JP2020027372A - Management device, management system, management method, and program - Google Patents

Abstract

To provide a management device, a monitoring system, a management method, and a program that can discriminate if a visitor who visits a home or a shop is a visitor who has a right reason for the visit or an unauthorized intruder who does not have a right reason for the visit automatically and can conduct proper processing according to the discrimination result.SOLUTION: A management device 100 of a condominium 30 has a device main body 101 comprising a detector 102 detecting a person who stands at outside of an entrance to a certain area of a building, an estimation part estimating necessity of specific processing from the person who stands at outside of the entrance detected by the detector on the basis of a learning result of a relationship between the person who stands at outside of the entrance to the certain area of the building and necessity of the specific processing, and a processing part conducting the specific processing when the estimation part has estimated that the specific processing is necessary.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a management device, a management system, a management method, and a program.

Based on images and sounds acquired from security devices installed in homes and stores, acquaintance information for identifying persons who do not need to be reported is recorded in advance, and new images or sounds of visitors are recorded. There is known a security system that, when acquired, collates the acquired information with pre-recorded acquaintance information (for example, see Patent Document 1).
[Prior art documents]
[Patent Document]
[Patent Document 1] JP-A-2006-177484

  However, in the above security system, when a new visitor is not recorded in the acquaintance information, it is regarded as an unauthorized intruder and reported to the user terminal, and the user is requested to perform an operation on the user terminal. It was troublesome for the user.

  In one embodiment of the present invention, a detection unit that detects a person outside an entrance to a specific region in a building, and a detection unit that determines whether a person outside the entrance to a specific region in the building and a specific process are necessary. Based on the learning result of the relationship, an estimating unit for estimating the necessity of a specific process from a person outside the entrance detected by the detecting unit, and a specific estimating unit when the estimating unit estimates that a specific process is necessary. A management device including a processing unit that executes processing is provided.

  According to one embodiment of the present invention, there is provided a management system including a plurality of the management devices, wherein a building in which one of the plurality of management devices is provided is one of a residence, a work place, and a school destination. However, when a building provided with another management device among a plurality of management devices is newly used as one of a residence, a work place, and a school destination, the learning result of one management device is transferred to another management device. A management system for sharing is provided.

  In one embodiment of the present invention, a detection step of detecting a person outside an entrance to a specific area in a building and a step of determining whether a person outside the entrance to a specific area in the building and a specific process are necessary. Based on the learning result of the relationship, an estimation step of estimating the necessity of a specific process from a person outside the entrance detected in the detection step, and a specific process when a specific process is estimated to be necessary by the estimation stage. And a processing step of performing the processing.

  According to one embodiment of the present invention, there is provided a program for causing a computer to execute the above management method.

  The above summary of the present invention does not list all of the necessary features of the present invention. Further, a sub-combination of these feature groups can also be an invention.

FIG. 4 is a schematic diagram of an entrance, which is a common part of the apartment 30 in which the management device 100 is installed, according to the first embodiment. FIG. 2 is a block diagram of the management device 100 according to the first embodiment. FIG. 4 is a flowchart illustrating an example of learning according to the first embodiment. FIG. 6 is a flowchart illustrating an example of a process until a specific process is performed based on a learning result according to the first embodiment. FIG. 6 is a flowchart illustrating an example of a process until a specific process is performed based on a learning result according to the first embodiment. FIG. 11 is a flowchart illustrating an example of a process until a specific process is performed based on a learning result according to the second embodiment. FIG. 14 illustrates an example of a computer 1200 in which aspects of the present invention may be wholly or partially embodied.

  Hereinafter, the present invention will be described through embodiments of the invention, but the following embodiments do not limit the invention according to the claims. In addition, not all combinations of the features described in the embodiments are necessarily essential to the solution of the invention. In the drawings, the same or similar portions are denoted by the same reference numerals, and duplicate description may be omitted.

  FIG. 1 is a schematic diagram of a state of an entrance, which is a common part of an apartment 30 in which a management device 100 is installed, according to the first embodiment. An entrance door 41 that opens and closes automatically is provided at the entrance of the condominium 30, and the entrance door 41 partitions an outer area 31 and an inner area 33 of the entrance. The apartment 30 is an example of a building, the area 33 inside the entrance door 41 is an example of a specific area in the building, and the entrance door 41 is an example of an entrance to the specific area.

  An operation panel 43 is provided in the area 31 outside the entrance door 41. In the situation shown in FIG. 1, a first person 61 operating the operation panel 43, a second person 63 holding a hand with the first person 61, and a first person are provided in the area 31 outside the entrance door 41. There is a third person 65 standing away from the second person 63 and the second person 63. The first person 61, the second person 63, and the third person 65 are examples of persons outside the entrance to the above-described specific area, and the first person 61 controls the operation panel 43 to unlock the entrance door 41. The second person 63 and the third person 65 are examples of a person different from the operator.

  The operation panel 43 is connected to the management device 100 via a communication network 50 by wire communication or wireless communication. The operation panel 43 has an interface operated by a resident of the apartment 30 or a visitor to the apartment 30. The interface includes, for example, a touch panel operated by the operator, and a camera that images the face of the operator from the front. The interface may further collect the uttered voice by the operator and utter the uttered voice collected by the indoor intercom provided in each room of the apartment 30. The touch panel includes, for example, an unlock button for unlocking the entrance door 41 and a call button for inputting and calling the room number of the apartment 30. Information input and output through the interface of the operation panel 43 is transmitted and received to and from the management device 100.

  The management device 100 includes a device main body 101 and a detection unit 102. The device main body 101 may be integrated with the operation panel 43, or may be provided separately from the operation panel 43, for example, in a management room of the apartment 30. The apparatus main body 101 is connected to the operation panel 43 and the detection unit 102 via a communication network 50 by wire communication or wireless communication. The apparatus main body 101 is further provided with a notification destination registered in advance by wire communication or wireless communication via the communication network 50, for example, an indoor intercom provided in each living room of the apartment 30, a communication terminal of each resident of the apartment 30, an apartment, The communication device may be connected to at least one of the communication device in the 30 administrator room, the communication device of the security company managing the security of the condominium 30, and the communication device of the police.

  The detection unit 102 detects a person in the area 31 outside the entrance door 41. The detection unit 102 includes, for example, a camera that captures a moving image. As an example, the detection unit 102 is installed on a wall surface above the entrance door 41 and captures an image of the area 31 outside the entrance door 41. In FIG. 1, as an example, a single detection unit 102 is installed, but instead of this, a plurality of detection units that detect at least a person who is in the area 31 outside the entrance door 41 from different directions. 102 may be installed. The detection unit 102 transmits the captured image data to the apparatus main body 101 via the communication network 50 as needed. The image data may be still image data or moving image data. The image data includes image data of a person in the area 31 outside the entrance door 41 as a subject.

  The apparatus main body 101 incorporates artificial intelligence (AI). In the present embodiment, the artificial intelligence of the device main body 101 learns the relationship between the person in the area 31 outside the entrance door 41 and the necessity of a specific process among a plurality of different processes, and based on the learning result. From the person in the outer region 31 detected by the detection unit 102, the necessity of a specific process among a plurality of different processes is estimated. Instead of this, the artificial intelligence of the device main body 101 learns the relationship between the person in the area 31 outside the entrance door 41 and the necessity of a single specific process, and performs detection based on the learning result. The necessity of the single specific process may be estimated from the person in the outer region 31 detected by the unit 102.

  The specific process is performed, for example, when the device main body 101 receives an input of an unlocking operation of the entrance door 41 by an operator of the operation panel 43 from the operation panel 43 via the communication network 50, and Request processing for requesting confirmation of a person different from the operator. The request process differs in real time by presenting information about the different person to the operator, for example, on a touch panel of the operation panel 43 after receiving an input of an unlocking operation of the entrance door 41 by the operator. A process for requesting confirmation of a person may be included. In addition, the request processing is performed, after receiving the input of the unlocking operation of the entrance door 41 by the operator, to the operator, for example, the information about the different person described above in the communication terminal or the room interphone of the operator registered in advance. May be included to request a confirmation of a different person afterwards. In addition, presenting information about a different person to each device is, for example, displaying an image of a different person detected by the detection unit 102 on the display of each device, and setting an index for notifying that a different person exists. It may include at least one of displaying on a display, and uttering a voice notifying that a different person is present from each device.

  The specific process also includes, as an example, an alert process for the entrance door 41. The warning process is performed by locking the entrance door 41, closing the entrance door 41, locking the entrance to the apartment 30 other than the entrance door 41, closing the entrance, warning at the entrance door 41, and a pre-registered example described above. At least one of notification to the notified destination. The warning at the entrance door 41 includes, for example, at least one of utterance of a warning sound from the operation panel 43 and blinking of a warning lamp provided in the area 31 outside the entrance door 41.

  Certain processes also include, by way of example, dominant processes. The superior processing includes, for example, (A) unlocking of the entrance door 41, (B) opening of the entrance door 41, (C) release of the alert of the entrance door 41, and (D) notification registered in advance. At least one of the above-mentioned (A) unlocking, the above (B) door opening, and the above (C) warning release remote request at least one of remote control operations. Here, the notification destination registered in advance includes, as an example, a communication terminal of a resident at a visit destination called by the operator of the operation panel 43 from the operation panel 43.

  The apparatus main body 101 further executes the specific processing when it is estimated that the specific processing is necessary.

  The management apparatus 100 uses such processing by artificial intelligence to determine whether specific processing is necessary not only for a person who has entered and exited the apartment 30 but also for a person who has visited the apartment 30 for the first time. Estimate whether or not to execute automatically.

  FIG. 2 is a block diagram of the management device 100 according to the first embodiment. The management device 100 includes the detection unit 102 in addition to the device main body 101 as described above. The device main body 101 includes a communication unit 111, an estimation unit 113, a storage unit 117, and a processing unit 119.

  When the communication unit 111 receives any information from the operation panel 43 via the communication network 50, the communication unit 111 outputs the information to the estimation unit 113. Upon receiving image data from the detection unit 102 via the communication network 50 as an example, the communication unit 111 outputs the image data to the estimation unit 113 and the processing unit 119. When any information and a control signal are input from the estimation unit 113 and the processing unit 119, the communication unit 111 transmits the information to any one of the operation panel 43 and the entrance door 41 via the communication network 50 based on the control signal. Transmit any information and / or control signals.

  The estimation unit 113 includes the above-described artificial intelligence. The estimating unit 113 learns the relationship between the person in the area 31 outside the entrance door 41 and the necessity of a specific process. Based on the learning result, the estimating unit 113 calculates, from the person in the outside area 31 detected by the detecting unit 102, Estimate the necessity of specific processing.

  As an example of the learning, the estimating unit 113 in the present embodiment learns the relationship between the interpersonal relationship between the operator of the operation panel 43 and a person different from the operator and whether or not the specific processing is required. I do. The interpersonal relationship is, for example, a relationship in which the operator is conscious of entering the area 33 inside the entrance door 41 together with the different person, and a consciousness of entering the area 33 inside. Including no relationships. The estimating unit 113 further executes the above-described request processing, and based on the result of the confirmation of the different person by the operator, determines the relationship between the interpersonal relationship between the operator and the different person and whether or not the specific processing is necessary. May be learned.

  As an example, the estimating unit 113 sends the case where at least one of the following conditions (D) to (K) is satisfied to the above-described region 33 inside the entrance door 41 together with a different operator of the operation panel 43. You may learn as a relationship conscious of entering. In addition, for example, the conditions shown in the following conditions (D) to (K) are, as an example, in addition to the detection target range by the detection unit 102, the area 33 inside the entrance door 41 of the apartment 30, the corridor, the elevator, and the like. Alternatively, image data that is detected by a camera or the like installed in at least one of the places such as a parking lot and the detected state may be transmitted to the estimation unit 113.

  (D) The time during which the state in which the distance between the operator of the operation panel 43 and a different person is shorter than the predetermined length threshold is longer than the predetermined time threshold. (E) A different person enters the inside area 33 from the entrance door 41 within a time shorter than a predetermined time threshold after the operator of the operation panel 43 enters the inside area 33 from the entrance door 41. thing. (F) A person different from the operator of the operation panel 43 is in direct or indirect contact. (G) There is a history that a person different from the operator of the operation panel 43 has entered the inside area 33 from the entrance door 41 together with the threshold of a predetermined number of times or more.

  (H) There is a history that a person different from the operator of the operation panel 43 has moved a predetermined distance or more in the area 33 inside the entrance door 41 together with the threshold of the predetermined number of times or more. thing. (I) The history that a person who is different from the operator of the operation panel 43 together with the operator of the operation panel 43 for a time equal to or more than a predetermined time threshold value is present in the room of the operator or a meeting room or an entrance hall which is a shared part of the apartment 30 is recorded. There is. (J) The image of the operator of the operation panel 43 published on the SNS includes a person different from the operator. (K) A different person visits the operator of the operation panel 43, and the operator responds in a good manner, for example, shows a good expression, answers with a good tone, or invites the operator to his / her room. Have a history.

  The estimating unit 113 in the present embodiment also learns the relationship between the person in the area 31 outside the entrance door 41 in the apartment 30 and the necessity of the above-described alert processing. The persons who need to be alerted include, for example, at least one of a thief, a robber, a suspicious person, a malicious salesman, a stalker, a trespasser, and an illegal dumper of garbage. Such a person may be registered as a subject requiring alert processing, for example, in a database of a security company of the condominium 30 or a criminal database of the police, and further record actions taken by such a person. It may be. The estimating unit 113 also learns the relationship between the situation of the person in the area 31 outside the entrance door 41 in the apartment 30 and the necessity of the alert processing. In this case, the estimating unit 113 obtains, as an example, a record of an action taken by a person registered as a target requiring alert processing from the database, and from the record, an entrance door requiring alert processing. The situation of the person in the area 31 outside the area 41 may be learned.

  As an example, the estimating unit 113 determines whether a person who is outside the entrance to a specific area in the building and needs the alert processing described above when at least one of the following conditions (L) to (N) is satisfied. You may learn as the situation. In addition, for example, the conditions shown in the following conditions (L) to (N) include the detection target range by the detection unit 102 and the area 33 inside the entrance door 41 of the apartment 30 in the same manner as described above. Image data that is detected by a camera or the like installed at the place and indicates the detected state may be transmitted to the estimation unit 113.

  (L) Performing a specific behavior pattern in the apartment 30. As a specific action pattern, as an example, the surroundings may be repeatedly squeezed before the entrance to a specific area in the apartment 30, the name tags and the contents of a plurality of posts may be confirmed, and the detection unit 102 and the operation panel 43 may be used. Closing the camera with a cloth or the like, coming close to the door of any room, opening the key, and leaving without performing any operation such as pressing the doorbell, access to a specific area in the apartment 30 Operating the lock at the entrance but leaving the door unlocked, leaving the door of any room for more than a predetermined time threshold, but leaving without doing anything, entrance to a specific area in the apartment 30 It is anticipated that the operation of breaking the lock will be performed, that the resident of the condominium 30 will perform an operation different from the usual flow line, and that a specific action such as a delivery company or a cleaning company will be performed. That clothing that went away without the action despite wearing, comprising at least one such. The management apparatus 100 may recognize that a certain person is a resident of the apartment 30 by unsupervised learning from image data and the like detected by the detection unit 102 and a camera installed at an arbitrary place in the building. The recognition may be performed by performing supervised learning together with the input information of the person, or by registering a person related to the person, for example, a parent living with the person or a manager of the apartment 30. May be.

  The operation of breaking the entry lock may include, for example, using a picking tool, crowbar, drill, etc. for the entry lock. The fact that the resident of the condominium 30 operates differently from the ordinary flow line is, for example, to visit a room registered in advance in relation to the resident, for example, to visit a room other than the resident's room, or to associate with the resident. And using at least one floor other than the floor registered in advance.

  (M) One or more persons who live in the apartment 30 have a history of poor responses to persons in the area 31 outside the entrance door 41 in the apartment 30. In the present embodiment, an example of a building in which the management device 100 is provided is the condominium 30. However, if the building in which the management device 100 is provided is an office building, a school, or the like, the condition (M) is set to the management device 100. That there is a history that one or more persons whose residence, work and / or commuting place is in the building where the building is located have been poorly addressed to persons outside the entrance to a particular area of the building. Is also good.

  The estimating unit 113 determines that a certain person has a building as one of a residence, a work place, and a school place from image data and the like detected by the detection unit 102 or a camera installed at an arbitrary place in the building. It may be recognized by unsupervised learning, may be recognized by performing supervised learning together with input information by the person, and may be a person related to the person, for example, a manager of a building provided with the management device 100, It may be recognized by being registered by the boss of the company where the person works, the teacher of the school where the person goes to school, or the like.

  (N) Appearing with a specific object in front of an entrance to a specific area in the apartment 30 or a person other than a resident of the apartment 30 enclosing garbage in front of the outer door of the garbage dump of the apartment 30. Appearing with a garbage bag that you are doing. The entrance to the specific area is, for example, an entrance door 41, an outer door of a bicycle parking lot which is a common part of the apartment 30, an outer door of a parking lot, a door of each room, an outer gate of each room, a window of each room, and , A garden gate of each room, and / or the like. Specific objects include, by way of example, picking tools, burs, and / or drills.

  The estimating unit 113 in the present embodiment also learns the relationship between the person outside the entrance to a specific area in the building and the necessity of the above-described superior processing. As an example, the estimating unit 113 determines that the same visual features on the surface of the object attached to the person who has exited from the inner area 33 via the entrance door 41 have the same characteristics as those of the person attached to the person outside the entrance door 41. The case where detection is performed from the surface may be learned as a situation requiring superior processing. Objects attached to a person include, for example, at least one of clothes, bags, shoes, watches, glasses, hats, and the like.

  As an example, the estimating unit 113 sets the case where at least one of the following conditions (O) to (S) is satisfied outside the entrance to the specific area in the building, which requires the above-described superior processing. You may learn as a person. In addition, for example, the conditions shown in the following conditions (O) to (S) include the detection target range by the detection unit 102 and the area 33 inside the entrance door 41 of the apartment 30 in the same manner as described above. Image data that is detected by a camera or the like installed at the place and indicates the detected state may be transmitted to the estimation unit 113.

  (O) There is a history that a person outside the entrance to a specific area in the apartment 30 has entered the inside of the entrance for a predetermined number of thresholds or more. (P) A person outside the entrance to a specific area in the apartment 30 has a history of being in the room of the apartment 30 for a predetermined time threshold or more. (Q) A person outside the entrance to a specific area in the apartment 30 is shown together with the resident in the image published by the resident of the apartment 30 on the SNS. (R) A person who is outside the entrance to a specific area in the apartment 30 visits a resident of the apartment 30 and has a history of the above-mentioned good response by the resident. (S) A history that at least one of the belongings and clothes of a person outside the entrance to a specific area in the apartment 30 has passed through the entrance at least a predetermined number of thresholds.

  The above various learning by the estimating unit 113 may be started after the management device 100 is installed in the apartment 30, and before the management device 100 is installed in the apartment 30, for example, in a place different from the apartment 30, Some learning may be completed in advance in a factory at the manufacturing stage of the management device 100, and after the management device 100 is installed in the apartment 30, learning may be continued in the same manner as the prior learning. In the latter case, the management device 100 may reduce the amount and period of learning performed after being installed in the apartment 30 as compared to the former case.

  The storage unit 117 stores a program for operating each component of the management device 100 and the like, and is referred to by the estimation unit 113 and the processing unit 119 as an example. The storage unit 117 also enters and exits the audio data, still image data, moving image data, text data, the resident of the apartment 30, the acquaintance of the resident, and the apartment 30 as read by at least one of the estimation unit 113 and the processing unit 119, for example. Information about at least one of the trader, and the target person who needs the alert processing, and the like, the information about the previously registered notification destination, the information about conditions for performing a plurality of determinations, and information about a plurality of processes, Is stored.

  The processing unit 119 executes the specific process when the estimation unit 113 estimates that the specific process is necessary. More specifically, when the estimation result is input from the estimation unit 113, the processing unit 119 executes a specific process included in the estimation result by referring to, for example, the storage unit 117, and Then, a control signal based on a specific process is transmitted to at least one of the operation panel 43 and the entrance door 41. The processing unit 119 also receives, via the communication unit 111, a detection result such as image data indicating a person in the area 31 outside the entrance door 41 detected by the detection unit 102, and refers to the storage unit 117. Thus, when it is determined that the detection result satisfies a predetermined condition, a specific exceptional process is preferentially executed.

  FIG. 3 is a flowchart illustrating an example of learning according to the first embodiment. The learning flow of FIG. 3 is started, for example, when the management device 100 is installed in the apartment 30 and becomes operable.

  The management device 100 waits until one of the operation buttons on the operation panel 43, for example, the unlock button and the call button is pressed (step S101: NO). When the operation button of the operation panel 43 is pressed and the input information corresponding to the operation is received from the operation panel 43 via the communication network 50 (step S101: YES), the management apparatus 100 via the communication network 50. The estimating unit 113 receives the image data transmitted from the detecting unit 102 as needed, and refers to the image data together with the input information (step S103).

  The estimating unit 113 determines whether or not a plurality of persons are present in the image of the referred image data (step S105). If it is determined that a plurality of persons are present (step S105: YES), the communication network The information of the operator of the operation panel 43 and the message information requesting the input of the interpersonal relationship with a person different from the operator are transmitted to the operation panel 43 via the display panel 50 and displayed on the touch panel of the operation panel 43. (Step S107).

  The information of the operator himself / herself is, for example, that the operator is a resident of the apartment 30, a relative or friend of the resident of the apartment 30, a resident related person such as a tutor or a visiting care helper, or a resident or a management of the apartment 30. It includes information indicating that the person is one of a company expected by a person and another person. When the user is a resident of the apartment 30, the information may further include information for identifying an individual such as a room number or a name of the apartment 30.

  The information on the interpersonal relationship between the operator and the different person is, for example, whether or not the operator is conscious of entering the different person into the area 33 inside the entrance door 41 together. If the information is included and the information of the conscious relationship is input, a different person may be in the same room as the operator, such as a resident of the same room as the operator, a relative or friend of the operator, a tutor, a visiting care helper, or the like. The information includes information indicating that the operator is at least one of a person related to the operator and a person that the operator grasps as a resident of another room. For example, these pieces of information to be input may be listed in advance and displayed on the touch panel of the operation panel 43 as options.

  The estimating unit 113 waits until both pieces of information are input from the operation panel 43 via the communication network 50 (step S109: NO), and when both pieces of information are input (step S109: YES), the input information Is stored in the storage unit 117 together with the input information corresponding to the operation on the operation panel 43 and the referenced image data, and one week has passed since the learning based on the input from the operation panel 43 and the detection unit 102 was started. It is determined whether or not (step S111).

  If the estimating unit 113 determines in step S105 that a plurality of persons are not shown in the image, that is, that only the operator is present in the area 31 outside the entrance door 41 (step S105: NO), the communication network 50 The message information requesting the input of the operator's own information on the operation panel 43 is transmitted to the operation panel 43 via the control panel 43 and displayed on the touch panel of the operation panel 43 (step S108). The estimating unit 113 waits until the information is input from the operation panel 43 via the communication network 50 (step S110: NO), and when the information is input (step S110: YES), the input information Is stored in the storage unit 117 together with the input information corresponding to the operation on the operation panel 43 and the referenced image data, and one week has passed since the learning based on the input from the operation panel 43 and the detection unit 102 was started. It is determined whether or not (step S111).

  If the estimating unit 113 determines in step S111 that one week has not elapsed (step S111: NO), the process returns to step S101, and if it determines that one week has elapsed (step S111: YES), the flow is determined. finish. In addition, in the repetition of step S107 and step S109: NO and the repetition of step S108 and step S110: NO, the repetition may be performed more than a predetermined time threshold or a predetermined number of times or more. If there is no information input from the operation panel 43, the repetition may be ended, and the flow may be ended.

  The estimating unit 113 determines whether the person in the area 31 outside the entrance door 41 of the condominium 30 during a period from the start of the learning based on the input from the operation panel 43 and the detecting unit 102 until one week has elapsed. , The input data corresponding to each operation of the unlock button and the call button on the operation panel 43, the information of the operator, and the interpersonal relationship between a different person from the operator. Using at least one of the information, that is, using the labeled training data, the interpersonal relationship between the operator of the operation panel 43 and a different person, the relationship between the interpersonal relationship and the necessity of the request processing, and the entrance Supervised learning is performed on at least one of the relationship between the person in the area 31 outside the door 41 and the necessity of superior processing. For learning, for example, techniques such as deep learning, machine learning, and statistical processing are used.

  Examples of the learning method include a support vector machine (SVM), a recurrent neural network (RNN), and a Bayesian network (BN). The SVM can discriminate an unknown sample with a small error by learning a relatively small number of samples. However, although the learning result can be understood to some extent, it is difficult for humans to understand, and it is difficult to understand the causal relationship of discrimination. The RNN requires many learning samples and takes a lot of time for learning. It is effective for objects that are influenced by the context (context), such as time series, but it is difficult to understand the learning results. The BN requires many learning samples and takes a long time to learn. Since the learning result is expressed in the form of a network connecting the conditional probability models, the causal relationship is easy to understand. In the learned network, known nodes and unknown nodes can be used in any combination by belief propagation.

  In the learning, the estimating unit 113 extracts a feature amount of the image using a convolution neural network (CNN). CNN is a kind of deep learning neural network (DLNN). DLNN is a three-layer neural network (NN) expanded to four or more layers, and a large amount of recent data can be stored. It is known that the performance is higher than that of a new calculation method that has appeared after NN due to the fact that it has been improved and the computer has become more sophisticated. Among them, the CNN uses the brain visual cortex (V1) as a model, and if it is learned in advance so as to increase the accuracy of image recognition, an image processing result similar to the brain visual cortex can be obtained. Therefore, this method is suitable for extracting the feature amount of an image. The NN itself has been actively researched since the 1980s. By combining a plurality of nodes and performing non-linear processing at each node, an apparently meaningless data array (pattern) is obtained. This is a calculation method (and a data structure therefor) in which meaningful symbols can be assigned.

  In the present embodiment, the training data is converted into image data detected by the detection unit 102, input information corresponding to each operation of the unlock button and the call button on the operation panel 43, information of the operator, and information of the operator. The training data is described, for example, with the voice data exchanged between the room intercom in the apartment room 30 and the operation panel 43 and the reader of the operation panel 43. It may include ID information of an electronic key to be read. The feature amount shown in the voice may include, for example, a voiceprint, an utterance content, and the like, and the utterance content may include, for example, “now,” “for the first time in a long time,” “this is OO transportation,” “ Would you let me do that? " When such other training data is included, a method other than CNN, such as deep learning, machine learning, or statistical processing, may be used as a conversion method close to brain information processing for each type of training data. For example, a self-organizing map (SOM) suitable for extracting features shown in speech, a recurrent neural network (RNN) suitable for extracting features of time-series data, and a deep neural network that can be used in the same manner as RNN A technique such as (DNN) may be used. However, when dealing with speech using SOM, it is difficult to handle time series with SOM alone, so it is necessary to combine it with another method. In the case where speech is handled using the RNN, it is possible to extract a feature amount indicated in the speech in combination with preprocessing selected separately. Unlike the RNN, the DNN can learn the preprocessing itself.

  After performing the supervised learning on the feature amounts of the persons shown in the various labeled images acquired in the learning flow, the estimating unit 113 outputs various images of the person in the area 31 outside the entrance door 41. Without the above input information, operator information and interpersonal relationship information, that is, continue to acquire unlabeled training data, automatically acquire the features of the person shown in the image, repeatedly, The interpersonal relationship between the operator of the operation panel 43 and a different person, the relationship between the interpersonal relationship and the necessity of the request processing, and the relation between the person in the area 31 outside the entrance door 41 and the necessity of the superior processing. Unsupervised learning is performed for at least one of the relationships. The estimating unit 113 also performs unsupervised learning on the relationship between the situation of the person in the outer area 31 and the necessity of the above-described alert processing, in addition to the preliminary learning before the management device 100 is installed in the apartment 30. Do. As an example of the unsupervised learning related to the alert processing, the estimating unit 113 performs the alert processing for the operator when the flow ends due to the absence of information input from the operation panel 43 by the operator in the learning flow. May be needed. The estimating unit 113 also executes the above-described request processing, and, based on the result of the confirmation of the above-mentioned different person by the above-mentioned operator, the relationship between the interpersonal relationship between the operator and the different person and the necessity of the specific processing. , Supervised learning may be performed. The feature quantities of the person shown in the image include, for example, feature quantities such as face, facial expression, body type, movement, way of walking, gesture, clothes, ornaments, glasses, belongings, and eyes.

  In the unsupervised learning, it is necessary to provide feedback on the suitability of the estimation result from a resident or a manager of the apartment 30 at an arbitrary timing. For example, every time the estimation unit 113 estimates the necessity of a specific process from a person in the outer region 31 detected by the detection unit 102, the estimation unit 113 sends the estimation result to a notification destination registered in advance in relation to the person. The feedback from the person may be obtained by transmitting the notification, the person confirming the result confirming the estimation result, and returning the information indicating the estimation failure when the estimation result is incorrect. In addition, in order to further reduce the time and effort of the inhabitants, for example, the management apparatus 100 actually executes the alert process based on the estimation result, and erroneously executes the alert process even though there is no need to execute the alert process, Feedback may be obtained by receiving an input for canceling the alert processing from the operation panel 43, an intercom in the living room, a specific notification destination, or the like.

  The estimating unit 113 estimates, based on these learning results, whether a specific process is necessary or not from the person in the outer region 31 detected by the detecting unit 102. The estimating unit 113 also uses the same method as the above-described learning method when estimating the necessity of a specific process. The same applies to the subsequent learning and estimation.

  Note that the above “relation” learned by the estimating unit 113 is also referred to as “learning model” in the art, and the estimating unit 113 sets input information corresponding to an operation such as unlocking on the operation panel 43, It includes the regularity, pattern, and the like between these data extracted from the operator information and interpersonal relationship information, and information indicating whether a specific process is required. In addition, it can be said that the “relation” is a correspondence between input information as input data, operator information and interpersonal relation information, and information indicating whether or not a specific process is required as output data.

  FIGS. 4 and 5 are flowcharts as an example until a specific process is executed based on a learning result according to the first embodiment. A and B shown in FIG. 4 respectively follow A and B shown in FIG. The description of the flow following FIG. 4 to FIG. 5 starts, for example, when the period of the supervised learning described with reference to FIG. 3 ends.

  The estimation unit 113 waits until the detection unit 102 detects a person in the area 31 outside the entrance door 41, that is, until image data indicating a person in the outside area 31 is received from the detection unit 102 (step If the image data is received (step S201: YES), based on the learning result, the situation of the person detected by the detection unit 102 shown in the image data is an example of a specific process. It is estimated whether or not a certain alert process is necessary (step S203).

  When the estimation unit 113 estimates that the situation of the person detected by the detection unit 102 does not require the alerting process (step S203: NO), the estimation unit 113 detects the person by the detection unit 102 within a predetermined time period. It is determined whether any one of the operation buttons of the operation panel 43, for example, the unlock button and the call button has been pressed, that is, the input information corresponding to the operation has been received from the operation panel 43 via the communication network 50. It is determined whether or not (Step S205).

  When the estimating unit 113 determines that the input information has not been received within the time period (step S205: NO), the process returns to step S201 and determines that the input information has been received (step S205: YES). The estimating unit 113 receives the image data transmitted from the detecting unit 102 as needed via the communication network 50, and refers to the image data together with the input information (step S207).

  The estimating unit 113 estimates whether or not the operator of the operation panel 43 indicated in the referred image data needs the alert processing, which is an example of the specific processing, based on the learning result (step S209). ), When it is estimated that the alert processing is not required (step S209: NO), it is determined whether or not a plurality of persons appear in the image of the referred image data (step S211). When the estimating unit 113 determines that a plurality of persons are present in the image (step S211: YES), subsequently, by referring to the storage unit 117, for example, a person different from the operator of the operation panel 43 is determined. It is determined whether or not a person who has been allowed to enter the area 33 inside the entrance door 41 is registered in advance (step S213).

  When the estimating unit 113 determines that a different person is not registered for permission (step S213: NO), the estimating unit 113 estimates an interpersonal relationship between the operator and the different person based on the learning result. Here, as an example, a description will be given below based on the situation of the area 31 outside the entrance door 41 shown in FIG.

  The estimating unit 113 determines the interpersonal relationship between the first person 61, which is the operator, and the second person 63, which is one of the different persons, such that the first person 61 moves to the area 33 inside the entrance door 41 together with the second person 63. It is presumed that the relationship is conscious of entry, that is, the second person 63 is a companion of the first person 61. The estimating unit 113 also determines that the first person 61 and the third person 65 are inside the entrance door 41 together with the third person 65 as the interpersonal relationship between the first person 61 as the operator and the third person 65 as another one of the different persons. That the third person 65 is a tailgear who tries to enter the area 33 inside the entrance door 41 in connection with the unlocking operation by the first person 61. presume. As an example, the companion enters the condominium 30 with a resident or an acquaintance of the condominium 30 previously permitted to enter the area 33 inside the entrance door 41, a resident of the condominium 30 not yet permitted to enter, or the condominium 30. This includes at least one of a visitor having a valid reason and an unauthorized intruder having no valid reason to enter the apartment 30.

  When estimating the interpersonal relationship between the operator and a different person, the estimating unit 113 estimates the relationship between the estimated interpersonal relationship and the necessity of the request process, which is an example of the specific process, based on the learning result. (Step S215). More specifically, the estimating unit 113 estimates that the request processing is unnecessary for the relationship that the second person 63 is a companion of the first person 61, while the third person 65 determines that the third person 65 is the first person. When it is estimated that the request process is necessary for the relationship of 61 tailgears (step S215: YES), a control signal for executing the request process is output to the processing unit 119.

  The processing unit 119 causes the touch panel of the operation panel 43 to display an image of the area 31 outside the entrance door 41 on the touch panel of the operation panel 43 based on the control signal input from the estimation unit 113 as an example of request processing. An operation is performed from the communication unit 111 via the communication network 50 to execute a process of requesting the first person 61 as an operator to confirm a third person 65 as another person different from the operator in real time. A control signal corresponding to the process is transmitted to the board 43 (step S217).

  The operation panel 43 enters the image of the area 31 outside the entrance door 41 and the third person 65 into the area 33 inside the entrance door 41 together on the touch panel based on the control signal received from the processing unit 119. And a message requesting a determination as to whether or not to permit the operation, and when an input from the first person 61 as the operator is received, the input information is transmitted to the processing unit 119 via the communication network 50. Send.

  When receiving the input information from the operation panel 43, the processing unit 119 determines whether or not a permission input for entering the input information is indicated (Step S219). When determining that the permission input is indicated (step S219: YES), the estimation unit 113 responds to the operation button, for example, the unlock button or the call button indicated by the input information received from the operation panel 43 in step S205. In order to execute the process, a control signal corresponding to the process is transmitted from the communication unit 111 to the entrance door 41 or the indoor intercom of the specific living room via the communication network 50 (step S221), and the flow ends.

  In step S203, when the estimation unit 113 estimates that the situation of the person detected by the detection unit 102 needs the alert processing based on the learning result (step S203: YES), the estimation unit 113 executes the alert processing. Is output to the processing unit 119, and the processing unit 119 executes a warning process based on the control signal (step S223), and the flow ends. As an example, the situation of the person in the area 31 outside the entrance door 41 where it is presumed that the alert processing is necessary is, for example, that the person possesses a weapon or picking tool in the outside area 31, There is a history of frequently visiting the apartment 30 and forcing the resident to perform malicious sales, that the person kyorokyoro many times in front of the entrance door 41, and that the person in the outer area 31 This includes at least one of checking the name tag and the contents of the post, and closing the camera of the detection unit 102 and the operation panel 43 in the outer region 31 with a cloth or the like. In addition, an example of the alert processing here may be to output a voice “What is your business?” From the operation panel 43. In this case, the management device 100 can indicate to the person that the outside area 31 is constantly monitored, and if the estimation by the artificial intelligence is incorrect, the person Even if the visitor has a reason, the warning message is not uttered, so that it is possible to avoid making the visitor uncomfortable. In addition, an example of the alert process here may be to output a voice from the operation panel 43 saying “You have been judged to be a malicious visiting business operator. Please pick up immediately.” In this case, the management apparatus 100 can avoid in advance a situation that is disadvantageous to the resident, such as that the person randomly calls the resident of the apartment 30 and performs a forcible and forcible sale.

  In step S209, if the operator of the operation panel 43 indicated in the referenced image data estimates that the alert processing is necessary (step S209: YES), the estimating unit 113 alerts the user based on the learning result. A control signal for executing the process is output to the processing unit 119, and the processing unit 119 executes a warning process based on the control signal (step S223), and the flow ends. As an example, the operator presumed that the alert process is required, for example, a person whose resident in the living room to be called from the operation panel 43 is alerting as a stalker, and has performed a calling operation on the operation panel 43. Closing the camera of the operation panel 43 with a cloth, holding a photograph over the camera of the operation panel 43, intentionally shifting the standing position so as not to be reflected on the camera of the operation panel 43, This includes at least one of a person wearing a hat deeply so that the face is not reflected. In addition, an example of the alert processing here may be to output a voice from the operation panel 43 saying, "You are not permitted to visit from the visitor. Please pick it up." . In this case, the management device 100 can completely prevent the person from contacting the resident at the call destination. In addition, an example of the alert processing here may be to output a voice from the operation panel 43 saying, "Your face cannot be recognized, so you cannot connect to the resident of the call destination." In this case, the management device 100 can urge the person who has unwillingly hidden the face to perform the operation again.

  In step S219, when the processing unit 119 determines that the permission input to enter the input information received from the operation panel 43 is not indicated (step S219: NO), the processing unit 119 executes the alert processing (step S223). The flow ends. An example of the alert process here is a process of inquiring the manager of the apartment 30 to call the manager in order to request the third person 65 to confirm his / her identity, and to have a security company or a policeman rush to the person immediately. And at least one of the following processes. Further, the processing unit 119 outputs the input information to the estimation unit 113, and the estimation unit 113 may perform supervised learning using the image data from the detection unit 102 and the input information as learning materials. Note that, after performing the input on the operation panel 43, the first person 61 may take a countermeasure to enter the inside of the apartment 30 by, for example, turning to an entrance other than the entrance door 41.

  In step S219, it is not possible to determine whether the first person 61 is a person who should not allow the third person 65 to enter the area 33 inside the entrance door 41, and the third person 65 is not allowed to enter the inside area 33. It is assumed that the priority is given to entering the inside area 33 rather than to preventing entry into the area 33. Therefore, the processing unit 119 opens the control panel 43 because it cannot determine whether to permit the third person 65 to enter the area 33 inside the entrance door 41 together with the operation panel 43. A control signal may be transmitted such that an option for reducing the door time is displayed on the touch panel.

  In step S211, the estimating unit 113 determines that a plurality of persons are not shown in the image of the referred image data, and that only the first person 61 who is the operator is in the outer region 31 (step S211: NO). ), Since the first person 61 has already been estimated based on the learning result in the step before step S211 as a person who does not need the alerting process, the process proceeds to step S221. Also, in step S213, when the estimating unit 113 determines that a different person is registered for permission (step S213: YES), the process similarly proceeds to step S221. Also, in step S215, the estimation unit 113 estimates that the interpersonal relationship between the operator and the different person in the area 31 outside the entrance door 41 does not require the request processing based on the learning result (step S215). (S215: NO), and similarly proceeds to step S221. As described above, the flow following FIG. 4 to FIG. 5 is repeatedly executed while the management device 100 is operating.

  In step S217, as an example of the request process, the processing unit 119 has been described as executing the process of requesting the first person 61 who is the operator of the operation panel 43 to confirm the third person 65 in real time. Alternatively, the processing unit 119 may execute, as an example of the request process, a process of requesting the first person 61 who is the operator of the operation panel 43 to confirm the third person 65 afterwards. More specifically, as an example, after step S221, the processing unit 119 communicates with the communication destination registered in advance by the first person 61 who is the operator of the operation panel 43, for example, the smartphone or the second person owned by the first person 61. A process of requesting the first person 61 to confirm the third person 65 may be performed by displaying an image of the area 31 outside the entrance door 41 on a display such as an indoor intercom of the room of the one person 61. . In this case, step S219 is omitted.

  Regardless of whether the content of the request processing by the processing unit 119 is to request the first person 61 to confirm the third person 65 in real time or afterward, the estimation unit 113 Is an interpersonal relationship between the first person 61 who is the operator and a third person 65 who is different from the operator, based on the confirmation result of the third person 65 that is different from the operator, and the necessity of the request processing as a specific processing. You may learn the relationship with no. In this case, the processing unit 119 determines whether to permit the operation panel 43 or the registered notification destination to allow the third person 65 to enter the area 33 inside the entrance door 41 together with the first person 61. In addition to presenting options, detailed interpersonal relationships between the first person 61 and the third person 65 may be, for example, whether or not they know each other. The user may be required to input whether the person is a person related to another resident of 30 or a trader. In the case where the processing unit 119 performs a request process to subsequently request confirmation of a third person 65 different from the first person 61 who is the operator of the operation panel 43, the estimation unit 113 A request process for requesting the resident of the room to which the third person 65 enters the area 33 inside the entrance door 41 to confirm the third person 65, instead of the first person 61, to the processing unit 119. It may be executed.

  The estimating unit 113 may receive the input information from the operation panel 43 or the registered notification destination, and may perform more detailed supervised learning using such input information as learning material. For example, when the input information acquired as feedback of the request process indicates that the first person 61 and the third person 65 are acquaintances, the estimating unit 113 determines whether the first person 61 and the third person 65 are acquainted in the area 31 outside the entrance door 41. Even if the first person 61 and the third person 65 stand apart from each other, it may be learned that the request processing is not necessary. As an example, the estimating unit 113 stores, in the storage unit 117, ranking information that ranks the reliability of the third person 65 together with the image data of the third person 65 based on the input information obtained as feedback of the request processing. After that, similarly, every time the third person 65 is detected by the detection unit 102, the ranking information is updated, and the identification required for the third person 65 according to the rank of the reliability indicated in the ranking information is performed. May be changed. As an example, when the third person 65 is a relative or friend of the first person 61, the third person 65 may be ranked in another rank of the condominium 30 where the third person 65 is recognized by the first person 61. In the case where the third person 65 is a related person of a resident or another resident, in the case where the third person 65 is a trader recognized by the first person 61, the number may be lowered in this order.

  In step S219, the estimation unit 113 accepts the input on the operation panel 43 on condition that no input is made from the first person 61 who is the operator of the operation panel 43 within a predetermined time. May be terminated, and the process may return to step S201. In this case, before the time has elapsed, the estimation unit 113 determines that the first person 61 has left the area 31 outside the entrance door 41 by referring to the image data transmitted from the detection unit 102 as needed. On the condition that the input has been performed, the reception of the input on the operation panel 43 may be immediately terminated.

  As described above, according to the management device 100 of the first embodiment, it is estimated whether or not a specific process is necessary for not only a person who has entered and exited the apartment 30 but also a person who has visited the apartment 30 for the first time. And automatically execute, so that it is possible to reduce the trouble of human operation and judgment. According to the management device 100 of the first embodiment, for example, when a resident of the apartment 30 or a visitor having a valid reason to enter the apartment 30 unlocks and opens the entrance door 41 of the apartment 30, When a person who does not have a valid reason to enter is trying to enter the condominium 30 together, the intrusion can be prevented beforehand by automatically executing the above-described request processing. Further, according to the management device 100 of the first embodiment, for example, a company that frequently visits the apartment 30 and compels the residents to perform vicious sales, a person who repeatedly stalks the residents of the apartment 30, or an entrance of the apartment 30 The above-mentioned alert processing is automatically executed for a person who is taking a suspicious action in the area 31 outside the door 41 or a person who needs to be alert such as possessing a weapon or picking tool. By doing so, the security of the condominium 30 can be enhanced, and it is possible to contribute to prevention of crime and arrest of criminals.

  In the first embodiment, the entrance door 41 that separates the outer area 31 and the inner area 33 in the entrance of the apartment 30 has been mainly described as an example of an entrance to a specific area in a building. In the first embodiment, the operation on the operation panel 43 installed in the area 31 outside the entrance door 41 is mainly described as a trigger for learning and estimation in the estimation unit 113 of the management device 100. The management device 100 according to the first embodiment is provided on the premise that a device having the same function as the operation panel 43 is provided, in addition to the entrance door 41, an outer door of a garbage dump that is a common part of the apartment 30. The present invention may be applied to at least one of an outer door of a bicycle parking lot, an outer door of a parking lot, a door of each room, an outer gate of each room, a window of each room, and a gate of a garden of each room. In addition, the management device 100 according to the first embodiment assumes that equipment having the same function as the operation panel 43 is provided, and other buildings other than the condominium 30, for example, detached houses, apartments, commercial facilities, Further, the present invention may be applied to an entrance to a specific area in a public facility or the like. When the target building is a detached house, the management device 100 according to the first embodiment includes at least one of an outer gate, a front door, a back door, a window, a garden door, and a parking door of the detached house. May be applied.

  When the target building is an office building which is a commercial facility, the management device 100 according to the first embodiment may be applied to an elevator of the office building. For example, assuming that a visitor who is going to visit a company located on a specific floor of an office building gets into an elevator of the office building and presses a button of the floor, the detection unit 102 detects that the visitor is in the elevator. The estimating unit 113 detects the visitor and notifies the visitor and the company as an example of a specific process, a guide display from the front of the elevator to the company on the floor, and refusal to enter the floor. Based on the learning result of at least one of the necessity and the necessity, it may be estimated that a specific process is necessary from the detected visitor, and the processing unit 119 may execute the specific process. The refusal to enter the floor includes, for example, at least one of disabling a button operation on the floor and uttering a warning message in the elevator.

  FIG. 6 is a flow chart as an example until a specific process is executed based on a learning result according to the second embodiment. The second embodiment is different from the first embodiment in that the management device 100 is applied to an entrance door 41 that partitions an outer area 31 and an inner area 33 in an entrance of an apartment 30 as an example of an entrance to a specific area in a building. Same as the form. However, the second embodiment differs from the first embodiment in that the detection of a person in the area 31 outside the entrance door 41 by the detection unit 102 is used as a trigger for learning and estimation in the estimation unit 113 of the management device 100. . Since the management device 100 according to the second embodiment has the same configuration as the management device 100 according to the first embodiment, the same components are denoted by the same reference numerals, and redundant description will be omitted. The description of the flow of FIG. 6 starts as an example when the period of the supervised learning described with reference to FIG. 3 ends.

  The estimation unit 113 waits until the detection unit 102 detects a person in the area 31 outside the entrance door 41, that is, until image data indicating a person in the outside area 31 is received from the detection unit 102 (step If the image data is received (step S301: YES), based on the learning result, the situation of the person detected by the detection unit 102 indicated in the image data is an example of a specific process (S301: NO). It is estimated whether or not a certain alert process is necessary (step S303).

  When the estimation unit 113 estimates that the situation of the person detected by the detection unit 102 does not require the alert processing (step S303: NO), the estimation unit 113 subsequently detects the person detected by the detection unit 102 based on the learning result described above. However, it is estimated whether or not a superior process, which is an example of a specific process, is required (step S305). Note that, similarly to step S209 in the flowchart of the first embodiment, the estimation unit 113 determines whether the person detected by the detection unit 102 needs the alert processing between step S303 and step S305. It may be estimated.

  When the estimation unit 113 estimates that the person detected by the detection unit 102 does not require superior processing (step S305: NO), the process returns to step S301, and estimates that the superior processing is required ( Step S305: YES), and outputs a control signal for executing superior processing to the processing unit 119.

  Based on the control signal input from the estimating unit 113, the processing unit 119 includes (A) unlocking the entrance door 41, (B) opening the entrance door 41, and (C) Remote control of the entrance door 41 and / or (D) remote control of at least one of the above (A) unlocking, the above (B) opening and the above (C) warning release for a pre-registered notification destination Transmitting a control signal corresponding to the processing to the entrance door 41 or the notification destination from the communication unit 111 via the communication network 50, in order to execute at least one of the processing for requesting Then, the above communication is made (step S307), and the flow ends.

  In step S303, when the estimation unit 113 estimates that the situation of the person detected by the detection unit 102 requires the alerting process based on the learning result (step S303: YES), the estimating unit 113 executes the alerting process. Is output to the processing unit 119, and the processing unit 119 executes a warning process based on the control signal (step S309), and the flow ends. As described above, the flow of FIG. 6 is repeatedly executed while the management device 100 is operating.

  In this flow, the management device 100 performs the alert processing when the person in the area 31 outside the entrance door 41 estimates that neither the alert processing nor the superior processing is necessary based on the learning result. It is not necessary to execute the superior processing. In this case, the person may operate the operation panel 43 to execute a process corresponding to the operation by the management device 100 as in the first embodiment. The authentication may be unlocked and opened, or a call operation may be made to communicate with the indoor intercom of a specific room without going through the management device 100.

  As described above, according to the management device 100 of the second embodiment, the same effects as those of the management device 100 of the first embodiment can be obtained. Further, according to the management device 100 of the second embodiment, for example, the above-described superior processing is automatically executed for a resident of the apartment 30 or a visitor having a valid reason to enter the apartment 30. This can increase convenience.

  The management device 100 according to the second embodiment is applied to a case where there are a plurality of persons and a case where there is a single person in the area 31 outside the entrance door 41. That is, when there are a plurality of persons in the area 31 outside the entrance door 41, the management apparatus 100 of the second embodiment targets all persons in the outside area 31 in steps S303 and S303 in the flow of FIG. The necessity of a specific process in each of the steps S305 is estimated, and when it is estimated that at least one person in the outer region 31 needs the specific process, a specific process for another person is performed. The specific processing may be executed regardless of whether or not is necessary.

  More specifically, when the management device 100 of the second embodiment estimates in step S303 that at least one person in the outer area 31 needs the alert processing based on the learning result described above. In step S305, when it is estimated that the situation of all the persons in the outer area 31 does not require the alert processing, the process proceeds to step S305. In step S303, the management device 100 according to the second embodiment determines that at least one person in the outer area 31 needs superior processing based on the learning result, and performs superior processing. Is performed, and if it is estimated that all the persons in the outer region 31 do not need the superior processing, the process returns to step S301.

  The management apparatus 100 according to the second embodiment includes an exterior door of a garbage dump, an exterior door of a bicycle parking lot, which is a common part of the apartment 30, irrespective of whether or not the operation panel 43 is provided. It may be applied to at least one of an outer door of a parking lot, a door of each room, an outer gate of each room, a window of each room, and a gate of a garden of each room. For example, it may be applied to an entrance to a specific area in a detached house, an apartment, a commercial facility, and a public facility. When the target building is a detached house, the present invention may be applied to at least one of an outer gate, an entrance door, a back door, a window, a garden door, and a parking lot door of the detached house. For example, assuming a situation in which a pet kept in a detached house is lost, the detecting unit 102 detects a pet returning to the front door of the house, and the estimating unit 113 specifies the pet and identifies the pet. Based on the learning result of the relationship with at least one of the necessity of notification to a resident or the like, which is an example of the process of opening the door, opening of the entrance and feeding out, it is estimated that a specific process is required from the detected pet. Then, the processing unit 119 may execute a specific process.

  The management system according to the third embodiment includes a plurality of management devices 100 of at least one of the first embodiment and the second embodiment. The management system is configured such that a person who sets a building, in which one of the plurality of management apparatuses 100 is provided, as a residence, a work place, or a place of commuting, has another management apparatus 100 among the plurality of management apparatuses 100. When the building provided with is newly used as one of a residence, a work place, and a school attendance place, the learning result of the one management apparatus 100 is shared with the other management apparatus 100. According to the management system according to the third embodiment, for example, when a specific person moves from a building provided with one management device 100 to a building provided with another management device 100, one management device 100 is provided. The learning result can be passed from one management device 100 to another management device 100. In addition, according to the management system according to the third embodiment, as an example, a person who lives in a residential building provided with one management device 100 changes a commercial building provided with another management device 100 to a new one. When the work location is set, the learning result can be passed from one management device 100 to another management device 100.

  In the management system according to the third embodiment, the operation information learned by the specific management apparatus 100 is uploaded to, for example, a cloud that can communicate with the plurality of management apparatuses 100, and the management information is exchanged with the other management apparatuses 100. They may be shared. The motion information, as an example, requires information on motions included in a plurality of conditions learned by the person detected by the detection unit 102 to estimate that superior processing is required, and alert processing is required. And information on the operations included in the plurality of conditions learned for estimating that the request processing is required, and the like. On the other hand, the personal information on the specific person learned by the specific management device 100 is not shared with the other management devices 100, and is passed to the management device 100 of the building to which the person has moved. Is also good.

  In any of the above-described first to third embodiments, the estimating unit 113 performs the alert processing on the person when a certain person first takes an action that is difficult to estimate that the alert processing is necessary. May need to be alerted, i.e., may temporarily learn that the person is gray. For example, an action that is difficult to estimate that the alert processing is necessary enters the inside area 33 together with the operator of the operation panel 43 without operating the operation panel 43 by himself / herself in the area 31 outside the entrance door 41 of the apartment 30. That the resident of the condominium 30 visits a room other than the resident's room or walks on a floor different from the floor where the resident's room is located; This is to leave the apartment 30 without carrying the furniture home appliance within a predetermined time although it is brought in, or a person other than the resident of the apartment 30 goes to the garbage dump of the apartment 30 to throw garbage.

  In this case, the estimating unit 113 determines whether the person who has learned that the gray has performed the same action or another similar action as described above or more than a predetermined number of thresholds, or for example, If the inquiry to the resident or the manager cannot be confirmed as a person who can be permitted to enter the area 33 inside the entrance door 41, it may be learned that the person needs to be alerted. Good. The estimating unit 113 further causes the processing unit 119 to execute an alert process when, for example, the detecting unit 102 detects that the person is going to take the same action again in the area 31 outside the entrance door 41. Is also good.

  On the other hand, the estimating unit 113 determines that the person who has learned that the region is gray is capable of clearly determining that superior processing is necessary, for example, by holding hands together with the resident of the apartment 30 and the area 33 inside the entrance door 41. The first time that the person enters the building, or when, for example, inquiries are made to a plurality of residents and managers of the condominium 30, it has been confirmed that the person can be permitted to enter the area 33 inside the entrance door 41. In this case, or when an action that may require a superior process is performed more than a predetermined number of times, it may be learned that the alert process is unnecessary for the person. The estimating unit 113 may further include, for example, a case where the detecting unit 102 detects that the person is trying to take an action that is difficult to estimate that the alert processing is necessary in the area 31 outside the entrance door 41. It is not necessary to cause the processing unit 119 to execute the alert processing.

  In any of the above-described first to third embodiments, the estimating unit 113 of the management device 100 determines that the person detected by the detecting unit 102 needs the alert processing, and then, It is determined whether or not the person has been registered in advance as a person who is allowed to enter the inside of the entrance to a specific area in the building. If the person is registered, the processing unit 119 is not executed to perform the alert processing. May be executed, and if not registered, the processing unit 119 may be caused to execute a warning process. Alternatively, the estimation unit 113 may first determine whether or not the person detected by the detection unit 102 is registered in advance as a person who is allowed to enter the entrance to a specific area in the building. If it is registered, the processing unit 119 may be allowed to execute superior processing without estimating whether or not the alert processing is necessary. If not, it may be continuously estimated whether or not the alert processing is necessary.

  In any of the above-described first to third embodiments, a person registered in advance in the management device 100 as a target person requiring alert processing is required to present, for example, an identification card to the manager of the apartment 30. As a condition, entry into the area 33 inside the entrance door 41 of the apartment 30 may be permitted. In addition, the management device 100 may exclude wandering elderly people and children from those who need to be alerted. The management device 100 excludes the wandering elderly from the subjects requiring the alert processing, for example, when the wandering elderly is a resident of the apartment 30 and registered with dementia or the like.

  In any of the above-described first to third embodiments, the detection unit 102 includes a camera that captures an image, and the captured image data shows a person in the area 31 outside the entrance door 41 as a subject. Regardless of whether or not the image data is captured, the image data is transmitted to the apparatus main body 101 as needed. Instead, the detection unit 102 determines whether or not a person in the area 31 outside the entrance door 41 is included in the captured image data as a subject, and detects the image data in which the person is included. Only the captured image data may be transmitted to the apparatus main body 101. In this case, the detection unit 102 may further determine whether or not there are a plurality of persons in the area 31 outside the entrance door 41, and may transmit the determination result to the apparatus main body 101 together with the image data. In this case, in step S211 of the flowchart of FIG. 5, the estimation unit 113 obtains, from the detection unit 102, a determination result as to whether or not there are a plurality of people in the area 31 outside the entrance door 41, and thereby obtains a plurality of It may be determined whether or not a person is reflected.

  In any of the first to third embodiments described above, the estimation unit 113 has been described as continuing unsupervised learning after supervised learning for a certain period. In the unsupervised learning, it is preferable to update the image of the resident of the apartment 30 as an example of the labeled training data acquired during the supervised learning period as needed. Thereby, the estimation unit 113 can identify the same person even if the appearance of the resident of the apartment 30 changes as he gets older.

  Various embodiments of the present invention may be described with reference to flowcharts and block diagrams, wherein blocks represent (1) steps in a process in which an operation is performed or (2) devices responsible for performing an operation. Section. Certain stages and sections are implemented by dedicated circuitry, programmable circuitry provided with computer readable instructions stored on computer readable media, and / or processors provided with computer readable instructions stored on computer readable media. May be. Dedicated circuits may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. Programmable circuits include logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logical operations, memory elements such as flip-flops, registers, field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), etc. And the like, and may include reconfigurable hardware circuits.

  Computer readable media may include any tangible device capable of storing instructions for execution by a suitable device, such that computer readable media having instructions stored thereon is specified in a flowchart or block diagram. Product comprising instructions that can be executed to create a means for performing the specified operation. Examples of the computer readable medium may include an electronic storage medium, a magnetic storage medium, an optical storage medium, an electromagnetic storage medium, a semiconductor storage medium, and the like. More specific examples of computer readable media include floppy disks, diskettes, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), Electrically erasable programmable read only memory (EEPROM), static random access memory (SRAM), compact disk read only memory (CD-ROM), digital versatile disk (DVD), Blu-ray (RTM) disk, memory stick, integrated A circuit card or the like may be included.

  The computer readable instructions may be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state setting data, or object oriented programming such as Smalltalk, JAVA, C ++, etc. Language, and any source or object code written in any combination of one or more programming languages, including conventional procedural programming languages, such as the "C" programming language or similar programming languages. Good.

  The computer readable instructions may be directed to a general purpose computer, special purpose computer, or other programmable data processing device processor or programmable circuit, either locally or over a wide area network (WAN) such as a local area network (LAN), the Internet, or the like. ) May be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, and the like.

  FIG. 7 illustrates an example of a computer 1200 in which aspects of the present invention may be wholly or partially embodied. The program installed in the computer 1200 causes the computer 1200 to function as one or more “units” of an operation associated with the device according to the embodiment of the present invention or the device, or the operation or the one or more “parts” of the device. Unit "and / or cause the computer 1200 to execute a process or steps of the process according to an embodiment of the present invention. Such programs may be executed by CPU 1212 to cause computer 1200 to perform certain operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

  The computer 1200 according to the present embodiment includes a CPU 1212, a RAM 1214, a graphic controller 1216, and a display device 1218, which are interconnected by a host controller 1210. The computer 1200 also includes an input / output unit such as a communication interface 1222, a hard disk drive 1224, a DVD-ROM drive 1226, and an IC card drive, which are connected to the host controller 1210 via the input / output controller 1220. The computer also includes legacy input / output units, such as a ROM 1230 and a keyboard 1242, which are connected to an input / output controller 1220 via an input / output chip 1240.

  The CPU 1212 operates according to the programs stored in the ROM 1230 and the RAM 1214, and controls each unit. The graphic controller 1216 acquires the image data generated by the CPU 1212 in a frame buffer or the like provided in the RAM 1214 or in the graphic controller 1216 itself, and causes the image data to be displayed on the display device 1218.

  The communication interface 1222 communicates with another electronic device via a network. The hard disk drive 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD-ROM drive 1226 reads a program or data from the DVD-ROM 1201 and provides the hard disk drive 1224 with the program or data via the RAM 1214. The IC card drive reads programs and data from the IC card and / or writes programs and data to the IC card.

  The ROM 1230 stores therein a boot program executed by the computer 1200 at the time of activation and / or a program depending on hardware of the computer 1200. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via a parallel port, a serial port, a keyboard port, a mouse port, and the like.

  The program is provided by a computer-readable storage medium such as a DVD-ROM 1201 or an IC card. The program is read from a computer-readable storage medium, installed in a hard disk drive 1224, a RAM 1214, or a ROM 1230, which is an example of the computer-readable storage medium, and executed by the CPU 1212. The information processing described in these programs is read by the computer 1200 and provides a link between the programs and the various types of hardware resources described above. An apparatus or method may be configured by implementing operations or processing of information according to the use of computer 1200.

  For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 executes the communication program loaded in the RAM 1214, and performs communication processing with the communication interface 1222 based on the processing described in the communication program. You may order. The communication interface 1222 reads transmission data stored in a transmission buffer area provided in a recording medium such as a RAM 1214, a hard disk drive 1224, a DVD-ROM 1201, or an IC card under the control of the CPU 1212, and reads the read transmission. The data is transmitted to the network, or the received data received from the network is written in a reception buffer area provided on a recording medium.

  In addition, the CPU 1212 causes the RAM 1214 to read all or a necessary part of a file or database stored in an external recording medium such as a hard disk drive 1224, a DVD-ROM drive 1226 (DVD-ROM 1201), an IC card or the like, Various types of processing may be performed on the data on RAM 1214. CPU 1212 may then write back the processed data to an external storage medium.

  Various types of information, such as various types of programs, data, tables, and databases, may be stored on a recording medium to be processed. The CPU 1212 performs various types of operations, information processing, conditional determination, conditional branching, unconditional branching, and information retrieval specified in the instruction sequence of the program on the data read from the RAM 1214 as described elsewhere in the present disclosure. Various types of processing may be performed, including / replace, and the results are written back to RAM 1214. Further, the CPU 1212 may search for information in a file, a database, or the like in the recording medium. For example, when the information is stored in a plurality of entry recording media each having the attribute value of the first attribute associated with the attribute value of the second attribute, the CPU 1212 selects the first entry from among the entries. An entry whose attribute value matches the specified condition is searched for, the attribute value of the second attribute stored in the entry is read, and the attribute value is associated with the first attribute satisfying the predetermined condition. The attribute value of the obtained second attribute may be obtained.

  The program or software module according to the above description may be stored on the computer 1200 or in a computer-readable storage medium in the vicinity of the computer 1200. Further, a recording medium such as a hard disk or a RAM provided in a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, whereby the program can be transferred to the computer 1200 via the network. provide.

  As described above, the present invention has been described using the embodiments, but the technical scope of the present invention is not limited to the scope described in the above embodiments. It is apparent to those skilled in the art that various changes or improvements can be made to the above embodiment. In addition, matters described in a specific embodiment can be applied to other embodiments within a technically consistent range. Also, each component may have the same features as other components having the same name and different reference numerals. It is apparent from the description of the appended claims that embodiments with such changes or improvements can be included in the technical scope of the present invention.

  The order of execution of processes such as operations, procedures, steps, and steps in the apparatuses, systems, programs, and methods shown in the claims, the description, and the drawings is particularly “before” or “before”. It should be noted that the output can be realized in any order as long as the output of the previous process is not used in the subsequent process. Even if the operation flow in the claims, the specification, and the drawings is described using “first”, “next”, or the like for convenience, it means that it is essential to implement in this order. Not something.

30 apartment, 31 outside area, 33 inside area, 41 entrance door, 43 operation panel, 50 communication network, 61 first person, 63 second person, 65 third person, 100 management device, 101 device body, 102 detection Unit, 111 communication unit, 113 estimation unit, 117 storage unit, 119 processing unit, 1200 computer, 1201 DVD-ROM, 1210 host controller, 1212 CPU, 1214 RAM, 1216 graphic controller, 1218 display device, 1220 input / output controller, 1222 Communication interface, 1224 hard disk drive, 1226 DVD-ROM drive, 1230 ROM, 1240 input / output chip, 1242 keyboard

Claims (15)

A detection unit that detects a person outside an entrance to a specific area of the building;
Based on the learning result of the relationship between the person outside the entrance to the specific area in the building and the necessity of the specific processing, the necessity of the specific processing is determined based on the person outside the entrance detected by the detection unit. An estimator for estimating
A management unit that executes the specific process when the specific process is estimated to be necessary by the estimation unit. The person outside the entrance includes an operator who performs the unlocking operation of the entrance and a person different from the operator, and the estimating unit includes an interpersonal relationship between the operator and the different person and the identification. Learn the relationship with the need for processing,
The management device according to claim 1. The interpersonal relationship includes a relationship in which the operator is conscious of entering the specific area with the different person, and a relation in which the operator is not conscious of entering the specific area.
The management device according to claim 2. The processing unit further performs different processing depending on whether the different person is registered as a person who is allowed to enter the specific area in advance,
The management device according to claim 2. The processing unit further performs different processing depending on whether there is a history of one or more persons who make the building a residence, a work place, and a place of commuting to the different person,
The management device according to claim 2. The specific process includes a request process for requesting the operator to confirm the different person when an input of the unlocking operation of the entrance by the operator is received,
The management device according to claim 2. The estimating unit learns a relationship between an interpersonal relationship between the operator and the different person and a necessity of the specific process based on a result of the confirmation of the different person by the operator,
The management device according to claim 6. The specific process includes an alert process of the entrance, the estimating unit learns the relationship between the situation of a person outside the entrance and the necessity of the alert process,
The management device according to claim 1. The alert process includes locking at the entrance, closing the entrance, warning at the entrance, and at least one of reporting to a pre-registered notification destination.
The management device according to claim 8. The estimating unit learns the situation of a person outside the entrance requiring the alert processing from a record of an action taken by a person registered as the target requiring the alert processing,
The management device according to claim 8. The estimating unit, as a situation of the person outside the entrance, a poor response to a person who is outside the entrance, one or more people who live in the building, any of work and school. If there is a history of learning, learn that the alert processing is necessary,
The management device according to any one of claims 8 to 10. The specific processing includes (A) unlocking of the entrance, (B) opening of the entrance, (C) release of security of the entrance, and (D) unlocking of a pre-registered notification destination. Contacting for requesting a remote operation of at least one of the door opening and the alert release, wherein the estimating unit communicates with a person outside the entrance and the superior Learn the relationship with the necessity of processing,
The management device according to claim 1. A management system comprising a plurality of the management devices according to any one of claims 1 to 12,
A person who sets the building provided with one of the management devices out of the plurality of management devices as any one of a residence, a work place, and a school destination is provided with the other one of the plurality of management devices. In the case where the building is newly used as one of a house, a work place, and a school place, the learning result of the one management apparatus is shared with the other management apparatus.
Management system. A detecting step of detecting a person outside an entrance to a specific area of the building;
Based on the learning result of the relationship between the person outside the entrance to the specific area in the building and the necessity of the specific processing, the necessity of the specific processing is determined based on the person outside the entrance detected in the detection step. An estimation step of estimating
A step of executing the specific process when the specific process is estimated to be necessary by the estimation step.   A program for causing a computer to execute the management method according to claim 14.