Event inference system, event inference method, and program

Abstract

The purpose of the present invention is to provide an event inference system that can appropriately provide information about an event that is being held in a prescribed area. This event inference system comprises an event detection unit that detects an event in a prescribed area on the basis of at least one of gathering information that indicates the gathering of people in the prescribed area and posted information that indicates a post related to the prescribed area, a detected event information acquisition unit that acquires detected event information that includes the location and time of the detected event, a past event information acquisition unit that acquires past event information that includes the location and time of an event that was held in the prescribed area in the past on the basis of the detected event information, and an event details inference unit that infers the details of the detected event on the basis of the detected event information and the past event information.

Description

Event Estimation System, Event Estimation Method, and Program

[0001] The present disclosure relates to an event estimation system, an event estimation method, and a program.

[0002] In order to improve the area value in a predetermined area, it is necessary to perform appropriate area management on the area. For example, in order to suppress crimes in the area and maintain a safe and secure town, various actors are required to be involved in the area. Actors include, for example, residents of the area, administrative organs of the area, or visitors to the area.

[0003] In recent years, regional ties have become weak, and it has become difficult to easily connect each actor. In order to increase the area value, countermeasures against such problems are desired. For example, it is conceivable to eliminate the dilution of regional ties by promoting participation in events held in the area for residents and visitors, and lead to an improvement in the area value.

[0004] As a related technology, Patent Document 1 discloses an event determination device that determines whether an event is held at a predetermined location. The event determination device receives predetermined information for determining whether an event is held at a predetermined location, and generates time-series data of the number of visitors to the predetermined location based on the predetermined information. Further, the event determination device compares the pattern of the generated time-series data with the pattern of the time-series data when there was an event in the past, etc., and determines the presence or absence of the event based on the comparison result. Further, the event determination device identifies the genre (sports, concert, etc.) of the event to be held.

[0005] Japanese Patent Application Laid-Open No. 2010-231605

[0006] To effectively encourage residents and visitors to participate in events, it is necessary to properly inform them about the event's content, date and time, and location. However, in the case of spontaneous events held in limited areas, such as those not published in the town's newsletter or on its website, the detailed content of the event may not be widely known. In such cases, residents and others may not know about the event's content or existence, and therefore cannot participate. The technology disclosed in Patent Document 1 does not adequately address this problem.

[0007] The purpose of this disclosure is to provide an event estimation system, an event estimation method, and a program that can appropriately provide information on events held in a given area, in light of the issues described above.

[0008] The event estimation system according to this disclosure includes: an event detection unit that detects events in a predetermined area based on at least one of dwelling information indicating the presence of people in the predetermined area and posting information indicating posts relating to the predetermined area; a detected event information acquisition unit that acquires detected event information including the location and time of the detected event; a past event information acquisition unit that acquires past event information including the location and time of events previously held in the predetermined area based on the detected event information; and an event content estimation unit that estimates the content of the detected event based on the past event information and the detected event information.

[0009] The event estimation method relating to this disclosure includes: an event detection step of detecting an event in a predetermined area based on at least one of dwelling information indicating the presence of people in the predetermined area and posting information indicating posts relating to the predetermined area; a detected event information acquisition step of acquiring detected event information including the location and time of the detected event; a past event information acquisition step of acquiring past event information including the location and time of events previously held in the predetermined area based on the detected event information; and an event content estimation step of estimating the content of the detected event based on the past event information and the detected event information.

[0010] The program relating to this disclosure causes a computer to perform the following steps: an event detection step to detect an event in a predetermined area based on dwelling information indicating the presence of people in the predetermined area and posting information indicating posts relating to the predetermined area; a detected event information acquisition step to acquire detected event information including the location and time of the detected event; a past event information acquisition step to acquire past event information including the location and time of events previously held in the predetermined area based on the detected event information; and an event content estimation step to estimate the content of the detected event based on the past event information and the detected event information.

[0011] The event estimation system, event estimation method, and program described herein can appropriately provide information on events held in a given area.

[0012] Figure 1 is a block diagram showing the configuration of the event estimation system according to this disclosure. Figure 2 is a flowchart showing the processing performed by the event estimation system. Figure 3 is a block diagram showing the overall configuration of the event estimation system according to this disclosure. Figure 4 is a block diagram showing the configuration of the event estimation system. Figure 5 is a diagram showing an example of a post containing an image taken in a predetermined area. Figure 6 is a diagram showing an example of a past event information DB that stores past event information. Figure 7 is a flowchart showing the processing performed by the event estimation device. Figure 8 is a block diagram illustrating the hardware configuration of a computer that implements the event estimation system, etc.

[0013] Embodiments of the present disclosure will be described in detail below with reference to the drawings. In each drawing, the same or corresponding elements are denoted by the same reference numerals. For clarity of explanation, redundant explanations will be omitted where necessary.

[0014] <Embodiment 1> (Event Estimation System 100) Figure 1 is a block diagram showing the configuration of the event estimation system 100 according to the present disclosure. The event estimation system 100 comprises an event detection unit 101, a detected event information acquisition unit 102, a past event information acquisition unit 103, and an event content estimation unit 104.

[0015] The event detection unit 101 detects events in a predetermined area based on at least one of the following: dwelling information indicating the presence of people in the predetermined area, and posting information indicating posts related to the predetermined area.

[0016] The detected event information acquisition unit 102 acquires detected event information, including the location and time of the event detected by the event detection unit 101.

[0017] The past event information acquisition unit 103 acquires past event information, including the location and date of events held in a predetermined area in the past, based on the detected event information acquired by the detected event information acquisition unit 102.

[0018] The event content estimation unit 104 estimates the content of the event detected by the event detection unit 101 based on past event information acquired by the past event information acquisition unit 103 and detected event information acquired by the detected event information acquisition unit 102.

[0019] The event estimation system 100 includes a processor, memory, and storage device (not shown). The storage device stores a computer program on which the processing described herein is implemented. The processor can load the computer program from the storage device into memory and execute the computer program. In this way, the processor realizes the functions of the event detection unit 101, the detected event information acquisition unit 102, the past event information acquisition unit 103, and the event content estimation unit 104.

[0020] Alternatively, the event detection unit 101, the detected event information acquisition unit 102, the past event information acquisition unit 103, and the event content estimation unit 104 may each be implemented with dedicated hardware. Furthermore, some or all of each component may be implemented by general-purpose or dedicated circuits, processors, etc., or combinations thereof. These may be configured by a single chip or by multiple chips connected via a bus. Some or all of each component may be implemented by a combination of the aforementioned circuits, etc., and programs.

[0021] (Processing of the event estimation system 100) The processing performed by the event estimation system 100 will be explained with reference to Figure 2. Figure 2 is a flowchart showing the processing performed by the event estimation system 100.

[0022] First, the event detection unit 101 detects an event in a predetermined area based on at least one of the dwelling information and the posting information (S1). Next, the detected event information acquisition unit 102 acquires detected event information, including the location and time of the detected event (S2).

[0023] Next, the past event information acquisition unit 103 acquires past event information based on the detected event information (S3). Then, the event content estimation unit 104 estimates the content of the detected event based on the past event information and the detected event information (S4).

[0024] As explained above, the event estimation system 100 relating to this disclosure can appropriately provide information on events held in a predetermined area.

[0025] <Embodiment 2> Next, Embodiment 2 will be described. Embodiment 2 is a specific example of Embodiment 1 described above.

[0026] (Event Estimation System 1) The overall configuration of the event estimation system 1 according to this disclosure will be described with reference to Figure 3. Figure 3 is a block diagram showing the overall configuration of the event estimation system 1 according to this disclosure. The event estimation system 1 is an example of the event estimation system 100 described above. The event estimation system 1 comprises an event estimation device 10, a plurality of terminal devices 20-1, 20-2, 20-3, ... and a plurality of beacon devices 30-1, 30-2, 30-3, ...

[0027] Multiple terminal devices 20-1, 20-2, 20-3, ... and multiple beacon devices 30-1, 30-2, 30-3, ... are located in a predetermined area. The predetermined area is, for example, a predetermined region defined by a city, town, or village, but is not limited to this. The predetermined area is any region where the event whose content is to be estimated is detected. The predetermined area may be set appropriately to match the range in which the event estimation system 1 is used.

[0028] Network N is a wired or wireless communication line. The event estimation device 10, the multiple terminal devices 20-1, 20-2, 20-3, ..., and the multiple beacon devices 30-1, 30-2, 30-3, ... each communicate with one another via Network N.

[0029] The event estimation device 10 acquires data from multiple terminal devices 20-1, 20-2, 20-3, ... and multiple beacon devices 30-1, 30-2, 30-3, ... and uses the acquired data to perform the processing described herein. For example, based on the acquired data, the event estimation device 10 detects an event to be held in a predetermined area and estimates the content of the event.

[0030] The events detected by the event estimation device 10 are spontaneous events held in a limited area, such as those not publicly announced in newsletters or on websites. The genre of the event is arbitrary. The event may be, for example, a concert, a street performance, a sports competition, a fireworks display, a karaoke competition, various local festivals, or a limited-time sale at a supermarket. However, it is not limited to these events; the event may also be one that has been publicly announced in newsletters or other publications.

[0031] Furthermore, the events detected by the event estimation device 10 may be traffic events in a predetermined area. Traffic events are events that occur on a road. Traffic events include, for example, traffic accidents. Traffic events include, for example, collisions between vehicles, collisions between people and vehicles, collisions between vehicles and obstacles, or various other events that occur on a road. Traffic events may also include events that do not result in traffic accidents but have a high probability of causing one (such as near misses). Traffic events may also include events such as landslides. The following describes each of the components of the event estimation system 1.

[0032] (Terminal device 20) Each of the multiple terminal devices 20-1, 20-2, 20-3, ... is a terminal device owned by a person in a designated area. The main configuration of each of the multiple terminal devices 20-1, 20-2, 20-3, ... may be the same. Therefore, when there is no need to distinguish each of the multiple terminal devices 20-1, 20-2, 20-3, ..., they may simply be referred to as "terminal device 20". A terminal device 20 may be, for example, a smartphone, mobile phone, tablet device, wearable device, or PC (Personal Computer).

[0033] (Beacon device 30) Each of the multiple beacon devices 30-1, 30-2, 30-3, ... is an example of a communication device installed in a predetermined area. The main configuration of each of the multiple beacon devices 30-1, 30-2, 30-3, ... may be the same. Therefore, when there is no need to distinguish each of the multiple beacon devices 30-1, 30-2, 30-3, ..., each may simply be called "beacon device 30".

[0034] The beacon device 30 is installed in a predetermined area. Multiple beacon devices 30 may be installed in the predetermined area. For example, the beacon device 30 transmits a beacon signal that includes a beacon device ID that identifies each beacon device 30. The beacon device 30 transmits the beacon signal using, for example, Bluetooth®. However, it is not limited to this, and the beacon device 30 may transmit the beacon signal using other wireless communication methods. The beacon device 30 may transmit the beacon signal using light such as infrared light instead of radio waves.

[0035] The number of each component in the event estimation system 1 is not limited to those shown in the diagram and can be any number. For example, the event estimation system 1 may have multiple event estimation devices 10. Also, for example, the event estimation system 1 may have four or more terminal devices 20 and four or more beacon devices 30.

[0036] (Event Estimation Device 10) Figure 4 is a block diagram showing the configuration of the event estimation system 1. The event estimation device 10 comprises an event detection unit 11, a detected event information acquisition unit 12, a past event information acquisition unit 13, an event content estimation unit 14, an information provision unit 15, a communication unit 17, and a storage unit 19. The event estimation device 10 may be configured by, for example, a PC.

[0037] The event detection unit 11 is an example of the event detection unit 101 described above. The event detection unit 11 detects events in a predetermined area based on at least one of the following: dwelling information indicating the presence of people in a predetermined area, and posting information indicating posts related to the predetermined area. The methods for detecting events using dwelling information and the methods for detecting events using posting information will be described below.

[0038] (Event detection using dwelling information) The event detection unit 11 acquires dwelling information using terminal devices 20 held by people in a predetermined area. For example, the event detection unit 11 acquires a terminal device ID that identifies the terminal device 20 and the location information of the terminal device 20 from each terminal device 20. Based on the location information from multiple terminal devices 20, the event detection unit 11 analyzes the dwelling status of people in a predetermined area and acquires the analysis results as dwelling information.

[0039] The dwelling information may include, for example, locations where people are densely packed, the degree of crowding, the rate at which people are increasing, or the duration of the crowded state. The event detection unit 11 may divide a predetermined area into smaller areas and analyze the dwelling situation in each divided area.

[0040] The event detection unit 11 may also acquire dwell time information using passing communication between multiple terminal devices 20. For example, a terminal device 20 may implement passing communication functionality by installing a predetermined application provided by a local government in a predetermined area. However, the terminal device 20 may also be equipped with passing communication functionality from the start. Here, it is assumed that multiple terminal devices 20 each have a predetermined application installed that enables passing communication.

[0041] Multiple terminal devices 20 automatically detect each other via wireless communication through a communication unit (not shown). Wireless communication may use, for example, Bluetooth®. Multiple terminal devices 20 automatically send and receive data to each other. If multiple terminal devices 20 successfully communicate, at least one of the multiple terminal devices 20 transmits a message to the event estimation device 10 indicating that communication was successful.

[0042] As a result, the terminal device 20 can transmit to the event estimation device 10 that it is in proximity to another terminal device 20. The event estimation device 10 receives data from a plurality of terminal devices 20 via the communication unit 17. The event detection unit 11 analyzes the stay situation based on the received data, and obtains that a plurality of people in a predetermined area are in proximity as stay information.

[0043] Further, the event detection unit 11 may obtain the stay information using the beacon device 30 which is a communication device provided in a predetermined area. For example, a plurality of beacon devices 30 are installed at different positions within a predetermined area, and each communicates with a terminal device 20 within a predetermined range. Each beacon device 30 transmits a beacon signal including a beacon device ID for identifying each beacon device 30.

[0044] The event estimation device 10 stores in advance the association between the beacon device ID and the position information of the beacon device 30. Alternatively, the beacon device 30 may transmit to the event estimation device 10 the association between the beacon device ID and the position information of the beacon device 30. The event detection unit 11 analyzes the stay situation based on the received data, and obtains that a plurality of people in a predetermined area are in proximity as stay information.

[0045] The event detection unit 11 may obtain data from each of the plurality of terminal devices 20 and the plurality of beacon devices 30 at a predetermined time interval, and obtain the stay information. The event detection unit 11 detects an event based on the obtained stay information. For example, the event detection unit 11 determines whether the level of people's stay is above a predetermined level. When the people's stay is at a level above a predetermined level, the event detection unit 11 determines that an event has occurred in the area. The event detection unit 11 may make the determination taking into account the speed at which people's stay has occurred, etc. As a result, the event detection unit 11 detects the event in the area.

[0046] (Event Detection Using Submission Information) The event detection unit 11 may detect an event in a predetermined area based on submission information indicating submissions related to the predetermined area. The submission information indicates information submitted to, for example, an SNS (Social Networking Service). The data format of the submission information is arbitrary. For example, the data format of the submission information may include data formats such as text, images, or audio. The image may be a still image or a moving image.

[0047] The submission information may include environmental information representing the environment of a predetermined area. The environmental information may be information that can be perceived by people, or for example, information that can be detected by various sensors provided in the terminal device 20.

[0048] The environmental information is, for example, information related to the sound generated in a predetermined area. The sound is, for example, a sound generated accompanying the holding of an event. For example, the event detection unit 11 acquires submissions such as "It's lively outside" and "The sound of a drum can be heard" as submission information. Also, the event detection unit 11 acquires submissions such as "The sirens of an ambulance can be heard" as submission information corresponding to a traffic event. Note that the environmental information is not limited to information related to sound. The environmental information may be information related to the smell generated in a predetermined area.

[0049] The event detection unit 11 acquires submission information including environmental information, and extracts information related to an event in a predetermined area from the acquired submission information. The event detection unit 11 detects an event based on the extraction result. For example, the event detection unit 11 detects the occurrence of an event using a drum based on submission information such as "The sound of a drum can be heard".

[0050] Also, the environmental information may be information indicated by an image taken in a predetermined area. For example, the event detection unit 11 acquires submission information including an image taken in a predetermined area, and extracts information related to an event in a predetermined area from the image. The event detection unit 11 detects an event based on the extraction result.

[0051] Figure 5 shows an example of a post P1 that includes an image taken in a designated area. Post P1 is a post made by an SNS user about a karaoke competition held at "ABC Cafe". Post P1 includes the post text P11 and the posted image P12.

[0052] Post P11 contains the text "It seems there's a karaoke competition at ABC Cafe" as information about a karaoke competition to be held at a cafe. Post image P12 includes images of signs B1 and B2 placed near the store. Sign B1 contains information about the upcoming karaoke competition. For example, sign B1 includes the date, time, location, and contact information for the karaoke competition. Sign B2 contains information about the cafe's regular business operations, such as the cafe's menu.

[0053] The event detection unit 11 acquires information about the post P1 via the network N and analyzes the post image P12 contained in the post P1. The event detection unit 11 may analyze the post image P12 using any image analysis technique. The event detection unit 11 extracts at least the date and time of the event and the location from the post image P12. The event detection unit 11 may further extract contact information, or, if the post P1 contains other information, it may extract that other information as well. Based on the information extracted from the post P1, the event detection unit 11 detects an event.

[0054] In this example, the event detection unit 11 detects future events from the time of post P1, but it is not limited to this. The event detection unit 11 may also detect events that are currently taking place at the time of post P1.

[0055] Furthermore, if the post P11 contains event information, the event detection unit 11 may extract the date and time and location of the event from the post P11 and detect the event based on the extraction results.

[0056] If the event detection unit 11 detects a completed event, it may store the information of the completed event as past event information in the storage unit 19. Past event information is information about events that have been held in the past within a predetermined area. This allows the event detection unit 11 to improve the accuracy of future event detection. Past event information will be described later.

[0057] The event detection unit 11 outputs detected event information to the detected event information acquisition unit 12 regarding the event it has detected based on at least one of the loitering information and the posting information. The detected event information includes at least the location and time of the detected event. For example, the event detection unit 11 identifies the location and time when a person loitered as the location and time of the event based on the loitering information, and outputs the identification result as detected event information to the detected event information acquisition unit 12.

[0058] The location of an event may be represented, for example, by an address or facility name, or by latitude and longitude. However, the location of an event may also be represented by mesh information that identifies a mesh region obtained by dividing a predetermined area. The timing of an event includes, for example, information about the date and time of the event or the duration of the event. The timing of the event may be the scheduled date and time of the event, or, if the event is already underway, the duration of the event including the time when the event was detected.

[0059] The detected event information may include, but is not limited to, the event name, organizer, or contact information. The event name indicates the name of the event. The organizer indicates the name of the event organizer or organization. The contact information indicates the organizer's contact information or where to register for the event.

[0060] The event detection unit 11 may also identify the location and time of the event based on the posted information and output the identification result as detected event information to the detected event information acquisition unit 12. The event detection unit 11 may also output the location and time of the event to the detected event information acquisition unit 12 using information extracted from the posted information, as explained using the example in Figure 5. The event detection unit 11 is not limited to this, and may also identify the location and time of the event from the Exif (Exchangeable image file format) information of the posted image. The event detection unit 11 may also include information other than the location and time of the event in the detected event information and output it to the detected event information acquisition unit 12.

[0061] Returning to Figure 4, the detected event information acquisition unit 12 is an example of the detected event information acquisition unit 102 described above. The detected event information acquisition unit 12 acquires detected event information, including the location and time of the detected event. For example, the detected event information acquisition unit 12 acquires the detected event information output from the event detection unit 11.

[0062] For example, in the example shown in Figure 5, the detected event information includes "ABC Cafe" as the venue for the karaoke competition, "2024 / 7 / 20 (Sat) 18:00-21:00" as the date and time of the karaoke competition, "XXX-XXXX-XXXX" as the contact phone number, "YYY" as the contact person, and "The 10th ABC Cafe Karaoke Competition" as the event name. These are just examples, so the detected event information acquisition unit 12 may acquire detected event information that does not include some of these details, or it may acquire detected event information that includes other information.

[0063] Furthermore, when an event is detected by the event detection unit 11 based on the dwell time information, the location and time of the event are obtained, but the content of the event is not obtained. When an event occurs, it is assumed that some kind of post about the event has been made on SNS. Therefore, the detected event information acquisition unit 12 can search for SNS posts based on the location and time of the detected event and acquire detected event information based on the extracted posts.

[0064] For example, the detected event information acquisition unit 12 searches for posting information based on the distance between the location of the detected event and the posting location, and the time difference between the time of the detected event and the posting date and time. For example, the detected event information acquisition unit 12 searches for posting information using the search conditions that the distance is within a predetermined range and the time difference is within a predetermined range. The detected event information acquisition unit 12 acquires detected event information based on posting information that satisfies these search conditions.

[0065] By narrowing down the search for posting information based on the event's location and timing, the detected event information acquisition unit 12 can accurately extract posting information related to the target event. Therefore, the number of postings acquired by the detected event information acquisition unit 12 can be relatively small.

[0066] Furthermore, on social networking services (SNS), even posts about the same event can vary in content depending on the poster. The event detection unit 12 may determine whether multiple different posts refer to the same event by calculating the similarity of the posts. For example, the event detection unit 12 may use methods such as tf-idf (term frequency-inverse document frequency) and cosine similarity to determine whether multiple different posts refer to the same event.

[0067] Furthermore, the detection event information acquisition unit 12 may acquire detection event information using data detected by sensors (not shown) installed in a predetermined area, not limited to SNS. The sensors (not shown) may be, for example, cameras installed in a predetermined area. For example, when an event is detected based on the dwell time information, the detection event information acquisition unit 12 acquires an image captured by a camera installed at or near the location of the detected event. The detection event information acquisition unit 12 extracts detection event information based on the captured image.

[0068] Furthermore, the detected event information acquisition unit 12 may acquire information on traffic events, not limited to events such as the karaoke competition described above. For example, the detected event information acquisition unit 12 acquires detected event information that includes information on traffic events in a predetermined area and weather information for the area where the traffic event was detected. The weather information includes, for example, information on weather conditions such as sunny, cloudy, rainy, windy, or snowy. The weather information may also include information such as rainfall, wind speed, snowfall, or temperature.

[0069] The past event information acquisition unit 13 is an example of the past event information acquisition unit 103 described above. Based on the detected event information, the past event information acquisition unit 13 acquires past event information, including the location and time of events held in a predetermined area in the past. For example, the past event information acquisition unit 13 refers to the past event information DB 191 and extracts past event information based on the location and time of the detected event.

[0070] The past event information acquisition unit 13 may also acquire past event information, including information on traffic events that have occurred in a predetermined area in the past and weather information for the area where the traffic event occurred, based on the detected event information. The past event information acquisition unit 13 refers to the past event information DB 191 and extracts past event information based on the location and time of the detected traffic event.

[0071] Specifically, the past event information acquisition unit 13 extracts past event information from the past event information DB 191 that corresponds to the location and time indicated by the detected event information. For example, the past event information acquisition unit 13 searches the past event information DB 191 using the following search conditions: that the distance to the location of the detected event is within a predetermined range, and that the time difference to the time of the detected event is within a predetermined range.

[0072] The past event information acquisition unit 13 may set search conditions for location and time using predetermined thresholds for each of the location and time. For example, the past event information acquisition unit 13 may set search conditions using a fixed distance and a fixed time difference. For example, the past event information acquisition unit 13 acquires past event information where the difference in location is within a predetermined distance (for example, within 100m) and the difference in date and time is within a predetermined range (for example, within 7 days before or after the same date and time of the previous year).

[0073] The past event information acquisition unit 13 may use the difference between the date and time of a past event and the date and time of the detected event as the time difference, excluding differences in the year the event was held, or it may use a specific period, such as "the third weekend of July," to determine the time difference.

[0074] The past event information acquisition unit 13 extracts past event information that satisfies these search conditions. This allows the past event information acquisition unit 13 to acquire past event information for past events held around the same time as the detected event, in an area close to the location of the detected event.

[0075] Figure 6 shows an example of a past event information DB 191 that stores past event information. In this example, the past event information DB 191 includes information such as event ID, location, date, event name, organizer / contact information, and weather information. The event ID is information that identifies a past event. The location and date indicate the location and date of the past event, respectively. The event name indicates the name of the event. The organizer / contact information indicates the name of the event organizer or organization and their contact information. The weather information indicates the weather conditions at the time the event occurred.

[0076] The past event information database 191 may be constructed using, for example, the results of interviews with neighborhood associations, local governments, or residents that manage a designated area. The likelihood of traffic events occurring varies depending on the location and time. Therefore, the past event information database 191 may store past event information related to traffic events based on information obtained from local residents or public institutions that have knowledge of traffic events. For example, the past event information database 191 stores past event information using information such as hazard maps and sections of roads where fatal accidents frequently occur.

[0077] In the example in Figure 6, event ID "001" shows past event information regarding the "9th Karaoke Competition" held at "ABC Cafe" on 2023 / 7 / 22. This past event information indicates that the karaoke competition shown in post P1 in Figure 5 was also held about a year ago. Additionally, ID "003" indicates that a traffic accident occurred at "X Intersection" on 2021 / 7 / 10.

[0078] In the example shown in Figure 6, general events such as karaoke competitions and traffic events are shown in the same past event information DB 191, but this is not limited to this. The event estimation device 10 may store general events and traffic events in different databases, or it may distinguish between the two using flags or the like in the past event information DB 191.

[0079] Note that the example shown in Figure 6 is just one example, and the past event information DB 191 may include other information. For example, the past event information DB 191 may include information that can identify an event as past event information, instead of the event name. This allows the event content estimation unit 14 to estimate events for which the event name is unclear.

[0080] As described above, the past event information acquisition unit 13 may acquire past event information from a pre-stored past event information DB 191, or it may acquire past event information using a different method. For example, the past event information acquisition unit 13 may search for past posting information related to a predetermined area in response to the detection of an event, and acquire past event information based on the search results.

[0081] For example, the past event information acquisition unit 13 searches for SNS posts in response to the detection of an event. The past event information acquisition unit 13 searches for posts using search conditions similar to those used when searching the past event information DB 191, such as the distance to the location of the detected event being within a predetermined range, and the time difference between the detected event and the current location being within a predetermined range. This eliminates the need to pre-build the past event information DB 191, thus reducing the costs associated with the construction work.

[0082] Returning to Figure 4, the event content estimation unit 14 is an example of the event content estimation unit 104 described above. The event content estimation unit 14 estimates the content of the detected event based on past event information and detected event information. The event content estimation unit 14 does not simply estimate the genre of the event, but estimates the specific content of the detected event.

[0083] For example, the event content estimation unit 14 estimates the name of the detected event. The event name may be, for example, "Karaoke Contest" or "Fireworks Display." The event content estimation unit 14 may also estimate more detailed event information, such as the number of times the event has been held, such as "10th time," or information about the organizer, such as "Sponsored by ABC Cafe." Based on the detected event information and past event information, the event content estimation unit 14 may also estimate participation fees and participation conditions. In addition, the event content estimation unit 14 may estimate various other information that can encourage participation in the event.

[0084] In this way, the event content estimation unit 14 estimates the specific content of the event, so the information provision unit 15 can provide information about the specific event to local residents, etc. This makes it possible to attract the interest of the event's target audience. The event content estimation unit 14 may also identify the genre of the event based on its content. Furthermore, the event content estimation unit 14 may also estimate the target audience for the event based on its content.

[0085] Specifically, for example, the event content estimation unit 14 estimates the content of the detected event based on the similarity between past event information and the detected event information. The event content estimation unit 14 may calculate the similarity between past event information and the detected event information using any method. The event content estimation unit 14 uses tf-idf and cosine similarity to identify past event information with a similarity of a predetermined level or higher to the detected event information. For example, the event content estimation unit 14 refers to the past event information DB 191 and identifies the past event information with the highest similarity to the detected event information. The event content estimation unit 14 estimates the content of the past event information with the highest similarity as the content of the detected event.

[0086] For example, the event content estimation unit 14 estimates that an event with posts such as "It's lively outside" and "I can hear the sound of drums" is a "Bon Odori festival hosted by the Z Neighborhood Association." In this way, the event content estimation unit 14 can estimate the content of a detected event based on past event information that is most similar to the detected event information.

[0087] The event content estimation unit 14 may also estimate the content of a detected event without using the similarity between past event information and the detected event information. For example, the event content estimation unit 14 may estimate the content of a detected event by using the similarity between keywords included in past event information and keywords included in the detected event information. Keywords may be, for example, words or sentences included in the posted information. For example, the event content estimation unit 14 estimates the content of the past event information with the highest similarity between keywords included in past event information and keywords included in the detected event information as the content of the detected event.

[0088] When the detected event information acquisition unit 12 acquires information on a traffic event and weather information for the area where the traffic event was detected, the event content estimation unit 14 estimates the content of the detected traffic event based on past event information and detected event information. For example, the event content estimation unit 14 estimates the traffic event as "traffic accident at intersection X" or "landslide in town Y".

[0089] The information provision unit 15 identifies target individuals who are encouraged to participate in the event based on the estimated event content and provides them with information including the estimated event content. For example, the information provision unit 15 identifies the attributes of users who are the target of the event based on the event content. Users are individuals who use the event estimation system 1. User attributes may include, for example, age, gender, occupation, or areas of interest. User attributes may be stored in advance in the storage unit 19 as user information. For example, the storage unit 19 stores user information for multiple users who use the event estimation system 1, associating it with a predetermined area where the user resides or is active.

[0090] The information provision unit 15 extracts users who are likely to participate in the event from among multiple users based on the event content, and identifies the extracted users as target users. The information provision unit 15 provides event information to the identified target users. For example, the information provision unit 15 transmits event information to the terminal device used by the target users.

[0091] Event information may include the event's location and date, as well as information about the organizer, past event details, participation fee, a URL to a webpage with detailed information, or information about the venue (e.g., a store). The event information may also include, for example, ratings on social media. This approach can increase the interest of those who receive the event information.

[0092] For example, the information provision unit 15 provides event information regarding events held near the apartment building to members of a community site composed of residents of the apartment building. The information provision unit 15 may also provide event information to members by posting it on an online bulletin board or similar platform accessible only to members. For example, the information provision unit 15 may overlay map information and event information and display them on the community site. In this way, members can intuitively grasp the details of events currently being held or scheduled to be held near the apartment building.

[0093] Furthermore, the information provision unit 15 may provide traffic event information related to traffic events. In this case, the information provision unit 15 identifies the target users for whom traffic event information is provided based on the user's current location and attributes. For example, the information provision unit 15 identifies users who are within a predetermined distance from the location where a traffic event was detected as target users.

[0094] For example, the information provision unit 15 transmits the content of the estimated traffic event to the target person's terminal device, such as "It appears there was a traffic accident at intersection X." Furthermore, if the information provision unit 15 obtains official information from relevant organizations regarding the detected traffic event, it may provide that official information as a follow-up report. For example, the information provision unit 15 may provide information such as, "There was a traffic accident at intersection X. Traffic congestion is occurring."

[0095] The communication unit 17 communicates with the terminal device 20 and the beacon device 30 via the network N. The communication unit 17 may be a communication interface for wired or wireless communication. For example, the communication unit 17 receives the terminal device ID and location information from the terminal device 20. The communication unit 17 also receives beacon signals from the beacon device 30.

[0096] The memory unit 19 is a storage device that stores programs for realizing each function of the event estimation device 10. The memory unit 19 also stores the past event information DB 191 mentioned above. When the event detection unit 11 detects a completed event, the memory unit 19 stores information about the completed event in the past event information DB 191. This allows the memory unit 19 to improve the event detection accuracy of the event detection unit 11.

[0097] The configuration of the event estimation system 1 has been described above. Note that the configuration of the event estimation system 1 described above is merely an example and can be modified as appropriate. If some or all of the components of the event estimation system 1 are implemented by multiple information processing devices or circuits, these devices may be centrally located or distributed. For example, the information processing devices or circuits may be implemented in a form where each is connected via a communication network, such as a client-server system or a cloud computing system. For example, the functions of the event estimation device 10 may be provided in SaaS (Software as a Service) format.

[0098] For example, in the above description, the event detection unit 11, detected event information acquisition unit 12, past event information acquisition unit 13, event content estimation unit 14, information provision unit 15, communication unit 17, and storage unit 19 are shown to be inside the event estimation device 10, but this is not limited to this. For example, part of the event detection unit 11, detected event information acquisition unit 12, past event information acquisition unit 13, event content estimation unit 14, and information provision unit 15 may be provided in a device other than the event estimation device 10.

[0099] Furthermore, although the above description explains an example in which the memory unit 19 stores past event information DB 191 and user information, it is not limited to this. Another device other than the event estimation device 10 may store past event information DB 191 and user information, and the event estimation device 10 may refer to that other device.

[0100] (Processing of the event estimation device 10) Next, the processing performed by the event estimation device 10 will be explained with reference to Figure 7. Figure 7 is a flowchart showing the processing performed by the event estimation device 10.

[0101] First, the event detection unit 11 acquires dwelling information or posting information (S11). The event detection unit 11 may acquire both dwelling information and posting information. For example, the event detection unit 11 acquires dwelling information using at least one of the terminal device 20 and the beacon device 30. For example, the event detection unit 11 analyzes the dwelling status of people in a predetermined area based on the data received from the terminal device 20 and the beacon device 30, and acquires the analysis results as dwelling information. The event detection unit 11 also acquires posting information related to the predetermined area from SNS or the like. Posting information includes data such as text, images, or audio.

[0102] Next, the event detection unit 11 detects events in a predetermined area (S12). For example, the event detection unit 11 detects events by detecting crowding in a predetermined area using dwelling information. The event detection unit 11 also detects events based on text, images, etc., included in the posted information.

[0103] Next, the event detection unit 11 determines whether the detected event has finished (S13). If it determines that the event has finished (YES in S13), the event detection unit 11 stores the information of the finished event in the past event information DB 191 of the storage unit 19 (S14). This improves the event detection accuracy of the event detection unit 11.

[0104] If the event is determined not to have ended (NO in S13), the event detection unit 11 outputs detected event information, including the location and time of the detected event, to the detected event information acquisition unit 12. The event detection unit 11 may also output detected event information that includes traffic event information and weather information for the area where the traffic event was detected. The detected event information acquisition unit 12 acquires the detected event information from the event detection unit 11 (S15).

[0105] Next, the past event information acquisition unit 13 acquires past event information based on the detected event information (S16). For example, the past event information acquisition unit 13 searches the past event information DB 191 using the search conditions that the distance to the location of the detected event is within a predetermined range, and the time difference with the time of the detected event is within a predetermined range. The past event information acquisition unit 13 acquires the past event information extracted by the search.

[0106] Next, the event content estimation unit 14 calculates the similarity between past event information and detected event information using any method (S17). Based on the calculated similarity, the event content estimation unit 14 estimates the content of the detected event (S18). For example, the event content estimation unit 14 refers to the past event information DB 191 and identifies the past event information with the highest similarity to the detected event information. The event content estimation unit 14 estimates the content of the past event information with the highest similarity as the content of the detected event.

[0107] Next, the information provision unit 15 identifies the target recipients of the information (S19). For example, the information provision unit 15 identifies the attributes of users who are the target of the event based on the content of the event, and identifies the target recipients based on the identified attributes. For example, the information provision unit 15 identifies the target recipients based on the user's age, gender, occupation, or genre of interest. If the detected event information includes information on a traffic event, the information provision unit 15 may identify users who are within a predetermined distance from the location where the traffic event was detected as target recipients.

[0108] The information provision unit 15 then provides information to the target person (S20). For example, the information provision unit 15 transmits event information regarding the event to the terminal device used by the target person.

[0109] As described above, the event estimation system 1 according to this disclosure detects events in a predetermined area based on at least one of dwelling information indicating the presence of people in the predetermined area and posting information indicating posts related to the predetermined area. The event estimation system 1 acquires detected event information including the location and time of the detected event, and acquires past event information including the location and time of events previously held in the predetermined area based on the detected event information. The event estimation system 1 estimates the content of the detected event based on the past event information and the detected event information.

[0110] According to the event estimation system 1 disclosed herein, it is possible to detect not only relatively large-scale events, such as those announced on the websites of commercial facilities, but also relatively small-scale, spontaneous events held in designated areas, and to estimate their content. Furthermore, since the event estimation system 1 can estimate not only the genre of the detected event but also its specific content, it can effectively encourage users to participate in the event.

[0111] Furthermore, if, for example, surveillance cameras are used to photograph the entire event location and the captured images are used to estimate the content of the event, there are concerns about the infringement of privacy. However, the event estimation system 1 disclosed herein estimates the content of the event using dwell time information based on data from terminal devices 20 and beacon devices 30, as well as information posted on social media, so this issue can also be addressed.

[0112] As described above, the event estimation system 1 described herein can appropriately provide information on events held in a predetermined area.

[0113] <Example of Hardware Configuration> Each functional component of the event estimation system 100 and the event estimation device 10 (hereinafter referred to as "event estimation system 100, etc.") may be implemented by hardware that realizes each functional component (e.g., hardwired electronic circuits, etc.), or by a combination of hardware and software (e.g., a combination of electronic circuits and a program that controls them, etc.). The case in which each functional component of the event estimation system 100, etc. is implemented by a combination of hardware and software will be further explained below.

[0114] Figure 8 is a block diagram illustrating the hardware configuration of a computer 900 that implements the event estimation system 100, etc. The computer 900 may be a dedicated computer designed to implement the event estimation system 100, etc., or it may be a general-purpose computer. The computer 900 may also be a portable computer such as a smartphone or tablet terminal.

[0115] For example, by installing a predetermined application on the computer 900, various functions of the event estimation system 100 and other such functions are realized on the computer 900. The above application consists of a program for realizing the functional components of the event estimation system 100 and other such functions.

[0116] The computer 900 includes a bus 902, a processor 904, a memory 906, a storage device 908, an input / output interface 910, and a network interface 912. The bus 902 is a data transmission path for the processor 904, memory 906, storage device 908, input / output interface 910, and network interface 912 to send and receive data to and from each other. However, the method of connecting the processor 904 and the other components to each other is not limited to bus connection.

[0117] The processor 904 is a variety of processors such as a CPU (Central Processing Unit), GPU (Graphics Processing Unit), FPGA (Field-Programmable Gate Array), or quantum processor (quantum computer control chip). The memory 906 is a main memory device implemented using RAM (Random Access Memory), etc. The storage device 908 is an auxiliary storage device implemented using a hard disk, SSD (Solid State Drive), memory card, or ROM (Read Only Memory), etc.

[0118] The input / output interface 910 is an interface for connecting the computer 900 with input / output devices. For example, input devices such as keyboards and output devices such as display devices are connected to the input / output interface 910.

[0119] The network interface 912 is an interface for connecting the computer 900 to a network. This network may be a LAN (Local Area Network) or a WAN (Wide Area Network).

[0120] The storage device 908 stores programs that implement each functional component of the event estimation system 100 (programs that implement the aforementioned applications). The processor 904 reads these programs into memory 906 and executes them to implement each functional component of the event estimation system 100.

[0121] Each processor executes one or more programs containing a set of instructions for causing a computer to perform the algorithms described with reference to the drawings. These programs, when loaded into a computer, contain a set of instructions (or software code) for causing the computer to perform one or more functions described in the embodiments. The programs may be stored in various types of non-transitory computer-readable medium or tangible storage medium. Examples, but not limited to, include non-transitory computer-readable medium or tangible storage medium, such as RAM, ROM, flash memory, SSD or other memory technologies, CD-ROM, DVD (Digital Versatile Disc), Blu-ray® disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The programs may also be transmitted over various types of transient computer-readable medium or communication medium. Examples, but not limited to, include transient computer-readable medium or communication medium, such as electrical, optical, acoustic or other forms of propagating signals.

[0122] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure are possible, as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each embodiment can be combined with other embodiments as appropriate.

[0123] Each drawing is merely illustrative to illustrate one or more embodiments. Each drawing may be associated with one or more other embodiments, rather than being associated with only one specific embodiment. As those skilled in the art will understand, various features or steps described with reference to any one drawing can be combined with features or steps shown in one or more other drawings to create embodiments that are not explicitly illustrated or described. Not all features or steps shown in any one drawing to illustrate an exemplary embodiment are necessarily required, and some features or steps may be omitted. The order of steps shown in any of the drawings may be changed as appropriate.

[0124] Some or all of the above embodiments may also be described as follows, but are not limited to the following: (Note 1) An event estimation system comprising: an event detection unit that detects an event in a predetermined area based on at least one of dwelling information indicating the presence of people in the predetermined area and posting information indicating postings relating to the predetermined area; a detection event information acquisition unit that acquires detected event information including the location and time of the detected event; a past event information acquisition unit that acquires past event information including the location and time of events previously held in the predetermined area based on the detected event information; and an event content estimation unit that estimates the content of the detected event based on the past event information and the detected event information. (Note 2) The event estimation system according to Note 1, further comprising an information provision unit that identifies target persons who are encouraged to participate in the event based on the estimated content of the event and provides the target persons with information including the estimated content of the event. (Note 3) The event estimation system according to Note 1 or 2, wherein the event content estimation unit estimates the content of the detected event based on the similarity between the past event information and the detected event information. (Note 4) The event estimation system according to any one of Notes 1 to 3, wherein the event detection unit acquires the dwelling information using at least one of a terminal device held by a person present in the predetermined area and a communication device provided in the predetermined area, and detects the event based on the acquired dwelling information. (Note 5) The event estimation system according to any one of Notes 1 to 4, wherein the event detection unit acquires the posting information including environmental information representing the environment of the predetermined area, extracts information regarding an event in the predetermined area from the acquired posting information, and detects the event based on the extraction result. (Note 6) The event estimation system according to any one of Notes 1 to 5, wherein the event detection unit acquires the posting information including an image taken in the predetermined area, extracts information regarding an event in the predetermined area from the image, and detects the event based on the extraction result.(Note 7) The event estimation system according to any one of Notes 1 to 6, further comprising a storage unit that stores information of a completed event as past event information when a completed event is detected in the event detection unit. (Note 8) The event estimation system according to any one of Notes 1 to 7, wherein the detected event information acquisition unit acquires the detected event information, which includes information of a traffic event in a predetermined area and weather information of the area where the traffic event was detected; the past event information acquisition unit acquires the past event information, which includes information of a traffic event that occurred in the past in the predetermined area and weather information of the area where the traffic event occurred, based on the detected event information; and the event content estimation unit estimates the content of the detected event based on the past event information and the detected event information. (Note 9) The event estimation system according to any one of Notes 1 to 8, wherein the past event information acquisition unit acquires the past event information from a past event information database that has been stored in advance. (Note 10) The past event information acquisition unit searches for past posting information relating to the predetermined area in response to the detection of the event, and acquires the past event information based on the search results, according to any one of the items in Note 1 to 9. (Note 11) An event estimation method comprising: an event detection step of detecting an event in the predetermined area based on at least one of dwelling information indicating the presence of people in the predetermined area and posting information indicating postings relating to the predetermined area; a detected event information acquisition step of acquiring detected event information including the location and time of the detected event; a past event information acquisition step of acquiring past event information including the location and time of events previously held in the predetermined area based on the detected event information; and an event content estimation step of estimating the content of the detected event based on the past event information and the detected event information.(Note 12) A program that causes a computer to execute the following steps: an event detection step that detects an event in a predetermined area based on dwelling information indicating the presence of people in the predetermined area and posting information indicating postings relating to the predetermined area; a detected event information acquisition step that acquires detected event information including the location and time of the detected event; a past event information acquisition step that acquires past event information including the location and time of events previously held in the predetermined area based on the detected event information; and an event content estimation step that estimates the content of the detected event based on the past event information and the detected event information.

[0125] Some or all of the elements (e.g., configuration and function) described in Appendices 2 to 10 that are subordinate to Appendice 1 may also be subordinate to Appendices 11 and 12 in the same manner as those described in Appendices 2 to 10. Some or all of the elements described in any appendice may be applied to various hardware, software, recording means, systems, and methods for recording software.

[0126] This application claims priority based on Japanese Patent Application No. 2024-167121, filed on 26 September 2024, and incorporates all of its disclosures herein.

[0127] 1 Event Estimation System 10 Event Estimation Device 11 Event Detection Unit 12 Detected Event Information Acquisition Unit 13 Past Event Information Acquisition Unit 14 Event Content Estimation Unit 15 Information Provision Unit 17 Communication Unit 19 Storage Unit 20-1 to 20-3 Terminal Devices 30-1 to 30-3 Beacon Device 100 Event Estimation System 101 Event Detection Unit 102 Detected Event Information Acquisition Unit 103 Past Event Information Acquisition Unit 104 Event Content Estimation Unit 191 Past Event Information DB 900 Computer 902 Bus 904 Processor 906 Memory 908 Storage Device 910 Input / Output Interface 912 Network Interface B1, B2 Signboard N Network P1 Post P11 Post Text P12 Post Image

Claims

1. An event estimation system comprising: an event detection means for detecting an event in a predetermined area based on at least one of dwelling information indicating the presence of people in the predetermined area and posting information indicating posts relating to the predetermined area; a detection event information acquisition means for acquiring detected event information including the location and time of the detected event; a past event information acquisition means for acquiring past event information including the location and time of events previously held in the predetermined area based on the detected event information; and an event content estimation means for estimating the content of the detected event based on the past event information and the detected event information.

2. The event estimation system according to claim 1, further comprising information provision means for identifying target individuals who are encouraged to participate in the event based on the estimated content of the event, and providing the target individuals with information including the estimated content of the event.

3. The event estimation system according to claim 1 or 2, wherein the event content estimation means estimates the content of the detected event based on the similarity between the past event information and the detected event information.

4. The event estimation system according to claim 1 or 2, wherein the event detection means acquires the dwelling information using at least one of a terminal device held by a person present in the predetermined area and a communication device provided in the predetermined area, and detects the event based on the acquired dwelling information.

5. The event estimation system according to claim 1 or 2, wherein the event detection means acquires the posting information which includes environmental information representing the environment of the predetermined area, extracts information about events in the predetermined area from the acquired posting information, and detects the events based on the extraction results.

6. The event estimation system according to claim 1 or 2, wherein the event detection means acquires the posting information including an image taken in the predetermined area, extracts information about an event in the predetermined area from the image, and detects the event based on the extraction result.

7. The event estimation system according to claim 1 or 2, further comprising a storage means for storing information of a completed event as past event information when a completed event is detected in the event detection means.

8. The event estimation system according to claim 1 or 2, wherein the detected event information acquisition means acquires the detected event information, which includes information on traffic events in the predetermined area and weather information for the area where the traffic event was detected; the past event information acquisition means acquires the past event information, which includes information on traffic events that occurred in the predetermined area in the past and weather information for the area where the traffic event occurred, based on the detected event information; and the event content estimation means estimates the content of the detected event based on the past event information and the detected event information.

9. The event estimation system according to claim 1 or 2, wherein the means for acquiring past event information acquires the past event information from a past event information database that has been stored in advance.

10. The event estimation system according to claim 1 or 2, wherein the means for acquiring past event information searches for past posting information relating to the predetermined area in response to the detection of the event, and acquires the past event information based on the search results.

11. An event estimation method that detects an event in a predetermined area based on at least one of dwelling information indicating the presence of people in a predetermined area and posting information indicating posts relating to the predetermined area; obtains detected event information including the location and time of the detected event; obtains past event information including the location and time of events previously held in the predetermined area based on the detected event information; and estimates the content of the detected event based on the past event information and the detected event information.

12. A program that causes a computer to perform the following actions: detect an event in a predetermined area based on dwelling information indicating the presence of people in that area and posting information indicating posts relating to the predetermined area; obtain detected event information including the location and time of the detected event; obtain past event information including the location and time of events previously held in the predetermined area based on the detected event information; and estimate the content of the detected event based on the past event information and the detected event information.

Images