JP2006215680A - Erroneous work warning system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an erroneous work warning system capable of selecting whether to issue a warning depending on the details of erroneous work. <P>SOLUTION: Based on a variety of monitor information, a server determines whether or not the details and procedure of a work to be performed by a worker are right. When determining that the worker is going to make an erroneous work (step S1-S3), the server determines whether or not it is appropriate to issue a warning to the worker according to the monitor information at that time (step S4). For example, if there is the possibility that issuing a warning could lead to another error, no warning is issued. If it is determined that it is possible to warn the worker, the server drives a vibrator, a speaker, a red turning light and the like to issue a warning to the worker (step S7, S8). No warning is issued if it is determined that it is not possible to issue a warning to the worker. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to an erroneous operation warning system, and in particular, for example, when a work having a content determined in accordance with a predetermined procedure, such as a nurse, a caregiver, or a process worker, is performed, the procedure or the content is incorrect. In this case, the present invention relates to an erroneous operation warning system that alerts a person who tries to perform the erroneous operation or issues an alarm.

Various systems and methods for preventing medical accidents and nursing accidents have been proposed. One of them is a behavior analysis system disclosed in Patent Document 1. In this behavior analysis system, it is possible to determine the possibility of an accident by comparing the current behavioral data of nurses with dictionary data registered in advance, and there is a possibility that an accident will occur In some cases, a warning is issued to avoid this.
JP 2004-157614 [G06F 17/60 A61B 5/107 5/11]

  In the system in Patent Document 1, for example, if it is a nurse, by issuing a warning with a buzzer or vibrator (vibrator) that each person wears or holds, or a red light or speaker installed in a hospital room or hallway, It is possible to prevent the occurrence of a predicted accident.

  However, when using a vibrator, for example, when the nurse is about to perform an injection or other action on a patient and the vibration of the vibrator is suddenly transmitted to the nurse, the nurse senses the vibration. You might be upset and make a mistake. Therefore, in this case, it may be necessary not to issue an alarm to the nurse at that time.

  Therefore, a main object of the present invention is to provide a novel erroneous operation warning system.

  Another object of the present invention is to provide an erroneous operation alarm system that can select whether or not to issue an alarm according to the content of an erroneous operation even if there is an erroneous operation.

  According to the first aspect of the present invention, the worker tries to make an erroneous work by the work situation recognition means for recognizing the worker's work situation based on the monitor information obtained by monitoring the worker's work situation. State determination means for determining whether or not it is possible to warn the worker when it is recognized, and an alarm for giving an alarm to the worker when the state determination means determines that the worker can be alerted This is an erroneous work warning system in which a warning means is not provided when the status judgment means judges that the worker is not in a state capable of warning the worker.

  In the invention of claim 1, monitors such as an objective sensor (22), a sound collecting microphone (24), a video camera (28), a pedometer (54), an inclination angle sensor (58), a tag reader (72) and the like in the embodiment. Various monitor information from the means is collected by work status recognition means constituted by, for example, the server (12), and the work status recognition means determines whether the work contents and work process at that time are correct based on the monitor information. By detecting, it is recognized whether the work of the worker being monitored is an erroneous work (steps S1 to S3). When the work status recognition means recognizes an erroneous work, for example, the state determination means configured by the server (12) determines whether or not the worker can be alerted (step S4). This state determination means determines whether or not an alarm can be issued to the worker by determining whether or not there is a possibility of causing another mistake by giving an alarm, for example. When the state determination unit determines that the worker can be alerted, for example, the server (12), which constitutes a part thereof, gives a warning to the worker (steps S7 and S8). Further, when the state determination means determines that the worker is not in a state capable of alarming, the alarm means is not activated (step S5).

  Therefore, according to the first aspect of the present invention, in the case where giving an alarm affects an operator's work, no alarm is given, so that another error is not induced by the alarm, for example.

  The invention of claim 2 is such that the alarm means can give an alarm by different methods, and further comprises an alarm method determining means for determining the alarm method of the alarm means according to the work situation, the alarm means being an alarm The erroneous operation alarm system according to claim 1, wherein an alarm is given to an operator by an alarm method determined by the method determination means.

  In the invention of claim 2, the alarm means is configured to be capable of alarming in a different method or manner such as a vibration method, a light method, a voice method, etc., and is configured by a server (12), for example. The method determining means is based on the recognized work situation, for example, whether the worker is working alone, working with another person, whether the worker's work partner is nearby, One or more alarm methods are determined. Therefore, the warning means gives a warning to the worker by the warning method determined by the warning method determination means.

  According to the invention of claim 2, an alarm can be given to the worker by an alarm method most suitable for the work situation at that time.

  The invention of claim 3 further comprises a serious accident judging means for judging whether the erroneous work leads to a serious accident when the state judging means judges that it is not in a state capable of alarming the worker, and the serious accident judging means The erroneous operation alarm system according to claim 1 or 2, wherein an alarm means is activated when it is determined that an erroneous operation leads to a serious accident.

  In the invention of claim 3, for example, the server (12) constitutes a serious accident determination means. This serious accident determination means (step S5) is, for example, whether or not the adverse effect caused by continuing the erroneous work without warning is greater than the harmful effect caused by the error that may be triggered by issuing the warning. To determine whether there is a possibility of a serious accident.

  According to the invention of claim 3, even when it is not appropriate to issue an alarm, an alarm is issued when the result of erroneous work may lead to a serious accident. It can be prevented beforehand.

  The invention according to claim 4 is the erroneous operation alarm system according to any one of claims 1 to 3, wherein the alarm method includes at least one of a vibration method, a light method, and a sound method.

  The invention according to claim 5 is a work situation recognition step for recognizing the worker's work situation based on monitor information obtained by monitoring the work situation of the worker, and the worker tries to perform an erroneous work in the work situation recognition step. When it is recognized that the alarm can be given to the worker, a state determination step for determining whether or not the worker can be alerted, and when it is determined that the worker can be alerted in the state determination step, the worker is alerted by an alarm means. This is a false work warning method that includes a warning step that gives a warning, and that the warning is not given by the warning means when it is determined that the worker is not in a state capable of warning the worker in the state judgment step.

  In the invention of claim 5, the same effect as that of the invention of claim 1 can be expected.

  According to the present invention, even if there is an erroneous operation, an alarm that affects the operator's operation is not given, so that, for example, another error is not induced by the alarm.

  The above object, other objects, features and advantages of the present invention will become more apparent from the following detailed description of embodiments with reference to the drawings.

  Referring to FIG. 1, a nursing accident warning monitor system 10 according to an embodiment of the present invention is applied to a hospital, for example, and includes a server 12. The server 12 is connected to a plurality of nurse terminals (hereinafter simply referred to as “terminals”) 16 and a plurality of stations 18 via a wired or wireless communication line (network) 14. The terminal 16 is a computer such as a personal computer or a workstation, and is assigned to each nurse. For example, the terminal 16 is installed in a nurse's station. However, a single terminal 16 may be used by several nurses. Each of the plurality of stations 18 is in a ward that accommodates inpatients, and is disposed at predetermined positions such as a corridor, a hospital room (entrance, bed, or the vicinity thereof), and a nurse's station, and is capable of wireless communication. Hereinafter, the identification information of 20 is simply acquired and transmitted to the server 12. Each of the plurality of sensor units 20 is assigned (attached) to a nurse, and the identification information of the sensor unit 20 is detected by the station 18 that exists in a wirelessly communicable range (for example, a radius of 3 to 5 meters). . Further, since the station 18 and the sensor unit 20 can communicate with each other, the sensor unit 20 detects identification information (station ID) of the station 18 existing in a range where wireless communication is possible. Although illustration is omitted, since the sensor units 20 can wirelessly communicate with each other, the two or more sensor units 20 existing in a wireless communicable range detect mutual identification information. You can also. The sensor unit 20 may be directly connected to the network 14 by a wireless LAN.

  FIG. 2 is a block diagram showing a specific configuration of the server 12. Referring to FIG. 2, the server 12 includes a plurality of objective sensors 22 and a plurality of sound collecting microphones 24, which are omitted in FIG. Is connected. The objective sensor 22 is installed in a take-out portion of a storage box storing a medical instrument such as a thermometer, a blood pressure monitor, a syringe, a drip syringe (injector), a blood collection test tube, a urinalysis cup, a nurse call terminal, etc. The presence or absence of use (removal) of these medical devices is detected. However, identification information such as tag information or a barcode may be added to these medical instruments and the presence or absence of use may be detected by reading the tag information or barcode.

  Further, the sound collecting microphone 24 is installed, for example, in a hospital room 26 shown in FIG. 3, and captures voices of patients and nurses in the hospital room 26 as well as ambient sounds such as sound generated by them. However, such a sound collecting microphone 24 is installed not only in the hospital room 26 but also in an arbitrary place in the ward such as a corridor, a hand-washing room, a toilet, and a bathroom.

  A video camera 28 is further installed in the hospital room 26 shown in FIG. This video camera 28 is used to record the actions of the nurse and to record the state of the patient. The moving image and still image data from each video camera 28 is given to the server 12, and the server 12 accumulates and analyzes the video in a database. The video camera 28 can also be installed, for example, in nursing stalls, hallways, and the like.

  The sound collection microphone 24 and the video camera 28 are a part of monitor means for monitoring the nurse's work status, and the audio information from the sound collection microphone 24 and the video information from the video camera 28 form monitor information. Similarly, the objective sensor 22 can also be a part of the monitoring means for outputting monitor information, and the server 12 uses the information from the objective sensor 22 to determine who is going to take out or use the medical instrument or the like. Can know.

  Similarly, a light emitting alarm device 30 such as a red light, and a sound alarm device 32 such as a buzzer or a speaker, which are examples of alarm means, are provided in a hospital room 26, a nursing place, a hallway, or the like. The light emission alarm 30 emits a flash to give an alarm to the nurse, and the voice alarm 32 gives an alarm to the nurse or the like with a buzzer sound, a synthesized voice or a human voice recorded in advance.

  The patient room 26 is further provided with a bed 34 for a patient. The bed 34 is additionally provided with an RF tag 36 in which an identification number (ID) of the bed is set. For example, the ID “abcd1111” is set in the RF tag 36 to indicate that the bed 34 of the hospital room has a unique ID of “abcd1111”, for example. By detecting the ID of the RF tag 36, it is possible to determine which patient the bed 34 belongs to. A similar RF tag 36 is also attached to the chemical container 38. This chemical container 38 is provided. If the ID of the chemical container is, for example, “xyz 99999”, the RF tag 36 has a setting of the ID “xyz 99999”. By detecting the ID of the RF tag 36, it is possible to determine which medicine the medicine container 38 belongs to.

  Such an RF tag 36 is read by, for example, a tag reader 72 (FIG. 4) worn by a nurse. Therefore, these tags 36 and the tag reader 72 that reads them also function as monitoring means for providing monitor information.

  Although omitted in FIG. 1, a plurality of databases (databases) are connected to the server 12 as shown in FIG. 2. Specifically, a nurse database 40, a ward event database 42, a location information database 44, an electronic medical record database 46, and a knowledge database 48 are connected.

  The nurse database 40 records data (nurse data) on the nurse's daily work behavior for each nurse. In the nurse data, for example, a nurse name is described as a label, and a date is described next to the nurse name. Below the nurse name and date, items (contents) related to the nursing work of the nurse are described. In other words, the start time of nursing work, the end time of nursing work, the target patient of nursing work, the contents of nursing work, the number of steps in nursing work, the average value of the inclination (inclining the upper body (body)) and the medical error in nursing work Accidents (accidents / incidents) in business such as Such nurse data is basically obtained from data measured by the sensor unit 20.

  The ward event database 42 includes a plurality of sensors, that is, object detection data obtained from the plurality of objective sensors 22 described above, audio data obtained from the plurality of sound collecting microphones 24, and video data obtained from the video camera 28 (collecting these data). Record the “ward event data”). Identification information such as the name of a medical instrument to be detected is attached to the object detection data as a tag. Identification information indicating the installation location of the sound collecting microphone 24 is attached to the audio data as a tag. Identification information indicating the installation location of the video camera 28 is attached to the video data as a tag. That is, the detection target can be specified from the objective detection data, and the place where the sound is collected or the video is acquired from the tag of the audio data or the video data can be specified.

  Furthermore, the server 12 acquires the time (time data) at which the ward event data such as information is acquired from the built-in clock circuit 12a, and adds it to the ward event data.

  For example, when objective detection data is input, the server 12 adds time data to the objective detection data and records it in the ward event database 42. The sound collecting microphone 24 is intended to collect, for example, a sound generated when an object falls or a loud voice uttered by a human, so that when a sound of a predetermined level or higher is input, the sound collecting microphone 24 Is input to the server 12, and the server 12 adds time data to the sound data and records it in the ward event database 42. However, although it is basically time-lapse (intermittent recording), video data is accumulated in time series.

  In the location information database 44, location information data (location information data) about the nurse is recorded. As will be described in detail later, the location information data includes identification information (nurse ID) such as tag information assigned to the sensor unit 20 worn by each nurse and the station 18 that detects the nurse ID. The tag information, that is, the identification information (station ID) is recorded in time series. Further, as described above, since the station 18 and the sensor unit 20 communicate with each other, the location information data includes data in which the station ID detected by the sensor unit 20 is recorded in time series. Further, as described above, the sensor units 20 can communicate with each other wirelessly, and the nurse ID assigned to each sensor unit 20 and the nurse ID of the sensor unit wirelessly communicated with the sensor unit 20 are recorded in time series. Data is also included. With this location information data, the location (action) of the nurse can be known. For example, you can know where (how many times, minutes and seconds) you were (patient room, station, corridor, etc.), and what time, minutes, and seconds you were with or who passed you. it can.

  The electronic medical record database 46 records an electronic medical record about a patient currently hospitalized or being treated. Although illustration is omitted, this electronic medical chart is obtained by extracting necessary items from the contents of the medical chart described by a doctor or the like and adding necessary items to electronic data. For example, the electronic medical record includes the patient name, the name of the nurse in charge (nurse category number), gender, disease name, medical condition, prescription (prescription of what kind of injection, infusion, or medication), rehabilitation status, hospitalization Information data (text data) such as a calendar and precautions for the patient is described, and a patient category number for the patient is attached to the text data as a label. Therefore, when a patient is specified, an electronic medical record for the patient can be specified according to the patient category number.

  The knowledge database 48 includes a work content recognition dictionary (template) that can recognize, for example, the work content performed by the nurse from the video information and audio information acquired by the server 12, and the process performed by the nurse at that time, for example. Various recognition dictionaries such as a work process recognition dictionary (template) that can determine whether (procedure) is correct or not are included. Therefore, the server 12 works on the monitor information inputted at that time from the monitor means, for example, the sound from the sound collecting microphone 24, the image from the video camera 28, the tag ID from the objective sensor 22 or the tag reader 72 (described later), and the like. By collating with the template of the content recognition dictionary, it is possible to recognize the work content that the nurse is trying to do at that time. Then, the server 12 collates the work content at that time recognized in this way with the template of the work process recognition dictionary, so that the work procedure of the work content that the nurse is trying to do is correct or wrong. Can recognize. The knowledge database 48 further determines whether or not it is likely to cause another more serious mistake or inconvenience at that time to alert the corresponding worker in the work situation recognized above. Judgment reference data is registered in advance. Therefore, it is possible to determine whether or not an alarm may be issued at that time by comparing the determination reference data with the work status.

  Here, FIG. 4 shows a detailed block diagram of the wearable sensor unit 20 that is worn on the body of each nurse and functions as a part of the monitoring means.

  Referring to FIG. 4, sensor unit 20 includes a CPU 50. Digital data indicating the number of steps the nurse has walked is input from the pedometer 54 to the CPU 50 through the A / D converter 52. Further, an A / D converter 56 is connected to the CPU 50, and an inclination angle sensor 58 is connected to the A / D converter 56. The A / D converter 56 receives an inclination angle input from the inclination angle sensor 58. (Angle) is converted into digital data (binary data) and input to the CPU 50. An encoder 60 is further connected to the CPU 50, and a headset microphone 62 is connected to the encoder 60. The encoder 60 modulates the audio signal input from the headset microphone 62 into compressed audio data such as MP3 (hereinafter simply referred to as “audio data”) and inputs the result to the CPU 50. Thus, the audio signal is compression-modulated because the capacity of a memory card 70 described later is taken into consideration, and when the capacity of such a recording medium can be ignored, it may be simply converted into digital data.

  For example, a non-contact sensor 64 such as a pyroelectric sensor is provided, and the CPU 50 can turn on / off the headset microphone 62 in accordance with an input from the non-contact sensor 64. In this embodiment, when the nurse raises and lowers his / her hand twice in front of the non-contact sensor 64, that is, the pyroelectric sensor, the detection signal is input to the CPU 50, and the CPU 50 turns on the headset microphone 62 accordingly. Then, when the nurse raises and lowers his / her hand twice in front of the pyroelectric sensor, the microphone 62 is turned off. However, the CPU 50 is configured to turn off the microphone 62 even when a predetermined time (10 seconds) has elapsed without depending on the operation of the nurse. In this embodiment, a headset type (FIG. 5) is used as the microphone 62, but other types such as a pin microphone may be used. However, a microphone 62 having directivity is used. This is to accurately input the voice of the nurse and protect the privacy of the patient.

  The interface 66 is an interface such as a LAN (wireless LAN) adapter, whereby the sensor unit 20 is directly connected to the network 14. However, by providing an interface such as RS232C or USB and using a cable, it is possible to connect to another terminal such as the server 12 or the terminal 16 so as to be communicable.

  A memory card 70 such as an MMC is detachably provided in the card slot 68. The memory card 70 stores data (step count data, inclination angle data, audio data) detected or acquired by the sensor unit 20. The data stored in the memory card 70 can be moved (copied) to the other terminal by mounting the memory card 70 on the other terminal such as the server 12 or the terminal 16.

  Further, the tag ID of the RF tag 36 (FIG. 3) read by the tag reader 72 is input to the CPU 50 from the tag reader 72. Therefore, by recognizing the tag ID read by the tag reader 72, the nurse recognizes the work status such as which patient's bed is nearby, which medicine container is being held or used. Can do.

  The clock circuit 74 is a circuit that measures the date and time, and the CPU 50 adds the time data acquired from the clock circuit 74 to the data acquired from each sensor and the data of the nurse ID and stores them in the memory card 70. To do. If necessary, the data to which the time data is attached is output to the server 12 and / or the terminal 16 connected to the network 14 via the interface 66.

  The DIP switch 76 is composed of, for example, 8 bits, and can set a numerical value between 0 and 255 by switching on / off of each bit. This numerical value is identification information, that is, a nurse ID, and a different value is set for each sensor unit 20. The CPU 50 attaches the nurse ID as a label and stores the data with the time data added to the memory card 70 or transfers it to the server 12.

  However, instead of the DIP switch 76, the nurse ID may be stored in the memory card 70. Further, instead of the DIP switch 76, a ROM or the like storing a nurse ID may be provided.

  The wireless transmitter 78 transmits the nurse ID set by the DIP switch 76 or other means by radio waves (weak radio waves) at a predetermined frequency in accordance with instructions from the CPU 50. The wireless receiver 80 receives a weak radio wave transmitted from another sensor unit 20 existing in a wireless communicable range, demodulates it to a nurse ID, and inputs data about the demodulated nurse ID to the CPU 50. By exchanging a nurse ID or the like by the wireless transmitter 78 or the wireless receiver 80, it can be determined whether or not another nurse or doctor exists near the nurse.

  Further, the CPU 50 can give an alarm to the nurse by vibration by giving a drive signal to the vibrator 82 worn on the arm, for example, as shown in FIG.

  Here, as described above, the station 18 detects the nurse ID of the sensor unit 20 and transmits the detected nurse ID to the server 12 via the network 14. Also, identification information (station ID) is assigned to the station 18, and the station ID is detected by the sensor unit 20 as described above. Thus, for example, the station 18 can be configured by using some circuit components of the sensor unit 20. Specifically, the station 18 includes a CPU 50, an interface 66, a DIP switch 76, a wireless transmitter 78, and a wireless receiver 80.

  Note that a ROM storing a station ID may be provided in place of the DIP switch 76 as in the case of the sensor unit 20.

  The sensor unit 20 configured as described above is attached to each nurse. For example, as shown in FIG. 5, circuit components other than the pedometer 54, the tilt angle sensor 58, the headset microphone 62, the non-contact sensor 64, and the vibrator 82 are included in a box (housing) 84 including the CPU 50 and the tag reader 72. The box 84 is mounted on the waist (belt portion) of the nurse. The non-contact sensor 64 and the tilt angle sensor 58 are housed in a pen-shaped case 86 so as to be inserted into a breast pocket of a nurse's clothes (white robe). However, in the drawings, the case 86 is shown outside the breast pocket for easy understanding. The pedometer 54 is attached to the nurse's waist as in the box 84 described above. Further, the headset microphone 62 is attached to the nurse's head.

  Although not shown in FIG. 5, the non-contact sensor 64 and the tag reader 72 are connected to the CPU 50 in the box 84 using connection lines, and the pedometer 54, the inclination angle sensor 58, and the microphone 62 each have connection lines. And is electrically connected to the A / D converter 52, the A / D converter 56 and the encoder 60 in the box 84. However, you may make it connect by short-distance radio | wireless like Bluetooth, without using a connection line. That is, it is only necessary to be electrically connected.

  As shown in FIG. 5, for example, the nurse stores and carries (carries) a portable computer (PDA in this embodiment) 88 in the front pocket of a lab coat. Although not shown, the PDA 88 is configured to be connectable to the network 14 shown in FIG. 1 by a wireless LAN. Since the PDA 88 is already known, a detailed description of its configuration and operation will be omitted. In the drawing, the PDA 88 is shown outside the front pocket for easy understanding.

  For example, when the main power supply of the sensor unit 20 is turned on by a nurse's operation, the CPU 50 detects an input from the tilt angle sensor 58 every predetermined time (in this embodiment, 500 ms). As described above, the microphone 62 is controlled to be turned on / off according to the input of the non-contact sensor 64. Further, the CPU 50 validates the input from the pedometer 54 when the microphone 62 is turned off.

  Therefore, the CPU 50 uses the step count data (step count data) measured by the pedometer 54, the angle data (angle data) measured by the tilt angle sensor 58, and the voice data (voice data) detected by the microphone 62. The data is identified and stored in the memory card 70, and transmitted to another terminal (in this embodiment, the server 12) by wireless LAN. Further, when recording the step count data, the angle data, and the voice data, the CPU 50 acquires time data about the acquisition start time and the acquisition end time of each data from the clock circuit 74, and attaches the time data to each data. It is like that.

  The behavior data obtained by the wearable sensor unit 20 as described above, and further, the behavior data obtained by the video camera 28 and the like described above are ultimately all stored in the server 12 and their associated databases (FIG. 2). ) Is recorded.

  For example, when the nurse n cares for the patient k, the contents of the statement that the nurse n said, “I will go to the patient (patient) visit of the patient k”, while going back and forth between the patient k's room Data on the number of steps and the angle (tilt angle) when the upper body is tilted while going back and forth in the hospital room are recorded. In addition, time data of the start time and end time of nursing work is added to this data.

  Such data on the voice, the number of steps and the angle of inclination and the time data attached thereto (sometimes collectively referred to as “measurement data”) are obtained for all of the daily tasks of nurse n. The As described above, the sensor unit 20 is connected by the wireless LAN (network 14). Therefore, the measurement data (business measurement data) for the daily work acquired as described above is transmitted from the sensor unit 20 to the terminal. 16 can be transmitted (transferred). If the memory card 70 is detachably attached to the terminal 16, business measurement data can be directly input to the terminal 16.

  The terminal 16 receives the transferred work measurement data, and the work measurement data is uploaded to the server 12 by the operation of a nurse, for example. The server 12 creates nurse data excluding the accident / incident based on the uploaded work measurement data. That is, the nurse is specified, and thereafter, the items of the nurse data excluding the accident / incident are specified (determined) from each measurement data and recorded.

  However, the business measurement data may be directly uploaded from the sensor unit 20 to the server 12 via the network 14.

  For example, the nurse can easily specify on the server 12 side based on the nurse ID attached to the work measurement data transferred from the sensor unit 20.

  The voice data included in the measurement data is subjected to voice recognition processing, and the patient name and the nursing work performed on the patient are specified from the recognized voice. That is, the server 12 has a voice recognition function, and also has a dictionary for voice recognition, that is, a memory (for example, a hard disk or a ROM) that records voice data corresponding to a plurality of utterances (voices). . However, the voice data of the nurse is recorded in the nurse database 28 as an example.

  Since this embodiment is not directly related to the nurse's action record itself, further explanation is omitted here, but this embodiment is simply described in the various types described above. By recognizing the work content and work procedure (work status) of a worker such as a nurse based on the monitor information from the monitoring means, it is detected whether the work that the worker is trying to do is an incorrect work. Alerts workers such as nurses who are trying to In this case, a warning is given to the worker only when it is determined that the worker can be warned in view of the work status of the worker such as a nurse, and the warning is not given otherwise. I am doing so. This prevents the operator from inducing another mistake with the given alarm. However, in a later embodiment, if it can be predicted that an erroneous work will lead to a more serious accident than this mistake, an alarm is given in an appropriate manner regardless of the work situation of the worker.

  FIG. 6 is a flowchart showing the operation of the server 12 in this embodiment, and this flowchart (program) is set in an internal memory (ROM or RAM: not shown) of the server 12 as an example.

  Here, with reference to this FIG. 6, the operation | movement of especially the server 12 of the erroneous operation | work warning system 10 of an Example is demonstrated. After starting the operation, in step S1, the server 12 receives the monitor information received at that time, for example, the signal from the objective sensor 22, the sound state from the sound collecting microphone 24, the video information from the video camera 28, the pedometer. Based on the step count information from 54, the tilt angle information from the tilt angle sensor 58, the voice information from the headset microphone 62, the tag ID from the tag reader 72, etc., the work contents of the nurse at that time are recognized. However, the information acquired by the wearable sensor unit 20 among the monitor information, that is, the number of steps information, the inclination angle / inclination angle information, the audio information from the headset microphone 62, the tag ID, etc. is collected in the server 12 through a network such as a wireless LAN. It is what is done.

  As described above, since the work content recognition dictionary (template) is registered in the knowledge database 48 in advance, the server 12 compares the monitor information collected as described above with the recognition dictionary. Then, it is possible to recognize the work contents that the nurse is going to perform. However, the work content may be recognized artificially by the administrator of the server 12.

  After recognizing or grasping the work content in step S1, the server 12 recognizes in step S1 using the work process recognition dictionary (template) registered in the knowledge database 48 in the next step S2. It is determined whether the contents of the work performed are performed in the correct procedure, that is, whether the recognized work is performed based on a predetermined rule or procedure. However, the work process may be recognized artificially by the administrator of the server 12.

  After recognizing the work content in step S1 and recognizing the work process in step S2, that is, after recognizing the work situation, in step S3, it is determined whether or not there is any problem in the work. If the work content in step S1 cannot be recognized, if it can be recognized, but the work itself is wrong, further, even if it is recognized in step S1 that the correct work is being performed, the work is performed in step S2 according to the procedure or rule. When the process is wrong, for example, it is determined in this step S3 that the work is wrong.

  In this way, by performing steps S1 to S3, if it is determined that the work that the nurse is trying to do is wrong, that is, an erroneous work, then in step S4, the server 12 It is determined whether or not a warning can be issued to the nurse. In this state determination, it is determined whether or not a warning is likely to induce another mistake or inconvenience. Such a state determination can be performed by collating with the determination reference data stored in the knowledge database 48.

  Specifically, for example, when operating a machine tool or industrial machine that requires concentration and a slight mistake leads to an accident, if concentration is hindered, the worker, surrounding people, or things may be at risk. The alarm is not given when performing various operations and operations. In a similar situation, if a nurse or doctor alerts you when you are about to give an injection to someone in the patient right now, this situation can alert you because the task can be affected by the alert. It is not in an appropriate state.

  In step S4, as described above, it is determined whether or not it is possible to issue an alarm based on the work content that the nurse worker is trying to perform. If “NO” in the step S4, the server 12 next determines whether or not the erroneous work determined above leads to a serious accident in a step S5. That is, the adverse effect caused by the mistake that may be triggered by the alarm and the adverse effect caused by the erroneous work are weighed, and when the latter is larger than the former, “YES” is determined in this step S5. For example, when a nurse or doctor is about to make an injection, the answer is “YES” if a serious side effect is predicted due to the erroneous operation (incorrect injection). In other words, when a harmful effect caused by an error that may be triggered by an alarm is compared with a harmful effect caused by the erroneous operation, if the latter is smaller than the former, it is determined as “NO” in this step S5. Is done.

  If “NO” is determined in each of steps S4 and S5, even if an erroneous operation is detected in steps S1 to S3, the server 12 ends the process without any warning.

  On the other hand, if “YES” is determined in step S4, or if “NO” is determined in step S4 but a serious accident is predicted, the server 12 goes through step S5 and then in step S6. Then, it is determined whether the alarm in the first mode is possible. As described above, as a method of issuing an alarm to a worker such as a nurse or a doctor, a method of giving an alarm by vibration of the vibrator 82 attached to the nurse or the like, a red rotating lamp 30 provided in a hospital room or a corridor, etc. In addition, there is a method of giving an alarm by light or sound of the speaker 32 (FIG. 3).

  For example, when the erroneous operation is an injection, if an alarm is given by vibration stimulation with the vibrator 82 when the injection is about to be performed, the vibration may cause a mistake. It is possible to issue an alarm at. In this case, the stimulus given to the worker by the alarm is not suitable for vibration but light or sound is appropriate.

  On the other hand, when an operator, such as a nurse, is together with a patient (working partner) and is taking any action on the patient, an alarm accompanied by light stimulation or voice stimulation by the red rotating light 30 or the speaker 32 is performed. In the method, the patient is informed that some kind of alarm has been given to the nurse, which may give the patient an unfounded anxiety or distrust. Therefore, in this case, it is appropriate to use an alarm method based on vibration of the vibrator 82 while avoiding an alarm method based on light or sound.

  Further, for example, when a nurse is working alone or with another nurse or doctor but no patient is present, the alarm method using the red rotating light 30 or the speaker 32 may be used. There is no particular problem, and it may be necessary to call attention to other nurses. In this case, an alarm method using the red rotating light 30 or the speaker 32 is used instead of the vibrator 82. Is appropriate.

  As described above, in this embodiment, a plurality of alarm methods can be selectively used to issue an alarm to the worker, and it is determined which of the different alarm methods can be used. An alarm can be given to the worker.

  In this embodiment, the alarm method by the vibrator 82 is defined as the first alarm method. In step S6, it is determined whether the first alarm method, that is, the vibrator 82 can be used. In this step S6, based on the various monitor information used for recognizing the work content of step S1, for example, by determining whether the injection is going to be correct or in the vicinity of the patient, the first alarm is issued. Determine whether the method can be used.

  If “YES” is determined in step S6, the server 12 gives a command to drive the vibrator 82 managed by the CPU 50 to the CPU 50 of the wearable sensor unit 20 through a network such as a wireless LAN. In response, the CPU 50 (FIG. 4) gives a drive signal to the vibrator 82. Then, the vibrator 82 vibrates, and a vibration stimulus is given to the nurse's arm wearing the vibrator 82. Therefore, the nurse assumes that there has been an alarm for an erroneous operation, and that the error in his / her work is incorrect. Recognizing and correcting the erroneous work, it is possible to perform the correct work (the work is correct and the work procedure is correct).

  When “NO” is determined in step S6, that is, when the vibrator 82 as the first alarm method cannot be used, the server 12 directly drives the red rotating lamp 30 and the speaker 32 shown in FIG. An alarm is given to the worker by light or sound as an alarm method. Therefore, the worker and related persons in the vicinity thereof can notice the warning and correct the erroneous work correctly.

  A specific operation example of the alarm system of this embodiment will be described.

  For example, when nurse A is preparing an infusion in front of a bed of a patient B, a tag ID from the tag reader 72 (FIG. 4) that has read the RF tag 36 (FIG. 3) (this is sent from the CPU 50 via the network). From the monitor information (such as collected by the server 12), the server 12 determines that the nurse A is in front of the bed of the patient B and the inclination angle sensor 58 and acceleration mounted on the nurse A in step S1. Based on monitor information such as images from a sensor (not shown) and a video camera 28 (FIG. 3) provided in the hospital room 26, it can be recognized as a work content that the nurse A is preparing for infusion. Furthermore, from the monitor information such as the tag ID from the tag reader 72 that has read the RF tag 36 of the medicine container 38, the server 12 is about to administer the medicine handled by the nurse A to the patient B as the work content. Can be recognized.

  In step S2, the server 12 confirms the work procedure, recognizes that the medicine should be administered to the patient C, not to the patient B, and the nurse A at that time It is determined that the work to be performed is an erroneous work (step S3).

  As a result of the recognition of the work content in step S1, if it is recognized that the work state of nurse A at that time is still in preparation of medicine, “YES” can be determined in step S4, and the server 12 Subsequently, in step S6, it is determined whether or not the first alarm method, that is, the alarm by the vibrator 82 is possible. Since it is still being prepared, “YES” is determined in this step S 6, and therefore the server 12 instructs the CPU 50 to drive the vibrator 82. In response, vibration is transmitted from the vibrator 82 to the arm of the nurse A, and the nurse A's attention is alerted.

  If it is found that nurse A is trying to pierce patient B with an infusion needle, the first alarm method, that is, alarm by vibrator 82 is not appropriate as described above. Therefore, in this case, “NO” is determined in the step S6, and the server 12 alerts the nurse A by the second alarm method using the red rotating light 30, for example. In this case, the patient B is informed that some mistake has occurred in the work of the nurse A. However, when the needle B is about to be pierced right now, the vibration is applied to the place where the puncture is performed. Since there is a possibility of inducing another serious accident such as deviation, the second alarm method is employed in order to avoid it.

  In the above-described embodiment, a medical service such as a nurse or a doctor has been described as an example. However, the work targeted by the present invention is intended for work involving various dangers, such as operation of machine tools and work of handling radioactive materials.

  Furthermore, although the method using vibration, light, or voice is exemplified as the alarm method, an alarm method that displays an alarm message on the display (not shown) of the nurse terminal 16 or the station 18 is also conceivable. .

FIG. 1 is an illustrative view showing one example of a configuration of an erroneous operation warning system of one embodiment of the present invention. FIG. 2 is an illustrative view showing an electrical configuration of the server shown in FIG. 1 and its attached portion. FIG. 3 is an illustrative view schematically showing various devices installed in a hospital room. FIG. 4 is an illustrative view showing one example of an electrical configuration of a sensor unit worn by a nurse. FIG. 5 is an illustrative view showing a state where the sensor unit shown in FIG. 4 is attached to a nurse. FIG. 6 is a flowchart showing the operation of this embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Error work warning system 12 ... Server 18 ... Station 20 ... Sensor unit 22 ... Objective sensor 24 ... Sound collecting microphone 28 ... Video camera 30 ... Red rotating light 32 ... Speaker 36 ... RF tag 50 ... CPU
66 ... Interface 70 ... Memory card 72 ... Tag reader 82 ... Vibrator

Claims (5)

Work status recognition means for recognizing the work status of the worker based on monitor information obtained by monitoring the work status of the worker;
When it is recognized by the work status recognition means that the worker is about to perform an erroneous work, state determination means for determining whether or not the worker can be alerted, and the state determination means for the worker Provided with an alarm means for giving an alarm to the worker when it is determined that the alarm is possible.
An erroneous operation warning system in which the warning by the warning means is not given when the status judgment means judges that the worker is not in a state capable of warning. The alarm means is configured to be able to give an alarm by a different method, and further includes an alarm method determining means for determining an alarm method of the alarm means according to the work situation,
The erroneous operation warning system according to claim 1, wherein the warning unit gives a warning to the worker by the warning method determined by the warning method determination unit. When it is determined that the state determination means is not in a state of being able to warn the worker, it further comprises a serious accident determination means for determining whether the erroneous work leads to a serious accident,
The erroneous operation alarm system according to claim 1 or 2, wherein when the serious accident determination unit determines that the erroneous operation leads to a serious accident, the alarm unit is activated.   The erroneous operation alarm system according to claim 1, wherein the alarm method includes at least one of a vibration method, a light method, and a sound method. A work situation recognition step for recognizing the worker's work situation based on monitor information obtained by monitoring the worker's work situation;
A state determination step for determining whether or not the worker can be alerted when the worker recognizes that the worker is trying to perform a wrong operation in the work state recognition step; and for the worker in the state determination step An alarm step of giving an alarm to the worker by an alarm means when it is determined that the alarm is possible,
An erroneous operation warning method in which an alarm by the alarm means is not given when it is determined in the state determination step that the operator is not in an alarmable state.

Images