JP2022164471A - Information provision device and method - Google Patents

Abstract

To provide an information provision device and method which allow for notifying a user of more real-time and reliable information on visitors at a specified spot.SOLUTION: An information provision device 10 of the present invention comprises a video selection unit 13 for selecting a video related to a pre-specified spot from among videos delivered via a network, a person detection unit 14 configured to detect persons included in the selected video, an attribute estimation unit 15 configured to estimate attributes of the detected persons, and an attribute trend determination unit 16 configured to determine an attribute trend of persons visiting the specified spot based on the estimated attributes of the persons.SELECTED DRAWING: Figure 1

Description

The present invention relates to an information providing apparatus and method.

In recent years, with the spread of mobile terminals such as smartphones and tablet terminals, SNSs (Social Networking Services) are frequently used. Information posted to SNS is used, for example, in a navigation system that provides route information and a system that provides destination information.

A technique related to a navigation service that provides a user with the degree of congestion of a destination based on information posted on an SNS has been disclosed. For example, Patent Literature 1 discloses a technique for providing guidance on changes in the degree of congestion at a destination facility.

JP 2020-177418 A

With the technology disclosed in Patent Document 1, it is possible to grasp the chronological degree of congestion at the destination, but it is not possible to grasp the detailed situation, such as what kind of attributes many people have. There are also facilities that use the Web to distribute information such as the degree of congestion. For example, even at a facility with a large number of families, there may be cases where there are many couples and it is not appropriate for families to visit, depending on the time of day or event.

In view of the above points, in the present disclosure, an information providing apparatus and method capable of notifying users of more real-time and reliable information about visitors at a designated point and information corresponding to an arbitrary period are provided. intended to provide

An information providing apparatus according to the present invention includes a video selection unit that selects a video related to a predesignated point from videos distributed over a network, a person detection unit that detects a person included in the selected video, and a detection an attribute estimating unit for estimating the attribute of the person who has visited the site; and an attribute trend determining unit for determining the attribute tendency of the person who visits the designated spot based on the estimated attribute of the person.

An information providing method according to the present invention comprises the steps of: selecting a video relating to a predesignated point from videos distributed over a network; detecting a person included in the selected video; A step of estimating an attribute and a step of determining an attribute tendency of a person who visits the designated spot based on the estimated attribute of the person.

According to the information providing apparatus and method of the present invention, it is possible to notify users of more real-time and reliable information about visitors to a designated spot, and to notify users of information according to any period of time.

1 is a configuration diagram of an information providing device according to Embodiment 1 of the present invention; FIG. FIG. 5 is a diagram showing an example of notification of determined personal attribute tendencies according to the first embodiment of the present invention; FIG. 4 is a flowchart of processing for notifying a person attribute tendency performed by the information providing apparatus according to the first embodiment of the present invention;

Hereinafter, embodiments will be described with reference to the drawings. Since the drawings are simplified, the technical scope of the embodiments should not be narrowly interpreted based on the description of the drawings. Also, the same elements are denoted by the same reference numerals, and overlapping descriptions are omitted.

For the sake of convenience, the following embodiments will be divided into a plurality of sections or embodiments when necessary. However, unless otherwise specified, they are not unrelated to each other, and one is a part or all of the other, such as modified examples, application examples, detailed explanations, and supplementary explanations. In addition, in the following embodiments, when referring to the number of elements, etc. (including the number, numerical value, amount, range, etc.), when it is particularly specified, when it is clearly limited to a specific number in principle, etc. is not limited to that particular number, and may be greater than or less than the particular number.

Furthermore, in the following embodiments, the constituent elements (including operation steps and the like) are not necessarily essential, unless otherwise specified or clearly considered essential in principle. Similarly, in the following embodiments, when referring to the shape, positional relationship, etc. of components, etc., unless otherwise explicitly stated or in principle clearly considered otherwise, the shape is substantially the same. It shall include those that are similar or similar to, etc. This also applies to the above numbers (including numbers, numerical values, amounts, ranges, etc.).

<Embodiment 1>
The configuration of the information providing device 10 according to this embodiment will be described with reference to FIG. FIG. 1 is a configuration diagram of an information providing device 10 according to this embodiment.

The information providing device 10 can communicate with the SNS server 20 mutually. The SNS server 20 may be a server provided on a network capable of communicating with the information providing apparatus 10, or may be a server of the official site of each facility. Also, the number of SNS servers 20 may be one or plural. The information providing device 10 also includes an input unit 11 , a point designation unit 12 , a video selection unit 13 , a person detection unit 14 , an attribute estimation unit 15 , an attribute trend determination unit 16 and a result notification unit 17 . The information providing device 10 may have a mode as a navigation device that provides the user with destinations and travel routes. Also, the information providing apparatus 10 may be a single server, or a plurality of servers may be used to distribute functions.

The input unit 11 gives an operation instruction to the point designation unit 12 . Operation instructions may be given by character input using a keyboard, a touch panel, or the like, or may be given by voice input using a microphone or the like.

The point designation unit 12 designates a point based on information input by the user through the input unit 11 . The input information may be, for example, latitude and longitude information of the destination point, facility names, and various other information. The information providing device 10 may have a map DB (not shown) containing map data. At this time, the specified point may be configured to be selected on the map.

The image selection unit 13 selects a location specified in advance by the location specification unit 12 from among images distributed over the network and provided with location information such as location names and facility names and location information such as latitude and longitude as tag information. The SNS server 20 is searched for videos having matching or similar point information and selected. When the video contains latitude and longitude information, the video selection unit 13 searches for and selects video showing latitude and longitude information within a predetermined range from the latitude and longitude of the specified point. “Within a predetermined range” may be arbitrarily set according to the attribute of the designated point, such as within 100 m from the designated point.

The image selection unit 13 selects images of a predetermined period going back from the point of time when the designation of the spot is accepted. The retrospect period may be arbitrarily set according to the attribute of the designated point, such as within one hour past from the time the point was designated, during the day when the point was designated, or within the past one week. Also, the video to be selected may be a still image or a moving image.

The video selected by the video selection unit 13 may be selected from news content, blogs, etc. provided on the official site of each facility, for example. Also, the video selected by the video selection unit 13 may be based on a real-time video from a fixed-point camera or the like connected to the network. That is, the SNS server 20 may be a server provided in each facility, or a server that distributes video from a fixed point camera. In addition, it is preferable that the information of SNS targeted in this embodiment targets many information which can be searched.

The person detection unit 14 detects a person included in the video selected by the video selection unit 13 . When a plurality of persons are included in the video, the person detection unit 14 may detect the plurality of persons. Of the videos selected by the video selection unit 13, videos that do not include a person are excluded from objects for which a person's attribute is estimated in the process of the attribute estimation unit 15, which will be described later, based on the detection result of the person detection unit 14. may

The attribute estimation unit 15 estimates attributes of the person detected by the person detection unit 14 . In the attribute estimation, the attributes of a single person or a plurality of persons detected by the person detection unit 14 are estimated. Attribute estimation is performed by using artificial intelligence that has learned various human states (e.g., gender such as male or female, age such as child, young, elderly, etc.), and the image of the person detected by the person detection unit 14. A person's attribute may be estimated from the feature amount of . The attribute estimation unit 15 may estimate the attribute of the detected individual and also the attribute of the group to which the detected person belongs. The attribute estimating unit 15 may estimate the attributes of a group, whether it is a single person, a couple, or a group, based on, for example, the distance between individuals, whether they are having a conversation, the direction of their eyes, their faces, and the like. The attribute may be, for example, various attributes such as gender such as male or female, age such as child, young, or elderly. Also, the attribute of the group to which the user belongs may be various groups such as, for example, a single person, a family with children, a couple, a group of men and women, a group of men and a group of women.

The attribute tendency determination unit 16 determines the attribute tendency of the person who visits the designated spot based on the attributes estimated by the attribute estimation unit 15 from the plurality of videos. That is, the attribute tendency determination unit 16 determines the attribute tendency using the ratio of the attributes of the person detected from the video. Personal attribute tendencies may be various, such as, for example, many families, many couples, many young couples, and many groups.

The result notification unit 17 is a notification unit that notifies the user of the attribute tendency of the person who visits the designated point, which is determined by the attribute tendency determination unit 16 . The mode of notification may be a mode of displaying the current position on the map and the attribute tendency of the destination on the screen. At this time, the current position may be acquired using a positioning system such as GPS (Global Positioning System). Although an example of attribute tendency notification is shown in FIG. 2, the manner in which the result notification unit 17 notifies is not limited to this. Further, the result notification unit 17 may have a function of outputting voice information. At this time, the attribute tendency determination unit 16 may create voice information that notifies the attribute tendency determined for each designated point.

Here, the flow of processing performed by the information providing apparatus 10 will be described with reference to FIG. FIG. 3 is a flow chart of processing for notifying a person's attribute tendency, which is performed by the information providing apparatus 10 according to the present embodiment.

First, the point designation unit 12 designates a point based on the information input by the user through the input unit 11 (step 101). The image selection unit 13 acquires the image of the point designated by the point designation unit 12 for a predetermined period from the SNS server 20 (step 102). The person detection unit 14 detects a person included in the video selected by the video selection unit 13 (step 103). The attribute estimation unit 15 estimates the attributes of the person detected by the person detection unit 14 at the specified point (step 104). The attribute tendency determination section 16 determines the tendency of the person's attributes at the specified point based on the attributes estimated by the attribute estimation section 15 from the plurality of images (step 105). The result notification unit 17 notifies the user of the attribute tendency of the person who visits the designated spot determined by the attribute tendency determination unit 16 (step 106).

As described above, the information providing apparatus 10 in this embodiment acquires still images and moving images for a predetermined period related to a point specified by the user from the SNS server 20 . The person detection unit 14 detects a person from the obtained still image or moving image, the attribute estimation unit 15 estimates the attribute of the person, and the result notification unit 17 notifies the estimated person attribute to the user. Therefore, the information providing device 10 can notify the user of more real-time and reliable information regarding the visitor at the designated point. In addition, the user can select a destination that matches the user's personal attributes by being notified of the personal attribute trends of the specified location.

<Embodiment 2>
The image selection unit 13 of the information providing apparatus 10 according to the first embodiment selects images of a predetermined period before the time when the point was designated, that is, within the past one hour, during the day when the point was designated, within the past one week, and the like. . In the present embodiment, the image selection unit 13 selects images of the same period in the past as the point in time when the point designation is accepted. The same period in the past means the same time, same day of the week, same month, and same season. The same season means, for example, every year Christmas, New Year, Golden Week, the blooming period of cherry blossoms, the period during which an event is held, or the period when the weather is similar, but it is not limited to this.

According to the information providing apparatus 10 of the present embodiment, it is possible to provide not only recent information but also personal attribute information of specified points at various times.

<Other embodiments>
The information providing apparatus 10 in the present invention has an embodiment as an information providing method, for example. That is, the information providing method comprises the steps of: selecting a video about a predesignated point from videos distributed over a network; detecting a person included in the selected video; and estimating the attribute of the detected person and determining an attribute tendency of a person who visits the specified location based on the estimated attribute of the person.

Although the embodiments of the present disclosure have been described in detail above with reference to the drawings, the specific configurations are not limited to those described above, and various design changes can be made without departing from the gist of the present disclosure. etc. is possible.

10 information providing device 11 input unit 12 point designation unit 13 image selection unit 14 person detection unit 15 attribute estimation unit 16 attribute trend determination unit 17 result notification unit 20 SNS server

Claims (5)

a video selection unit that selects a video about a pre-specified point from videos distributed over a network;
a person detection unit that detects a person included in the selected video;
an attribute estimation unit for estimating attributes of the detected person;
an attribute trend determination unit that determines an attribute trend of a person who visits the specified location based on the estimated attribute of the person;
An information providing device with The image selection unit selects images of a predetermined period going back from the time when the designation of the point is accepted.
The information providing device according to claim 1. The video selection unit selects a video of the same time in the past as the point in time when the designation of the point was accepted.
The information providing device according to claim 1. Further comprising a notification unit that notifies the attribute tendency of the person visiting the point determined by the attribute trend determination unit,
The information providing device according to any one of claims 1 to 3. a step of selecting a video about a pre-specified point from videos distributed over a network;
detecting a person included in the selected video;
estimating attributes of the detected person;
determining an attribute tendency of a person who visits the specified location based on the estimated attribute of the person;
method of providing information with

Images