Facility-related knowledge acquisition system

Abstract

To provide review by which facility-related knowledge can be acquired in an early stage.SOLUTION: The control device 16 of the facility-related knowledge acquisition system 10 includes the representative action recognition section 19, which recognizes an answering action of the representative 1 for a problem displayed on the first display device 11 in the learning area 4 on the basis of the digital apparatus 13, and the most frequent person action recognition section 20, which recognizes an answering action performed by each individual in a group including the representative 1 and the companion 2 for the problem and recognizes a most frequent person answering action, which is an answering action of a majority in the group 3. The device has a correct / incorrect determination part 21 for storing the result of determination in a storage device 15, and a question selection part 18 for displaying a question whose result of determination of the maximum number of persons answering operation is incorrect on a second display device 14 of a review area 5.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a facility-related knowledge acquisition system for collectively acquiring knowledge related to facilities such as waste disposal plants. [Background technology]

[0002] Facilities such as waste incineration plants regularly hold tours for schoolchildren. These tours allow participants to learn knowledge related to the facility (hereinafter referred to as "facility-related knowledge") through explanations by animated characters using digital devices such as smartphones (see Patent Document 1). On the other hand, technology has been developed that allows users to experience and learn actual operating procedures using virtual reality devices (hereinafter referred to as "VR devices") (see Patent Document 2), and technology that allows users to easily review what they have learned at experiential facilities at home using digital devices such as computers (see Patent Document 3). Furthermore, a technology has been developed that can grasp the individual gestures of multiple participants, for example, the number of people who have raised their right hand and the number of people who have raised their left hand (see Patent Document 4). Furthermore, a system has been developed in which people or characters are displayed on a display device equipped with a camera, microphone, speaker, and generation AI, and the user can ask questions verbally to the display device to obtain the desired answers in a conversational format (see Patent Document 5). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-171091 [Patent Document 2] JP 2019-12154 A [Patent Document 3] Japanese Patent Application Laid-Open No. 2010-225129 [Patent Document 4] Japanese Patent Application Laid-Open No. 2010-239327 [Patent Document 5] Japanese Patent Publication No. 2020-182092 Summary of the Invention [Problem to be solved by the invention]

[0004] During facility tours, when a group of multiple participants is learning about facility-related knowledge for the first time, it is desirable to restrict the use of digital devices owned by each individual participant in the group, such as mobile devices such as smartphones and tablets. This is because participants generally have their own apps (e.g., game apps) installed on their digital devices, and if these apps are started during the tour, it could cause the participants to be unable to concentrate on their studies. Therefore, when holding a facility tour, it is desirable to limit the use of digital devices owned by each participant and instead have the organizer of the tour lend out digital devices specifically for learning that do not have any apps installed that are unnecessary for learning facility-related knowledge.

[0005] Incidentally, the number of participants in a group attending a facility tour, such as a waste incineration plant tour for schoolchildren, is usually as large as 30 to 40. For this reason, it is not desirable from a cost perspective to lend dedicated digital devices to all participants in a group. To reduce costs, one possible learning format is to have only one person selected from among multiple participants in a group use a dedicated digital device, while the other participants, i.e., accompanying people, observe the actions of the representative. However, with this learning format, accompanying people cannot use dedicated digital devices, making it difficult for them to maintain concentration on their studies, not just for schoolchildren but also for adults. Therefore, with this learning format, there is a risk that the effectiveness of acquiring facility-related knowledge will be reduced when viewed as a whole group.

[0006] In addition, in order to effectively acquire facility-related knowledge, it is desirable to carry out appropriate review. However, it is not easy to carry out review that will quickly improve the effectiveness of facility-related knowledge acquisition for the entire group.

[0007] Therefore, the present invention aims to provide a facility-related knowledge acquisition system that uses a learning format in which a representative learns facility-related knowledge using digital devices in the learning area while accompanying persons learn facility-related knowledge without using digital devices, and that can maintain the concentration of the entire group of representative and accompanying persons when learning facility-related knowledge in the learning area, and can quickly improve the effectiveness of facility-related knowledge acquisition for the entire group when reviewing facility-related knowledge in the review area. [Means for solving the problem]

[0008] The facility-related knowledge acquisition system of the present invention is a system for a group including a representative and accompanying persons to acquire facility-related knowledge. The study area is equipped with a first imaging device for capturing images of the group, a digital device used only by the representative and not by the accompanying persons, and a first display device that displays at least the same content as that seen by the representative and that can be viewed by at least the accompanying persons. The review area is equipped with a second display device that displays at least the same content as the representative and accompanying persons. The system also includes a storage device that stores a plurality of preset questions related to facility-related knowledge, a plurality of explanations corresponding to the correct answers to each of the plurality of questions, and the correct actions of the representative and accompanying persons corresponding to each correct answer, and a control device.

[0009] Among these, the control device comprises a question selection unit that selects at least one question from the plurality of questions stored in the storage device and displays it on the first display device; a representative action recognition unit that recognizes the representative's response action to the question displayed on the first display device based on the digital device; and a representative action recognition unit that recognizes the response action of each individual in the group performed using "large body movements" to the question displayed on the first display device based on the first imaging device, and corrects the recognition based on the first imaging device based on difference information that indicates that the representative's response action is different from the "large body movements" recognized by the representative action recognition unit, The group is equipped with at least a most-popular action recognition unit that recognizes the most popular answering action that indicates the answering action performed by the most people in the entire group; a correct / incorrect judgment unit that judges the correctness of the representative's answering action and the most popular answering action by comparing the representative's answering action recognized by the representative action recognition unit and the most popular answering action recognized by the most popular action recognition unit with the correct actions stored in the storage device, and stores the results of the correct / incorrect judgment in the storage device corresponding to each question; and a correct / incorrect explanation unit that displays the results of the representative's correct / incorrect judgment on the first display device and displays an explanation corresponding to the judgment result on the first display device or outputs it as an audio from the first display device. Then, the question selection unit causes the second display device to display, from among the plurality of questions, questions for which the result of the determination of the most popular answering action stored in the storage device is incorrect. [Effects of the Invention]

[0010] According to the facility-related knowledge acquisition system of the present invention, in a learning area where a group is learning facility-related knowledge, not only the representative who can answer questions using a digital device, but also accompanying persons who do not use digital devices can participate in answering questions displayed on the first display device by using the first imaging device to make "large body movements" such as gestures. This allows not only the representative but also the accompanying persons to learn facility-related knowledge while maintaining their concentration. Furthermore, according to the facility-related knowledge acquisition system of the present invention, in the review area where the group reviews the facility-related knowledge learned in the study area, questions posed in the study area for which the result of the judgment of the most common answer action taken by the most number of members of the group was incorrect, i.e., questions for which the majority of members of the group answered incorrectly, are displayed on at least the second display device and can be answered again. In other words, questions that the majority of members of the group answered incorrectly can be selectively reviewed by the entire group, thereby enabling the entire group to quickly improve their understanding of the questions.

[0011] In other words, according to the facility-related knowledge acquisition system of the present invention, in the learning area, the representative learns facility-related knowledge using digital devices, while the accompanying persons learn facility-related knowledge without using digital devices. However, while learning facility-related knowledge in the learning area, the concentration of the entire group can be maintained, and when reviewing facility-related knowledge in the review area, the effectiveness of facility-related knowledge acquisition for the entire group can be improved early on. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a schematic configuration diagram showing a facility-related knowledge acquisition system according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0013] A facility-related knowledge acquisition system 10 according to an embodiment of the present invention will be described below with reference to FIG. 1. The configurations shown below are merely examples, and are not intended to exclude various modifications or applications of technologies not explicitly stated. The configurations shown in the embodiments can be modified in various ways without departing from the spirit of the invention. Furthermore, the configurations can be selected or combined as needed, except for the essential components of the present invention.

[0014] The facility-related knowledge acquisition system 10 is a system for a group 3 including a representative 1 and accompanying person 2 to acquire facility-related knowledge. Acquiring facility-related knowledge means acquiring knowledge related to a specific facility, such as a waste disposal facility such as a waste incineration plant, a plant or company such as a power plant or chemical plant, or even an entertainment facility such as an amusement park. If the facility is a waste incineration plant, group 3 can acquire facility-related knowledge such as waste (garbage) sorting, disposal methods for each type of waste, and the operation and role of each piece of equipment in the waste incineration plant. That is, the facility-related knowledge acquisition system 10 can be used when a group including at least one representative and one accompanying person acquires knowledge related to some facility. Here, as an example, we will explain using group 3, which consists of 10 people in total, including two representatives (1-1, 1-2) and eight accompanying persons (2-1 to 2-8), as shown in Figure 1. The number of representatives and accompanying persons can be changed as appropriate, as long as each is at least one. In Study Area 4, which will be described later, all members of Group 3 are restricted from using their own digital devices, such as smartphones; instead, Representative 1 can use a dedicated digital device 13, but Accompanying Person 2 cannot use said digital device. On the other hand, in Review Area 5, digital device 13 is not loaned to any of them, so none of the members of Group 3 can use said digital device 13. However, in Review Area 5, there are no restrictions on the use of the digital devices owned by each member of Group 3.

[0015] First, the basic configuration of the facility-related knowledge acquisition system 10 will be explained, followed by a detailed description of each component. The overall operation of the facility-related knowledge acquisition system 10 will become clear in the description of the control device 16 below. First, we will explain the basic configuration of the facility-related knowledge acquisition system 10. The facility-related knowledge acquisition system 10 has at least the following components. Within the learning area 4, there are arranged a first display device 11 that displays questions about facility-related knowledge, as well as correct / incorrect answers and explanations for those questions, a first imaging device 12 that captures images of all members of group 3, namely representative 1 and accompanying person 2, and a digital device 13 that can only be used by representative 1 and not accompanying person 2. Also, a second display device 14 is arranged in the review area 5 to display questions that the majority of the group 3 got wrong at least in the study area. Furthermore, a memory device 15 that stores the multiple questions displayed on the first display device 11 and the second display device 14, the explanations corresponding to the correct answers to each question, and the correct actions of the person corresponding to the correct answers to each question, and a control device 16 that exchanges various information with the above-mentioned devices and equipment and memory device 15 placed in the study area 4 and the review area 5 to control them are placed in either the study area 4, the review area 5, or a location other than these. The exchange of various information between the control device 16 and the devices and equipment described above located in the study area 4 and review area 5, as well as the storage device 15, i.e., the sending and receiving of these various information, may be performed either wired or wirelessly. Information does not need to be sent and received directly between the devices, but may be sent and received indirectly via a communication network such as the Internet.

[0016] The learning area 4 is a specific location where all members of the group 3 gather to learn facility-related knowledge. In other words, the learning area 4 is a specific location. As long as the first imaging device 12 can capture images of all members of the group 3, including the representative 1 and accompanying persons 2, the specific location may be indoors, outdoors, inside the facility, or outside the facility. For example, the learning area 4 may be a specific location such as a conference room or multipurpose hall within the facility, a hallway or plaza within the facility, or a specific space outside the facility, such as a school classroom or an event venue such as an exhibition. Furthermore, review area 5 is a place where each of group 3's members, representative 1 and accompanying person 2, reviews the facility-related knowledge they learned in study area 4. Like study area 4, review area 5 may be a specific location where all group 3 members gather, or, unlike study area 4, it may be multiple locations where each individual member of group 3 or each group of group 3 is dispersed to different locations. In other words, review area 5 may be a specific location or multiple locations. For example, review area 5 may be a conference room or multipurpose hall within the facility, a hallway or plaza within the facility, a specific space outside the facility at a school classroom or event venue such as an exhibition, or the home of each member. Furthermore, the review area 5 may be located in the same place as the learning area 4. For example, after the group 3 has learned facility-related knowledge in the learning area 4, the group 3 may use the same place as the learning area 4 as the review area 5 to review the facility-related knowledge learned in the learning area 4.

[0017] [About the structure of Learning Area 4] Each component will now be described in turn. First, the components of the facility-related knowledge acquisition system 10 in the learning area 4 shown in FIG. The first display device 11 is a device that receives and displays questions about facility-related knowledge, as well as information such as correct answers and explanations for those questions, transmitted by the control device 16 described below, and also a device that allows the representative 1 to share information such as images that can be viewed on the digital device 13 described below with the accompanying person 2. Therefore, the first display device 11 may be any type of display device, and may be single or multiple, as long as all members of the group 3 can see the same content displayed on the digital device 13. However, if there are multiple first display devices 11, the same content is displayed on all first display devices 11 at the same time. The first display device 11 may be, for example, a display device such as a liquid crystal monitor, a screen combined with a projector, or an "air display" which has been developed in recent years. The first display device 11 may be equipped with a speaker and configured to be capable of outputting audio by reading out the questions, explanations, etc. The first imaging device 12 is a device that captures images of all members of the group 3, including the representative 1 and accompanying persons 2, and transmits the captured information to the control device 16, which will be described later, and is, for example, a wide-angle camera or an all-around camera. Since the first imaging device 12 needs to capture the body movements of each member of the group 3, it is desirable that it be a video camera that captures moving images or multiple still images that are consecutive in time. The microphone 17 is a device that collects the voices of the entire group 3 in the study area 4 and transmits information about the collected voices to the control device 16, which will be described later.

[0018] Digital devices 13 (two in Figure 1, 13-1 and 13-2) are digital devices that can be operated only by representative 1 (only two people, 1-1 and 1-2 in Figure 1), not by accompanying person 2, among the members of group 3. These devices receive and display information such as the questions and explanations described above from control device 16, which will be described later, and transmit representative 1's response actions to the questions to control device 16. Digital devices 13 are lent to representative 1, for example, by the facility administrator, only when learning facility-related knowledge in learning area 4. Digital devices 13 may also be lent to representative 1 when reviewing facility-related knowledge in review area 5, which will be described later, but as a general rule, digital devices 13 are not lent to any of the members of group 3 when such reviewing is being done. In addition, the representative 1 can answer the question without using the digital device 13 by having the first imaging device 12 (or the second imaging device 24 in the review area 5) capture his or her body movements, just like the accompanying person 2.

[0019] Of the above-mentioned components in the study area 4, the digital device 13 will be described in detail. The digital device 13 may be any device that can transmit information regarding the answering actions ("large body movements" and "small body movements" described below) that the representative 1 takes to answer the above questions to the control device 16 described below. Therefore, digital device 13 may be, for example, a tablet-type mobile terminal (hereinafter referred to as a "tablet") or a smartphone. Digital device 13 may also be a device for virtual reality, i.e., a VR device, or a device for augmented reality, i.e., an AR device. Digital device 13 may also be a device for mixed reality, i.e., an MR device, or a device for substitutional reality, i.e., an SR device. For example, if representative 1 is presented with questions while having a VR experience in order to acquire facility-related knowledge, digital device 13 is a VR device, and the VR device may be (a) VR goggles only, (b) a set of VR goggles and a VR module that is operated by hand with switches, etc., or (c) a VR module only.

[0020] It is desirable that digital device 13 is equipped with at least one of a camera, a motion sensor, or a switch in order to acquire information about the representative 1's answering action. Digital device 13 equipped with a camera or a motion sensor recognizes that the representative 1 has answered with a "large body movement" (described below) from the video captured by the camera or the change in acceleration detected by the motion sensor, and transmits information about the answering action to control device 16. Digital device 13 equipped with a switch recognizes that the representative 1 has answered with a "small body movement" (described below) from contact with the switch with a finger (for example, touching a touch panel) or pressing down the switch with a finger, and transmits information about the answering action to control device 16.

[0021] Here, "large body movements" refer to movements that involve large movements of large body parts such as the arms and legs, such as raising and lowering the arms, crouching, standing up, etc. Raising the right hand or the left hand is also a "large body movement." On the other hand, "small body movements" do not involve large movements of large body parts such as the arms or legs, but rather movements that involve small body parts such as the fingertips, for example, finger movements. Here, we will proceed under the assumption that the control device 16 can recognize "large body movements" as answering movements based on the information captured by the first imaging device 12, but that the control device 16 cannot or has difficulty recognizing "small body movements" as answering movements based on the information captured by the first imaging device 12. Furthermore, if the digital device 13 is equipped with both the camera and the like as described above, the representative 1 can simultaneously answer using both "large body movements" and "small body movements," which may result in contradictory answering actions. In this case, the facility-related knowledge acquisition system 10 deals with this by establishing a rule in advance, for example, to give priority to answering actions using "small body movements." For ease of explanation, the following discussion will proceed assuming that the answering action by the digital device 13 is not a simultaneous "large body movement" and "small body movement," but rather that only one of the answering actions is performed for a given question.

[0022] [About the structure of Review Area 5] Next, we will explain the configuration of the facility-related knowledge acquisition system 10 in the review area 5 shown in Fig. 1. The review area 5 in Fig. 1 is a diagram showing, as an example, a state in which all members of a group 3 are gathered and seated in a classroom in a school or the like. As mentioned above, in the review area 5, unlike the study area 4, digital devices 13 are not loaned to any of the members of group 3 in principle, so there is no point in distinguishing between representative 1 and accompanying person 2. In other words, in this case, all members perform the answering actions corresponding to the accompanying person in study area 4. However, for convenience, the same numbers as those used for the members of study area 4 in Figure 1 are used for the members of review area 5.

[0023] First, second display device 14 is a device that receives and displays questions about facility-related knowledge transmitted by control device 16, which will be described later, at least questions asked in learning area 4 that the majority of members of group 3 got wrong, as well as information such as correct / incorrect answers and explanations for those questions. Like first display device 11, second display device 14 may be any type of display device, such as an LCD monitor or an aerial display, as long as all members of group 3 can see the same content, and may be singular or multiple. Furthermore, in the study area 4, none of the members of group 3 could use their own digital devices as the first display device 11, but in the review area 5, they could use their own digital devices, such as smartphones, tablets, or laptops, as the second display device 14. In this case, unlike the first display device 11, the content and timing of display of questions, explanations, etc. on the second display device 14 do not have to be the same and may be different for each member. In other words, each member of group 3 can access the control device 16 using their own digital device and review at their own desired speed. Like the first display device 11, the second display device 14 may be provided with a speaker and configured to be capable of outputting audio reading of the questions, explanations, etc.

[0024] Next, second imaging device 24, like first imaging device 12, is a device that captures images of members of group 3 and transmits the captured information to control device 16 (described later), and is, for example, a wide-angle or omnidirectional video camera. In FIG. 1, second imaging device 24 captures "large body movements" (for example, raising the right or left hand) of the upper body of all seated members of group 3. Also, as described above, in review area 5, members of group 3 can use their own digital devices, so second imaging device 24 may be a camera built into each member's digital device. In addition, if the study area 4 and the review area 5 are in the same location, the second display device 14 may be the first display device 11, and the second imaging device 24 may be the first imaging device 12.

[0025] [Regarding the storage device 15 and the control device 16] Next, we will explain the storage device 15 and control device 16 provided in the facility-related knowledge acquisition system 10. As mentioned above, the storage device 15 and control device 16 are placed in either the learning area 4, the review area 5, or a location other than these, but if the learning area 4 is placed within the facility, it is desirable to place them in the learning area 4 or within the facility to facilitate management and maintenance of the facility-related knowledge acquisition system 10. First, the storage device 15 pre-stores at least a plurality of questions for acquiring facility-related knowledge, a plurality of explanations corresponding to the correct answers to each of the plurality of questions, and information regarding each "correct action" for each question.

[0026] Here, the "correct action" for a certain question means an action that corresponds to the correct answer to the question, among the possible action responses that the representative or accompanying person can perform. As described above, the representative 1 can answer each question using two types of answering actions: either a "large body movement" or a "small body movement." On the other hand, the accompanying person 2 answers each question using only a "large body movement." Therefore, the storage device 15 stores in advance two types of correct answering actions for each question: either a "large body movement" or a "small body movement." For example, if the correct answer to the question "Which is correct, right or left?" is "right," the correct body movement action of "moving your arm to point to the right," which is a type of "large body movement," is pre-stored in storage device 15. In addition to this information, information on the correct body movement action of "pressing down the switch corresponding to 'right' on digital device 13" or "touching the switch corresponding to 'right' on the touch panel," which is a type of "small body movement," is also pre-stored in storage device 15.

[0027] When control is performed using microphone 17, which will be described later, information about the voice of the word (vocabulary word) corresponding to the correct action for each question (hereinafter referred to as "voice information") is stored in advance in storage device 15, linked to the correct action for each question. For example, in the case of the correct action of "pointing to the right by moving your arm," voice information of the word "right" is stored in advance in storage device 15. Similarly, in the case of the correct action of "pointing to the left by moving your arm," voice information of the word "left" is stored in advance in storage device 15, linked to the correct action.

[0028] Next, the control device 16 will be described. The control device 16 includes at least a question selection unit 18, a representative action recognition unit 19, a most-person action recognition unit 20, a correct / incorrect determination unit 21, and a correct answer explanation unit 22. The control device 16 may further include a group voice recognition unit 23. These configurations will be explained in order below.

[0029] [About Question Selection Section 18] The question selection unit 18 selects at least some of the questions stored in the memory device 15 and displays them on the first display device 11 and the digital device 13 in the study area 4. The question selection unit 18 may select each question sequentially in the order in which the questions are stored in the memory device 15, or may select each question randomly. In addition, the question selection unit 18 selects from the memory device 15 the questions for which the "most common answering action," which is the answering action taken by the most number of all members of group 3, was incorrect as a result of questions being asked in the learning area 4, and displays the questions on the second display device 14 in the review area 5.

[0030] [About Representative Action Recognition Unit 19] First, the representative action recognition unit 19 receives information about the representative 1's answer action using "large body movements" or "small body movements" in response to the question that the question selection unit 18 has displayed on the first display device 11 in the study area 4 from the digital device 13. When there are multiple representatives 1, for example, when there are two representatives 1-1 and 1-2 as shown in FIG. 1, the representative action recognition unit 19 separately receives information about each representative's answer action from the respective digital devices 13 (13-1, 13-2) used by each representative. For example, in the case of a question such as "Which is correct, right or left?", the representative action recognition unit 19 recognizes, based on the received information, what kind of response action the representative 1 made by "large body action" or "small body action", i.e., whether the representative made (1) a response action corresponding to "right", (2) a response action corresponding to "left", or (3) a response action that does not correspond to "right" or "left" (for example, a response action corresponding to "up" or "down"). If there are multiple representatives 1, the representative action recognition unit 19 performs this recognition for each representative.

[0031] Next, the representative action recognition unit 19 transmits information about the recognized answering action of the representative 1 (here, information about any one of (1), (2), and (3) above) to the correctness determination unit 21, which will be described later, and also to the most-person action recognition unit 20, which will be described later. If there are multiple representatives 1, the representative action recognition unit 19 transmits information about the recognized answering action of each representative to the correctness determination unit 21 and the most-person action recognition unit 20, for each representative. Here, if the recognized answering action of representative 1 is an answering action using a "small body movement," the representative action recognition unit 19 transmits information about the recognized answering action of representative 1 (here, information about one of the above (1), (2), and (3)) to the most-person action recognition unit 20, along with "difference information" indicating that the answering action is not a "large body movement."

[0032] [About the Largest Number of People Action Recognition Unit 20] First, the most number of people action recognition unit 20 receives the information captured by the first imaging device 12 in the learning area 4, individually recognizes the answering actions using "large body movements" of each member of the group 3, and counts the number of people who performed the specified answering action. For example, in the case of a question such as "Which is correct, right or left?", based on the information captured by the first imaging device 12, the largest-person action recognition unit 20 individually recognizes for each member of group 3 whether they (1) made an answering action corresponding to "right", (2) made an answering action corresponding to "left", or (3) made an answering action that did not correspond to "right" or "left". Now, assume that representative 1 and accompanying person 2 make a "large body movement" by raising their hands as an answering action, as shown in learning area 4 in Fig. 1. Then, based on the information captured by first imaging device 12, most-person action recognition unit 20 recognizes that, of all 10 members of group 3, six people made an answering action corresponding to (1) "right" (i.e., the number of people corresponding to accompanying people 2-1, 2-2, 2-3, 2-4, 2-5, and 2-6 in Fig. 1), two people made an answering action corresponding to (2) "left" (i.e., the number of people corresponding to representative 1-2 and accompanying person 2-7 in Fig. 1), and two people made an answering action that did not correspond to (3) "right" or "left" (i.e., the number of people corresponding to representative 1-1 and accompanying person 2-8). At this time, if there is an answering action by the representative 1-1 accompanied by "discrepancy information," the answering action is not a "large body movement," and therefore the counting result recognized by the most numerous person action recognition unit 20 based only on the information photographed by the first imaging device 12 (hereinafter referred to as "counting result based only on photographed information") will be inaccurate. In this example, in the recognition result of the most numerous person action recognition unit 20 based only on the information photographed by the first imaging device 12, the representative 1-1 is counted as being included in those who made answering actions that do not correspond to "right" or "left" in (3), which are different from the actual answering actions.

[0033] Therefore, the most-person action recognition unit 20 uses the “difference information” received from the representative action recognition unit 19 to correct the counting result recognized based only on information related to photography by the first imaging device 12 . For example, at this time, it is assumed that the most-person action recognition unit 20 receives from the representative action recognition unit 19 an answer action (1) accompanied by "difference information" for one of the two representatives, representative 1-1 and representative 1-2 (here, representative 1-1), and an answer action (2) without "difference information" for the other representative (here, representative 1-2). As a result, since the answering action of one person is accompanied by "difference information," the most-person action recognition unit 20 subtracts one person from the counting result for (3) among the counting results based only on the photographed information, and corrects the counting result for (3) to be (2-1) = 1, which is 1 person. Furthermore, since it is clear from the information received from the representative action recognition unit 19 that the answering action accompanied by "difference information" for the one person subtracted is the answering action of (1), the most-person action recognition unit 20 adds one person to the counting result for (1) among the counting results based only on the information photographed by the first imaging device 12, and corrects the counting result for (1) to be (6+1) = 7, which is 7 people (i.e., the number of people corresponding to the representative 1-1 and accompanying persons 2-1, 2-2, 2-3, 2-4, 2-5, and 2-6 in FIG. 1).

[0034] That is, with this correction, the most-person action recognition unit 20 accurately recognizes that seven people made an answering action corresponding to "right" in (1), two people made an answering action corresponding to "left" in (2), and one person made an answering action that does not correspond to "right" or "left" in (3). Then, the most popular action recognition unit 20 compares the counting results of (1), (2), and (3) after the correction, and recognizes that the most popular answer action, which is the most popular answer action among the answer actions of all the members of group 3, is answer action (1), and transmits information about answer action (1) as the ``most popular answer action'' to the correctness determination unit 21 described below.

[0035] In this example, the answering action of the most people is the answering action of seven people, which is the majority of the members of group 3, but depending on the question, such as a multiple-choice question, the answering action that is the majority in group 3 may not necessarily be recognized as the answering action of the most people by most people action recognition unit 20. As a result of making the above-mentioned corrections, most people action recognition unit 20 recognizes the answering action of the most majority in group 3 as the answering action of the most people. However, there may be cases where the answering actions of all members of group 3 are divided into multiple groups with the same number of answering actions in each group. For example, in the above example, there may be cases where, of the 10 members of group 3, the counting result of (1) is 5 and the counting result of (2) is 5. In this case, the most-popular-person action recognition unit 20 may select either the answering action of (1) or (2) as the "most-popular-person answering action." As described above, the question selection unit 18 displays questions for which the "most-popular-person answering action" is incorrect on the second display device 14 in the review area 5, and has all members of group 3 review the questions. However, questions with an equal number of correct or incorrect answers are not as high a priority as questions for which the majority of group 3 get them wrong, from the perspective of improving the effectiveness of group 3's overall acquisition of facility-related knowledge, and so may or may not be selected as review questions.

[0036] When transmitting the most popular answering action to the correctness determining unit 21 described later, the most popular action recognizing unit 20 may also transmit "first compulsory information" linked to the most popular answering action. The "first compulsory information" is information indicating whether the "action answered by the most people" is performed by a predetermined percentage or less of the number of members constituting group 3, and if the number is less than the predetermined percentage, the most popular action recognition unit 20 transmits the "first compulsory information" together with information about the "action answered by the most people" to the correctness determination unit 21. Note that the information means that the question regarding the "action answered by the most people" linked to the "first compulsory information" is to be reviewed by all members constituting group 3 in the review area 5, regardless of whether the "action answered by the most people" was actually correct or incorrect. In this case, the most people's action recognition unit 20 calculates the proportion of the number of people in group 3 who performed the most people's answering action from the ratio between the number of people who performed the most people's answering action and the total number of members constituting group 3.

[0037] As mentioned above, if the answering actions of all members of group 3 are divided into equal numbers, it may or may not be selected as a review question. However, for example, if the above-mentioned predetermined ratio of the "first compulsory information" is set to 50%, and if, out of the 10 members of group 3, the counting results of (1) are 5 and the counting results of (2) are 5, then regardless of whether the "answering action of the most people" was actually correct or incorrect, all members of group 3 can be sure to review the question corresponding to the "answering action of the most people" in review area 5. Furthermore, for example, if the predetermined percentage is set to 70%, even if the "most popular answering action" performed by 70% of the people is correct, all members of group 3 can be made to review it in review area 5. That is, when the configuration in which the most-person action recognition unit 20 transmits the "first required information" is adopted, the result of group 3 acquiring facility-related knowledge can be further strengthened.

[0038] When reviewing in the review area 5, the most-person action recognition unit 20 receives information captured by the second imaging device 24 in the review area 5 and performs the same operations as those in the study area 4. However, with regard to the review area 5, the most-person action recognition unit 20 does not receive information from the representative action recognition unit 19, which is different from the operations in the study area 4.

[0039] [About the accuracy check unit 21] In the learning area 4, the correctness determination unit 21 receives information about the representative 1's answering action recognized by the representative action recognition unit 19 and information about the answering action of the most popular person recognized by the most popular person action recognition unit 20. Then, the correctness determination unit 21 compares each of these received pieces of information with information about the correct action stored in the storage device 15, thereby determining whether the representative 1's answering action and the most popular person's answering action for each question are correct or incorrect, and transmits the determination result of either a correct answer or an incorrect answer to the correct answer explanation unit 22, which will be described later. Furthermore, correctness judgment unit 21 stores the judgment results of whether the representative 1's answering action and the most popular answering action are correct or incorrect (i.e., the judgment result of either correct or incorrect) in memory device 15, linked to the corresponding question. Here, control device 16 can determine whether it is study time in study area 4 or review time in review area 5 based on whether the judgment result is stored in memory device 15 or not. In other words, control device 16 can recognize that it is study time when it stores the judgment result in memory device 15 for the first time, and that it is review time when it saves the judgment result by overwriting an already stored judgment result. In addition, the correctness judgment unit 21 judges the most popular answer action received along with "mandatory information" (including not only "first mandatory information" but also "second mandatory information" described below) as an incorrect answer regardless of whether it is actually correct or incorrect. Furthermore, when reviewing in the review area 5, the correctness determination unit 21 performs the same operations as in the learning area 4. However, at this time, the correctness determination unit 21 does not receive information from the representative action recognition unit 19, which is different from the operations in the learning area 4.

[0040] [About the correct answer explanation section 22] During learning in the learning area 4, the correct answer explanation unit 22 displays the judgment result of the representative 1 on the first display device 11 in the learning area 4 based on at least information relating to the judgment result of the representative 1's answer action, out of the information relating to the judgment result received or the information relating to the judgment result stored in the storage device 15. The correct answer explanation unit 22 may also display the judgment result relating to the answer action of the most people on the first display device 11. Then, the correct answer explanation unit 22 displays an explanation corresponding to the judgment result (for example, an explanation of the correct answer to the question) on the first display device 11, or outputs it as audio from a speaker or the like of the first display device 11 using a generation AI or the like. In addition, when reviewing in the review area 5, the correct answer explanation unit 22 displays the judgment result regarding the most popular answer action and the explanation corresponding to the judgment result on the second display device 14, or outputs it as audio from the speaker of the second display device 14 using a generation AI or the like.

[0041] [About the Group Speech Recognition Unit 23] The group voice recognition unit 23 receives voice information collected by the microphone 17 in the learning area 4 and words corresponding to the correct action for each question stored in advance in the storage device 15, and performs a voice analysis. For example, in the case of the question "Which is correct, right or left?", the collective voice recognition unit 23 has received in advance voice information, such as "right," as a word corresponding to the correct action from the storage device 15. Then, when the collective voice recognition unit 23 receives input of voice information collected by the microphone 17 and cannot recognize voice information corresponding to "right," which is the word corresponding to the correct action, at a volume equal to or greater than a predetermined level, it recognizes that the majority of the members of the group 3 are not confident that the answer is correct, that there is disagreement within the group 3, or that the answer is incorrect. Therefore, in this case, the collective voice recognition unit 23 transmits "second compulsory information" to the correctness determination unit 21 as information linked to the information on the action answered by the most people transmitted by the most people action recognition unit 20. Like the first compulsory information, the "second compulsory information" is information that means that regardless of whether the "action with the most people answering" is actually correct or not, all members of group 3 will be required to review it in review area 5. Therefore, even if the "action with the most people answering" for a certain question is correct, if the majority of members of group 3 are not confident that it is the correct answer or if there is a dispute of opinion, all members of group 3 can be required to review it in review area 5. That is, when the group speech recognition unit 23 is configured to transmit the "second compulsory information," the result of acquiring facility-related knowledge for group 3 can be further strengthened. When the group voice recognition unit 23 recognizes the voice information corresponding to the word "right," which corresponds to the correct action, at a volume equal to or greater than a predetermined volume, it recognizes that the majority of the members of group 3 are confident that the answer is correct. In this case, the group voice recognition unit 23 does not transmit the "second compulsory information" to the correctness determination unit 21.

[0042] As described above, according to the facility-related knowledge acquisition system of the present invention, in the learning area, the representative learns facility-related knowledge using digital devices, while the accompanying persons learn facility-related knowledge without using digital devices. However, while learning facility-related knowledge in the learning area, the concentration of the entire group can be maintained, and when reviewing facility-related knowledge in the review area, the effectiveness of facility-related knowledge acquisition for the entire group can be improved early on. The first display device 11 may be configured as a single panel-type device in which the first display device 11, the first imaging device 12, the microphone 17, and a speaker (not shown) are integrated together, and similarly, the second display device 14 may be configured as a single panel-type device in which the second display device 14, the second imaging device 24, and a speaker (not shown) are integrated together. The first display device 11 and the second display device 14 may also be provided with a function to print correct answers and explanations for each question. Furthermore, the first imaging device 12 and the second imaging device 24 are not limited to being a single imaging device each, and may be a system made up of a plurality of imaging devices. [Explanation of symbols]

[0043] 1, 1-1~1-2 Representative 2, 2-1~2―8 Companions 3. Group 4. Study Area 5 Review Area 10 Facility-related knowledge acquisition system 11 First display device 12 First imaging device 13, 13-1, 13-2 Digital devices 14 Second display device 15 Storage device 16 Control device 17. Mike 18 Question Selection Section 19 Representative action recognition unit 20 Maximum number of people motion recognition unit 21 Correctness Judgment Section 22 Correct Answer Explanation Section 23 Group Voice Recognition Unit 24 Second imaging device

Claims

1. A facility-related knowledge acquisition system for a group including a representative and a companion to acquire facility-related knowledge, The learning area includes a first imaging device that images the group, a digital device that is not used by the accompanying person but is used only by the representative, and a first display device that displays at least the same content as that seen by the representative and that can be seen by at least the accompanying person. The review area includes a second display device that allows the representative and the accompanying person to view the same content. and a storage device that stores a plurality of questions set in advance regarding the facility-related knowledge, a plurality of explanations corresponding to the correct answers to each of the plurality of questions, and correct actions of the representative and the accompanying person corresponding to each of the correct answers; Control device and and The control device a question selection unit that selects at least one question from the plurality of questions stored in the storage device and displays it on the first display device; a representative action recognition unit that recognizes, based on the digital device, an answer action of the representative to the question displayed on the first display device; a most-popular-person action recognition unit that recognizes, based on the first imaging device, each answering action made by each individual of the group using large body movements in response to a question displayed on the first display device, and corrects the recognition based on the first imaging device based on difference information indicating that the answering action of the representative recognized by the representative action recognition unit is different from the large body movements, thereby recognizing a most-popular-person answering action that indicates the answering action made by the most people in the entire group; a correctness determination unit that determines whether the representative's answering action and the most popular answering action are correct by comparing the representative's answering action recognized by the representative action recognition unit and the most popular answering action recognized by the most popular action recognition unit with the correct actions stored in the storage device, and stores the results of the correctness determination in the storage device in association with each of the questions; a correct answer explanation unit that displays a result of the determination of correctness by the representative on the first display device, and that displays or outputs the explanation corresponding to the result of the determination on the first display device or by voice from the first display device; Equipped with The question selection unit is a facility-related knowledge acquisition system that displays on the second display device, among the plurality of questions, questions for which the result of the judgment of the most popular answer action stored in the memory device was incorrect.

2. the most-popular-person action recognition unit transmits required information indicating that the percentage of people who performed the most-popular response action is equal to or less than a predetermined percentage to the correct / incorrect determination unit; 2. The facility-related knowledge acquisition system according to claim 1, wherein the correctness determining unit determines that the most popular answering action is incorrect when the required information is received.

3. the study area is a single location where all members of the group gather; The facility-related knowledge acquisition system of claim 2, wherein the review area is either the same location as the study area, a single location different from the study area where all members of the group gather, or multiple locations where each individual in the group is dispersed.

4. the review area is a single location where everyone in the group gathers; the review area further includes a second imaging device that images the group; the most numerous person action recognition unit recognizes, based on the second imaging device, each answering action made by each individual of the group with a large body movement in response to a question displayed on the second display device by the question selection unit, thereby recognizing a most numerous answering action that indicates the answering action made by the most number of people in the entire group; the correctness determination unit determines whether the most popular answering action is correct or incorrect; The facility-related knowledge acquisition system described in claim 3, wherein the correct answer explanation unit displays the result of the correct / incorrect judgment on the second display device, and displays the explanation corresponding to the result of the judgment on the second display device or outputs it as audio from the second display device.

5. a microphone located in the study area; a group voice recognition unit that recognizes voices collected by the microphone; and The correctness determination unit When the group voice recognition unit recognizes the words corresponding to the most popular answering action at a volume equal to or greater than a predetermined volume, it determines whether the words are correct or incorrect based on the most popular answering action; A facility-related knowledge acquisition system as described in any one of claims 1 to 4, wherein if the collective voice recognition unit recognizes the words corresponding to the most popular answering action at a volume less than the predetermined amount, it determines that the most popular answering action is incorrect.

Images