JP2019192191A - Housing management device, housing management method, and program - Google Patents

Abstract

To provide a housing management device that does not require a user to switch between modes with different processing contents with a manual operation, a housing management method, and a program.SOLUTION: A housing management device 100 comprises: a detection unit 102 that detects an input and output in a specific region in a housing; an estimation unit 113 that estimates a situation from the input and output detected by the detection unit on the basis of a learning result of a relationship between the input and output in the specific region in the housing and a situation in the housing; and a processing unit 119 that executes a specific processing on the basis of the situation estimated by the estimation unit. The detection unit detects the input and output in a single or a plurality of entrances between an indoor and an outdoor in the housing providing the detection unit.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a housing management apparatus, a housing management method, and a program.

There is known an integrated monitoring and communication system in which a user can manually switch a mode changeover switch to any one of a home mode, an outing mode, and an action management mode with different processing contents (for example, see Patent Document 1). reference).
[Prior art documents]
[Patent Literature]
[Patent Document 1] Japanese Patent Application Laid-Open No. 2017-16610

  However, the above system is troublesome for the user because it is necessary for the user to manually switch between modes having different processing contents.

  In one aspect of the present invention, based on a detection unit that detects entry / exit in a specific area in a house and a learning result of a relationship between entry / exit in the specific area and the situation in the house, There is provided a housing management apparatus including an estimation unit that estimates a situation and a processing unit that executes a specific process that is predetermined based on the situation estimated by the estimation unit.

  In one aspect of the present invention, the detection unit that detects exit from a specific area in a house, and the exit status that is the status of a person who exits from the specific area is identified and identified from the exit detected by the detection unit. The determination unit that determines whether the absence is for a short time or the absence for a long time based on the status of the exited person, and the determination result of the determination unit is based on whether the determination result is absence for a short time or absence for a long time. There is provided a house management device including a processing unit that executes different specific processing.

  In one aspect of the present invention, detection is performed at the detection stage based on a detection stage for detecting entry / exit in a specific area of the house and a learning result of a relationship between the entry / exit in the specific area of the house and the situation in the house. There is provided a housing management method including an estimation stage for estimating a situation from the entrance and exit, and a processing stage for executing a specific process based on the situation estimated in the estimation stage.

  In one aspect of the present invention, from the detection stage for detecting exit from a specific area in a house and the exit detected in the detection stage, the status of a person who exits from the specific area is identified and specified. Based on the status of the person who left, the judgment stage for judging whether the person is absent for a short time or for a long time, and whether the judgment result of the judgment stage is absent for a short time or absent for a long time. There is provided a housing management method comprising processing steps for executing different specific processes.

  It should be noted that the above summary of the invention does not enumerate all the necessary features of the present invention. In addition, a sub-combination of these feature groups can also be an invention.

It is the schematic of the house management system 10 by 1st Embodiment. It is a schematic diagram of the at-home situation of the house 30 by 1st Embodiment. It is a block diagram of the housing management apparatus 100 by 1st Embodiment. It is a flowchart of learning by a 1st embodiment. It is a flowchart until it performs a specific process based on the learning result by 1st Embodiment. It is an example of the process table stored in the storage part 117 by 1st Embodiment. It is an example of the process table stored in the storage part 117 by 2nd Embodiment. It is a schematic diagram of the at-home situation of the house 30 by 3rd Embodiment. It is an example of the process table stored in the storage part 117 by 3rd Embodiment. It is a flowchart of learning by 3rd Embodiment. It is a schematic diagram of the at-home situation of the house 30 by 4th Embodiment. It is a flowchart until it performs a specific process based on the learning result by 4th Embodiment. It is a schematic diagram of the at-home situation of the house 30 by 5th Embodiment. It is a flowchart of a warning process by 5th Embodiment. And FIG. 11 is a diagram illustrating an example of a computer 1200 in which aspects of the present invention may be embodied in whole or in part.

  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 the combinations of features described in the embodiments are essential for the solving means of the invention. In the drawings, the same or similar parts are denoted by the same reference numerals, and redundant description may be omitted.

  FIG. 1 is a schematic diagram of a house management system 10 according to the first embodiment, and FIG. 2 is a schematic diagram of a home status of a house 30 included in the house management system 10 shown in FIG. FIG. 2A is a schematic diagram of a home situation on the first floor 31 of the house 30, and FIG. 2B is a schematic diagram of a home situation on the second floor 32 of the house 30.

  The family composition of the resident of the house 30 is, for example, a first resident 61 that is a father, a second resident 63 that is a mother, and a third resident 65 that is a child of the first resident 61 and the second resident 63, for example. A family. The third resident 65 is a minor who is less than a junior high school student, for example. Moreover, in this embodiment, all the 1st inhabitants 61, the 2nd inhabitants 63, and the 3rd inhabitants 65 are healthy persons who can lead a normal life by themselves.

  In addition to the house 30, the house management system 10 includes the house management apparatus 100 shown in FIG. 2, the router 50 installed indoors in the house 30, and the house management apparatus 100 via the router 50 and the communication network 40. A first communication terminal 71 and a second communication terminal 73 that perform wireless communication are included. As shown in FIG. 1, the first communication terminal 71 is possessed by the first resident 61, and the second communication terminal 73 is possessed by the second resident 63. In the present embodiment, the third resident 65 does not have a communication terminal, but the first communication terminal 71 and the second communication terminal can contact only any communication terminal, for example, the first resident 61 and the second resident 63. A communication terminal capable of communicating with 73 may be possessed.

  The housing management apparatus 100 according to the present embodiment includes a device main body 101 installed at the front door 81 on the first floor 31, a back door sensor 93 installed at the back door 83 on the first floor 31, and a small bedroom 35 on the first floor 31. The small bedroom sensor 95 installed in the small bedroom window 85 and the large bedroom sensor 97 installed in the large bedroom window 87 of the large bedroom 37 on the first floor 31 are provided. The house management apparatus 100 further includes a living room sensor 99 installed in the living room window 89 of the living room 39 on the second floor 32. The small bedroom 35 is mainly used by the third resident 65, the large bedroom 37 is mainly used by the first resident 61 and the second resident 63, and the living room 39 is used by all the resident. The front port 81, the back port 83, the small bedroom window 85, the large bedroom window 87, and the living room window 89 are examples of entrances and exits.

  The back door sensor 93 is, for example, a pair of infrared sensors, and detects that an object to be detected passes through the back door 83 by installing one on the indoor wall surface and the other on the outdoor wall surface near the back door 83. To do. By having such an exemplary configuration, the back door sensor 93 identifies and detects exit from the back door 83 to the outside and entry from the back door 83 into the room. In addition, when the back door sensor 93 is a pair of infrared sensors, for example, a light emitting unit that emits infrared light is disposed at an installation location illustrated in FIG. 2, and an additional light receiving unit that receives infrared light emitted by the light emitting unit is disposed. May be. Further, a virtual plane inside the door frame of the back door 83 may be scanned.

  Each of the small bedroom sensor 95, the large bedroom sensor 97, and the living room sensor 99 has the same configuration as that of the back door sensor 93. Therefore, each detects the entrance / exit in the small bedroom window 85, the large bedroom window 87, and the living room window 89 so that identification is possible.

  In addition, the apparatus main body 101 includes an imaging unit 105 that images a subject. The imaging unit 105 is installed on the indoor side of the door of the front door 81, and for example, an indoor camera that images the inside of the entrance so that the face of a person who wants to leave the front door 81 is included in the field of view, The outdoor camera which is installed in the outdoor side of 81 doors, and images the exterior of a front door so that the face of the person who is going to enter indoors from the front port 81 is included in a visual field is included. The imaging unit 105, the back door sensor 93, the small bedroom sensor 95, the large bedroom sensor 97, and the living room sensor 99 described above are an example of a detection unit that detects entry / exit at one or a plurality of entrances between indoors and outdoors. is there. In the following description, some or all of the imaging unit 105, the back door sensor 93, the small bedroom sensor 95, the large bedroom sensor 97, and the living room sensor 99 may be collectively referred to as the detection unit 102.

  The house management apparatus 100 further includes a front door operation panel 21 installed on the wall surface of the entrance near the front door 81 inside the house 30, a small bedroom operation panel 25 installed on the wall surface of the small bedroom 35, A large bedroom operation panel 27 installed on the wall surface of the large bedroom 37 and a living room operation panel 29 installed on the wall surface of the living room 39 are provided. In any of these operation panels, a person staying in the house 30 can operate to lock / unlock the front port 81 without directly operating the apparatus main body 101 installed on the door of the front port 81, or An input unit such as a touch panel and a push button is provided so that an operation for turning on and off the automatic locking mode of the camera and an operation for setting and canceling a warning at an entrance / exit can be performed.

  The device main body 101 incorporates artificial intelligence (AI). The artificial intelligence learns the relationship between the entrances and exits at a plurality of entrances of the house 30 and the indoor home situation, and based on the learning result, The home situation is estimated from the entry / exit detected by the detection unit. An example of a home situation is the presence or absence of a home, the number of homes, for example, the composition of the homes such as healthy adults, only children and the elderly, who are homes, and exit from the doorway For example, the length of time that a person staying at home goes out and on. In addition, the person who is at home includes a person who is a resident of the house 30 and stays at the house 30 and a person who is a visitor to the house 30 and is at home. In addition to human beings, other animals such as pets may be included as targets to be detected by the detection unit.

  The apparatus main body 101 further executes a specific process from a plurality of different processes based on the estimated at-home situation.

  According to such a house management system 10, by using artificial intelligence, it is possible to automate the switching and execution of specific processes having different processing contents, thereby eliminating the need for manual operation by the user.

  FIG. 3 is a block diagram of the house management apparatus 100. As described above, the house management device 100 includes the back door sensor 93, the small bedroom sensor 95, the large bedroom sensor 97, the living room sensor 99, the front door operation panel 21, the small bedroom operation panel 25, the large bedroom, in addition to the apparatus main body 101. The operation panel 27 and the operation panel group of the living room operation panel 29 are included. In addition to the imaging unit 105, the apparatus main body 101 includes a key possession detection unit 107 that detects whether or not a home person who is about to exit the front port 81 has a key for locking and unlocking the front port 81. . The detection unit 102 described above includes a key possession detection unit 107.

  The apparatus main body 101 further includes a handle operation detection unit 110 that detects an operation of the door handle of the front port 81 and outputs the operation to the imaging unit 105. The above-described imaging unit 105 starts imaging the indoor side and the outdoor side of the front port 81 using the input from the handle operation detection unit 110 as a trigger. The imaging unit 105 ends the imaging when a predetermined time has elapsed since the imaging was started. Note that the apparatus main body 101 may not include the handle operation detection unit 110. In this case, the imaging unit 105 may always capture images, and other sensors, for example, an opening / closing door that detects the opening / closing door of the front port 81. Imaging may be started using an input from the sensor as a trigger.

  The apparatus main body 101 further includes an estimation unit 113 having the above-described artificial intelligence, an input unit 115 that receives an external voice input or touch input and outputs information input to the estimation unit 113, a back door sensor 93, and the like. Or the communication part 111 which communicates by radio | wireless is provided. The apparatus main body 101 further includes a sound output unit 116 that outputs a specific sound in response to an input from the estimation unit 113, and a storage unit 117 that stores various kinds of information, for example, the data of the specific sound described above.

  The input unit 115 is disposed on the indoor side of the front port 81, and the audio output unit 116 is disposed on each of the indoor side and the outdoor side of the front port 81. The communication part 111 will output to the estimation part 113, if the information of the entrance / exit in each entrance detected by the back door sensor 93 grade | etc., Is received. The estimation unit 113 also receives images captured on the indoor side and the outdoor side of the front port 81 from the imaging unit 105 described above.

  The estimation unit 113 learns the relationship between the entrances and exits at a plurality of entrances and exits indicated by the input information from the detection unit 102 and the indoor status of the house 30. Based on the learning result, the estimation unit 113 further estimates the home status from the entrances and exits at a plurality of entrances indicated by the input information from the detection unit 102. Here, an example of the learning flow will be described with reference to FIG.

  FIG. 4 is a learning flowchart according to the first embodiment. The description of the flow in FIG. 4 is started by an arbitrary resident of the house 30 by an input to the cue for starting learning by the house management apparatus 100, for example, the input unit 115.

  The operation waits until the door handle of the front port 81 is operated, for example, the handle is pulled, that is, until the imaging unit 105 receives an input from the handle operation detection unit 110 (S101: NO). When there is the input (S101: YES), the imaging unit 105 starts imaging the indoor side and the outdoor side of the front port 81 (S103). The imaging may be a continuous still image at regular intervals or a moving image.

  Subsequent to step S103, when the image data captured by the imaging unit 105 is input, the estimation unit 113 refers to the storage unit 117 and causes the voice output unit 116 to utter an information input request message ( S105). The estimation unit 113 determines whether or not the resident has input resident information and advance / retreat information to the input unit 115 in response to the message (S107). If not input (S107: NO), the process proceeds to step S105. Return.

  The resident information referred to here is information indicating who is one of the first resident 61, the second resident 63, and the third resident 65. The advance / retreat information is information indicating whether the user is about to leave the front port 81 or to enter the room. In addition, when the audio output unit 116 and the input unit 115 are arranged only on the indoor side of the front port 81, the resident information is input indoors by the resident who is entering the indoor from the front port 81. Since it is performed after entering, the advance / retreat information in this case is information indicating that the vehicle has entered indoors from the front port 81.

  When resident information and advance / retreat information are input in step S107 (S107: YES), it is determined whether or not one week has passed since the start of learning (S109), and has not elapsed. If so (S109: NO), the process returns to step S101, and if it has elapsed (S109: YES), the flow ends.

  According to the learning flow described above, the estimation unit 113 performs various operations when entering and exiting the front entrance 81 for each of the first resident 61, the second resident 63, and the third resident 65 during one week after the start of learning. The supervised learning is performed on the relationship between the entrance / exit at the front port 81 and the indoor status of the house 30 using the training data with the advance / retreat information, that is, the labeled image. 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). SVM can discriminate with little error even for unknown samples from learning a relatively small number of samples. However, although the learning results can be understood to some extent, it is difficult for humans to understand and the causal relationship of discrimination is difficult to understand. The RNN requires many learning samples and takes a lot of time for learning. It is effective for subjects that are affected by context (context) such as time series, but it is difficult to understand the learning results. BN requires many learning samples and takes time to learn. Since the learning results are expressed in the form of a network connecting 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 probability propagation.

  In learning, the estimation unit 113 extracts image feature amounts using a convolutional neural network (CNN). CNN is a type of deep learning neural network (DLNN). DLNN is a three-layered neural network (NN) that has been expanded to four or more layers, and it has become possible to accumulate large amounts of recent data. It has been known that the performance has been improved compared to new calculation methods that have come out after NN due to the fact that the computer has been improved and the functionality of the computer has been improved. Among them, the CNN uses the brain visual cortex (V1) as a model, and if it is learned in advance so that the accuracy of image recognition is high, an image processing result similar to the brain visual cortex can be obtained. Therefore, this is a method suitable for extracting the feature amount of the image. The NN itself has been actively researched since the 1980s. By combining multiple nodes and performing non-linear processing at each node, an array (pattern) of seemingly meaningless data can be obtained. This is a calculation method (and a data structure therefor) in which a meaningful symbol can be assigned.

  In the present embodiment, the training data is described by focusing on images, sensing information from the back door sensor 93, and the like. However, the training data may include voice or ID information of an electronic key. The feature amount shown in the voice may include, for example, a voice print, utterance content, etc., and the utterance content includes, for example, "I will come", "I'm welcome", "I'm right", "Welcome", etc. May be. When such other training data is included, a technique such as deep learning, machine learning, or statistical processing other than CNN 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 feature quantities shown in speech, a recurrent neural network (RNN) suitable for extracting feature quantities of time-series data, and a deep neural network that can be used in the same way as RNN A method such as (DNN) may be used. However, when using SOM to handle speech, it is difficult to handle time series with a single SOM, so it is necessary to combine it with another method. In addition, when handling speech using RNN, it is possible to extract the feature amount indicated in speech in combination with separately selected preprocessing. Unlike the RNN, the DNN can learn the preprocessing itself.

  After performing the supervised learning on the feature amount of the person shown in the various labeled images acquired in the learning flow, the estimating unit 113 displays the various images when entering and exiting the front port 81 as resident information. Also, it continues to acquire training data without advancing / retreating information, that is, without labeling, and automatically acquires the feature amount of the person shown in the image, and repeatedly enters and exits at the front door 81 and stays indoors in the house 30 Conduct unsupervised learning about the relationship to the situation. The feature quantity of the person shown in the image includes, for example, feature quantities such as face, facial expression, body shape, movement, how to walk, gesture, clothing, ornaments, glasses, belongings, line of sight, and the like.

  In unsupervised learning, feedback from the resident is required regarding the suitability of the estimation results. For example, the estimation unit 113 transmits the estimation result to one or both of the first communication terminal 71 and the second communication terminal 73 each time the home situation is estimated, and one or both of the first resident 61 and the second resident 63. May check the estimation result, and obtain feedback by returning information indicating an estimation failure when the estimation result is incorrect. Further, in order to further save the labor of the resident, for example, the house management device 100 actually executes a warning process based on the estimation result, and the same warning as when there is no resident even though the resident is present in the house 30. Feedback may be obtained by making a setting mistakenly and receiving a warning release input by the home-stayer from an arbitrary operation panel.

  Based on these learning results, the estimation unit 113 estimates the home status from the entrance / exit at one or more entrances / exits indicated in the input information from the detection unit 102. The same technique as that used in the above learning is also used when estimating the home situation. The same applies to subsequent learning and estimation.

  The above-mentioned “relationship” learned by the estimation unit 113 is also referred to as a “learning model” in the technical field, and the estimation unit 113 extracts the information from the entrance / exit at the entrance and the information indicating the indoor home status. , Including regularity, pattern, etc. between these data. In addition, the “relationship” can be said to be a correspondence relationship between information indicating access at the entrance and exit as input data and information indicating an indoor home status as output data.

  Referring again to FIG. 3, the apparatus main body 101 further refers to the processing information stored in the storage unit 117, and executes a processing unit 119 that executes various processes, and an unlocking / unlocking unit 121 that locks and unlocks the front port 81. Is provided. The processing unit 119 receives the estimation result from the estimation unit 113. The processing unit 119 executes the specific process described above based on the home situation indicated in the estimation result. An example of the specific process is a warning process. The warning processing includes, for example, application of the front door 81, closing of the front door 81, turning on the warning mode of each doorway, turning on the going-out mode that puts all doorways in a warning state, and partially or all of all the doorways. The processing contents differ from each other, such as turning on the home mode to be in the alert state, notification to the first communication terminal 71, the second communication terminal 73, and the like. Another example of the specific processing is to execute either one of the doorway locking and unlocking according to the estimated home situation. Another example of the specific process is to notify a predetermined notification terminal when it is estimated that a specific home situation has been reached.

  For example, when the estimation unit 113 estimates that there is no resident in the room as the home status from the outdoor exit at the entrance / exit detected by the detection unit 102, the processing unit 119 executes a warning process for all entrances / exits. Also good. The on / off of the warning mode of a specific entrance / exit included in the alert processing includes setting to issue a warning or a notification when sensing data or image data is input from the detection unit 102 provided at the specific entrance / exit. . In this case, the resident exits from the entrance / exit of the warning mode, the resident who returns to the house 30 unlocks the entrance / exit with the electronic key, enters the indoor, or the resident uses an arbitrary operation panel. If someone enters the room through the doorway that has been unlocked, it may be configured not to issue a warning or a warning. Alternatively, an alarm device may be provided in each of the detection units 102, and the alarm device may be turned on and off.

  In addition, for example, the estimation unit 113 estimates that a specific person who is predetermined indoors as a home situation, for example, the third resident 65 is not home from the entrance into the doorway detected by the detection unit 102. In this case, the processing unit 119 cancels the warning process for some or all of the entrances and exits, and the third resident 65 is at home in predetermined notification terminals, for example, the first communication terminal 71 and the second communication terminal 73. You may notify. In this case, from the situation where the estimation unit 113 enters the indoor at the entrance / exit detected by the detection unit 102, as a home situation, a person other than the third resident 65 is in a room other than the third resident 65, For example, when it is estimated that the acquaintance 66 of the third resident 65 shown in FIG. 2 is also at home, the first communication terminal 71 and the second communication terminal 73 are notified that the acquaintance 66 is also at home. May be.

  In addition, for example, the processing unit 119 may execute different warning processes for a plurality of entrances according to the at-home situation estimated by the estimation unit 113. In this case, the estimation unit 113 may learn in advance the relationship between the home status and the entrance / exit used in the home status among a plurality of entrances / exits. Further, the processing unit 119 cancels the warning process of the entrance / exit used in the home status estimated by the estimation unit 113 among the plurality of entrances / exits, and is used in the home status estimated by the estimation unit 113 out of the plurality of entrances / exits. You may perform the warning process of entrances / exits other than the entrance / exit.

  As learning about the relationship between the home status and the gateway used in the home status among multiple entrances, for example, information about who is at home as the home status and the home status, that is, the home You may learn the relationship with the information which exit / entrance was detected by which exit / entrance. In this exemplary learning, instead of the information on which doorway is detected at the entrance and exit of the home person, the home person wears a wearable device that can communicate with the apparatus body 101, and the apparatus body 101 is wearable. The device may be configured to acquire the position information of the device, and the position information indicating which room a particular home person is staying at home may be used. Similarly, alternatively, a odor sensor or a human sensor is installed in each room of the house 30, and the apparatus main body 101 is configured to acquire sensing data from these sensors, and a specific home person is at home. In addition, information on which room the sensor data was obtained from may be used.

  When the processing unit 119 inputs the information of the entry / exit detected at the specific entrance / exit while the warning mode of the specific entrance / exit is turned on, the processing unit 119 refers to the storage unit 117 to display a specific warning message. The voice output unit 116 utters, and further reports to the first communication terminal 71 and the second communication terminal 73 via the communication unit 111. In this case, the processing unit 119 may further report to an information terminal such as a security company or the police via the communication unit 111.

  The processing unit 119 also transmits the warning processing content to the operation panel group via the communication unit 111 and displays the content on the display of the operation panel group. The processing unit 119 also receives operation information from the operation panel group, for example, locking / unlocking setting information and warning state setting information, via the communication unit 111.

  The apparatus main body 101 further reads out the ID of an electronic key as a key for locking and unlocking the front port 81 by short-range communication, including the cylinder and thumb turn incorporated in the door of the front port 81 and the lock. And a reading unit 125. Reading unit 125 includes an operation unit for selecting locking and unlocking. In the present embodiment, the first communication terminal 71 and the second communication terminal 73 described above have built-in electronic keys, that is, the first resident 61 and the second resident 63 possess a single electronic key. Instead, it has a communication terminal with a built-in electronic key. The third resident 65 is assumed to have a single electronic key.

  The apparatus main body 101 further includes an authentication unit 127 that collates the registration ID stored in the storage unit 117 with the ID input from the reading unit 125 and authenticates when they match. Upon authenticating, the authenticating unit 127 outputs the authenticated information and the selection information selected from locking and unlocking input from the reading unit 125 to the locking / unlocking unit 121. The locking / unlocking unit 121 locks / unlocks the front port 81 based on inputs from the locking / unlocking operation unit 123 and the authentication unit 127. That is, in this embodiment, the apparatus main body 101 does not automatically lock and unlock the front port 81.

  When the processing unit 119 described above receives unlocking information including authenticated information from the locking / unlocking unit 121 while the warning mode of the front port 81 is on, the processing unit 119 turns off the warning mode of the front port 81. Switch. When the processing unit 119 receives unlocking information that does not include authenticated information from the locking / unlocking unit 121 while the warning mode of the front port 81 is on, that is, the authentication unit 127 performs authentication. If the locking / unlocking unit 121 is unlocked by the operation of the locking / unlocking operation unit 123 without referring to the storage unit 117, a specific warning message is uttered by the voice output unit 116, and further, via the communication unit 111. The first communication terminal 71, the second communication terminal 73, the security company, and the police communication terminal may be notified.

  FIG. 5 is a flowchart until a specific process is executed based on a learning result according to the first embodiment. The description of the flow in FIG. 5 starts when the supervised learning period described with reference to FIG. 4 ends.

  The estimation unit 113 waits until the detection unit 102 detects entry / exit at the entrance / exit, that is, until sensing data or image data is input from the detection unit 102 (S111: NO). When there is an input (S111: YES), the estimation unit 113 estimates the home situation from the input sensing data or image data based on the learning result (S113).

  The estimation unit 113 outputs the estimation result to the processing unit 119, and the processing unit 119 executes specific processing by referring to the storage unit 117 (S115), and the flow ends. As described above, the processing flow of FIG. 5 is repeatedly executed while the house management apparatus 100 is operating.

  FIG. 6 is an example of a processing table stored in the storage unit 117 according to the first embodiment. In the table, whether each of the first resident 61, the second resident 63, the third resident 65, and the acquaintance 66 is at home or not, and each of six different types of warning processing are stored in association with each other. The table has 8 rows according to the number of combinations of home and absence of each person.

  The first row of the table indicates that the warning process is A in a home situation where all of the first resident 61, the second resident 63 and the third resident 65 are at home and no acquaintance 66 is present. Yes. The second row of the table shows that the second resident 63 is absent but the warning process is the same A as a difference from the home status of the first row.

  In the third row of the table, the third inhabitant 65 is absent and the second inhabitant 63 is at home or absent, which is different from the at-home status in the first row, and the warning process is set to B in the at-home status. It is shown. The fourth row of the table shows that the first resident 61 is absent as a difference from the home status in the first row, and that the warning process is C in the home status.

  The fifth row of the table indicates that the first resident 61 and the third resident 65 are absent as a difference from the home status in the first row, and that the warning process is D in the home status. The sixth row of the table shows that the first resident 61 and the second resident 63 are absent as a difference from the home status in the first row, and that the warning process is E in the home status. The seventh row of the table shows that the acquaintance 66 is at home as a different point from the home status in the sixth row, and that the warning process is set to E even in the home status.

  In the 8th row of the table, all the first resident 61, the second resident 63, and the third resident 65 are absent as a difference from the home status in the first row, and the warning process is F in the home status. It has been shown.

  When the above warning processing is A, the warning processing is canceled, that is, the warning mode of all entrances is turned off. When the alert process is B, only the alert mode of the small bedroom window 85 is turned on. When the warning process is C, the warning mode of the front door 81 and the back door 83 is turned on. When the warning process is D, the warning mode of the small bedroom window 85 is also turned on in addition to the case of C.

  When the alert process is E, the alert mode of the small bedroom window 85 is turned off, the alert modes of other entrances are all turned on, and further, the first communication terminal 71 and the second communication terminal 73 are notified. When the warning process is F, the warning mode for all the entrances is turned on.

  As described above, the first inhabitant 61, the second inhabitant 63, and the third inhabitant 65 are, for example, a father, a mother, and a child, and have high self-defense power in this order, that is, for example, the third inhabitant 65 that is a child is the most. Low self-defense ability. Therefore, for example, in a home situation where only the third resident 65 is at home, except for a home situation where no one is home, the most strict alert state is required and the content of the alert process is as described above. Note that the third resident 65 may be an elderly person with a low self-defense ability like a child.

  By using such a processing table, the house management device 100 can automatically change the security level of the alert mode according to the person at home indicated by the in-home situation estimated from the entrance / exit at the entrance / exit.

  Referring to FIG. 2 again, the home management apparatus 100 is because the acquaintance 66 entered the house 30 through the front door 81 after the third resident 65 was at home, that is, after executing the above-described warning process E. As the home situation, it is estimated that the third resident 65 and the acquaintance 66 are at home, and the above warning process E is executed again. That is, each of the warning modes continues and the first communication terminal 71 and the second communication terminal 73 are continued. Shows the status of re-notification.

  Since only the third resident 65 is at home, the warning process E is executed, so the warning mode of the front port 81 is on. Therefore, the acquaintance 66 rings an intercom outside the house 30 before entering the house 30, and the third resident 65 performs an operation to release the alert from the small bedroom operation panel 25, for example, in response to the interphone call. .

  In this case, even if it is an acquaintance 66, the case where the 1st inhabitant 61 and the 2nd inhabitant 63 do not approve the approach to the indoor of the house 30 can be considered. Therefore, when the acquaintance 66 rings the intercom, the face of the acquaintance 66 is imaged by the intercom camera, the face image of the acquaintance 66 is transmitted to at least one of the first communication terminal 71 and the second communication terminal 73, and the first resident If either 61 or the second resident 63 does not input the approval remotely, the front port 81 may not be unlocked.

  In addition, when executing the warning process E after executing the above-described warning processes A to D, that is, the state where at least one of the first resident 61 and the second resident 63 is at home from the state where only the third resident 65 is at home. In this case, the first communication terminal 71 and the second communication terminal 73 need not be notified.

  As described above, according to the house management system 10 of the present embodiment, by using artificial intelligence, it is possible to automate the switching and execution of specific processes having different processing contents, and eliminate the need for manual operation by the user. For example, by using the processing table shown in FIG. 6, the security level of the alert mode can be automatically changed according to the home person indicated by the home situation estimated from the entrance / exit at the entrance / exit.

  In the present embodiment, as illustrated in FIG. 2, the first resident 61 and the second resident 63 are described as using the large bedroom 37 together for the convenience of the layout of the house 30. When the number of bedrooms is larger, another bedroom may be used, and the warning processing content in this case may be further subdivided than the processing table of FIG.

  In addition, although the imaging part 105 in this embodiment was demonstrated as a structure distribute | arranged to the indoor side and outdoor side of the front port 81, you may distribute | arrange only to the indoor side of the front port 81. FIG. In this case, in the learning flow described with reference to FIG. 4, the estimation unit 113 starts from the apparatus main body 101 in advance within the field of view of the imaging unit 105 immediately after the imaging unit 105 starts imaging based on an input from the handle operation detection unit 110. By judging whether or not a resident within a predetermined distance range is imaged, that is, whether or not there is a resident near the indoor side of the front door 81, the resident is going to enter the indoor or leave the outdoor. You may judge whether you are doing.

  In the present embodiment, the third resident 65 may be an elderly person, and the house management system 10 may be used to monitor the elderly person by the care center in addition to the first resident 61 and the second resident 63. In this case, a load sensor is provided in the bed of the small bedroom 35 used by the third resident 65, or a human sensor is provided in the toilet on the first floor 31 where the third resident 65 travels. In addition, it is possible to watch whether the third resident 65 can live properly while the second resident 63 is absent.

  Also, in the case of the above-mentioned watching, when the activation of various indoor sensors and the detection by the various sensors described above satisfy the predetermined conditions in the warning process E when only the third resident 65 is at home. You may include starting of the system notified to the 1st communication terminal 71 grade | etc.,.

  In the case of the above-mentioned watching, a sound sensor is further provided in the room to detect the scream of the third resident 65 or some loud sound, or a human sensor and a timer are provided in the bathroom to bathe the third resident 65. May be detected to be longer than a predetermined time. Furthermore, even if it detects that the 3rd inhabitant 65 is going out to the outdoors of the house 30 from the entrance / exit, or detects that the temperature of the room is higher or lower than a predetermined temperature. Good.

  When the processing unit 119 acquires sensing data from these additional sensors, the processing unit 119 transmits the communication data to the first communication terminal 71, the second communication terminal 73, a care center, a security company, a police communication terminal, and the like. It may be reported.

  In addition, when it is estimated from the sensing data that some emergency has occurred in the third inhabitant 65 during watching, a notification to a resident in the next house, a report to an emergency, an audio output unit 116 are additionally provided. From the outside of the house 30, a voice such as “It is expected that the elderly inside the house is in danger. Someone should enter the room and check the safety of the elderly.” When the front port 81 is automatically locked, the automatic locking may be additionally turned off. In addition, since it is assumed that there is a person who can run away without being near the house 30, information may be diffused on the SNS to notify an unspecified number of people of the emergency situation of the third resident 65. .

  In addition, in this embodiment, although demonstrated as the structure which does not lock the front port 81 automatically, for example in the situation where the 1st inhabitant 61 is absent and both the 2nd inhabitant 63 and the 3rd inhabitant 65 or only one is at home. When a person having a better physique than the second resident 63 and the third resident 65 is photographed within a predetermined distance range outside the front mouth 81, the front mouth 81 is automatically locked. May be.

  In the present embodiment, it has been described that the estimation unit 113 continues unsupervised learning after supervised learning for a certain period. In the unsupervised learning, it is preferable to update the resident image as the labeled training data acquired during the supervised learning period. Thereby, the estimation part 113 can identify that it is the same person, even if a resident's appearance changes as he gets older.

  Note that, in the present embodiment, the description has been made assuming that the content of the warning process is subdivided as in the process table shown in FIG. Instead, for example, the house management device 100 estimates that all the residents of the house 30 have gone out as the at-home situation, turns on the warning mode of the entrance / exit except for the front door 81 of the house 30, and displays the state in that state. The alarm may be issued when the user enters the house 30 without passing through the mouth 81.

  In addition, when it is estimated that the resident has returned home from the state where no one is in the house 30, regardless of who the resident is, the warning mode of all the entrances is turned off, Alternatively, the home mode may be used in which only the alert mode is on and the others are off. Further, when only the child comes home, the parental mode may be similarly turned off or the home mode may be set to notify the parent additionally. Further, when the parent goes out and only the child remains, the warning mode of all the entrances may be turned on or the home mode may be set. The parent may also be notified when a child is accompanied when the child returns home or when the child manually opens the front door 81 and invites someone.

  FIG. 7 is an example of a processing table stored in the storage unit 117 according to the second embodiment. The present embodiment is the same as the first embodiment except that a processing table different from the processing table exemplarily described with reference to FIG. 6 is used. Also in the following embodiments, differences from the above-described embodiments will be described, and overlapping descriptions will be omitted. In the present embodiment, the third resident 65 is a bedridden elderly person, and the acquaintance 66 is a caregiver who visits the house 30 from a care center, for example.

  In the table, whether each of the first resident 61, the second resident 63, the third resident 65, and the acquaintance 66 is at home or not, and each of four different types of warning processing are stored in association with each other. The table is provided with 5 rows according to the number of combinations of home and absence of each person.

  The first row of the table shows that the warning process is B in a home situation where all of the first resident 61, the second resident 63, and the third resident 65 are at home and no acquaintance 66 is present. Yes. The second row of the table shows that the second resident 63 is absent but the warning process is the same B as a difference from the home status of the first row.

  The third row of the table shows that the first resident 61 is absent as a difference from the home status in the first row, and that the warning process is D in the home status. The fourth row of the table shows that the first resident 61 and the second resident 63 are absent as a difference from the home status in the first row, and that the warning process is F in the home status. The fifth row of the table shows that the acquaintance 66 is at home as a difference from the home status in the fourth row, and that the warning process is E in the home status.

  The contents of the warning processes B, D, E, and F are the same as the warning processes B, D, E, and F in the first embodiment described with reference to FIG. Bedridden elderly people cannot move on their own intentions, and have lower self-defense capabilities than children, healthy elderly people, and elderly people. For this reason, for example, in a home situation where only a bedridden elderly person is at home, it is preferable to set the most strict alert state, which is the same as the home situation in which no one is home, and the contents of the alert process as described above.

  As described above, this embodiment also has the same effects as the above-described effects of the first embodiment. Further, in a home situation where only a bedridden elderly person is at home, the first resident 61 and the second resident 63 who live with the elderly person have the caregiver perform a warning by the house management device 100 executing the warning process E described above. It is possible to remotely know that he / she has come to the home 30 for home care.

  FIG. 8 is a schematic diagram of the home status of the house 30 according to the third embodiment, FIG. 9 is an example of a processing table stored in the storage unit 117 according to the embodiment, and FIG. 10 is according to the embodiment. It is a flowchart of learning. FIG. 8A is a schematic diagram of a home situation on the first floor 31 of the house 30, and FIG. 8B is a schematic diagram of a home situation on the second floor 32 of the house 30.

  In this embodiment, as a different point from the first embodiment, the locking / unlocking unit 121 is configured to automatically lock the front port 81, and specifically, from one of the authentication unit 127 and the locking / unlocking operation unit 123. After the front port 81 is unlocked by the input, the front port 81 is automatically locked when a predetermined time elapses. As a further different point, the processing unit 119 always turns on the warning mode of the front port 81 regardless of whether or not the first resident 61 is at home.

  Further, as a different point, the back door sensor 93 and the like in the detection unit 102 includes a camera similarly to the imaging unit 105, detects exit from the entrance to the outdoors, and outputs image data indicating the exit.

  Further, as a further different point, the estimation unit 113 identifies the exit status that is the status of the person who exits from the entrance to the outside based on the exit detected by the detection unit 102. An example of an exit situation is that a person leaving the doorway is wearing pajamas with a baby or child wearing a trash bag, wearing work shoes, trash sandals, etc. Stubborn, stretched hair, disordered hairstyle, office bag, business suitcase, travel bag, cleaning tool around the entrance, watering tool in the garden Holding a seal, holding a key of an outdoor storeroom, holding a circulation board, or a combination thereof. The estimation unit 113 determines whether it is absent for a short time or absent for a long time on the basis of the identified exit status.

  More specifically, the estimation unit 113 processes the image data input from the detection unit 102, extracts feature amounts in the image, and distinguishes and learns what kind of leaving person situation. Further, the estimating unit 113 learns by distinguishing whether a person staying indoors in the house 30 is going out for a long time such as going out to work from the front port 81, for example, taking out a small amount of garbage. Hereinafter, such a small outing is referred to as absence for a short time, and outing for a long time is referred to as absence for a long time. The estimation unit 113 further learns the relationship between the status of the person leaving and the absence for a short time and the absence for a long time. Based on the learning result, the estimation unit 113 further estimates that either the short absence or the long absence is determined based on the identified exit status as described above. The estimation unit 113 is an example of a determination unit.

  For example, the exit shown in the image data at the entrance / exit has a garbage bag, a cleaning tool around the entrance, a watering tool in the garden, a seal, a key for outdoor storage, a circular board, etc. The combination of wearing a sandal for taking out trash, wearing pajamas, stretching stubbornness, distorted hairstyle, or the absence of this for a short time May be included. On the other hand, for example, the exit person shown in the image data at the entrance / exit is wearing work shoes, being with a baby or a child, wearing a bag or hair, It may include a combination of carrying a suitcase for business trips, a traveling bag or the like, or a combination thereof and absence for a long time.

  Further, as a further different point, the processing unit 119 executes different processes depending on whether the home status estimated by the estimation unit 113 is absent for a short time or absent for a long time.

  For example, the processing unit 119 continues the doorway warning process when the estimation unit 113 estimates that there is a long absence from the exit status, and the estimation unit 113 estimates that there is a short absence from the exit status The warning process at the doorway may be canceled.

  In addition, for example, the processing unit 119 continues the automatic locking mode of the entrance when the estimation unit 113 estimates that there is a long absence from the exit status, and the estimation unit 113 estimates that the exit status is absent for a short time from the exit status. When it does, you may cancel the automatic lock mode of an entrance.

  In addition, regarding the different processes described above, when the processing unit 119 turns off the warning mode of the front port 81 under a specific condition, the processing unit 119 determines whether the estimation unit 113 has been absent for a long time. On the other hand, when the estimation unit 113 estimates that it is absent for a short time, the warning process at the entrance / exit may be released.

  Further, when the locking / unlocking unit 121 does not automatically lock the front port 81, the processing unit 119 estimates that the estimation unit 113 is absent for a long time, and there is no input in the locking / unlocking unit 121 after the estimation. A warning message that tells the storage unit 117 that the user has forgotten to lock may be uttered from the voice output unit 116. On the other hand, when the estimation unit 113 estimates that the user is absent for a short time, the warning message is not uttered. Also good.

  FIG. 10 shows a learning flow of operations as a subroutine between YES and S109 in the operation of FIG. If the resident information and advance / retreat information are input in step S107 of FIG. 4 (S107: YES), the estimation unit 113 continues to determine whether the advance / retreat information indicates the exit of the house 30 to the outdoors. If it is determined (S301) and no exit is indicated (S301: NO), the process proceeds to step S109 in FIG.

  If the exit is indicated in step S301 (S301: YES), the estimation unit 113 refers to the storage unit 117 to send a message requesting selection of absence for a short time or absence for a long time to the voice output unit 116. Speak (S303). The estimation unit 113 determines whether or not the resident has input a selection of absence for a short time or absence for a long time to the input unit 115 according to the message (S305), and if not input (S305: NO) Returning to step S303, if it is input (S305: YES), the process proceeds to step S109 in FIG.

  By the learning flow including the above subroutine, the estimating unit 113 enters and exits the front mouth 81 for each of the first resident 61, the second resident 63, and the third resident 65 in one week after starting learning. If the various images are accompanied by advance / retreat information, and if the advance / retreat information indicates exit, with a selection information of absence for a short time and absence for a long time, the status of the exit at the front door 81 and absence of a short time and absence for a long time Do supervised learning about relationships. When the estimation unit 113 identifies the exit status from the outdoor exit at the entrance or exits indicated by the input information from the detection unit 102, the estimation unit 113 is absent from the identified exit status for a short time based on these learning results. Or whether it is absent for a long time.

  This embodiment also has the same effect as the first embodiment. Furthermore, as shown in FIG. 8, when a home person who tries to leave the front door 81 is absent for a short time such as taking out garbage, the automatic locking and warning mode at the front mouth 81 are automatically released and turned off. Can be. Therefore, for example, if the resident is out of the trash without carrying the electronic key, it can be prevented from being locked out outdoors, or even if the resident carries out the electronic key and goes out of the trash, For example, it is possible to eliminate the trouble of making the electronic key close to the reading unit 125 of the apparatus main body 101 for authentication.

  In addition, in addition to the learning content in 1st Embodiment, the estimation part 113 in this embodiment adds the learning content in 1st Embodiment, and the relationship between the leaving person situation of those who leave outdoors, the absence for a short time, and absence for a long time. Although described as learning, the relationship may be learned instead of the learning content in the first embodiment. That is, the estimation unit 113 according to the present embodiment does not have to learn the relationship between the entrances and exits at a plurality of entrances of the house 30 and the indoor home status.

  In the present embodiment, the detection unit 102 may include an odor sensor instead of or in addition to the camera, and may detect the smell of perfume from the exit person as the exit from the entrance. In addition or alternatively, the detection unit 102 includes a magnetic sensor, a load sensor, a proximity sensor, an optical sensor, a pressure switch, and the like that are arranged on a key hook installed at the entrance and detects the presence or absence of a key. As an exit from, it may be detected that the exit has taken the key from the lock.

  In addition or in addition, the detection unit 102 includes a sensor that detects a radio wave periodically transmitted from the electronic key, a radio wave intensity, and the like, and the exit person possesses the electronic key as an exit from the entrance / exit. May be detected. In addition or as an alternative, the detection unit 102 includes a load sensor installed in a crib placed in an arbitrary room, and the weight determined in advance by the load sensor of the crib as exit from the entrance / exit. It may be detected that there is no more load.

  In addition or in addition, the detection unit 102 includes a sensor that detects the power state of a specific electrical device in the house 30, and that the power of the specific electrical device has been turned off as the exit from the entrance / exit. It may be detected. In addition or alternatively, the detection unit 102 includes a sensor that detects the amount of power used, the amount of gas used, the amount of water used in the house 30, and the amount of electricity used as a predetermined amount of exit from the doorway. It may be detected that the amount of gas used, the amount of water used is less than the amount used.

  In the present embodiment, the device main body 101 does not need to incorporate artificial intelligence (AI), and specifically, the device main body 101 does not need to include the estimation unit 113. In this case, the storage unit 117 may store a condition for determining whether the person is absent for a short time or absent for a long time based on the status of the exit at a plurality of entrances. Further, the apparatus main body 101 may include a determination unit instead of the estimation unit 113. The determination unit refers to the storage unit 117, the above-described conditions stored in the storage unit 117, and the detection unit 102. Whether the person is absent for a short time or absent for a long time may be determined on the basis of the status of the person who has left from the input information.

  When the exit from the doorway detected by the detection unit 102 to the outside is image data, the storage unit 117 stores, for example, the feature amount of an image of a specific personal belonging, and the determination unit receives from the detection unit 102. Even if it is determined that the exit person possesses the specific possession by processing the input image data and comparing it with the characteristic amount of the specific possession stored in the storage unit 117. Good. In addition, the above-described conditions stored in the storage unit 117 may include, for example, a table in which the various leavers described above are associated with any one of a short absence and a long absence. The above conditions are stored in the storage unit 117 within a specific period before the start of the above process by the house management system 10 in the same manner as the learning flow of supervised learning described with reference to FIGS. 4 and 10. May be.

  FIG. 11 is a schematic diagram of the staying status of the house 30 according to the fourth embodiment, and FIG. 12 is a flowchart until a specific process is executed based on the learning result according to the embodiment. FIG. 11A is a schematic diagram of a home situation on the first floor 31 of the house 30, and FIG. 11B is a schematic diagram of a home situation on the second floor 32 of the house 30.

  In this embodiment, as a point different from the third embodiment, the processing unit 119 always turns off the alert mode of the front port 81 while someone is at home, regardless of who is at home. Further, the processing unit 119 executes either one of the doorway locking and unlocking according to the staying home state estimated by the estimation unit 113. More specifically, the processing unit 119 locks the entrance / exit when the estimation unit 113 estimates that there is a person staying indoors as a home situation from the exit to the outdoors at the entrance / exit detected by the detection unit 102. . Another difference is that when the estimation unit 113 estimates that there is no other home person indoors as a home situation based on the detection by the detection unit 102 and the exit from the entrance / exit by the home person, the detection unit 102 The processing unit 119 executes different processes depending on whether or not possession of the key is detected when the person leaves the room.

  For example, the processing unit 119 locks the entrance / exit when the detection unit 102 detects the possession of the key as well as the exit from the home person. In addition, the processing unit 119 uses the detection unit 102 as a home resident in the situation where the second resident 63 who is the last resident in FIG. 11 forgets to place the second communication terminal 73 in the room and goes out of the front port 81. If the possession of the key is not detected when the key is left, the door is not locked, and a warning message is sent from the voice output unit 116 to the outside of the front port 81 by referring to the storage unit 117 to notify that the key has been left behind. Let

  The description of the flow in FIG. 12 starts when the supervised learning period described with reference to FIG. 4 ends. Steps S411 to S413 are the same as steps S111 to S113 in FIG.

  Subsequent to step S413, the processing unit 119 determines whether or not the key possession detection unit 107 of the detection unit 102 has detected possession of the key of the last resident, that is, the sensing data is input from the key possession detection unit 107. If there is an input (S415: YES), the front port 81 is locked by the locking / unlocking part 121 (S421), and the flow ends.

  When there is no input in step S415 (S415: NO), the processing unit 119 starts the utterance of the warning message from the voice output unit 116 (S417). The processing unit 119 returns to the house 30 in response to the warning and returns to the house 30 to detect that the processing unit 119 has entered the room, that is, image data indicating entry from the imaging unit 105 of the front port 81 into the room. (S419: No). If there is an input (S419: YES), the processing unit 119 stops uttering the warning message (S421), and the process returns to step S411. As described above, the processing flow of FIG. 12 is repeatedly executed while the house management apparatus 100 is operating.

  This embodiment also has the same effect as the first embodiment. Further, not only is the automatic locking performed when the last home person goes out with the key, but the automatic locking is performed when the last home person goes out without the key as shown in FIG. Without warning of the key being left behind, it is possible to prevent the key from being confined indoors, and to save the trouble of having the last home person ask the security company to unlock the front port 81, for example.

  In the present embodiment, the warning mode of the front port 81 is turned off while the last home person is at home, and the warning mode is automatically turned on when the last home person goes out. Well, in this case, as in the third embodiment, it is estimated whether the last resident is absent for a long time or absent for a short time. Also good.

  FIG. 13 is a schematic diagram of the home status of the house 30 according to the fifth embodiment, and FIG. 14 is a flowchart of the alert process according to the embodiment. FIG. 13A is a schematic diagram of the home situation on the first floor 31 of the house 30, and FIG. 13B is a schematic diagram of the home situation on the second floor 32 of the house 30. In this embodiment, as a point different from the first embodiment, the processing unit 119 always turns off the alert mode of the front port 81 while someone is at home, regardless of who is at home. Further, in the home situation shown in FIG. 13, it is assumed that the resident of the house 30 does not lock the front port 81. FIG. 13 shows a state where a suspicious person 67 is approaching the outside of the front port 81.

  Further, as a further different point, the processing unit 119 refers to the image of the resident of the house 30 stored in the storage unit 117 by the estimation unit 113, so that the resident of the house 30 approaches from the outside of the front door 81. However, if a person other than the resident of the house 30 approaches, the warning mode is switched on, and the lock / unlock section 121 is further locked. In this case, the processing unit 119 further notifies the first communication terminal 71 and the second communication terminal 73. In this case, when the processing unit 119 disables the unlocking / unlocking unit 121 or when the apparatus main body 101 additionally includes a preliminary lock that does not have a cylinder for preventing picking, The preliminary lock may be automatically locked. In this case, the processing unit 119 further gives a warning message from the audio output unit 116 on the condition that, for example, a person other than the resident is staying without doing anything within a certain range outside the front port 81. May be uttered.

  The description of the flow in FIG. 14 starts when the resident is at home 30. The processing unit 119 receives input of image data indicating that a person approaching the outside of the front port 81, for example, a suspicious person 67, is detected by the imaging unit 105, that is, the person from the imaging unit 105 is approaching from the outside. (S521: NO).

  When there is an input in step S521 (S521: YES), the processing unit 119 determines whether or not the person indicated in the image data is a person who can enter indoors, for example, the third resident 65 (S523). ), If the person is OK (S523: YES), the flow ends.

  If the person is not an OK person in step S523 (S523: NO), the processing unit 119 turns on locking and warning of the front port 81 (S525). Subsequent to S525, the processing unit 119 waits until a person who is outside the front port 81 leaves, that is, until there is input of image data indicating that no person is present in front of the front port 81 from the imaging unit 105. (S527: NO).

  When there is an input in step S527 (S527: YES), the processing unit 119 turns off the locking and warning of the front port 81 (S529), and the flow ends.

  This embodiment also has the same effect as the first embodiment. Further, as shown in FIG. 13, when there is a suspicious person 67 approaching the front mouth 81, the automatic locking and warning mode at the front mouth 81 are automatically set and turned on, and the resident is notified. be able to. Therefore, for example, while the resident is relaxing on the second floor 32 of the house 30, it is possible to prevent the suspicious person 67 from entering the indoor through the unlocked front port 81 and working theft on the first floor 31. In addition, the resident who has received the notification can confirm the appearance of the suspicious person 67 from, for example, a window overlooking the outdoor side of the front door 81 of the house 30, and thereby whether or not the suspicious person 67 is actually an OK person. Can be judged by the residents themselves.

  In addition, as a situation similar to the present embodiment, a person staying indoors in the house 30 wants to always keep the warning mode at each entrance and exit, but may not want to issue a report. In addition, there is a case where a part of processing is desired to be temporarily stopped even if the home person is set to the home mode while at home. For example, this is a case where an OK person returns home. In this case, an OK person may be learned in advance, and the OK person may be configured not to be notified even when the door is unlocked or opened. In addition, after an OK person opens the door, an alarm may be issued if a person other than the OK person enters the room. Thereby, since it is not necessary for the resident to manually switch the mode according to the situation, the labor of the resident can be omitted.

  In the house management apparatus 100 described in the first to fifth embodiments, the detection unit 102 detects entry / exit at one or a plurality of entrances between the indoor and the outdoor, and the estimation unit 113 includes the entrance / exit. It was explained as a way to learn the relationship between going in and out and indoor home conditions. The indoor at-home situation is an example of an indoor situation. Further, in the housing management apparatus 100, the detection unit 102 detects the exit to the outdoors from one or a plurality of entrances between the indoor and the outdoor, and the estimation unit 113 detects the above exit detected by the detection unit 102. It was explained as specifying the exit status, which is the status of those exiting from the doorway. Here, the housing management apparatus by 6th Embodiment provided with the structure different from the structure of the housing management apparatus 100 demonstrated in the above 1st Embodiment to 5th Embodiment is demonstrated. Of the configuration of the housing management apparatus of the present embodiment, the same points as the configuration of the housing management apparatus 100 described above will not be described repeatedly.

  The housing management apparatus according to the present embodiment may enter or exit in a specific area in the house 30, for example, in and out of the living room 39 instead of or in addition to a part or all of the configuration of the detecting unit 102. A detection unit for detecting is provided. The detection unit may be, for example, a single or a plurality of indoor cameras that capture an image of the space in the living room 39, a single or a plurality of sensors that detect some movement in the space. The detection unit may detect an exit from a specific area in the house 30. In addition, the specific area | region in the house 30 is not only the inside in the house 30, but the specific area | region in the site which the resident of the house 30 occupies, for example, the inner side from the outer gate of a detached house or a condominium, and the inner side from the fence of a detached house May be included.

  In addition, the house management device according to the present embodiment replaces or adds to the estimation unit 113, and the relationship between the entry / exit in a specific area of the house 30 and the indoor situation indicated by the input information from the detection unit described above. The estimation part which learns is provided. An example of the indoor situation is a resident's state when the resident of the house 30 enters the specific area, instead of the indoor home situation described above. The state of the resident when the resident of the house 30 enters the specific area is, for example, someone who is threatened by someone, being forced by a salesman visiting the house 30, or someone While entering the area while talking happily.

  Another example of the indoor situation is that the resident of the house 30 is not supposed to be a visitor to the house 30, in other words, the resident of the house 30 does not allow the house 30 to enter the house. This is a situation where an NG person exists indoors in the house 30 or is acting indoors. The situation in which an NG person is present in the house 30 is, for example, a situation in which someone is in a vacant nest to the house 30, and a situation in which an NG person is acting indoors in the house 30. Is a situation where, for example, someone is ruining the indoors. The estimation unit further estimates an indoor situation based on the learning result based on the entry / exit in a specific area of the house 30 indicated by the input information from the detection unit. In addition, the estimation unit may further specify a leaver situation that is a situation of a person leaving the specific area from the exit detected by the detection unit.

  This embodiment also has the same effects as those of the first to fifth embodiments. In addition, as long as each structure in the above several embodiment can be considered, it may be used in combination with each other.

  In the above embodiments, for example, a person who has come to the house 30 several times together with the family of the house 30, or a family as a helper or maid has permitted the OK person. A person or a courier who has come to the house 30 in the past and the family has handled correctly may be included.

  In any of the embodiments described above, a sensor for detecting bedtime may be additionally installed in each bedroom. The sensor is, for example, a camera, and detects that a resident's bag in a bedroom is closed for a predetermined time or by detecting that a resident in the bedroom has put on a futon. You may detect bedtime. The sensor may be, for example, an illuminance sensor, and may detect bedtime by detecting that the illuminance of the bedroom is equal to or lower than a predetermined threshold value. The sleep may be detected by detecting that the voltage of the lighting switch is grounded. The processing unit 119 may turn off the warning mode at the entrance / exit while someone is at home, and turn on the warning mode when it is detected that all the resident are sleeping. Further, when it is detected that any home-staying person has woken up, the processing unit 119 may turn off the alert mode. Further, when only a child gets up, only the warning mode of the small bedroom window 85 may be turned off.

  In any of the embodiments described above, a sensor that detects entering and exiting the bathroom may be additionally installed in the bathroom. The sensor may be, for example, a camera, an infrared sensor, or a human sensor. When someone is at home, the processing unit 119 turns off the entrance warning mode and detects that the last home person has entered the bathroom, or a home person staying with a bedridden elderly person enters the bathroom. If it is detected that it has entered, the alert mode may be turned on. In addition, when it is detected that a person who has taken a bath has gone out of the bathroom, the processing unit 119 may turn off the alert mode. In addition, when another resident comes home while the resident is taking a bath, the processing unit 119 may turn off the alert mode.

  In any of the above-described embodiments, the detection unit further detects that the power of one or a plurality of electrical devices in the house 30 is turned on, and the estimation unit performs the entry / exit at the entrance / exit and the electrical device. You may learn the relationship between the power-on of and the home situation. In this case, based on the learning result, the estimation unit may estimate the home status from the entrance / exit detected by the detection unit, and may estimate that the power of a specific electrical device is turned on based on the home status. . Furthermore, the processing unit 119 may turn on the power supply of the specific electrical device based on the power supply of the specific electrical device estimated by the estimation unit being turned on. For example, the house management device 100 stores the electrical devices that the father who has returned to the house 30 turned on immediately after returning home, learns which electrical devices are frequently turned on, and then the father returns home. Sometimes the power of the above-mentioned electrical equipment is automatically turned on. In this case, the estimation unit may be a part of the configuration of the electric device control apparatus different from the apparatus main body 101.

  In any of the above embodiments, the estimation unit may learn who is a resident who is likely to forget to lock, and may warn the person when he / she goes out. The estimation unit may learn a resident's life pattern and time schedule. For example, it may be learned that a specific resident is absent for a short period of time around 20:00 on Sunday to take out trash, or that a specific resident is absent for a long period of time at 8 o'clock on weekdays. In this case, the estimation unit may further automatically unlock the entrance and exit in advance at a specific time zone or turn off the warning mode based on the life pattern of a specific resident.

  In any of the above-described embodiments, as a specific process, the processing unit 119 detects the home person whose both hands are covered with a bag or dust when the indoor camera of the imaging unit 105 of the front port 81 detects the home person. You may assist a lock and opening. In addition, when the estimation unit learns that a specific person enters and exits the front mouth 81 during a specific time period, such as taking out garbage or commuting by a specific person, the processing unit 119 can perform more than the time period. The front port 81 may be automatically unlocked in advance. In addition, when the locking / unlocking unit 121 does not normally automatically lock the front port 81 and the estimation unit estimates that a specific person is absent for a long time due to commuting or the like, the processing unit 119 identifies The front port 81 after the person has gone out may be automatically locked. In addition, when the estimation unit learns the resident, the outdoor camera of the imaging unit 105 in the front port 81 detects that the specific resident has come home, or the specific resident is in a state where both hands are blocked. When it is detected that the user has returned home, the processing unit 119 may assist in unlocking or opening the front port 81.

  In the case where the locking / unlocking portion 121 automatically locks the front port 81 as in the third and fourth embodiments, even if the front port 81 is automatically unlocked and opened automatically in case of emergency or disaster. Good.

  In any of the embodiments described above, the estimation unit additionally learns the relationship between the entrance / exit at the entrance and the indoor home status, and learns the relationship between the exit status from the entrance and the short absence and long absence. Similarly, the above specific processing may be learned.

  In any of the above embodiments, the house management apparatus 100 may additionally include means for detecting a person who has entered the house 30 from a place where the detection unit is not installed, for example, a suspicious person 67. The means may be, for example, a human sensor provided at an arbitrary place in the room. In this case, when it is estimated that there is no resident in the house 30, the house management device 100 may turn on all the entrance sensors and turn on all the indoor human sensors. Further, when it is estimated that only a specific home person is in the house 30, the house management device 100 turns on a warning mode for an entrance / exit other than the entrance / exit related to the specific home person, and You may turn on the human sensor provided in a room other than the room related to the person at home. In any case, the house management device 100 issues a notification not only when an entrance from any of the entrances and exits in the alert mode is detected, but also when only the human sensor detects a person indoors. It may be configured as follows.

  In any of the above-described embodiments, the estimation unit having artificial intelligence in the house management apparatus 100 has been described as starting each learning after the house management apparatus 100 is installed in the house 30. In addition, the estimation unit of the house management apparatus 100 has already learned a certain amount in advance at a manufacturing stage of the house management apparatus 100 in a different place before the house management apparatus 100 is installed in the house 30, for example. Also good. Thereby, you may reduce the quantity and period of learning after the housing management apparatus 100 demonstrated in said embodiment was installed in the house 30. FIG. The learning method in this case is preferably the same method as that described in the above embodiment, considering that each learning is continued after the house management device 100 is installed in the house 30.

  Various embodiments of the invention may be described with reference to flowcharts and block diagrams, where a block is either (1) a stage in a process in which the operation is performed or (2) an apparatus responsible for performing the operation. May represent a section of Certain stages and sections are implemented by dedicated circuitry, programmable circuitry supplied with computer readable instructions stored on a computer readable medium, and / or processor supplied with computer readable instructions stored on a computer readable medium. It's okay. Dedicated circuitry may include digital and / or analog hardware circuitry and may include integrated circuits (ICs) and / or discrete circuits. Programmable circuits include memory elements such as logical AND, logical OR, logical XOR, logical NAND, logical NOR, and other logical operations, flip-flops, registers, field programmable gate arrays (FPGA), programmable logic arrays (PLA), etc. Reconfigurable hardware circuitry, including and the like.

  Computer readable media may include any tangible device capable of storing instructions to be executed by a suitable device, such that a computer readable medium having instructions stored thereon is specified in a flowchart or block diagram. A product including instructions that can be executed to create a means for performing the operation. Examples of computer readable media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, 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 disc read only memory (CD-ROM), digital versatile disc (DVD), Blu-ray (RTM) disc, memory stick, integrated A circuit card or the like may be included.

  Computer readable instructions can 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. Including any source code or object code written in any combination of one or more programming languages, including languages and conventional procedural programming languages such as "C" programming language or similar programming languages Good.

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

  FIG. 15 illustrates an example computer 1200 in which aspects of the present invention may be embodied in whole or in part. The program installed in the computer 1200 causes the computer 1200 to function as an operation associated with the apparatus according to the embodiment of the present invention or one or more “units” of the apparatus, or to perform the operation or the one or more “parts”. Can be executed and / or the computer 1200 can execute a process according to an embodiment of the present invention or a stage of the process. Such a program 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.

  A computer 1200 according to this embodiment includes a CPU 1212, a RAM 1214, a graphic controller 1216, and a display device 1218, which are connected to each other by a host controller 1210. The computer 1200 also includes input / output units 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 ROM 1230 and keyboard 1242, which are connected to input / output controller 1220 via input / output chip 1240.

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

  The communication interface 1222 communicates with other electronic devices 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 program or data to the hard disk drive 1224 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, for example, a boot program executed by the computer 1200 at the time of activation and / or a program depending on the 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 the hard disk drive 1224, the RAM 1214, or the ROM 1230, which is also an example of a computer-readable storage medium, and executed by the CPU 1212. Information processing described in these programs is read by the computer 1200 to bring about cooperation between the programs and the various types of hardware resources. An apparatus or method may be configured by implementing information operations or processing in accordance with the use of computer 1200.

  For example, when communication is performed between the computer 1200 and an external device, the CPU 1212 executes a communication program loaded in the RAM 1214 and performs communication processing on the communication interface 1222 based on 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 the read transmission. Data is transmitted to the network or received data received from the network is written into a reception buffer area provided on the recording medium.

  Further, the CPU 1212 allows 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, etc. Various types of processing may be performed on the data on the RAM 1214. The CPU 1212 may then write back the processed data to an external recording 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 describes various types of operation, information processing, conditional judgment, conditional branching, unconditional branching, and information retrieval that are described in various places in the present disclosure for data read from the RAM 1214 and specified by the instruction sequence of the program. Various types of processing may be performed, including / replacement, etc., and the result is written back to RAM 1214. In addition, the CPU 1212 may search for information in files, databases, etc. in the recording medium. For example, when a plurality of entries each having the attribute value of the first attribute associated with the attribute value of the second attribute are stored in the recording medium, the CPU 1212 selects the first entry from the plurality of entries. An entry that matches the condition for which the attribute value of the attribute is specified is read, the attribute value of the second attribute stored in the entry is read, and the first attribute that satisfies the predetermined condition is thereby read. The attribute value of the associated second attribute may be obtained.

  The program or software module according to the above description may be stored in a computer-readable storage medium on the computer 1200 or in the vicinity of the computer 1200. In addition, 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 is transmitted to the computer 1200 via the network. provide.

  As mentioned above, although this invention was demonstrated using embodiment, the technical scope of this invention is not limited to the range as described in the said embodiment. It will be apparent to those skilled in the art that various modifications or improvements can be added to the above-described embodiment. In addition, the matters described in the specific embodiment can be applied to other embodiments within a technically consistent range. Moreover, each component may have the same characteristics as other components having the same name and different reference numerals. It is apparent from the scope of the claims that the embodiments added with such changes or improvements can be included in the technical scope of the present invention.

  The order of execution of each process such as operations, procedures, steps, and stages in the apparatus, system, program, and method shown in the claims, the description, and the drawings is particularly “before” or “prior to”. It should be noted that the output can be realized in any order unless the output of the previous process is used in the subsequent process. Regarding the operation flow in the claims, the description, and the drawings, even if it is described using “first”, “next”, etc. for convenience, it means that it is essential to carry out in this order. It is not a thing.

10 Housing management system, 21 Front door operation panel, 25 Small bedroom operation panel, 27 Large bedroom operation panel, 29 Living room operation panel, 30 House, 31 1st floor, 32 2nd floor, 40 Communication network, 50 router, 61 1st resident , 63 2nd Resident, 65 3rd Resident, 66 Acquaintance, 67 Suspicious Person, 71 1st Communication Terminal, 73 2nd Communication Terminal, 81 Front Entrance, 83 Back Door, 85 Small Bedroom Window, 87 Large Bedroom Window, 89 Living Room Window , 93 Back door sensor, 95 Small bedroom sensor, 97 Large bedroom sensor, 99 Living room sensor, 101 Device main body, 102 Detection unit, 105 Imaging unit, 107 Key possession detection unit, 110 Handle operation detection unit, 111 Communication unit, 113 Estimation unit 115 Input unit 116 Audio output unit 117 Storage unit 119 Processing unit 121 Locking / unlocking unit 123 Locking / unlocking operation unit 125 Reading unit 12 Authentication unit, 1200 computer, 1201 DVD-ROM, 1210 host controller, 1212 CPU, 1214 RAM, 1216 graphic controller, 1218 display device, 1220 I / O controller, 1222 communication interface, 1224 hard disk drive, 1226 DVD-ROM drive, 1230 ROM 1240 Input / output chip, 1242 Keyboard

Claims (18)

A detection unit for detecting entry and exit in a specific area of the house;
Based on the learning result of the relationship between the entry and exit in a specific area in the house and the situation in the house, an estimation unit that estimates the situation from the entry and exit detected by the detection unit;
A housing management apparatus comprising: a processing unit that executes a specific process based on the situation estimated by the estimation unit.   The housing management apparatus according to claim 1, wherein the detection unit detects entry / exit at one or a plurality of doorways between the indoor and the outdoor in the house where the detection unit is provided.   The housing management apparatus according to claim 2, wherein the learning result uses a result of learning a relationship between an entrance / exit at the entrance / exit where the detection unit is provided and an in-home situation in the house.   The housing management apparatus according to claim 3, wherein the specific process includes executing either one of locking and unlocking of the entrance / exit according to the staying home state estimated by the estimation unit.   The housing management apparatus according to claim 3 or 4, wherein the specific processing includes notifying a predetermined notification terminal when the estimation unit estimates that the specific home status has been reached.   When the estimation unit estimates from the exit to the outdoors at the doorway detected by the detection unit that there is no resident in the indoor as the home status, the processing unit executes a warning process for the doorway The housing management apparatus according to any one of claims 3 to 5.   The housing management apparatus according to claim 3, wherein the processing unit executes different warning processes for the plurality of entrances according to the home situation estimated by the estimation unit. The estimation unit learns in advance the relationship between the home status and the gateway used in the home status among the plurality of gateways,
The processor is
Among the plurality of entrances, the estimator estimates the entrance / exit warning process used in the at-home situation,
The housing management apparatus according to claim 7, wherein a warning process for an entrance / exit other than the entrance / exit used by the estimation unit, which is estimated by the estimation unit, is executed among the plurality of entrances / exits.   The said specific process includes performing either one of locking and unlocking of the entrance / exit between the indoor and the outdoor in the said house according to the said condition estimated by the said estimation part. Housing management equipment.   The housing management apparatus according to claim 1, wherein the specific process includes notifying a predetermined notification terminal when the estimation unit estimates that the specific situation has occurred.   The said process part performs the warning process of the entrance / exit between the indoors and the outdoors in the said house, when the said estimation part estimates that there is no resident in the said house as the said situation. The housing management apparatus according to any one of the above. A detection unit for detecting exit from a specific area in the house;
From the exit detected by the detection unit, the exit status that is the status of the person leaving the specific area is specified, and the absence status is absent for a short time or for a long time based on the identified exit status. A determination unit for determining whether or not
A housing management apparatus provided with the process part which performs a mutually different specific process according to whether the judgment result of the said judgment part is absence of the said short time or the said long time absence.   The housing management apparatus according to claim 12, wherein the detection unit detects exit to the outdoor from a single or a plurality of entrances between indoors and outdoors in the house where the detection unit is provided.   Based on the learning result of the relationship between the exit status and absence for a short time and absence for a long time, the determination unit estimates from the identified exit status that either the short absence or the absence for a long time The housing management apparatus according to claim 12 or 13. A storage unit for storing a condition for determining whether the absence for a short period of time or the absence of a long period of time based on the exit status;
The housing management apparatus according to claim 12, wherein the determination unit determines whether the absence is present for a short time or the absence for a long time from the identified status of the exit by referring to the storage unit. A detection stage for detecting entry and exit in a specific area of the house;
Based on the learning result of the relationship between the entry and exit in a specific area in the house and the situation in the house, an estimation stage for estimating the situation from the entry and exit detected in the detection stage;
A housing management method comprising: a processing stage that executes a specific process based on the situation estimated in the estimation stage. A detection stage for detecting exit from a specific area in the house;
From the exit detected in the detection step, the status of a person who is leaving the specific area is identified, and based on the identified exit situation, the person is absent for a short time or absent for a long time. A judgment stage for judging whether
A housing management method comprising: a processing step of executing different specific processes according to whether the determination result of the determination step is absent for a short time or absent for a long time.   A program for causing a computer to execute the housing management method according to claim 16 or 17.