Parking lot fullness / emptiness prediction device, operation and rest plan generation device, and parking lot fullness / emptiness prediction system

Abstract

To provide a support technique for obtaining high prediction accuracy related to an emptiness state of a parking lot.SOLUTION: A parking lot fullness / emptiness prediction device related to a support technique has a data collection function of collecting fullness / emptiness information being the information which indicates a past fullness / emptiness state of a parking lot, a data management function of recording the fullness / emptiness information as time series data, and a prediction processing function of predicting the fullness / emptiness state of the parking lot in a prediction object date and time being the designated date and time based on the recorded fullness / emptiness information.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The technology disclosed in this specification relates to a technology for predicting the occupancy status of a parking lot and its utilization.

Background Art

[0002] Conventionally, there has been an information providing system for determining the availability of a parking lot based on the traffic conditions on the road (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the technology described in Patent Document 1, for a service area such as a highway, based on the traffic volume in the direction towards the service area, the number of vehicles using the service area after a certain period of time is predicted. When using this technology to obtain the availability of the parking lot at the time when the own vehicle arrives at the service area, it is necessary that all the vehicles arriving at the service area after a certain period of time have already traveled on the highway, and the traffic volume flowing into the highway cannot be taken into account. Therefore, it is difficult to predict more than a certain period of time in advance, such as the availability of the parking lot the next day, or the prediction accuracy regarding the availability of the parking lot is not sufficient.

[0005] The technology disclosed in this specification has been made in view of the problems described above, and is a technology for obtaining high prediction accuracy regarding the availability of a parking lot.

Means for Solving the Problems

[0006] The parking lot occupancy prediction device, which is the first aspect of the technology disclosed in this specification, includes a data collection function for collecting occupancy information, which is information indicating the past occupancy state of a parking lot, a data management function for recording the occupancy information as time-series data, and a prediction processing function for predicting the occupancy state of the parking lot at a specified date and time, which is the prediction target date and time, based on the recorded occupancy information.

Effect of the Invention

[0007] According to at least the first aspect of the technology disclosed in this specification, the accuracy of prediction can be improved by predicting the occupancy state of the parking lot at the prediction target date and time based on the past occupancy information of the parking lot.

[0008] Also, the objects, features, aspects, and advantages related to the technology disclosed in this specification will become clearer by the following detailed description and the accompanying drawings.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Embodiments for Carrying Out the Invention

[0010] Hereinafter, embodiments will be described with reference to the accompanying drawings. In the following embodiments, detailed features and the like are also shown for the purpose of explaining the technology, but these are examples, and not all of them are necessarily essential features for the embodiments to be implemented.

[0011] Note that the drawings are shown schematically, and for the convenience of explanation, omissions or simplifications of the configuration are made in the drawings as appropriate. Also, the mutual relationships of the sizes and positions of the configurations shown in different drawings are not necessarily accurately described and can be changed as appropriate. Further, in drawings such as a plan view that is not a cross-sectional view, hatching may be added to facilitate understanding of the content of the embodiment.

[0012] Also, in the descriptions shown below, the same reference numerals are attached to and illustrated for similar components, and their names and functions are also considered the same. Therefore, detailed descriptions thereof may be omitted to avoid duplication.

[0013] Also, in the descriptions described in the present specification, when a certain component is described as "including", "containing", or "having", etc., it is not an exclusive expression that excludes the existence of other components unless otherwise specified.

[0014] Also, in the descriptions described in the present specification, even when ordinal numbers such as "first" or "second" are used, these terms are used for convenience to facilitate understanding of the content of the embodiment, and the content of the embodiment is not limited to the order or the like that may be caused by these ordinal numbers.

[0015] <First Embodiment> Hereinafter, a parking lot occupancy prediction device, a parking lot occupancy prediction system, and a support system according to the present embodiment will be described.

[0016] <Regarding the Configuration of the Support System> FIG. 1 is a diagram showing an example of the configuration of the support system according to the present embodiment.

[0017] As shown by the example in FIG. 1, the support system includes an entry / exit sensor 11 that counts (detects) the number of vehicles entering and leaving the parking lot at a certain date and time, a parking space sensor 12 that detects whether a vehicle is parked in each parking space, a temperature and humidity sensor 21 that measures temperature and humidity, a sunshine sensor 22 that measures the amount of sunshine, a rainfall sensor 23 that measures the amount of precipitation, and a parking lot occupancy prediction device 100 that acquires and stores data input from each sensor and predicts the occupancy state of the parking lot at a future date and time based on these data (for example, information indicating whether the parking lot is full or empty, information indicating the congestion level of the parking lot, or information indicating the parking rate of the parking lot, etc.). A user 20 who uses the parking lot occupancy prediction device 100 can acquire the prediction result of the occupancy state from the parking lot occupancy prediction device 100.

[0018] The data obtained from the entry / exit sensor 11 and the parking space sensor 12 constitute occupancy information 1 indicating the occupancy state of the parking lot at the date and time (past date and time) of the parking lot. Also, the data obtained from the temperature and humidity sensor 21, the sunshine sensor 22, and the rainfall sensor 23 constitute weather information 2 indicating the weather information of the parking lot at the date and time.

[0019] The parking lot occupancy prediction device 100 includes a data collection function 110 that periodically reads occupancy information 1 and weather information 2 from various sensors, or receives occupancy information 1 and weather information 2 periodically output from various sensors, and passes these data to a data management function 120 for storage; a data management function 120 that stores the data received from the data collection function 110 in a database 121 in time series and reads the data in response to a read request for the data stored in the database 121; and a prediction processing function 130 that transmits a read request for data to the data management function 120, acquires the response from the data management function 120, and predicts the occupancy state of the parking lot at a future time.

[0020] Among various sensors, only one of the entry / exit sensor 11 and the parking space sensor 12 may be provided, and various sensors for measuring weather information 2 such as the temperature / humidity sensor 21, the sunshine sensor 22, and the rainfall sensor 23 may not be provided. That is, the information input to the prediction processing function 130 only needs to include at least the occupancy information 1.

[0021] FIG. 2 is a diagram showing an example of the configuration of the parking lot occupancy prediction device 100 according to the present embodiment. As shown in the example of FIG. 2, the parking lot occupancy prediction device 100 includes a data collection function 110, a data management function 120, and a prediction processing function 130.

[0022] The data collection function 110 includes a data acquisition unit 111 that receives the occupancy information 1 or the weather information 2, and a data storage unit 112 that transmits the acquired data (occupancy information 1 or weather information 2) to the data management function 120 to store the data.

[0023] The data management function 120 includes a data storage interface unit 122 that receives data to be stored from the data storage unit 112 of the data collection function 110, a database 121 that stores the received data in a manner that can be read out according to various conditions, and a data readout interface unit 123 that receives a data readout request from the prediction processing function 130, reads out data from the database 121 according to the conditions specified in the readout request, and responds.

[0024] The prediction processing function 130 includes a prediction request reception unit 131 that receives a prediction request from the user 20, a prediction processing unit 132 that predicts the occupancy state of the parking lot at a future date and time according to the prediction request received by the prediction request reception unit 131 and outputs a prediction result, and a prediction result output unit 133 that responds to the user 20 with the prediction result generated by the prediction processing unit 132.

[0025] <Regarding the operation of the parking lot occupancy prediction device> Next, the data collection operation of the parking lot occupancy prediction device 100 according to the present embodiment will be described with reference to FIGS. 2, 3, 4, and 5. Here, FIG. 3 is a diagram showing an example of the format of data passed from the data acquisition unit 111 to the data storage unit 112. FIG. 4 is a diagram showing an example of data for two times passed from the data acquisition unit 111 to the data storage unit 112. FIG. 5 is a diagram showing an example of the format of a data storage request passed from the data storage unit 112 to the data storage interface unit 122.

[0026] First, the data acquisition unit 111 of the data collection function 110 acquires the occupancy information 1 or the weather information 2 at regular intervals. Let the acquisition start time at this time be T1, the acquisition completion time be T1 + ΔT, and for the next data acquisition, let the acquisition start time be T2 and the acquisition completion time be T2 + ΔT. Here, ΔT is a value smaller than the time difference (T2 - T1) between T2 and T1. Also, T1 and T2 are time information including year, month, and day information.

[0027] The data acquisition unit 111 stores the request source ID that can uniquely identify itself, a unique request ID, and the number of data in the data format shown in FIG. 3, and after storing the set of the acquisition start time, the acquisition completion time, the occupancy information 1, and the weather information 2 for the number of data, passes the data to the data storage unit 112.

[0028] As for the timing when the data acquisition unit 111 passes data to the data storage unit 112, it may be passed each time at the timing when the data acquisition unit 111 acquires the occupancy information 1 or the weather information 2 (at the time of acquisition completion), or may be passed collectively at the timing when a certain number of data are acquired. Note that whether the data are passed each time or collectively in multiple times, as shown in the example in FIG. 4, the format of the data may be the same as the format shown in FIG. 3. In FIG. 4, the requesting source ID is 5, the request ID is 3, the number of data is 2, and as each data, a set of the start time of acquisition (time A), the completion time of acquisition (time B), the occupancy information A and the weather information A, and a set of the start time of acquisition (time C), the completion time of acquisition (time D), the occupancy information B and the weather information B are included in the shown data.

[0029] The data storage unit 112 that has received the data passes a data storage request in the format as shown in FIG. 5 to the data storage interface unit 122 of the data management function 120. The data storage unit 112 stores the requesting source ID that can uniquely identify itself, a unique request ID, and the number of data to be stored, and after storing the start time of acquisition, the completion time of acquisition, and the sets of the occupancy information 1 and the weather information 2 for the number of data, passes the data storage request to the data storage interface unit 122.

[0030] As for the timing when the data storage unit 112 passes a data storage request to the data storage interface unit 122, it may be passed each time at the timing when the data storage unit 112 acquires data from the data acquisition unit 111 (at the time of acquisition completion), or may be passed as a single data storage request for a plurality of times of data collectively. Note that in any case, the format of the data storage request may be the format shown in FIG. 5.

[0031] The data storage interface unit 122 extracts one or a plurality of data sets included in the received data storage request and stores them in the database 121. At this time, the start time of acquisition becomes the key information in the database 121.

[0032] Next, the prediction processing operation of the parking lot occupancy prediction device 100 according to the present embodiment will be described with reference to FIGS. 2, 6, and 7. Here, FIG. 6 is a diagram showing an example of the format of a prediction request input to the parking lot occupancy prediction device 100. FIG. 7 is a diagram showing an example of the format of a prediction result output from the parking lot occupancy prediction device 100 to the user 20.

[0033] First, the user 20 inputs one or more dates and times to be predicted to the parking lot occupancy prediction device 100.

[0034] The prediction request receiving unit 131 provided in the prediction processing function 130 creates a prediction request based on the input date and time. The prediction request is in the format of the prediction request of the data shown in FIG. 6, and specifies a requester ID that uniquely identifies the requester, a request ID that uniquely identifies each prediction request from the requester, the number of prediction target dates and times included in the request, and the prediction target dates and times. Further, when the weather conditions (weather forecast information) at each prediction target date and time are known, the weather conditions at the parking lot on the prediction target date and time can also be additionally specified.

[0035] When the prediction request receiving unit 131 creates a prediction request, it passes the prediction request to the queue for receiving requests of the prediction processing unit 132.

[0036] Next, the prediction processing unit 132 checks the queue for receiving requests. If a prediction request is stored in the queue, the prediction request is taken out from the queue. As a method of taking out the prediction request from the queue, for example, FIFO (FIRST IN FIRST OUT) is used.

[0037] The prediction processing unit 132 uses the prediction target date and time included in the prediction request taken out from the queue, and if included, the weather conditions of the prediction target date and time, and extracts a value predicted as the full / empty state at that date and time based on the information stored in the database 121, and passes it to the prediction result output unit 133 as the prediction result. If the specified prediction target date and time is a past date and time, the prediction processing unit 132 passes the actual data of the specified date and time to the prediction result output unit 133.

[0038] Specific methods for predicting the full / empty state include, for example, a method using learning and analysis by artificial intelligence (AI), a method in which based on the prediction target date and time, the full / empty state of the same date and time in the past year or the same day of the week closest to the same date and time is used as the prediction result, or a method in which, using the weather conditions as well, the full / empty state of the day with the most similar date and time or weather conditions is used as the prediction result. Note that it is not limited to the above prediction methods.

[0039] For example, as a method using learning and analysis by AI, first, a learned model is created by machine learning for the accumulated past full / empty states. Then, using the learned model, the output is predicted as the full / empty state with the prediction target date and time, day of the week, and weather conditions as inputs. Note that the weather conditions may not be included in the inputs.

[0040] Also, for example, as a method in which based on the prediction target date and time, the full / empty state of the same date and time in the past year is used as the prediction result, first, for each item of the accumulated past full / empty states, records of the same date and time as the prediction target date and time are extracted. If the number of extracted records is 1, the value is used as the prediction result, and if the number of extracted records is multiple, the average value is used as the prediction result.

[0041] Also, for example, as a method of using the occupancy / vacancy state on the same day of the same day of the week closest to the prediction target date and time in the past year based on the prediction target date and time as the prediction result, first, for each of the accumulated past occupancy / vacancy state records, among the records of the same date and time as the date and time to be predicted, select the year with the closest day of the week. Then, extract the record of the same day of the week closest to the prediction target date and time, and use its occupancy / vacancy state as the prediction result. When multiple years are selected, extract the records of the same day of the week closest to the prediction target date and time for each year, and use the average value of their occupancy / vacancy states as the prediction result.

[0042] Also, for example, as a method of using the occupancy / vacancy state under the same weather conditions closest to the same date and time in the past year based on the prediction target date and time and the weather conditions as the prediction result, first, for each of the accumulated past occupancy / vacancy state records, calculate the difference between the prediction target weather conditions and the recorded weather conditions for the records of the date and time within a certain difference (for example, two weeks) from the date and time to be predicted. If there is one record with a difference below a certain value, use the occupancy / vacancy state of that record as the prediction result, and if there are multiple records, use the average value of their occupancy / vacancy states as the prediction result.

[0043] The prediction result output unit 133 that has received the prediction result outputs the prediction result in the format as shown in FIG. 7 based on the source ID or the request ID. In the prediction result, the source ID and the request ID use the values included in the prediction request as they are. Also, as the number of data, store the number of sets of the prediction target date and time, weather conditions (which may be omitted), and occupancy / vacancy prediction values included in the prediction result. The prediction result stores the number of sets (sets of the prediction target date and time, weather conditions, and occupancy / vacancy prediction values) specified by the number of data.

[0044] Note that only the value corresponding to the prediction target date and time specified in the prediction request may be stored as the occupancy / vacancy prediction value. In that case, the number of data included in the prediction request and the number of data included in the prediction result are the same value. Also, for the prediction target date and time included in the prediction request, multiple occupancy / vacancy prediction values including the time zones before and after it may be included in the prediction result. In this case, the number of data included in the prediction result is larger than the number of data included in the prediction request.

[0045] In this embodiment, the data collection function 110, the data management function 120, and the prediction processing function 130 are described as being integrated as the parking lot occupancy prediction device 100. However, each function may be implemented as a separate device, and the devices may be connected to each other via a network (parking lot occupancy prediction system).

[0046] Also, the user 20 is not limited to a human who uses the parking lot occupancy prediction device 100, and may be a program that operates on the same or a different device as the parking lot occupancy prediction device 100.

[0047] Furthermore, in order to improve the accuracy of occupancy prediction, the prediction processing unit 132 may correct the prediction result in consideration of the date and time of a specific event that affects the degree of congestion in the parking lot. For example, the occupancy state on the date and time of the same event in any past year may be used as the prediction result, or the average value of the occupancy states on the date and time of the same event in multiple past years may be used as the prediction result.

[0048] Also, data for a certain period before and after the predicted target date and time specified by the user 20 may be output.

[0049] Note that the prediction processing unit 132 of this embodiment performs prediction processing after receiving a prediction request. However, based on the data stored in the database 121, occupancy prediction values up to a certain period in the future may be automatically extracted in advance, and these values may be referred to and the occupancy prediction value may be output when a prediction request is received.

[0050] As described above, according to this embodiment, the occupancy information 1 or the weather information 2 is stored as time-series data, and based on this, future occupancy prediction can be performed. Therefore, prediction based on actual results is possible, and the effect of improving prediction accuracy can be obtained. In addition, the prediction accuracy can be further improved by combining with the weather information 2 or the like.

[0051] <Second Embodiment> A parking lot occupancy prediction device, an operation and rest plan creation device, a parking lot occupancy prediction system, and a support system according to the present embodiment will be described. In the following description, components similar to those described in the above-described embodiment will be denoted by the same reference numerals and illustrated, and detailed descriptions thereof will be omitted as appropriate.

[0052] <Regarding the configuration of the support system> In the first embodiment, a parking lot occupancy prediction device capable of accurately predicting occupancy was shown. In the present embodiment, a form is shown in which a program operates as a user of the parking lot occupancy prediction device, and the program uses the predicted result value for creating an operation and rest plan.

[0053] FIG. 8 is a diagram showing an example of the configuration of a support system according to the present embodiment. As shown in FIG. 8, the support system includes a parking lot occupancy prediction device 100 and an operation and rest plan creation device 200. In FIG. 8, one parking lot occupancy prediction device 100 is provided, but a plurality of parking lot occupancy prediction devices 100 may be provided.

[0054] Data is input to the parking lot occupancy prediction device 100 in FIG. 8 from an entrance / exit sensor 11, a parking space sensor 12, a temperature / humidity sensor 21, a sunlight sensor 22, and a rainfall sensor 23. The parking lot occupancy prediction device 100 includes a data collection function 110, a data management function 120 including a database 121, and a prediction processing function 130.

[0055] In the present embodiment, an operation and rest plan creation device 200 is further provided that creates an operation and rest plan using the prediction result output from the parking lot occupancy prediction device 100.

[0056] The operation and rest plan creation device 200 includes an operation and rest plan creation function 210 for creating an operation and rest plan, and a prediction result collection function 220 for obtaining prediction results from one or more parking lot occupancy prediction devices 100. A user 20 who uses the operation and rest plan creation device 200 can obtain an operation and rest plan from the operation and rest plan creation device 200.

[0057] FIG. 9 is a diagram showing an example of the configuration of the operation and rest plan creation device 200 according to the present embodiment. As shown in the example of FIG. 9, the operation and rest plan creation device 200 includes an operation and rest plan creation function 210 and a prediction result collection function 220.

[0058] The operation and rest plan creation function 210 includes a plan creation request reception unit 211 that receives a plan creation request from a user, an operation route plan creation unit 212 that creates an operation route plan based on the plan creation request, a plan creation processing unit 213 that creates an optimal operation and rest plan for the operation route plan based on the occupancy prediction value of the parking lot serving as the rest location, and a plan creation result output unit 214 that outputs the created operation and rest plan to the user.

[0059] The prediction result collection function 220 includes one or more prediction result acquisition units 221 that obtain the occupancy prediction values required by the plan creation processing unit 213 from the parking lot occupancy prediction device 100, and a parking lot occupancy prediction device list 222 that holds access destination list information of the parking lot occupancy prediction device 100 capable of performing occupancy prediction for each parking lot and can answer the access destination information of the parking lot occupancy prediction device of the corresponding parking lot from the parking lot name or parking lot ID.

[0060] <Regarding the operation of the operation and rest plan creation device> Next, the operation and rest plan creation operation of the operation and rest plan creation device 200 according to the present embodiment will be described with reference to FIGS. 9, 10, 11, and 12. Here, FIG. 10 is a diagram showing an example of the format of a plan creation request input from a user to the operation and rest plan creation device 200. FIG. 12 is a flowchart showing an example of the operation and rest plan creation processing flow for the operation route plan.

[0061] First, the plan creation request receiving unit 211 of the operation and rest plan creation function 210 receives information on the departure place, one or more transit places, the final destination, and the departure date and time from the user, and creates a plan creation request.

[0062] The plan creation request is in the data format shown in FIG. 10, and stores a requester ID that uniquely identifies the requester, a request ID that uniquely identifies the request, and the number of data items to be the target of plan creation, and stores the departure date and time, the departure place, the final destination, the number of transit places, and a set of zero or more transit places for the specified number of data items.

[0063] When the plan creation request receiving unit 211 creates a plan creation request, it passes this to the request acceptance queue of the operation route plan creation unit 212.

[0064] The operation route plan creation unit 212 checks the request acceptance queue, and when a plan creation request is stored, it takes this out of the queue and creates an operation route plan. As a method of taking out from the request acceptance queue, for example, FIFO is used.

[0065] When the operation route plan creation unit 212 takes out a plan creation request from the request acceptance queue, it creates each operation route plan according to the number of data items included in the plan creation request. The operation route plan includes a route that departs from the specified departure place at the specified departure time, passes through the transit places, and arrives at the final destination, a parking lot where rest is possible on the route, and the respective scheduled arrival times at the transit places, the parking lot, and the final destination.

[0066] FIG. 11 is a diagram showing an example of an operation route plan. As shown in the example of FIG. 11, for each of the departure point, waypoints, parking lots, and destinations on the operation route, the type, date and time, and location are stored in the operation route plan.

[0067] The type stores either "departure point", "waypoint", "parking lot", or "destination", and the date and time stores the arrival date and time at that location. However, for the departure point only, the departure date and time are stored as the date and time. Also, as the location, the name of each point is stored.

[0068] In the initially created operation route plan, the arrival time is stored such that it stays at each waypoint for a fixed time set in advance only from the departure point to the destination. Note that the staying time may be zero.

[0069] The operation route plan creation unit 212 passes the created operation route plan to the plan creation processing unit 213.

[0070] When the plan creation processing unit 213 receives the operation route plan, it starts creating an operation and rest plan that also includes information on rest acquisition locations. For the location to acquire rest, for example, it is selected from the waypoints or parking lots included in the operation route plan by a method as shown in the flowchart of FIG. 12 described below. Hereinafter, the time set in advance as the time that continuous driving is possible without taking a rest is called the continuous driving possible time.

[0071] As a method of selecting a location to acquire rest, first, the location to be focused on among each location included in the operation route plan is set as location X, and the departure point is set as location X first (step ST1101).

[0072] Next, calculate the time required to go from location X to the destination, and use this as the required time (step ST1102).

[0073] Next, it is determined whether the required time is less than or equal to the continuous driving possible time (step ST1103). And when the required time is less than or equal to the continuous driving possible time, that is, when corresponding to "YES" that branches from step ST1103 shown in FIG. 12 for example, it is determined that rest acquisition is unnecessary, and the driving route plan is output to the plan creation result output unit 214 as a driving and rest plan (step ST1108), and the process ends.

[0074] On the other hand, when the required time is longer than the continuous driving possible time, that is, when corresponding to "NO" that branches from step ST1103 shown in FIG. 12 for example, it is determined whether it is possible to extract a location among waypoints and parking lots that can be reached within the continuous driving possible time from the departure place (step ST1104). And when it is possible to extract a location that has not been extracted, that is, when corresponding to "YES" that branches from step ST1104 shown in FIG. 12 for example, the above-mentioned locations are extracted in descending order of arrival time and the process proceeds to step ST1105. On the other hand, when it is not possible to extract a location that has not been extracted, that is, when corresponding to "NO" that branches from step ST1104 shown in FIG. 12 for example, an error indicating that the rest location cannot be extracted is output to the plan creation result output unit 214 (step ST1107), and the process ends.

[0075] Next, in step ST1105, it is determined whether the location extracted in step ST1104 is a waypoint. And when the extracted location is a waypoint, that is, when corresponding to "YES" that branches from step ST1105 shown in FIG. 12 for example, the process proceeds to step ST1110.

[0076] On the other hand, when the extracted location is not a waypoint (when it is a parking lot), that is, when corresponding to "NO" that branches from step ST1105 shown in FIG. 12 for example, the process proceeds to step ST1106.

[0077] In step ST1106, the occupancy status at the arrival scheduled time of the parking lot, which is the extracted location, is obtained from the prediction result of the parking lot occupancy prediction device 100 (step ST1106).

[0078] Then, it is determined whether the obtained occupancy status indicates a congestion level less than a preset value (step ST1109). And if the congestion level is less than the preset value, that is, when corresponding to "YES" branched from step ST1109 as shown in FIG. 12, it is determined that it is possible to enter the parking lot and take a break, and the process proceeds to step ST1110. On the other hand, if the congestion level is greater than or equal to the preset value, that is, when corresponding to "NO" branched from step ST1109 as shown in FIG. 12, the process returns to step ST1104.

[0079] Here, the congestion level is calculated as M÷N using the maximum number of parking spaces N in the parking lot and the predicted number of parked vehicles M.

[0080] In step ST1110, taking the extracted location as the rest location, the operation route plan is updated such that the vehicle stays at the location for a preset rest time (step ST1110).

[0081] Next, taking the rest location as location X (step ST1111), the process returns to the process of step ST1102.

[0082] Through the above processing, an error indicating that the rest location cannot be extracted, or either the operation and rest plan is output to the plan creation result output unit 214.

[0083] In this embodiment, the case where the support system includes the operation and rest plan creation device 200 as a device independent of the parking lot occupancy prediction device 100 has been described, but it is also possible to configure the parking lot occupancy prediction device 100 and the operation and rest plan creation device 200 integrally.

[0084] Also, the user 20 may be not only a human who uses the operation and rest plan creation device 200, but also a program that operates on the same or different device as the operation and rest plan creation device 200.

[0085] In the present embodiment, when an error indicating that the rest location cannot be extracted is output by the process of step ST1107, the start time of the operation route plan may be shifted and the creation of the operation and rest plan may be attempted again.

[0086] As described above, by configuring the operation and rest plan creation device 200 to be able to create an operation and rest plan using the prediction result output from the parking lot occupancy prediction device 100, it is possible to reduce the case where it is impossible to enter and rest at the rest location due to congestion at arrival. For example, in the case of a transport truck, an effect that appropriate rest can be obtained as defined by law can be obtained.

[0087] <Third Embodiment> The parking lot occupancy prediction device, the parking lot occupancy prediction system, and the support system according to the present embodiment will be described. In the following description, the same components as those described in the above-described embodiment will be denoted by the same reference numerals and illustrated, and the detailed description thereof will be omitted as appropriate.

[0088] <Regarding the Configuration of the Support System> FIG. 13 is a diagram showing an example of the configuration of the support system according to the present embodiment. As shown in FIG. 13, the support system includes a parking lot occupancy prediction device 100.

[0089] In the parking lot occupancy prediction device 100 shown in FIG. 13, in addition to the entry / exit sensor 11, the parking space sensor 12, the temperature / humidity sensor 21, the sunlight sensor 22, and the rainfall sensor 23, data is input from the store sales management 31 that manages the past sales information of the stores co-located in the parking lot. The parking lot occupancy prediction device 100 includes a data collection function 110, a data management function 120 including a database 121, and a prediction processing function 130. The information input from the store sales management 31 constitutes the sales information 3 described later.

[0090] FIG. 14 is a diagram showing an example of the configuration of the parking lot occupancy prediction device 100 according to the present embodiment.

[0091] In FIG. 14, the configuration other than the prediction processing unit 132 that performs prediction in consideration of the sales information 3 obtained from the store sales management 31 and the sales information 3 is the same as that shown in FIG. 2. The sales information 3 is the cumulative sales value from the start of business on that day until the time point when the sales information is generated.

[0092] <Regarding the operation of the parking lot occupancy prediction device> Next, the data collection operation of the parking lot occupancy prediction device 100 according to the present embodiment will be described with reference to FIGS. 14, 15, 16, and 17. Here, FIG. 15 is a diagram showing an example of the format of the data passed from the data acquisition unit 111 to the data storage unit 112. FIG. 16 is a diagram showing an example of two sets of data passed from the data acquisition unit 111 to the data storage unit 112. FIG. 17 is a diagram showing an example of the format of the data storage request passed from the data storage unit 112 to the data storage interface unit 122.

[0093] Regarding the occupancy information 1 or the weather information 2, the operation is the same as that shown in the first embodiment. On the other hand, regarding the sales information 3, the data acquisition unit 111 of the data collection function 110 also acquires it at a fixed cycle.

[0094] The data acquisition unit 111 stores the requesting source ID, the request ID, and the number of data in the data format shown in FIG. 15, in the same manner as in the case shown in the first embodiment. In the present embodiment, the set in which the number of data is stored in compartments is a set that combines sales information in addition to the acquisition start time, the acquisition completion time, the full / empty information, and the weather information, which are the same as those in the case of the first embodiment.

[0095] Note that whether the data is passed each time or passed in a batch for multiple times, as shown in the example of FIG. 16, the format of the data may be the same as the format shown in FIG. 15. In FIG. 16, the requesting source ID is 5, the request ID is 3, the number of data is 2, and as each piece of data, a set of time A which is the acquisition start time, time B which is the acquisition completion time, full / empty information A, weather information A, and sales information A, and a set of time C which is the acquisition start time, time D which is the acquisition completion time, full / empty information B, weather information B, and sales information B are included in the shown data.

[0096] The data storage unit 112 that has received the data passes a data storage request in the format shown in FIG. 17 to the data storage interface unit 122 of the data management function 120. The data storage unit 112 stores the requesting source ID, the request ID, and the number of data, in the same manner as in the case of the first embodiment. In the present embodiment, the set in which the number of data is stored in compartments is a set that combines sales information in addition to the acquisition start time, the acquisition completion time, the full / empty information, and the weather information, which are the same as those in the case of the first embodiment. The data storage unit 112 passes the data storage request to the data storage interface unit 122.

[0097] The data storage interface unit 122 that has received the data storage request stores the received data set in the database 121, in the same manner as in the case of the first embodiment.

[0098] Next, the prediction processing operation of the parking lot occupancy prediction device 100 according to the present embodiment will be described with reference to FIGS. 14, 18, and 19. Here, FIG. 18 is a diagram showing an example of the format of a prediction request input to the parking lot occupancy prediction device 100. FIG. 19 is a diagram showing an example of the format of a prediction result output from the parking lot occupancy prediction device 100 to the user 20.

[0099] Also in the present embodiment, as in the case shown in the first embodiment, the process starts from when the prediction request receiving unit 131 receives an input from the user 20. The prediction request shall be in the format shown in FIG. 18.

[0100] The prediction request receiving unit 131 passes the received prediction request to the prediction processing unit 132.

[0101] Upon receiving the prediction request, the prediction processing unit 132 generates times divided at a preset time interval (for example, 30 minutes) from the business start time of the day (hereinafter referred to as the prediction target day) to the time specified as the prediction target time (hereinafter referred to as the prediction target time) for the specified prediction target date and time. Using all the generated times, a plurality of times on the prediction target day are used as new prediction target date and times, and occupancy prediction values are obtained in the same manner as in the first embodiment.

[0102] As described above, occupancy prediction values at regular time intervals from the business start time to the prediction target time on the prediction target day are obtained.

[0103] Next, based on the obtained occupancy prediction values, a sales prediction from the business start to the prediction target time on the prediction target day is performed. The specific sales prediction method is not limited in the present embodiment. For example, a method using learning and analysis by artificial intelligence (AI), a method in which, based on the prediction target date and time and the occupancy prediction value, the sales information of the day with the closest date and occupancy status in the past year is used as the prediction result, or a method in which, further using weather conditions, the sales information of the day with the most similar date, weather conditions, or occupancy status is used as the prediction result, etc. are conceivable. Note that it is not limited to the above prediction methods.

[0104] For example, as a method using AI-based learning and analysis, first, a trained model is created by machine learning for the accumulated past full / empty states. Then, using the trained model, the output is predicted as the full / empty state with the prediction target date and time, day of the week, and weather conditions as inputs. Further, the sales information corresponding to the predicted full / empty state is used as the prediction result. Note that the weather conditions may not be included in the input.

[0105] Also, for example, as a method of using the sales information of the day with the closest date and full / empty state in the past year as the prediction result based on the prediction target date and time and the full / empty prediction value, first, for each of the accumulated past full / empty state records, the year with the closest full / empty state among the records of the same date as the prediction target date is selected. Then, the sales information corresponding to the selected full / empty state is used as the prediction result.

[0106] Also, for example, as a method of using the sales information of the day with the closest date and full / empty state and the same weather conditions in the past year as the prediction result based on the prediction target date and time and the full / empty prediction value, first, for each of the accumulated past full / empty state records, the difference between the prediction target weather conditions and the recorded weather conditions is calculated for the records of the days with a difference within a certain range (for example, two weeks) from the prediction target date. If there is one record with a difference below a certain value, the sales information corresponding to the full / empty state of that record is used as the prediction result, and if there are multiple records, the sales information corresponding to the average value of those full / empty states is used as the prediction result.

[0107] When the prediction processing unit 132 obtains the sales prediction value, it creates a prediction result including this value and passes it to the prediction result output unit 133. The format of the prediction result is, for example, the format shown in FIG. 19.

[0108] The prediction result output unit 133 that has received the prediction result outputs the above prediction result to the user 20.

[0109] For example, when user 20 wants to predict the cumulative sales amount for one day of the target prediction date, the predicted value of the cumulative sales amount for that day can be obtained by setting 23:59:59 of that day as the target prediction date and time.

[0110] In this embodiment, in a form that extends the first embodiment, the configuration for realizing the sales amount prediction of the store annexed to the parking lot has been described. However, by the same extension, it is also possible to predict the number of visitors to the annexed store or the sales amount for each product.

[0111] As described above, as data handled by the parking lot occupancy prediction device 100, in addition to the occupancy information 1 and the weather information 2, the sales information 3 of the store annexed to the parking lot is included, and these are accumulated as time-series data, and based on this, future occupancy prediction and store sales prediction can be performed. Therefore, it is possible to perform sales prediction based on actual results.

[0112] <Hardware Configuration of Parking Lot Occupancy Prediction Device, Operation, and Rest Plan Creation Device> FIG. 20 and FIG. 21 are diagrams schematically illustrating the hardware configuration when actually operating the parking lot occupancy prediction device, operation, and rest plan creation device exemplified in FIGS. 1, 8, and 13.

[0113] Note that the hardware configurations exemplified in FIGS. 20 and 21 may not match in terms of numbers and the like with the configurations exemplified in FIGS. 1, 8, and 13, but this is due to the fact that the configurations exemplified in FIGS. 1, 8, and 13 show conceptual units.

[0114] Therefore, at least, it is conceivable that one configuration exemplified in FIGS. 1, 8, and 13 consists of a plurality of hardware configurations exemplified in FIGS. 20 and 21, one configuration exemplified in FIGS. 1, 8, and 13 corresponds to a part of the hardware configuration exemplified in FIGS. 20 and 21, and furthermore, a plurality of configurations exemplified in FIGS. 1, 8, and 13 are provided in one hardware configuration exemplified in FIGS. 20 and 21.

[0115] In FIG. 20, as a hardware configuration for realizing the data collection function 110, data management function 120, prediction processing function 130, operation and rest plan creation function 210, prediction result collection function 220, etc. in FIGS. 1, 8, and 13, a processing circuit 1102A that performs calculations, a storage device 1103 that can store information, an input device 1104A such as a mouse, keyboard, touch panel, or various switches that can input information, an output device 1105A (including the case of sharing with the input device 1104A) such as a display, liquid crystal display device, or lamp that can output information, and a measurement device 1106A such as a sensor or analyzer that can measure physical quantities, etc. are shown. This configuration is the same in any of the above embodiments.

[0116] In FIG. 21, as a hardware configuration for realizing the data collection function 110, data management function 120, prediction processing function 130, operation and rest plan creation function 210, prediction result collection function 220, etc. in FIGS. 1, 8, and 13, a processing circuit 1102B that performs calculations, an input device 1104B such as a mouse, keyboard, touch panel, or various switches that can input information, an output device 1105B (including the case of sharing with the input device 1104B) such as a display, liquid crystal display device, or lamp that can output information, and a measurement device 1106B such as a sensor or analyzer that can measure physical quantities, etc. are shown. This configuration is the same in any of the above embodiments.

[0117] The data management function 120 is realized by the storage device 1103 or another storage device (not shown here).

[0118] The memory device 1103 may be, for example, a hard disk drive (HDD), a random access memory (RAM), a read only memory (ROM), a flash memory, an erasable programmable read only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or other volatile or non-volatile semiconductor memories, magnetic disks, flexible disks, optical disks, compact disks, mini disks, DVDs, or any other recording medium to be used in the future.

[0119] The processing circuit 1102A may execute a program stored in the memory device 1103, an external CD-ROM, an external DVD-ROM, or an external flash memory. That is, for example, it may be a central processing unit (CPU), a microprocessor, a microcomputer, or a digital signal processor (DSP).

[0120] When the processing circuit 1102A executes a program stored in the memory device 1103, an external CD-ROM, an external DVD-ROM, or an external flash memory, the data collection function 110, the prediction processing function 130, the operation and rest plan creation function 210, and the prediction result collection function 220 are realized by software, firmware, or a combination of software and firmware in which the program stored in the memory device 1103 is executed by the processing circuit 1102A. Note that the functions of the data collection function 110, the prediction processing function 130, the operation and rest plan creation function 210, and the prediction result collection function 220 may be realized, for example, by cooperation of a plurality of processing circuits.

[0121] Software and firmware may be described as programs and stored in the storage device 1103. In that case, the processing circuit 1102A realizes the above functions by reading and executing the programs stored in the storage device 1103. That is, the storage device 1103 may store a program that, when executed by the processing circuit 1102A, results in the realization of the above functions.

[0122] Also, the processing circuit 1102B may be dedicated hardware. That is, for example, it may be a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of these circuits.

[0123] When the processing circuit 1102B is dedicated hardware, the data collection function 110, the prediction processing function 130, the operation and rest plan creation function 210, and the prediction result collection function 220 are realized by the operation of the processing circuit 1102B. Note that the functions of the data collection function 110, the prediction processing function 130, the operation and rest plan creation function 210, and the prediction result collection function 220 may be realized by separate circuits or a single circuit.

[0124] Note that the functions of the data collection function 110, the prediction processing function 130, the operation and rest plan creation function 210, and the prediction result collection function 220 may be partially realized in the processing circuit 1102A that executes a program stored in the storage device 1103 and partially realized in the processing circuit 1102B that is dedicated hardware.

[0125] In addition, the data acquisition unit 111 of the data collection function 110, the prediction request receiving unit 131 of the prediction processing function 130, the plan creation request receiving unit 211 of the operation and rest plan creation function 210, the prediction result acquisition unit 221 of the prediction result collection function 220, etc. are realized by the input device 1104A or the input device 1104B.

[0126] In addition, the prediction result output unit 133 of the prediction processing function 130, the plan creation result output unit 214 of the operation and rest plan creation function 210, etc. are realized by the output device 1105A or the output device 1105B (they may be shared with the input device).

[0127] In addition, various sensors for inputting data to the data collection function 110, etc. are realized by the measuring device 1106A or the measuring device 1106B.

[0128] <Regarding the effects produced by the above-described multiple embodiments> Next, examples of the effects produced by the above-described multiple embodiments are shown. In the following description, although the effects are described based on the specific configurations shown in the above-described multiple embodiments, within the range where the same effects are produced, they may be replaced with other specific configurations shown in the present specification. That is, hereinafter, for the sake of convenience, only one of the corresponding specific configurations may be representatively described, but the representatively described specific configuration may be replaced with other corresponding specific configurations.

[0129] In addition, such replacement may be made across multiple embodiments. That is, even when the respective configurations shown in different embodiments are combined and the same effects are produced, it may be the case.

[0130] According to the embodiments described above, the parking lot occupancy prediction device includes a data collection function 110 that collects occupancy information 1, which is information indicating the past occupancy state of the parking lot, a data management function 120 that records the occupancy information 1 as time-series data, and a prediction processing function 130 that predicts the occupancy state of the parking lot at a prediction target date and time, which is a specified date and time, based on the recorded occupancy information 1.

[0131] Also, according to the embodiments described above, the parking lot occupancy prediction device includes an input device 1104A, an output device 1105A, and a measurement device 1106A. The parking lot occupancy prediction device also includes a processing circuit 1102A that executes a program and a storage device 1103 that stores the program to be executed. Then, by the processing circuit 1102A executing the program, the following operations are realized.

[0132] That is, occupancy information 1, which is information indicating the past occupancy state of the parking lot, is collected, the occupancy information 1 is recorded as time-series data, and based on the recorded occupancy information 1, the occupancy state of the parking lot at the prediction target date and time, which is a specified date and time, is predicted.

[0133] Also, according to the embodiments described above, the parking lot occupancy prediction device includes an input device 1104B, an output device 1105B, and a measurement device 1106B. The parking lot occupancy prediction device also includes a processing circuit 1102B, which is dedicated hardware. Then, the processing circuit 1102B, which is dedicated hardware, performs the following operations.

[0134] That is, the processing circuit 1102B, which is dedicated hardware, collects occupancy information 1, which is information indicating the past occupancy state of the parking lot, records the occupancy information 1 as time-series data, and predicts the occupancy state of the parking lot at the prediction target date and time, which is a specified date and time, based on the recorded occupancy information 1.

[0135] According to such a configuration, by predicting the occupancy state of the parking lot at the prediction target date and time based on the past occupancy information of the parking lot, the prediction accuracy can be improved.

[0136] In addition to the occupancy / vacancy record of the parking lot, if it is configured to accumulate weather information 2 such as weather or temperature, and further information on the holding of specific events, etc., and utilize them for predicting the occupancy / vacancy state, the accuracy of the prediction can be further improved.

[0137] In addition, when other configurations exemplified in the present specification are appropriately added to the above configuration, that is, even when other configurations in the present specification not mentioned as the above configuration are appropriately added, the same effects can be achieved.

[0138] Further, according to the embodiment described above, the prediction processing function 130 corrects the occupancy / vacancy information 1 when the prediction target date and time is the holding date and time of a specific event. According to such a configuration, since it is possible to consider the number of vehicles in the parking lot that increases or decreases due to the holding of a specific event, the accuracy of predicting the occupancy / vacancy state can be enhanced.

[0139] Further, according to the embodiment described above, the prediction processing function 130 predicts the occupancy / vacancy state of the parking lot in a predetermined period before and after the prediction target date and time. According to such a configuration, it is possible to predict the occupancy / vacancy state not only at a specific date and time but also within a certain time range.

[0140] Further, according to the embodiment described above, the prediction processing function 130 automatically predicts the occupancy / vacancy state of the parking lot from the current time to a time a predetermined period ahead regardless of an external prediction request. According to such a configuration, it is possible to automatically extract the occupancy / vacancy prediction values up to a certain period in the future in advance, and when a prediction request is received, refer to these values and smoothly output the occupancy / vacancy prediction values.

[0141] Also, according to the embodiments described above, the data collection function 110 collects the past sales information 3 of the stores annexed to the parking lot. Then, the prediction processing function 130 predicts the sales of the store within a predetermined time range on the prediction target date based on the predicted occupancy status of the parking lot and the sales information 3. With such a configuration, it is possible to predict the sales of the stores annexed to the parking lot, and efficient management such as adjustment of the purchase quantity can be performed based on this.

[0142] According to the embodiments described above, the operation and rest plan creation device creates an operation and rest plan based on the occupancy status at the prediction target date and time output from the above-described parking lot occupancy prediction device 100.

[0143] With such a configuration, the predicted occupancy status can be utilized for creating the operation and rest plan. Therefore, it is possible to reduce the possibility of problems such as the parking lot scheduled for rest being full and unavailable for use, or a waiting time occurring until it becomes available for use, and it becomes possible to operate and rest as planned.

[0144] Also, according to the embodiments described above, it is configured to be integrated with the parking lot occupancy prediction device 100. With such a configuration, it is possible to create an operation and rest plan based on the occupancy status at the prediction target date and time using one device.

[0145] Also, according to the embodiments described above, when the occupancy status is less than a predetermined threshold value, an operation and rest plan is created with the parking lot as a rest place. With such a configuration, it is possible to determine whether or not to use the parking lot as a rest place based on the predicted occupancy status, and create an appropriate operation and rest plan.

[0146] Also, according to the embodiments described above, when a rest place cannot be set in the operation and rest plan, the departure time of the operation and rest plan is shifted, and the operation and rest plan is created again. According to such a configuration, an operation and rest plan in which a rest place can be set can be effectively created.

[0147] According to the embodiments described above, in a parking lot occupancy prediction system, a data collection function 110 that collects occupancy information 1, which is information indicating the past occupancy state of a parking lot, a data management function 120 that records the occupancy information 1 as time-series data, and a prediction processing function 130 that predicts the occupancy state of the parking lot at a prediction target date and time, which is a specified date and time, based on the recorded occupancy information 1 are provided. The data collection function 110, the data management function 120, and the prediction processing function 130 are each provided in different devices and can communicate with each other via a network.

[0148] According to such a configuration, the accuracy of the prediction can be improved by predicting the occupancy state of the parking lot at the prediction target date and time based on the past occupancy information of the parking lot.

[0149] In addition to the occupancy record of the parking lot, if weather information 2 such as weather or temperature, and further information on the holding of specific events are accumulated and configured to be utilized for predicting the occupancy state, the accuracy of the prediction can be further improved.

[0150] Also, when other configurations exemplified in the present specification are appropriately added to the above configuration, that is, even when other configurations in the present specification that are not mentioned as the above configuration are appropriately added, the same effects can be achieved.

[0151] <Regarding variations of the above-described multiple embodiments> In the multiple embodiments described above, the dimensions, shapes, relative arrangement relationships, or implementation conditions of each component may be described, but these are all examples in all aspects and are not limiting.

[0152] Therefore, numerous variations and equivalents not shown in the examples are envisioned within the scope of the technology disclosed in the present specification. For example, when deforming, adding, or omitting at least one component, or even when extracting at least one component in at least one embodiment and combining it with components in other embodiments, it shall be included.

[0153] Also, as long as there is no contradiction, when it is described in the above-described embodiments that a component is provided with "one", the component may be provided with "one or more".

[0154] Furthermore, each component in the above-described embodiments is a conceptual unit, and within the scope of the technology disclosed in the present specification, it shall include cases where one component consists of a plurality of structures, cases where one component corresponds to a part of a certain structure, and even cases where a plurality of components are provided in one structure.

[0155] Also, each component in the above-described embodiments shall include structures having other structures or shapes as long as they perform the same function.

[0156] Also, the descriptions in the present specification are for reference for all purposes related to the present technology, and none of them are recognized as prior art.

[0157] Also, each component described in the above-described embodiments is envisioned as either software or firmware, or the corresponding hardware. As software, for example, it is referred to as a "part", etc., and as hardware, for example, it is referred to as a "processing circuitry", etc.

[0158] Hereinafter, aspects of the present disclosure will be collectively described as appendices.

[0159] (Appendix 1) A data collection function for collecting occupancy information, which is information indicating the past occupancy status of a parking lot, A data management function for recording the occupancy information as time-series data, And a prediction processing function for predicting the occupancy status of the parking lot at a prediction target date and time, which is a specified date and time, based on the recorded occupancy information. Parking lot occupancy prediction device.

[0160] (Appendix 2) The parking lot occupancy prediction device according to Appendix 1, Wherein the prediction processing function corrects the occupancy information when the prediction target date and time is the holding date and time of a specific event. Parking lot occupancy prediction device.

[0161] (Appendix 3) The parking lot occupancy prediction device according to Appendix 1 or 2, Wherein the prediction processing function predicts the occupancy status of the parking lot in a predetermined period before and after the prediction target date and time. Parking lot occupancy prediction device.

[0162] (Appendix 4) The parking lot occupancy prediction device according to any one of Appendices 1 to 3, Wherein the prediction processing function automatically predicts the occupancy status of the parking lot from the current time to a time after a predetermined period without being dependent on an external prediction request. Parking lot occupancy prediction device.

[0163] (Appendix 5) The parking lot occupancy prediction device according to any one of Appendices 1 to 4, Wherein the data collection function collects past sales information of a store annexed to the parking lot, And the prediction processing function predicts the sales of the store based on the predicted occupancy status of the parking lot and the sales information. Parking lot occupancy prediction device.

[0164] (Appendix 6) It is a parking lot occupancy prediction device according to any one of Appendices 1 to 5, wherein the prediction processing function uses a pre-created learned model obtained by machine learning based on the recorded occupancy information, takes the prediction target date and time as an input, and outputs the occupancy state of the parking lot. Parking lot occupancy prediction device.

[0165] (Appendix 7) It is a parking lot occupancy prediction device according to any one of Appendices 1 to 6, wherein when there is a plurality of occupancy information corresponding to the prediction target date and time, the prediction processing function predicts the occupancy state of the parking lot at the prediction target date and time based on the average value of the plurality of occupancy information corresponding to the prediction target date and time. Parking lot occupancy prediction device.

[0166] (Appendix 8) It is a parking lot occupancy prediction device according to any one of Appendices 1 to 7, wherein when there is a plurality of occupancy information corresponding to the prediction target date and time, the prediction processing function predicts the occupancy state of the parking lot at the prediction target date and time based on the occupancy information closest to the day of the week of the prediction target date and time. Parking lot occupancy prediction device.

[0167] (Appendix 9) It is a parking lot occupancy prediction device according to any one of Appendices 1 to 8, wherein the prediction processing function predicts the occupancy state of the parking lot at the prediction target date and time based on the occupancy information and the weather information of the prediction target date and time. Parking lot occupancy prediction device.

[0168] (Appendix 10) Based on the occupancy state at the prediction target date and time output from the parking lot occupancy prediction device according to any one of Appendices 1 to 9, an operation and rest plan is created. Operation and rest plan creation device.

[0169] (Appendix 11) It is an operation and rest plan creation device described in Appendix 10, which is configured to be integrated with the parking lot occupancy prediction device, Operation and rest plan creation device.

[0170] (Appendix 12) It is an operation and rest plan creation device described in Appendix 10 or 11, and creates the operation and rest plan that uses the parking lot as a rest place when the occupancy state is less than a predetermined threshold value. Operation and rest plan creation device.

[0171] (Appendix 13) It is an operation and rest plan creation device described in any one of Appendices 10 to 12, and when the rest place cannot be set in the operation and rest plan, it shifts the departure time of the operation and rest plan and creates the operation and rest plan again. Operation and rest plan creation device.

[0172] (Appendix 14) A data collection function for collecting occupancy information, which is information indicating the past occupancy state of a parking lot, a data management function for recording the occupancy information as time-series data, and a prediction processing function for predicting the occupancy state of the parking lot at a prediction target date and time, which is a specified date and time, based on the recorded occupancy information. Each of the data collection function, the data management function, and the prediction processing function is provided in a different device and can communicate with each other via a network. Parking lot occupancy prediction system.

[0173] (Appendix 15) It is a parking lot occupancy prediction system described in Appendix 14, When the prediction processing function determines that the prediction target date and time is the date and time of a specific event, the occupancy information is corrected. Parking lot occupancy prediction system.

[0174] (Appendix 16) The parking lot occupancy prediction system according to Appendix 14 or 15, wherein the prediction processing function predicts the occupancy state of the parking lot during a predetermined period before and after the prediction target date and time. Parking lot occupancy prediction system.

[0175] (Appendix 17) The parking lot occupancy prediction system according to any one of Appendices 14 to 16, wherein the prediction processing function automatically predicts the occupancy state of the parking lot from the current time to a time period determined in advance without being dependent on an external prediction request. Parking lot occupancy prediction system.

[0176] (Appendix 18) The parking lot occupancy prediction system according to any one of Appendices 14 to 17, wherein the data collection function collects sales information of a store co-located with the parking lot, and the prediction processing function predicts the sales of the store at the prediction target date and time based on the predicted occupancy state of the parking lot and the sales information. Parking lot occupancy prediction system.

Explanation of reference numerals

[0177] 1 Occupancy Information, 2 Weather Information, 3 Sales Information, 11 Entrance / Exit Sensor, 12 Parking Space Sensor, 20 User, 21 Temperature and Humidity Sensor, 22 Sunshine Sensor, 23 Rainfall Sensor, 31 Store Sales Management, 100 Parking Lot Occupancy Prediction Device, 110 Data Collection Function, 111 Data Acquisition Unit, 112 Data Storage Unit, 120 Data Management Function, 121 Database, 122 Data Storage Interface Unit, 123 Data Readout Interface Unit, 130 Prediction Processing Function, 131 Prediction Request Receiver, 132 Prediction Processing Unit, 133 Prediction Result Output Unit, 200 Operation and Break Plan Creation Device, 210 Operation and Break Plan Creation Function, 211 Plan Creation Request Receiver, 212 Operation Route Plan Creation Unit, 213 Plan Creation Processing Unit, 214 Plan Creation Result Output Unit, 220 Prediction Result Collection Function, 221 Prediction Result Acquisition Unit, 222 List of Parking Lot Occupancy Prediction Devices, 1102A Processing Circuit, 1102B Processing Circuit, 1103 Storage Device, 1104A Input Device, 1104B Input Device, 1105A Output Device, 1105B Output Device, 1106A Measuring Device, 1106B Measuring Device.

Claims

1. A data collection function for collecting occupancy information, which is information indicating the past occupancy status of a parking lot, A data management function for recording the occupancy information as time-series data, And a prediction processing function for predicting the occupancy status of the parking lot at a prediction target date and time, which is a specified date and time, based on the recorded occupancy information. A parking lot occupancy prediction device.

2. The parking lot occupancy prediction device according to claim 1, wherein the prediction processing function corrects the occupancy information when the prediction target date and time is the opening date and time of a specific event. A parking lot occupancy prediction device.

3. The parking lot occupancy prediction device according to claim 1 or 2, wherein the prediction processing function predicts the occupancy status of the parking lot during a predetermined period before and after the prediction target date and time. A parking lot occupancy prediction device.

4. The parking lot occupancy prediction device according to claim 1 or 2, wherein the prediction processing function automatically predicts the occupancy status of the parking lot from the current time to a time after a predetermined period without depending on an external prediction request. A parking lot occupancy prediction device.

5. The parking lot occupancy prediction device according to claim 1 or 2, wherein the data collection function collects past sales information of a store annexed to the parking lot, and the prediction processing function predicts the sales of the store based on the predicted occupancy status of the parking lot and the sales information. A parking lot occupancy prediction device.

6. The parking lot occupancy prediction device according to claim 1 or 2, The prediction processing function uses a pre-trained model created in advance by machine learning based on the recorded full / empty information to output the full / empty state of the parking lot with the prediction target date and time as the input. Parking lot full / empty prediction device.

7. The parking lot full / empty prediction device according to claim 1 or 2, when there is a plurality of the full / empty information corresponding to the prediction target date and time, the prediction processing function predicts the full / empty state of the parking lot at the prediction target date and time based on the average value of the plurality of the full / empty information corresponding to the prediction target date and time. Parking lot full / empty prediction device.

8. The parking lot full / empty prediction device according to claim 1 or 2, when there is a plurality of the full / empty information corresponding to the prediction target date and time, the prediction processing function predicts the full / empty state of the parking lot at the prediction target date and time based on the full / empty information closest to the day of the week of the prediction target date and time. Parking lot full / empty prediction device.

9. The parking lot full / empty prediction device according to claim 1 or 2, the prediction processing function predicts the full / empty state of the parking lot at the prediction target date and time based on the full / empty information and the weather information of the prediction target date and time. Parking lot full / empty prediction device.

10. creating an operation and rest plan based on the full / empty state at the prediction target date and time output from the parking lot full / empty prediction device according to claim 1 or 2. Operation and rest plan creation device.

11. The operation and rest plan creation device according to claim 10, being configured integrally with the parking lot full / empty prediction device. Operation and rest plan creation device.

12. The operation and rest plan creation device according to claim 10, When the full / empty state is less than a predetermined threshold value, create the operation and rest plan that uses the parking lot as a rest place. An operation and rest plan creation device.

13. An operation and rest plan creation device according to Claim 10, When the rest place cannot be set in the operation and rest plan, shift the departure time of the operation and rest plan and create the operation and rest plan again. An operation and rest plan creation device.

14. A data collection function for collecting full / empty information which is information indicating the past full / empty state of a parking lot, A data management function for recording the full / empty information as time-series data, A prediction processing function for predicting the full / empty state of the parking lot at a prediction target date and time which is a specified date and time based on the recorded full / empty information, and each of the data collection function, the data management function, and the prediction processing function is provided in a different device and can communicate with each other via a network, A parking lot full / empty prediction system.

15. A parking lot full / empty prediction system according to Claim 14, where the prediction processing function corrects the full / empty information when the prediction target date and time is the opening date and time of a specific event. A parking lot full / empty prediction system.

16. A parking lot full / empty prediction system according to Claim 14 or 15, where the prediction processing function predicts the full / empty state of the parking lot in a predetermined period before and after the prediction target date and time. A parking lot full / empty prediction system.

17. A parking lot full / empty prediction system according to Claim 14 or 15, The prediction processing function automatically predicts the occupancy status of the parking lot from the current time to a time in advance determined period, regardless of a prediction request from the outside. Parking lot occupancy prediction system.

18. The parking lot occupancy prediction system according to claim 14 or 15, wherein the data collection function collects sales information of a store annexed to the parking lot, and the prediction processing function predicts the sales of the store on the prediction target date and time based on the predicted occupancy status of the parking lot and the sales information. Parking lot occupancy prediction system.

Images