Question answering device and question answering method

Abstract

This question answering device (2) comprises: a question data acquisition unit (21) that acquires question data indicating a question pertaining to a care recipient; and a database search unit (23) that searches one or more databases, which are used to create an answer to the question indicated by the question data acquired by the question data acquisition unit (21), from among a first database (41) recording sensing data of a sensor for monitoring the situation of the care recipient and a second database (42) recording care information relating to the care recipient. The question answering device (2) further comprises: an answer creation unit (25) that creates an answer to the question on the basis of details recorded in the databases searched by the database search unit (23); and an answer data return unit (26) that returns answer data indicating the answer created by the answer creation unit (25).

Description

Question and answering device and question and answering method

[0001] The present disclosure relates to a question and answering device and a question and answering method.

[0002] There is a question answering device that generates answers to questions about care recipients. For example, Patent Literature 1 discloses a question answering device that includes 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 the similarity between each of a plurality of answer candidate sentences that describe an answer to the question and the query sentence. The extraction unit extracts, from the plurality of answer candidate sentences, an answer candidate sentence that has a relatively high similarity calculated by the calculation unit, and transmits the extracted answer candidate sentence to the user terminal.

[0003] Japanese Patent Application Laid-Open No. 2021-124824

[0004] 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 is a problem in that they do not necessarily indicate an answer that reflects the situation of a specific person related to the question.

[0005] 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.

[0006] A question answering device according to the present disclosure includes a question data acquisition unit that acquires question data indicating a question about a care recipient, and a database search unit that searches for one or more databases to be used for creating an answer to the question indicated by the question data acquired by the question data acquisition unit from a first database that records sensing data from a sensor that monitors the condition of the care recipient and a second database that records care information about the care recipient. The question answering device also includes an answer creation unit that creates an answer to the question based on the recorded contents of the database searched by the database search unit, and an answer data reply unit that replies with answer data indicating the answer created by the answer creation unit.

[0007] According to the present disclosure, it is possible to create an answer to a question that reflects the condition of the care recipient.

[0008] 1 is a configuration diagram showing a system including a question and answering apparatus 2 according to embodiment 1. FIG. 2 is a hardware configuration diagram showing the hardware of the question and answering apparatus 2 according to embodiment 1. FIG. 3 is a hardware configuration diagram of a computer when the question and answering apparatus 2 is realized by software, firmware, or the like. FIG. 4 is a flowchart showing a question and answering method, which is a processing procedure of the question and answering apparatus 2. FIG. 5 is an explanatory diagram showing the answer "You need ◇◇ ml more" when the question is "How much more water does Mr. / Ms. XX need?". FIG. 6 is an explanatory diagram showing an example of an image for supplementing the answer. FIG. 7 is a configuration diagram showing a system including a question and answering apparatus 2 according to embodiment 2. FIG. 8 is a hardware configuration diagram showing the hardware of the question and answering apparatus 2 according to embodiment 2.

[0009] In order to explain the present disclosure in more detail, embodiments of the present disclosure will be described below with reference to the accompanying drawings.

[0010] Embodiment 1. Fig. 1 is a configuration diagram showing a system including a question and answering apparatus 2 according to embodiment 1. Fig. 2 is a hardware configuration diagram showing the hardware of the question and answering apparatus 2 according to embodiment 1. The system shown in Fig. 1 includes a chatbot 1, a question and answering apparatus 2, and a sensing device 3.

[0011] The chatbot 1 includes 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 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 as question data to the question answering device 2. The chatbot 1 outputs the answer data returned from the question answering device 2 to the display unit 14 and the voice output unit 15, respectively.

[0012] The speech recognition unit 11 recognizes the user's speech and creates text data representing the user's speech based on the speech data recorded in the speech database 12. The speech data recorded in the speech database 12 is, for example, speech piece data representing speech pieces. The speech recognition unit 11 outputs the text data as question data to the chatbot engine unit 13. The speech database 12 stores, for example, speech piece data and text data corresponding to the speech piece data.

[0013] When the chatbot engine unit 13 acquires question data from the voice recognition unit 11, it outputs the question data to the question answering apparatus 2, and when 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 answering apparatus 2. The chatbot engine unit 13 displays the answer indicated by the answer data on the display unit 14. The chatbot engine unit 13 outputs the answer indicated by the answer data by voice from the audio output unit 15.

[0014] The display unit 14 displays on a display (not shown) the answer indicated by the answer data output from the chatbot engine unit 13. 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).

[0015] The question and answering device 2 includes a question data acquisition unit 21, a sensing data collection unit 22, a database search unit 23, a sensing data selection unit 24, an answer creation unit 25, and an answer data reply unit 26. The question data acquisition unit 21 is realized, for example, by a question data acquisition circuit 31 shown in FIG. 2. The question data acquisition unit 21 acquires question data indicating a question about the care recipient from the chatbot engine unit 13 of the chatbot 1. The question data acquisition unit 21 outputs the question data to the database search unit 23, the sensing data selection unit 24, and the answer creation unit 25, respectively.

[0016] The sensing data collection unit 22 is realized by, for example, the sensing data collection circuit 32 shown in FIG. 2 . The sensing data collection unit 22 collects sensing data from various sensors included in the sensing device 3. The various sensors are sensors that monitor the condition of the care recipient. The condition of the care recipient may, for example, be the vital signs of the care recipient, the behavior of the care recipient, or the situation in which the care recipient is placed. The situation of the care recipient may, for example, be the temperature, humidity, or ambient noise in the care recipient's room. The sensing data collection unit 22 records the sensing data in a first database 41. The first database 41 is a database for recording the sensing data collected by the sensing data collection unit 22. The second database 42 is a database for recording care information of the care recipient.

[0017] The database search unit 23 is realized by, for example, the database search circuit 33 shown in Fig. 2. The database search unit 23 acquires question data from the question data acquisition unit 21. The database search unit 23 searches for one or more databases to be used to create an answer to the question indicated by the question data from a first database 41 that records sensing data from a sensor that monitors the condition of the care recipient and a second database 42 that records care information about the care recipient. The database search unit 23 outputs information indicating the database to be used to create an answer to the question to each of the sensing data selection unit 24 and the answer creation unit 25.

[0018] Specifically, the database search unit 23 provides the question data to the learning model 43 and acquires, from the learning model 43, information indicating a database corresponding to the question indicated by the question data. The learning model 43 is realized, for example, by a neural network. During learning, the learning model 43 is provided with question data indicating a question about the care recipient and information indicating a database corresponding to the question, and learns the database corresponding to the question. The information indicating the database corresponding to the question is training data. During inference, when the learning model 43 is provided with question data from the database search unit 23, it outputs, to the database search unit 23, information indicating the database corresponding to the question indicated by the question data.

[0019] The sensing data selection unit 24 is realized by, for example, the sensing data selection circuit 34 shown in FIG. 2 . The sensing data selection unit 24 acquires question data from the question data acquisition unit 21, and acquires information indicating a database to be used to create an answer to the question from the database search unit 23. When the database search unit 23 searches the first database 41, the sensing data selection unit 24 selects sensing data corresponding to the question indicated by the question data from the sensing data recorded in the first database 41. The sensing data selection unit 24 outputs the selected sensing data to the answer creation unit 25.

[0020] Specifically, the sensing data selection unit 24 provides the question data to the learning model 44 and acquires, from the learning model 44, selection information indicating sensing data corresponding to the question indicated by the question data. The sensing data selection unit 24 acquires sensing data indicated by the selection information from the sensing data recorded in the first database 41. The learning model 44 is realized, for example, by a neural network. During learning, the learning model 44 is provided with question data indicating a question about the care recipient and selection information indicating sensing data to be selected, and learns the sensing data to be selected. The selection information indicating the sensing data to be selected is training data. During inference, when question data is provided from the sensing data selection unit 24, the learning model 44 outputs selection information indicating sensing data corresponding to the question indicated by the question data to the sensing data selection unit 24.

[0021] The answer creation unit 25 is realized by, for example, the answer creation circuit 35 shown in FIG. 2 . The answer creation unit 25 acquires question data from the question data acquisition unit 21. When the database search unit 23 searches the first database 41, the answer creation unit 25 creates an answer to the question indicated by the question data based on the sensing data output from the sensing data selection unit 24. When the database search unit 23 searches the second database 42, the answer creation unit 25 creates an answer to the question indicated by the question data based on the care information of the care recipient recorded in the second database 42. When the database search unit 23 searches both the first database 41 and the second database 42, the answer creation unit 25 creates an answer to the question indicated by the question data based on the sensing data output from the sensing data selection unit 24 and the care information of the care recipient recorded in the second database 42. The answer creation unit 25 outputs answer data indicating the created answer to the answer data return unit 26.

[0022] Specifically, the answer creation unit 25 provides the question data to the learning model 45 and acquires, from the learning model 45, a template of an answer to the question indicated by the question data. The learning model 45 is realized, for example, by a neural network. During learning, the learning model 45 is provided with question data indicating a question about the care recipient and template data indicating a template of an answer corresponding to the question, and learns the template of the answer. The template data is training data. During inference, when the learning model 45 is provided with question data from the answer creation unit 25, it outputs template data indicating a template of an answer corresponding to the question indicated by the question data to the answer creation unit 25.

[0023] When the database search unit 23 searches the first database 41, the answer creation unit 25 creates an answer to the question indicated by the question data based on the answer template and the sensing data output from the sensing data selection unit 24. When the database search unit 23 searches the second database 42, the answer creation unit 25 creates an answer to the question indicated by the question data based on the answer template and the care information of the care recipient recorded in the second database 42. When the database search unit 23 searches both the first database 41 and the second database 42, the answer creation unit 25 creates an answer to the question indicated by the question data based on the answer template, the sensing data output from the sensing data selection unit 24, and the care information of the care recipient recorded in the second database 42.

[0024] 1 , the first database 41, the second database 42, and the learning models 43, 44, and 45 are each provided outside the question and answering apparatus 2. However, this is merely an example, and the first database 41, the second database 42, and the learning models 43, 44, and 45 may each be provided inside the question and answering apparatus 2.

[0025] The answer data reply unit 26 is realized by, for example, the answer data reply circuit 36 ​​shown in Figure 2. The answer data reply unit 26 acquires answer data from the answer creation unit 25. The answer data reply unit 26 replies to the answer data to the chatbot engine unit 13 of the chatbot 1.

[0026] 1, it is assumed that each of the components of the question and answering apparatus 2, namely, question data acquisition unit 21, sensing data collection unit 22, database search unit 23, sensing data selection unit 24, answer creation unit 25, and answer data reply unit 26, is realized by dedicated hardware as shown in Fig. 2. In other words, it is assumed that the question and answering apparatus 2 is realized by a question data acquisition circuit 31, sensing data collection circuit 32, database search circuit 33, sensing data selection circuit 34, answer creation circuit 35, and answer data reply circuit 36. Each of the query data acquisition circuit 31, the sensing data collection circuit 32, the database search circuit 33, the sensing data selection circuit 34, the answer creation circuit 35, and the answer data return circuit 36 ​​is, 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 thereof.

[0027] 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. Software or firmware is stored as a program in the memory of a computer. A computer refers to hardware that executes a 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).

[0028] 3 is a hardware configuration diagram of a computer when the question and answering apparatus 2 is realized by software, firmware, etc. When the question and answering apparatus 2 is realized by software, firmware, etc., a program for causing a computer to execute the processing procedures of the question data acquisition unit 21, the sensing data collection unit 22, the database search unit 23, the sensing data selection unit 24, the answer creation unit 25, and the answer data return unit 26 is stored in a memory 51. A processor 52 of the computer then executes the program stored in the memory 51.

[0029] 2 shows an example in which each of the components of the question answering apparatus 2 is realized by dedicated hardware, and Fig. 3 shows an example in which the question answering apparatus 2 is realized by software, firmware, etc. However, this is merely an example, and some of the components in the question answering apparatus 2 may be realized by dedicated hardware and the remaining components may be realized by software, firmware, etc.

[0030] The sensing device 3 includes 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 ingestion detection sensor 66, and also includes 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 bed. The room sensor 62 is a sensor installed in the care recipient's room and monitors, for example, the care recipient's sleep, falls, or body movements.

[0031] 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 of the care recipient's room. The human presence sensor 64 is, for example, a sensor attached to an entrance or exit of the care recipient's room and detects, for example, when the care recipient leaves the room. The vital sign sensor 65 is, for example, a sensor attached to a wall, ceiling, furniture, or the care recipient's room and monitors, for example, the care recipient's vital signs. 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 care recipient's water intake behavior or food intake behavior. The sensing data recording unit 67 is a database that records sensing data from the bed sensor 61, the room sensor 62, the home appliance sensor 63, the human presence sensor 64, the vital sign sensor 65, and the intake detection sensor 66.

[0032] Next, we will explain the operation of the question answering device 2 shown in Fig. 1. Fig. 4 is a flowchart showing a question answering method, which is a processing procedure of the question answering device 2. In the system shown in Fig. 1, the care recipient is, for example, a person hospitalized in a nursing home or a medical hospital, and the user who asks a question about the care recipient is, for example, a staff member of the nursing home or the medical hospital.

[0033] When the voice of the staff member is provided to the voice recognition unit 11 of the chatbot 1 via a microphone (not shown), the voice recognition unit 11 breaks down the voice of the staff member into, for example, a plurality of speech segments. The voice recognition unit 11 acquires text data corresponding to each speech segment from the voice database 12. The voice recognition unit 11 connects the text data corresponding to each speech segment and outputs the connected text data to the chatbot engine unit 13 as question data.

[0034] The question data may include, for example, "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?"

[0035] Here, the staff member's voice is provided to the voice recognition unit 11, and text data is output as question data from the voice recognition unit 11 to the chatbot engine unit 13. However, this is merely an 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.

[0036] 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 21 of the question and answering apparatus 2.

[0037] The question data acquisition unit 21 acquires question data indicating a question about the care recipient from the chatbot engine unit 13 (step ST1 in FIG. 4 ). The question data acquisition unit 21 outputs the question data to each of the database search unit 23, the sensing data selection unit 24, and the answer creation unit 25.

[0038] The sensing data collection unit 22 collects sensing data related 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 collection unit 22 identifies the care recipient by performing a care recipient identification process. The care recipient identification process may, for example, be a well-known process of identifying the care recipient by searching for the care recipient's name included in the question data output from the question data acquisition unit 21. If the care recipient is Mr. / Ms. XX, the sensing data collection unit 22 collects sensing data related to Mr. / Ms. XX, and if the care recipient is Mr. / Ms. △△, the sensing data collection unit 22 collects sensing data related to Mr. / Ms. △△. The sensing data collection unit 22 records the collected sensing data in the first database 41.

[0039] The database search unit 23 acquires question data from the question data acquisition unit 21. The database search unit 23 searches the first database 41 and the second database 42 for one or more databases to be used to generate an answer to the question indicated by the question data (step ST3 in FIG. 4 ). Specifically, the database search unit 23 provides the question data to the learning model 43 and acquires, from the learning model 43, information indicating a database corresponding to the question indicated by the question data. If the question indicated by the question data is, for example, "Is Mr. / Ms. X sleeping now?" or "Is Mr. / Ms. X eating?", the database search unit 23 acquires, from the learning model 43, information indicating that the first database 41 will be used as the database to be used to generate an answer to the question. If the question indicated by the question data is, for example, "Did Mr. / Ms. X have a bowel movement today?" or "Does Mr. / Ms. X have a vaccination scheduled today?", the database search unit 23 acquires, from the learning model 43, information indicating that the second database 42 will be used as the database to be used to generate an answer to the question. For example, if the question indicated by the question data is "How much more water does Mr. / Ms. XX need?" or "Have you been sleeping well recently?", information indicating that both the first database 41 and the second database 42 will be used as databases to create an answer to the question is obtained from the learning model 43. The database search unit 23 outputs information indicating the database to be used to create an answer to the question to each of the sensing data selection unit 24 and the answer creation unit 25.

[0040] The sensing data selection unit 24 acquires question data from the question data acquisition unit 21, and acquires information indicating a database to be used to create an answer to the question from the database search unit 23. When the first database 41 is searched by the database search unit 23 (step ST4 in FIG. 4: YES), the sensing data selection unit 24 selects sensing data corresponding to the question indicated by the question data from the sensing data recorded in the first database 41 (step ST5 in FIG. 4).

[0041] Specifically, the sensing data selection unit 24 provides the question data to the learning model 44 and acquires, from the learning model 44, selection information indicating sensing data corresponding to the question indicated by the question data. For example, if the question indicated by the question data is, "Is Mr. / Ms. XX sleeping now?", the learning model 44 outputs selection information indicating sensing data from the bed sensor 61 or selection information indicating sensing data from the room sensor 62 as sensing data corresponding to the question. For example, if the question indicated by the question data is, "Is Mr. / Ms. XX eating?", the learning model 44 outputs selection information indicating sensing data from the ingestion detection sensor 66 as sensing data corresponding to the question. The sensing data selection unit 24 acquires sensing data indicated by the selection information from the sensing data recorded in the first database 41. The sensing data selection unit 24 outputs the acquired sensing data to the answer creation unit 25.

[0042] The answer creation unit 25 acquires question data from the question data acquisition unit 21 and acquires information indicating a database to be used to create an answer to the question from the database search unit 23. The answer creation unit 25 acquires sensing data from the sensing data selection unit 24. If the second database 42 has not been searched by the database search unit 23 (step ST6 in FIG. 4 : NO), the answer creation unit 25 creates an answer to the question indicated by the question data based on the sensing data (step ST7 in FIG. 4 ). Specifically, the answer creation unit 25 provides the question data to the learning model 45 and acquires, from the learning model 45, an answer template for the question indicated by the question data. If the question indicated by the question data is, for example, "Is Mr. / Ms. X sleeping now?", for example, the answer creation unit 25 acquires an answer template of "Mr. / Ms. X sleeping now" as answer template (1) and an answer template of "Mr. / Ms. X is not sleeping now" 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 25 outputs answer template (1) as answer data indicating an answer corresponding to the question to the answer data reply unit 26. 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 25 outputs answer template (2) as answer data indicating an answer corresponding to the question to the answer data reply unit 26.

[0043] If the question indicated by the question data is, for example, "Is X-san eating?", then, for example, an answer template "X-san is eating" is acquired as answer template (1) and an answer template "X-san is not eating" is acquired as answer template (2). If the sensing data of the ingestion detection sensor 66 indicates that X-san is eating, the answer creating unit 25 outputs answer template (1) to the answer data replying unit 26 as answer data indicating the answer corresponding to the question. If the sensing data of the ingestion detection sensor 66 indicates that X-san is not eating, the answer creating unit 25 outputs answer template (2) to the answer data replying unit 26 as answer data indicating the answer corresponding to the question.

[0044] When the database search unit 23 searches only the second database 42 (step ST4: NO, step ST5: YES in FIG. 4 ), the answer creation unit 25 acquires the care information of the care recipient from the second database 42. The answer creation unit 25 creates an answer to the question indicated by the question data based on the care information of the care recipient (step ST9 in FIG. 4 ). If the question indicated by the question data is, for example, "Did Mr. / Ms. X have a bowel movement today?", the answer creation unit 25 acquires, for example, an answer template such as "Mr. / Ms. X had a bowel movement today" as answer template (1) and an answer template such as "Mr. / Ms. X did not have a bowel movement today" as answer template (2). If the care information of the care recipient contains a bowel movement record of Mr. / Ms. X today, the answer creation unit 25 outputs answer template (1) to the answer data reply unit 26 as answer data indicating an answer corresponding to the question. If there is no bowel movement record for Mr. / Ms. XX today in the care information of the care recipient, the answer creation unit 25 outputs answer template (2) to the answer data reply unit 26 as answer data indicating the answer corresponding to the question.

[0045] For example, if the question indicated by the question data is, "Does Mr. / Ms. XX have a vaccination scheduled for today?", the answer creation unit 25 acquires, for example, an answer template such as "Mr. / Ms. XX has a vaccination scheduled for today" as answer template (1) and an answer template such as "Mr. / Ms. XX does not have a vaccination scheduled for today" as answer template (2). If the care information of the care recipient includes a vaccination scheduled for Mr. / Ms. XX today, the answer creation unit 25 outputs answer template (1) to the answer data reply unit 26 as answer data indicating an answer corresponding to the question. If the care information of the care recipient does not include a vaccination scheduled for Mr. / Ms. XX today, the answer creation unit 25 outputs answer template (2) to the answer data reply unit 26 as answer data indicating an answer corresponding to the question.

[0046] When the database search unit 23 has searched both the first database 41 and the second database 42 (step ST6 in FIG. 4 : YES), the answer creation unit 25 acquires the care information of the care recipient from the second database 42. The answer creation unit 25 creates an answer to the question indicated by the question data based on the sensing data and the care information of the care recipient (step ST10 in FIG. 4 ). For example, if the question indicated by the question data is, "How much more water does Mr. / Ms. XX need?", the answer creation unit 25 acquires, for example, an answer template such as "YY ml more needed" as answer template (1) and an answer template such as "The required amount of water has already been acquired" as answer template (2). The answer creation unit 25 acquires information on "the amount of water intake required by Mr. / Ms. XX per day" from the care information of the care recipient. If Mr. / Ms. XX's medical history includes diabetes, information on "the amount of water intake required by Mr. / Ms. XX per day" may be included in Mr. / Ms. XX's care record. For example, if the question indicated by the question data is "How much more water does Mr. / Ms. X need?", the answer creation unit 25 acquires information on "X's water intake today" from the sensing data of the intake detection sensor 66. If "X's water intake today" is equal to or greater than "X's required daily water intake," the answer creation unit 25 selects answer template (2) from answer template (1) and answer template (2). Then, the answer creation unit 25 outputs answer template (2) to the answer data reply unit 26 as answer data indicating the answer corresponding to the question. If "X's water intake today" is less than "X's required daily water intake," the answer creation unit 25 selects answer template (1) from answer template (1) and answer template (2). Then, the answer creation unit 25 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 reply unit 26 as answer data indicating the answer corresponding to the question.

[0047] For example, if the question indicated by the question data is, "Has Mr. / Ms. XX been sleeping well recently?", the answer creation unit 25 acquires, for example, an answer template "Mr. / Ms. XX has been sleeping well recently" as answer template (1), and an answer template "Mr. / Ms. XX has not been sleeping very well recently" as answer template (2). The answer creation unit 25 acquires information on "Mr. / Ms. XX's average sleeping time" from the care information of the care recipient. If the question indicated by the question data is, for example, "Has Mr. / Ms. XX been sleeping well recently?", the answer creation unit 25 acquires information on "Mr. / Ms. XX's sleeping time yesterday" from the sensing data of the bed sensor 61 or the sensing data of the room sensor 62. If "Mr. / Ms. XX's sleeping time yesterday" is equal to or longer than "Mr. / Ms. XX's average sleeping time," the answer creation unit 25 selects answer template (1) from answer template (1) and answer template (2). Then, the answer creation unit 25 outputs answer template (1) to the answer data reply unit 26 as answer data indicating an answer corresponding to the question. If "X's sleeping time yesterday" is less than "X's average sleeping time," the answer creation unit 25 selects answer template (2) from answer template (1) and answer template (2). Then, the answer creation unit 25 outputs answer template (2) to the answer data reply unit 26 as answer data indicating an answer corresponding to the question.

[0048] If neither the first database 41 nor the second database 42 has been searched (step ST8 in FIG. 4: NO), the answer creating unit 25 does not create an answer corresponding to the question.

[0049] The answer data reply unit 26 acquires the answer data from the answer creation unit 25. The answer data reply unit 26 replies with the answer data to the chatbot engine unit 13 of the chatbot 1 (step ST11 in FIG. 4).

[0050] The chatbot engine unit 13 acquires the answer data from the answer data reply unit 26. As shown in FIG. 5, the chatbot engine unit 13 displays the answer indicated by the answer data on the display of the display unit 14. The chatbot engine unit 13 also outputs the answer indicated by the answer data aloud from the speaker of the audio output unit 15. FIG. 5 is an explanatory diagram showing the answer "You need ◇◇ ml more" when the question is "How much more water does Mr. / Ms. XX need?". Note that ◇◇ contains the difference between "The amount of water Mr. / Ms. XX needs to drink per day" and "The amount of water Mr. / Ms. XX has drunk today." In FIG. 5, □□□□ is the name of the staff member.

[0051] In the first embodiment described above, question answering device 2 is configured to include question data acquiring unit 21 that acquires question data indicating a question regarding the care recipient, and database searching unit 23 that searches one or more databases to be used for creating an answer to the question indicated by the question data acquired by question data acquiring unit 21 from first database 41 that records sensing data from a sensor that monitors the condition of the care recipient and second database 42 that records care information about the care recipient. Question answering device 2 also includes answer creating unit 25 that creates an answer to the question based on the recorded content of the database searched by database searching unit 23, and answer data reply unit 26 that returns answer data indicating the answer created by answer creating unit 25. Therefore, question answering device 2 can create an answer to a question that reflects the condition of the care recipient.

[0052] In the question answering device 2 shown in FIG. 1 , the answer creation unit 25 creates an answer to a question based on the recorded contents of the database searched by the database search unit 23. In addition to creating an answer, the answer creation unit 25 may also create an image to supplement the answer, as shown in FIG. 6 . In this case, the answer data reply unit 26 replies to the chatbot engine unit 13 with answer data indicating the answer created by the answer creation unit 25 and image data indicating the image created by the answer creation unit 25. FIG. 6 is an explanatory diagram showing an example of an image to supplement the answer. In FIG. 6 , when the answer to the question, "How much more water does Mr. / Ms. X need?" is "You need ◇◇ ml more," a graph showing "X's water intake today" and "X's required daily water intake" is displayed as an image to supplement the answer. In the example of FIG. 6 , "X's water intake today" is 600 ml, and "X's required daily water intake" is 1500 ml.

[0053] Here, the answer creating unit 25 creates graphs showing "X's water intake today" and "X's daily required water intake" as images to supplement the answer. However, this is just one example, and the answer creating unit 25 may create, as images to supplement the answer, images showing, for example, X's image, X's nursing care record, X's medication record, or X's schedule.

[0054] In the question answering device 2 shown in FIG. 1 , the database search unit 23 provides question data to the learning model 43 and acquires, from the learning model 43, information indicating a database corresponding to the question indicated by the question data. However, this is merely an example, and the database search unit 23 may also acquire information indicating a database corresponding to the question indicated by the question data based on, for example, a rule base. In the question answering device 2 shown in FIG. 1 , the sensing data selection unit 24 provides question data to the learning model 44 and acquires, from the learning model 44, selection information indicating sensing data corresponding to the question indicated by the question data. However, this is merely an example, and the sensing data selection unit 24 may also acquire, for example, based on a rule base, selection information indicating sensing data corresponding to the question indicated by the question data. In the question answering device 2 shown in FIG. 1 , the answer creation unit 25 provides question data to the learning model 45 and acquires, from the learning model 45, a template of an answer to the question indicated by the question data. However, this is merely an example, and the answer creation unit 25 may also acquire, for example, a template of an answer to the question indicated by the question data based on, for example, a rule base.

[0055] In the question answering device 2 shown in FIG. 1 , a question includes information indicating that the care recipient is, for example, “Mr. / Ms. XX” or “Mr. / Ms. △△.” However, this is merely an example, and the question does not necessarily include information indicating that the care recipient is, for example, “Mr. / Ms. XX” or “Mr. / Ms. △△.” In this case, for example, when a staff member at a nursing home or the like speaks to the voice recognition unit 11 of the chatbot 1, the staff member provides the chatbot engine unit 13 with their ID (IDentification). The chatbot engine unit 13 then displays information indicating one or more care recipients for which the staff member is responsible on the display unit 14. The chatbot engine unit 13 then accepts a selection operation by the 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 22 collects sensing data related to the care recipient indicated in the care recipient information from the sensing data recorded in the sensing data recording unit 67 of the sensing device 3.

[0056] Second Embodiment In a second embodiment, a question and answering device 2 will be described in which the answer data replying unit 27 not only replies with answer data indicating the answer created by the answer creating unit, but also contacts an emergency contact person.

[0057] FIG. 7 is a configuration diagram showing a system including a question answering apparatus 2 according to embodiment 2. In FIG. 7, the same reference numerals as in FIG. 1 indicate the same or corresponding parts, and detailed description thereof will be omitted. FIG. 8 is a hardware configuration diagram showing the hardware of the question answering apparatus 2 according to embodiment 2. In FIG. 8, the same reference numerals as in FIG. 2 indicate the same or corresponding parts, and detailed description thereof will be omitted. The system shown in FIG. 7 includes a chatbot 1, a question answering apparatus 2, and a sensing device 3. The question answering apparatus 2 shown in FIG. 7 includes a question data acquiring unit 21, a sensing data collecting unit 22, a database searching unit 23, a sensing data selecting unit 24, an answer creating unit 25, and an answer data returning unit 27.

[0058] The answer data reply unit 27 is realized by, for example, the answer data reply circuit 37 shown in Fig. 8. The answer data reply unit 27 acquires answer data from the answer creation unit 25. The answer data reply unit 27 returns the answer data to the chatbot engine unit 13 and also performs processing to contact an emergency contact. The answer data reply unit 27 also performs processing to return a video showing the condition of the care recipient to the chatbot engine unit 13, or processing to notify a doctor of the condition of the care recipient.

[0059] 7, it is assumed that each of the components of the question and answering apparatus 2, namely, the question data acquisition unit 21, the sensing data collection unit 22, the database search unit 23, the sensing data selection unit 24, the answer creation unit 25, and the answer data reply unit 27, is realized by dedicated hardware such as that shown in Fig. 8. That is, it is assumed that the question and answering apparatus 2 is realized by a question data acquisition circuit 31, a sensing data collection circuit 32, a database search circuit 33, a sensing data selection circuit 34, an answer creation circuit 35, and an answer data reply circuit 37. Each of the question data acquisition circuit 31, the sensing data collection circuit 32, the database search circuit 33, the sensing data selection circuit 34, the answer creation circuit 35, and the answer data reply circuit 37 corresponds to, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC, an FPGA, or a combination thereof.

[0060] 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 apparatus 2 is realized by software, firmware, or the like, programs for causing a computer to execute the processing procedures of the question data acquiring unit 21, the sensing data collecting unit 22, the database searching unit 23, the sensing data selecting unit 24, the answer creating unit 25, and the answer data returning unit 27 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.

[0061] 8 shows an example in which each of the components of the question answering apparatus 2 is realized by dedicated hardware, while Fig. 3 shows an example in which the question answering apparatus 2 is realized by software, firmware, etc. However, this is merely an example, and some of the components of the question answering apparatus 2 may be realized by dedicated hardware, and the remaining components may be realized by software, firmware, etc.

[0062] Next, the operation of the question answering apparatus 2 shown in Fig. 7 will be described. However, apart from the answer data replying unit 27, the question answering apparatus 2 is the same as that shown in Fig. 1. Therefore, only the operation of the answer data replying unit 27 will be described here.

[0063] The answer data reply unit 27 acquires answer data from the answer creation unit 25. Similar to the answer data reply unit 26 shown in FIG. 1 , the answer data reply unit 27 replies to the chatbot engine unit 13. For example, the telephone number or email address of an emergency contact is stored in the internal memory of the answer data reply unit 27 or an external memory (not shown). When replying the answer data to the chatbot engine unit 13, the answer data reply unit 27 calls the telephone number of the emergency contact and, for example, outputs a voice message indicating the answer data to the emergency contact. Alternatively, the answer data reply unit 27 sends the answer data to the email address of the emergency contact. In this example, the answer data reply unit 27 outputs a voice message indicating the answer data to the emergency contact. However, this is merely an example, and the answer data reply unit 27 may output a voice message indicating that an emergency is required. Whether an emergency is required may be determined by the answer data reply unit 27 analyzing the answer data, or the answer data reply unit 27 may receive a notification from the answer creation unit 25 that the answer is an emergency.

[0064] In addition, when the answer data reply unit 27 replies to the answer data to the chatbot engine unit 13, it may acquire video showing the condition of the person being cared for from a camera not shown and reply to the video to the chatbot engine unit 13.

[0065] The internal memory of the answer data reply unit 27 or an external memory (not shown) stores, for example, the doctor's telephone number or the doctor's email address. When replying to the chatbot engine unit 13 with answer data, the answer data reply unit 27 calls the doctor's telephone number and outputs, for example, a voice indicating the answer data to the doctor as the condition of the care recipient. Alternatively, the answer data reply unit 27 sends the answer data to the doctor's email address. Here, the answer data reply unit 27 outputs, to the doctor, a voice indicating the answer data as the condition of the care recipient. However, this is merely an example, and the answer data reply unit 27 may also output, for example, sensing data used to create the answer to the question or care information about the care recipient to the doctor as the condition of the care recipient.

[0066] In addition, the present disclosure allows for free combination of the respective embodiments, modification of any of the components of the respective embodiments, or omission of any of the components of the respective embodiments.

[0067] The present disclosure is suitable for a question and answering device and a question and answering method.

[0068] 1 Chatbot, 2 Question and answer device, 3 Sensing device, 11 Speech recognition unit, 12 Speech database, 13 Chatbot engine unit, 14 Display unit, 15 Speech output unit, 21 Question data acquisition unit, 22 Sensing data collection unit, 23 Database search unit, 24 Sensing data selection unit, 25 Answer creation unit, 26, 27 Answer data return unit, 31 Question data acquisition circuit, 32 Sensing data collection circuit, 33 Database search circuit, 34 Sensing data selection circuit, 35 Answer creation circuit, 36, 37 Answer data return circuit, 41 First database, 42 Second database, 43, 44, 45 Learning model, 51 Memory, 52 Processor, 61 Bed sensor, 62 Room sensor, 63 Home appliance sensor, 64 Human presence sensor, 65 Vital sensor, 66 Intake detection sensor, 67 Sensing data recording unit.

Claims

1. A question answering device comprising: a question data acquisition unit that acquires question data indicating a question regarding a care recipient; a database search unit that searches for one or more databases to be used for creating an answer to the question indicated by the question data acquired by the question data acquisition unit from a first database that records sensing data from a sensor monitoring the condition of the care recipient and a second database that records care information for the care recipient; an answer creation unit that creates an answer to the question based on the recorded contents of the database searched by the database search unit; and an answer data reply unit that replies with answer data indicating the answer created by the answer creation unit.

2. The question answering device described in claim 1, characterized in that it comprises a sensing data collection unit that collects sensing data from a sensor that monitors the condition of the care recipient and records the sensing data in the first database, and a sensing data selection unit that, when the first database is searched by the database search unit, selects sensing data from the sensing data recorded in the first database that corresponds to the question indicated by the question data acquired by the question data acquisition unit, and outputs the selected sensing data to the answer creation unit.

3. The question answering device described in claim 1, characterized in that the answer creation unit creates an image to supplement the answer in addition to creating an answer to the question based on the recorded contents of the database searched by the database search unit, and the answer data return unit returns answer data indicating the answer created by the answer creation unit and image data indicating the image created by the answer creation unit.

4. The question and answer device according to claim 1, characterized in that said answer data replying section contacts an emergency contact in addition to replying with answer data indicating the answer created by said answer creating section.

5. The question answering device according to claim 1, characterized in that the answer data replying unit, in addition to replying answer data indicating the answer created by the answer creating unit, also replies with a video showing the condition of the person being cared for.

6. The question and answer device according to claim 1, characterized in that the answer data replying unit not only replies with answer data indicating the answer created by the answer creating unit, but also notifies a doctor of the condition of the person being cared for.

7. A question answering method in which a question data acquisition unit acquires question data indicating a question regarding a care recipient; a database search unit searches for one or more databases to be used for creating an answer to the question indicated by the question data acquired by the question data acquisition unit, from a first database which records sensing data from a sensor monitoring the condition of the care recipient and a second database which records care information for the care recipient; an answer creation unit creates an answer to the question based on the recorded contents of the database searched by the database search unit; and an answer data reply unit replies with answer data indicating the answer created by the answer creation unit.

Images