Congestion level estimation device, congestion level estimation system, congestion level estimation method, and program

Abstract

To provide a congestion estimation device, congestion estimation system, congestion estimation method and program, which improve accuracy in estimating congestion.SOLUTION: A congestion estimation device is provided, comprising a reception unit configured to receive detection information acquired when a detection unit detects users in a main space crowed with users within a facility where a plurality of users can stay, an identification unit for identifying user types of the users according to the detection information, and an estimation unit configured to estimate the degree of congestion of the facility based on the user types.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present disclosure relates to a congestion level estimation device, a congestion level estimation system, a congestion level estimation method, and a program. [Background technology]

[0002] With the spread of GPS (Global Positioning System) and other technologies, there is a growing trend to use individual location information for various services. For example, Patent Document 1 discloses a facility congestion level information providing device that can estimate the congestion level for each facility even when there is little location information data available. The facility congestion level information providing device obtains the correspondence between the number of visitors and the average stay time, as well as current visitor information, and estimates the congestion level based on these. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-4168 Summary of the Invention [Problem to be solved by the invention]

[0004] However, there is a need for further improvement in the accuracy of congestion estimation.

[0005] The present disclosure has been made to solve the above-mentioned problems, and aims to provide a congestion level estimation device, a congestion level estimation system, a congestion level estimation method, and a program that can improve the accuracy of congestion level estimation. [Means for solving the problem]

[0006] According to one aspect of the present disclosure, a congestion degree estimation device includes a receiving unit that receives detection information acquired by a detection unit detecting users in a main space where the users are concentrated in a facility where multiple users can stay, a determining unit that determines the user type of the users based on the detection information, and an estimating unit that estimates the congestion degree of the facility based on the user type. an entry / exit time measurement unit that measures the entry / exit times of the users based on the detection information; a stay time calculation unit that calculates the stay time of the users from the entry / exit times of the users; a number of users information calculation unit that calculates number of users information based on the detection information; an average stay time calculation unit that calculates an average stay time for each user type; and an allowable number of users calculation unit that calculates the allowable number of users in the main space based on the number of users information. Equipped with The determination unit determines the user type based on whether the user is accompanied by a child or whether the user is using a stroller, and the estimation unit estimates the congestion level based on the entry and exit times, the average stay time, and the allowable number of people. .

[0007] According to one aspect of the present disclosure, a congestion level estimation system includes the congestion level estimation device described above and the detection unit.

[0008] According to one aspect of the present disclosure, in a facility where multiple users can stay, a method includes receiving detection information obtained by a detection unit detecting users in a main space where the users are concentrated; determining the user type of the users based on the detection information; and estimating the congestion level of the facility based on the user type. a step of measuring the entry and exit times of the users based on the detection information, a step of calculating the stay time of the users from the entry and exit times of the users, a step of calculating information on the number of users based on the detection information, a step of calculating the average stay time for each user type, and a step of calculating the capacity number of people in the main space based on the number of people information. With In the step of determining the user type, the user type is determined based on whether the user is accompanied by a child or whether the user is using a stroller, and in the step of estimating the congestion level, the congestion level is estimated based on the entry and exit times, the average stay time, and the allowable number of people. .

[0009] According to one aspect of the present disclosure, the program includes the steps of: receiving detection information obtained by a detection unit detecting users in a main space where the users are concentrated in a facility where multiple users can stay; determining a user type of the users based on the detection information; and estimating a congestion level of the facility based on the user type; a step of measuring the entry and exit times of the users based on the detection information, a step of calculating the stay time of the users from the entry and exit times of the users, a step of calculating information on the number of users based on the detection information, a step of calculating the average stay time for each user type, and a step of calculating the capacity number of people in the main space based on the number of people information. The computer of the congestion degree estimation device executes the above. In the step of determining the user type, the computer is caused to determine the user type based on whether the user is accompanied by a child or whether the user is using a stroller, and in the step of estimating the degree of congestion, the computer is caused to estimate the degree of congestion based on the entry and exit times, the average stay time, and the allowable number of people. . [Effects of the Invention]

[0010] According to the congestion level estimation device, congestion level estimation system, congestion level estimation method, and program of the present disclosure, it is possible to improve the accuracy of congestion level estimation. [Brief explanation of the drawings]

[0011] [Figure 1]1 is a diagram illustrating an overall configuration of a congestion level estimation system according to an embodiment of the present disclosure. [Figure 2] FIG. 1 is a diagram showing a restaurant, which is an example of a main space within a facility according to an embodiment of the present disclosure. [Figure 3] FIG. 10 is a diagram illustrating point cloud data of a user detected by a detection unit according to an embodiment of the present disclosure. [Figure 4] FIG. 10 is a diagram illustrating point cloud data of a stroller detected by a detection unit according to an embodiment of the present disclosure. [Figure 5] 1 is a diagram illustrating an overall configuration of a congestion level estimation system and a functional configuration of a congestion level estimation device according to an embodiment of the present disclosure. [Figure 6] FIG. 2 is a diagram illustrating a functional configuration of a processor of the congestion level estimation device according to an embodiment of the present disclosure. [Figure 7] FIG. 10 is a diagram illustrating an example of a database related to processing of the congestion level estimation device according to an embodiment of the present disclosure. [Figure 8] FIG. 2 is a first flowchart illustrating an example of processing of the congestion level estimation device according to the embodiment of the present disclosure. [Figure 9] FIG. 10 is a second flowchart illustrating an example of the processing of the congestion degree estimation device according to the embodiment of the present disclosure. [Figure 10] FIG. 10 is a third flowchart illustrating an example of processing of the congestion degree estimation device according to the embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, a congestion level estimation system 10 and a congestion level estimation device 20 according to an embodiment of the present disclosure will be described with reference to the drawings. FIG. 1 is a diagram illustrating an overall configuration of a congestion level estimation system according to an embodiment of the present disclosure. As shown in FIG. 1, the congestion level estimation system 10 includes a detection unit 11, a congestion level estimation device 20, a control device 12, and an external device 13.

[0013] The congestion level estimation system 10 and the congestion level estimation device 20 are used to estimate the congestion level of a facility 1 where multiple users A can stay. In this embodiment, a service area (SA) attached to a highway will be described as an example of the facility 1 where multiple users A can stay.

[0014] Within facility 1, there are multiple main spaces S1 where users of facility 1 are concentrated. Each main space S1 has a different capacity for user A. In this embodiment, a restaurant 2, a passageway 3, and an event venue 4 are provided as main spaces S1 within facility 1. In other words, main space S1 is a space that provides the main purpose of facility 1, or a point for entering and exiting this space. Passageway 3 connects restaurant 2 and event venue 4. The congestion level estimation device 20 collects and processes information for each main space S1 and estimates the congestion level of the entire facility 1. The following describes an example in which the congestion level estimation device 20 collects and processes information about the restaurant 2 in the main space S1.

[0015] FIG. 2 is a diagram showing a restaurant, which is an example of a main space in a facility according to an embodiment of the present disclosure. As shown in FIG. 2, restaurant 2 is provided with a first entrance 2a for direct entrance and exit from the parking lot to restaurant 2, and a second entrance 2a for entrance and exit from passage 3 to restaurant 2. In addition, a waiting space S2 is provided near first entrance 2a. Waiting space S2 is provided outside restaurant 2. Waiting space S2 is connected to restaurant 2 via first entrance 2a.

[0016] In this embodiment, a detection unit 11 is provided for each main space S1. The detection unit 11 detects the user A and acquires detection information. The detection information includes, for example, appearance information of each user A. In this embodiment, the detection unit 11 is, for example, a sensor that measures distance in three dimensions. More specifically, the detection unit 11 is a 3D-LiDAR (Light Detection And Ranging). Therefore, in this embodiment, the detection unit 11 can acquire the position and distance of each user A without interruption of the movement line.

[0017] FIG. 3 is a diagram illustrating point cloud data of a user detected by a detection unit according to an embodiment of the present disclosure. 3, the detection unit 11 acquires appearance information of the user A and appearance information of the objects as point cloud data. The point cloud data reflects information such as the height L of each user A and the size of each object.

[0018] 4 is a diagram showing point cloud data of a stroller B detected by a detection unit according to an embodiment of the present disclosure. In FIG. 4, only the silhouette of the person pushing the stroller is shown, and point cloud data representing the person is omitted. When a user is using stroller B, the detection unit 11 can also acquire the stroller B as point cloud data. As shown in Fig. 4, the tire B1 of stroller B acquired as point cloud data by the detection unit 11 is acquired as individual point cloud data that can be distinguished from parts of stroller B other than the tire B1. The detection unit 11 sequentially transmits the detection information to the congestion level estimation device 20. In this embodiment, the detection unit 11 acquires the detection information at intervals of, for example, once every 50 msec, and transmits it to the congestion level estimation device 20. The frequency at which the detection unit 11 acquires and transmits the detection information can be changed as appropriate.

[0019] Returning to FIG. 2 , the congestion level estimation device 20 is a so-called center server (computer). The congestion level estimation device 20 processes the detection information transmitted from the detection unit 11 and determines, for each main space S1, information on the number of users A and whether or not the users A are accompanied by children. Furthermore, the congestion level estimation device 20 estimates the congestion level of the entire facility 1 based on the information of each main space S1 obtained by processing the detection information. In this embodiment, the congestion level estimation device 20 estimates the current congestion level of the facility 1 and calculates a congestion rate. The congestion level estimation device 20 of this embodiment also calculates an expected stay time and can estimate the future congestion level of the facility 1 based on the expected stay time. The future congestion level is also calculated as a congestion rate. The functional configuration of the congestion level estimation device 20 will be described in detail later. The congestion level estimation device 20 transmits information such as the congestion level of the facility 1 and the expected stay time obtained by processing the detection information to the control device 12.

[0020] The control device 12 is installed in a control room that controls each system and device in the facility 1. The control device 12 includes a display unit 12a. The display unit 12a displays information such as the congestion level of the facility 1 and the expected stay time transmitted from the congestion level estimation device 20. The information displayed on the display unit 12a is visible to users in the control room. The control device 12 transmits information from the congestion level estimation device 20 and other information based on the information from the congestion level estimation device 20 to the external device 13. In this embodiment, the control device 12 can select whether or not to transmit information to the external device 13.

[0021] Examples of external device 13 include a main line bulletin board installed on the main line of a highway, an antenna for a transportation system, etc. The main line bulletin board displays information such as the degree of congestion and expected stay time at facility 1 based on information from, for example, control device 12. The antenna transmits information such as the degree of congestion and expected stay time at facility 1 in real time to a car navigation system of a vehicle traveling on the main line of the highway based on information from, for example, control device 12. In other words, this antenna is a device that transmits information to vehicles traveling on the highway.

[0022] (Functional configuration of the congestion level estimation device) The functional configuration of the congestion level estimation device 20 will be described with reference to FIG. FIG. 5 is a diagram illustrating an overall configuration of a congestion level estimation system and a functional configuration of a congestion level estimation device according to an embodiment of the disclosure. As shown in FIG. 5, the congestion level estimation device 20 includes a processor 21, a main memory 22, a storage 23, and a communication interface 24.

[0023] The processor 21 is, for example, a CPU, and executes each process of the congestion level estimation device 20. The function of the processor 21 will be described later.

[0024] The main memory 22 has a memory area necessary for the operation of the processor 21 .

[0025] The storage 23 is a so-called auxiliary storage device. Examples of the storage 23 include a magnetic disk, a magneto-optical disk, a semiconductor memory, etc. The storage 23 may be an internal medium directly connected to a bus of the computer, or an external medium connected to the congestion level estimation device 20 (computer) via a communication interface 24 or a communication line.

[0026] The communication interface 24 is an interface for transmitting and receiving information to and from the detection unit 11 and the control device 12 that are installed outside the congestion level estimation device 20.

[0027] Next, we will explain the functions of the processor 21. The processor 21 performs the following functions by operating in accordance with a predetermined program.

[0028] FIG. 6 is a diagram illustrating a functional configuration of a processor of the congestion level estimation device according to the embodiment of the disclosure. As shown in Figure 6, the processor 21 has functions as a receiving unit 30, a discrimination unit 31, an entry / exit time measurement unit 32, a stay time calculation unit 33, a number of people information calculation unit 34, an average stay time calculation unit 35, an allowable number of people calculation unit 36, an expected stay time calculation unit 37, an estimation unit 38, a notification unit 39, and an analysis unit 40.

[0029] The receiving unit 30 receives detection information acquired by the detection unit 11 notifying the user of the main space S1.

[0030] The discrimination unit 31 discriminates the user type of user A based on the detection information. In this embodiment, the discrimination unit 31 discriminates the user type based on whether or not user A is accompanied by a child or whether or not user A is using a stroller. Note that the discrimination unit 31 may also discriminate the user type based on either whether or not user A is accompanied by a child or whether or not user A is using a stroller. The discrimination unit 31 discriminates the child A1 based on the height information included in the detection information. Furthermore, the determination unit 31 determines whether or not the user A is using the stroller B based on the appearance information of the user A included in the detection information.

[0031] The entry / exit time measurement unit 32 measures the entry / exit times of user A based on the detection information.

[0032] The stay time calculation unit 33 calculates the stay time of the user A from the entry and exit times of the user A.

[0033] The number of people information calculation unit 34 calculates the number of people information of the user A based on the detection information.

[0034] The average stay time calculation unit 35 calculates the average stay time for each user type.

[0035] The allowable number-of-people calculation unit 36 ​​calculates the allowable number of people in the main space S1 based on the information about the number of users A.

[0036] The expected stay time calculation unit 37 calculates the expected stay time of the user by referring to the stay times by user type that are defined as expected stay times by user type.

[0037] FIG. 7 is a diagram illustrating an example of a database related to the processing of the congestion level estimation device according to the embodiment of the present disclosure. In this embodiment, the staying time by user type is stored in a database shown in FIG. 7. The database in FIG. 7 is stored, for example, in storage 23. There are three types of times by user type: adults only, those with children, and those using strollers. The times by user type differ for each main space S1. FIG. 7 shows a specific example of the times by user type when the main space S1 is restaurant 2. The calculation of the expected staying time by referring to the times by user type will be described in detail later.

[0038] The processes of the discrimination unit 31, the entry / exit time measurement unit 32, the stay time calculation unit 33, the number of people information calculation unit 34, the average stay time calculation unit 35, the allowable number of people calculation unit 36, and the expected stay time calculation unit 37 are performed for each main space S1. That is, the entry / exit time, stay time, number of people information, average stay time, allowable number of people, and expected stay time are calculated for each main space S1.

[0039] The estimation unit 38 estimates the congestion level of the facility 1 based on the user type. In this embodiment, the estimation unit 38 estimates the current congestion level of the facility 1 based on the entry and exit times, the average stay time calculated for each user type, and the capacity number of people in the main space S1. In this embodiment, the estimation unit 38 can also estimate the future congestion level of the facility 1 based on the expected stay time.

[0040] The notification unit 39 notifies the outside of the congestion level of the facility 1. In this embodiment, the notification unit 39 notifies the control device 12 of the congestion level of the facility 1.

[0041] The analysis unit 40 analyzes the information calculated by each functional unit. In this embodiment, the analysis unit 40 analyzes, for example, the number of people, the length of stay, and the type of user, and provides feedback to the processing required to estimate the congestion level.

[0042] (Processing flow of the congestion level estimation device) The flow of processing by the congestion level estimation device 20 will be described below with reference to FIGS.

[0043] FIG. 8 is a first flowchart illustrating an example of the process of the congestion degree estimation device 20 according to the embodiment of the present disclosure. First, the receiving unit 30 receives the detection information transmitted from the detecting unit 11 (step S10). In this embodiment, the detection information is acquired and processed for each main space S1. In the following description of the processing flow of the congestion degree estimation device 20, unless otherwise specified, the main space S1 will be described as a restaurant 2.

[0044] Next, the discrimination unit 31 discriminates the user type of the user A based on the detection information (step S11). In step S11, the discrimination unit 31 first discriminates the child A1 from among the people to be detected based on the height information included in the detection information.

[0045] FIG. 9 is a second flowchart illustrating an example of the process of the congestion degree estimation device according to the embodiment of the present disclosure. When the discrimination unit 31 discriminates a child A1, the flow shown in FIG. 9 is executed. The discrimination unit 31 determines whether the height L (see FIG. 3) is equal to or less than a predetermined threshold (step S110). In this embodiment, the predetermined threshold is set to, for example, 120 cm. The predetermined threshold can be changed as appropriate. If the height L is equal to or less than the predetermined threshold (step S110; YES), the discrimination unit 31 discriminates the person to be discriminated as a child (step S111). If the height L is not equal to or less than the predetermined threshold (step S110; NO), the discrimination unit 31 discriminates the person to be discriminated as an adult A2 (step S112). The discrimination unit 31 discriminates whether the user A is only the adult A2 or is accompanied by a child based on the discrimination result of the child A1 or the adult A2 and the distance between the people. After the discrimination unit 31 discriminates whether the person to be discriminated is a child A1 or an adult A2, it determines whether the object in the detection area of ​​the detection unit 11 is a stroller.

[0046] FIG. 10 is a third flowchart illustrating an example of the process of the congestion degree estimation device according to the embodiment of the present disclosure. When the discrimination unit 31 discriminates the stroller B, the flow shown in FIG. 10 is executed. First, the discrimination unit 31 determines whether the object to be discriminated has three or four pieces of point cloud data indicating the tire B1 (step S113). If the object to be discriminated does not have three or four pieces of point cloud data indicating the tire B1 (step S113; NO), the discrimination unit 31 discriminates that the object to be discriminated is not the stroller B (step S114). If the object to be discriminated has three or four pieces of point cloud data indicating the tire B1 (step S113; YES), the discrimination unit 31 determines whether the shape of the point cloud data of the object to be discriminated is similar to the specification values ​​of the stroller B (step S115). If the shape of the point cloud data of the object to be discriminated is not similar to the specification values ​​of the stroller B (step S115; NO), the discrimination unit 31 discriminates that the object to be discriminated is not the stroller B (step S114). If the shape of the point cloud data of the object to be identified is similar to the specification values ​​of the stroller (step S115; YES), the discrimination unit 31 determines whether the point cloud data of the object to be identified is adjacent to the adult A2 (step S116). If the point cloud data of the object to be identified is not adjacent to the adult A2 (step S116; NO), the discrimination unit 31 determines that the object to be identified is not the stroller B (step S114). If the point cloud data of the object to be identified is adjacent to the adult A2 (step S116; YES), the discrimination unit 31 determines that the object to be identified is the stroller B (step S117). Based on the discrimination result of whether the object is the stroller B, the discrimination unit 31 determines whether the user A, who is the adult A2 adjacent to the stroller B, is the user of the stroller B. After the determination unit 31 determines the user type in this way, the process returns to the flow of FIG.

[0047] Next, the entry / exit time measurement unit 32 measures the entry and exit times of user A based on the detection information (step S12). Specifically, the entry / exit time measurement unit 32 measures the time when user A moves from waiting space S2 to restaurant 2 or from aisle 3 to restaurant 2 as the entry time of user A, and measures the time when user A moves from restaurant 2 to waiting space S2 or from restaurant 2 to aisle 3 as the exit time.

[0048] Next, the stay time calculation unit 33 calculates the stay time of user A from the entry and exit times of user A (step S13).

[0049] Next, the number of people information calculation unit 34 calculates the number of people information of user A based on the detection information (step S14). Note that step S14 may be performed before step S12.

[0050] Next, the average stay time calculation unit 35 calculates the average stay time for each user type based on the stay time of each user A and the number of people information for each user type (step S15).

[0051] Next, the allowable number-of-people calculation unit 36 ​​calculates the allowable number of people in the main space S1 based on the number-of-people information of users A calculated by the number-of-people information calculation unit 34 (step S16). For example, the allowable number-of-people calculation unit 36 ​​calculates the allowable number of people in the main space S1 from the difference between the preset number of people that the main space S1 can accommodate and the number of users A actually present in the accommodation space S1. The allowable number-of-people calculation unit 36 ​​may refer to the user type of each user A when calculating the allowable number of people in the main space S1.

[0052] Next, the expected stay time calculation unit 37 calculates the expected stay time of user A by referring to the stay times by user type defined as expected stay times by user type (step S17).

[0053] In this embodiment, the expected stay time calculation unit 37 calculates the expected stay time by referring to the stay times by user type stored in the database of FIG. 7. The expected stay time calculation unit 37 calculates the expected stay time by adding up the stay times by user type and the added time. Note that if the user type corresponds to both people with children and people using strollers, the longer time by user type is used to calculate the expected stay time. The added time is a time determined by the conditions and circumstances of the main space S1. In the case of the restaurant 2, the added time is set mainly taking into consideration, for example, the time it takes to serve food. Note that in the case of the corridor 3 or the event venue 4, the added time is set mainly taking into consideration, for example, the congestion situation.

[0054] In the example shown in Figure 7, when a group of four people visit Restaurant 2, if the group includes one child and one stroller user, the expected stay time is calculated as 20 minutes (stay time by user type: with child or stroller user) + 15 minutes (additional time) = 35 minutes.

[0055] Next, the estimation unit 38 estimates the congestion level of the facility 1 based on the user type (step S18). In this embodiment, the estimation unit 38 estimates the current congestion level of the facility 1 based on the entry and exit times, the average stay time calculated for each user type, and the capacity number of people in the main space S1. Furthermore, the estimation unit 38 estimates the future congestion level of the facility 1 based on the expected stay time. When the estimation unit 38 estimates the congestion level, information such as the entry and exit times, the average stay time, and the capacity number of people in the main space S1 is processed for each main space S1. The estimation unit 38 calculates the current and future congestion rates of the facility 1 as a specific congestion rate, for example, 80%. Note that the estimation unit 38 may calculate the congestion level not only for the entire facility 1 but also for each main space S1.

[0056] After estimating the congestion level, the notification unit 39 notifies the control device 12 of the congestion level of the facility 1 (step S19). In this embodiment, the notification unit 39 notifies the control device 12 of the congestion level of the facility 1. The notification unit 39 notifies the control device 12 of the expected stay time together with the congestion rate (%) indicating the congestion level of the facility 1. The information such as the congestion rate (%) and expected stay time of the facility 1 notified to the control device 12 is selected by the user of the control device 12 and transmitted to the external device 13 (main line bulletin board, antenna for the traffic system, etc.). As a result, the information such as the congestion rate (%) and expected stay time of the facility 1 is notified to the driver and passengers of the vehicle in motion via the external device 13. The driver and passengers of the vehicle can determine whether to use the facility 1 and the timing to use the facility 1 based on the notified information.

[0057] After the congestion level is notified, the analysis unit 40 analyzes the information calculated by each functional unit (step S20). In this embodiment, the analysis unit 40 analyzes, for example, the number of people information, the length of stay, and the user type, and feeds back the results to the processing required to estimate the congestion level. Specifically, the analysis unit 40 stores the number of people information, the length of stay, and the user type for each breakdown of the number of people (for example, out of a total of ** people, ** children and ** strollers), for example, in the storage 23, and performs processing such as returning the average results to each functional unit. Based on the feedback from the analysis unit 40, the method for calculating the congestion level is corrected, and the information in the database shown in FIG. 7 is updated to an appropriate value. When the notification unit 39 notifies the outside of the congestion level, the flow shown in FIG. 8 ends.

[0058] The congestion level estimation device 20 constantly receives detection information at the receiving unit 30 and starts processing at regular intervals (for example, once per minute). In this way, the congestion level estimation device 20 repeatedly executes the series of processes shown in the flowchart of Fig. 8 at regular intervals.

[0059] (Action and effect) As described above, the congestion level estimation device 20 includes a receiving unit 30 that receives detection information, a discrimination unit 31 that discriminates the user type of user A based on the detection information, and an estimation unit 38 that estimates the congestion level of facility 1 based on the user type.

[0060] It is expected that the length of stay of user A will vary depending on each individual's circumstances. According to this embodiment, the congestion level estimation device 20 can estimate the congestion level of facility 1 by taking into account information on the user type. This can improve the accuracy of the congestion level estimation by the congestion level estimation device 20.

[0061] The congestion degree estimation device 20 further includes an entry / exit time measurement unit 32 that measures the entry and exit times of user A based on the detection information, a stay time calculation unit 33 that calculates the stay time of user A from the entry and exit times of user A, a number of people information calculation unit 34 that calculates the number of people information of user A based on the detection information, an average stay time calculation unit 35 that calculates the average stay time for each user type, and an allowable number of people calculation unit 36 ​​that calculates the allowable number of people in the main space S1 based on the number of people information of user A, and the discrimination unit 31 discriminates the user type based on whether user A is with a child or whether user A is using a stroller B, and the estimation unit 38 estimates the congestion degree based on the entry / exit times, the average stay time, and the allowable number of people in the main space S1.

[0062] If user A is with a child or is using a stroller, user A's stay time tends to be longer. According to this embodiment, the congestion degree estimation device 20 can determine whether user A is with a child or whether user A is using a stroller as a user type and take this into consideration when estimating the congestion degree. Furthermore, the congestion degree estimation device 20 can estimate the congestion degree of the facility 1 by taking into consideration information on the entry and exit times, the average stay time, and the capacity of the main space S1 in addition to the user type. In this way, the congestion degree estimation device 20 can estimate the congestion degree of the facility 1 by taking into consideration multiple factors. Therefore, the accuracy of the congestion degree estimation by the congestion degree estimation device 20 can be further improved.

[0063] In addition, the congestion degree estimation device 20 further includes an expected stay time calculation unit 37 that calculates the expected stay time of user A by referring to the stay time by user type defined as the expected stay time by user type, and the estimation unit 38 estimates the future congestion degree based on the expected stay time.

[0064] In this way, the congestion level estimation device 20 can estimate the future congestion level.

[0065] The congestion level estimation device 20 further includes an analysis unit 40 that analyzes the number of people information, the stay time, and the user type, and feeds back the results to the process required for estimating the congestion level.

[0066] In this way, the accuracy of congestion degree estimation by the congestion degree estimation device 20 can be further improved.

[0067] Furthermore, the discrimination unit 31 discriminates the child A1 based on height information included in the detection information.

[0068] In this way, the congestion degree estimation device 20 can distinguish between children A1 using the clear criterion of height L. This allows the congestion degree estimation device 20 to clearly and easily determine whether the user type is a person with a child or not. Therefore, the congestion degree estimation device 20 can efficiently estimate the congestion degree.

[0069] Furthermore, the determination unit 31 determines whether or not the user A is using the stroller B based on the appearance information of the user A included in the detection information.

[0070] In this way, the congestion degree estimation device 20 can determine whether stroller B is being used or not using the appearance information as a clear criterion. This allows the congestion degree estimation device 20 to clearly and easily determine whether user A is using stroller B or not. Therefore, the congestion degree estimation device 20 can efficiently estimate the congestion degree.

[0071] The congestion level estimation device 20 further includes a notification unit 39 that notifies the outside of the congestion level.

[0072] In this way, the congestion level estimation device 20 can notify the outside of the estimated congestion level, thereby providing people who are planning to use the facility 1 with useful information when deciding whether or not to actually use the facility 1 and when to use the facility 1.

[0073] Furthermore, the detection unit 11 acquires appearance information of the user A as point cloud data.

[0074] In this way, the detection unit 11 can accurately acquire appearance information of user A while reducing the volume of detection information. This allows the detection unit 11 to efficiently transmit the detection information, and the congestion level estimation device 20 to efficiently process the received detection information. Therefore, the congestion level estimation system 10 can perform congestion level estimation even more efficiently.

[0075] The detection unit 11 is a 3D-LiDAR, and transmits detection information to the congestion level estimation device 20 successively.

[0076] In this way, the detection unit 11 can sequentially transmit the detection information to the congestion level estimation device 20. This allows the congestion level estimation device 20 to estimate the congestion level in real time. Therefore, the accuracy of the congestion level estimation by the congestion level estimation system 10 can be further improved.

[0077] As described above, the embodiments of the present disclosure have been described, but these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents as defined in the claims, as well as in the scope and spirit of the invention.

[0078] In the above embodiment, a service area (SA) has been described as an example of the facility 1 in which the congestion level estimation system 10 and the congestion level estimation device 20 are used, but the present invention is not limited to this. The facility 1 in which the congestion level estimation system 10 and the congestion level estimation device 20 are used may be, for example, a service area (PA) or a highway oasis (HO).

[0079] In the above embodiment, the main space S1 within the facility 1 is described as including a restaurant 2, a corridor 3, and an event venue 4, but this is not limited to this and may also include, for example, a shop or a dog run.

[0080] In the above embodiment, the detection unit 11 is a sensor that measures distance in three dimensions, such as a 3D-LiDAR, but is not limited to this. The detection unit 11 may be, for example, a camera, and the information acquired as the detection information may be a simple video or still image.

[0081] In the above embodiment, the congestion level estimation device 20 is a so-called center server (computer), but is not limited to this and may be a portable computer such as a laptop computer.

[0082] In the above embodiment, the control device 12 transmits information such as the congestion level of the facility 1 received from the congestion level estimation device 20 to the external device 13, and the external device 13 displays the information transmitted from the control device 12. However, the present invention is not limited to this. Information such as the congestion level of the facility 1 may be transmitted directly from the congestion level estimation device 20 to the external device 13.

[0083] In the above embodiment, the detection unit 11 estimates the congestion level of the facility 1 based on the detection information acquired by detecting the user A in the main space S1 (such as the restaurant 2), but the present invention is not limited to this. For example, when the main space S1 is crowded and the user A is waiting in the waiting space S2, the detection unit 11 may estimate the congestion level of the facility 1 based on the detection information of the user A in the waiting space S2.

[0084] <Additional Notes> The congestion level estimation device 20, the congestion level estimation system 10, the congestion level estimation method, and the program described in each embodiment can be understood, for example, as follows.

[0085] According to a first aspect of the present disclosure, the congestion degree estimation device 20 includes a receiving unit 30 that receives detection information obtained by a detection unit 11 detecting a user A in a main space S1 where the users A are concentrated within a facility 1 where multiple users A can stay, a discrimination unit 31 that discriminates the user type of the user A based on the detection information, and an estimation unit 38 that estimates the congestion degree of the facility 1 based on the user type. Examples of the facility 1 include free rest facilities located on expressways, such as service areas (SA), parking areas (PA), and highway oases (HO). Examples of the main space S1 include a restaurant 2, a passageway 3, an event venue 4, a shop, a dog run, etc.

[0086] The length of stay of user A is expected to vary depending on each individual's circumstances. According to this aspect, the congestion level estimation device 20 can estimate the congestion level of the facility 1 by taking into account information on the user type. This can improve the accuracy of the congestion level estimation by the congestion level estimation device 20.

[0087] According to a second aspect of the present disclosure, the congestion degree estimation device 20 according to the first aspect further includes an entry / exit time measurement unit 32 that measures the entry and exit times of the user A based on the detection information, a stay time calculation unit 33 that calculates the stay time of the user A from the entry and exit times of the user, a number of people information calculation unit 34 that calculates number of people information of the user A based on the detection information, an average stay time calculation unit 35 that calculates the average stay time for each user type, and an allowable number of people calculation unit 36 ​​that calculates the allowable number of people for the main space S1 based on the number of people information, wherein the discrimination unit 31 discriminates the user type based on whether the user A is accompanied by a child or whether the user A is using a stroller B, and the estimation unit 38 estimates the congestion degree based on the entry / exit times, the average stay time, and the allowable number of people.

[0088] If user A is with a child or is using stroller B, user A's stay time tends to be longer. According to this aspect, the congestion degree estimation device 20 can determine whether user A is with a child or whether the user is using a stroller as a user type and take this into consideration when estimating the congestion degree. Furthermore, the congestion degree estimation device 20 can estimate the congestion degree of the facility 1 by taking into consideration information on the entry and exit times, the average stay time, and the capacity of the main space S1 in addition to the user type. In this way, the congestion degree estimation device 20 can estimate the congestion degree of the facility 1 by taking into consideration multiple factors. Therefore, the congestion degree estimation accuracy of the congestion degree estimation device 20 can be further improved.

[0089] According to a third aspect of the present disclosure, the congestion degree estimation device 20 relating to the second aspect further includes an expected stay time calculation unit 37 that calculates the expected stay time of user A by referring to a stay time by user type defined as the expected stay time for each user type, and the estimation unit 38 estimates the future congestion degree based on the expected stay time.

[0090] In this way, the congestion level estimation device 20 can estimate the future congestion level.

[0091] According to a fourth aspect of the present disclosure, the congestion degree estimation device 20 according to the second or third aspect further includes an analysis unit 40 that analyzes the number of people information, the stay time, and the user type and provides feedback to the processing required to estimate the congestion degree.

[0092] In this way, the accuracy of congestion degree estimation by the congestion degree estimation device 20 can be further improved.

[0093] According to a fifth aspect of the present disclosure, in the congestion level estimation device 20 according to any one of the second to fourth aspects, the discrimination unit 31 discriminates children based on height information included in the detection information.

[0094] In this way, the congestion degree estimation device 20 can distinguish between children using the clear criterion of height L. This allows the congestion degree estimation device 20 to clearly and easily determine whether the user type is a person with a child or not. Therefore, the congestion degree estimation device 20 can efficiently estimate the congestion degree.

[0095] According to a sixth aspect of the present disclosure, in a congestion level estimation device 20 relating to any one of the second to fifth aspects, the discrimination unit 31 determines whether or not the user A is using a stroller B from the appearance information of the user A included in the detection information.

[0096] In this way, the congestion degree estimation device 20 can determine whether stroller B is being used or not using the appearance information as a clear criterion. This allows the congestion degree estimation device 20 to clearly and easily determine whether user A is using stroller B or not. Therefore, the congestion degree estimation device 20 can efficiently estimate the congestion degree.

[0097] According to a seventh aspect of the present disclosure, the congestion level estimation device 20 according to any one of the first to sixth aspects further includes a notification unit 39 that notifies the outside of the congestion level.

[0098] In this way, the congestion level estimation device 20 can notify the outside of the estimated congestion level, thereby providing people who are planning to use the facility 1 with useful information when deciding whether or not to actually use the facility 1 and when to use the facility 1.

[0099] According to an eighth aspect of the present disclosure, a congestion level estimation system 10 includes any one of the first to seventh congestion level estimation devices 20 and the detection unit 11.

[0100] According to a ninth aspect of the present disclosure, in the congestion level estimation system 10 according to the eighth aspect, the detection unit 11 acquires appearance information of the user as point cloud data.

[0101] In this way, the detection unit 11 can accurately acquire appearance information of user A while reducing the volume of detection information. This allows the detection unit 11 to efficiently transmit the detection information, and the congestion level estimation device 20 to efficiently process the received detection information. Therefore, the congestion level estimation system 10 can perform congestion level estimation even more efficiently.

[0102] According to a tenth aspect of the present disclosure, in the congestion level estimation system 10 relating to the eighth or ninth aspect, the detection unit 11 is a 3D-LiDAR and sequentially transmits the detection information to the congestion level estimation device 20.

[0103] In this way, the detection unit 11 can sequentially transmit the detection information to the congestion level estimation device 20. This allows the congestion level estimation device 20 to estimate the congestion level in real time. Therefore, the accuracy of the congestion level estimation by the congestion level estimation system 10 can be further improved.

[0104] According to an eleventh aspect of the present disclosure, a congestion degree estimation method includes the steps of receiving detection information obtained by a detection unit 11 detecting a user A in a main space S1 where the users A are concentrated within a facility 1 where multiple users A can stay, determining the user type of the user A based on the detection information, and estimating the congestion degree of the facility 1 based on the user type.

[0105] According to a twelfth aspect of the present disclosure, the program causes a computer of a congestion degree estimation device 20 to perform the following steps: receiving detection information obtained by a detection unit 11 detecting user A in a main space S1 where user A is concentrated within a facility 1 where multiple users can stay; determining the user type of user A based on the detection information; and estimating the congestion degree of the facility 1 based on the user type. [Explanation of symbols]

[0106] 1 facility 2. Restaurants 2a entrance / exit 3 aisles 4. Event venue 10 Congestion estimation system 11. Detection unit 12 Control device 12a Display section 13 External device 20. Congestion estimation device 21 processors 22 Main Memory 23. Storage 24 Communication Interface 30 Receiving unit 31 Discrimination part 32 Entry / Exit Time Measurement Unit 33 Stay time calculation unit 34 Number of people information calculation section 35 Average stay time calculation section 36 Capacity Calculation Section 37 Estimated Stay Time Calculation Unit 38 Estimation part 39 Notification Department 40. Analysis Department S1 Main Space S2 standby space

Claims

1. a receiving unit that receives detection information acquired by detecting users in a main space where the users are concentrated in a facility where multiple users can stay, using a detecting unit; a determination unit that determines a user type of the user based on the detection information; an estimation unit that estimates a congestion level of the facility based on the user type; an entry / exit time measurement unit that measures the entry / exit times of the users based on the detection information; a stay time calculation unit that calculates the stay time of the user from the entry and exit times of the user; a number-of-users information calculation unit that calculates number-of-users information based on the detection information; an average stay time calculation unit that calculates an average stay time for each user type; an allowable number of people calculation unit that calculates the allowable number of people in the main space based on the number of people information; Equipped with the determination unit determines the user type based on whether the user is accompanied by a child or whether the user is using a stroller; the estimation unit estimates the congestion degree based on the entry and exit times, the average stay time, and the allowable number of people. Congestion estimation device.

2. an expected stay time calculation unit that calculates an expected stay time of the user by referring to a stay time by user type that is defined as the stay time expected for each user type; The estimation unit estimates the future congestion degree based on the expected stay time. The congestion level estimation device according to claim 1 .

3. An analysis unit that analyzes the number of people information, the staying time, and the user type and feeds back the information to a process required for estimating the congestion degree. The congestion level estimation device according to claim 1 or 2.

4. The discrimination unit discriminates the child based on height information included in the detection information. The congestion level estimation device according to claim 1 .

5. the determination unit determines whether the user is using a stroller based on appearance information of the user included in the detection information. The congestion level estimation device according to claim 1 .

6. The congestion level estimation device according to claim 1 , further comprising a notification unit that notifies an external device of the congestion level.

7. The congestion degree estimation device according to any one of claims 1 to 6, The detection unit; A congestion estimation system comprising:

8. The detection unit acquires appearance information of the user as point cloud data. The congestion level estimation system according to claim 7 .

9. The detection unit is a 3D-LiDAR and sequentially transmits the detection information to the congestion degree estimation device. The congestion level estimation system according to claim 7 or 8.

10. receiving detection information acquired by detecting users in a main space where the users are concentrated by a detection unit in a facility where multiple users can stay; determining a user type of the user based on the detection information; estimating a congestion level of the facility based on the user type; measuring the entry and exit times of the users based on the detection information; calculating the stay time of the user from the entry and exit times of the user; calculating information about the number of users based on the detection information; calculating an average stay time for each user type; Calculating the number of people allowed in the main space based on the number of people information; and In the step of determining the user type, the user type is determined based on whether the user is accompanied by a child or whether the user is using a stroller; In the step of estimating the congestion level, the congestion level is estimated based on the entry and exit times, the average stay time, and the allowable number of people. Congestion estimation method.

11. receiving detection information acquired by detecting users in a main space where the users are concentrated by a detection unit in a facility where multiple users can stay; determining a user type of the user based on the detection information; estimating a congestion level of the facility based on the user type; measuring the entry and exit times of the users based on the detection information; calculating the stay time of the user from the entry and exit times of the user; calculating information about the number of users based on the detection information; calculating an average stay time for each user type; calculating the capacity of the main space based on the number of people information; In the step of determining the user type, the computer is caused to determine the user type based on whether the user is accompanied by a child or whether the user is using a stroller; In the step of estimating the congestion level, the computer is caused to estimate the congestion level based on the entry and exit times, the average stay time, and the allowable number of people. program.

Images