JP2017204168A - Taxi demand estimation system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a taxi demand estimation system capable of estimating demand of a taxi even for an area that taxi business does not sufficiently cover.SOLUTION: The taxi demand estimation system comprises: a ride information acquisition part 2 for acquiring ride information indicating the number of people in a taxi for each area; a facility information acquisition part 3 for acquiring facility information related to a facility including information indicating the position of a facility; an estimation part 4 for estimating the area expected to have demand of a taxi on the basis of the ride information in each area acquired by the ride information acquisition part 2 and the facility information related to the facility inside and outside each area acquired by the facility information acquisition part 3; and an output part 5 for outputting information indicating the area estimated by the estimation part 4.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a taxi demand estimation system that estimates the demand for taxis.

  Conventionally, there is a system that estimates taxi demand from business performance data indicating the business performance of a taxi. For example, Patent Document 1 discloses a system that predicts a location where a taxi is expected to be boarded. This system calculates the taxi ride probability for each area from business performance data, and analyzes items such as weather conditions, other transportation conditions, and time and other factors that have a causal relationship with the ride.

JP 2014-130552 A

  With the system described in Patent Document 1, it is possible to estimate the demand for taxis in an area where taxis are operating, but it is difficult to estimate the demand for taxis in areas where taxis are not sufficiently operated. . For this reason, it is desired to estimate the demand for a taxi, that is, the location where the taxi is expected to be taken even in an area where the taxi is not sufficiently operated.

  An object of this invention is to provide the taxi demand estimation system which can estimate the demand of a taxi also about the area where the business of a taxi is not enough.

  In order to achieve the above object, a taxi demand estimation system according to the present invention is a facility related to a facility including boarding information acquisition means for acquiring boarding information indicating the number of taxis boarding for each area, and information indicating the position of the facility. Based on the facility information acquisition means for acquiring information, the boarding information in each area acquired by the boarding information acquisition means, and the facility information related to the facilities inside and outside each area acquired by the facility information acquisition means, An estimation unit that estimates an area in which demand is expected, and an output unit that outputs information indicating the area estimated by the estimation unit.

  The taxi demand estimation system according to the present invention estimates an area where taxi demand is expected by paying attention to facilities, so taxis are not sufficiently operated and taxi information is also available for areas where there is no taxi information. Demand can be estimated.

  The facility information acquisition unit may acquire facility information including information indicating the type of facility, and the estimation unit may estimate an area where taxi demand is expected based on the type of facility. In this case, for example, an area having the same type of facility as the factor causing the demand for taxis can be estimated as an area where the demand for taxis is expected.

  The facility information acquisition means acquires facility information including information indicating the feature quantity indicating the feature of the facility, and the estimation means obtains a relational expression between the feature quantity of the facility in the area and the number of taxi rides in the area. Estimate the estimated number of taxis related to the facilities outside the area from the feature quantities of the facilities outside the area using the estimated relational expression, and estimate the taxi demand from the estimated number of taxis May be estimated. In this case, for example, an area including a facility with a large estimated number of taxi rides can be estimated as an area where demand for taxis is expected.

  The facility information acquisition means acquires facility information including information indicating the number of persons related to the facility, and the estimation means estimates an area where taxi demand is expected based on the number of persons related to the facility outside the area. May be. In this case, for example, an area including a facility with a large number of people involved in the facility can be estimated as an area where demand for taxis is expected.

  The facility information acquisition means acquires facility information including information indicating the number of persons related to the facility, and the estimation means is expected to demand taxi from the facility based on the number of persons related to the facilities in the area. You may extract the facility in the area used for area estimation. In this case, for example, a facility with a large number of persons involved in the facility can be extracted as a facility in the area used for estimation. As a result, an area where taxi demand is expected can be accurately estimated.

  A boarding information acquisition means may acquire the information which shows the boarding position of a taxi, cluster a boarding position, and may acquire boarding information. In this case, it is possible to handle the boarding information having the same facilities that cause taxi demand as a group. As a result, an area where taxi demand is expected can be accurately estimated.

  In the present invention, it is possible to estimate the demand for taxis even in areas where taxis are not sufficiently operated.

It is a block diagram of the taxi demand estimation system concerning an embodiment. It is a figure which shows the hardware constitutions of a server. It is a figure which shows the example of an event occurrence point table. It is a figure for demonstrating the spatial clustering of sales data. It is a figure which shows the example of an event occurrence point cluster table. It is a figure which shows the example of the average expectation value table classified by category. It is a figure which shows the example of a high contribution facility list table. It is a figure which shows the example of a facility feature-value table. It is a figure which shows the example of a latent facility list table. It is a flowchart which shows operation | movement of a taxi demand estimation system.

  Hereinafter, embodiments of a taxi demand estimation system according to the present invention will be described in detail with reference to the drawings. In the description of the drawings, the same elements are denoted by the same reference numerals, and redundant description is omitted.

  FIG. 1 is a block diagram of a taxi demand estimation system according to the embodiment. A taxi demand estimation system (hereinafter also simply referred to as “system”) 1 is for estimating the demand for taxis, and specifically, a computer system for estimating an area where the demand for taxis is expected. It is.

  FIG. 2 is a diagram illustrating a hardware configuration of the taxi demand estimation system. As shown in FIG. 2, the system 1 includes one or more CPUs (Central Processing Units) 101, a RAM (Random Access Memory) 102 and a ROM (Read Only Memory) 103, which are main storage devices, for communication. The communication module 104 includes a computer including hardware 105 such as an auxiliary storage device such as a hard disk. When these components operate according to a program or the like, the functions of the functional elements of the system 1 in FIG. 1 are exhibited. The system 1 may be configured by a computer system including a plurality of computers. Hereinafter, each functional element and each database shown in FIG. 1 will be described.

  As shown in FIG. 1, the system 1 includes a boarding information acquisition unit 2, a facility information acquisition unit 3, an estimation unit 4, an output unit 5, a business data storage unit 11, a facility information storage unit 12, It has.

  The business data storage unit 11 is a device that stores taxi business data (business results data). The sales data includes boarding position information including, for example, latitude and longitude, and a boarding time information indicating a boarding time that is a time when the passenger boarded the taxi. Specifically, the business data storage unit 11 stores business data in an event occurrence point table as shown in FIG. The method for storing the sales data in the sales data storage unit 11 is not limited. For example, each time a passenger gets in a taxi, a terminal provided in each taxi may generate business data, and the generated business data may be transmitted to the business data storage unit 11 via a communication network.

  The boarding information acquisition unit 2 is boarding information acquisition means for acquiring boarding information indicating the number of taxi rides for each area. The boarding information acquisition part 2 acquires the information which shows the boarding position of a taxi, clusters boarding positions, and acquires boarding information. Specifically, first, the boarding information acquisition unit 2 acquires sales data from the sales data storage unit 11. The boarding information acquisition part 2 acquires the business data for one week before that, for example for every week. The boarding information acquisition part 2 may acquire sales data at the predetermined timing determined in advance as described above, or may acquire sales data at other timings. Moreover, the boarding information acquisition part 2 may acquire the sales data of the predetermined period which was previously determined among the sales data memorize | stored in the sales data memory | storage part 11, or the sales data of all periods May be.

  Subsequently, the boarding information acquisition unit 2 classifies (stratifies) the acquired business data for each day of the week and time zone, and spatially clusters the classified business data. With reference to FIG. 4, the spatial clustering of sales data will be described. In FIG. 4, the boarding positions of a plurality of sales data corresponding to the day of the week and the time zone when the boarding time is indicated by points (event occurrence points) corresponding positions on the map. The boarding information acquisition unit 2 generates clusters C <b> 1 to C <b> 5 as a set of points located in a spatially close range from these multiple points. Spatial clustering is performed using, for example, a well-known mean shift method.

  The boarding information acquisition unit 2 generates a cluster by performing spatial clustering of sales data for each day of the week and time, and for each generated cluster, the position of the center of gravity of the cluster, the size of the cluster, and the number of event occurrence points in the cluster That is, the number of taxi rides is obtained. The cluster centroid position is the average position of event occurrence points included in the cluster. The size of the cluster is the distance between the event occurrence point farthest from the center of gravity position and the center of gravity position among the event occurrence points included in the cluster. The boarding information acquisition unit 2 generates cluster information shown in the event occurrence point cluster table of FIG. The cluster information includes the centroid position information indicating the centroid position of the cluster, for example, latitude and longitude, the day of the week, the time zone, the cluster ID indicating the cluster, the size of the cluster, and the number of event occurrence points in the cluster. Become.

  FIG. 5 is a diagram illustrating an example of an event occurrence point cluster table. Here, the time zone is set every hour. For example, “1” indicates a time zone in the range of 1 am (a time zone after 1 am and before 2 am). The time period may be set according to the distribution of the number of sales data so that the number of sales data becomes a meaningful number. For example, a midnight time zone with a small number of business data may be set as one time zone. Further, the time zone may be set by dividing the day into n (n is a natural number) so that the distribution of the number of business data in each time zone is uniform. The boarding information acquisition unit 2 sends business data and cluster information to the estimation unit 4.

  The facility information storage unit 12 is a device that stores facility information related to a facility (for example, POI: point of interest). The facility information includes, for example, position information indicating the location of the facility, for example, latitude and longitude, a category indicating the type of facility, a feature amount indicating the feature of the facility, information indicating the number of persons involved in the facility, and the like. The category is, for example, a station, a hotel, a mall, a hospital, an embassy, a temple, a museum, or the like. The feature amount will be described later. The facility information storage unit 12 stores these facility information in association with each facility. The method for storing facility information in the facility information storage unit 12 is not limited. For example, the administrator of the system 10 can store the facility information in the facility information storage unit 12 in advance.

  Specifically, the facility information storage unit 12 stores the number of check-ins to the facility as information indicating the number of people involved in the facility. Check-in is a post made to notify that a user of an SNS (Social Networking Service) has visited a specific facility. Since a facility with a large number of check-ins is a facility where many such postings have been made, the number of check-ins can be considered as a parameter indicating the popularity of the facility. A facility with a large number of check-ins is a facility visited by many people, and can be a factor in demand for taxis. The number of check-ins is a value uniquely specified by the facility regardless of the day of the week and the time zone. In addition, since the number of check-ins is generally disclosed by the SNS, for example, the administrator of the system 10 obtains the number of check-ins and stores it in the facility information storage unit 12 in advance together with other facility information. can do. Or the facility information storage part 12 may acquire the said information from the server of SNS holding the information of the number of check-ins of a facility.

  The facility information acquisition unit 3 acquires facility information related to a facility including information indicating the location of the facility, information indicating the type of the facility, information indicating the feature of the facility, and information indicating the number of persons involved in the facility. Means. Specifically, the facility information acquisition unit 3 acquires facility information from the facility information storage unit 12. The facility information acquisition unit 3 may acquire the facility information at a predetermined timing in synchronization with the boarding information acquisition unit 2 acquiring the boarding information, or may acquire the facility information at other timings. You may get it. The facility information acquisition unit 3 sends the acquired facility information to the estimation unit 4.

  Based on the boarding information in each area (cluster) acquired by the boarding information acquisition unit and the facility information regarding the facilities inside and outside each area acquired by the facility information acquisition unit, the estimation unit 4 determines the demand for taxis. It is an estimation means for estimating the expected area. The facility information includes category information indicating the type of facility. First, the estimation unit 4 inputs cluster information from the boarding information acquisition unit 2 and inputs facility information from the facility information acquisition unit 3. Subsequently, the estimation unit 4 detects a facility in the cluster for each cluster indicated by the cluster information from the facilities indicated by the facility information based on the input facility information and cluster information. A facility in a cluster is a facility located within a range of a distance d that is the size of the cluster from the center of gravity of the cluster (a circle having the center of gravity of the cluster as the center and the distance d as a radius). Here, the estimation part 4 may extract the cluster used for said estimation among clusters. For example, a preset number of clusters having a higher number of sales data included in the cluster (that is, a cluster in which a taxi is often used) may be used for the above estimation.

  Subsequently, the estimation unit 4 estimates a relational expression (demand estimation function) between the feature amount of the facility in the cluster and the number of taxi rides in the cluster. Here, according to the relational expression estimated based on facilities that are unlikely to contribute to taxi rides, there is a possibility that the estimation accuracy of the number of taxi rides for facilities in areas where taxi sales are not sufficiently performed may be reduced. . Therefore, the estimation unit 4 extracts, from the facility, a facility used for estimating an area where taxi demand is expected, based on the number of persons related to the facility in the area. Specifically, the estimation unit 4 extracts, from among the facilities in the cluster, high-contribution facilities that are highly likely to contribute to taxi rides, particularly focusing on the number of check-ins and categories of the facilities. Perform high-precision filter processing. According to the high-precision filter processing, it is possible to eliminate facilities that are unlikely to contribute to taxi rides.

The high accuracy filtering process will be described. The estimation unit 4 inputs business data from the boarding information acquisition unit 2. The estimation unit 4 is based on the business data and has a predetermined distance (for example, 100 m or less) within a predetermined distance from each of the facilities in all the clusters indicated by the cluster information (a circle centered on the facility and having a radius of the predetermined distance). An average expected value, which is an average value of the number of taxi rides generated in the city, is obtained for each category, day of the week, and time zone. The estimation unit 4 stores the obtained average expected value in a category-specific average expected value table as shown in FIG. Subsequently, the estimation unit 4 obtains the contribution degree to the taxi ride in the corresponding category, day of the week, and time zone for each facility in the cluster from the following formula (1). However, the number of facilities in the cluster is n (n is a natural number), the number of check-ins is x _p , the average expected value is x _e , and the contribution is x _c . Facilities with a check-in number of 0 are excluded from the contribution calculation. That is, when x _p = 0, x _c = 0 regardless of the following formula (1). Alternatively, the contribution may be normalized by dividing the contribution by the sum of contributions of all facilities in the cluster so that the sum of contributions of all facilities in the cluster becomes 1.
x _c = log (x _p ) * x _e (1)

  The estimation unit 4 extracts, for each cluster, a facility having a top N contribution (N is a preset natural number) as a high contribution facility. According to such high-accuracy filter processing, not only the popularity but also the category, day of the week, and time zone are taken into account, so that highly contributing facilities can be extracted with high accuracy. For example, if a station, a hamburger shop, and a bar are detected as facilities in the same cluster on Friday and midnight, the station and bar are extracted as highly contributing facilities by performing high-precision filter processing. Can do. Note that the estimation unit 4 may store the business hours of the facility in advance, and exclude the facility by high-accuracy filter processing when it is outside the business hours. The high contribution facility information indicating the high contribution facility extracted by the estimation unit 4 in this way is information of a high contribution facility list table (POI list table) as shown in FIG. The highly contributing facility information includes the name of the highly contributing facility, the location information of the highly contributing facility, the number of check-ins, the category, the day of the week, the time zone, and the cluster ID.

  Subsequently, the estimation unit 4 sets the feature amount of each high-contributing facility as an explanatory variable (x), and sets the number of taxi rides in the cluster corresponding to each high-contributing facility as a target variable (y). The relational expression between the feature amount of the highly contributing facility and the number of taxi rides is estimated for each day of the week, time zone, and facility category. The feature amount of the high-contribution facility as an explanatory variable is, for example, the distance to the nearest school (x0), the distance to the nearest commercial facility (x1), the distance to the nearest station (x2), or the closest station. Number of trains per day (x3), distance to nearest bus stop (x4), number of buses per day at nearest bus stop (x5), population by weekday time zone (morning, noon, evening, night, midnight) (X6_1, x6_2, ...), weekday holiday differential population (x7), and generation (0's, 10's, 20's, 30's ... 90's and above) population (x8_0, x8_1, ...) , X8_9). The population data (x6, x7, and x8) may be, for example, government-published values, or for each mesh based on mobile spatial statistics data that estimates the demographic population of Japan nationwide from mobile phone operation data by time zone. It may be calculated in the following manner. For x6, for example, the estimation unit 4 may estimate the relational expression by reducing the weight of the feature amount in a time zone other than the time zone to be estimated, or the time zone to be estimated is determined in advance. Then, as x6, only the corresponding feature amount may be set as the explanatory variable. Further, if the target to be estimated is a weekday, the estimation unit 4 may estimate the relational expression by reducing the weight of x7, for example, or may not set x7 as an explanatory variable. Specifically, the relational expression is estimated by expressing these explanatory variables (x0 to x8) in a linear combination form and learning parameters related to each explanatory variable by regression analysis. For regression analysis, multiple regression analysis, Random Forest, Support Vector Regression, etc. are generally used. As described above, the facility information storage unit 12 stores the feature amount of each facility including the highly contributing facility in advance. The facility information storage unit 12 stores, for example, the name and feature amount of each facility in association with the facility feature amount table shown in FIG.

  Subsequently, the estimation unit 4 uses the estimated relational expression to estimate the number of taxi occupying the facility outside the area from the feature amount of the facility outside the area, and based on the estimated number of taxi occupancy, Estimate areas where demand is expected. Specifically, the estimation unit 4 detects a facility that is not included in the cluster indicated by the cluster information as a facility outside the area from the facilities indicated by the facility information. The estimation unit 4 uses the relational expressions estimated for each day of the week, time zone, and category to calculate the number of taxi rides as the estimated number of rides for each facility outside the area for each day of the week, time zone, and category.

  The estimation unit 4 extracts a facility whose calculated number of rides (score) is equal to or greater than a preset threshold among the facilities outside the area as a potential facility that may cause a taxi demand. The estimation unit 4 estimates an area including the facility, for example, an area in the vicinity of the facility as an area where demand for taxis is expected. The latent facility information, which is information indicating the potential facilities extracted by the estimation unit 4, is information of a potential facility list table as shown in FIG. The latent facility information includes the name of the facility, day of the week, time zone, location information, category, and estimated number of rides. The estimation unit 4 sends the generated latent facility information to the output unit 5.

  The output unit 5 is an output unit that outputs information indicating a facility estimated by the estimation unit as information indicating an area where a taxi demand is expected. Specifically, the output unit 5 may input the latent facility information from the estimation unit 4, and may distribute the latent facility information to terminals provided in each taxi via, for example, a communication network. The output unit 5 may output the latent facility information by means other than this.

  FIG. 10 is a flowchart showing the operation of the taxi demand estimation system. As shown in FIG. 10, first, the system 1 acquires sales data from the sales data storage unit 11 by the boarding information acquisition unit 2 at a predetermined timing, and generates a cluster (S11). The facility information acquisition unit 3 acquires the facility information from the facility information storage unit 12 (S12). Next, the system 1 detects facilities in the cluster by the estimation unit 4 based on the facility information and the cluster information, and extracts a highly contributing facility from the detected facilities (S13). Subsequently, the system 1 estimates the relational expression between the feature amount of the highly contributing facility and the number of taxi rides by the estimation unit 4 (S14), and uses the estimated relational expression to estimate the taxi ride for the facility outside the area. The number is calculated (S15). Further, the system 1 extracts potential facilities based on the estimated number of taxi rides by the estimation unit 4 (S16). The system 1 outputs the potential facility information through the output unit 5 (S17).

  As described above, the latent facility information output by the system 1 is information indicating a potential facility that can be a factor of taxi demand. The output of the potential facility information by the system 1 corresponds to the system 1 estimating the vicinity of the potential facility as an area where demand for taxis is expected. In this way, the system 1 estimates the area where taxi demand is expected by paying attention to the facilities, so the taxi demand can be estimated even in areas where the taxi business is not sufficient and there is no business data. It is. Since the system 1 performs high-accuracy filtering processing, it is possible to extract high-contribution facilities used for estimation of an area where taxi demand is expected in consideration of not only popularity but also category, day of the week, and time zone. . As a result, an area where taxi demand is expected can be accurately estimated. In addition, the system 1 generates a cluster by clustering event occurrence points included in the business data. For this reason, it is possible to handle taxi boarding information having the same facilities that cause taxi demand as a group. As a result, it is possible to estimate the area where taxi demand is expected more accurately.

  As mentioned above, although embodiment of this invention was described, this invention is not limited to the said embodiment, It deform | transforms in the range which does not change the summary described in each claim, or applied to another thing. There may be.

  For example, the system 1 may estimate the demand for a taxi at the timing requested by the administrator. Specifically, the system 1 outputs latent facility information using a predetermined time from that time as an estimation target time zone. For example, when the time is 1 pm on Wednesday, the system 1 sets the time zone for estimation to 1 pm on Wednesday. As described above, since the estimation target day of the week and time zone are one, the processing load of the system 1 is reduced. Here, when the estimation unit 4 extracts a potential facility that may be a factor of taxi demand from facilities outside the area, the calculated number of rides (score) is simply greater than or equal to a preset threshold value. Instead of extracting a facility, a facility having a calculated number of rides (score) equal to or greater than a preset threshold and the number of human flow data equal to or greater than a preset threshold may be extracted. The number of human flow data is the number of people staying around the facility during the latest t minutes from that point. According to the number of human flow data, the state of the latest facility can be reflected in the estimation result of the system 1.

  For example, a smartphone possessed by the user performs positioning periodically (for example, every few minutes) and transmits a smartphone log obtained by positioning to the system 1 in advance. The estimation part 4 receives the smart phone log containing the positional information acquired by positioning point extraction functions, such as smart phone GPS and WiFi, and is predetermined distance (for example, 100 m or less) predetermined from the facility from the smart phone log. The number of human flow data for the last 30 minutes within the range is acquired. Note that the number of people who have already moved on vehicles such as cars and trains may be removed from the number of people flow data by making a movement determination. Specifically, for example, the number of human flow data of a person whose speed obtained by the smartphone log within the latest t minutes is equal to or less than a threshold is extracted as the number of human flow data around the facility. It is also possible to perform the stay determination and calculate the number of human flow data. For example, the number of human flow data of people who are located in the above range for a certain time or longer is extracted as the number of human flow data around the facility. Further, the number of human flow data may be used as a score, and weighting may be performed so that the influence on the score is eliminated as the distance from the facility increases. In addition, for example, it is possible to obtain an average value of the number of human flow data for one month for one month by using a smartphone log, and use it as data related to the population in the feature amount of the facility described above.

  For example, the system 1 does not necessarily have to consider both day of the week and time. The system 1 may consider only one of the day of the week and time, or may estimate the area where demand for taxis is expected without considering both the day of the week and time. Moreover, the system 1 should just consider at least any one of facility information, and does not necessarily need to consider the category of a facility. Moreover, the boarding information acquisition part 2 may classify sales data for every predetermined rectangular mesh area, without performing spatial clustering of sales data. In addition, the estimation unit 4 may extract, for example, the top N check-in facilities among the facilities in the cluster as high-contribution facilities without performing the high-precision filter processing.

  Further, in the above-described embodiment, the number of persons related to the facility is set to the number of check-ins and the number of human flow data for each process used for calculation, but may be replaced. That is, the number of people flow data may be used where the number of check-ins is used, and the number of check-ins may be used where the number of people flow data is used. Further, the number of persons involved in the facility may be other than the number of check-ins and the number of human flow data.

DESCRIPTION OF SYMBOLS 1 ... Taxi demand estimation system, 2 ... Boarding information acquisition part, 3 ... Facility information acquisition part, 4 ... Estimation part, 5 ... Output part.

Claims (6)

Boarding information acquisition means for acquiring boarding information indicating the number of taxis in each area;
Facility information acquisition means for acquiring facility information about the facility including information indicating the location of the facility;
Based on the boarding information in each area acquired by the boarding information acquisition means and the facility information related to the facilities inside and outside each area acquired by the facility information acquisition means, an area where a taxi demand is expected is estimated. An estimation means;
Output means for outputting information indicating the area estimated by the estimation means;
Taxi demand estimation system equipped with. The facility information acquisition means acquires the facility information including information indicating a type of the facility,
The taxi demand estimation system according to claim 1, wherein the estimation means estimates an area where taxi demand is expected based on the type of facility. The facility information acquisition means acquires the facility information including information indicating a feature amount indicating the feature of the facility,
The estimation means estimates a relational expression between the feature amount of the facility in the area and the number of taxi rides in the area, and uses the estimated relational expression to calculate the feature amount of the facility outside the area from the feature area. The taxi demand estimation system according to claim 1 or 2, wherein the number of taxi rides related to the facility is estimated, and an area where taxi demand is expected is estimated from the estimated taxi ride number. The facility information acquisition means acquires the facility information including information indicating the number of persons related to the facility,
The taxi demand estimation system according to any one of claims 1 to 3, wherein the estimation means estimates an area in which taxi demand is expected based on the number of persons related to facilities outside the area. The facility information acquisition means acquires the facility information including information indicating the number of persons related to the facility,
The said estimation means extracts the facility in the said area used for the estimation of the area where the demand of a taxi is anticipated from the said facility based on the number of persons who concern on the facility in an area. Taxi demand estimation system according to one item. The taxi demand estimation system according to any one of claims 1 to 5, wherein the boarding information acquisition unit acquires information indicating a taxi boarding position, and acquires boarding information by clustering the boarding positions.

Images