JP7511794B1 - Question answering device and question answering method - Google Patents

Abstract

The question answering device (2) is configured to include a sensing data collection unit (21) that collects sensing data from a sensor that monitors the condition of the care recipient, and a question data acquisition unit (22) that acquires question data indicating a question about the care recipient. The question answering device (2) also includes an answer creation unit (23) that creates an answer to a question indicated by the question data acquired by the question data acquisition unit (22) based on the sensing data collected by the sensing data collection unit (21), and an answer data reply unit (24) that replies with answer data indicating the answer created by the answer creation unit (23).

Description

The present disclosure relates to a question answering device and a question answering method.

There is a question answering device that creates answers to questions about a care recipient.
As such a question and answering device, for example, Patent Literature 1 discloses a question and answering device including an acquisition unit, a calculation unit, and an extraction unit.
The acquisition unit acquires a query sentence indicating the content of a question from a user terminal. The calculation unit calculates a similarity between the query sentence and each of a plurality of answer candidate sentences in which an answer to the question is described. The extraction unit extracts an answer candidate sentence having a relatively high similarity calculated by the calculation unit from the plurality of answer candidate sentences, and transmits the extracted answer candidate sentence to the user terminal.

JP 2021-124824 A

The answer candidate sentences extracted by the extraction unit of the question answering device disclosed in Patent Document 1 are answer candidate sentences with a relatively high degree of similarity among multiple answer candidate sentences, but there was a problem in that they did not necessarily indicate an answer that reflected the situation of a specific person related to the question.

The present disclosure has been made to solve the above-mentioned problems, and aims to provide a question answering device that can create answers to questions that reflect the situation of the person being cared for.

The question answering device according to the present disclosure includes a sensing data collection unit that collects sensing data from a sensor that monitors the condition of the care recipient, and a question data acquisition unit that acquires question data indicating a question about the care recipient. The question answering device also includes an answer creation unit that creates an answer to a question indicated by the question data acquired by the question data acquisition unit based on the sensing data collected by the sensing data collection unit, and an answer data reply unit that replies with answer data indicating the answer created by the answer creation unit.

According to the present disclosure, answers to questions can be created that reflect the situation of the person being cared for.

1 is a configuration diagram showing a system including a question and answering device 2 according to a first embodiment. 1 is a hardware configuration diagram showing hardware of a question and answering device 2 according to a first embodiment. FIG. FIG. 2 is a hardware configuration diagram of a computer when the question and answering device 2 is realized by software, firmware, or the like. 4 is a flowchart showing a question answering method which is a processing procedure of the question answering apparatus 2. 1 is an explanatory diagram showing the answer "You need ◇◇ ml more" when the question is "How much more water does Mr. XX need?". FIG. 11 is a configuration diagram showing a system including a question and answering device 2 according to a second embodiment. FIG. 11 is a hardware configuration diagram showing hardware of a question and answering device 2 according to a second embodiment. This is an explanatory diagram showing the answer "You need ◇◇ ml more" when the question is "How much more water does Mr./Ms. XX need?", the advice "Mr./Ms. XX has a target amount of water to drink because he/she has diabetes. Please encourage him/her to drink as much water as possible," and a graph showing changes in the sensing data over time. FIG. 11 is a configuration diagram showing a system including a question and answering device 2 according to a third embodiment. FIG. 11 is a hardware configuration diagram showing hardware of a question and answering device 2 according to a third embodiment.

In order to explain the present disclosure in more detail, the form for implementing the present disclosure will be described below with reference to the attached drawings.

Embodiment 1.
FIG. 1 is a configuration diagram showing a system including a question and answering apparatus 2 according to the first embodiment.
FIG. 2 is a hardware configuration diagram showing the hardware of the question and answering device 2 according to the first embodiment.
The system shown in FIG. 1 includes a chatbot 1, a question and answering device 2, and a sensing device 3.

The chatbot 1 comprises a voice recognition unit 11, a voice database 12, a chatbot engine unit 13, a display unit 14 and a voice output unit 15.
The chatbot 1 recognizes the user's voice and outputs text data indicating the user's voice to the question and answering device 2.
In the system shown in FIG. 1, the text data indicates a question about the care recipient, and the text data is output to the question answering device 2 as question data.
The chatbot 1 outputs the answer data returned from the question and answering apparatus 2 to both the display unit 14 and the audio output unit 15 .

The voice recognition unit 11 recognizes the user's voice and creates text data representing the user's voice based on the voice data recorded in the voice database 12. The voice data recorded in the voice database 12 is, for example, voice piece data representing a voice piece.
The voice recognition unit 11 outputs the text data to the chatbot engine unit 13 as question data.
The speech database 12 stores, for example, speech unit data and text data corresponding to the speech unit data.

If the chatbot engine unit 13 obtains question data from the voice recognition unit 11, it outputs the question data to the question answering apparatus 2, and if text data is provided as question data from a keyboard or the like not shown, it outputs the text data to the question answering apparatus 2.
The chatbot engine unit 13 acquires answer data from the question and answering apparatus 2 .
The chatbot engine unit 13 causes the display unit 14 to display the answer indicated by the answer data.
The chatbot engine unit 13 causes the voice output unit 15 to output the answer indicated by the answer data by voice.

The display unit 14 displays the answer indicated by the answer data output from the chatbot engine unit 13 on a display (not shown).
The audio output unit 15 outputs the answer indicated by the answer data output from the chatbot engine unit 13 as audio from a speaker (not shown).

The question and answering apparatus 2 includes a sensing data collection unit 21 , a question data acquisition unit 22 , an answer creation unit 23 , and an answer data reply unit 24 .
The sensing data collection unit 21 is realized by, for example, a sensing data collection circuit 31 shown in FIG.
The sensing data collection unit 21 collects sensing data from various sensors included in the sensing device 3. The various sensors are sensors for monitoring the condition of the care recipient.
The condition of the care recipient may be, for example, the vital signs of the care recipient, the behavior of the care recipient, or the situation the care recipient is in. The condition of the care recipient may be, for example, the temperature, humidity, or surrounding noise in the care recipient's room.
The sensing data collection unit 21 outputs the sensing data to the answer creation unit 23 .

The question data acquiring unit 22 is realized by, for example, a question data acquiring circuit 32 shown in FIG.
The question data acquisition unit 22 acquires question data indicating a question about the care recipient from the chatbot engine unit 13 of the chatbot 1.
The question data acquiring unit 22 outputs the question data to each of the sensing data collecting unit 21 and the answer creating unit 23 .

The answer generating unit 23 is realized by, for example, an answer generating circuit 33 shown in FIG.
The answer creating unit 23 acquires the sensing data from the sensing data collecting unit 21 and acquires the question data from the question data acquiring unit 22 .
The answer creating unit 23 creates an answer to the question indicated by the question data based on the sensing data and the care record of the care recipient.
The answer creating unit 23 outputs answer data indicating the created answer to the answer data reply unit 24 .

Specifically, the answer creation unit 23 provides the question data to the learning model 41 and obtains, from the learning model 41, a template for an answer to the question indicated by the question data.
The answer generating unit 23 acquires the care record of the care recipient from the care record database 42 .
The answer creating unit 23 creates an answer to the question indicated by the question data based on the answer template, the sensing data, and the care record of the care recipient.
The learning model 41 is realized by, for example, a neural network.
During learning, the learning model 41 is provided with question data indicating questions about the care recipient and template data indicating templates of answers corresponding to the questions, and learns answer templates. The template data is teacher data.
During inference, when question data is given from the answer creation unit 23, the learning model 41 outputs template data indicating a template of an answer corresponding to the question indicated by the question data.
The care record database 42 stores the care records of the care recipients.
1 , the learning model 41 and the care record database 42 are each provided outside the question answering apparatus 2. However, this is merely an example, and the learning model 41 and the care record database 42 may each be provided inside the question answering apparatus 2.

The response data reply unit 24 is realized by, for example, a response data reply circuit 34 shown in FIG.
The answer data replying unit 24 acquires the answer data from the answer creating unit 23 .
The answer data reply unit 24 replies with the answer data to the chatbot engine unit 13 of the chatbot 1.

1, it is assumed that each of the components of the question answering apparatus 2, that is, the sensing data collection unit 21, the question data acquisition unit 22, the answer creation unit 23, and the answer data reply unit 24, is realized by dedicated hardware as shown in Fig. 2. In other words, it is assumed that the question answering apparatus 2 is realized by a sensing data collection circuit 31, a question data acquisition circuit 32, an answer creation circuit 33, and an answer data reply circuit 34.
Each of the sensing data collection circuit 31, the question data acquisition circuit 32, the answer creation circuit 33 and the answer data reply circuit 34 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination of these.

The components of the question answering apparatus 2 are not limited to those realized by dedicated hardware, and the question answering apparatus 2 may be realized by software, firmware, or a combination of software and firmware.
The software or firmware is stored as a program in the memory of a computer. The computer means hardware that executes the program, and includes, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a central processing unit, a processing unit, an arithmetic unit, a microprocessor, a microcomputer, a processor, or a DSP (Digital Signal Processor).

FIG. 3 is a hardware configuration diagram of a computer in the case where the question and answering device 2 is realized by software, firmware, or the like.
When the question answering device 2 is realized by software, firmware, or the like, programs for causing a computer to execute the respective processing procedures of the sensing data collection unit 21, the question data acquisition unit 22, the answer creation unit 23, and the answer data reply unit 24 are stored in the memory 51. Then, a processor 52 of the computer executes the programs stored in the memory 51.

2 shows an example in which each of the components of the question answering device 2 is realized by dedicated hardware, and FIG. 3 shows an example in which the question answering device 2 is realized by software or firmware, etc. However, this is merely one example, and some of the components in the question answering device 2 may be realized by dedicated hardware, and the remaining components may be realized by software or firmware, etc.

The sensing device 3 is equipped with sensors for monitoring the condition of the care recipient, such as a bed sensor 61, a room sensor 62, an appliance sensor 63, a human presence sensor 64, a vital sign sensor 65 and an intake detection sensor 66, and the sensing device 3 is also equipped with a sensing data recording unit 67.
The bed sensor 61 is a sensor attached to the bed used by the care recipient, and monitors, for example, the state of the care recipient turning over in his/her sleep.
The room sensor 62 is a sensor installed in the room of the care recipient, and monitors, for example, the sleep, falls, or body movements of the care recipient.

The home appliance sensor 63 is, for example, a sensor attached to an air conditioner in the care recipient's room, and monitors, for example, the room temperature in the care recipient's room.
The home appliance sensor 63 is a sensor attached to a home appliance such as a refrigerator, a stove, a rice cooker, or a microwave oven, and monitors, for example, the usage status of the home appliance. The home appliance is used by the care recipient. If the usage status of the home appliance is known, it is possible to determine the independence of the care recipient.
The human presence sensor 64 is, for example, a sensor attached to the entrance of the care recipient's room, and detects, for example, when the care recipient goes out.
The vital sign sensor 65 is, for example, a sensor attached to a wall, ceiling, or furniture in the care recipient's room, or to the care recipient, and monitors, for example, the vital signs of the care recipient.
The intake detection sensor 66 is, for example, a sensor equipped with a camera attached to the wall of the care recipient's room, and monitors, for example, the fluid intake behavior or food intake behavior of the care recipient.
The sensing data recording unit 67 is a database that records the sensing data from the bed sensor 61, the room sensor 62, the home appliance sensor 63, the human presence sensor 64, the vital sensor 65, and the ingestion detection sensor 66.

Next, the operation of the question answering apparatus 2 shown in FIG. 1 will be described.
FIG. 4 is a flowchart showing a question answering method which is a processing procedure of the question answering apparatus 2.
In the system shown in FIG. 1, the person receiving care is, for example, a person hospitalized in a nursing home or a medical hospital, and the user who asks questions about the person receiving care is, for example, a staff member of the nursing home or the medical hospital.

When the voice recognition unit 11 of the chatbot 1 receives the voice of a staff member from a microphone (not shown), it breaks down the voice of the staff member into, for example, multiple speech fragments.
The speech recognition unit 11 obtains text data corresponding to each speech piece from the speech database 12 .
The voice recognition unit 11 connects together the text data corresponding to each speech piece, and outputs the connected text data to the chatbot engine unit 13 as question data.

Examples of questions that may be included in the question data include, "How much more water does Mr./Ms. XX need to drink?", "Has anything changed about Mr./Ms. XX?", "Has Mr./Ms. XX been sleeping well recently?", or "How active was Mr./Ms. XX during the day yesterday?"

Here, the staff member's voice is provided to the voice recognition unit 11, and text data is output from the voice recognition unit 11 to the chatbot engine unit 13 as question data. However, this is merely one example, and the staff member may operate a keyboard or the like (not shown) to provide text data as question data to the chatbot engine unit 13 from the keyboard or the like.

The chatbot engine unit 13 acquires question data from the voice recognition unit 11.
The chatbot engine unit 13 outputs the question data to the question data acquisition unit 22 of the question answering apparatus 2 .

The question data acquiring unit 22 acquires question data indicating a question about the care recipient from the chatbot engine unit 13 (step ST1 in FIG. 4).
The question data acquiring unit 22 outputs the question data to the answer creating unit 23 .

The sensing data collection unit 21 collects sensing data relating to the care recipient from the sensing data recorded in the sensing data recording unit 67 of the sensing device 3 (step ST2 in FIG. 4).
Specifically, the sensing data collecting unit 21 identifies the care recipient by performing a process of identifying the care recipient. For example, the process of identifying the care recipient may be a known process of identifying who the care recipient is by searching for the name of the care recipient included in the question data output from the question data acquiring unit 22.
The sensing data collecting unit 21 also identifies the sensing data to be collected by performing a process of identifying the sensing data to be collected. The process of identifying the sensing data is, for example, a known process of searching for sensing data related to a term included in the question data output from the question data acquiring unit 22 to identify which sensing data is the sensing data to be collected.

For example, if the question is "How much more fluid does Mr./Ms. XX need?", the sensing data collector 21 identifies the sensing data from the intake detection sensor 66 related to "fluid."
For example, if the question is "Have you been sleeping well recently, Mr./Ms. XX?", the sensing data collection unit 21 will identify the sensing data from the bed sensor 61 or the sensing data from the room sensor 62 that is related to "sleeping well".
For example, if the care recipient is Mr./Ms. XX and the sensing data to be collected is sensing data from the ingestion detection sensor 66, the sensing data collection unit 21 collects the sensing data from the ingestion detection sensor 66 related to Mr./Ms. XX.
For example, if the care recipient is Mr. △△ and the sensing data to be collected is sensing data from the bed sensor 61, the sensing data collection unit 21 collects the sensing data from the bed sensor 61 related to Mr. △△.
Here, the sensing data collection unit 21 identifies which sensing data is to be collected by searching for sensing data related to the terms included in the question data. However, this is merely an example, and the sensing data collection unit 21 may identify which sensing data is to be collected by referring to a database in which sensing data corresponding to the terms included in the question data is recorded.
The sensing data collection unit 21 outputs the collected sensing data to the answer creation unit 23 .

The answer creating unit 23 acquires the sensing data from the sensing data collecting unit 21 and acquires the question data from the question data acquiring unit 22 .
In addition, the answer creating unit 23 acquires the care record of the care recipient from the care record database 42 .
The answer creating unit 23 creates an answer to the question indicated by the question data based on the sensing data and the care record of the care recipient (step ST3 in FIG. 4).
The process of creating an answer by the answer creating unit 23 will be specifically described below.

The answer creation unit 23 provides the question data to the learning model 41 and obtains, from the learning model 41, a template for an answer to the question indicated by the question data.
For example, if the question indicated by the question data is "How much more fluid does Mr./Ms. XX need?", then, for example, an answer template (1) of "You need ◇◇ ml more," and an answer template (2) of "You have already obtained the required amount of fluid," are obtained.
If the question indicated by the question data is, for example, "Have you been sleeping well recently?", then, for example, an answer template (1) of "X has been sleeping well recently" is obtained, and an answer template (2) of "X has not been sleeping well recently" is obtained.

For example, if the question indicated by the question data is "How much more water does Mr./Ms. XX need to drink?", the answer creation unit 23 obtains information on "the amount of water that Mr./Ms. XX needs to drink per day" from Mr./Ms. XX's nursing care record stored in the nursing care record database 42. If Mr./Ms. XX's medical history includes diabetes, the information on "the amount of water that Mr./Ms. XX needs to drink per day" may be included in Mr./Ms. XX's nursing care record.
The answer creating unit 23 acquires information on “Mr. X's amount of water consumed today” from the sensing data of the intake detection sensor 66 recorded in the sensing data recording unit 67 .
The amount of water consumed by Mr./Ms. XX per unit time is recorded in the sensing data recording unit 67 as time-series data.

If "Mr. X's water intake today" is equal to or greater than "Mr. X's required daily water intake," the answer creation unit 23 selects answer template (2) from answer template (1) and answer template (2).
Then, the answer creating unit 23 outputs the answer template (2) to the answer data replying unit 24 as answer data indicating the answer corresponding to the question.
If “Mr. X’s amount of water consumed today” is less than “Mr. X’s required daily amount of water consumption,” the answer creation unit 23 selects answer template (1) from answer template (1) and answer template (2).
Then, the answer creation unit 23 embeds the difference between "The amount of water that Mr./Ms. XX needs to drink per day" and "The amount of water that Mr./Ms. XX needs to drink today" in the "◇◇" in the answer template (1), and outputs the answer template (1) with the embedded difference to the answer data return unit 24 as answer data indicating the answer corresponding to the question.

If the question indicated by the question data is, for example, "Has Mr./Ms. X been sleeping well recently?", the answer creation unit 23 obtains information on "Mr./Ms. X's average sleeping hours" from Mr./Ms. X's care record stored in the care record database 42.
The answer creating unit 23 acquires information on “Mr./Ms. XX's sleeping hours yesterday” from the sensing data of the bed sensor 61 or the sensing data of the room sensor 62 recorded in the sensing data recording unit 67 .

If "X-san's sleep time yesterday" is equal to or longer than "X-san's average sleep time," the answer creation unit 23 selects answer template (1) from answer template (1) and answer template (2).
Then, the answer creating unit 23 outputs the answer template (1) to the answer data replying unit 24 as answer data indicating the answer corresponding to the question.
If "Mr. X's sleep time yesterday" is less than "Mr. X's average sleep time," the answer creation unit 23 selects answer template (2) from answer template (1) and answer template (2).
Then, the answer creating unit 23 outputs the answer template (2) to the answer data replying unit 24 as answer data indicating the answer corresponding to the question.

1, the answer creating unit 23 creates an answer to a question indicated by the question data based on the sensing data and the care record of the care recipient. However, this is merely an example, and the answer creating unit 23 may create an answer to a question indicated by the question data based only on the sensing data.
In this case as well, the answer creation unit 23 provides the question data to the learning model 41 and obtains from the learning model 41 a template for an answer to the question indicated by the question data.
If the question indicated by the question data is, for example, "Is Mr./Ms. XX sleeping now?", then, for example, an answer template "Mr./Ms. XX is sleeping now" is obtained as answer template (1), and an answer template "Mr./Ms. XX is not sleeping now" is obtained as answer template (2).
If the sensing data of the bed sensor 61 or the sensing data of the room sensor 62 indicates that Mr./Ms. XX is sleeping, the answer creation unit 23 outputs answer template (1) to the answer data return unit 24 as answer data indicating the answer corresponding to the question.
If the sensing data of the bed sensor 61 or the sensing data of the room sensor 62 indicates that Mr./Ms. XX is awake, the answer creation unit 23 outputs the answer template (2) to the answer data return unit 24 as answer data indicating the answer corresponding to the question.

If the question indicated by the question data is, for example, "Is Mr./Ms. XX eating?", then, for example, an answer template "Mr./Ms. XX is eating" is obtained as answer template (1), and an answer template "Mr./Ms. XX is not eating" is obtained as answer template (2).
If the sensing data of the intake detection sensor 66 indicates that Mr./Ms. XX is eating, the answer creation unit 23 outputs answer template (1) to the answer data return unit 24 as answer data indicating the answer corresponding to the question.
If the sensing data of the intake detection sensor 66 indicates that Mr./Ms. XX is not eating, the answer creation unit 23 outputs answer template (2) to the answer data return unit 24 as answer data indicating the answer corresponding to the question.

The answer data replying unit 24 acquires the answer data from the answer creating unit 23 .
The answer data reply unit 24 replies with the answer data to the chatbot engine unit 13 of the chatbot 1 (step ST4 in FIG. 4).

The chatbot engine unit 13 acquires the answer data from the answer data reply unit 24.
The chatbot engine unit 13 displays the answer indicated by the answer data on the display of the display unit 14, as shown in FIG. 5.
In addition, the chatbot engine unit 13 outputs the answer indicated by the answer data by voice from the speaker of the audio output unit 15.
5 is an explanatory diagram showing the answer "You need ◇◇ ml more" when the question is "How much more water does Mr. XX need?". Note that ◇◇ contains the difference between "XX's daily required amount of water" and "XX's amount of water to drink today".
In FIG. 5, □□□□ is the name of a staff member.

In the above-described first embodiment, the question answering device 2 is configured to include a sensing data collection unit 21 that collects sensing data from a sensor that monitors the condition of the care recipient, and a question data acquisition unit 22 that acquires question data indicating a question about the care recipient. The question answering device 2 also includes an answer creation unit 23 that creates an answer to a question indicated by the question data acquired by the question data acquisition unit 22 based on the sensing data collected by the sensing data collection unit 21, and an answer data reply unit 24 that replies with answer data indicating the answer created by the answer creation unit 23. Thus, the question answering device 2 can create an answer that reflects the condition of the care recipient as an answer to a question.

In the question answering device 2 shown in Fig. 1, the answer creation unit 23 provides question data to the learning model 41 and obtains a template of an answer to the question indicated by the question data from the learning model 41. However, this is merely one example, and the answer creation unit 23 may obtain a template of an answer to the question indicated by the question data based on a rule base, for example.

In the question answering device 2 shown in Fig. 1, the question contains information indicating that the care recipient is, for example, "Mr. XX" or "Mr. △△". However, this is merely an example, and the question does not have to contain information indicating that the care recipient is, for example, "Mr. XX" or "Mr. △△". In this case, for example, when a staff member at a nursing home or the like gives a voice to the voice recognition unit 11 of the chatbot 1, the staff member's ID (IDentification) is provided to the chatbot engine unit 13, and the chatbot engine unit 13 displays information indicating one or more care recipients that the staff member is in charge of on the display unit 14.
Then, the chatbot engine unit 13 accepts a selection operation by a staff member to select a care recipient related to the question from one or more care recipients, and outputs care recipient information indicating the care recipient related to the question to the question answering device 2. The sensing data collection unit 21 collects sensing data related to the care recipient indicated by the care recipient information from the sensing data recorded in the sensing data recording unit 67 of the sensing device 3.

Embodiment 2.
In the second embodiment, a question answering device 2 in which the answer creating unit 25 creates advice corresponding to the condition of the care recipient in addition to an answer to a question will be described.

Fig. 6 is a configuration diagram showing a system including a question answering apparatus 2 according to embodiment 2. In Fig. 6, the same reference numerals as in Fig. 1 indicate the same or corresponding parts, and detailed description thereof will be omitted.
Fig. 7 is a hardware configuration diagram showing the hardware of the question answering device 2 according to embodiment 2. In Fig. 7, the same reference numerals as in Fig. 2 denote the same or corresponding parts, and detailed description thereof will be omitted.
The question and answering apparatus 2 includes a sensing data collection unit 21, a question data acquisition unit 22, an answer creation unit 25, and an answer data reply unit .

The answer generating unit 25 is realized by, for example, an answer generating circuit 35 shown in FIG.
The answer creating unit 25 acquires the sensing data from the sensing data collecting unit 21 and acquires the question data from the question data acquiring unit 22 .
The answer creating unit 25 creates an answer to the question indicated by the question data based on the sensing data and the care record of the care recipient.
In addition, the response creating unit 25 creates advice corresponding to the condition of the care recipient.
The answer creating unit 25 outputs answer data indicating the created answer and advice data indicating the advice to the answer data reply unit 26.

The answer data reply unit 26 is realized by, for example, an answer data reply circuit 36 shown in FIG.
The answer data reply unit 26 acquires the answer data and the advice data from the answer creation unit 25 .
The answer data reply unit 26 replies to the answer data and advice data to the chatbot engine unit 13 of the chatbot 1.

6, it is assumed that each of the components of the question answering apparatus 2, that is, the sensing data collection unit 21, the question data acquisition unit 22, the answer creation unit 25, and the answer data reply unit 26, is realized by dedicated hardware as shown in Fig. 7. In other words, it is assumed that the question answering apparatus 2 is realized by a sensing data collection circuit 31, a question data acquisition circuit 32, an answer creation circuit 35, and an answer data reply circuit 36.
Each of the sensing data collection circuit 31, the question data acquisition circuit 32, the answer creation circuit 35 and the answer data reply circuit 36 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination of these.

The components of the question answering apparatus 2 are not limited to those realized by dedicated hardware, and the question answering apparatus 2 may be realized by software, firmware, or a combination of software and firmware.
When the question answering device 2 is realized by software, firmware, or the like, programs for causing a computer to execute the respective processing procedures in the sensing data collection unit 21, the question data acquisition unit 22, the answer creation unit 25, and the answer data reply unit 26 are stored in a memory 51 shown in Fig. 3. Then, a processor 52 shown in Fig. 3 executes the programs stored in the memory 51.

Furthermore, Fig. 7 shows an example in which each of the components of the question answering device 2 is realized by dedicated hardware, and Fig. 3 shows an example in which the question answering device 2 is realized by software or firmware, etc. However, this is merely one example, and some of the components in the question answering device 2 may be realized by dedicated hardware, and the remaining components may be realized by software or firmware, etc.

Next, we will explain the operation of the question answering device 2 shown in Figure 6. However, since the parts other than the answer creation unit 25 and the answer data reply unit 26 are the same as those of the question answering device 2 shown in Figure 1, we will mainly explain the operation of the answer creation unit 25 and the answer data reply unit 26 here.

The answer creating unit 25 acquires the sensing data from the sensing data collecting unit 21 and acquires the question data from the question data acquiring unit 22 .
In addition, the answer creating unit 25 acquires the care record of the care recipient from the care record database 42 .
The answer creation unit 25 creates an answer to a question indicated by the question data based on the sensing data and the care record of the care recipient, similar to the answer creation unit 23 shown in Fig. 1. The answer creation unit 25 may create an answer to a question indicated by the question data based only on the sensing data, similar to the answer creation unit 23 shown in Fig. 1.
The answer creating unit 25 differs from the answer creating unit 23 shown in FIG. 1 in that it creates advice corresponding to the condition of the care recipient.
The answer creating unit 25 outputs answer data indicating the answer and advice data indicating the advice to the answer data replying unit 26 .

Specifically, if an answer template and advice are linked in the learning model 41, the answer creation unit 25 obtains advice corresponding to the answer template when obtaining the answer template from the learning model 41.
When the answer creation unit 25 obtains an answer template such as "You need ◇◇ ml more" from the learning model 41, it obtains advice such as "Mr. XX has a target amount of water to drink because he/she has diabetes. Please make sure he/she drinks plenty of water."
When the answer creation unit 25 obtains an answer template such as "You need ◇◇ ml more" from the learning model 41, it obtains advice such as "Mr. XX has a target amount of water to drink because he/she has diabetes. Please make sure he/she drinks plenty of water."
In this case, during learning, the learning model 41 is given question data, template data, and advice data, and learns answer templates and advice. Each of the template data and the advice data is teacher data.
During inference, when question data is given from the answer creation unit 23, the learning model 41 outputs template data indicating a template of an answer corresponding to the question indicated by the question data and advice data indicating an advice.

In the question answering device 2 shown in Fig. 6, answer templates and advice are linked in the learning model 41. However, this is merely one example, and the question answering device 2 may be provided with an advice database that records advice corresponding to answer templates, and the answer creation unit 25 may obtain advice corresponding to the answer template obtained from the learning model 41 from the advice database.

When creating an answer corresponding to a question, the answer creation unit 25 may create a graph showing the change over time in the sensing data collected by the sensing data collection unit 21, or a table showing the change over time in the sensing data.
If the question is "How much more fluid does Mr./Ms. XX need?", the answer creation unit 25 will create, for example, a graph showing the change over time in the sensing data of the ingestion detection sensor 66 recorded in the sensing data recording unit 67, or a table showing the change over time in the sensing data of the ingestion detection sensor 66.
In this case, the sensing data from the ingestion detection sensor 66 is recorded in the sensing data recording unit 67 as time-series data.
If the answer creating section 25 creates a graph showing the change over time of the sensing data or a table showing the change over time of the sensing data, it outputs the graph or the like to the answer data reply section 26 .

The answer data reply unit 26 acquires the answer data and advice data from the answer creation unit 25 .
The answer data reply unit 26 replies to the answer data and advice data to the chatbot engine unit 13.
When the answer data reply unit 26 receives a graph or the like from the answer creation unit 25, it replies with the graph or the like to the chatbot engine unit 13.

The chatbot engine unit 13 obtains the answer data and advice data from the answer data reply unit 26.
The chatbot engine unit 13 displays the answer indicated by the answer data and the advice data indicated by the advice data on the display of the display unit 14.
When the chatbot engine unit 13 obtains a graph or the like from the answer data reply unit 26, it displays the graph or the like on the display of the display unit 14.
In addition, the chatbot engine unit 13 outputs the answer indicated by the answer data and the advice data indicated by the advice data from the speaker of the audio output unit 15.
Figure 8 is an explanatory diagram showing the answer "You need ◇◇ ml more" when the question is "How much more water does Mr./Ms. XX need?", the advice "Mr./Ms. XX has a target amount of water to drink because he/she has diabetes. Please encourage him/her to drink as much water as possible," and a graph showing changes in the sensing data over time.

In the above-described second embodiment, the question answering device 2 is configured so that the answer creating unit 25 creates advice corresponding to the situation of the care recipient in addition to an answer to a question indicated by the question data acquired by the question data acquiring unit 22, and the answer data returning unit 26 returns advice data indicating the advice created by the answer creating unit 25 in addition to answer data indicating the answer created by the answer creating unit 25. Thus, the question answering device 2 can create answers that reflect the situation of the care recipient as answers to questions, and can also create advice corresponding to the situation of the care recipient.

Embodiment 3.
In embodiment 3, a question answering device 2 is described in which the answer creation unit 27 acquires, as the care record of the care recipient, information indicating the medical history of the care recipient, information about the care recipient recorded on a face sheet, or information indicating the care recipient's schedule.

Fig. 9 is a configuration diagram showing a system including a question answering device 2 according to embodiment 3. In Fig. 9, the same reference numerals as in Fig. 1 and Fig. 6 indicate the same or corresponding parts, and detailed description thereof will be omitted.
Fig. 10 is a hardware configuration diagram showing the hardware of the question answering device 2 according to embodiment 3. In Fig. 10, the same reference numerals as in Fig. 2 and Fig. 7 denote the same or corresponding parts, and therefore detailed description thereof will be omitted.
The question and answering apparatus 2 includes a sensing data collection unit 21 , a question data acquisition unit 22 , an answer creation unit 27 , and an answer data reply unit 24 .

The care record database 43 stores the care records of the care recipient. The care record database 43 also stores, as the care records of the care recipient, information indicating the medical history of the care recipient, information of the care recipient recorded on a face sheet, or the schedule of the care recipient. The information of the care recipient recorded on the face sheet includes, for example, the name, age, address, family structure, hobbies, preferences, or work history of the care recipient. The schedule of the care recipient includes, for example, a schedule for visiting a hospital, a schedule for attending a hobby class, or a schedule for going to the bank.
In addition, the care record database 43 stores the visit history of the care recipient or the prescription record of the care recipient.

9 , information indicating the medical history of the care recipient, information about the care recipient recorded on a face sheet, the care recipient's schedule, the care recipient's visit history, or the care recipient's prescription record is stored in the care record database 43. However, this is merely an example, and information indicating the medical history of the care recipient, information about the care recipient recorded on a face sheet, the care recipient's schedule, the care recipient's visit history, or the care recipient's prescription record may be stored in a database different from the care record database 43.
9 , the learning model 41 and the care record database 43 are each provided outside the question answering apparatus 2. However, this is merely an example, and the learning model 41 and the care record database 43 may each be provided inside the question answering apparatus 2.

The answer generating unit 27 is realized by, for example, an answer generating circuit 37 shown in FIG.
The answer creating unit 27 acquires the sensing data from the sensing data collecting unit 21 and acquires the question data from the question data acquiring unit 22 .
The answer creating unit 27 creates an answer to the question indicated by the question data based on the sensing data and the care record of the care recipient.
When the answer creation unit 27 acquires the care recipient's house call history or the care recipient's prescription record, it creates an answer to the question indicated by the question data based on the care recipient's house call history or the care recipient's prescription record in addition to the sensing data and the care recipient's nursing record.
The answer creating unit 27 outputs answer data indicating the created answer to the answer data reply unit 24 .

9, it is assumed that each of the components of the question answering apparatus 2, that is, the sensing data collection unit 21, the question data acquisition unit 22, the answer creation unit 27, and the answer data reply unit 24, is realized by dedicated hardware as shown in Fig. 10. In other words, it is assumed that the question answering apparatus 2 is realized by a sensing data collection circuit 31, a question data acquisition circuit 32, an answer creation circuit 37, and an answer data reply circuit 34.
Each of the sensing data collection circuit 31, the question data acquisition circuit 32, the answer creation circuit 37 and the answer data reply circuit 34 may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination of these.

The components of the question answering apparatus 2 are not limited to those realized by dedicated hardware, and the question answering apparatus 2 may be realized by software, firmware, or a combination of software and firmware.
When the question answering device 2 is realized by software, firmware, or the like, programs for causing a computer to execute the respective processing procedures in the sensing data collection unit 21, the question data acquisition unit 22, the answer creation unit 27, and the answer data reply unit 24 are stored in a memory 51 shown in Fig. 3. Then, a processor 52 shown in Fig. 3 executes the programs stored in the memory 51.

Furthermore, Fig. 10 shows an example in which each of the components of the question answering device 2 is realized by dedicated hardware, and Fig. 3 shows an example in which the question answering device 2 is realized by software or firmware, etc. However, this is merely one example, and some of the components in the question answering device 2 may be realized by dedicated hardware, and the remaining components may be realized by software or firmware, etc.

Next, we will explain the operation of the question answering device 2 shown in Figure 9. However, since the parts other than the answer creation unit 27 are the same as those of the question answering device 2 shown in Figure 1, we will mainly explain the operation of the answer creation unit 27 here.

The answer creation unit 27 provides the question data to the learning model 41 and obtains, from the learning model 41, a template for an answer to the question indicated by the question data.
If the question indicated by the question data is, for example, "Has Mr./Ms. XX changed anything recently?", the answer creation unit 27 obtains a template answer such as that shown below from the learning model 41.
The answer creation unit 27 acquires, for example, an answer template (1) of "There is nothing unusual about Mr./Ms. XX.", an answer template (2) of "There is a change in Mr./Ms. XX. He is sleeping less.", an answer template (3) of "There is a change in Mr./Ms. XX. He is eating less.", and an answer template (4) of "There is a change in Mr./Ms. XX. He is spending less time on hobbies."

The answer creation unit 27 obtains information on "Mr. X's average sleep hours,""Mr.X's daily food needs," or information on Mr. X's hobbies recorded on the face sheet from Mr. X's nursing care records stored in the nursing care record database 43.
The answer creating unit 23 acquires information on “Mr./Ms. XX's sleeping hours yesterday” from the sensing data of the bed sensor 61 or the sensing data of the room sensor 62 recorded in the sensing data recording unit 67 .
The answer creating unit 23 acquires information on “the amount of food consumed by Mr./Ms. XX yesterday” from the sensing data of the intake detection sensor 66 recorded in the sensing data recording unit 67 .
The answer creation unit 23 acquires information about the time that Mr. X spent on his hobbies from Mr. X's care record.

The answer creation unit 23 compares "X-X's average sleep time" with "X-X's sleep time yesterday" and compares "X-X's required daily food amount" with "X-X's food amount consumed yesterday."
If Mr./Ms. XX's sleep time yesterday is less than his/her average sleep time, the answer creation unit 23 selects answer template (2) from among answer templates (1) to (4).
If the amount of food consumed by Mr./Ms. XX yesterday is less than the amount of food required for Mr./Ms. XX in a day, the answer creation unit 23 selects answer template (3) from among answer templates (1) to (4).
If the amount of time that Mr./Ms. XX spends on hobbies is on the decline, the answer creation unit 23 selects answer template (4) from among answer templates (1) to (4).
The answer creation unit 23 selects answer template (1) from among answer templates (1) to (4) if the amount of sleep time of Mr./Ms. XX yesterday was equal to or longer than his/her average amount of sleep time, the amount of sleep time of Mr./Ms. XX yesterday was equal to or longer than his/her average amount of sleep time, and the amount of time spent on hobbies is not showing a decreasing trend.
The answer creating unit 23 outputs the selected answer template as the created answer, and answer data indicating the answer, to the answer data reply unit 24 .

Here, the answer creation unit 27 acquires answer templates (1) to (4) from the learning model 41.
The answer creation unit 27 may acquire an answer template (5) from the learning model 41. An example of the answer template (5) is a template such as "I've noticed a change in Mr. X. Mr. X.'s schedule is busy."
The answer creation unit 23 acquires information on "Ms. X's schedule" from Ms. X's nursing care records, and compares how busy her schedule is with the average schedule of people of the same age as her.
If the schedule of Mr./Ms. XX is busier than the average schedule of a person of the same age as Mr./Ms. XX, the answer creation unit 23 selects answer template (5) from among answer templates (1) to (5).

Here, the answer creation unit 27 acquires answer templates (1) to (5) from the learning model 41.
The answer creation unit 27 may acquire an answer template (6) from the learning model 41. An example of the answer template (6) is a template that reads, "I've noticed a change in Mr./Ms. XX. There may be something wrong with Mr./Ms. XX's body."
The response creation unit 23 acquires information on "Mr. X's house call history" from Mr. X's care records.
The answer creation unit 23 selects answer template (6) from answer templates (1) to (6) if, for example, the nursing record contains a history of a house call for Mr./Ms. X within the past week.

Here, the answer creation unit 27 acquires answer templates (1) to (6) from the learning model 41.
The answer creation unit 27 may acquire an answer template (7) from the learning model 41. An example of the answer template (7) is a template that reads, "I've noticed a change in Mr. X. The type of medication he takes or the amount of medication he takes has increased."
The answer creation unit 23 acquires information on "Mr. X's prescription record" from Mr. X's nursing care record.
If the number of types of medication taken by Mr./Ms. XX has increased, or if the amount of medication taken by Mr./Ms. XX has increased, the answer creation unit 23 selects answer template (7) from among answer templates (1) to (7).

The question answering device 2 of the above-described embodiment 3 can create answers to questions that further reflect the situation of the person being cared for than the question answering device 2 of embodiment 1.

Embodiment 4.
In the question answering device 2 according to the first to third embodiments, the answer creating units 23, 25, and 27 create answers to questions indicated by the question data acquired by the question data acquiring unit 22, based on the sensing data collected by the sensing data collecting unit 21. In addition to creating answers to questions, the answer creating units 23, 25, and 27 may determine the degree of independence of the care recipient based on the usage status of a home appliance indicated by the monitoring results of a home appliance sensor 63 attached to the home appliance, such as a refrigerator.
Specifically, if the home appliance to which the home appliance sensor 63 is attached is, for example, a refrigerator, the answer creation units 23, 25, and 27 calculate the frequency with which the refrigerator door is opened and closed based on the monitoring results of the home appliance sensor 63. If the home appliance to which the home appliance sensor 63 is attached is, for example, a microwave oven, the answer creation units 23, 25, and 27 calculate the frequency with which the microwave oven is used based on the monitoring results of the home appliance sensor 63.
The frequency of these may be, for example, a daily frequency, a weekly frequency, or a monthly frequency.
For example, the answer generating units 23, 25, and 27 determine that the higher the frequency, the higher the degree of independence of the care recipient. It is sufficient that the higher the frequency, the higher the degree of independence, and it does not matter whether the relationship between the frequency and the degree of independence is linear.
The answer data reply units 24, 26 output the independence degree determination results obtained by the answer creation units 23, 25, 27 to the chatbot engine unit 13.
The chatbot engine unit 13 obtains the independence degree judgment result from the answer data return unit 24, 26.
The chatbot engine unit 13 causes the display unit 14 to display the result of the independence degree judgment, or causes the audio output unit 15 to output the result of the independence degree judgment by voice.

In addition, this disclosure allows for any combination of the embodiments, any modification of any component of each embodiment, or any omission of any component of each embodiment.

The present disclosure is suitable for a question answering device and a question answering method.

1 Chatbot, 2 Question answering device, 3 Sensing device, 11 Voice recognition unit, 12 Voice database, 13 Chatbot engine unit, 14 Display unit, 15 Voice output unit, 21 Sensing data collection unit, 22 Question data acquisition unit, 23 Answer creation unit, 24 Answer data reply unit, 25 Answer creation unit, 26 Answer data reply unit, 27 Answer creation unit, 31 Sensing data collection circuit, 32 Question data acquisition circuit, 33 Answer creation circuit, 34 Answer data reply circuit, 35 Answer creation circuit, 36 Answer data reply circuit, 37 Answer creation circuit, 41 Learning model, 42, 43 Care record database, 51 Memory, 52 Processor, 61 Bed sensor, 62 Room sensor, 63 Home appliance sensor, 64 Human presence sensor, 65 Vital sensor, 66 Ingestion detection sensor, 67 Sensing data recording unit.

Claims (9)

a sensing data collection unit that collects sensing data from a sensor that monitors the condition of the care recipient;
a question data acquiring unit for acquiring question data indicating a question regarding the care recipient;
an answer creation unit that creates an answer to a question indicated by the question data acquired by the question data acquisition unit, based on the sensing data collected by the sensing data collection unit;
an answer data reply unit that replies with answer data indicating the answer created by the answer creation unit ,
The question answering device is characterized in that the answer creation unit obtains multiple answer templates to the question indicated by the question data, and selects, from the multiple templates, a template that corresponds to the situation indicated by the sensing data as an answer to the question. The answer creation unit:
The question answering device according to claim 1, characterized in that an answer to a question indicated by the question data acquired by the question data acquisition unit is created based on the sensing data collected by the sensing data collection unit and the care records of the care recipient. The answer creation unit:
creating advice corresponding to the situation of the care recipient in addition to answers to questions indicated by the question data acquired by the question data acquisition unit;
The answer data reply unit:
2. The question and answering device according to claim 1, wherein advice data indicating advice prepared by said answer preparation section is returned in addition to answer data indicating the answer prepared by said answer preparation section. The answer creation unit:
In addition to the answers to the questions, a graph showing the change over time of the sensing data collected by the sensing data collection unit or a table showing the change over time of the sensing data is created;
The answer data reply unit:
2. The question and answering device according to claim 1, further comprising: a response section for responding to the question and answering request; The answer creation unit:
Acquire information indicating the medical history of the care recipient, information about the care recipient recorded on a face sheet, or information indicating the schedule of the care recipient as a care record of the care recipient;
The question answering device according to claim 2, characterized in that an answer to a question indicated by the question data acquired by the question data acquisition unit is created based on the sensing data collected by the sensing data collection unit and the care record of the care recipient. The answer creation unit:
The question answering device described in claim 2, characterized in that in addition to the sensing data collected by the sensing data collection unit and the care record of the care recipient, answers to questions indicated by the question data acquired by the question data acquisition unit are created based on the care recipient's house call history. The answer creation unit:
The question answering device according to claim 2, characterized in that in addition to the sensing data collected by the sensing data collection unit and the care record of the care recipient, an answer to a question indicated by the question data acquired by the question data acquisition unit is created based on the prescription record of the care recipient. a sensing data collection unit that collects sensing data from a sensor that monitors the condition of the care recipient;
a question data acquiring unit for acquiring question data indicating a question regarding the care recipient;
an answer creation unit that creates an answer to a question indicated by the question data acquired by the question data acquisition unit, based on the sensing data collected by the sensing data collection unit;
an answer data returning unit that returns answer data indicating the answer created by the answer creating unit;
Equipped with
The sensor is a home appliance sensor that monitors the usage status of a home appliance used by the care recipient,
The question answering device is characterized in that the answer creation unit not only creates answers to questions indicated by the question data acquired by the question data acquisition unit, but also determines the degree of independence of the care recipient based on the usage status of the home appliance indicated by the monitoring results of the home appliance sensor. The sensing data collection unit collects sensing data from a sensor that monitors the condition of the care recipient,
a question data acquisition unit acquires question data indicating a question regarding the care recipient;
an answer creation unit creates an answer to a question indicated by the question data acquired by the question data acquisition unit, based on the sensing data collected by the sensing data collection unit;
an answer data reply unit that replies with answer data indicating the answer created by the answer creation unit,
The question answering method is characterized in that the answer creation unit obtains multiple answer templates to the question indicated by the question data, and selects, from the multiple templates, a template that corresponds to the situation indicated by the sensing data as an answer to the question .

Images