Accident cause analysis system, accident report system, accident cause analysis method, accident report generation method, and control program

Abstract

To provide an accident cause analysis system that easily generates a cause of an accident and a countermeasure when an accident occurs.SOLUTION: An accident cause analysis system includes: a shooting unit that shoots a user; a determination unit 51 that determines a cause of an accident from a video related to the accident among video data shot by the shooting unit; a prompt generation unit 53 that generates a prompt related to the cause of the accident determined by the determination unit 51; and a countermeasure generation unit 52 that generates an accident countermeasure that is a countermeasure for the accident using the input prompt and a database in which accident causes and accident countermeasures are recorded.SELECTED DRAWING: Figure 6

Description

[Technical Field]

[0001] The present invention relates to an accident cause analysis system, an accident report system, an accident cause analysis method, an accident report generation method, and a control program. [Background technology]

[0002] Japan has seen a remarkable increase in life expectancy due to improvements in living standards, sanitary conditions, and medical standards that came with the rapid economic growth after the war. This, combined with a declining birth rate, has led to an aging society with a high aging rate. In such an aging society, it is expected that the number of people requiring care due to illness, injury, aging, etc. will increase.

[0003] People who require care may fall while walking or fall out of bed and injure themselves in facilities such as hospitals and elderly care facilities. Generally, such incidents are required to be reported as accidents.

[0004] Patent Document 1 discloses a technology for easily generating documents related to an accident when an accident such as a traffic accident involving a vehicle occurs. Patent Document 1 states (abstract): "An information processing system 100 has a first terminal that operates a platform for collecting accident-related information using a camera installed in the first terminal and transmits the information from the terminal to a first server, and the first server that generates documents related to the accident based on the information. In the event of an accident (a concept that includes both traffic accidents and vehicle troubles), the situation of the accident and documents necessary for accident processing are photographed, saved, and transmitted to an insurance company's server." [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2017-116998 Summary of the Invention [Problem to be solved by the invention]

[0006] The technology in Patent Document 1 makes it easy to create documentation after an accident occurs by recording the circumstances of the accident based on video footage captured by a camera, but it does not go so far as to allow for the investigation of the cause of the accident or countermeasures.

[0007] The present invention has been made in view of the above circumstances, and has as its object to easily generate the cause of an accident and countermeasures when an accident occurs. [Means for solving the problem]

[0008] The above object of the present invention can be achieved by the following means.

[0009] (1) a photographing unit that photographs the user; an identification unit that identifies a cause of an accident from a video related to the accident among the video data captured by the imaging unit; a prompt generation unit that generates a prompt regarding the cause of the accident identified by the identification unit; a countermeasure generation unit that generates an accident countermeasure, which is a countermeasure for the accident, using the input prompt and a database in which accident causes and accident countermeasures are recorded; An accident cause analysis system comprising:

[0010] (2) The accident cause analysis system described in (1) above, wherein the photographing unit photographs the user's room, including the bed, from a bird's-eye view.

[0011] (3) The accident cause analysis system according to (1) above, wherein the accident includes at least one of a fall accident, a pica accident, and aspiration accident.

[0012] (4) The accident cause analysis system according to (1) above, further comprising a determination unit that determines the occurrence of an accident from the video.

[0013] (5) The accident cause analysis system described in (4) above, wherein the judgment unit detects joint points of a person appearing in a video and determines the occurrence of an accident based on changes over time in the position of the joint points or the skeleton connecting the joint points.

[0014] (6) The accident cause analysis system according to (1) above, wherein the identification unit is a trained model.

[0015] (7) The accident cause analysis system described in (1) above, wherein the countermeasure generation unit includes a first trained model.

[0016] (8) The accident cause analysis system described in (7) above, wherein the countermeasure generation unit further includes a second trained model using a naturally trained model.

[0017] (9) The countermeasure generation unit outputs countermeasures for one or more accidents as countermeasure candidates; The accident cause analysis system described in (1) above further comprises a countermeasure candidate selection receiving unit that presents one or more output countermeasure candidate measures to a user and receives a selection by the user from among the presented countermeasure candidate measures.

[0018] (10) The accident cause analysis system described in (9) above, wherein the countermeasure candidate selection reception unit, when presenting the countermeasure candidate to the user, extracts past cases in which the countermeasure candidate was applied from the database and presents them as reference data in association with the countermeasure candidate.

[0019] (11) A photography unit that photographs the user; an identification unit that identifies information about a cause of an accident and a situation when the accident occurred from a video related to the accident among the video data captured by the imaging unit; a prompt generation unit that generates a prompt regarding the cause of the accident identified by the identification unit; a countermeasure generation unit that generates an accident countermeasure, which is a countermeasure for the accident, using the input prompt and a database in which accident causes and accident countermeasures are recorded; an input unit that inputs information about the countermeasures generated by the countermeasure generation unit and the situation when the accident identified by the identification unit occurred into a report; An accident reporting system comprising:

[0020] (12) The accident report system described in (11) above, wherein the photographing unit photographs the user's room, including the bed, from a bird's-eye view.

[0021] (13) The accident reporting system described in (11) above, wherein the accident includes at least one of a fall accident, a pica accident, and an aspiration accident.

[0022] (14) The accident report system according to (11) above, further comprising a determination unit that determines whether an accident has occurred from the video.

[0023] (15) The accident report system described in (14) above, wherein the judgment unit detects joint points of a person appearing in a video and determines the occurrence of an accident based on changes over time in the position of the joint points or the skeleton connecting the joint points.

[0024] (16) The accident report system described in (11) above, wherein the identification unit is a trained model.

[0025] (17) The accident report system described in (11) above, wherein the countermeasure generation unit includes a first trained model.

[0026] (18) The accident report system described in (17) above, wherein the countermeasure generation unit further includes a second trained model using a naturally trained model.

[0027] (19) The countermeasure generation unit outputs countermeasures for one or more accidents as countermeasure candidates; The accident report system described in (11) above further comprises a countermeasure candidate selection receiving unit that presents one or more output countermeasure candidate options to the user and receives the user's selection from among the presented countermeasure candidate options.

[0028] (20) The accident report system described in (19) above, wherein the countermeasure candidate selection reception unit, when presenting the countermeasure candidate to the user, extracts past cases in which the countermeasure candidate was applied from the database and presents them as reference data in association with the countermeasure candidate.

[0029] (21) An accident reporting system as described in (11) above, wherein the information regarding the circumstances of the accident obtained by the identification unit includes the date and time of the accident, the location, the name of the user involved in the accident, and the past circumstances of the user involved in the accident.

[0030] (22) A step (a) of identifying the cause of the accident from a video related to the accident among video data taken by the user; (b) generating a prompt related to the cause of the accident identified in (a); a step (c) of generating an accident countermeasure that is a countermeasure for the accident using the input prompt and a database in which accident causes and accident countermeasures are recorded; Accident cause analysis methods, including:

[0031] (23) A step (a) of identifying information about the cause of the accident and the circumstances surrounding the accident from a video related to the accident among video data taken by the user; (b) generating a prompt related to the cause of the accident identified in (a); a step (c) of generating an accident countermeasure that is a countermeasure for the accident using the input prompt and a database in which accident causes and accident countermeasures are recorded; Step (d) of entering information about the measures generated in step (c) and the circumstances under which the accident identified in step (a) occurred into a report; An accident report generation method comprising:

[0032] (24) A step (a) of identifying the cause of the accident from a video related to the accident among video data taken by the user; (b) generating a prompt related to the cause of the accident identified in (a); a step (c) of generating an accident countermeasure that is a countermeasure for the accident using the input prompt and a database in which accident causes and accident countermeasures are recorded; A control program for causing a computer to execute a process including the above.

[0033] (25) A step (a) of identifying information about the cause of the accident and the circumstances under which the accident occurred from a video related to the accident among video data taken by the user; (b) generating a prompt related to the cause of the accident identified in (a); a step (c) of generating an accident countermeasure that is a countermeasure for the accident using the input prompt and a database in which accident causes and accident countermeasures are recorded; Step (d) of entering information about the measures generated in step (c) and the circumstances under which the accident identified in step (a) occurred into a report; A control program for causing a computer to execute a process including the above. [Effects of the Invention]

[0034] The accident cause analysis system of the present invention includes a camera unit that films a user, an identification unit that identifies the cause of the accident from video related to the accident among video data filmed by the camera unit, a prompt generation unit that generates a prompt related to the cause of the accident identified by the identification unit, and a countermeasure generation unit that generates an accident countermeasure that is a countermeasure for the accident using the input prompt and a database in which the accident cause and accident countermeasures are recorded. This allows the user to easily identify the cause of the accident and the countermeasures for the accident simply by checking the generated information.

[0035] The accident report system of the present invention includes a camera unit that films a user, an identification unit that identifies the cause of the accident and information about the circumstances when the accident occurred from video data about the accident that is captured by the camera unit, a prompt generation unit that generates a prompt about the cause of the accident identified by the identification unit, a countermeasure generation unit that generates an accident countermeasure that is a countermeasure for the accident using the input prompt and a database that records the accident cause and accident countermeasures, and an input unit that inputs the countermeasure generated by the countermeasure generation unit and information about the circumstances when the accident occurred identified by the identification unit into a report. This allows a user to automatically generate an accident report that describes appropriate accident countermeasures. [Brief explanation of the drawings]

[0036] Advantages and features provided by one or more embodiments of the present invention will be more fully understood from the following detailed description and the accompanying drawings, which are for purposes of illustration only and are not intended to be limiting. [Figure 1] 1 is a schematic diagram illustrating an information processing system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a block diagram showing the configuration of a detection unit. [Figure 3] FIG. 2 is a block diagram showing the configuration of a control device. [Figure 4] FIG. 10 is a schematic diagram showing a person / object detection process and a joint point detection process performed based on photographic data. [Figure 5] FIG. 1 is a block diagram showing a configuration of an information processing device. [Figure 6] FIG. 2 is a schematic diagram showing the flow of various data in the first embodiment. [Figure 7] 1 is a flowchart illustrating a method for generating an accident report by an information processing system. [Figure 8] FIG. 10 is a diagram illustrating an example of an accident report. DETAILED DESCRIPTION OF THE INVENTION

[0037] Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the scope of the present invention is not limited to the disclosed embodiments. In the description of the drawings, the same elements are denoted by the same reference numerals, and duplicate explanations will be omitted. Furthermore, the dimensional proportions in the drawings are exaggerated for the convenience of explanation and may differ from the actual proportions.

[0038] 1 is a schematic diagram showing an information processing system 1000. The information processing system 1000 includes an information processing device 10, a detection unit 20, and a control device 30, and each device is connected to communicate with each other via a network 50. The information processing system 1000 functions as an accident cause analysis system or an accident report system.

[0039] The information processing device 10 is a server or a personal computer (PC). When the information processing device 10 is configured as a server, it may be an on-premise server installed in a nursing care facility or a cloud server using a commercial cloud service. The control device 30 is a PC operated by users such as nursing care staff (hereinafter simply referred to as staff) or administrators at the nursing care facility. The control device 30 is installed in the nursing care facility and functions as an edge server. The detection unit 20 will be described first, followed by the control device 30 and the information processing device 10. In the information processing system 1000 shown in FIG. 1, a detection unit 20 and a control device 30 are installed in multiple rooms in the nursing care facility. Each device in the nursing care facility is connected to the information processing device 10 via a network 50. That is, the information processing device 10 is connected to each device 20 and 30 in one nursing care facility. However, this is not limited thereto, and one information processing device 10 may be connected to multiple nursing care facilities, each of which has a control device 30 and multiple detection units 20.

[0040] Here, the term "accident" as used herein refers to an incident that occurs within a facility and affects the health and safety of facility users (hereinafter also referred to as care recipients). Accidents include falls, pica-eating incidents, and aspiration incidents. Falls are particularly incidents in which a care recipient breaks a bone or bleeds due to a fall, resulting in treatment at a medical institution (including medical treatment within the facility) or hospitalization. However, relatively minor injuries such as abrasions and bruises may be excluded. A pica-eating incident typically refers to an incident in which an inappropriate food or drink is put into the mouth. An aspiration incident is an incident in which food or drink accidentally enters the trachea. When something that should normally pass through the esophagus accidentally enters the trachea, there is a risk of choking and, as a complication, pneumonia.

[0041] (Detection unit 20) FIG. 2 is a block diagram showing the configuration of the detection unit 20. Referring to FIGS. 1 and 2, the detection unit 20 is configured to monitor the movements (behavior) of the care recipient 71 within the observation area (room), with the observation area being a room including a bed where the care recipient 71 is located in a nursing care facility. The care recipient 71 is a person receiving care and also a user residing in the nursing care facility. Care or nursing care is provided to the care recipient 71 by staff. The room is, for example, one room in a nursing care facility where multiple care recipients 71 reside. Furthermore, the information processing device 10 is connected to detection units 20 provided in each of the multiple rooms as shown in FIG. 1. The device ID of each detection unit 20 and the subject ID of the care recipient 71 to be monitored are associated and stored in a memory unit (memory unit 32 or memory unit 12a described below).

[0042] As shown in FIG. 2, the detection unit 20 includes a control unit 21, a communication unit 22, a camera 23, a sensor 24, a care call unit 25, etc. The detection unit 20 generates sensing data (video data, etc.) by constantly sensing the care recipient 71 in the observation area (room) in real time, 24 hours a day, using a plurality of various sensors. The control unit 21 may also include a large-capacity memory. The camera 23 and the sensor 24 are disposed in the main body of the detection unit 20. The main body is disposed on the ceiling or upper part of the wall of the room. The care call unit 25 is disposed separately from the main body and is communicatively connected to the main body via wired or short-range wireless communication.

[0043] The control unit 21 is composed of a CPU, RAM, ROM, etc., and controls each part of the detection unit 20 and performs calculation processing according to a program. The communication unit 22 is an interface circuit (for example, a LAN card, etc.) for communicating with other devices such as the control device 30 via the network 50.

[0044] The camera 23 is placed, for example, on the ceiling or upper part of the wall of the room, and captures an overhead image of the room of the user (care recipient 71), including the bed directly below as an observation area (photography area). By capturing an overhead image, the information processing system 1000 can detect movements that could lead to an accident involving the care recipient 71. The camera 23 is an example of a sensor that detects the movements of the care recipient 71 within the observation area. The room contains objects such as a bed (bed) 81 and a wheelchair 82. The camera 23 captures images of the care recipient 71, who is a person, as well as surrounding objects, and outputs the captured image data (video). The camera 23 is a near-infrared camera, but a visible light camera may be used instead, or both may be used. The camera 23 may also be a wide-angle camera.

[0045] The sensor 24 detects the movement of the care recipient 71. The sensor 24 includes various sensors other than the camera 23. For example, the sensor 24 may include at least one of a body movement sensor, a bed sensor, a mat sensor, a thermal sensor, and an infrared sensor. The "body movement sensor" may be a Doppler shift sensor that transmits and receives microwaves to and from the bed 81 and detects the Doppler shift of the microwaves caused by the body movement (e.g., breathing) of the care recipient 71. This body movement sensor detects chest movement (up and down movement of the chest) associated with the breathing of the care recipient 71. The period and amplitude of the body movement can be used to determine the sleep state or abnormal micro-movements (e.g., due to cardiac arrest). The "bed sensor" may be a sensor attached to the bed. For example, the bed sensor may detect weight and be placed on the bed 81 or on the floor at the exit of the bed 81 as an observation area to detect whether a person is standing on the sensor or to detect the sleep state. The "mat sensor" has the same function as the bed sensor, detecting the presence of a person in each divided area of ​​the floor. The "infrared sensor," also known as a human presence sensor, detects whether a person is present in the room. For example, the infrared sensor is placed throughout the room or on the bed 81 as its observation area.

[0046] The care call unit 25 includes a push button switch, and detects a care call when the care recipient 71 operates this switch.

[0047] (Control device 30) FIG. 3 is a block diagram showing the configuration of the control device 30. As shown in FIG. 3, the control device 30 includes a control unit 31, a memory unit 32, a communication unit 33, a display unit 34, and an operation input unit 35. The control unit 31 is composed of a CPU, RAM, ROM, etc., and controls each unit of the control device 30 and performs calculations according to a program. The control unit 31 functions as a determination unit 311. The memory unit 32 is composed of a hard disk, etc., which stores various programs and various data. The communication unit 33 is an interface circuit for communicating with other devices via the network 50. The display unit 34 is composed of an LCD display, a touch sensor, etc., and displays various information and an operation screen. The operation input unit 35 is an input device such as a keyboard and a mouse. The operation input unit 35 accepts inputs from staff members, staff leaders of units (also referred to as areas or groups in charge), and facility managers (hereinafter collectively referred to as managers, etc.). As will be described later, in the event of an accident, multiple accident prevention measures (potential measures) are presented to a user such as an administrator via the display unit 34 and the operation input unit 35, and the administrator is allowed to select the accident prevention measure to be applied from among the multiple accident prevention measures.

[0048] (Judgment unit 311) FIG. 4 is a schematic diagram showing the person / object detection process and the joint point detection process performed based on the captured image data.

[0049] (Human and object detection processing) The determination unit 311 detects a person rectangle 710 and object rectangles 810 and 820 corresponding to people and non-human objects, respectively, from the captured data using a person / object detection process described below. The person rectangle 710 is an area within a rectangle (dashed line frame) that includes the care recipient 71 in the captured data. The object rectangles 810 and 820 are areas within a rectangle (dashed line frame) that includes specific objects other than people (e.g., a bed, wheelchair, or chair).

[0050] In the person / object detection process, areas in the captured data where objects, including people, exist are detected as object presence areas, and a reliability score (also called likelihood; hereafter, the reliability score will be referred to simply as score) is calculated for each predetermined category of objects contained in the detected object presence areas. The score is the likelihood of the target object. The person / object detection process can calculate the score using known technology using a DNN (Deep Neural Network).

[0051] The predetermined category may be, for example, a person, a chair, furniture, and bedding. In the person / object detection process, the object existence region with the highest score in the person category is detected as a person rectangle 710. That is, in the person / object detection process, the care recipient 71 is detected as an object (moving object). Similarly, the object existence region with the highest score in a predetermined object category is detected as an object rectangle 820 (e.g., an object region of a wheelchair) of the category with the highest score.

[0052] Alternatively, as another example of a method for detecting the human rectangle 710, a background subtraction method may be used, which extracts the difference between the photographic data of the detection target and a background image of the photographic area that has been extracted in advance by the fixed camera 23. Alternatively, an inter-frame (temporal) subtraction method may be used, which extracts the difference between the photographic data of the detection target and the average of past photographic data.

[0053] By such human / object detection processing, coordinates (object position coordinates) on the shooting data calculated based on the object rectangle 810 of an object other than a human are output. This output coordinate information is stored in the storage unit 12 as time-series object information in association with each frame. The object position coordinates (object coordinates) may use the center position of the object rectangle or the positions of two or more vertices that are diagonally opposite each other.

[0054] (Joint point detection processing) In the joint point etc. detection process, a head rectangle 720 of the care recipient 71 and multiple feature points 730 (see FIG. 4 for both) are detected from the human rectangle 710. More specifically, in the joint point etc. detection process, an area including the head of the care recipient 71 is detected (estimated) as the head rectangle 720 from the human rectangle 710. In addition, in the joint point etc. detection process, feature points 730 including joints related to the body of the care recipient 71 are detected (estimated) from the human rectangle 710. In FIG. 4, the positions of the multiple feature points 730 are indicated by open circles. Note that thick lines connecting the joint points (between the feature points 730) indicate the skeleton (bones). The feature points 730 include, for example, the head, neck, shoulders, elbows, hands, waist, thighs, knees, and feet. The feature points 730 may include feature points 730 other than those described above, or may not include any of the above. In the joint point etc. detection process, the feature points 730 of the care recipient 71 can be estimated from the human rectangle 710 using a DNN that reflects a dictionary for detecting feature points 730 from the human rectangle 710. For example, in the joint point etc. detection process, the feature points 730 can be estimated using a known technique that uses a DNN. In the joint point etc. detection process, the feature points 730 can be output as their respective coordinates on the imaging data. The coordinates of the human rectangle 710, the head rectangle 720, and the feature points 730 (joint point coordinates, head coordinates) are associated with each other for each frame of the imaging data and stored in the storage unit 32 as chronological human information.

[0055] The determination unit 311 determines a person's behavior based on changes in the position of the person's joints or skeleton over time. The determination unit classifies behavior scenes using a trained model. This trained model is trained through supervised learning using time-series information on people (joint coordinates, head coordinates), object information (object position coordinates such as wheelchairs and beds), and correct labels for behavior scenes. For example, it is stored in the memory unit 32. This learning is performed using a recurrent neural network (RNN) or a hidden Markov model (HMM). The behavior scenes to be determined include getting up, getting out of bed, falling, and tripping. When a behavior scene is determined from the video data from the camera 23, it is notified to the staff as an event. In addition, the determined event is linked to the occurrence status, such as the time, room number, and name of the care recipient, and is recorded in an event list. The room number of the room can be obtained from the location information (room number) where the camera 23 is installed. The name of the care recipient can be traced using the room number and the user information shown below.

[0056] (Storage unit 32) The storage unit 32 stores video data, an event list, user information, staff information, care records, trained models, etc. The event list includes accident events such as falls and trips determined by the determination unit 311 (or events that are close to accidents but do not amount to accidents).

[0057] "User information" is information about the care recipient 71, including the room number in which the care recipient 71 resides, family information, the age, gender, medical history, and medical conditions of the care recipient 71. The user information also includes information about the care recipient's physical and mental condition and lifestyle. Examples of information about the physical and mental condition include the care recipient's 71 height, weight, and level of care required. The physical and mental condition may also include the care recipient's level of independent walking and the ability to transfer from the bed to a care chair. The physical and mental condition information may also include the resident's dementia level. The dementia level may be input by a facility manager or the like. Alternatively, the control device 30 may determine the care recipient's 71's level of unsteadiness while moving from images captured by the camera 23, and use this information to evaluate and determine the dementia level. Information about the resident's lifestyle includes the resident's activity level (travel time, travel distance), sleep time (life rhythm), number of care calls, etc. Medical history is past information about medical events and health, such as illnesses, injuries, surgeries, treatments, and allergies.

[0058] "Staff information" includes information such as staff name, affiliated unit, and work schedule.

[0059] "Nursing care records" include nursing record sheets, nursing record sheets (medical charts, life records), and diagnostic charts that record the care and treatment provided by staff, caregivers, nurses, and doctors (hereinafter referred to as "staff, etc.") who provide care to the care recipient 71. These records may be entered as text by scanning sheets handwritten by the staff, etc., and performing OCR processing. Alternatively, they may be entered by the staff, etc., through a staff terminal such as a smartphone that the staff, etc., carries while on duty. Care records include the amount of medication administered to the care recipient 71, medication care related to medication dosage, the amount of food eaten by the care recipient 71, dietary and hydration care related to fluid intake, the amount and quality of excretion, vital values ​​(body temperature, blood pressure, pulse rate, etc.), and the time of occurrence of these events.

[0060] The video data is acquired by the camera 23 of the detection unit 20 in each room. The video data is stored for a predetermined period of time. In addition, for an accident event, video data is linked to the event and recorded for a predetermined time before and after the accident (for example, one minute before and one minute after) and stored for a long period of time.

[0061] The trained model is used by the determination unit 311 as described above, and is useful for estimating joints and bones and classifying action scenes.

[0062] (Information processing device 10) The configuration of the information processing device 10 will be described below with reference to Fig. 5 and Fig. 6. Fig. 5 is a block diagram showing the configuration of the information processing device 10. Fig. 6 is a schematic diagram showing the flow of various data in the accident cause analysis system according to the first embodiment.

[0063] 5, information processing device 10 includes control unit 11, storage units 12a and 12b, and communication unit 13. Control unit 11 is composed of a CPU, RAM, ROM, etc., and controls and performs calculation processing on each unit of information processing device 10 according to a program. Control unit 11 functions as identification unit 51, measure generation unit 52, prompt generation unit 53, natural language model 54, measure candidate selection reception unit 55, and input unit 56.

[0064] The storage units 12a and 12b are configured with hard disks and the like that store various programs and various data. Hereinafter, these will be collectively referred to simply as storage unit 12. The storage units 12a and 12b may be configured separately. The storage unit 12 may also be an external database independent of the information processing system 1000. For example, this database may be a database centrally managed by the government that compiles cases of accidents at nursing care facilities across the country. By referring to cases of accidents at other nursing care facilities, more effective accident countermeasures can be obtained based on broader knowledge and insight rather than closed information. The communication unit 13 is an interface circuit for communicating with other devices via the network 50.

[0065] The memory unit 12a stores a predetermined accident report format (hereinafter simply referred to as a format). There are multiple types of formats corresponding to the respective destinations to which the accident report (hereinafter simply referred to as a "report") should be submitted. For example, the formats include (1) a format for submission to the address on the resident registration card of the person involved in the accident (care recipient 71), (2) a format for submission to the city, ward, town, or village (local government) where the facility where the accident occurred is located, and (3) a format for submission to the parent company that manages the facility. Depending on the nursing care facility, multiple types of formats may be applied to a single accident, and multiple reports to be submitted to different destinations may be generated. The memory unit 12a also stores multiple types of trained models 1 to 4, etc. The trained models will be described later.

[0066] (Control unit 11) (Specific part 51) The identification unit 51 identifies the cause of an accident for a specific event (a fall or a tumble) related to the accident among the events determined by the determination unit 311. The identification unit 51 acquires video data associated with the accident at the time of the accident. This video data is video data of a predetermined time associated with the accident event as described above.

[0067] The identification unit 51 identifies the cause of the accident from the video data using the trained model 1. This trained model is trained using training data that is a combination of video data and correct labels that indicate the cause of the accident. As shown in Figure 6, the identification unit 51 outputs the cause of the accident when video data is input. (1) For example, in the case of a fall accident, the care recipient 71 tries to grab a walker or cane when getting up from the bed, but the position of the walker or cane is far from the bed. In this case, the cause of the accident is that the care recipient loses balance while trying to grab the walker or cane, causing the fall. One way to prevent this accident is to move the walker or cane further back. (2) Another example is when a care recipient 71, who normally uses a walker to walk, falls while trying to move along the wall of their room without using the walker at night because it is too much hassle. In this case, the cause of the fall is the attempt to walk without using the walker. One way to prevent this is to add handrails to the wall. (3) If the care recipient 71 trips over a mat in the room and falls, the cause of the fall is the mat. One of the measures to prevent the accident is to change the mat. (4) If care recipient 71 loses his / her balance and falls while trying to put on slippers when getting out of bed, the cause of the fall is that the care recipient is not wearing slippers. One way to prevent the accident is to change the size of the slippers.

[0068] The identification unit 51 also acquires information on the accident situation. The information on the accident situation includes the date and time of the accident, the location of the accident (room number), the name of the person involved in the accident (name of the person receiving care), and the condition of the person involved. The condition of the person involved can be acquired from the user information stored in the memory unit 32. The condition of the person involved includes the medical history and past illnesses of the person receiving care. The condition of the person involved also includes information on the physical and mental condition. The information on the physical and mental condition includes, for example, the height, weight, level of care required, level of independent walking, level of ability to transfer from bed to a care chair by oneself, and level of dementia of the person receiving care 71.

[0069] (Countermeasure generation unit 52) The countermeasure generation unit 52 generates accident countermeasures based on the accident cause and accident circumstances obtained from the identification unit 51. The countermeasure generation unit 52 references a database of accident information. This database contains a large number of accident reports regarding accidents that have occurred at nursing care facilities, each of which describes the victim of the accident, an outline of the accident such as the circumstances of the accident, the cause of the accident, and measures to prevent recurrence of the accident (countermeasures). It is desirable that this database also includes records of accidents at facilities other than the nursing care facility where the information processing system 1000 is used. The trained model 3 (also referred to as the first trained model) used by the countermeasure generation unit 52 converts the information in this database into structured information, and extracts information on accidents that are highly similar to the accident cause and accident circumstances that have been input.

[0070] The countermeasure generation unit 52 outputs a plurality of countermeasures for accidents up to a predetermined number, for example, the top few (for example, top five) countermeasures for accidents in descending order of reliability score.

[0071] (Prompt generation unit 53) The prompt generation unit 53 generates a prompt to be input to the natural language model 54, which is an interactive system, based on the accident cause generated by the countermeasure generation unit 52. Generating an appropriate prompt enables the natural language model 54 to generate expected information and responses.

[0072] For example, the prompt generation unit 53 creates a sentence to be input based on the cause of the accident. For example, if the cause of the accident is a word, the sentence is created from that. Alternatively, the prompt generation unit 53 creates a sentence to be input by extracting related keywords from user information based on the cause of the accident or summarizing related information from the user information. The prompt generation unit operates using a rule-based algorithm or an algorithm that uses the trained model 2. The prompt generation unit 53 may also generate a prompt from the cause of the accident, taking into account the occurrence situation sent from the identification unit 51.

[0073] (Natural Language Model 54) The natural language model 54 is included in the countermeasure generation unit 52 and operates according to an algorithm that uses the trained model 4 (also referred to as the second trained model). In addition to the accident countermeasure statement generation function described below, the natural language model 54 may also function as a countermeasure generation unit that generates accident countermeasures, which are countermeasures for accidents, using an input prompt and a database in which the accident causes and accident countermeasures are recorded. The natural language model may be provided in an external system.

[0074] The natural language model 54 can apply a large-scale language model (LLM) using existing technology such as BERT (Bidirectional Encoder Representations from Transformers) as natural language processing. Using the natural language model 54, an accident countermeasure sentence to be entered in the accident report (hereinafter referred to as the accident countermeasure sentence) is output in response to an input prompt.

[0075] (Measure candidate selection reception unit 55) The candidate countermeasure selection receiving unit 55 presents to the user the accident countermeasure sentences that the natural language model 54 has generated and output by the countermeasure generation unit 52 and that are formatted in a report format for each of the multiple accident countermeasures, and receives a selection of an accident countermeasure to be applied from among them. For example, the candidate countermeasure selection receiving unit 55 displays multiple accident countermeasures on the display unit 34 for the user using the control device 30. The user selects an appropriate accident countermeasure from the multiple accident countermeasures (candidate accident countermeasures) through the operation input unit 35. For example, the candidate countermeasure selection receiving unit 55 may select the accident countermeasure with the highest score. Alternatively, in a nursing care facility, if the accident countermeasure with the highest score is difficult to apply due to the facility environment, such as the number of staff and costs, the next best accident countermeasure may be selected. The candidate countermeasure selection receiving unit 55 determines the received accident countermeasure as the final accident countermeasure. Note that two or more selections of accident countermeasures may be received. In this case, the multiple accident countermeasures are listed side by side in the report.

[0076] Furthermore, when presenting a plurality of accident countermeasure statements to the user, the countermeasure candidate selection receiving unit 55 may present past accident countermeasure examples recorded in the database of the storage unit 12b as past examples of each accident countermeasure for reference. In this case, the presented past examples preferably include information on the details of the accident, the cause of the accident, the accident countermeasure, and the accident situation. By referring to past examples, the user can confirm the validity of the accident countermeasure presented by the information processing system 1000. Furthermore, the user can refer to them when selecting one of the presented accident countermeasures.

[0077] (Input section 56) The input unit 56 inputs the accident countermeasures generated by the countermeasure generation unit 52 and determined by the countermeasure candidate selection receiving unit 55, and information regarding the accident circumstances at the time of the accident identified by the identification unit 51, into a report to generate the report. At this time, the input unit 56 generates the report using the accident countermeasure statements and the accident circumstances using an accident report format stored in the memory unit 12a. The input unit 56 may also be configured to accept additions and corrections by the user to the report generated by the system. The added and corrected report is output as the final report.

[0078] (Accident report generation process by information processing system 1000) Next, a method for generating an accident report performed by the information processing system 1000 will be described with reference to Figs. 7 and 8. Fig. 7 is a flowchart showing the method for generating an accident report performed by the information processing system 1000. Fig. 8 is an example of a generated accident report. The process of Fig. 7 may be started automatically every time the determination unit 311 determines that an accident has occurred, or may be started at a predetermined timing, for example, every day, in response to a start instruction from the user.

[0079] (Step S01) The detection unit 20 captures video using a camera 23 that captures a bird's-eye view of the care recipient 71. The determination unit 311 of the control device 30 determines the occurrence of an accident and records video data of a predetermined time before and after the accident, linking it to the accident. Hereinafter, the video data linked to the accident will also be referred to as accident video.

[0080] (Step S02) The identification unit 51 acquires the accident situation. As described above, the information on the accident situation includes the date and time of the accident, the location of the accident (room number), the name of the person involved in the accident (name of the person receiving care), the medical history of the person involved, the level of care required, and other conditions of the person involved.

[0081] (Step S03) The identification unit 51 identifies the cause of the accident from the accident video.

[0082] (Step S04) The input unit 56 acquires a preset accident report format from the storage unit 12a and inputs the accident situation and the accident cause. In the accident report shown in FIG. 8, the input unit 56 inputs the information on the accident situation acquired in step S02 into area A. The input unit 56 also inputs the accident cause identified in step S03 into area B. Note that the input results up to this point may be presented to the user, and a process may be performed to confirm the contents.

[0083] (Step S05) The control unit 11 inputs the accident situation and accident cause obtained in steps S02 and S03 to the countermeasure generation unit 52, thereby obtaining countermeasures for the accident as an output. For example, a plurality of countermeasures for the accident are output in descending order of the score.

[0084] (Step S06) The prompt generating unit 53 generates a prompt for input from each of a plurality of accident countermeasures.

[0085] (Step S07) The control unit 11 inputs the prompt generated in step S06 into the natural language model 54, and obtains, as an output, an accident countermeasure sentence relating to each accident countermeasure.

[0086] (Step S08) The countermeasure candidate selection receiving unit 55 presents a plurality of countermeasure statements to the user, receives a selection from the plurality of countermeasures, and determines the selected countermeasure as the final countermeasure.

[0087] (Step S09) In the accident report shown in FIG. 8, input unit 56 inputs, in area C, the accident countermeasure statement regarding the accident countermeasure received in step S08.

[0088] (Step S10) After the input is completed, the control unit 11 outputs the report. For example, it transmits the report to a predetermined destination or stores it in the storage unit 32.

[0089] As described above, the accident cause analysis system according to this embodiment includes a camera unit that films a user, an identification unit that identifies the cause of an accident from video related to the accident among the video data captured by the camera unit, and a prompt generation unit that generates a prompt related to the cause of the accident identified by the identification unit. The accident cause analysis system also includes a countermeasure generation unit that generates an accident countermeasure, which is a countermeasure for the accident, using the input prompt and a database that records the accident cause and accident countermeasures. This allows the user to easily generate the cause of an accident and its countermeasure when an accident occurs, simply by checking the generated information.

[0090] The accident report system according to the present embodiment includes a camera unit that films a user, an identification unit that identifies the cause of the accident and information about the circumstances surrounding the accident from video data related to the accident captured by the camera unit, and a prompt generation unit that generates a prompt related to the cause of the accident identified by the identification unit. The accident report system also includes a countermeasure generation unit that generates a countermeasure for the accident using the input prompt and a database that records the cause of the accident and the accident countermeasures, and an input unit that inputs the countermeasure generated by the countermeasure generation unit and information about the circumstances surrounding the accident identified by the identification unit into a report. This makes it possible to generate the cause of the accident and the countermeasure when an accident occurs, and to automatically generate an accident report that describes appropriate accident countermeasures.

[0091] The configuration of the information processing system 1000 described above is a main configuration for explaining the features of the above embodiment, but is not limited to the above configuration and can be modified in various ways within the scope of the claims. Furthermore, configurations that are included in general information processing systems are not excluded.

[0092] 1 and the like, the control device 30 and the information processing device 10 are described as separate entities, but they may be integrated. For example, the control device 30 functions as the information processing device 10. Alternatively, the functions of the determination unit 311 of the control device 30 may be provided on the control unit 11 side of the information processing device 10.

[0093] Furthermore, the means and methods for performing various processes in the information processing device or information processing system according to the above-described embodiments can be realized by either a dedicated hardware circuit or a programmed computer. The program may be provided, for example, by a computer-readable recording medium such as a USB memory or a DVD (Digital Versatile Disc)-ROM, or may be provided online via a network such as the Internet. In this case, the program recorded on the computer-readable recording medium is typically transferred and stored in a storage unit such as a hard disk. The program may also be provided as standalone application software, or may be incorporated as a function into the software of a device such as a detection unit.

[0094] While embodiments of the present invention have been described and illustrated in detail, the disclosed embodiments are made for purposes of illustration and example only and are not intended to be limiting, and the scope of the present invention should be construed by the language of the appended claims. [Explanation of symbols]

[0095] 1000 Information Processing Systems 10. Information processing equipment 11 Control section 51 Specific part 52 Countermeasure Generation Unit 53 Prompt Generation Unit 54 Natural Language Models 55 Countermeasure candidate selection reception section 56 Input section 20 Detector 21 Control section 22 Communications Department 23 Camera 24 sensors 25 Care Call Department 30 Control device 31 Control Unit 311 Judgment section 32 Storage section 33 Communications Department 34 Display section 35 Operation input section

Claims

1. a photographing unit that photographs the user; an identification unit that identifies a cause of an accident from a video related to the accident among the video data captured by the imaging unit; a prompt generation unit that generates a prompt regarding the cause of the accident identified by the identification unit; a countermeasure generation unit that generates an accident countermeasure, which is a countermeasure for the accident, using the input prompt and a database in which accident causes and accident countermeasures are recorded; An accident cause analysis system comprising:

2. The accident cause analysis system according to claim 1 , wherein the photographing unit photographs the user's room including the bed from a bird's-eye view.

3. The accident cause analysis system according to claim 1 , wherein the accident includes at least one of a fall accident, a pica accident, and an aspiration accident.

4. The accident cause analysis system according to claim 1 , further comprising a determination unit that determines the occurrence of an accident from the video.

5. 5. The accident cause analysis system according to claim 4, wherein the determination unit detects joint points of a person appearing in a video, and determines whether an accident has occurred based on changes over time in the positions of the joint points or the skeleton connecting the joint points.

6. The accident cause analysis system according to claim 1 , wherein the identification unit is a trained model.

7. The accident cause analysis system according to claim 1 , wherein the countermeasure generation unit includes a first trained model.

8. The accident cause analysis system according to claim 7 , wherein the countermeasure generation unit further includes a second trained model using a naturally trained model.

9. the countermeasure generation unit outputs countermeasures for one or more accidents as countermeasure candidates; The accident cause analysis system according to claim 1 , further comprising a countermeasure candidate selection receiving unit that presents the output one or more countermeasure candidate to a user and receives a selection by the user from among the presented countermeasure candidate.

10. 10. The accident cause analysis system according to claim 9, wherein the countermeasure candidate selection receiving unit, when presenting the countermeasure candidate to the user, extracts past cases in which the countermeasure candidate was applied from the database and presents the cases in association with the countermeasure candidate as reference data.

11. a photographing unit that photographs the user; an identification unit that identifies information about a cause of an accident and a situation when the accident occurred from a video related to the accident among the video data captured by the imaging unit; a prompt generation unit that generates a prompt regarding the cause of the accident identified by the identification unit; a countermeasure generation unit that generates an accident countermeasure, which is a countermeasure for the accident, using the input prompt and a database in which accident causes and accident countermeasures are recorded; an input unit that inputs information about the countermeasures generated by the countermeasure generation unit and the situation when the accident identified by the identification unit occurred into a report; An accident reporting system comprising:

12. The accident report system according to claim 11 , wherein the photographing unit photographs the user's room including the bed from a bird's-eye view.

13. The accident reporting system according to claim 11 , wherein the accident includes at least one of a fall accident, a pica accident, and an aspiration accident.

14. The accident report system according to claim 11 , further comprising a determination unit that determines the occurrence of an accident from the video.

15. The accident report system according to claim 14 , wherein the determination unit detects joint points of a person appearing in a video and determines whether an accident has occurred based on changes over time in the positions of the joint points or the skeleton connecting the joint points.

16. The accident report system of claim 11 , wherein the identification unit is a trained model.

17. The accident report system of claim 11 , wherein the countermeasure generator includes a first trained model.

18. The accident report system according to claim 17 , wherein the countermeasure generation unit further includes a second trained model using a naturally trained model.

19. the countermeasure generation unit outputs countermeasures for one or more accidents as countermeasure candidates; The accident report system according to claim 11, further comprising a countermeasure candidate selection receiving unit that presents the output one or more countermeasure candidate to a user and receives a selection by the user from among the presented countermeasure candidate.

20. The accident report system of claim 19, wherein the countermeasure candidate selection receiving unit, when presenting the countermeasure candidate to the user, extracts past cases in which the accident countermeasure candidate was applied from the database and presents the cases in association with the countermeasure candidate as reference data.

21. The accident report system of claim 11, wherein the information regarding the circumstances of the accident obtained by the identification unit includes the date and time of the accident, the location, the name of the user involved in the accident, and the past circumstances of the user involved in the accident.

22. A step (a) of identifying the cause of an accident from a video related to the accident among video data taken by a user; (b) generating a prompt related to the cause of the accident identified in step (a); a step (c) of generating an accident countermeasure that is a countermeasure for the accident using the input prompt and a database in which accident causes and accident countermeasures are recorded; Accident cause analysis methods, including:

23. A step (a) of identifying information about the cause of an accident and the circumstances under which the accident occurred from a video related to the accident among video data taken by a user; (b) generating a prompt related to the cause of the accident identified in step (a); a step (c) of generating an accident countermeasure that is a countermeasure for the accident using the input prompt and a database in which accident causes and accident countermeasures are recorded; Step (d) of inputting information about the countermeasures generated in step (c) and the circumstances under which the accident identified in step (a) occurred into a report; An accident report generation method comprising:

24. A step (a) of identifying the cause of an accident from a video related to the accident among video data taken by a user; (b) generating a prompt related to the cause of the accident identified in step (a); a step (c) of generating an accident countermeasure that is a countermeasure for the accident using the input prompt and a database in which accident causes and accident countermeasures are recorded; A control program for causing a computer to execute a process including the above.

25. A step (a) of identifying information about the cause of an accident and the circumstances under which the accident occurred from a video related to the accident among video data taken by a user; (b) generating a prompt related to the cause of the accident identified in step (a); a step (c) of generating an accident countermeasure that is a countermeasure for the accident using the input prompt and a database in which accident causes and accident countermeasures are recorded; Step (d) of inputting information about the countermeasures generated in step (c) and the circumstances under which the accident identified in step (a) occurred into a report; A control program for causing a computer to execute a process including the above.

Images