JP2007034738A - Warning system and warning method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a warning system and warning method effectively preventing medical accidents and medical errors by warning only when seriously needed. <P>SOLUTION: The warning system 10 includes a server 12, and the server 12 detects the behavior of a nurse to be watched through a monitoring means such as an objective sensor, microphone, and video camera, judges whether the nurse can obtain the objective of nursing service from the nurse's service and a scenario corresponding to the nursing service when the nurse practices the nursing service, judges whether the nurse shifts to the other nursing service when the nurse cannot obtain the objective of the nursing service, warns the nurse about inobservance to the scenario when the nurse does not shift to the other nursing service and attempts to stop the current nursing service, and warns the nurse about the inobservance to the scenario when the nurse shifted to the other nursing service, finishes the other nursing service, and does not return to the original service. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a warning system and a warning method, and more particularly to a warning system and a warning method for predicting and warning of the occurrence of a nursing accident by a nurse.

An example of this type of warning system is disclosed in Patent Document 1. According to Patent Document 1, a procedure and a device used for nursing work are stored in a knowledge database, and if a nurse mistakes a procedure, a device used or a method of using the procedure, or skips the procedure, The teacher is warned.
Japanese Patent Laid-Open No. 2005-92440

  However, in this background art, if a procedure is wrong or skipped, a warning is issued immediately, so even if no problem occurs as a result, a warning is issued. become. In other words, warnings may occur frequently, and for example, a situation may occur in which a nurse ignores warnings (warning familiarity). In this case, an accident cannot be prevented in advance, and it does not function as a warning device (warning system).

  Therefore, a main object of the present invention is to provide a warning system and a warning method that can issue a warning only when it is really necessary.

  According to the first aspect of the present invention, a behavior detection means for detecting a behavior of a subject who performs business, a scenario storage means for storing a scenario for a plurality of business operations, and whether or not the final goal can be reached based on the behavior and the scenario of the subject. An inference system comprising inference means for inferring and warning means for issuing a warning when an inference result of the inference means cannot reach a final goal.

  According to the first aspect of the present invention, the behavior detecting means (12, 18, 20, 22, 24, 26, 56: reference numerals corresponding to the embodiments. The same applies hereinafter) detects the behavior of the subject performing the business. To do. The scenario storage means (30) stores scenarios for a plurality of tasks. In simple terms, a scenario describes the correct action sequence for a business. The inference means (12, S33) infers whether or not the final goal can be reached based on the behavior and scenario of the subject. That is, it is inferred whether the final goal can be explained from the current behavior and scenario of the subject. The warning means (12, S39, S53) issues a warning when the inference result of the inference means (12, S33) cannot reach the final goal, that is, when the final goal cannot be explained. This is because when the inference result cannot reach the final goal, the current job is not executed at all, or the current job is finished without following the steps to be executed. This is because there is a high probability that such inconveniences occur.

  According to the first aspect of the present invention, the warning is issued only when the inference result cannot reach the final goal, so that the warning can be prevented from being overwhelmed. In other words, it is possible to warn only when it is really necessary, for example, when there is a risk of a medical accident or medical error.

  The invention of claim 2 is dependent on claim 1, and each scenario includes a plurality of partial scenarios, and the inference means infers whether or not the sub-goal can be reached for each partial scenario.

  In the invention of claim 2, each scenario is composed of a plurality of partial scenarios (sub-scenarios). Therefore, the inference means (12, S33) infers whether or not the sub-target (sub-target) can be reached for each partial scenario.

  According to the invention of claim 2, since it is inferred whether or not the sub-goal can be reached for each sub-scenario, even if an error occurs during the work, a warning is issued to prevent an accident etc. can do.

  The invention of claim 3 is dependent on claim 2, and when it is inferred by the reasoning means that the sub-goal cannot be reached, task determination means for determining whether or not the subject has moved to another task, and task determination means When it is determined that the subject has not moved to another job, the device further includes a mid-work end judging means for judging whether or not to end the current business halfway. A warning is issued when it is determined that the current job is to be terminated.

  In the invention of claim 3, when it is inferred that the sub-target cannot be reached by the reasoning means (12, S33), the task determination means (12, S45) determines whether or not the subject has moved to another task. To do. The mid-work end judging means (12, S47) determines that the subject has not moved to another work ("NO" in S45) when the work judging means (12, S45, S51) judges the current work. Determine if you are going to exit halfway. The warning means (12, S39, S53) issues a warning when it is determined by the work halfway end judging means (12, S47) that the current work is to be halfway finished ("YES" in S47).

  According to the invention of claim 3, since the warning is given only when the current job is to be terminated halfway, the occurrence of warnings can be prevented.

  The invention of claim 4 is dependent on claim 2 or 3, and the work determination means returns to the original work when the subject ends the other work after determining that the subject has moved to another work. The warning means issues a warning when the subject does not return to the original job.

  In the invention of claim 4, when the subject discriminating means (12, S45, S51) discriminates that the subject has moved to another task (“YES” in S45), the subject finishes the another task Determine whether to return to the original job. The warning means (12, S39, S53) issues a warning when the subject does not return to the original job (“NO” in S51).

  According to the invention of claim 4, when another work is interrupted during execution of a certain work, a warning is issued only when the subject does not return to the original certain work. In other words, since the warning is not issued simply by shifting to another business, the occurrence of warnings can be prevented.

  The invention of claim 5 is a warning method for a warning system comprising scenario storage means for storing scenarios for at least a plurality of tasks. This warning method (a) detects the behavior of the subject performing work, (b) infers whether the final goal can be reached based on the subject's behavior and scenario, and (c) in step (b) A warning is issued when the inference result cannot reach the final goal.

  In the invention of claim 5, as in the invention of claim 1, a warning can be issued only when it is really necessary.

  According to the present invention, since the warning is issued only when the inference result cannot reach the final goal, the warning can be issued only when necessary.

  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 warning 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 in 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). .

  Note that since the station 18 and the sensor unit 20 can communicate with each other, the sensor unit 20 detects the identification information (station ID) of the station 18 that exists within a wireless communicable range. 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. The server 12 is connected to a plurality of objective sensors 22, a plurality of sound collecting microphones 24, and a plurality of video cameras 26, which are omitted in FIG. The Although not shown, in this embodiment, the plurality of objective sensors 22 stores a medical instrument such as a thermometer, a sphygmomanometer, a syringe, a drip syringe (injector), a blood collection test tube, and a urinalysis cup. It is installed in a box take-out part or a nurse call terminal and detects the use (take-out) of those medical devices. However, identification information such as tag information (RF-ID) or barcode is added to these medical devices, and the presence or absence of use is detected by reading the tag information or barcode. Also good. The plurality of microphones 24 are located in a hospital ward that accommodates inpatients and are installed in hallways and hospital rooms (beds or the vicinity thereof) to collect ambient sounds (mainly nurses' voices in this embodiment). Sound. Further, like the sound collecting microphone 24, the plurality of video cameras 26 are in a hospital ward that accommodates inpatients, and are installed in a corridor and a hospital room (bed or in the vicinity thereof), and also in a nurse's station. Take a picture of a nurse who is set up and does nursing work. Here, nursing work is a general term for work to be performed by a nurse such as inquiry, temperature measurement, pressure detection, injection, medication, drip injection, and discharge guidance. However, in this embodiment, when simply referred to as “nursing work”, any one work is indicated.

  Although omitted in FIG. 1, three databases (DB) are connected to the server 12. Specifically, an electronic medical record DB 28, a scenario DB 30, and a knowledge DB 32 are connected to the server 12.

  The electronic medical record DB 28 records electronic medical records for patients 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 (or identification information), gender, disease name, medical condition, prescription (what kind of injection or infusion, prescription and prescription time), rehabilitation The data (text data) of information such as the situation, hospitalization calendar, and precautions for the patient is described.

The scenario DB 30 describes correct behavior procedures (scenarios) for nursing work. However, information on the equipment to be used and information on how to use it are also included. Here, the scenario s _i is a set of actions or events (events) in nursing work created with reference to the nurse's work manual, and is arranged according to basic procedures (time series). The scenario s _i is expressed by Equation 1. However, in equation 1, “in chronic order” means that not all events e _i need to be executed according to the procedure (time series), but some events e _i that need to be executed partially according to the time series. Is included.

たとえば、シナリオｓ_i,ｓ_h,ｓ_aは、それぞれ、複数のイベントによって構成され、数２で示される。

For example, the scenarios s _i, s _{h, and} s _a are each composed of a plurality of events, and are expressed by Equation 2.

[Equation 2]
s _i = {e _i1 = preparing syringe, e _i2 = preparing distilled water and diax, e _i3 = dissolving diax, e _i4 = suctioning diaxox, e _i5 = waiting, e _i6 = Inject}
s _h = {e _h1 = power supply of various monitors, e _h2 = drip set, e _h3 = preparation of necessary items, e _h4 = suction set, e _h5 = waist / cannabis preparation, e _h6 = light・ Check head position}
s _a = {e _a1 = received from ward nurse, e _a2 = push ID card to cost table, e _a3 = report blood pressure of patient to anesthesiologist, e _a4 = chestrate on schaukasten, e _a5 = wearing monitors, e _a6 = assisting in securing blood vessels, e _a7 = assisting in hips / hards, e _a8 = assisting in introducing anesthesia, e _a9 = wearing a urinary and deep body temperature monitor, e _a10 = electric knife E _a11 = Take position, e _a12 = L frame, Mayo stand, light installation, e _a13 = Assistance of gown technique, e _a14 = Isodine, put raw food on the instrument table, e _a15 = Electricity Female, suction cord connection}
However, the scenario s _i (the same applies to the other scenarios s _{h and} s _a ) includes a plurality of scenarios s _in (hereinafter sometimes referred to as “partial scenarios” for convenience of explanation). Can be represented by a set of Although detailed description is omitted, each partial scenario s _ij is represented by a set of two or more events (e). In Equation 3, O _i is a final target when the scenario s _i is executed, and O _ij is a subordinate (auxiliary) target when the partial scenario s _ih is executed. However, the final goal (final goal) is obtained by the nurse performing the nursing work according to the scenario s _i . In other words, the final goal is the correct result of nursing action. In addition, the subordinate goal (subordinate goal) is obtained by executing a part of the nursing work according to the partial scenario s _ih .

[Equation 3]
s _i = {S _i1 , S _i2 ,..., S _in ; O _i }
s _ij = {e _j1 , e _j2 ,..., e _jk ; O _ij }
However, for example, a certain partial scenario s _il (c) = {e _l1 , e _l2 ,..., E _lm ; O _il } needs to be executed in time series, but another partial scenario s _ip (n) = {E _p1 , e _p2 ,..., E _pq ; O _ip } need not be executed in time series. For example, in the example shown in Equation 2, the event e _i4 (aspirated with dissolved Diamond) needs to be executed before the event e _i6 (injection).

  Although illustration is omitted, information on whether or not a partial scenario needs to be executed in chronological order is labeled with each partial scenario or stored in association with each partial scenario. .

  The knowledge DB 32 stores data on axioms and hypotheses. In this example, an axiom is an event, action, or element that inevitably yields an ideal state of prescription or treatment for that patient and the causality of that ideal state, and more generally, what It is such a relationship (general fact) that does not break the relationship. In addition, the hypothesis is observed or monitored by monitoring means (in this embodiment, the station 18, the sensor unit 20, the objective sensor 22, the sound collecting microphone 24, the video camera 26, and the headset microphone 56) or RFID (tag information). Possible events, actions, elements, etc. that are variable, and that may not hold at the same time (events).

  The server 12 has a clock circuit 12a therein. The clock circuit 12a measures the date and time. In this embodiment, the server 12 refers to the clock circuit 12a to determine whether or not it is the start time (date and time) of the work described in the electronic medical record.

  FIG. 3 is a block diagram showing a specific configuration of the sensor unit 20, and the sensor unit 20 includes a CPU 40. A memory 42, an encoder 44, a non-contact sensor 46, an interface 48, a DIP switch 50, a wireless transmitter 52 and a wireless receiver 54 are connected to the CPU 40. The memory 42 functions as a work memory or a buffer memory and is used by the CPU 40. A headset microphone 56 is connected to the encoder 44, and the encoder 44 modulates the audio signal input from the headset microphone 56 into compressed audio data such as MP3 (hereinafter simply referred to as “audio data”) and the CPU 40. To enter. The reason why the audio signal is compressed and modulated is to reduce the capacity of the memory 42 and to reduce the amount of data transmitted through the interface 48, as will be described later. .

  The headset microphone 56 used in this embodiment has directivity. This is to protect the privacy of the patient by detecting only the voice of the nurse wearing the headset microphone 56. In addition, although not shown in the drawings, a combination of the earphone and the headset microphone 56 may be referred to as a headset.

  A pyroelectric sensor can be used as the non-contact sensor 46, and the CPU 40 turns on / off the headset microphone 56 in accordance with an input from the non-contact sensor 46. In this embodiment, when the nurse raises and lowers his / her hand twice in front of the non-contact sensor 46, that is, the pyroelectric sensor, the detection signal is input to the CPU 40, and the CPU 40 turns on the headset microphone 56 accordingly. Then, when the nurse raises and lowers his / her hand twice in front of the pyroelectric sensor, the headset microphone 56 is turned off. However, the CPU 40 is configured to turn off the headset microphone 56 even when a predetermined time (10 seconds) has elapsed without depending on the operation of the nurse.

  The interface 48 is an interface such as a LAN (wireless LAN) adapter, whereby the sensor unit 20 is directly connected to the network 14. Accordingly, the sesa unit 20 can communicate with a terminal such as the server 12 or the terminal 16 via the network 14.

  The DIP switch 50 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 the identification information (nurse ID) of the nurse, and a different value is set for each sensor unit 20. The CPU 40 attaches the nurse ID as a label to the data to be transmitted and transfers it to the server 12 via the interface 48 and the network 14. Although illustration is omitted, if the table data describing the name of the nurse corresponding to the nurse ID is stored in an internal memory or database such as a hard disk, the server 12 determines the nurse or nurse from the nurse ID. The name can be specified.

  In this embodiment, the nurse ID is set using the DIP switch 50. However, the present invention should not be limited to this. For example, instead of the DIP switch 50, a ROM storing a nurse ID may be provided.

  The wireless transmitter 52 transmits the nurse ID set by the DIP switch 50 by radio waves (weak radio waves) at a predetermined frequency in accordance with instructions from the CPU 40. The wireless receiver 54 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 40.

  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 40, a DIP switch 50, a wireless transmitter 52, and a wireless receiver 54.

  Note that a ROM that stores a station ID may be provided instead of the DIP switch 50, as in the case of the sensor unit 20.

  The sensor unit 20 configured as described above is attached to each subject (nurse). For example, as shown in FIGS. 3 and 4, circuit components other than the non-contact sensor 46 and the headset microphone 56 are accommodated in a box (housing) 60, and the box 60 is attached to the waist (belt portion) of the nurse. The Further, the non-contact sensor 46 is accommodated in a pen-type case so as to be inserted into a breast pocket of a nurse's clothes (white robe). However, in the drawings, a pen-shaped case is shown outside the breast pocket for easy understanding. The headset microphone 56 is attached to the nurse's head.

  Although not shown in FIG. 4, the non-contact sensor 46 is connected to the CPU 40 in the box 60 using a connection line, and the headset microphone 56 is electrically connected to the encoder 44 in the box 60 using a connection line. Is done. 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.

  Further, as shown in FIG. 4, the nurse stores and carries (carries) a portable computer (PDA in this embodiment) 70 in a front pocket of a white robe, for example. Although not shown, the PDA 70 is configured to be connectable to the network 14 shown in FIG. 1 by a wireless LAN. Since the PDA 70 is already known, a detailed description of its configuration and operation will be omitted. In the drawing, it is shown outside the front pocket for easy understanding.

  For example, when the server 12 detects that the nurse has started nursing care, whether or not the server 12 can obtain the final goal O based on at least the background knowledge F including the behavior or action of the nurse and the scenario. To infer. The action (operation) of the nurse is detected (specified) based on the outputs of the monitor means, that is, the station 18, the sensor unit 20, the objective sensor 22, the sound collection microphone 24, the video camera 26, and the headset microphone 56.

  As described above, since the station 18 detects the nurse ID output from the sensor unit 20 and gives it to the server 12, there is a nurse having the nurse ID at the installation position of the station 18 where the nurse ID is detected. You can know what to do (the location of the nurse). Further, the movement (path) of the nurse having the nurse ID can be known by the change of the station 18 to which the nurse ID is input. Further, the appliance used by the nurse can be known from the output of the objective sensor 22. Further, it is possible to know the nursing work to be performed by the nurse based on the sound input through the sound collecting microphone 24 and the headset microphone 56. Furthermore, the action of the nurse can be detected (identified) by analyzing the video image (image data, video data) taken by the video camera 26. For example, if the detection results of the monitoring means are combined and taken into account, the behavior of the nurse can be detected relatively accurately. The same applies hereinafter.

  Inference is performed according to Equation 4. However, the background knowledge F includes axioms and hypotheses included in the knowledge DB 32.

ただし、∪は論理のＯＲを意味する。

However, ∪ means logical OR.

If the final goal O is considered to be a subset of the sub-goal O _j , it can be inferred according to Equation 5.

ここで、推論結果がサブ目標Ｏ_jを得ることができる場合には、次の部分シナリオについての推論を行う。ただし、当該サブ目標Ｏ_jが最終目標Ｏと一致する場合には、看護業務を終了したと判断する。

Here, when the inference result can obtain the sub-target O _j , the following partial scenario is inferred. However, if the sub-goal O _j matches the final goal O, it is determined that the nursing work has been completed.

On the other hand, if the inference result fails to obtain the sub-target O _j , a warning is given that the nursing service violates the scenario in any of the following cases. This is to prevent medical accidents and medical errors from occurring in advance. Specifically, when the inference result cannot obtain the sub target O _j , it is determined whether or not the nurse has shifted to another nursing service. Here, when the nurse's action cannot return or reach the event to be returned or to proceed, it is determined that the nurse has shifted to another nursing service.

  If the nurse has not shifted to another nursing service, it is determined whether or not the current nursing service is to be terminated. For example, when a nurse performs an event that has nothing to do with the current nursing work, or skips an intermediate event and tries to execute the last event (for example, try not to dissolve Diax and try to inject). , It is determined that the current nursing work is about to be terminated.

  Further, when the nurse shifts to another nursing service, it is determined whether or not to return to the original nursing service (the above-mentioned current nursing service) after finishing the other nursing service. Whether or not another nursing operation has been completed is determined by whether or not the last event included in the scenario for the other nursing operation has been executed. Whether or not the operation has returned to the original nursing service is determined by whether or not the action of the nurse matches an event that is included in the scenario corresponding to the original nursing service and should be executed.

  If the current nursing service is to be terminated midway, or if another nursing service is terminated and the original nursing service is not returned, the correct final goal of the scenario for the nursing service cannot be obtained. That is, since it may cause inconveniences such as medical accidents as described above, a warning is given to the nurse that the scenario is violated.

  It is to be noted that when a nurse performs a certain nursing service, it is a daily routine to be asked for another nursing service, and a warning is not issued simply by moving to another nursing service. This is to prevent the occurrence of warnings and give a warning only when it is really necessary to cause a medical accident or a medical error, so that the function of the warning system 10 can be fully exerted.

  In this embodiment, the warning is given only to the nurse of interest. However, by alerting other nurses and head nurses in the vicinity of the nurse, a medical accident or the like can be surely performed. You may make it prevent.

  Specifically, the server 12 executes the entire process according to the flowchart shown in FIG. However, the entire process shown in FIG. 5 is executed at regular time intervals (for example, 15 to 30 minutes) for one nurse of interest. That is, the entire process is executed for each nurse. As shown in FIG. 5, when the server 12 starts the entire process, the server 12 confirms the business in step S1. Here, with reference to the electronic medical record DB 28, it is determined whether or not there is a work to be performed on the patient in charge of the nurse concerned. In a succeeding step S3, it is determined whether or not it is a business start time. That is, it is determined whether there is a business to be started. However, it is not necessary to strictly determine whether or not it is the start time of the work, and it is determined whether or not it is within a certain time (for example, 3 to 5 minutes) before and after the start time of the work.

  If “NO” in the step S3, that is, if it is not the business start time, the process returns to the same step S3 as it is. However, in order to reduce wasteful processing, the process may return to step S3 after waiting for a certain time (for example, 3 to 5 minutes). On the other hand, if “YES” in the step S3, if it is the start time of the work, it is determined whether or not the nurse concerned pays off the work in a step S5. Here, the station 18 for detecting the nurse ID of the nurse of interest changes, the nurse is photographed by the video camera 26, or the nurse starts work through the headset microphone 56. It is determined whether or not there is a voice input.

  If “NO” in the step S5, that is, if the business is not started, a business start alarm (warning) is issued in a step S7, and the process returns to the step S5. Here, the warning is performed, for example, by transmitting a message indicating that the work should be started to the nurse terminal 16 assigned to the nurse of interest or the PDA 70 possessed by the nurse. However, since the focused nurse may not have seen the display screen of the nurse terminal 16 or the PDA 70, a warning is given to the nurse by using the earphone of the nurse's headset. Also good. Further, instead of the headset or in combination with the headset, for example, a wristwatch type display with vibration may be attached to the nurse and a warning may be given thereto.

On the other hand, if "YES" in the step S5, that is, if the start of the business, in step S9, it is determined whether there is a scenario including the event e _i. Here, the server 12 detects the action of the focused nurse as described above. Then, the server 12 refers to the scenario DB 30, it is determined whether the scenario s _i are present including the event e _i that matches the detected action.

If “NO” in the step S9, that is, if there is no scenario s _i including the event e _i that matches the nurse's action, a series of actions (event e _i ) are set as a new scenario s _z in a step S11. Remember. Here, there is easily shown, but for example, until the nurse noted that terminates the business, by detecting the behavior (event e _i) for each predetermined time, is to register the scenario DB 30 (storage) . That is, a new scenario s _z is added. Here, the new scenario s _z is registered as it is in the scenario DB 30, but may be registered after correction is made by the creator of the scenario s _i (scenario DB 30). However, since the scenario s _i is created from a nursing service manual, it is considered that a new scenario s _z is hardly added.

On the other hand, if "YES" in the step S9, that is, if a scenario s _i including the event e _i that matches the behavior of the nurses, in step S13, to confirm the target Oi. Here, the target Oi is a target obtained when the business is performed according to the scenario s _i . In step S13, the target O _i scenario s _i including the event e _i is the business described in the electronic medical chart, that is, it is confirmed if it matches the nursing activities confirmed in step S1 (target O) is there.

In a succeeding step S15, it is determined whether or not the target O cannot be explained from all the scenarios s _i . That is, it is determined whether or not the target O _i of all scenarios s _i including the action e _i matches the target O described in the electronic medical record. If “YES” in the step S15, that is, if the target O _i of all the scenarios s _i including the action e _i does not match the target O described in the electronic medical record, the process returns to the step S9 as it is, and the scenario s _i The detection and the confirmation of the target O _i are executed again. However, if “NO” in the step S15, that is, if the target O _i of the scenario s _i including the action e _i coincides with the target O described in the electronic medical record, confirmation of achievement of each sub target described later in a step S17. Then, the warning process (see FIG. 6) is executed and the whole process is terminated.

  Although illustration is omitted, not only the process of step S9 but also the process of step S11 detects the action of the nurse of interest.

6 and 7 are flowcharts showing confirmation (inference) and warning processing of each sub-goal achievement in step S17 shown in FIG. When the server 12 starts confirmation and warning processing of each sub-goal achievement, it initializes a variable j (j = 1) in step S31. In a succeeding step S33, it is determined (confirmed) whether or not the sub-target O _j can be explained from the current background knowledge F and the partial scenario s _ij . If "NO" in the step S33, that is, it is inferred that explain the sub target O _j from the current background knowledge F and partial scenarios s _ij, it is determined to be able to achieve sub-goals O _j, at step S35 Then, it is determined whether or not the scenario s _ij includes events to be executed in chronological order. This is determined with reference to the label attached to the partial scenario _sij .

If “NO” in the step S35, that is, if the scenario s _ij does not include events to be executed in time series order, the process proceeds to a step S41 as it is. However, if “YES” in the step S35, that is, if the scenario s _ij includes events to be executed in time series, it is determined in a step S37 whether or not the events are executed in time series. Here, the action of the nurse is detected, and it is determined whether or not the action is about to be executed according to the event included in the scenario s _ij .

If “NO” in the step S37, that is, if the event is not executed in chronological order, a scenario violation is alarmed in a step S39, and the process returns to the step S37. However, if “YES” in the step S37, that is, if the events are executed in chronological order, it is determined whether or not all the current jobs are completed in a step S41. That is, it is determined whether or not the execution of all the events e _i included in the scenario s _i has been completed and the goal O _i has been achieved (the nursing work indicated by the electronic medical record has been completed). If “NO” in the step S41, that is, if all the current jobs are not completed, the variable j is incremented (j = j + 1) in a step S43, and the process returns to the step S33. That is, it is inferred whether or not the next sub-target O _{j + 1} is achieved. However, if “YES” in the step S41, that is, if all the current work is ended, confirmation of each sub-goal achievement and warning processing are returned.

Furthermore, if "YES" in the step S33, i.e. it determines that if it is inferred that not explain the sub target O _j from the current background knowledge F and scenarios s _ij, can not be achieved subgoals O _j, 7 In step S45, it is determined whether or not another nursing operation has been performed. If “NO” in the step S45, that is, if it is not shifted to another nursing work, it is determined whether or not the current nursing work is terminated in a step S47.

  If “NO” in the step S47, that is, if the current nursing work is not ended halfway, the process returns to the step S33 shown in FIG. 6 as it is. On the other hand, if “YES” in the step S47, that is, if the current nursing work is ended halfway, the process proceeds to a step S53 as it is.

Furthermore, if "YES" in the step S45, that is, if the operation proceeds to another nursing operations, at step S49, the check the scenario s _k corresponding to the different care business, the process proceeds to step S51. In this embodiment, for simplicity, the confirmation processing of the scenario s _k corresponding to another nursing operations are shown in one step (processing), but strictly speaking, the process of step S9~ step S17 Is executed. In other words, even if a transition is made to another nursing service, a medical accident may occur in the other nursing service. This is to detect the occurrence of this in advance and give a warning.

  In step S51, it is determined whether or not to return to the original nursing service. Here, the original nursing service is the nursing service (the current nursing service described above) that was performed immediately before “YES” is determined in step S45. If “YES” in the step S51, that is, if returning to the original nursing work, the process returns to the step S33 as it is. However, if “NO” in the step S51, that is, if the original nursing service is not returned, a scenario violation alarm is given in a step S53, and the process returns to the step S49.

  Although illustration is omitted, in the processes of steps S33, S37, S41, S43, S45, and S49, the action of the nurse of interest is detected.

  According to this embodiment, a result obtained from a nurse's behavior and scenario and a scenario are inferred, and a warning is issued only when the inference result cannot achieve a desired goal. You can warn only when.

  In this embodiment, the scenario is created based on the nursing work manual, but the present invention is not limited to this. It is also possible to create a scenario by monitoring the actual nursing work of a nurse. In addition to referring to a nursing service manual, the actual nursing service may be monitored to create a scenario.

  In this embodiment, the case of functioning as a warning system for nursing work has been described. However, it may function as a warning system for other work. For example, it can be used as a warning system for a test (experimental) facility or factory that handles powerful drugs, or a factory that performs assembly work such as automobiles.

It is an illustration figure which shows an example of a structure of the warning system of this invention. FIG. 2 is an illustrative view showing an electrical configuration of the server shown in FIG. 1. It is an illustration figure which shows an example of the electrical constitution of the sensor unit with which a nurse is mounted | worn. It is an illustration figure which shows a mode that the sensor unit shown in FIG. 3 was mounted | worn with the nurse. It is a flowchart which shows the whole process of the server shown in FIG. It is a flowchart which shows a part of confirmation and warning process of each sub target achievement of the server shown in FIG. FIG. 7 is another part of the confirmation and warning processing of the achievement of each sub-goal of the server shown in FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... Warning system 12 ... Server 16 ... Terminal 18 ... Station 20 ... Sensor unit 22 ... Objective sensor 24 ... Sound collection microphone 26 ... Video camera 28, 30, 32 ... DB
40 ... CPU
42 ... Memory 46 ... Non-contact sensor 50 ... DIP switch 52 ... Wireless transmitter 54 ... Wireless receiver 56 ... Microphone 70 ... PDA

Claims (5)

A behavior detection means for detecting the behavior of a subject performing business,
Scenario storage means for storing a plurality of scenarios for the business;
Inference means for inferring whether or not a final goal can be reached based on the behavior of the subject and the scenario, and warning means for issuing a warning when the inference result of the inference means cannot reach the final goal, Warning system. Each of the scenarios includes a plurality of partial scenarios,
The warning system according to claim 1, wherein the inference means infers whether or not the sub-goal can be reached for each partial scenario. When it is inferred by the reasoning means that the sub-goal cannot be reached, task determination means for determining whether or not the subject has moved to another task; and the task determination means causes the subject to move to another task. When it is determined that the current job is not completed, the job further includes a mid-work end determination means for determining whether or not to end the current business halfway.
The warning system according to claim 2, wherein the warning unit issues a warning when it is determined by the job halfway end determination unit that the current job is to be ended halfway. After determining that the subject has moved to another task, the task determining means determines whether or not to return to the original task when the subject ends the other task,
The warning system according to claim 2 or 3, wherein the warning means issues a warning when the subject does not return to the original job. A warning method of a warning system comprising scenario storage means for storing scenarios for at least a plurality of tasks,
(a) detecting the behavior of the subject performing the task,
(b) inferring whether the final goal is reachable based on the subject's behavior and the scenario; and
(c) A warning method that issues a warning when the inference result of the step (b) cannot reach the final goal.

Images