JP2022095619A - Recuperation support system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a recuperation support system capable of providing batter service.

SOLUTION: A recuperation support system includes a biological sensor for detecting a biological state of an object person, and a voice sensor for detecting a voice of the object person. The recuperation support system provides output information including at least one of visual information and auditory information that vary according to an emotional state of the object person estimated based on at least one of the biological state and the voice.

SELECTED DRAWING: Figure 1

COPYRIGHT: (C)2022,JPO&INPIT

Description

An embodiment of the present invention relates to a medical treatment support system.

Care recipients such as the elderly receive medical treatment at homes, hospitals, or long-term care facilities. In medical treatment, a medical treatment support system that can provide better services to care recipients, families, medical staff, long-term care staff, etc. is desired.

Japanese Unexamined Patent Publication No. 2002-41671

An embodiment of the present invention provides a medical treatment support system capable of providing better services.

According to the embodiment, the medical treatment support system includes a biological sensor for detecting the biological state of the subject and a sound sensor for detecting the voice of the subject. The medical treatment support system provides output information including at least one of visual information and auditory information that changes according to the emotional state of the subject estimated based on at least one of the biological state and the voice. ..

An embodiment of the present invention can provide a medical treatment support system that can provide better services.

1 (a) to 1 (d) are schematic views illustrating the medical treatment support system according to the first embodiment. FIG. 2 is a schematic diagram illustrating information used in the medical treatment support system according to the embodiment. 3A and 3B are schematic views illustrating the operation of the medical treatment support system according to the first embodiment. 4 (a) to 4 (c) are schematic views illustrating the medical treatment support system according to the second embodiment. 5 (a) to 5 (d) are schematic views illustrating the medical treatment support system according to the third embodiment. 6 (a) to 6 (c) are schematic views illustrating the medical treatment support system according to the fourth embodiment. 7 (a) to 7 (c) are schematic views illustrating the medical treatment support system according to the fifth embodiment.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
In the present specification and each figure, the same elements as those described above with respect to the above-mentioned figures are designated by the same reference numerals, and detailed description thereof will be omitted as appropriate.

(First Embodiment)
1 (a) to 1 (d) are schematic views illustrating the medical treatment support system according to the first embodiment.
1 (b) to 1 (d) schematically illustrate various information (data or signals) in the medical treatment support system.

As shown in FIG. 1A, the medical treatment support system 110 according to the present embodiment includes a biological sensor 20 and a sound sensor 11.

The biological sensor 20 detects the biological state of the subject 81.

The subject 81 is a recuperator. The target person 81 receives support from the supporter 80. The supporter 80 includes, for example, at least one of a doctor 83, a nurse 82a, a caregiver 82b, and a family member 82c. The nurse 82a (or caregiver 82b) has, for example, a recognition tag 82s (eg, an ID tag, etc.).

The subject 81 receives support from the supporter 80, for example, at the subject 81's house, hospital, or long-term care facility. The subject 81 is, for example, a care recipient.

According to the medical treatment support system 110 according to the embodiment, for example, at least one of the target person 81 and the supporter 80 receives a service (a service related to medical treatment of the target person 81).

For example, the subject 81 is, for example, a user of the bed 70. The bed 70 is, for example, an electric bed. In this example, the bed 70 includes a bottom 71 and a mattress 76. The mattress 76 is placed on the bottom 71. The subject 81 lies on the mattress 76.

In this example, the biosensor 20 is provided between the bottom 71 and the mattress 76. The biosensor 20 detects, for example, a force (including vibration) applied to the biosensor 20. For example, a force (vibration, etc.) according to the state of the subject 81 on the mattress 76 is detected by the biosensor 20. For example, at least a part of the biological state of the subject 81 may be detected by a load sensor provided on the bed 70 or the like.

Biological conditions include, for example, at least one of heart rate, pulse rate, respiratory rate, body temperature, blood pressure, blood oxygen saturation, body weight, sleep, arousal, getting out of bed, rising and sitting. Blood oxygen saturation includes, for example, percutaneous arterial oxygen saturation (SpO2). The biological state may be detected automatically, for example, continuously.

As the biological sensor 20, a sensor or the like attached to or attached to the body (or clothes) of the subject 81 may be used.

The signal (information) obtained by the biosensor 20 is transmitted to, for example, the communication device 25. Any wired or wireless method may be applied to this transmission.

The sound sensor 11 detects the voice V0 of the subject 81. The sound sensor 11 may further detect the voice of the supporter 80 (for example, at least one of a nurse 82a, a caregiver 82b, and a family member 82c). The sound sensor 11 is, for example, a microphone.

The sound sensor 11 is included in, for example, the support device 10. The support device 10 includes a housing 14. The sound sensor 11 is provided in the housing 14. In this example, the support device 10 is further provided with a sound generation unit 12, a short-range communication unit 15, and a transmission / reception unit 13.

The sound generation unit 12 is, for example, a speaker. As will be described later, the sound generation unit 12 outputs voice to, for example, the target person 81 or the supporter 80 (for example, at least one of a nurse 82a, a caregiver 82b, and a family member 82c).

The short-range communication unit 15 recognizes the recognition tag 82s of the nurse 82a (or the caregiver 82b, etc.). At least a part of the operation of the support device 10 may be controlled by the recognition of the nurse 82a.

The transmission / reception unit 13 transmits / receives (communicates) a signal with, for example, the communication device 25. Any wired or wireless method may be applied to this communication.

The signal (information) regarding the voice V0 of the subject 81 detected by the sound sensor 11 is supplied to the voice information database DB 1 via the communication device 25. On the other hand, the signal (information) obtained by the biological sensor 20 is supplied to the biological information database DB 2 via the communication device 25. These databases may be provided on the cloud, for example.

The voice recognition process is performed based on the voice information database DB1. The voice corresponding to the voice V0 of the subject 81 is analyzed by the physical feature amount. The emotion of the subject 81 is estimated based on the physical feature analysis. For example, emotional tendencies are analyzed from the voice data of the subject 81. The physical feature quantity includes, for example, at least one of an outline of the spectrum of speech, a spectral power of speech, a pitch F0 of speech, and a spectral flatness SFM of speech. Emotions are, for example, classified by a plurality of types. The plurality of types include, for example, at least one of normality, joy, anger and sadness. The emotion of the subject 81 is converted into a numerical value (for example, an emotion parameter) according to the type of emotion. For example, the heightened emotions are expressed by emotional parameters (numerical values). For example, emotions may be analyzed based on Russell's annulus model and the like. Numerical values are derived from the results of the analysis. Temporal changes in emotional parameters corresponding to the emotions of the subject 81 are derived.

On the other hand, based on the biological information database DB2, the temporal change of the biological state of the subject 81 is derived. For example, the biometric information parameter D1 is derived for each of heart rate, pulse rate, respiratory rate, body temperature, blood pressure, blood oxygen saturation, body weight, sleep, arousal, getting out of bed, getting up and sitting. For example, thresholds are set for each biometric parameter D1 of heart rate, pulse rate, respiratory rate, body temperature, blood pressure, blood oxygen saturation, weight, sleep, arousal, getting out of bed, getting up and sitting. .. When the measured value of the biological information parameter D1 exceeds the threshold value, it is determined to be in an abnormal state. Alternatively, when the measured value exceeds the threshold value for two or more combinations of the plurality of biometric information parameters D1, it may be determined to be an abnormal state.

FIG. 1B schematically illustrates the temporal change of the audio signal V1 corresponding to the voice V0 of the subject 81. FIG. 1 (c) schematically illustrates the temporal change of the emotion parameter E1 derived from the audio signal V1. FIG. 1D schematically illustrates the temporal change of the biological information parameter D1 corresponding to the biological state of the subject 81. The horizontal axis of these figures is time t.

For example, as shown in FIG. 1 (d), a state (abnormal state) in which the biological information parameter D1 exceeds the threshold value DL1 is detected. In this example, the biological information parameter D1 is blood pressure. In this example, an abnormal state occurs at the first time t1 and the second time t2. In addition to physical abnormalities, emotional abnormalities are thought to affect abnormal blood pressure.

In the present embodiment, the emotion parameter E1 is derived based on the temporal change of the audio signal V1 (see FIG. 1 (b)) (see FIG. 1 (c)). In this example, the emotional parameter E1 changes significantly at the first time t1. At the second time t2, the change in the emotion parameter E1 is small.

For example, the following situations can be considered. The grandchildren of the subject 81 participated in the sports competition. Before and after the first time t1, the sports competition was broadcast on television. The subject 81 watched the broadcast. Therefore, at the first time t1, the emotional parameters of the subject 81 changed significantly.

At the second time t2, the emotion parameter E1 is not abnormal. Therefore, it is considered that the abnormal state (high blood pressure state) of the biological information parameter D1 at the second time t2 is caused by the abnormal state of the body. For example, the abnormal state of the biological information parameter D1 at the second time t2 is likely to indicate a dangerous state.

On the other hand, at the first time t1, the emotion parameter E1 is abnormal. Therefore, it is considered that the abnormal state (high blood pressure state) of the biological information parameter D1 at the first time t1 is due to the influence of the above-mentioned television broadcasting.

By paying attention to the emotional parameter E1 in addition to the biological information parameter D1, it is considered that the state of the subject 81 can be grasped more accurately. For example, the doctor 83 grasps the state of the subject 81 by grasping the biological state of the subject 81. At this time, by grasping the emotional change of the subject 81 together with the biological state, the state of the subject 81 can be grasped more accurately.

As shown in FIG. 1A, in the embodiment, for example, the display device 83D (for example, the providing unit) used by the doctor 83 (supporter 80) has the emotion parameter E1 in addition to the biological information parameter D1. The corresponding emotion information ES1 is displayed. For example, as the emotion information ES1, a pictogram based on the emotion parameter E1 may be displayed. Thereby, the doctor 83 can grasp the biological information parameter D1 more accurately, for example, excluding the influence of emotions.

As described above, the medical treatment support system 110 according to the embodiment uses, for example, the emotional information ES1 corresponding to the emotional state of the subject 81, and the biological information based on at least a part of the biological state of the subject 81 (for example, the biological information parameter D1). ). As described above, this emotional state is estimated based on the voice V0 of the subject 81 detected by the sound sensor 11. For example, the emotional state of the subject 81 is estimated by performing voice recognition processing on the voice based on the voice V0.

According to the embodiment, the supporter 80 (for example, a doctor 83) can more accurately grasp the biological state except for the influence of emotional changes. Thereby, the supporter 80 can provide the subject 81 with a treatment for more appropriate medical treatment. According to the embodiment, it is possible to provide a medical treatment support system that can provide better services.

For example, when the output information OS is provided to the display device 83D (for example, the providing unit) from the medical treatment support system 110 according to the embodiment, the above display is performed on the display device 83D. The output information OS in this case corresponds to the visual information VS. As will be described later, auditory information may be provided from the medical treatment support system 110. For example, the medical treatment support system 110 provides an output information OS including at least one of visual information VS and auditory information. This output information OS changes according to the emotional state of the subject 81. The emotional state of the subject 81 is estimated based on at least one of the biological state and the voice V0. For example, the visual information VS includes an image signal (data) or a video signal (data). By supplying the visual information VS to the display device, the display device performs the display according to the visual information VS. The visual information VS may include a displayed image or video.

In the embodiment, the derivation of the emotional information ES1 corresponding to the emotional state of the subject 81 is performed by, for example, the processing unit 60. Then, the derivation of the biological information (for example, the biological information parameter D1) based on at least a part of the biological state of the subject 81 is performed by, for example, the processing unit 60. The processing unit 60 may be provided on the cloud, for example. The processing unit 60 may be provided in, for example, the support device 10. The processing unit 60 may be provided in, for example, a computer including the display device 83D.

In the embodiment, at least one of the detection of the voice V0, the voice recognition of the voice obtained from the voice V0, and the estimation of the emotional state may be started based on the detection result by the biosensor 20. For example, if voice recognition is constantly performed, the processing unit 60 is required to have high processing capacity (including processing speed). Further, a high communication speed is required for communication with the processing unit 60. At this time, the demand for the processing unit 60 and the communication speed is relaxed by performing voice recognition or the like when necessary.

For example, when the biological state detected by the biological sensor 20 is determined to be an abnormal state, the detection of voice V0 is started. Alternatively, once the biological state is determined to be an abnormal state, the estimation of the emotional state may be started. Emotional state estimation includes, for example, at least a portion of speech recognition processing. This makes it possible to provide a medical treatment support system that is easier to use.

For example, biological conditions are continuously detected. Then, the emotional state based on the voice V0 is estimated by using the time when the biological state is determined to be abnormal as a trigger. Efficient emotional state estimation is possible.

For example, if the short-range communication unit 15 recognizes the recognition tag 82s of the nurse 82a (or the caregiver 82b, etc.), even if the detection of the voice V0 or the estimation of the emotional state (including voice recognition) is started. good.

For example, the motion sensor 16 may be provided in the support device 10. When the motion sensor 16 detects that the supporter 80 has approached the subject 81, the detection of the voice V0 or the estimation of the emotional state (including voice recognition) may be started.

For example, when the sound sensor 11 detects that the supporter 80 has spoken to the target person 81, the estimation of the emotional state (including voice recognition) may be started.

Further, in the embodiment, the support-requiring state of the subject 81 may be estimated. The support-requiring state is estimated, for example, based on at least one of the biological state and the voice V0. Support-requiring conditions include at least one of subject 81's deterioration of health, restlessness, excretion, pressure ulcers, and the possibility of falling. For example, by detecting the biological condition of the subject 81, for example, it is possible to grasp (predict) the deterioration of the health condition, restlessness, excretion, pressure ulcer, and at least immediately before the fall. For example, by voice recognition processing based on the voice V0 of the subject 81, it is possible to grasp (predict), for example, deterioration of health condition, restlessness, excretion, pressure ulcer, and at least immediately before any one of falls. can.

In the embodiment, the medical treatment support system 110 may further inform the supporter 80 of such a support-requiring state of the target person 81. For example, the support-requiring state may be notified by a sound generating unit 12 (speaker) or a lamp provided in the support device 10. For example, a display (or sound or vibration) indicating that support is required may be displayed on a display such as a nurse station provided in the facility where the target person 81 is located. A display (or sound or vibration generation, etc.) is displayed on a terminal device (for example, a display device 83D, etc.) owned by a supporter 80 (for example, a doctor 83, a nurse 82a, a caregiver 82b, a family member, etc. 82c). It may be done.

In this way, by notifying the status of support required, more appropriate support can be provided promptly at an appropriate time.

In the present embodiment, the sound generation unit 12 (for example, a speaker) may output the voice S1 (for example, auditory information) directed to the target person 81. For example, the sound generation unit 12 generates a voice S1 including at least one of a question and a call to the subject 81 (see FIG. 1A). This content is related to the health and safety status of the subject 81. This content is determined based on at least one of the biological condition of the subject 81 and the voice V0 of the subject.

For example, when the biological state of the subject 81 is body temperature, when the body temperature is higher than normal temperature, the sound generator 12 asks, "It seems that the heat is high. How is it?" The voice S1 is output. For example, the subject 81 may be generating a voice V0 that seems to be painful. In such a case, the sound generation unit 12 outputs the voice S1 of the content of the question, such as "How is it?".

Then, the sound sensor 11 may further detect another voice of the subject 81 after the generation of the voice S1. The emotional state may then be further estimated based on that other voice.

In this way, when the biological state is detected by the biological sensor 20 and the detected biological state is abnormal, the voice recognition of the subject's voice V0 is started, and the emotional state is estimated. In addition to this, the voice S1 of the content such as a question about the health and safety state may be generated to the subject 81. Then, another voice (answer) of the subject 81 generated in response to the voice S1 is further voice-processed, and the emotional state is estimated. This makes it possible to estimate the emotional state more accurately.

In the medical treatment support system 110, for example, emotions are estimated from voice, and abnormal values of biological information due to temporary emotions are removed. This makes it possible to improve the accuracy of detecting abnormal values for biological information.

The voice S1 (for example, auditory information) corresponds to at least a part of the output information OS provided (output) from the medical treatment support system 110. As described above, the medical treatment support system 110 provides an output information OS including at least one of visual information VS and auditory information (for example, audio S1). The output information OS changes according to the emotional state of the subject 81 estimated based on at least one of the biological state and the voice V0. For example, the auditory information may include a signal (for example, an electric signal) for generating the voice S1. The auditory information may include sound waves generated by the sound generating unit 12 (speaker).

For example, the voice information database DB1 and the care information database DB4 may be associated with each other. For example, the care information database DB4 may be referred to when providing the emotional information ES1 and the biological information (for example, the biological information parameter D1).

The care information database DB4 is, for example, a master database. The care information database DB 4 includes basic information (information specifying the target person 81 or arbitrary information regarding the state of the target person 81). For example, the detailed information of care may be changed depending on the facility where the target person 81 is located. Detailed information on care is stored in the care information database DB4. In such a case, the emotional information ES1 may be provided together with the biological information (for example, the biological information parameter D1) based on the care information database DB4.

FIG. 2 is a schematic diagram illustrating information used in the medical treatment support system according to the embodiment. FIG. 2 illustrates a care code as an example of care information.
As shown in FIG. 2, the care code includes a major classification CL1, a middle classification CL2, a minor classification CL3, and the like. The major classification CL1 is, for example, "bathing, cleanliness, maintenance, and changing clothes". In addition, the major classification CL1 includes "movement / transfer / position exchange", "meal", "excretion", "life independence support", "social life support", "behavioral problems", "medical care", and "function". It may include "training" or "work that is not directly related to the target person". When the major classification CL1 is "bathing / cleanliness / dressing / changing clothes", the middle classification CL2 includes, for example, "bathing" and "cleaning". When the middle classification CL2 is "cleaning", the minor classification CL3 includes "preparation", "verbal action", "caregiving", "watching, etc.", and "cleanup". A code CN is defined for each of the plurality of sub-classifications CL3.

According to such a code CN, the state of the subject 81 is expressed and recorded.

In the medical treatment support system 110, the state of the subject 81 is more accurately grasped by using the care code (care information) stored in the care information database DB 4 in addition to the biological information and the voice recognition information. ..

Information about voice may be added (learned) in the medical treatment support system 110. For example, the subject 81 may make a strange voice by assisting one of the care classifications. In such a case, the strange voice (voice) is treated as noise as voice information. Information about voice treated as noise may be added (learned). Thereby, the state of the subject 81 can be estimated more accurately from the voice.

3A and 3B are schematic views illustrating the operation of the medical treatment support system according to the first embodiment.
As illustrated in FIG. 3A, in the medical treatment support system 110 according to the embodiment, for example, the display device 83D (for example, the providing unit) used by the doctor 83 (supporter 80) is provided with the draft I1 of the interview content. Is displayed. The draft I1 of the interview content is based on, for example, at least one of the biological state detected by the biological sensor 20 and the voice V0 (that is, the voice recognition processing result thereof) detected by the sound sensor 11.

For example, the draft I1 of the interview content is derived based on at least one of the biological state detected by the biological sensor 20 and the voice V0 (or the voice recognition processing result) detected by the sound sensor 11. For example, a database regarding the contents of interviews is provided. From this database, some proposals for the contents of the interview are extracted. The extracted plan is proposed to doctor 83 and the like as plan I1. This can support more appropriate medical examinations.

For example, as already described, the biometric information (biological information parameter D1) and the emotional information ES1 exemplified in FIG. 1A are provided to the doctor 83. Such information is used as a material for the judgment of the interview or the judgment of the prescription. Further, the draft I1 of the contents of the interview and the answers of the subject 81 to the draft I1 are used as the material for the prescription judgment. For example, it is possible to support the visiting doctor to more appropriately grasp the situation of the subject 81.

As illustrated in FIG. 3B, the display device 82D (for example, the providing unit) may be capable of displaying the proposal I2 for asking a question or calling out to the target person 81. The display device 82D is a display device (portable terminal or the like) used by, for example, a nurse 82a, a caregiver 82b, a family member 82c, or the like. The proposal I2 is based on, for example, at least one of the biological state detected by the biological sensor 20 and the voice V0 (and its voice recognition processing) detected by the sound sensor 11.

For example, a proposal I2 for asking a question or calling out to the subject 81 is proposed to the supporter 80 (nurse 82a, caregiver 82b, family member 82c, etc.). For example, as Plan I2, "Ask me if there is any pain?", "Let's say that the flowers by the window have opened", or "I know who I am". A suggestion for a question (or a call) such as "Let's ask?" Is displayed. Based on this plan I2, the supporter 80 talks with the target person 81. As a result, the state of the subject 81 can be known more accurately.

For example, a sign of disturbing behavior due to dementia in the subject 81 can be estimated. For example, the timing of consulting with a doctor 83 or the like for alleviating a situation such as pain can be suggested to a nurse 82a, a caregiver 82b, a family member 82c, or the like.

As described above, the medical treatment support system 110 according to the embodiment can provide a plan (plan I1 or plan I2, etc.) regarding the content (topic, etc.) of the conversation with the target person 81. This provision is performed by, for example, the display device 83D or the display device 82D described above. This proposal may be provided by voice or the like.

The content of the conversation with the subject 81 is related to, for example, the health and safety status of the subject 81. The proposed proposal (such as proposal I1 or proposal I2) is based on at least one of the detected biological conditions and voice V0.

Based on such a plan, the supporter 80 (doctor 83, nurse 82a, caregiver 82b, family member 82c, etc.) conducts an interview or conversation. Then, the subject 81 answers according to the interview or the conversation. The voice of this answer may be further voice-recognized.

For example, the sound sensor 11 receives the voice of the supporter 80 of the target person 81 (question based on the plan I2 or the like) and another voice (answer) of the target person 81 generated in response to the voice of the supporter 80. Further detect. This voice of supporter 80 includes content based on at least a portion of the above provided proposals (such as proposal I1 or proposal I2). Then, the emotional state may be further estimated based on the other voice (answer).

Further, the voice of the supporter 80 of the target person 81 (question based on the plan I2, etc.) and another voice (answer) of the target person 81 generated in response to the voice of the supporter 80 are reproduced. It may be provided to a doctor 83 or the like. For example, the voice of the supporter 80 of the target person 81 and another voice (answer) of the target person 81 may be voice-recognized and displayed as a sentence. This display may be provided to a doctor 83 or the like.

For example, at the second time t2 illustrated in FIG. 1 (a), it is determined that the biological state is abnormal. At this time, the proposed question I2 as described above is displayed on the display device 82D owned by the nurse 82a. The nurse 82a asks the subject 81 a question based on the plan I2. The voice of the answer of the subject 81 to the question is detected. The voice of the answer is processed by voice. By voice processing, for example, the pain state of the subject 81 is stored as information in the voice information database DB1 or the like. After that, the state of the subject 81 obtained by voice processing is provided to the doctor 83 and the like. As described above, in the embodiment, at least a part of the content corresponding to the above-mentioned other voice (answer of the subject 81) can be further provided.

For example, in one example, the doctor 83 conducts a medical examination after a lapse of time after the biological condition is determined to be abnormal. In another example, medical examinations by the doctor 83 are performed regularly, such as once a week, and the doctor 83 is aware of changes in the biological condition during the week. At this time, when the biological condition is abnormal, the condition of the subject 81 can be known more accurately by receiving the information obtained from the voice of the subject 81 in response to the voice of the question based on the plan I2 or the like. Can be done. A supporter 80 (for example, a doctor 83) can provide a better service to the subject 81.

The above-mentioned plans I1 and I2 correspond to at least a part of the output information OS. Proposal I1 and Proposal I2 may be included in at least one of visual information VS and auditory information (for example, audio S1), for example. Also in this case, the medical treatment support system 110 provides the output information OS. The output information OS changes according to the emotional state of the subject 81 estimated based on at least one of the biological state and the voice V0.

(Second Embodiment)
4 (a) to 4 (c) are schematic views illustrating the medical treatment support system according to the second embodiment.
As shown in FIG. 4A, the medical treatment support system 120 according to the present embodiment also includes a biological sensor 20 and a sound sensor 11. In this example as well, the biosensor 20 is provided on the bed 70 of the subject 81. Hereinafter, the part of the medical treatment support system 120 different from that of the medical treatment support system 110 will be described.

In the medical treatment support system 120, the proposal regarding the content of the conversation with the subject 81 (such as proposal I1 or proposal I2) is based on the detected biological condition and at least one of the voice V0 and the care information. ing. The care information is stored in, for example, the care information database DB4.

For example, based on the biological condition detected by the biological sensor 20, the voice V0 (and its voice recognition processing) detected by the sound sensor 11, or the care information, the draft I1 of the interview content is proposed to the doctor 83 or the like. .. For example, based on the biological condition detected by the biological sensor 20, the voice V0 (and its voice recognition processing) detected by the sound sensor 11, or the care information, a proposal I2 of a question or a voice to the subject 81 can be obtained. It is possible to propose.

In the medical treatment support system 120, the state of the subject 81 is more accurately grasped by using the care code (care information) in addition to the biological information and the voice recognition information.

In the medical treatment support system 120, the voice S1 from the sound generation unit 12 (speaker) may be based on the care code (care information) in addition to the biological information and the voice recognition information. This voice S1 includes at least one of the contents of a question and a call to the subject 81 (contents related to the health and safety state of the subject 81). A more appropriate question or call voice S1 is obtained.

In the medical treatment support system 120, the emotional information corresponding to the emotional state of the subject 81 (such as the emotional information ES1 exemplified in FIG. 1A) is the biological information based on at least a part of the biological state (for example, FIG. 1A). It may be provided together with the biological information parameter D1) exemplified in. This emotional information may be estimated based on the care information in addition to the voice V0. Better services can also be provided in the medical treatment support system 120.

In the medical treatment support system 120, for example, a sign of disturbing behavior due to dementia can be estimated. For example, an appropriate "care response knowledge" can be instantly proposed to nurses 82a, caregivers 82b, family members 82c, and the like. For example, "knowledge" that can be used as a reference for judgments such as interviews can be displayed on the display device 83D (for example, the providing unit) used by the doctor 83. For example, it is possible to support the visiting doctor to grasp the patient situation.

The daily report information database DB3 may be used in the medical treatment support system 120. For example, in the medical treatment support system 120, the long-term care record (for example, daily report information) is further used. For example, the long-term care record is recorded or input by the supporter 80 of the subject 81. The supporter 80 is, for example, a nurse 82a, a caregiver 82b, a family member 82c, or the like. For example, the support (work) by the supporter 80 to the target person 81 is recorded (or input). The recorded (or input) long-term care record is supplied to the daily report information database DB3.

By using the daily report information database DB3, even better services can be provided. For example, the voice information database DB1, the daily report information database DB3, and the care information database DB4 may be related to each other. By using the information stored in the care information database DB4, the state of the subject 81 can be grasped more accurately. Even better service can be provided.

(Third Embodiment)
5 (a) to 5 (d) are schematic views illustrating the medical treatment support system according to the third embodiment.
5 (b) to 5 (d) schematically illustrate various types of information (data or signals) in the medical treatment support system.

As shown in FIG. 5A, the medical treatment support system 130 according to the present embodiment includes a biological sensor 20. The medical treatment support system 130 may further include a display device 83D (an example of a providing unit).

Also in this example, the biological sensor 20 detects the biological state of the subject 81. Also in this example, the biosensor 20 is provided on the bed 70 of the subject 81. As described above, the biosensor 20 may be attached or attached to the body (or clothing) of the subject 81 or the like.

Also in the present embodiment, the medical treatment support system 130 (for example, the display device 83D) uses the emotional information (for example, the emotional parameter E1) corresponding to the emotional state of the subject 81 as the biological information (for example, the biological information) based on at least a part of the biological state. , Provided with the biometric information parameter D1). In this embodiment, emotional information is estimated based on at least a portion of the biological state. For example, emotional information is estimated based on autonomic nervous states derived from at least a portion of the biological state.

For example, the biological state of the subject 81 (for example, heart rate, pulse rate, respiratory rate, body temperature, blood pressure, oxygen saturation of blood, weight, sleep, arousal, getting out of bed, getting up and sitting) is the subject 81. It is associated with autonomic nervous status. Autonomic nerve states include sympathetic and parasympathetic states. The autonomic nervous state of the subject 81 is associated with the emotional state of the subject 81 (at least one of normal, joy, anger, and sadness).

For example, the biological state of the subject 81 is detected by the biological sensor 20. The detection result (biological information, for example, the biological information parameter D1) is supplied to the biological information database DB2 via the communication device 25. The autonomic nervous state N1 of the subject 81 is derived from the biological information (biological information parameter D1). The autonomic nerve state N1 is supplied to the autonomic nerve analysis unit 61. In the autonomic nerve analysis unit 61, the emotional state (for example, the emotional parameter E1) of the subject 81 is derived based on the autonomic nerve state N1. The emotion information ES1 is derived from the emotion parameter E1.

As shown in FIG. 5A, for example, the emotion parameter E1 is displayed on the display device 83D together with the biological information parameter D1. This allows the doctor 83 to more accurately grasp the biological information parameter D1, for example, excluding the influence of emotional changes.

In this embodiment, for example, the sound sensor 11 can be omitted. The autonomic nervous state is derived by the biological sensor 20 that detects the biological state. Based on this autonomic nervous state, the emotional state of the subject 81 is estimated. Therefore, in the medical treatment support system 130, the configuration becomes simple.

In the medical treatment support system 130, the support-requiring state of the subject 81 may be notified. In this case, the support-requiring state is estimated based on at least one of the biological state and the autonomic nervous state. Support-requiring conditions include at least one of subject 81's deterioration of health, restlessness, excretion, pressure ulcers, and the possibility of falling.

For example, the autonomic nervous state N1 of the subject 81 is derived based on the biological state obtained from the biological sensor 20. For example, at least one of the biological state (eg, heart rate, pulse rate, respiratory rate, body temperature, blood pressure, blood oxygen saturation, weight, sleep, arousal, getting out of bed, rising and sitting), and autonomic nervous state N1. Based on the above, the notification of the support-requiring state of the target person 81 may be performed. The notification is performed, for example, by a display such as a nurse station of a facility where the target person 81 is located. The notification may be performed by, for example, a terminal device owned by a supporter 80 (for example, a doctor 83, a nurse 82a, a caregiver 82b, a family member 82c, etc.). The notification may include at least one of display, sound and vibration.

The medical treatment support system 130 may also provide a draft of the content of the conversation with the subject 81 (see FIGS. 2A and 2B, such as Plan I1 or Plan I2). The content is related to the health and safety status of the subject 81. The proposal is based on, for example, at least one of a biological state and an autonomic nervous state N1.

In the medical treatment support system 130, for example, the autonomic nervous state is derived from biological information (state), and emotions are estimated. As a result, for example, an abnormal value of biological information due to a temporary change in emotion is removed. For example, the accuracy of detecting abnormal values of biological information can be improved. As a result, the biological condition of the subject 81 can be grasped more accurately.

For example, the autonomic nervous state based on biological information (state) may be derived based on, for example, analysis of data by artificial intelligence or the like. In this case, the autonomic nerve can be derived more efficiently and more accurately than when the analyst estimates the state of the autonomic nerve while looking at the waveform or numerical value related to the biological information.

In the medical treatment support system 130 according to the present embodiment, a sound sensor 11 (see FIG. 1A) may be further provided as in the medical treatment support system 110.

In this case as well, the sound sensor 11 detects the voice V0 of the subject 81. Then, the emotional information ES1 may be estimated based on this voice V0 in addition to the above-mentioned autonomic nervous state N1. Thereby, for example, the emotional state of the subject 81 can be estimated more accurately.

Further, the sound sensor 11 may detect the voice of the supporter 80 of the target person 81 and the voice of the target person 81 generated in response to the voice of the supporter 80. The voice of the supporter 80 includes content (eg, a question, etc.) based on at least a part of the above plan (plan I1 or plan I2, etc.). The voice of the subject 81 generated in response to the voice of the supporter 80 includes an answer in response to a question or the like. In this case, the emotional information ES1 may be further estimated based on the voice (answer) of the subject 81 in addition to the above-mentioned autonomic nervous state N1. Thereby, for example, the emotional state of the subject 81 can be estimated more accurately.

For example, the voice of the supporter 80 of the target person 81 (question based on the plan I2, etc.) and another voice (answer) of the target person 81 generated in response to the voice of the supporter 80 are reproduced. It may be provided to a doctor 83 or the like. For example, these voices may be voice-recognized and processed into a sentence, and this sentence may be provided to a doctor 83 or the like.

In the medical treatment support system 130, a sound sensor 11 and a sound generation unit 12 (speaker, see FIG. 1A) may be provided as in the medical treatment support system 130. In this case, the sound generation unit 12 generates a voice S1 (see FIG. 1A) including a content including at least one of a question and a call to the subject 81. This content is related to the health and safety status of the subject 81. This content is based on at least one of the biological state and the autonomic nervous state N1. The sound sensor 11 detects the voice of the subject 81 (answer to the voice S1) after the generation of the voice S1. The emotional state may be further estimated based on this voice (answer) of the subject 81. Thereby, for example, the emotional state of the subject 81 can be estimated more accurately.

In the medical treatment support system 130, at least a part of the content corresponding to the above voice (answer) of the subject 81 may be provided. For example, the voice S1 generated from the sound generation unit 12 and another voice (answer) of the subject 81 generated in response to the voice S1 may be reproduced and provided to the doctor 83 or the like. For example, another voice (answer) of the subject 81 may be voice-recognized and processed into a sentence, and this sentence may be provided to the doctor 83 or the like together with the sentence corresponding to the voice S1.

(Fourth Embodiment)
6 (a) to 6 (c) are schematic views illustrating the medical treatment support system according to the fourth embodiment.
The medical treatment support system 140 according to the present embodiment includes a sound sensor 11 and a providing unit (for example, a display device 83D or a display device 82D).

The sound sensor 11 collects, for example, the voice around the subject 81. For example, the sound sensor 11 detects the voice V0 of the subject 81. The providing unit (for example, the display device 83D or the display device 82D) provides the first plan based on the sound collected by the sound sensor 11. The first plan is, for example, a plan for encouraging the subject 81 to answer about the health and safety status of the subject 81. For example, the providing unit provides a first plan regarding the content of the conversation with the target person 81. The content of the conversation with the subject 81 is related to the health and safety status of the subject 81. This first plan is based on the voice V0 of the subject 81 detected by the sound sensor 11.

For example, when the supporter 80 who uses the medical treatment support system 140 is a doctor 83, a proposal I1 of the contents of the interview is provided as the first proposal above (see FIG. 6B). For example, when the supporter 80 who uses the medical treatment support system 140 is a nurse 82a, a caregiver 82b, a family member, etc. 82c, the first plan above is a plan I2 for asking or calling out to the subject 81.

For example, the voice V0 of the subject 81 detected by the sound sensor 11 is voice-recognized. The state of the subject 81 (for example, the health and safety state) is estimated from the result of the voice recognition process. Based on the estimated state of the subject 81, the first proposal regarding the content of the conversation with the subject 81 is provided. As a result, the supporter 80 (doctor 83, nurse 82a, caregiver 82b, family member 82c, etc.) can provide more appropriate support to the target person 81.

In the medical treatment support system 140, if the recognition tag 82s of the nurse 82a (or the caregiver 82b, etc.) is recognized by the short-distance communication unit 15, even if the voice V0 is detected or the voice recognition of the voice V0 is started. good. Alternatively, when it is detected by the motion sensor 16 provided in the support device 10 or the like that the supporter 80 approaches the target person 81, the voice V0 detection or the voice recognition of the voice V0 may be started. .. For example, when the sound sensor 11 detects that the supporter 80 has called out to the target person 81, voice recognition may be started.

In the medical treatment support system 140, the speaker is identified by, for example, an IC tag (recognition tag 82s) of a staff member (nurse 82a, caregiver 82b, family member, etc. 82c). In the medical treatment support system 140, for example, by detecting an IC tag (recognition tag 82s), it becomes a trigger for acquiring conversation information for voice recognition.

In the medical treatment support system 140, the sound sensor 11 uses the voice (question or voice) of the supporter 80 of the subject 81 and another voice (answer) of the subject 81 generated in response to the voice of the supporter 80. May be further detected. This voice of the supporter 80 includes content based on at least a part of the above-mentioned first plan (question content plan I1 or question or voice plan I2 to the subject 81).

At this time, the medical treatment support system 140 (for example, the providing unit) may further provide a second proposal regarding the above contents. For example, this second proposal is based on the above-mentioned other voice (answer of subject 81). For example, the content of this second plan is to find out the state of the subject 81 in more detail based on the answer of the subject 81.

For example, when the supporter 80 who uses the medical treatment support system 140 is a doctor 83, the first plan gives an overview of the state of the subject 81. Then, as the second plan, a plan for asking in more detail is provided based on the outline obtained by the interview of the first plan.

For example, based on the first plan, the doctor 83 asks the subject 81, "Did you have any family-like symptoms?" This corresponds to the voice (question or voice) of the supporter 80. In response to this question, subject 81 replies, "My father had a similar illness." This answer corresponds to the other voice above (answer of subject 81). At this time, as a second plan, for example, "Ask your father if he had any other illness?" Or "Are there any other pains besides the headache?" Let's ask. " For example, such a second plan is displayed on the display device 83D. Based on such a second plan, the doctor 83 further asks the subject 81, for example, "Are there any pains in other parts?" Such a proposal may be proposed repeatedly.

For example, when the supporter 80 who uses the medical treatment support system 140 is a nurse 82a, a caregiver 82b, or a family member 82c, the supporter 80 asks the target person 81, "Where does it hurt?" ? ". This corresponds to the voice (question or voice) of the supporter 80. In response to this question, the subject 81 replies, "I have a headache." This answer corresponds to the other voice above (answer of subject 81). At this time, as a second plan, for example, "Let's ask when?" Or "Let's ask if it's getting worse?" Is proposed. For example, such a second plan is displayed on the display device 82D. The supporter 80 (nurse 82a, caregiver 82b, family member 82c, etc.) further asks the subject 81, for example, "Is it getting worse?" Based on such a second plan. Such a proposal may be proposed repeatedly.

As described above, the subject 81 answers the question based on the first plan. The second plan is provided based on the response of the subject 81. For example, the response of the subject 81 narrows down the outline of the state of the subject 81. A second proposal is further provided based on the narrowed down state of the subject 81. The second plan contains more detailed questions than the first plan. The second plan may include contents that were not included in the first plan. For example, at least part of the second plan is different from the first plan.

In the present embodiment, the voice recognition process of the voice V0 of the subject 81 is performed so as to be related to the health and safety state of the subject 81. For example, in voice recognition generally performed by a computer or the like, voice recognition is performed when a specific word (for example, a name given to the computer) is uttered. The detected voice V0 includes a wide range of contents. Therefore, when the voice based on the voice V0 is processed for voice recognition, it is designed so that it can be applied to a wide range of contents.

On the other hand, in the embodiment, the recognition related to the health and safety state is given priority. For example, speech recognition with meanings such as "painful", "painful", "mood", "heat", or "trembling" is given priority. On the other hand, the recognition rate of voice that is not directly related to the health and safety status may be low, such as "What is the fashion that is popular now?". For example, in a statistical model used in speech recognition, the priority of words related to health and safety status may be increased. For example, words (and vocalizations) related to the health and safety state may be preferentially registered in the word dictionary used in speech recognition. For example, in a learning model in automated learning, words (and vocalizations) related to health and safety may be highly weighted. For example, in the language model used in speech recognition, the memory of the chain of words related to the health and safety state may be preferentially performed.

By giving priority to recognition related to health and safety status, voice recognition related to medical treatment is performed more efficiently.

(Fifth Embodiment)
7 (a) to 7 (d) are schematic views illustrating the medical treatment support system according to the fifth embodiment.
The medical treatment support system 150 according to the present embodiment includes a sound sensor 11 and a providing unit (for example, a display device 83D or a display device 82D). The sound sensor 11 is provided in the support device 10. In the medical treatment support system 150, the support device 10 includes a moving mechanism 17. Other configurations of the medical treatment support system 150 can be the same as those of the medical treatment support system 140.

The support device 10 can be moved by the moving mechanism 17. The support device 10 is a self-propelled robot. The support device 10 may include a sound generation unit 12, a transmission / reception unit 13, a housing 14, a short-range communication unit 15, and a motion sensor 16. The support device 10 in the medical treatment support system 150 may perform the same operation as the support device 10 in the medical treatment support system 140.

Since the support device 10 is movable by the moving mechanism 17, various operations are further possible.

For example, the support device 10 may function as a communication robot. For example, the support device 10 is a conversation partner of the target person 81. For example, the subject 81 moves from the bed 70 to the dining room table. Subject 81 waits for a meal to be served. The support device 10 becomes a conversation partner while the subject 81 is waiting. The support device 10 is, for example, a communication robot that fills the gaps between work.

For example, the subject 81 may have a communication disorder. Communication problems may occur, for example, due to a stroke or other illness, or a head injury. The support device 10 can support such rehabilitation of the subject 81.

The support device 10 may be capable of supporting the rehabilitation of the target person 81 at home. The support device 10 may function as a training device, for example. The support device 10 can provide rehabilitation support tailored to each of the subjects 81.

The support device 10 can support, for example, training to remember words or to re-listen to one's own words.

The support device 10 can change the position of the support device 10 based on the information detected by the sound sensor 11, the short-range communication unit 15, the motion sensor 16, and the like. For example, the support device 10 may be self-propelled and movable in conjunction with the movement of the target person 81.

According to the medical treatment support system 150, it is possible to provide a medical treatment support system that can provide better services.

(Sixth Embodiment)
The medical treatment support system according to the present embodiment includes a sound sensor 11, a biological sensor 20, and a providing unit (for example, a display device 83D or a display device 82D). In this medical treatment support system, one of the sound sensor 11 and the biological sensor 20 may be omitted.

In the medical treatment support system, long-term care records (for example, daily report information) are further used. Other than this, it can be the same as any medical treatment support system according to the above embodiment.

For example, the long-term care record is recorded or input by the supporter 80 of the subject 81. The supporter 80 is, for example, a nurse 82a, a caregiver 82b, a family member 82c, or the like. For example, the support (work) by the supporter 80 to the target person 81 is recorded (or input). The recorded (or input) long-term care record is supplied to the daily report information database DB3.

For example, in the medical treatment support system 120, the subject 81 is based on the voice information database DB1 regarding the voice V0 of the subject 81, the biological information database DB2 regarding the biological state detected by the biological sensor 20, the daily report information database DB3, and the like. A proposal regarding the content of the conversation with (eg, proposal I1 or proposal I2) is provided. The proposal may be further based on care information.

For example, in the supporter 80 (nurse 82a, caregiver 82b, family member 82c, etc.), for example, a sign of disturbing behavior due to dementia in the subject 81 can be estimated. For example, the timing of consulting with a doctor 83 or the like for alleviating a situation such as pain can be suggested to a nurse 82a, a caregiver 82b, a family member 82c, or the like.

For example, the supporter 80 (doctor 83) is provided with a proposal regarding the content of the conversation with the subject 81 (such as the proposal I1 of the interview content). The provided proposal will be used as the material for the judgment of the interview or the judgment of the prescription. Further, the draft I1 of the contents of the interview and the answers of the subject 81 to the draft I1 are used as the material for the prescription judgment. For example, it is possible to support the visiting doctor to more appropriately grasp the situation of the subject 81.

Long-term care records (eg, daily report information) may be used in the above embodiments and variations thereof. For example, the voice S1 generated from the sound generation unit 12 may be further based on the care record in addition to the voice V0 of the subject 81. The voice S1 generated from the sound generation unit 12 may be further based on the care record in addition to the autonomic nerve state N1 derived from the biological information. For example, the proposed proposals (Proposal I1, Proposal I2, Proposal 1 or Proposal 2) may be further based on the long-term care record.

(Sixth Embodiment)
In this embodiment, a plurality of sets including at least one of the biological sensor 20 and the sound sensor 11 are provided. For example, a plurality of subjects 81 move into one facility, and each of the plurality of subjects 81 is provided with a set including at least one of a biological sensor 20 and a sound sensor 11. Or, for example, each of the plurality of subjects 81 is receiving medical treatment at home. Each of the plurality of subjects 81 is provided with a set including at least one of the biological sensor 20 and the sound sensor 11. In this way, the plurality of sets are provided corresponding to the plurality of target persons 81, respectively.

In such a case, the medical treatment support system provides the priority of the response to the plurality of subjects 81 based on the biological state (or biological information) and emotional state (or emotional information) obtained from each of the plurality of sets. You may. For example, the supporter 80 (doctor 83, nurse 82a, or caregiver 82b) preferentially treats the subject 81 with a high degree of urgency.

For example, when supporting a plurality of target persons 81, it is possible to propose an appropriate arrangement of a plurality of supporters 80 (nurse 82a or caregiver 82b). More efficient support will be possible.

According to the embodiment, it is possible to provide a medical treatment support system that can provide better services.

Hereinafter, embodiments of the present invention have been described with reference to specific examples. However, the present invention is not limited to these specific examples. For example, regarding the specific configuration of each element such as a sound sensor, a biological sensor, and a providing unit included in the medical treatment support system, the present invention is similarly carried out by appropriately selecting from a range known to those skilled in the art. Is included in the scope of the present invention as long as the effect of the above can be obtained.

A combination of any two or more elements of each specific example to the extent technically possible is also included in the scope of the present invention as long as the gist of the present invention is included.

In addition, all medical treatment support systems that can be appropriately designed and implemented by those skilled in the art based on the medical treatment support system described above as an embodiment of the present invention are also within the scope of the present invention as long as the gist of the present invention is included. Belongs.

In addition, in the scope of the idea of the present invention, those skilled in the art can come up with various modified examples and modified examples, and it is understood that these modified examples and modified examples also belong to the scope of the present invention. ..

10 ... Support device, 11 ... Sound sensor, 12 ... Sound generator, 13 ... Transmission / reception unit, 14 ... Housing, 15 ... Short-range communication unit, 16 ... Human sensor, 17 ... Movement mechanism, 20 ... Biological sensor, 25 ... Communication device, 60 ... Processing unit, 61 ... Autonomous nerve analysis unit, 70 ... Bed, 71 ... Bottom, 76 ... Mattress, 80 ... Supporter, 81 ... Target person, 82D ... Display device, 82a ... Nurse, 82b ... Caregiver, 82c ... family, etc., 82s ... recognition tag, 83 ... doctor, 83D ... display device, 110, 120, 130, 140, 150 ... medical treatment support system, CL1 ... major classification, CL2 ... middle classification, CL3 ... minor classification , D1 ... biometric information parameter, DB1 ... voice information database, DB2 ... biometric information database, DB3 ... daily report information database, DB4 ... care information database, DL1 ... threshold, E1 ... emotional parameter, ES1 ... emotional information, I1, I2 ... Draft, N1 ... Autonomous nervous state, S1 ... Voice (auditory information), OS ... Output information, V0 ... Voice, V1 ... Voice signal, VS ... Visual information, t ... Time, t1, t2 ... First, second time

Claims (4)

A biological sensor that detects the biological condition of the subject,
The sound sensor that detects the voice of the subject and
Equipped with
The emotional state of the subject estimated based on the voice is provided as output information together with the biological information.
The output information is a medical treatment support system including whether or not the emotional state of the subject is abnormal and whether or not the biological information of the subject is abnormal. Further inform the target person of the need for support,
The support-requiring state is estimated based on at least one of the biological state and the voice-based speech recognition process.
The medical treatment support system according to claim 1, wherein the support-requiring state includes at least one of deterioration, restlessness, excretion, pressure ulcer, and possibility of falling of the subject. With more sound generators
The sound generating unit generates a voice including at least one of the contents of a question and a call to the subject, the contents are related to the health and safety state of the subject, and the contents are the biological state and the biological state. Based on at least one of the above voices
The sound sensor further detects another voice of the subject after the generation of the voice.
The medical treatment support system according to claim 2, wherein the emotional state is further estimated based on the other voice. It is possible to further provide a proposal regarding the content of the conversation with the subject.
The content is related to the health and safety status of the subject.
The medical treatment support system according to claim 2 or 3, wherein the proposal is based on at least one of the biological condition and the voice.

Images