Support system and support method

Abstract

To provide a support system that prevents accidents and promotes voluntary actions by those receiving support. The system detects when a support recipient approaches a support-requiring location where an accident is likely to occur. and installed at the support location 3 A detection device 10, an alarm device 32 that notifies the surroundings of a place where the alarm device 32 is installed, and a support recipient 1 that is detected by the detection device 10 as approaching a support-requiring place 3, In each support location, the number of support recipients is When it is determined that notification is necessary by the notification determination unit 53 that determines the necessity of notification by the notification device 32 based on the risk DB 52 that stores the level of accident risk and the level of accident risk stored in the risk DB 52 for the support recipient 1 who has approached the support required place 3, Installed at location 3 where support recipient 1 approached and a notification execution unit 54 that executes notification by the notification device 32.

Description

[Technical Field]

[0001] The present disclosure relates to an assistance system and an assistance method. [Background technology]

[0002] In recent years, with the aging of society, the demand for nursing care services at elderly care facilities has been rapidly increasing. However, this demand is being met with a serious shortage of nursing care staff, and there are limits to how much care can be provided by staff alone. To address this issue, it is desirable to provide high-quality services while also properly managing the accident risks of users. In elderly care facilities, the physical and mental conditions of users can change suddenly, and it is necessary to respond to these changes quickly and appropriately. However, traditional nursing care methods rely heavily on the experience and intuition of staff, and staff shortages can lead to inconsistent quality of accident risk management (accident management, activity promotion, etc.). For this reason, technical support is essential to achieve efficient and effective accident risk management.

[0003] Claim 1 of Patent Document 1 describes a monitoring system in which a user communication terminal device on the wheelchair user's side and a monitor communication terminal device on the monitor's side are connected to a cloud server via a communication means, wherein wheelchair behavior conditions for the wheelchair user are pre-programmed and stored on the cloud network, and when the behavior conditions deviate or are at risk of deviating in light of the wheelchair behavior information, an alert signal or behavior guideline signal is sent to the user communication terminal device and the monitor communication terminal device. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2023-99262 Summary of the Invention [Problem to be solved by the invention]

[0005] In the monitoring system described in Patent Document 1, when the behavior of each wheelchair user or other user deviates from preset behavioral conditions, an alert signal is sent to the user and the monitor (see paragraphs 0026, 0032, etc.). However, while the range of user behavior varies from user to user, straying from that range does not necessarily result in an accident such as a fall. Therefore, if an alert signal is sent every time a user's behavior deviates from the preset behavioral conditions, the user's behavior may be excessively restricted. As a result, the user's spontaneous behavior is hindered, and the user's activities cannot be promoted. The problem that the present disclosure aims to solve is to provide a support system and a support method that can simultaneously prevent accidents from occurring and encourage voluntary actions by support recipients. [Means for solving the problem]

[0006] The support system of the present disclosure includes a detection device that detects when a support recipient approaches a support-requiring location where an accident is likely to occur, and an alarm device that issues an alarm to those around the location where the alarm device is installed. and installed in the location where support is required. The support device includes a notification device and a support device, and the support device detects a risk that the support recipient, who is detected by the detection device as approaching the support-requiring location, will cause an accident at the support-requiring location. , the support recipient's own for each support-requiring location a risk database storing the level of accident risk; a notification determination unit that determines the necessity of notification by the notification device for the support target who approaches the support required location based on the level of accident risk stored in the risk database; and when the notification determination unit determines that notification is necessary, The support recipient is located in the support-requiring location. and a notification execution unit that executes notification by the notification device. Other solutions will be described later in the description of the preferred embodiment of the present invention. [Effects of the Invention]

[0007] According to the present disclosure, it is possible to provide a support system and a support method that can prevent accidents from occurring and encourage spontaneous behavior among support recipients. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a block diagram illustrating a support system of the present disclosure. [Figure 2] FIG. 2 is a schematic diagram showing a location database. [Figure 3] FIG. 2 is a block diagram showing a hardware configuration of the support device of the present disclosure. [Figure 4] FIG. 2 is a schematic diagram showing a risk database. [Figure 5] FIG. 2 is a schematic diagram showing a subject database. [Figure 6] 1 is a flowchart illustrating a support method of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, modes for carrying out the present disclosure (hereinafter referred to as "embodiments") will be described with reference to the drawings. In the following description of one embodiment, other embodiments applicable to the one embodiment will also be described as appropriate. The present disclosure is not limited to the one embodiment described below, and different embodiments can be combined with each other or modified as desired without significantly impairing the effects of the present disclosure. Furthermore, the same components will be given the same reference numerals, and redundant descriptions will be omitted. Furthermore, components having the same functions will be given the same names. The contents shown are merely schematic, and for convenience of illustration, changes may be made from the actual configuration within the scope of not significantly impairing the effects of the present disclosure, and some components may be omitted or modified between drawings. Furthermore, the same embodiment does not necessarily have to include all of the configurations.

[0010] FIG. 1 is a block diagram showing a support system 100 of the present disclosure. The support system 100 is a system that grasps the level of accident risk, which varies for each support recipient 1, such as an elderly person, and for each support-requiring place 3, such as a toilet. The support system 100 can assist the supporter 2 (which may include a supervisor) who supports the support recipient 1 in making a decision, specifically, in determining whether or not support is necessary for the support recipient 1 (whether or not the risk of an accident is high). In addition, the support system 100 is a system that issues a warning via a warning device 32 when the support recipient 1 approaches a support-requiring place 3 that has been determined to have a high accident risk for the support recipient 1.

[0011] Examples of support recipients 1 include elderly people, physically disabled people, etc. Examples of support-requiring places 3 include toilets, rooms such as bedrooms, and washrooms. Accident risk is the risk (possibility) of accidents such as falling, tripping, or hitting a structure. In the example of the present disclosure, accidents include minor accidents, serious accidents (e.g., life-threatening accidents), as well as near misses that lead to accidents.

[0012] The level of accident risk differs depending on physical ability (level of care required, level of support required, etc.) and also on the location where the support recipient 1 is active (support required location 3). For this reason, as will be described in detail later, a location DB 55 and a risk DB 52 are used that associate and store the level of accident risk for each support required location 3. For example, a person who uses a wheelchair needs to get out of the wheelchair when using the toilet. For this reason, the risk of an accident in the toilet is extremely high. However, when traveling along a straight, wide, flat corridor inside a facility 30 such as a hospital, there is no need to get out of the wheelchair, and there are usually no obstacles in the corridor, so the risk of an accident is extremely low.

[0013] Furthermore, even when getting out of a wheelchair to use the toilet, the risk of an accident is not that high for a user with a care level of 1, but the risk of an accident is extremely high for a user with a care level of 4. For this reason, as will be described in detail later, a target DB 56 and a risk DB 52 are also used, which store the level of accident risk associated with each support target 1.

[0014] In particular, some support recipients 1 try to do everything by themselves so as not to bother supporter 2. For this reason, although an accident would not occur (i.e., the risk of an accident is low) if support recipient 1 had support from supporter 2, accidents may occur because they do things by themselves (i.e., the risk of an accident increases).

[0015] Therefore, in the present disclosure, the level of accident risk is determined for each support recipient 1 and each support-requiring place 3, and a risk DB 52 is constructed. Then, if it is determined that the accident risk is high based on the risk DB 52, an alert is issued, for example, by an alert device 32 disposed in the support-requiring place 3. This alert can alert the support recipient 1 in the support-requiring place 3, thereby reducing the risk of an accident. Furthermore, through the alert from the mobile communication terminal 21 (an example of the alert device 32) carried by the supporter 2, the supporter 2 can know which support recipient 1 needs support from the supporter 2 at which support-requiring place 3. As a result, even if the supporter 2 is not at the support-requiring place 3 at the time of the alert, the supporter 2 can notice the alert from the alert device 32 and rush to the support-requiring place 3. This can prevent accidents from occurring.

[0016] On the other hand, if an alert is always issued when any support recipient 1 approaches the support-requiring place 3, an alert will be issued even when the support recipient 1 approaches with a low accident risk, as described above. This may cause the support recipient 1 to feel annoyed and may inhibit the support recipient 1's behavior. Furthermore, if a supporter 2 notices the alert from the alert device 32 and rushes to the support-requiring place 3, the supporter 2 will understand that the support recipient 1 has a low accident risk and does not need support. As a result, the supporter 2 may feel that excessive alerts are being issued and may shut down the alert device 32 or the support system 100.

[0017] Therefore, as described above, depending on the level of the accident risk, a notification is made when the support recipient 1 needs support at the support-requiring location 3, and a notification is not made when the support recipient 1 does not need support at the support-requiring location 3. This makes it possible to both prevent accidents and encourage the support recipient 1 to take voluntary action. Furthermore, even when a notification is made that the accident risk is high, some support recipients 1 may continue their actions. However, even in this case, it is expected that the support recipient 1 who notices the notification will act more hesitantly than if they had not been notified. This means that it takes longer for the support recipient 1 to take action, and time can be bought before an accident occurs. This allows the supporter 2 to arrive at the support-requiring location 3 within that time, thereby preventing accidents from occurring.

[0018] The accident risk may be, for example, a numerical value of the accident risk, a conceptual value such as "high," "medium," or "low," or a binary value such as whether or not an accident has actually occurred. In the examples of the present disclosure, conceptual accident risks such as "high," "medium," or "low" are mainly exemplified as the accident risk.

[0019] The assistance system 100 includes a detection device 10, a notification device 32, an assistance device 50, a display device 60, and an input device 61.

[0020] The detection device 10 is a device that detects that the support recipient 1 has approached a support-requiring place 3 where there is a concern that an accident may occur. Approaching includes cases where the support recipient 1 is within a predetermined distance of the support-requiring place 3, as well as cases where the support recipient 1 has reached the support-requiring place 3 (the distance between the support recipient 1 and the support-requiring place 3 is 0). Conceptually, there is a concern that an accident may occur. However, strictly speaking, an accident may occur anywhere. However, it is preferable that the support-requiring place 3 where there is a concern that an accident may occur does not include places that are considered "socially unlikely to cause an accident." This reduces the effort required to build the place DB 55, which will be described later.

[0021] The support-requiring place 3 is, for example, a place where there is a risk of an accident if the support recipient 1 acts alone, but where an accident can be avoided if the support recipient 2 acts with support. The support-requiring place 3 is, for example, a place in each facility 30, such as a hospital, a nursing home, or a residence for elderly or physically disabled people. Because the facility 30 is home to elderly or physically disabled people, the risk of accidents is relatively higher than in other general facilities (for example, entertainment facilities, restaurants, residences where young people live, etc.). Therefore, being located in the facility 30 can reduce the risk of accidents. Specific examples of the support-requiring place 3 in each facility 30 are places where the support recipient 1 may change their posture, such as a toilet, a bed (room such as a bedroom), or a washroom.

[0022] The detection device 10 is a device that performs at least one of transmission and reception (sending and receiving radio waves) and imaging. By using such a device, it is possible to detect that the support recipient 1 has approached the support-requiring location 3. Examples of the transmission and reception device that performs transmission and reception include devices that perform one-way communication or two-way communication. However, in the example of the present disclosure, a device that can identify the support recipient 1, that is, that can identify who has approached the support-requiring location 3, is used as the detection device 10. Examples of the device that performs imaging (imaging device) include devices such as a camera and an image sensor. Note that when an imaging device is used, it is possible to detect which support recipient 1 has approached by recognizing, for example, the face, body shape, etc. of the support recipient 1 in an image or video.

[0023] In the example of the present disclosure, the detection device 10 is a transmitting / receiving device that performs one-way communication and includes identification devices 11 and 31. The identification device 11 is, for example, placed on an item (e.g., a wheelchair, a cane, etc.) carried by the support recipient 1 or moved together with the support recipient 1. The identification device 11 is, for example, a proximity beacon, a device that emits radio waves that transmit only over short distances such as Bluetooth (registered trademark), an RFID driven by induced current, a distance sensor, etc. On the other hand, the identification device 31 is, for example, a receiving device that receives radio waves emitted from the identification device 11. If the identification device 11 is a device that emits a proximity beacon, the identification device 31 is a device that receives the emitted proximity beacon. The identification device 31 is placed, for example, at the support-requiring location 3. This allows the detection device 10 to detect which support recipient 1 has approached the support-requiring location 3.

[0024] The notification device 32 is a device that issues a notification to those around the location where the notification device 32 is installed. The notification is preferably made in a way that is easy to understand (easy to recognize and understand) for the support recipient 1 and the supporter 2 who are the notification targets. As described above, the notification device 32 issues a notification when there is a high risk of an accident for the support recipient 1 approaching the support-requiring place 3. This allows people around the notification device 32, including the support recipient 1 himself, to know that there is a high risk of an accident for the support recipient 1 approaching the support-requiring place 3. This makes it possible, for example, to urge the support recipient 1 himself to act with sufficient caution in the support-requiring place 3. Furthermore, the supporter 2 around the notification device 32 can know that support is needed, and can support the support recipient 1 at the support-requiring place 3.

[0025] The alarm device 32 is, for example, a device that emits at least one of sound and light (or both) toward the periphery of the alarm device 32. Sound and light can travel long distances. Therefore, even if a supporter 2 (such as a caregiver, nurse, or staff member (supervisor, etc.)) is not present near the location where the alarm device 32 is installed (e.g., the support-requiring place 3), a supporter 2 who is far away can recognize the sound or light. This allows the supporter 2 who is far away to rush to the support-requiring place 3 and support the support recipient 1's actions at the support-requiring place 3. This reduces the risk of accidents. In particular, if the support-requiring place 3 is hidden, for example, by a structure and cannot be seen, the sound can be recognized by hearing.

[0026] The sound may be an alarm sound to warn or call attention to, or may be, for example, a voice calling out the name of the approaching support recipient 1. For example, by calling out the name of the support recipient 1 by voice, such as "Mr. / Ms. ~, please be careful" or "Mr. / Ms. ~, please wait until the supporter arrives," it is possible to directly call attention to the support recipient 1. Furthermore, if a light is used, for example, the same color may be emitted each time an alert is issued, or different colors of light may be emitted depending on the level of the accident risk.

[0027] The alarm device 32 is placed in a location that is determined to have a high accident risk in the location DB 55 (DB stands for database, and the same applies hereinafter. This is an example of a database). The location DB 55 is a database that stores at least one of information that affects the level of accident risk (hereinafter referred to as location information) for each support-requiring location 3, or the level of accident risk itself. First, the location DB 55 will be described.

[0028] Fig. 2 is a schematic diagram showing the location DB 55. Note that the contents (especially the recorded contents) of the location DB 55 shown in Fig. 2 may differ from the actual contents, and therefore the contents of the location DB 55 are not limited to the contents in Fig. 2. The same applies to the risk DB 52 and the risk DB 52 described below.

[0029] The location DB 55 is a database that stores (records) support-requiring locations 3 in association with the level of accident risk. Furthermore, the location DB 55 stores the location information for each support-requiring location 3. The location information includes, for example, the danger of the support-requiring location 3 and the number of accidents that actually occurred due to the danger (number of accidents). Of these, the greater the number of accidents, the higher the accident risk. Therefore, in the example of the present disclosure, the location DB 55 stores the number of accidents (part of the location information).

[0030] For example, the accident risk of a support-requiring place 3 with a relatively high number of accidents is high, the accident risk of a support-requiring place 3 with a relatively medium number of accidents is also medium, and the accident risk of a support-requiring place 3 with a relatively low number of accidents is low. The accident risk assigned to each support-requiring place 3 in the place DB 55 will be described in detail later, but may be determined, for example, by the supporter 2 or using a predetermined machine learning model.

[0031] For example, if support-requiring place 3 is a toilet, an example of the anticipated risk is that support recipient 1 will fall. For example, 10 cases are stored as the number of accidents involving falls in the toilet. Another anticipated risk is that support recipient 1 will fall and hit the toilet bowl. For example, 7 cases are stored as the number of such accidents. Therefore, it can be said that the risk of accidents in support-requiring place 3 is high.

[0032] Similarly, if support-requiring place 3 is a bed, for example, an expected risk could be, for example, an accident in which support recipient 1 falls and hits their body against the bed. The number of such accidents that have occurred is stored as, for example, 5. Therefore, the risk of accidents at support-requiring place 3 is medium. Furthermore, if support-requiring place 3 is a bathroom, for example, an expected risk could be, for example, an accident in which support recipient 1 falls and hits their body against the sink. The number of such accidents that have occurred is stored as, for example, 1. Therefore, the risk of accidents at support-requiring place 3 is low.

[0033] The level of accident risk differs depending on the actual circumstances, such as the design of the support-requiring place 3. Therefore, it is preferable that a location DB 55 is determined for each facility 30 that has a support-requiring place 3. Specifically, for example, it is preferable that in advance, in the facility 30, support-requiring places 3 that are empirically assumed to have a high risk of accidents by supporters 2 or the like are extracted, and the specific dangers present for each support-requiring place 3 are determined. Furthermore, if an accident should occur in a determined support-requiring place 3, it is also preferable to store the number of accidents as shown in FIG. 2. This can improve the reliability of the location DB 55.

[0034] For example, the supporter 2 or the like inputs location information (including the number of accidents) using the input device 61 via the input unit 57, for example, every predetermined period or every time an accident occurs, etc. In this way, the location DB 55 is updated.

[0035] Furthermore, when a facility 30 is newly established, the number of accidents at all support-requiring places 3 is zero. For this reason, it is preferable to determine the accident risk with reference to the number of accidents at support-requiring places 3 at other facilities 30. For example, it can be inferred that the accident risk at a support-requiring place 3 where the number of accidents is high at other facilities 30 will also be high at the facility 30 where the support system 100 is newly installed. For this reason, the supporter 2 or the like can input location information and accident risk for each support-requiring place 3 into the support device 50 via the input unit 57 using the input device 61. This allows a new location DB 55 to be constructed.

[0036] The level of accident risk can be objectively determined by a supporter 2 or the like based on, for example, the number of incidents. For example, if the number of accidents is equal to or greater than a predetermined value, the accident risk can be determined to be high, and if the number of accidents is less than the predetermined value, the accident risk can be determined to be low. Accident risk can also be determined, for example, using a machine learning model with location information as the explanatory variable and accident risk as the objective variable. When performing machine learning, it is preferable to perform machine learning using training data in which location information is labeled (annotated) with the level of accident risk. Any artificial intelligence model (for example, a convolutional neural network (CNN), a deep neural network (DNN), a recurrent neural network (RNN), etc.) can be used for machine learning.

[0037] Although the accident risk varies depending on the support recipient 1, in places where the supporter 2 or other supporters consider the risk of an accident to be high, the risk of an accident can be said to be relatively high for all support recipients 1, although the degree of risk may vary. For example, in a toilet, the interior of the toilet is relatively narrow, and there are many places where the support recipient 1 may hit their head if they fall, such as the edge of the toilet bowl or the edge of the hand wash basin. Furthermore, in the toilet, the support recipient 1 takes off and puts on clothes (pants, etc.). Therefore, a support recipient 1 who uses a wheelchair must stand up from their wheelchair, and a support recipient 1 who uses a cane must let go of their cane. Therefore, the interior of the toilet is an environment where falls are likely to occur. Therefore, by placing the alarm device 32 in such high-risk locations as described above, the occurrence of accidents in high-risk locations can be effectively reduced. Furthermore, since the alarm device 32 can be placed along the predetermined location DB 55, the effort required to determine the placement of the alarm device 32 can be reduced.

[0038] The information stored in the support device 50, the information obtained by the support system 100, and the like, including the contents of the place DB 55, are displayed on the display device 60 (an example of an output device). Display on the display device 60 is performed by the output unit 59. The display device 60 is, for example, a monitor, a display, a touch panel, or the like. Therefore, for example, the supporter 2 or the like can place the notification device 32 based on the contents of the place DB 55 displayed on the display device 60. When installing based on the place DB 55, for example, the notification device 32 may be installed in a support-requiring place 3 recorded as having a high accident risk, or in a support-requiring place 3 where the number of accidents is equal to or greater than the predetermined value (threshold) for the number of accidents that can be evaluated as having a high accident risk. Furthermore, the place DB 55 may be different for each facility 30 that has a support-requiring place 3, or may be common to all facilities 30.

[0039] 1, it is preferable that the notification device 32 is placed at the support-requiring location 3 as described above. This allows a support person 2 who is located away from the notification device 32 and notices the notification from the notification device 32 to intuitively head towards the support-requiring location 3 where the notification device 32 that issued the notification is located.

[0040] The notification device 32 notifies at least the support recipient 1. Therefore, the notification device 32 is placed in a position where the support recipient 1 in the support-requiring place 3 can notice it. This makes it possible to alert the support recipient 1 to take the above-mentioned precautions.

[0041] The position where the support recipient 1 notices it varies depending on the support-requiring place 3, but for example, it is within the range of movement of the support recipient 1 at the support-requiring place 3. That is, the notification device 32 is placed in a position where the support recipient 1 notices it (a position where it is easy to notice). For example, if the support-requiring place 3 is a toilet with a door, the notification device 32 can be attached around a handle or doorknob for opening and closing the door (for example, on the door itself).

[0042] The notification device 32 also notifies the supporter 2. As described above, the supporter 2 is a person who supports the support recipient 1 who has been notified. The notification device 32 is preferably placed in a position in the support-requiring place 3 where it can be easily noticed by the supporter 2 who is in a distant location. Specifically, it is preferable to place the notification device 32 in a position where it can be easily noticed by the supporter 2, such as on a wall or door at the entrance to the support-requiring place 3, such as a toilet, bedroom, or washroom, on the side facing a hallway. In this way, the supporter 2 who is in a distant location can head to the support-requiring place 3, and accidents that may occur when the support recipient 1 acts alone in the support-requiring place 3 can be reduced.

[0043] As will be described in detail later, when the support recipient 1 approaches the support-requiring place 3, in addition to being notified by the notification device 32 placed at the support-requiring place 3, a notification is also sent to the mobile communication terminal 21 as the notification device 32 carried by the supporter 2. As a result, even if the supporter 2 does not notice the notification from the notification device 32 placed at the support-requiring place 3, the supporter 2 can notice through the mobile communication terminal 21 carried by the supporter 2 that the support recipient 1 has approached the support-requiring place 3. The mobile communication terminal 21 is, for example, a mobile phone, a PHS, a smartphone, a tablet, etc.

[0044] The alarm device 32 may be placed at the support-requiring place 3 as described above, carried by the support person 2, or may be placed, for example, in the support person 2's station (for example, an office, nurse station, security room, etc. in a nursing home, hospital, etc.). Since there is usually someone at the station, an alarm issued at the station can alert someone to the approach to the support-requiring place 3. Furthermore, like the identification device 11, the alarm device 32 may be placed on an item (for example, a wheelchair, a cane, etc.) carried by the support recipient 1 or moved together with the support recipient 1. This can prevent the support recipient 1 from noticing the alarm from the alarm device 32.

[0045] The support device 50 is a device that, for example, determines the level of accident risk at the support-requiring place 3 for the support recipient 1 who approaches the support-requiring place 3, and builds a risk DB 52. The support device 50 determines the need for notification based on the built risk DB 52, and if notification is necessary, issues a notification to the notification device 32. By providing such a support device 50, it is possible to both prevent accidents from occurring and encourage the support recipient 1 to take voluntary action.

[0046] 3 is a block diagram showing the hardware configuration of the assistance device 50 of the present disclosure. The assistance device 50 is configured to include, for example, a CPU (Central Processing Unit) 1001, a RAM (Random Access Memory) 1002, a ROM (Read Only Memory) 1003, an I / F (Interface) 1004, and a bus 1005. The CPU 1001, RAM 1002, ROM 1003, and I / F 1004 are connected, for example, via the bus 1005. The assistance device 50 is realized by a predetermined control program (e.g., the assistance method of the present disclosure) stored in the ROM 1003 being loaded into the RAM 1002 and executed by the CPU 1001. Signals and information are exchanged between the assistance device 50 and various devices (e.g., the detection device 10, the alarm device 32, a server), an external network, etc., in terms of hardware, via the I / F 1004.

[0047] 1 , the support device 50 includes a detection unit 51, a risk DB 52, a notification determination unit 53, a notification execution unit 54, the location DB 55, the target DB 56, an input unit 57, a construction unit 58, and an output unit 59. At least a part (or all) of the functional units (detection unit 51, risk DB 52, notification determination unit 53, notification execution unit 54, location DB 55, target DB 56, input unit 57, construction unit 58, and output unit 59) constituting the support device 50 may be stored in a server (not shown, cloud, etc.) installed in a location remote from the facility 30.

[0048] The detection unit 51 is a functional unit that detects that the support recipient 1 has approached a support-requiring place 3. This detection includes identifying the support recipient 1 who has approached and the support-requiring place 3 that has been approached, i.e., which support recipient 1 has approached which support-requiring place 3. As described above, the detection is performed by inputting a detection signal from the detection device 10 (the identification device 31 in the illustrated example) to the detection unit 51.

[0049] The risk DB 52 is a database that stores the level of accident risk at the support-requiring place 3 for the support recipient 1 who is detected by the detection device 10 as approaching the support-requiring place 3. As described above, the accident risk is the risk that the support recipient 1 will have an accident at the support-requiring place 3. For ease of explanation, the risk DB 52 will be referred to first, and then the subject DB 56 used to build the risk DB 52 will be explained.

[0050] FIG. 4 is a schematic diagram showing the risk DB 52. The risk DB 52 is a database that stores support recipients 1, support-requiring locations 3, and the level of accident risk in association with each other. However, in FIG. 4, the level of accident risk is stored as the notification method. For example, when the accident risk is high, a "○" (circle) is recorded as a notification method using sound and light to further raise awareness. On the other hand, when the accident risk is medium, a "△" (triangle) is recorded as a notification method using sound only (or light only) to further raise awareness. For example, when the accident risk is low, support is not necessary, so an "×" (cross) is recorded as the notification method.

[0051] In the case of support recipient A, the alarm is set to sound and light in the toilet, which is support required place 3, because the risk of an accident is high. On the other hand, the alarm is not set to sound in a room (bedroom, etc.), which is support required place 3, because the risk of an accident is low. In the case of support recipient B, the toilet, which is support required place 3, has a medium accident risk, so a warning using only sound is made. On the other hand, in a room (bedroom, etc.), which is support required place 3, the risk of an accident is also medium, so a warning using only sound is made.

[0052] In the case of support recipient C, the toilet, which is support required place 3, has a medium accident risk, so an alarm is issued using only sound. On the other hand, in a room (such as a bedroom), which is support required place 3, the risk of an accident is low, so no alarm is issued. In the case of support recipient D, the risk of an accident is low in the toilet, which is support required place 3, so no notification is made. On the other hand, the risk of an accident is medium in a room (bedroom, etc.), which is support required place 3, so a notification using only sound is made.

[0053] By using this risk DB 52, it is possible to determine an objective and consistent accident risk, and it is possible to objectively evaluate "what kind of people, in what places, and what kind of actions lead to danger," thereby preventing accidents in support-requiring locations 3 where there is a risk of accidents.

[0054] Returning to FIG. 1 , the support device 50 includes the construction unit 58 as described above, and the construction unit 58 is a functional unit that constructs the risk DB 52. The construction unit 58 constructs the risk DB 52 using first information and second information. The first information is at least one of a predetermined accident risk for each support recipient 1 and information from the support recipient 1's past information that influences the level of the accident risk (subject information, described below). The first information is recorded, for example, in the subject DB 56, which will be described below. The second information is at least one of a predetermined accident risk for each support-requiring location 3 and information that influences the level of the accident risk (the above-mentioned location information). The second information is recorded, for example, in the above-mentioned location DB 55. Therefore, the construction unit 58 constructs the risk DB 52 using, for example, the location DB 55 and the subject DB 56. The construction unit 58 can associate the support recipient 1, the support-requiring location 3, and the level of accident risk, and can create the risk DB 52, which serves as a criterion for determining whether to issue a notification. The subject DB 56 in which the first information is recorded will be described below.

[0055] FIG. 5 is a schematic diagram showing the target DB 56. The target DB 56 is a database that stores, in association with each other, information from the support target 1's past information that influences the level of accident risk, and a predetermined level of accident risk. Hereinafter, information from the support target 1's past information that influences the level of accident risk will be referred to as target information. The target DB 56 stores, for each support target 1, the target information and the accident risk that has been determined in advance by the supporter 2, etc. The recorded accident risk has the same meaning as the accident risk explained with reference to FIG. 2 above.

[0056] The subject information includes signs of future accidents. For example, the older the subject, the higher the likelihood of an accident occurring in the future, and the higher the accident risk. From this perspective, the subject information to be stored for each support recipient 1 may include, for example, age, level of care required (or level of assistance required), residence history (e.g., in the case of a nursing home or care facility), vital signs (body temperature, blood pressure, etc.), and, although not shown, behavioral records (including ADLs (activities of daily living)) such as meals (menu, amount eaten, etc.) and excretion (time, number of times, etc.), accident reports, near misses, and other accident records (number, details, etc.). In addition, although not shown, images, videos, etc. captured by imaging devices such as cameras and image sensors may also be stored. Furthermore, the location, speed, posture, and facial expressions of the support recipient 1, which are acquired by analyzing and inferring from these images, videos, etc., may also be stored.

[0057] The subject information is, for example, chronological information (past information) that can be acquired by comparing the usual state of each support recipient 1 with the recent state of the support recipient 1. The subject information can be acquired, for example, by a supporter 2 such as a caregiver who continuously comes into contact with the support recipient 1 every day while using a facility 30 that has a support-requiring place 3. Alternatively, the subject information can be acquired automatically without bothering the supporter 2 by, for example, having the support recipient 1 wear a device (for example, a vital sensor) that acquires the subject information.

[0058] The accident risk assigned to each support recipient 1 in the recipient DB 56 may be determined, for example, by the supporter 2 or by using a predetermined machine learning model. When using a machine learning model, the accident risk can be determined using a machine learning model with the recipient information as the explanatory variable and the accident risk as the objective variable. Since the recipient information is past data and includes time-series data, it is preferable to use a recurrent neural network that is excellent at learning time-series features. Furthermore, from the perspective of learning a huge amount of recipient information over a long period of time, it is preferable to use a long-short-term memory (LSTM) model that is capable of long-term calculations.

[0059] Returning to FIG. 1 , the support device 50 includes an input unit 57. The input unit 57 is a functional unit that accepts input of subject information and appropriate accident risks. By including the input unit 57, the subject information and accident risks can be input to the support device 50, and a subject DB 56 can be constructed. Furthermore, by including the input unit 57, subject information can be input each time, for example, at predetermined intervals. This allows the subject DB 56 to be changed, for example, each time input is made, and the subject DB 56 can be "updated," so to speak. Furthermore, by recording the subject information in the subject DB 56, the supporter 2 can know who he or she needs to pay particular attention to.

[0060] In the risk DB 52, the construction unit 58 labels each support recipient 1, who is a person, as being high or low in accident risk. Therefore, a user such as a supporter 2 may intervene in labeling the high or low accident risk.

[0061] The support device 50 includes an output unit 59 and an input unit 57. The output unit 59 is a functional unit that outputs the accident risks stored in the risk DB 52 to a user (supporter 2, etc.). The output is performed, for example, by displaying on a display device 60. This allows the accident risks stored in the risk DB 52 to be proposed to the supporter 2, etc., and provides an opportunity for the supporter 2, etc. to modify the stored accident risks. The input unit 57 is a functional unit that receives input of accident risks by a user that are stored in the risk DB 52.

[0062] The construction unit 58 outputs the accident risk stored in the risk DB 52 to a user (a user of the support system 100; the same applies in the specification of the present disclosure), such as the supporter 2, via the output unit. At the same time, the construction unit 58 stores the accident risk input by the user via the input unit 57 in the risk DB 52. This allows for a more realistic accident risk to be assigned. Furthermore, the level of accident risk can be associated with a notification, allowing for an objective understanding of the criteria for whether or not to notify. This makes it possible to clearly indicate what kind of people and what kind of actions lead to danger. Therefore, accountability for the risk DB 52 to, for example, the support recipient 1, the supporter 2, etc. can be fulfilled. Furthermore, fulfilling accountability allows the supporter 2 to understand when and why a notification is issued, allowing for proper use of the support system 100.

[0063] In other words, the risk DB 52 is updated based on input by the user via the input unit 57. This allows for notification based on accident risks that are more in line with the actual situation.

[0064] The notification determination unit 53 is a functional unit that determines the necessity of notification by the notification device 32 for the support recipient 1 who has approached the support-requiring location 3, based on the level of the accident risk stored in the risk DB 52. By providing the notification determination unit 53, it is possible to determine the necessity of notification based on the level of the accident risk, and to issue a notification by the notification device 32 when it is determined that notification is necessary.

[0065] The notification execution unit 54 is a functional unit that executes notification by the notification device 32 when it is determined that notification is necessary by the notification determination unit 53. In this way, instead of issuing a uniform notification when the support recipient 1 approaches the support-requiring place 3, by varying whether or not to issue a notification depending on the level of the accident risk, it is possible to suppress unnecessary notifications to the support recipient 1 and promote spontaneous behavior by the support recipient 1.

[0066] In another embodiment, the notification execution unit 54 notifies in different ways depending on the level of the accident risk. In this way, the supporter 2 who is located far from the support-requiring place 3 can understand the level of accident risk from the notification method by the notification device 32 (the notification method shown in FIG. 4 above). For example, if the accident risk is high, the supporter 2 can hurry to the support-requiring place 3, but if the accident risk is not considered to be very high despite the notification, the supporter 2's convenience can be prioritized before heading to the support-requiring place 3, allowing for flexible responses.

[0067] Alternatively, for example, if the determined accident risk is a numerical value, a predetermined first threshold value that can be used to evaluate the accident risk as high and a predetermined second threshold value that can be used to evaluate the accident risk as medium are used. If the determined accident risk numerical value is equal to or greater than the first threshold value, there is a high possibility of an accident occurring or a serious accident occurring. Therefore, in this case, for example, the alarm device 32 uses both sound and light to notify the supporter 2 so that the supporter 2 can easily notice and not overlook the risk.

[0068] On the other hand, if the determined accident risk value is less than the first threshold and equal to or greater than the second threshold, there is a possibility that an accident may occur, but the possibility is not very high, or there is a possibility that a minor accident (including a near miss) may occur. Therefore, in this case, for example, the alarm device 32 issues an alert using only sound (or only light). Furthermore, if the determined accident risk value is less than the second threshold, it is considered that the possibility of an accident, including a minor accident, is low. Therefore, in this case, for example, the alarm device 32 does not issue an alert.

[0069] Fig. 6 is a flowchart showing the support method of the present disclosure. The support method of the present disclosure can be executed, for example, by the support system 100 shown in Fig. 1 above. Therefore, the explanation of Fig. 6 will be made with reference to Fig. 1 above as appropriate. Furthermore, the matters explained in relation to the support system 100 above can be similarly applied to the support method of the present disclosure shown in Fig. 6.

[0070] The support method of the present disclosure includes steps S1 to S3. First, the detection unit 51 detects that the support recipient 1 has approached a support-requiring place 3 where an accident is a concern (step S1: detection step). The detection here also includes identifying which support recipient 1 has approached the support-requiring place 3 (i.e., who approached where). Next, the notification determination unit 53 determines the need for notification for the support recipient 1 who has approached the support-requiring place 3 based on the level of accident risk stored in the risk DB 52 (step S2: notification determination step). As described above, the risk DB 52 is a database that stores the level of accident risk, which is the risk that the support recipient 1 detected to have approached the support-requiring place 3 in step S1 will have an accident at the support-requiring place 3.

[0071] If it is determined in step S3 that notification is necessary (Yes in step S3), the notification execution unit 54 executes notification to the surroundings using the notification device 32 (step S4, notification execution step). On the other hand, if it is determined in step S3 that notification is not necessary (No in step S3), the series of flows ends.

[0072] According to the support system 100 and the support method of the present disclosure, a notification is given when the support recipient 1 needs support at the support-requiring place 3, and a notification is not given when the support recipient 1 does not need support at the support-requiring place 3. This can encourage the support recipient 1 to take voluntary action. In addition, accidents involving the support recipient 1 can be prevented.

[0073] Furthermore, when there are support recipients 1 with different accident risks, the supporter 2 can know each time which support recipient 1 he or she should pay particular attention to. This reduces the burden on the supporter 2 and prevents accidents from occurring. Furthermore, during times when there are fewer support recipients 2 (for example, at night or early in the morning, on holidays, etc.), it is difficult for the supporter 2 to keep track of the actions of all support recipients 1. Therefore, by using the support system 100 and the support method of the present disclosure to issue a notification each time support is needed, accidents for the support recipients 1 can be prevented and the workload of the supporter 2 can be reduced.

[0074] Nursing homes, hospitals, homes for the elderly and physically disabled, construction sites, work sites, and the like, which serve as facilities 30, are home to support recipients 1 who are generally considered to be at high risk of accidents. Therefore, application of the support device 50 and the support method of the present disclosure to these facilities 30 is an area in which the effects of the present disclosure are particularly expected. [Explanation of symbols]

[0075] 1. Eligible recipients 10. Detection Device 100 Support System 11 Identification devices 2 supporters 21 Mobile communication terminal (alarm device) 3 Locations requiring support 30 facilities 31 Identification devices 32 Alarm device 50 Support equipment 51 Detection unit 52 Risk DB (Risk Database. Database) 53 Notification Judgment Department 54 Notification Department 55 Place DB (Place Database. Database) 56 Subject DB (Subject database. Database) 57 Input section 60 Display device 61 Input Device S1 step (detection step) Step S2 (notification decision step) S3 step (notification execution step)

Claims

1. a detection device that detects when a person requiring support approaches a support location where an accident is likely to occur; an alarm device that issues an alarm around a location where the alarm device is installed and is attached to the support-requiring location; and a support device; The support device includes: a risk database storing the level of accident risk of the support recipient himself / herself for each support required place, which is the risk that the support recipient detected by the detection device approaching the support required place will cause an accident at the support required place; and a notification determination unit that determines the necessity of notification by the notification device for the support target who has approached the support-requiring location based on the level of the accident risk stored in the risk database; a notification execution unit that, when it is determined by the notification determination unit that notification is necessary, executes notification by the notification device installed at the support-requiring location that the support recipient has approached; Equipped with A support system characterized by:

2. The assistance system according to claim 1, The detection device is a device that performs at least one of transmission and reception of radio waves, or imaging. A support system characterized by:

3. The assistance system according to claim 1, The alarm device is a device that emits at least one of sound and light toward the surroundings of the alarm device. A support system characterized by:

4. The assistance system according to claim 1, The risk database is a database that stores the support recipients, the support-requiring locations, and the level of the accident risk in association with each other, The support device includes: First information is at least one of the predetermined accident risk for each support recipient, or target information which is information that influences the level of the accident risk among past information of the support recipient; Second information is at least one of the predetermined accident risk for each support required location or the number of accidents, which is information that affects the level of the accident risk; a construction unit that constructs the risk database using When the first information includes the subject information, the level of the accident risk is determined using a machine learning model in which the subject information is an explanatory variable and the accident risk is a target variable; When the second information includes the number of accidents, the level of the accident risk is determined to be relatively high in the support-requiring location where the number of accidents is relatively high, and the level of the accident risk is determined to be relatively low in the support-requiring location where the number of accidents is relatively low. A support system characterized by:

5. 5. The assistance system according to claim 4, The support device includes: an output unit that outputs the accident risk stored in the risk database to a user; an input unit that receives input of the accident risk stored in the risk database from a user; Equipped with The construction unit outputting the accident risk stored in the risk database to the user through the output unit; The accident risk input by the user through the input unit is stored in the risk database. A support system characterized by:

6. The assistance system according to claim 5, The risk database is updated based on the input by the user through the input unit. A support system characterized by:

7. The assistance system according to claim 1, The notification device is installed at a location where the accident risk is determined to be high in a database that stores at least one of the number of accidents, which is information that affects the level of the accident risk for each support required location, or the level of the accident risk, and When the number of accidents is stored in the database, the level of the accident risk is determined to be relatively high in the support-requiring location where the number of accidents is relatively high, and the level of the accident risk is determined to be relatively low in the support-requiring location where the number of accidents is relatively low. A support system characterized by:

8. a detection step in which a detection unit detects that a support recipient has approached a support-requiring location where an accident is likely to occur; a notification determination step in which a notification determination unit determines the necessity of notification for the support recipient who has approached the support-requiring place based on the level of accident risk stored in a risk database that stores the level of accident risk of the support recipient himself / herself for each support-requiring place, which is the risk that the support recipient who has been detected as approaching the support-requiring place in the detection step will have an accident at the support-requiring place; and a notification execution step in which, when it is determined in the notification determination step that notification is necessary, a notification execution unit executes notification to the surroundings by a notification device attached to the support-requiring place that the support recipient has approached. A support method characterized by:

Images