JP2019175052A - Caring behavior estimation system - Google Patents

Abstract

To provide a caring behavior estimation system capable of reducing labor of inputting executed caring behavior.SOLUTION: A caring behavior estimation system includes: a voice acquisition device 10 for acquiring voice; a control device 30 (a voice recognition part) for recognizing the acquired voice as character information; the control device 30 (a storage part) for storing a first keyword showing the type of caring behavior; and the control device 30 (an estimation part) for estimating an executed caring behavior by collating the character information recognized by the control device 30 (the voice recognition part) with the first keyword.SELECTED DRAWING: Figure 3

Description

  The present invention relates to a technique of a nursing care action estimation system that estimates a nursing care action.

  Conventionally, the technology of a care support system has been publicly known. For example, as described in Patent Document 1.

  In Patent Document 1, a mobile phone held by a caregiver, a server that converts voice input from the mobile phone into text data by a voice recognition function, and transmits the text data to the mobile phone, and transmission / reception of the mobile phone A care support system including a portable printer that outputs content is described. In the care support system, after the care service is performed, the caregiver inputs the care content (care action) from the mobile phone by voice and transmits it to the server, and the care service content that has been performed from the mobile printer. Can be output. Thereby, even if it does not write by hand, the third party can grasp | ascertain the content of care implementation later.

  However, the technique described in Patent Document 1 is troublesome in that it is not necessary to manually record the contents of the nursing care, but it is still necessary to input the contents of the nursing care after the care service is implemented.

JP 2012-73739 A

  This invention is made | formed in view of the above situations, The subject which it is going to solve is providing the nursing care action estimation system which can reduce the effort which inputs the nursing care practice implemented.

  The problem to be solved by the present invention is as described above. Next, means for solving the problem will be described.

  That is, in claim 1, a voice acquisition unit that acquires voice, a voice recognition unit that recognizes the acquired voice as character information, a storage unit that stores a first keyword indicating the type of care action, An estimation unit that estimates the care action performed by comparing the character information recognized by the voice recognition unit with the first keyword.

  In Claim 2, the personal identification part which identifies the individual who uttered the acquired said sound was provided, and the said estimation part originated from the specific individual extracted based on the identification result of the said personal identification part The estimation is performed using speech.

  In Claim 3, The said memory | storage part memorize | stores the 2nd keyword which shows execution of the care act corresponding to a said 1st keyword, The said estimation part is in the said character information recognized by the said voice recognition part. When the first keyword is included and the second keyword is included, the implementation of the nursing care action corresponding to the first keyword is confirmed.

  According to a fourth aspect of the present invention, a detection unit that detects a person leaving the room is provided, and the storage unit indicates a type of care action that requires the person to leave the room among the first keywords. The keyword is classified and stored as a third keyword, and the estimation unit includes the third keyword in the character information recognized by the voice recognition unit, and is detected from the room by the detection unit. When the exit of a person is detected, the execution of the care action corresponding to the third keyword is confirmed.

  According to a fifth aspect of the present invention, the information processing apparatus includes a notification unit that notifies the estimation result obtained by the estimation unit.

  As effects of the present invention, the following effects can be obtained.

  In Claim 1, the effort which inputs the implemented care act can be reduced.

  In Claim 2, since the said estimation can be performed using the voice of the person (caregiver) important for estimation of a care act, the precision of estimation can be improved.

  In Claim 3, the precision of estimation whether the care act was actually performed can be improved.

  According to the fourth aspect of the present invention, it is possible to improve the accuracy of estimation as to whether or not a nursing care action (toilet assistance, etc.) requiring a person leaving the room has actually been performed.

  In Claim 5, the implemented care act can be grasped | ascertained easily.

The figure which shows the structure of the care act estimation system which concerns on one Embodiment of this invention. The figure which shows the keyword list of the care act estimation system which concerns on one Embodiment of this invention. The flowchart which shows the estimation control of the care act estimation system which concerns on one Embodiment of this invention. The figure which shows the keyword list of the care act estimation system which concerns on 2nd embodiment of this invention. The flowchart which shows the estimation control of the care action estimation system which concerns on 2nd embodiment of this invention. The figure which shows the aspect of the estimation of a toilet assistance act. The figure which shows the aspect of the estimation of a toilet assistance act. The figure which shows the structure of the care act estimation system which concerns on 3rd embodiment of this invention.

  First, the outline | summary of a structure of the nursing care action estimation system 1 which concerns on one Embodiment of this invention is demonstrated using FIG.

  The care action estimation system 1 is a system for estimating a care action carried out at a care site. A user (caregiver or the like) of the nursing care activity estimation system 1 can confirm the nursing care activity performed during the nursing service using the estimation result even after the nursing service. In the present specification, the “care service” includes not only public services by business operators but also home care. The care action estimation system 1 is mainly used in a home, a hospital, a nursing home, and the like. The care action estimation system 1 includes a sound acquisition device 10, a human detection device 20, a control device 30, and a data output device 40.

  The sound acquisition device 10 acquires sound such as voice. For example, a microphone is used as the sound acquisition device 10. The sound acquisition device 10 is provided in a room in which care is performed (hereinafter sometimes simply referred to as “room”), and voices generated by caregivers (care staff, etc.) or care recipients in the room, Acquire sound that occurs in the room.

  The human detection device 20 detects the presence of a person in the room. As the human detection device 20, for example, a human sensor using infrared rays, microwaves, or the like is used. The person detection device 20 is provided in a room where care is performed, and detects the presence of a person in the room.

  The control device 30 performs data storage and analysis. The control device 30 includes a storage unit such as a RAM and a ROM, an arithmetic processing unit such as a CPU, and the like. The control device 30 has a voice recognition function for recognizing voice as character information, and the voice obtained by the sound acquisition device 10 is converted into character information by the function (hereinafter referred to as “voice text”). Can be created. The control device 30 associates the voice text with the time information and stores the voice text in the storage unit (so that the time when the voice is uttered can be known).

  In addition, the control device 30 has a speaker recognition function for identifying who the voice acquired by the sound acquisition device 10 is (the individual who emitted the voice). The control device 30 compares the voice acquired by the sound acquisition device 10 with the voice data of a caregiver or the like stored in advance in the storage unit, and identifies the individual who emitted the voice.

  In addition, the control device 30 stores a list of keywords that serve as determination criteria for estimating the performed care action in the storage unit (see FIG. 2). The list shown in FIG. 2 includes a first keyword indicating the type of care action (for example, “toilet”, “bath”, “bathing”, “meal”, “rehabilitation”, “change of clothes”, “vital”, “ Exchange sheets, etc.), the second keyword indicating the execution of the nursing care action, specifically, the keyword indicating the start of the nursing care action (for example, “do”, “do”, “start”, “start” ”,“ Let ’s go ”, etc.), and keywords that indicate the completion of care (for example,“ Done ”,“ Done ”,“ End ”,“ End ”,“ End ”, "Completed") is included, and the first keyword and the second keyword are classified and stored.

  The control device 30 estimates the nursing action based on the voice text and the keywords stored in the list shown in FIG. Specifically, the control device 30 determines whether or not the extracted speech text includes a keyword stored in the list shown in FIG. 2, and based on the included keyword, Estimate the contents.

  The data output device 40 outputs various data. As the data output device 40, for example, a printer is used. The data output device 40 is electrically connected to the control device 30 and can output an estimation result of the care action by the control device 30.

  Hereinafter, with reference to FIG. 3, the control (estimation control) related to the estimation of the nursing care action will be described.

  In step S <b> 10, the control device 30 determines whether or not sound is acquired by the sound acquisition device 10.

  When it is determined that the sound is acquired by the sound acquisition device 10 (“YES” in step S10), the control device 30 proceeds to step S12. On the other hand, when it is determined that no sound has been acquired by the sound acquisition device 10 (“NO” in step S10), the control device 30 ends the estimation control illustrated in FIG.

  In step S12, the control device 30 converts the voice acquired by the sound acquisition device 10 into character information by the voice recognition function to create a voice text. After performing the process of step S12, the control device 30 proceeds to step S14.

  In step S <b> 14, the control device 30 identifies (specifies) the person (speaker) who has uttered the sound acquired by the sound acquisition device 10 by the speaker identification function. When there are a plurality of speakers, the control device 30 sets a tag for each person (speaker) specified by the speaker identification function, and classifies the speech text for each set tag. After performing the process of step S14, the control device 30 proceeds to step S16.

  In step S <b> 16, the control device 30 determines whether there is a caregiver's voice in the acquired sound. In this step, the control device 30 makes this determination based on the classification performed in step S14. At that time, the control device 30 may delete the voice text other than the caregiver.

  When it is determined that there is a caregiver's voice (“YES” in step S16), the control device 30 proceeds to step S18. On the other hand, when it is determined that there is no caregiver's voice (“NO” in step S16), the control device 30 ends the estimation control shown in FIG.

  In step S <b> 18, the control device 30 determines whether or not the caregiver's voice text includes a first keyword indicating the type of care action. In this step, the control device 30 determines whether or not the extracted voice text of the caregiver includes the first keyword shown in FIG. 2 (keyword indicating the type of care action such as “toilet” and “change of clothes”). Determine whether.

  When it is determined that the extracted speech text includes the first keyword (“YES” in step S18), the control device 30 proceeds to step S20. On the other hand, when it is determined that the extracted speech text does not include the first keyword (“NO” in step S18), the control device 30 ends the estimation control illustrated in FIG.

  In step S20, the control device 30 estimates the type of care action. In this step, the control device 30 estimates the type of care action based on the first keyword (keyword indicating the type of care action) included in the extracted speech text.

  For example, it is assumed that the sound acquisition device 10 has acquired the voice “Let's change your clothes” issued by a caregiver. In this case, since the first keyword “change of clothes” is included in the voice text of the caregiver, the control device 30 estimates that the type of care action performed is “help of change of clothes”.

  After performing the process of step S20, the control device 30 proceeds to step S26.

  In step S <b> 26, the control device 30 determines whether or not the extracted voice text includes a second keyword indicating execution of a care act. Specifically, the control device 30 adds keywords (“Shi”, “Saisho”, “Start”), “Start” to the start of the nursing care action shown in FIG. )), Or keywords that indicate the completion of nursing care (such as “Done”, “Done”, “End”, “Ended”, “Ended”, “Ended”, etc.) It is determined whether or not.

  When it is determined that the extracted speech text includes the second keyword (“YES” in step S26), the control device 30 proceeds to step S28. On the other hand, when it is determined that the extracted speech text does not include the second keyword (“NO” in step S26), the control device 30 ends the estimation control illustrated in FIG.

  In step S <b> 28, the control device 30 estimates that a care act has been performed. In this step, the control device 30 estimates that the nursing care action (help for changing clothes) estimated based on the first keyword included in the extracted speech text (see step S20) was actually performed (see step S20). Confirm the implementation of nursing care).

  For example, the control device 30 includes the second keyword (keyword indicating the start of the care action) of “let's change” in the caregiver's voice text “Let's change clothes”, and thus the estimation is made in step S20. It is presumed that “Assistance for changing clothes”, which is an act of nursing care, has started.

  Furthermore, it is assumed that after the “Let's change your clothes”, the sound acquisition device 10 has acquired the voice “Now you ’ll finish changing your clothes” issued by the caregiver. In this case, the control device 30 includes the second keyword (keyword indicating the completion of the nursing care action) of “finishing” in the voice text of the caregiver, and thus is the nursing care action estimated in step S20. It is presumed that “Assistance for changing clothes” has been completed.

  As a result, the control device 30 estimates that “assistance for change of clothes”, which is the care action estimated in step S20, has been executed. In addition, the control device 30 determines the time when the second keyword “Let's start” indicating the start of the nursing care action is issued based on the time information associated with the voice text, and the second time indicating the completion of the nursing care action. The time when the keyword “End” is issued is extracted, and thereby the start time and completion time of the care act “Assistance for changing clothes” based on the first keyword are calculated.

  After performing the process of step S28, the control device 30 proceeds to step S30.

  In step S30, the control device 30 stores the care action data. The control device 30 uses the estimated type of care action (see step S20), the fact that the care action was actually performed, the start time and completion time of the care action (see step S28), etc. as care action data. Store (record) in the storage unit. The control device 30 can notify the user of the care action data via the data output device 40 in response to a request from the user (caregiver or the like).

  The control apparatus 30 complete | finishes the estimation control shown in FIG. 3, after performing the process of the said step S30.

  Note that the estimation control shown in FIG. 3 is performed when the silent state continues for a predetermined period after the process of step S30 (when no sound is input to the sound acquisition apparatus 10 for a predetermined period). The process may be ended when a keyword related to the end is input, or when the person detecting device 20 detects that the number of people in the room has decreased to the original number of people (care recipients only).

  As described above, in the nursing care action estimation system 1, it is possible to acquire a conversation during a nursing service (speech uttered by a caregiver) and to estimate the implementation contents of the nursing action based on the acquired conversation. Therefore, it is possible to reduce the trouble of inputting the content of the nursing care action performed during the nursing care service after the nursing care service for the application of the nursing care reward. Moreover, the estimated result of the care act can be automatically recorded without the caregiver stopping the work during the care service. In addition, since the estimation result can be output via the data output device 40, a caregiver or the like can easily confirm the performed care action even after the care service.

  In addition, since the estimation is based on the second keyword indicating the execution of the care act as well as the first keyword indicating the type of the care act (see Steps S26 and S28), the estimation of whether the care act is actually performed is performed. Accuracy can be improved. It is also possible to grasp the time when the care act was performed.

  In addition, since the caregiver's voice can be specified even in an environment where various sounds fly (see steps S14 and S16), information necessary for estimating the care action can be narrowed down. For this reason, the accuracy of estimation can be improved.

  In addition, by enabling cooperation with various IoT devices, it is possible to add functions and improve recording accuracy.

As described above, the nursing care activity estimation system 1 according to the present embodiment includes a sound acquisition device 10 (voice acquisition unit) that acquires voice, and a control device 30 (voice recognition unit) that recognizes the acquired voice as character information. And the control device 30 (storage unit) that stores a first keyword indicating the type of care action, and the character information recognized by the control device 30 (voice recognition unit) is compared with the first keyword. The control apparatus 30 (estimation part) which estimates the implemented nursing action by this is comprised.
By comprising in this way, the effort which inputs the implemented nursing care act can be reduced.

Moreover, the nursing care activity estimation system 1 according to the present embodiment includes a control device 30 (personal identification unit) that identifies the individual who has uttered the acquired voice, and the control device 30 (estimation unit) The estimation is performed using a voice uttered by a specific individual extracted based on the identification result of the device 30 (personal identification unit).
By comprising in this way, since the said estimation can be performed using the audio | voice of a person (caregiver) important for estimation of a care act, the precision of estimation can be improved.

In addition, the control device 30 (storage unit) stores a second keyword indicating execution of the care action corresponding to the first keyword, and the control device 30 (estimation unit) stores the control device 30 (voice). If the first keyword is included in the character information recognized by the recognizing unit) and the second keyword is included, the implementation of the care action corresponding to the first keyword is confirmed. To do.
By configuring in this way, it is possible to improve the accuracy of estimation of whether or not the care act has actually been performed.

Moreover, the nursing care activity estimation system 1 according to the present embodiment includes a data output device 40 (notification unit) that notifies the estimation result by the control device 30 (estimation unit).
By comprising in this way, the implemented care act can be grasped | ascertained easily.

Note that the sound acquisition device 10 according to the present embodiment is an embodiment of a sound acquisition unit.
In addition, the human detection device 20 according to the present embodiment is an embodiment of a detection unit.
In addition, the control device 30 according to the present embodiment is an embodiment of a voice recognition unit, a storage unit, an estimation unit, and a personal identification unit.
The data output device 40 according to the present embodiment is an embodiment of a notification unit.

  As mentioned above, although one Embodiment of this invention was described, this invention is not limited to the said structure, A various change is possible within the range of the invention described in the claim.

  For example, in this embodiment, not only the determination based on the first keyword (see step S18) but also the determination based on the second keyword (see step S26) is performed, but the determination based on the first keyword is performed. It is good also as what estimates the implemented care act by performing only (refer step S18).

  In the present embodiment, the caregiver's voice is identified and the estimation is performed based on the caregiver's voice (text). However, the estimation may be performed based on all the voices or the caregiver. It is good also as what estimates based on the audio | voice of persons other than a person (caregivers etc.).

  Moreover, in this embodiment, although the case where both the keyword which shows the start of a nursing care act, and the keyword which shows completion of a nursing care action was included as a 2nd keyword was demonstrated as an example, the control apparatus 30 was demonstrated. If the voice text contains either a keyword indicating the start of a care act or a keyword indicating the completion of a care action, the execution of the care action is estimated in steps S26 and S28 (step S28). Data can be stored (step S30).

  In the present embodiment, when the voice text does not include the second keyword (“NO” in step S26), it is assumed that the implementation of the care action is not estimated (the care action data is not stored). Even if “NO” is determined in step S <b> 26, the device 30 may estimate the execution of the nursing care action (store the nursing care action data). At this time, the control device 30 may store the nursing care action data by changing the level of the possibility of implementation between “YES” and “NO” in step S26. Specifically, in the case of “YES” in step S26, the control device 30 shows that there is a high possibility that the nursing action is actually performed, compared to the case of “NO” in step S26. The care activity data may be stored.

  In the present embodiment, the keyword indicating the start of the nursing care action (for example, “I will do”, “I will do”, “I will start”, “I will start”, “Let's go”, etc.) is the second. However, it may be included in the first keyword. That is, the first keyword may be a keyword indicating the type of care action and the start of the care action (for example, “toilet”, “let's take a toilet”, “let's go to the toilet”, etc.). Secondly, keywords that indicate the completion of nursing care (for example, “Done”, “Done”, “End”, “Ended”, “Ended”, “Ended”, etc.) It is good also as a keyword.

  In this embodiment, the estimation control shown in FIG. 3 is always executed. However, it is assumed that the estimation control shown in FIG. 3 is executed at a fixed time, for example, at the end of the day. It is good also as what analyzes and estimates a care act.

  Next, the nursing care action estimation system 1 according to the second embodiment of the present invention will be described with reference to FIGS. 4 to 6.

  The care action estimation system 1 according to the second embodiment is different from the first embodiment in the list stored in the storage unit of the control device 30. Specifically, as shown in FIG. 4, in the list according to the second embodiment, the first keyword indicating the type of care action is an action that requires leaving the room (for example, “toilet”, “bath” ”,“ Bathing ”,“ meal ”,“ rehabilitation ”, etc.) and actions that do not require leaving the room (for example,“ changing clothes ”,“ vital ”,“ sheet changing ”, etc.) Yes.

  Further, the main difference between the estimation control according to the second embodiment shown in FIG. 5 and the estimation control according to the first embodiment shown in FIG. 3 is that the processes of step S22 and step S24 are further performed. Therefore, in the following, the same steps as the estimation control shown in FIG. 3 in the estimation control shown in FIG.

  The control device 30 proceeds to step S22 after performing the process of step S20 (estimation of the type of care action).

  In step S22, the control device 30 determines whether or not the care action estimated based on the first keyword indicating the type of care action is an action that requires the person to leave the room. The control device 30 makes this determination based on the classification of the list shown in FIG.

  When it is determined that the care action estimated based on the first keyword is an action that requires the person to leave the room (“YES” in step S22), the control device 30 proceeds to step S24.

  In step S24, the control device 30 determines whether or not a person has left the room. When it is determined that the number of people in the room has decreased based on the detection result of the human detection device 20, the control device 30 determines that a person has left the room.

  When it is determined that a person has left the room (“YES” in step S24), the control device 30 proceeds to step S28. On the other hand, when it is determined that no person has left the room (“NO” in step S24), the control device 30 ends the estimation control shown in FIG.

  On the other hand, when it is determined that the care action estimated based on the first keyword is not an action that requires the person to leave the room ("NO" in step S22), the control device 30 proceeds to step S26. . In step S <b> 26, the control device 30 determines whether or not the extracted voice text includes a second keyword indicating execution of a care act, as in the first embodiment. When it is determined that the extracted speech text includes the second keyword (“YES” in step S26), the control device 30 proceeds to step S28. On the other hand, when it is determined that the extracted speech text does not include the second keyword (“NO” in step S26), the control device 30 ends the estimation control illustrated in FIG. Subsequent processing is the same as in the first embodiment.

  Hereinafter, a specific example will be described. As shown in FIG. 6, for example, it is assumed that the sound acquisition device 10 has acquired the voice “Let's go to the toilet” issued by the caregiver. In this case, since the first keyword “toilet” is included in the voice text of the caregiver in step S <b> 20, the control device 30 estimates that the type of the care action performed is “toilet assistance”. .

  Then, in step S22, the control device 30 needs the person to leave the room for the care action (toilet assistance) estimated based on the first keyword “toilet” based on the list shown in FIG. It is determined that the action is an act ("YES" in step S22).

  Thereafter, when the control device 30 determines that the number of people in the room has decreased based on the detection result of the human detection device 20, the person (for example, the caregiver A and the care receiver B) has left the room. Determination is made (“YES” in step S24). If it does so, the control apparatus 30 will estimate that the care act (help of a toilet) was actually performed (refer step S28).

  In this way, when a nursing action is performed outside the room, it is possible to estimate the implementation of the nursing action more accurately.

As described above, the nursing care activity estimation system 1 according to the second embodiment includes the human detection device 20 (detection unit) that detects the exit of a person from the room, and the control device 30 (storage unit) Of the one keyword, a keyword indicating the type of care action that requires the person to leave the room is classified and stored as a third keyword, and the control device 30 (estimating unit) When the third keyword is included in the character information recognized by the voice recognition unit) and the person detection device 20 detects a person leaving the room, it corresponds to the third keyword. This is to confirm the implementation of nursing care activities.
By configuring in this way, it is possible to improve the accuracy of estimation of whether or not a nursing care action (such as toilet assistance) that requires the person to leave the room has actually been performed.

  The second embodiment of the present invention has been described above, but the present invention is not limited to the above-described configuration, and various modifications can be made within the scope of the invention described in the claims.

  For example, in the second embodiment, a person's exit from a room is detected by a human sensor (see step S24), but may be detected by an IC card, a GPS, a camera, or the like. It may be detected based on the opening / closing sound of the door acquired by.

  In the second embodiment, the control device 30 determines that the acquired voice text includes the first keyword indicating the type of care action (see step S18) and that the person has left the room. (See step S24), it is assumed that the care act was actually performed (confirmed implementation), but the acquired voice text further includes a second keyword ("going to" It may be estimated that the nursing care action was actually performed.

  In the second embodiment, when it is determined that there is no person leaving the room (“NO” in step S24), the control device 30 ends the estimation control shown in FIG. Even if “NO” in step S <b> 24, the device 30 may estimate the implementation of the nursing care action (store the nursing care action data). At that time, the control device 30 may store the nursing care action data by changing the level of the possibility of implementation between “YES” and “NO” in step S24. Specifically, in the case of “YES” in step S24, the control device 30 understands that there is a high possibility that the nursing action is actually performed, compared to the case of “NO” in step S24. The care activity data may be stored.

  In addition, as shown in FIG. 7, the nursing care activity estimation system 1 acquires the nursing care keywords (“toilet”, “suru”, etc.) in the destination (toilet) as well as the original room, and Assuming that a person (caregiver A and cared person B) not only exits the room but also enters the toilet, it is assumed that a care act (toilet assistance) was actually performed. Good.

  Moreover, in order to improve the accuracy of the estimation of the nursing care action as in the nursing care action estimation system 2 according to the third embodiment shown in FIG. 8, the image acquisition device (camera) 50, the indoor environment sensor 60, the vital sensor Various sensors such as 70 and the triaxial acceleration sensor 80 may be provided, and the data of these devices may be utilized by the control device 30. By providing the image acquisition device (camera) 50, it is possible to assist the estimation of the nursing care action, and the accuracy of the estimation can be improved. By providing, for example, a thermometer as the indoor environment sensor 60, it is possible to assist in detecting the presence / absence of a room. By providing, for example, an odor sensor as the indoor environment sensor 60, it is possible to assist in estimating the nursing action “diaper exchange”. By providing the vital sensor 70 (for example, a pulse meter), it is possible to grasp a change in vital signs, and based on this, it is possible to assist in determining whether to perform a nursing action. By providing the triaxial acceleration sensor 80, it is possible to assist in determining whether or not a person has moved out of the room (withdrawal and entry).

DESCRIPTION OF SYMBOLS 1 Nursing care estimation system 10 Sound acquisition device 20 Human detection device 30 Control device 40 Data output device

Claims (5)

An audio acquisition unit for acquiring audio;
A voice recognition unit that recognizes the acquired voice as character information;
A storage unit for storing a first keyword indicating a type of care action;
An estimation unit that estimates an implemented care action by comparing the character information recognized by the voice recognition unit with the first keyword;
Comprising
Nursing care estimation system. Comprising a personal identification unit for identifying the individual who uttered the acquired voice;
The estimation unit includes
Extracting based on the identification result of the personal identification unit, using the voice uttered by a specific individual, to perform the estimation,
The nursing care activity estimation system according to claim 1. The storage unit
Storing a second keyword indicating execution of a care act corresponding to the first keyword;
The estimation unit includes
When the first keyword is included in the character information recognized by the voice recognition unit and the second keyword is included, the care action corresponding to the first keyword is performed. Determine,
The nursing care action estimation system according to claim 1 or 2. It has a detection unit that detects the exit of a person from the room,
The storage unit
Among the first keywords, a keyword indicating a type of care action that requires a person to leave the room is classified and stored as a third keyword,
The estimation unit includes
When the third keyword is included in the character information recognized by the voice recognition unit, and a person leaving the room is detected by the detection unit, the care corresponding to the third keyword Confirm the conduct of the action,
The care act estimation system according to any one of claims 1 to 3. A notification unit for notifying the result of the estimation by the estimation unit;
The care act estimation system according to any one of claims 1 to 4.

Images