (step 312). Here, the reservation management unit 124 registers the identifier of the target vehicle, the reservation start time, and the reservation end time for the service facility specified in the reservation request. In the reservation start time and the reservation end time, the predicted arrival time and the time when the above-mentioned parking time elapses from the predicted arrival time are registered, respectively. Further, the reservation management unit 124 adds 1 to the number of reservations from the reservation start time to the reservation end time.

For example, the reservation management unit 124 registers the reservation of the target vehicle "CAR1" for the parking lot of the service facility "S4" and updates the number of reservations as shown in the reservation information (updated) of FIG.

The reservation management unit 124 transmits a reservation completion notification to the terminal device 200 (step 313). Here, the reservation completion notification includes the identifier of the service facility that reserved the parking lot.

For example, the reservation management unit 124 transmits a reservation completion notification including the service facility identifier “S4” to the terminal device 200 of the target vehicle “CAR1”.

When the terminal device 200 receives the reservation completion notification (step S355), the terminal device 200 presents (displays) the reservation completion to the user (step S356).

For example, the terminal device 200 of the target vehicle "CAR1" presents to the user that the reservation for the parking lot of the service facility "S4" has been completed.

When updating the reservation information, the reservation management unit 124 charges the user of the target vehicle to pay the reservation fee via a charging system (not shown) provided by a credit card company or the like. Processing may be performed.

<Reservation control processing>
Next, the reservation control process will be described.

Here, it is assumed that the reservation information (after update) of FIG. 19 and the allocation information (before update) of FIG. 20 are stored in the reservation information storage unit 123 and the allocation information storage unit 311, respectively.

FIG. 24 is a flowchart showing the reservation control process in the second embodiment. The reservation control process is executed at the reservation start time of the reservation for each reservation registered in the reservation information.

The reservation management unit 124 of the parking information providing device 100 transmits a parking frame control request to the parking frame control device 300 of the service facility where the parking lot is reserved for the reservation at the reservation start time (step S401). Here, the parking frame control request includes the identifier of the reserved vehicle, the reservation start time, and the reservation end time.

For example, the reservation management unit 124 provides a parking frame control request including the reserved vehicle identifier "CAR1", the reservation start time "11:00", and the reservation end time "11:30" at the time "11:00". It is transmitted to the parking frame control device 300 of the facility "S4".

When the control unit 312 of the parking frame control device 300 receives the parking frame control request (step S451), the parking frame allocated to the reserved vehicle based on the vehicle detection status acquired from the vehicle sensor 400 of each parking frame and the allocation information. Is determined (step S452). Here, the control unit 312 determines the parking frame to which the vehicle is not assigned and the vehicle is not parked as the parking frame to be assigned to the reserved vehicle.

For example, the control unit 312 allocates the parking frame "L3" to the vehicle "CAR1" based on the vehicle detection status and the reservation information (before update) in FIG.

The control unit 312 may allocate to the reserved vehicle in order from the parking frame that can be assigned to the reserved vehicle, for example, the parking frame closest to a specific place such as the entrance of the building of the service facility.

The control unit 312 updates the allocation information according to the parking frame allocation result (step S453). Here, the control unit 312 registers the vehicle identifier, the reservation start time, and the reservation end time for the assigned parking frame.

For example, the control unit 312 registers the allocation of the parking frame "L3" to the vehicle "CAR1" as in the reservation information (updated) of FIG.

The control unit 312 causes the assigned parking frame display device 500 to display that the parking frame is reserved (step S454). Here, the control unit 312 may display the identifier of the vehicle to which the parking frame is assigned on the display device 500.

For example, the control unit 312 causes the display device 500 of the parking frame "L3" to display that the reservation has been made.

As a result, when the user of the reserved vehicle arrives at the parking lot of the service facility for which the parking lot is reserved, the parking lot assigned to the reserved vehicle can be specified and the vehicle can be parked in the parking lot.

The control unit 312 further terminates the reserved display on the display device 500 of the parking frame at the reservation end time of the allocated parking frame, and deletes the vehicle allocation for the parking frame from the allocation information. To do.

The control unit 312 reserves a parking lot assigned to the reserved vehicle when the reserved vehicle departs from the reserved parking lot before the reservation end time or passes through the reserved parking lot without using the parking lot. The completed display may be terminated and the parking lot allocation may be deleted from the allocation information. In this case, the control unit 312 periodically acquires the position of the reserved vehicle after the reservation start time from the terminal device 200 of the reserved vehicle via the parking information providing device 100, and from the parking lot of the reserved vehicle. Detect departures and passages.

As described above, the operation of the second embodiment is completed.

Next, the effect of the second embodiment will be described.

According to the second embodiment, the parking lot reservation service can be provided without deteriorating the operational efficiency of the parking lot installed along the road. The reason is that the parking information generation unit 122 determines whether or not the parking lot can be reserved based on the predicted demand at the estimated arrival time of the target vehicle, and when it is determined that the reservation is possible, the reservation management unit 124 However, this is because the parking lot is reserved according to the instruction from the target vehicle.

In the second embodiment, it is determined whether or not the parking lot can be reserved when the predicted demand for the parking lot is less than the predetermined reservation determination threshold, but the present invention is not limited to this, and the predicted demand for the parking lot is equal to or greater than the predetermined reservation determination threshold. You may decide whether or not to make a reservation. In this case, the reservation determination threshold value may be equal to or greater than the number of parking lots that can be accommodated, or may be less than the number of parking lots that can be accommodated.

Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. Various changes that can be understood by those skilled in the art can be made within the scope of the present invention in terms of the structure and details of the present invention.

1 Information providing system 100 Parking information providing device 101 CPU
102 Storage device 103 Input / output device 104 Communication device 111 Road information storage unit 112 Traffic condition storage unit 113 Traffic prediction model learning unit 114 Traffic prediction model storage unit 115 Facility information storage unit 116 Demand information storage unit 117 Demand forecast model learning unit 118 Demand Prediction model storage unit 119 Request reception unit 120 Arrival time prediction unit 121 Demand prediction unit 122 Parking information generation unit 123 Reservation information storage unit 124 Reservation management unit 200 Terminal device 300 Parking frame control device 311 Allocation information storage unit 312 Control unit 400 Vehicle sensor 500 display device

Claims (9)

Arrival of the target vehicle at a parking lot located along the road in the direction of travel of the target vehicle on the road so as to be accessible to and from the road based on the traffic conditions at each point on the road. Arrival time prediction means for predicting time,
A demand forecasting means that predicts demand, which is the number of vehicles that require the use of the parking lot at the predicted arrival time, based on the traffic conditions at each point on the road.
A parking information generating means that determines the vacancy status of the parking lot at the predicted arrival time based on the predicted demand, generates parking information including the determination result of the vacancy status, and outputs the parking information to the target vehicle.
Information provision system equipped with. The parking information generating means predicts the waiting time of the parking lot from the predicted arrival time when the determination result of the availability of the parking lot is full, and the parking information including the predicted waiting time. To generate,
The information providing system according to claim 1. Based on the predicted demand, the parking information generating means determines whether or not the parking lot can be reserved at the predicted arrival time, and generates the parking information including the result of determining whether or not the parking lot can be reserved.
Further, it is provided with a reservation management means for making a reservation for the parking lot for the target vehicle in response to an instruction from the target vehicle when it is determined that the parking lot can be reserved.
The information providing system according to claim 1 or 2. The parking information generating means determines that the parking lot can be reserved when the number of vehicles indicated by the predicted demand is less than a predetermined threshold value equal to or less than the number of cars accommodated in the parking lot.
The information providing system according to claim 3. The reservation management means instructs the parking frame control device that allocates the parking frame of the parking lot to the reserved vehicle to allocate the parking frame to the target vehicle from the predicted arrival time.
The information providing system according to claim 3 or 4. The parking lot is a parking lot of a facility arranged along the road.
The parking information generating means generates the parking information including the determination result of the availability of the parking lot of the facility that exists in the traveling direction of the target vehicle and satisfies the requirement condition specified by the target vehicle.
The information providing system according to any one of claims 1 to 5. The requirement includes at least one of a condition relating to the function of the facility and a condition relating to the time required to reach the parking lot.
The information providing system according to claim 6. Arrival of the target vehicle at a parking lot located along the road in the direction of travel of the target vehicle on the road so as to be accessible to and from the road based on the traffic conditions at each point on the road. Predict the time and
Based on the traffic conditions at each point on the road, the demand, which is the number of vehicles requiring the use of the parking lot at the predicted arrival time, is predicted.
Based on the predicted demand, the vacancy status of the parking lot at the predicted arrival time is determined, parking information including the determination result of the vacancy status is generated, and output to the target vehicle.
Information provision method. On the computer
Arrival of the target vehicle at a parking lot located along the road in the direction of travel of the target vehicle on the road so as to be accessible to and from the road based on the traffic conditions at each point on the road. Predict the time and
Based on the traffic conditions at each point on the road, the demand, which is the number of vehicles requiring the use of the parking lot at the predicted arrival time, is predicted.
Based on the predicted demand, the vacancy status of the parking lot at the predicted arrival time is determined, parking information including the determination result of the vacancy status is generated, and output to the target vehicle.
A program that executes processing.

Images