Behavioral support device and intervention support method

Abstract

To provide an action support device and an intervention measure support method capable of supporting an intervention measure by estimating a mental state of a user based on objective index data.SOLUTION: An action support device 3 includes: an action support unit 33 that estimates, on the basis of index data that reflects a mental state of a user, feeling intensity of the user, determines, on the basis of setting data including load information of an intervention measure for the user, an intervention load of the intervention measure for the user, and determines, on the basis of the feeling intensity and the intervention load, a tolerance limit of the user; and a display unit 32 that displays, on a manager terminal 6, the tolerance limit of the user. The intervention load of the intervention measure for the user can be adjusted according to the tolerance limit of the user.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present invention relates to a behavior support device and an intervention measure support method.

Background Art

[0002] Patent Document 1 discloses an organization improvement activity support device. In order to improve the success rate of workplace improvement activities without the intervention of experts on site, the organization improvement activity support device of Patent Document 1 outputs advice based on the transition value of the behavior evaluation value indicating the evaluation on the behavior side of the measure and the emotion evaluation value indicating the latest evaluation on the emotion side. As the emotion evaluation value, "member responsiveness" is exemplified, and it is shown that evaluation is made in the categories of "good response", "no response", and "bad response". Thus, the emotion evaluation value is an index based on subjective judgment.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When implementing measures to change behavioral patterns, including education (referred to as intervention measures), the mental state of the target individuals influences their acceptance of these measures. Learning new things or changing existing behavioral patterns is stressful to some degree for the target individuals. For example, if an intervention measure is implemented for a target individual who is exhausted, it may not be sufficiently effective. If the intervention measure is conducted in person and the educator is experienced, it would be possible to understand the situation of the target individuals and adjust the content, level, and duration of the intervention measure to ensure effectiveness. However, if the educator is inexperienced or the intervention measure is implemented in a remote environment, it may be difficult to understand the situation of the target individuals, or there may be no mechanism to understand their situation. As a result, uniform intervention measures may be implemented without considering the mental state of the target individuals, leading to variability in the effectiveness of the intervention measure.

[0005] As described in Patent Document 1, if subjects are asked to input their mental state based on their own subjective judgment, then variations are unavoidable because each subject's perception is different. For this reason, it is desirable to judge the subject's mental state from objective indicators related to the subject and implement intervention measures that are appropriate to the subject's mental state. [Means for solving the problem]

[0006] One embodiment of the present invention is a behavioral support device that is connected via a network to a user terminal accessed by a user and an administrator terminal accessed by an administrator, and is a behavioral support device that supports administrator intervention measures for users, and reflects the mental state of the user. Regarding indicators classified into biometric indicators, behavioral indicators, and environmental indicators An input section for inputting indicator data and configuration data including information on the load of intervention measures for users, Based on a predetermined correspondence between combinations of multiple indicator data from different categories and levels of emotional intensity, the user Metric data from User emotional intensity level We estimate, Based on a predetermined correspondence between intervention load information and intervention load levels, Configuration data from Intervention burden of user intervention measures level Determine, Based on a predetermined correspondence between the level of emotional intensity, the level of intervention load, and the level of tolerance, the user emotional intensity Level and intervention measures for users intervention load From level, User tolerance level The behavioral support unit determines the user's tolerance level. level It has a display unit that displays on the administrator terminal, and the intervention burden of intervention measures for users is limited to the user's tolerance. level It is said to be adjustable accordingly. [Effects of the Invention]

[0007] By estimating the user's mental state based on objective indicator data, it becomes possible to support intervention measures. Other challenges and novel features will become apparent from the description and accompanying drawings in this specification. [Brief explanation of the drawing]

[0008] [Figure 1A] This is an intervention policy implementation system. [Figure 1B] This is an example of a hardware configuration for an information processing device. [Figure 2] This is a functional block diagram of the behavioral support device. [Figure 3] This is a flowchart for processing support for intervention measures. [Figure 4] This is an example of a biomarker. [Figure 5] This is an example of a behavioral indicator. [Figure 6] This is an example of an environmental indicator. [Figure 7] This is a flowchart for the emotion intensity estimation process. [Figure 8] This is an example of criteria for prioritizing indicators. [Figure 9A] This is an example of a data structure for an emotion intensity estimation database. [Figure 9B] This is an example of a data structure for an emotion intensity estimation database. [Figure 10] This is an example of a correspondence table. [Figure 11] This is a flowchart for the intervention load determination process. [Figure 12A] This is an example of a data structure for an intervention load determination database. [Figure 12B]This is an example of the data structure of the intervention load determination database. [Figure 13] This is an example of a correspondence table. [Figure 14] This is a flowchart of the tolerance determination process. [Figure 15A] This is an example of the data structure of the tolerance determination database. [Figure 15B] This is an example of the data structure of the tolerance determination database. [Figure 16] This is an example of a start screen. [Figure 17A] This is an example of the display of the estimated result of emotional intensity. [Figure 17B] This is an example of the display of the tolerance determination result. [Figure 18] This is an example of an evaluation screen. [Figure 19] This is a diagram for explaining the intervention measure execution support function.

Embodiments for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present invention will be described with reference to the drawings.

[0010] FIG. 1A shows an intervention measure execution system 1. The intervention measure execution system 1 includes a behavior support device 3, a user terminal 5 accessed by a user, and an administrator terminal 6 accessed by an administrator, and these are communicably connected to each other by a network 4. The content of the intervention measure executed by the intervention measure execution system 1 is not particularly limited, but here, an example will be described in which an administrator educates a target person (user) who is at home or in a remote location using the user terminal 5.

[0011] Sensor 2 is installed to understand the mental state of users receiving intervention measures (education in this example). Sensing data from sensor 2 is input as indicator data from the user terminal 5 to the behavior support device 3, which estimates the mental state of the user receiving education, in this case, emotional intensity. Based on the emotional intensity estimated from the indicator data and the intervention load determined from the educational content (in this example, the load required for the user to understand the educational content), the behavior support device 3 determines whether the user has sufficient tolerance to digest the educational content. The determination result is displayed on the administrator terminal 6, and for example, the administrator of the intervention measure (educator in this example) can adjust the educational content for the user and implement education according to their tolerance level. This makes it possible to maximize the effectiveness of the intervention measure.

[0012] The behavioral support device 3, user terminal 5, and administrator terminal 6 are each implemented by an information processing device 10, which primarily includes a processor (CPU) 11, memory 12, storage device 13, input device 14, output device 15, communication device 16, and bus 17, as shown in Figure 1B. The processor 11 functions as a functional unit that provides predetermined functions by executing processing according to a program loaded into the memory 12. The storage device 13 stores data and programs used by the functional unit. The storage device 13 uses a non-volatile storage medium such as an HDD (Hard Disk Drive) or SSD (Solid State Drive). The input device 14 is a keyboard, pointing device, etc., and the output device 15 is a display, etc. The communication device 16 enables communication with other information processing devices via the network 4. These are connected to each other via the bus 17.

[0013] Furthermore, some or all of the functions of the behavioral support device 3 may be implemented as a cloud-based application.

[0014] Figure 2 is a functional block diagram of the behavior support device 3. The behavior support device 3 is a device realized when the information processing device 10 executes a behavior support program, and has functional units including an input unit 31, a display unit 32, and a behavior support unit 33.

[0015] The input unit 31 is a functional unit that receives setting data 41 for supporting intervention measures (in this case, education) and indicator data 42 calculated by the user terminal 5 from sensing data from sensor 2, and stores them in the data storage unit 40. The data storage unit 40 also stores databases 45-48 necessary for processing by the behavior support device 3. Details of the setting data 41, indicator data 42, and databases 45-48 will be described later. The input of data 41 and 42 is performed via the communication device 16 from the user terminal 5 or administrator terminal 6 connected via the network 4. Alternatively, the data itself may be stored in the storage device 13, or the data itself may be stored in a data server that the behavior support device 3 can connect to via the network 4, and the storage device 13 may store the address for accessing the data server.

[0016] The behavioral support unit 33 is a functional unit that determines whether the user has sufficient tolerance for intervention measures. The behavioral support unit 33 includes an emotion intensity estimation unit 34, an intervention load determination unit 35, and a tolerance determination unit 36 ​​as sub-functional units. Details of these will be described later.

[0017] The display unit 32 is a functional unit that presents the results of the user's tolerance assessment by the behavior support unit 33 to the administrator (educator). The presentation to the administrator is made via the communication device 16 to the administrator terminal 6 connected through the network 4.

[0018] Figure 3 shows a flowchart of the intervention support process performed by the behavioral support device 3.

[0019] S01: The environment and content of the education the user receives are set in advance by the administrator and stored in the data storage unit 40 as setting data 41. The user accesses information about the education they will receive from the start screen displayed on the user terminal 5. Figure 16 shows an example of the start screen 50. When the user presses the access button 51, the setting information contained in the setting data 41 is displayed to the user. The pre-set content includes an index for estimating emotional intensity, educational load (intervention load), and educational information indicating the content and level of education.

[0020] Area 53 displays indicators for estimating emotional intensity. Check marks identify the indicators measured by user terminal 5 as indicator data. Here, three types of indicators can be set to estimate the user's emotional intensity: biometric indicators, behavioral indicators, and environmental indicators. Biometric indicators are based on sensing data that detects physiological changes reflecting the user's mental state. Examples include heart rate, voice, facial expressions, and eye gaze. There are no limitations on the sensors used to obtain the sensing data. Behavioral indicators are based on sensing data that detects the user's movements. Unconscious movements can also reflect the user's mental state. Examples include activity level and range of motion. Environmental indicators are based on sensing data that detects the environment in which the user receives education. Examples include thermal, acoustics, and the density of other people.

[0021] Area 54 displays intervention burden information. This information includes classifications based on factors such as the duration of the intervention, difficulty level, and complexity.

[0022] Area 55 displays information about the content of the intervention measures. In this example, since it is education, the content of the education is displayed in the education enrollment information, and the level of the participants is displayed in the occupational competency level. The occupational competency level may be local or public. This information is registered by the administrator based on the educational curriculum or educational content information registered in the education and occupational database 48.

[0023] S02: When the user confirms the contents of the start screen 50 and presses the measurement start button 52, sensing by sensor 2 begins in order to acquire index data. The user terminal 5 creates index data 42 from the sensing data from sensor 2 and transmits it to the behavior support device 3. The index data 42 is stored in the data storage unit 40. Figures 4 to 6 show examples of index data. Here, an example is shown in which sensing by sensor 2 is performed for 5 minutes, and the series of average values ​​of the sensing data every minute is used as index data.

[0024] Figure 4 shows examples of biometric indicators 42a, including heart rate (bpm), voice (dB), and facial expression (variability). Heart rate may be measured using a heart rate monitor as a sensor, or by using a camera as a sensor and extracting the pulse wave signal from images of the skin surface, such as the face. Voice can be measured using a microphone as a sensor. Facial expression can be measured by using a camera as a sensor and extracting changes in facial expression.

[0025] Figure 5 shows an example of behavioral indicator 42b, illustrating activity level and range of motion as behavioral indicators. Activity level can be measured using an accelerometer integrated into the wearable sensor. Range of motion may also be measured using an accelerometer, or it may be measured by using a camera as a sensor and extracting the user's movements.

[0026] Figure 6 shows an example of environmental indicator 42c, illustrating examples of environmental indicators such as thermal, acoustics (indoors), and other-person density (number of people in the room). Since environmental indicators are based on sensing data about the indoor environment in which the user is located, it is desirable to use sensors that can monitor a wide area of ​​the room where the user is located. For example, setting data from air conditioning equipment installed in the room, or sensing data from cameras and microphones built into air conditioning equipment, can be used. Thermal can be measured, for example, based on the air conditioning set temperature and the distance between the user's position and the air conditioning equipment, extracted from images from the camera built into the air conditioning equipment. Acoustics can be measured using a microphone built into the air conditioning equipment. Other-person density can be measured by extracting the positions of people from images from the camera built into the air conditioning equipment.

[0027] S03: The emotion intensity estimation unit 34 (see Figure 2) of the behavior support unit 33 estimates the emotion intensity as the user's mental state. Figure 7 shows the detailed flow of step S03. First, the indicator data 42 is read (S11), and the read indicator data 42 is ranked (S12). The criteria for ranking the indicators are shown in Figure 8. As shown in Figure 8, the priority of the indicators is determined in the order of biological indicators, behavioral indicators, and environmental indicators. This is because it is thought that the values ​​will more strongly reflect the user's emotion intensity in this order. However, if there are many missing values ​​in the indicator data, the user's emotion intensity may not be correctly reflected in the indicator data. For this reason, criteria for ranking the indicators are established, and the indicator data is made available with priority when the predetermined criteria are met.

[0028] In this example, the criteria for using the indicators are as follows: for biometric indicators, at least three average data points per minute are measured during a 5-minute measurement period; for behavioral indicators, sensing is performed simultaneously with the sensing of biometric indicators (for example, simultaneous sensing is determined if the time difference between the measurement data of biometric and behavioral indicators is within 30 seconds), and at least three average data points per minute are measured during a 5-minute measurement period; and for environmental indicators, measurement is performed within a spatial distance of 5m from the subject during the 5-minute measurement period for biometric indicators. From the indicators that meet these defined criteria, the top two priority combinations are selected as indicator data for estimating emotion intensity (S13). In the following, those with higher priority are referred to as priority classification 1, and those with lower priority are referred to as priority classification 2.

[0029] The user's emotional intensity is estimated (S14) by comparing the combination of indicators selected in step S13 with the emotional intensity estimation database 45. Figures 9A and 9B show the data structure of the emotional intensity estimation DB 45. Figure 9A defines the levels when each indicator (including indicators categorized into biometric indicators, behavioral indicators, and environmental indicators) is selected as priority classification 1, and Figure 9B defines the levels when each indicator (including indicators categorized into biometric indicators, behavioral indicators, and environmental indicators) is selected as priority classification 2. In both cases, the level is determined by the value of the indicator, and priority classification 1 is divided into 5 levels, and priority classification 2 is divided into 2 levels. Figure 10 is a correspondence table between the combinations of levels in priority classification 1 and priority classification 2 and emotional intensity. By referring to the correspondence table in Figure 10, for example, if the heart rate is 65 (level 2) and the acceleration is 15 (low level), the emotional intensity is estimated to be 3.

[0030] S04: Returning to the explanation of Figure 3. The intervention load determination unit 35 (see Figure 2) of the behavior support unit 33 determines the magnitude of the burden of the intervention measure (in this case, education) on the user. Figure 11 shows the detailed flow of step S04. First, the intervention load information set by the administrator is read from the setting data 41 (S21). The intervention load information corresponds to the content displayed in area 54 of the start screen 50. For the intervention load information, the measure implementation time is used as the intervention load information for priority classification 1, and either the difficulty level or complexity level is used as the intervention load information for priority classification 2.

[0031] The intervention load is determined (S21) by comparing the combination of intervention load information selected in step S21 with the intervention load determination database 46. Figures 12A and 12B show the data structure of the intervention load determination DB 46. Figure 12A defines the levels of the policy implementation time, which is priority classification 1, and Figure 9B defines the levels when each intervention load information (difficulty and complexity) is selected as priority classification 2. In both cases, the level is determined by the value or classification of the intervention load information, and priority classification 1 is divided into 5 levels, and priority classification 2 is divided into 2 levels. Figure 13 is a correspondence table between the combinations of levels in priority classification 1 and priority classification 2 and the intervention load. By referring to the correspondence table in Figure 13, for example, if the policy implementation time is 45 minutes (level 2) and the difficulty is known (low level), the intervention load is determined to be 3.

[0032] S05: The tolerance determination unit 36 ​​(see Figure 2) of the behavior support unit 33 determines the user's tolerance based on the user's emotional intensity estimated by the emotional intensity estimation unit 34 and the intervention load determination unit 35. Figure 14 shows the detailed flow of step S05. The emotional intensity estimation result and the intervention load determination result are input (S31, S32), and the tolerance is determined by comparing them with the tolerance determination database 47 (S33).

[0033] Figure 15A shows the data structure of the tolerance determination DB47. Tolerance is determined by a combination of the emotional intensity level and the intervention load level. High tolerance means that, in this example, the user is in a state of high educational effectiveness, and even with more demanding educational content, the educational effectiveness will increase. On the other hand, low tolerance means that, in this example, the user is in a state of low educational effectiveness, and the educational effectiveness will increase by using less demanding educational content. Figure 15B shows another example of the data structure of the tolerance determination DB47. While the example in Figure 15A only shows the criteria for determining tolerance, the example in Figure 15B includes recommendations for adjusting intervention measures according to the tolerance determination. By presenting administrators with not only the user's tolerance determination result but also recommended intervention measures (S34), administrators can adjust the load of the intervention measures to match the user's current mental state before implementing the intervention measures.

[0034] S06: Returning to the explanation of Figure 3. Upon receiving the tolerance assessment from the behavior support unit 33, the display unit 32 (see Figure 2) transmits the evaluation results from the behavior support unit 33 to the administrator terminal 6 and displays them to the administrator. Figure 17A is an example of the display of the estimated results of emotional intensity. Figure 17B is a map display of the tolerance assessment results. The determined tolerance is displayed as a map using emotional intensity and intervention load, which are elements of the tolerance assessment, as two axes.

[0035] Figure 18 shows an example of the evaluation screen 60 displayed on the administrator terminal 6. Area 61 displays the tolerance assessment result for the current intervention measure. The administrator can check the tolerance assessment result and adjust the workload of the intervention measure (education) to be implemented for the user by checking the intervention workload information displayed in area 62. When the administrator presses the intervention measure start button 63, the intervention measure (in this case, user education) is started. If the intervention workload is adjusted in area 62, education will be implemented according to the adjusted workload.

[0036] Furthermore, it is also possible to display screens such as Figures 17A and 17B, which show the elements for determining tolerance, from this screen. In addition, instead of displaying the tolerance assessment results for intervention measures for all users to the administrator, it is possible to request the administrator's confirmation only for users who have been evaluated as having the highest or lowest tolerance, for example.

[0037] Furthermore, by pressing the execution support function button 64, the system can support the execution of intervention measures while monitoring the user's state in real time. Figure 19 illustrates the support for the execution of intervention measures through real-time monitoring of emotional intensity. When supporting the execution of intervention measures, the sensor 2 continuously performs sensing, regardless of whether it is before or after the start of the implementation of the intervention measures, and the behavior support device 3 calculates the emotional intensity. Based on the calculated emotional intensity, the behavior support device 3 sends instructions to the user terminal 5 regarding the implementation of the intervention measures. For example, it may wait for the emotional intensity to subside before starting the implementation of the intervention measures, or if it is detected that the emotional intensity is increasing during the implementation of the intervention measures, it may display an alert on the user terminal 5 indicating that the emotional intensity is increasing. This allows the user to consciously maintain a good mental state and supports the appropriate execution of the intervention measures.

[0038] While education was used as an example of an intervention measure, the content of intervention measures is not limited to education. For example, it can be used in situations such as supporting people in taking exercises for health or encouraging them to take energy-saving actions in their daily lives.

[0039] The present invention is not limited to the embodiments described above, and includes various modifications. For example, the embodiments described above are described in detail to make the present invention easier to understand, and are not necessarily limited to those having all the configurations described. Furthermore, it is possible to replace parts of the configuration of one embodiment with the configuration of another embodiment, and it is also possible to add configurations from other embodiments to the configuration of one embodiment. In addition, it is possible to add, delete, or replace parts of the configuration of each embodiment with other configurations. [Explanation of symbols]

[0040] 1: Intervention measure execution system, 2: Sensor, 3: Behavioral support device, 4: Network, 5: User terminal, 6: Administrator terminal, 10: Information processing device, 11: Processor (CPU), 12: Memory, 13: Storage device, 14: Input device, 15: Output device, 16: Communication device, 17: Bus, 31: Input unit, 32: Display unit, 33: Behavioral support unit, 34: Emotion intensity estimation unit, 35: Intervention load determination unit, 36: Tolerance determination unit, 40: Data storage unit, 41: Setting data, 42: Indicator data, 45: Emotion intensity estimation database, 46: Intervention load determination database, 47: Tolerance determination database, 48: Education / professional database, 50: Start screen, 51: Call button, 52: Measurement start button, 53, 54, 55: Area, 60: Evaluation screen, 61, 62: Area, 63: Intervention measure start button, 64: Execution support function button.

Claims

1. An action support device that is connected via a network to a user terminal accessed by a user and an administrator terminal accessed by an administrator, and that supports the administrator's intervention measures for the user, An input unit that inputs indicator data for indicators that reflect the mental state of the user and are classified into biometric indicators, behavioral indicators, and environmental indicators, as well as setting data including information on the burden of the intervention measures on the user. A behavioral support unit that estimates the user's emotional intensity level from the user's indicator data based on a predetermined correspondence between a combination of multiple indicator data of different classifications and the emotional intensity level, determines the intervention load level of the intervention measure for the user from the setting data based on a predetermined correspondence between the load information of the intervention measure and the intervention load level, and determines the user's tolerance level from the user's emotional intensity level and the intervention load level of the intervention measure for the user, based on a predetermined correspondence between the combination of the emotional intensity level and the intervention load level and the tolerance level, The system includes a display unit that displays the user's tolerance level on the administrator terminal, A behavioral support device in which the intervention load of the intervention measures for the user can be adjusted according to the user's tolerance level.

2. In claim 1, Prior to implementing the intervention measures for the user, sensing is performed by a sensor, and the indicator data is created by the user terminal from the sensing data from the sensor and transmitted to the behavior support device.

3. In claim 1, The aforementioned indicator data includes indicator data created from sensing data that detects the physiological changes or movements of the user, and indicator data created from sensing data that detects the environment in which the user is located.

4. In claim 1, The load information for the intervention measures for the user includes the time the measures are implemented. A behavioral support device in which the duration of the intervention measures for the user can be adjusted according to the user's level of tolerance.

5. In claim 1, Prior to implementing the intervention measures for the user, sensing is initiated using sensors, and the indicator data is created by the user terminal from the sensing data from the sensors. A behavioral support device in which the intervention measures are implemented for the user according to the level of the user's emotional intensity.

6. An intervention support method using an action support device that is connected via a network to a user terminal accessed by a user and an administrator terminal accessed by an administrator, and which supports the administrator's intervention measures for the user, The aforementioned behavioral support device comprises an input unit, a behavioral support unit, and a display unit. The input unit receives indicator data for indicators that reflect the user's mental state and are classified into biometric indicators, behavioral indicators, and environmental indicators, as well as setting data including information on the burden of the intervention measures on the user. The behavioral support unit estimates the user's emotional intensity level from the user's indicator data based on a predetermined correspondence between the combination of multiple indicator data of different classifications and the emotional intensity level, determines the intervention load level of the intervention measure for the user from the setting data based on a predetermined correspondence between the load information of the intervention measure and the intervention load level, and determines the user's tolerance level from the user's emotional intensity level and the intervention load level of the intervention measure for the user based on a predetermined correspondence between the combination of the emotional intensity level and the intervention load level and the tolerance level. The display unit displays the user's tolerance level on the administrator terminal. An intervention support method wherein the intervention burden of the intervention measure for the user can be adjusted according to the user's tolerance level.

7. In claim 6, An intervention support method comprising: sensing by a sensor prior to the implementation of the intervention measure on the user; the indicator data being created by the user terminal from the sensing data from the sensor and transmitted to the behavior support device.

8. In claim 6, The aforementioned indicator data includes indicator data created from sensing data that detects the physiological changes or movements of the user and indicator data created from sensing data that detects the environment in which the user is located, as part of an intervention support method.

9. In claim 6, The load information for the intervention measures for the user includes the time the measures are implemented. An intervention support method wherein the duration of the implementation of the intervention measure for the user can be adjusted according to the user's tolerance level.

10. In claim 6, Prior to implementing the intervention measures for the user, sensing is initiated using sensors, and the indicator data is created by the user terminal from the sensing data from the sensors. An intervention support method comprising the implementation of the intervention measure for the user according to the level of the user's emotional intensity.

Images