JP2021026477A - Support device and support program - Google Patents

Abstract

To provide a technology that appropriately supports an action of a user.SOLUTION: A support device 50 comprises: a user information acquisition section 61 that continually acquires information sensed by a sensor which senses information indicating a state of a user; an action history acquisition section 64 that acquires an action history of the user; and an analyzing section 65 that analyzes influence given to the state of the user, in which state an action is represented by an index, from a correspondence relation between user's action content acquired by the action history acquisition section 64 and an index value based on information acquired by the user information acquisition section 61 before, during, or after performing the action.SELECTED DRAWING: Figure 2

Description

The present invention relates to user assistive technology, and more particularly to assistive devices and assistive programs that support user behavior.

Various services for managing the health condition of the user are provided (see, for example, Patent Document 1). The health information analyzer described in Patent Document 1 provides a plurality of analysis programs for analyzing health information related to the user's health and creating analysis result information showing the analysis results, and the creator of the analysis program. An analysis program acquisition means acquired together with the creator identification information for identification, a storage unit for storing the analysis program and the creator identification information associated with each other, an execution means for executing the analysis program, and the above. A selection information receiving means for receiving selection information from a user for selecting one of a plurality of analysis programs, and the above-mentioned analysis program created by executing the selected analysis program by the execution means based on the selection information. It is characterized by comprising a display control means for displaying the analysis result on the display unit based on the analysis result information. As a result, it is possible to create a plurality of analysis result information from the same health information and provide the user with the results of analyzing the health condition of the user from various aspects.

Japanese Unexamined Patent Publication No. 2011-258080

The present inventors have considered that by continuously collecting information on the user's condition while the user is living, it is possible to more appropriately support the healthy life of the user, and the present invention has been made. I came up with it.

The present invention has been made in view of such problems, and an object of the present invention is to provide a technique for appropriately supporting user behavior.

In order to solve the above problem, the support device of a certain aspect of the present invention acquires a user information acquisition unit that continuously acquires information detected by a sensor that detects information indicating a user's state, and a user's action history. The action history acquisition unit to be acquired, the content of the user's action acquired by the action history acquisition unit, and the value of the index based on the information acquired by the user information acquisition unit before, during, or after the execution of the action. It is provided with an analysis unit that analyzes the influence of the behavior on the user's condition represented by the index from the correspondence of the above.

Another aspect of the invention is a support program. This support program uses an information acquisition unit that continuously acquires information detected by a sensor that detects information indicating the user's status, an action history acquisition unit that acquires the user's action history, and an action history acquisition unit. It functions as a recording unit that records the correspondence between the acquired content of the user's action and the value of the index based on the information acquired by the information acquisition unit before, during, or after the execution of the action.

It should be noted that any combination of the above components and the conversion of the expression of the present invention between methods, devices, systems, recording media, computer programs and the like are also effective as aspects of the present invention.

According to the present invention, it is possible to provide a technique for appropriately supporting the behavior of a user.

It is a figure which shows the structure of the support system which concerns on embodiment. It is a figure which shows the structure of the support device which concerns on embodiment. It is a figure which shows the example of the time change of the index calculated by the index calculation part. It is a figure which shows the example of the analysis by the analysis department. It is a figure which shows another example of the analysis by the analysis department. It is a figure which shows still another example of analysis by an analysis part. It is a figure which shows still another example of analysis by an analysis part. It is a figure which shows still another example of analysis by an analysis part.

The support system according to the embodiment continuously detects and accumulates information indicating the user's condition during the user's life in order to support the healthy life of the user, and is based on the accumulated information. From the correspondence between the index value calculated in the above and the user's behavior history, the influence of the user's behavior on the user's condition is analyzed. As a result, it is possible to recommend to the user the content and timing of actions that can maintain or improve the user's condition, and to present to the user actions that may worsen the user's condition. It is possible to provide the user with an action guideline for the user to live a healthy life.

Further, the support system according to the embodiment machine-learns an algorithm for calculating an index and an algorithm for determining the content of a recommended action based on the user's action record. As a result, the algorithm can be customized according to the user, so that the user's behavior can be supported more appropriately.

The accumulated information indicating the user's condition and the user's behavior history are the service providers who provide the service to the user, the products, devices, equipment used by the user, and the food ingested by the user. , Supplements, pharmaceuticals, etc. may be provided to entities that develop, manufacture, and sell. As a result, the service provider can provide a service that can maintain or improve the health of the user according to the state and behavior history of each user, so that both the service provider and the user can use it. A useful support system can be realized. In addition, since it is possible to develop, manufacture, sell, and provide products and services that can maintain or improve the health of users by analyzing the state and behavior history of a large number of users, service providers and products. It is possible to realize a support system that is beneficial to both the entity that develops, manufactures, and sells such products as well as the user. Further, the management entity of the support system charges the provider for the provision of such information, so that a business model that is useful for the management entity of the support system can be constructed.

FIG. 1 shows the configuration of the support system according to the embodiment. The support system 1 includes a sensor that detects information indicating the state of the user 20 and information indicating the state of the environment around the user, and a support device 50 that supports the behavior of the user 20. The information indicating the state of the user 20 may be detected by a wearable sensor 39 that the user 20 can wear on the body, or is detected by a sensor installed in the house 2 which is an example of the living space in which the user 20 lives. Alternatively, it may be detected by a sensor installed in a facility or space where the user 20 executes an action such as work or exercise. Information indicating the state of the environment around the user may also be detected by a wearable sensor 39, a sensor installed in a house 2, a facility, a space, or the like.

The house 2 has a plurality of indoor areas such as an entrance 3, a Western-style room 4, a living room (LDK) 5, a Japanese-style room 6, a bedroom 7, a toilet 8, a bathroom 9, and a washroom 10, and a plurality of outdoor areas such as a parking space 16. And include. In the house 2, as an example of a sensor that detects information indicating the state of the user 20 living in the house 2, an image sensor 30, a load sensor 31, a thermo camera 32, an electrode 33, an odor sensor 34, a piezoelectric sensor 35, and a hyper A spectrum camera 36, a sound sensor (microphone) 37, and the like are installed. These sensors are installed in building materials, furniture, equipment, equipment, etc. installed in the house 2 and automatically and continuously detect information indicating the state of the user 20.

The height, body shape, facial expression, complexion, skin color, sweating amount, etc. of the user 20 are detected by an image captured by an image sensor 30 installed in the bathroom 9 or the washroom 10. The weight, body fat mass, muscle mass, etc. of the user 20 are detected by a load sensor 31, a weight scale, a body composition meter, etc. installed in the bathroom 9, the washroom 10, the bed in the bedroom 7, and the like. The body temperature of the user 20 is detected by a thermo camera 32 or the like installed in the bathroom 9, the washroom 10, or the like. The electrocardiogram of the user 20 is detected by an electrode 33 or the like installed in a bathtub in the bathroom 9. The body odor, urine odor, stool odor, etc. of the user 20 are detected by an odor sensor 34 or the like installed in the toilet 8 or the like. The heartbeat of the user 20 is detected by a piezoelectric sensor 35 or a Doppler sensor installed in the toilet 8, the washroom 10, or the like. The urine component of the user 20 is detected by a hyperspectral camera 36 or the like installed in the toilet bowl of the toilet 8. The utterances and daily life sounds of the user 20 are detected by a sound sensor 37 or the like installed in the living room 5.

Information indicating environmental conditions such as ambient temperature, humidity, air volume, weather, weather, and brightness of the user 20 includes an image sensor 30, a thermo camera 32, a sound sensor 37, a brightness sensor 38, a hygrometer, and an air volume meter. May be detected by.

The information detected by these sensors is transmitted to the home server 41 by wireless communication. The home server 41 transmits the collected information to the support device 50 via the Internet 40.

Sensors are not limited to houses, but are used by people to live, stay, or stay in accommodation facilities, sites such as parking lots and gardens attached to houses and accommodation facilities, and facilities for infants and the elderly to stay. It may be installed in any living space including a building or a site. In addition, the sensor may be installed in a commercial facility, a public facility, an athletic facility, a medical facility, a stay facility, or the like used by the user. The information detected by these sensors may be transmitted to the support device 50 via a communication network such as the Internet 40, or may be transmitted to a mobile terminal or the like possessed by the user, and transmitted from the mobile terminal to the support device 50. You may. As a result, even when the user is in a facility or space other than the house 2, information indicating the state of the user and information indicating the state of the environment around the user can be automatically and continuously acquired and accumulated. ..

The wearable sensor 39 that can be worn on the user's body may be a heart rate monitor, a blood pressure monitor, a thermometer, a pedometer, a blood oxygen concentration meter, or the like. The information detected by these sensors may be transmitted to the support device 50 via a communication network such as the Internet 40, or may be transmitted to a mobile terminal or the like owned by the user, and transmitted from the mobile terminal to the support device 50. Alternatively, it may be recorded in a memory mounted on the sensor or the like and transmitted to the home server 41 when the user returns home. As a result, no matter where or what the user is doing, information indicating the user's status can be constantly and continuously acquired and accumulated. In addition, information indicating the user's state can be detected and accumulated more accurately.

FIG. 2 shows the configuration of the support device according to the embodiment. The support device 50 includes a communication device 51, a display device 52, an input device 53, a speaker 54, a control device 60, and a storage device 70. The support device 50 may be a server device, a device such as a personal computer, or a mobile terminal such as a mobile phone terminal, a smartphone, or a tablet terminal.

The communication device 51 controls communication with other devices via a communication network such as the Internet 40. The communication device 51 may perform communication by any wired or wireless communication method. The display device 52 displays the screen generated by the control device 60. The display device 52 may be a liquid crystal display device, an organic EL display device, or the like. The input device 53 transmits an instruction input by the user or the manager of the support device 50 to the control device 60. The input device 53 may be a mouse, a keyboard, a touch pad, or the like. The display device 52 and the input device 53 may be mounted as a touch panel. The speaker 54 outputs the sound generated by the control device 60. The input device 53 may be a microphone or the like for inputting voice, and the voice may be converted into text information by voice recognition technology and input.

The storage device 70 stores programs, data, and the like used by the control device 60. The storage device 70 may be a semiconductor memory, a hard disk, or the like. The storage device 70 includes a user database 71, a device information holding unit 72, an index calculation algorithm 73, a device control algorithm 74, an action recommendation algorithm 75, and a history information holding unit 76.

The user database 71 stores information on users who are the targets of support by the support device 50. The user database 71 contains, for example, attribute information such as the user's gender, age, blood type, occupation, biological information such as height, weight, and health condition, medical information such as medical history and health examination results, hobbies, and likes. Stores preference information such as food and drink.

The device information holding unit 72 stores information on devices used by the user during the user's actions and devices for controlling the environment around the user. The device information holding unit 72 stores the type, performance, setting parameters, etc. of each device. The device information holding unit 72 stores the value of the setting parameter set in each device during the user's action, and when the support device 50 changes the value of the setting parameter, the stored setting parameter value Update the value.

The index calculation algorithm 73 is an algorithm for calculating the value of the index based on the detection information indicating the state of the user. The index calculation algorithm 73 calculates an index that quantifies the physical or mental state of the user, which may affect the quality of life of the user, such as the degree of fatigue, recovery, activity, beauty, and mental state of the user. To do. The index calculation algorithm 73 may be a mathematical formula for calculating an index by using detection information indicating the user's state or environment information indicating the state of the environment around the user as variables, or detection information indicating the user's state or It may be a neural network or the like in which information indicating the environmental state of the environment around the user is input to the input layer and the index value is output from the output layer. The index calculation algorithm 73 may be a neural network or the like that outputs the values of a plurality of types of indexes from the output layer. Further, a plurality of index calculation algorithms 73 that output the values of a plurality of types of indexes may be provided.

The device control algorithm 74 is an algorithm for automatically controlling a device for controlling the environment around the user. The device control algorithm 74 inputs detection information, environmental information, indicators, user action history, etc. acquired during the user's action, and outputs the control content of the device. The device control algorithm 74 may be a neural network or the like that inputs these information to the input layer and outputs the control contents of the device from the output layer, or when the conditions related to the information and the conditions are satisfied. It may be a rule-based algorithm that associates with the control content of the device. The device control algorithm 74 may be provided for each attribute such as the age, gender, and occupation of the user, or may be provided for each user.

The action recommendation algorithm 75 is an algorithm for recommending the content of the action to be executed by the user based on the analysis result of the correlation between the index and the action. The action recommendation algorithm 75 inputs detection information, environmental information, indicators, user action history, and the like, and outputs the content of the recommended action. The action recommendation algorithm 75 may be a neural network or the like that inputs these information to the input layer and outputs the content of the recommended action from the output layer, and the conditions related to these information and the conditions are satisfied. It may be a rule-based algorithm that associates with the content of the action recommended at the time. The action recommendation algorithm 75 may be provided for each attribute such as the age, gender, and occupation of the user, or may be provided for each user.

The history information holding unit 76 includes detection information indicating the user's state, environmental information indicating the state of the environment around the user, an index value calculated based on the detection information, a user's behavior history, and a correlation between the index and the behavior. It stores historical information such as analysis results such as, the content of the action recommended by the user, and whether or not the user has executed the recommended action.

The control device 60 includes a user information acquisition unit 61, an environment information acquisition unit 62, an index calculation unit 63, an action history acquisition unit 64, an analysis unit 65, an action recommendation unit 66, a device control unit 67, an information presentation unit 68, and an information transmission unit. It includes 69 and a learning unit 80. These configurations are realized by the CPU, memory, other LSI, etc. of any computer in terms of hardware, and are realized by programs loaded in memory in terms of software, but here, their cooperation is realized. It depicts a functional block realized by. Therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various forms such as hardware alone or a combination of hardware and software.

The user information acquisition unit 61 continuously acquires the detection information indicating the state of the user and records it in the history information holding unit 76. The user information acquisition unit 61 may acquire the detection information from the home server 41 or the user's mobile terminal, or may directly acquire the detection information from each sensor.

The environment information acquisition unit 62 acquires environment information indicating the state of the environment around the user, and records it in the history information holding unit 76 in association with the detection information indicating the state of the user. The environment information acquisition unit 62 may acquire the environment information from the home server 41 or the user's mobile terminal, or may acquire the environment information directly from each sensor.

The index calculation unit 63 uses the index calculation algorithm 73 to calculate an index from the detection information indicating the user's state at a predetermined timing, for example, at a predetermined time interval. The index calculation unit 63 may select the type of index to be calculated according to the user's goal, purpose, or the like, and calculate the index using the index calculation algorithm 73 for calculating the selected index. The index calculation unit 63 may calculate a plurality of indexes in order to represent the state of the user from various viewpoints.

The action history acquisition unit 64 acquires the user's action history. The action history acquisition unit 64 may acquire the content of the action input by the user, or may acquire the content of the user's action from another device or application that provides a service related to the user's action. The user's behavior may be acquired by analyzing the detection information acquired by the user information acquisition unit 61. For example, the action history acquisition unit 64 may acquire the contents of the user's diet and exercise from an application for managing the user's diet and exercise. In addition, the behavior history acquisition unit 64 acquires the user's behavior in a space such as a house 2 or a facility by analyzing information such as an image captured by the image sensor 30 and a sound detected by the sound sensor 37. You may.

The analysis unit 65 is an index calculation unit 63 based on the content of the user's action acquired by the action history acquisition unit 64 and the information acquired by the user information acquisition unit 61 before, during, or after the execution of the action. From the correspondence with the value of the index calculated by, the influence of the behavior on the state of the user represented by the index is analyzed. The analysis unit 65 may analyze the correspondence between the content of the action and the amount or rate of change of the index due to the execution of the action. For example, when the fatigue degree indicating the degree of fatigue of the user is calculated as an index, the analysis unit 65 may analyze how the fatigue degree changes depending on actions such as work, exercise, and sleep. The analysis unit 65 determines the correspondence between the content of the action, the timing at which the action is executed, the value of the index when the action is executed, the attribute or state of the user, and the amount or rate of change of the index. You may analyze it. For example, the analysis unit 65 may determine the difference in the degree of fatigue depending on the timing of sleep, the difference in the degree of fatigue between when exercising when the degree of fatigue is high and when exercising when the degree of fatigue is low, and The correlation between the change in the degree of fatigue due to sleep and the weight of the user may be analyzed. The analysis unit 65 may analyze the correspondence between the content of the action, the content or timing of another action executed before or after the action, and the amount or rate of change of the index. For example, the analysis unit 65 may analyze the difference in the degree of fatigue between the case of exercising after work and the case of sleeping after work. The analysis unit 65 may analyze the correspondence between the content of the action, the environment around the user when the action is executed, and the amount or rate of change of the index. For example, the analysis unit 65 may analyze the difference in the degree of fatigue between the case of sleeping in a bright place and the case of sleeping in a dark place.

The action recommendation unit 66 recommends the content or timing of the action that can maintain or improve the index based on the result analyzed by the analysis unit 65. The action recommendation unit 66 inputs detection information, environmental information, indicators, user action history, and the like into the action recommendation algorithm 75, and obtains an output of the content of the recommended action. The action recommendation unit 66 may display the content of the recommended action on the display device 52, or may output the content of the recommended action from the speaker 54. The action recommendation unit 66 may determine the recommended action based on the content or timing of the action executed by the user in the past and the amount or rate of change of the index due to the execution of the action. May recommend the content or timing of actions that have not been performed in the past. In the latter case, the action recommendation unit 66 may recommend the content or timing of the action that is presumed to be able to maintain or improve the index based on the past performance of the user's action. The action recommendation unit 66 includes sleep timing, time, environment, wake-up timing, method, environment, meal timing, amount, menu, environment, intake timing of supplements and medicines, type, amount, bath timing, etc. Time, environment, timing of exercise, time, type, method, environment, timing of entertainment, time, type, environment, work environment, time, etc. may be recommended.

The device control unit 67 controls the device so as to provide an environment suitable for the action being executed or scheduled to be executed based on the result analyzed by the analysis unit 65. The device control unit 67 inputs detection information, environmental information, indicators, user action history, and the like into the device control algorithm 74, and obtains an output of the control contents of the device. The device control unit 67 refers to the information held in the device information holding unit 72, and transmits a control signal for realizing the obtained control content to the device.

The information presentation unit 68 presents the result analyzed by the analysis unit 65. The information presentation unit 68 presents the content or timing of an action that may deteriorate the index calculated by the index calculation unit 63, the transition of the index calculated by the index calculation unit 63, and the like.

The information transmission unit 69 includes detection information that indicates the user's state, environmental information that indicates the state of the environment around the user, index values calculated based on the detection information, and user's information that is held in the history information storage unit 76. The behavior history, analysis results such as the correlation between the index and the behavior, the content of the behavior recommended by the user, and the history information such as whether or not the user has executed the recommended behavior are transmitted to the information provider. The information transmission unit 69 is a service provider of medical facilities, exercise facilities, commercial facilities, public facilities, accommodation facilities, etc., an entity that develops, manufactures, and sells products, foods, pharmaceuticals, equipment, equipment, furniture, and users. You may send the history information to your family, work place, etc. The information transmitting unit 69 may charge the information providing destination a consideration according to the type, amount, timing, and the like of the information transmitted to the information providing destination.

The learning unit 80 uses the history information held in the history information holding unit 76 as learning data, and learns the index calculation algorithm 73, the device control algorithm 74, and the action recommendation algorithm 75. For example, the learning unit 80 acquires an evaluation result from the user as to whether or not the value of the index calculated by the index calculation algorithm 73 accurately represents the state of the user, and according to the evaluation result, the intermediate layer of the neural network. The index calculation algorithm 73 may be learned by adjusting the weight, the coefficient of the mathematical formula, and the like. The learning unit 80 determines the control content based on the amount of change or rate of change of the index after the device is controlled according to the output of the device control algorithm 74, the amount of change or rate of change of information indicating the user's state, and the like. The device control algorithm 74 may be learned by determining the quality and adjusting the weight of the intermediate layer of the neural network according to the determination result. The learning unit 80 recommends an action based on the amount of change or rate of change of the index after recommending the action to the user according to the output by the action recommendation algorithm 75, the amount of change or rate of change of the information indicating the user's state, and the like. The action recommendation algorithm 75 may be learned by determining the quality of the behavior and adjusting the weight of the intermediate layer of the neural network according to the determination result. The learning unit 80 may further acquire information indicating whether or not the user actually executed the recommended action and use it for learning the action recommendation algorithm 75. The learning unit 80 may learn the index calculation algorithm 73, the device control algorithm 74, and the action recommendation algorithm 75 for each user. As a result, the result of actually applying the index calculation algorithm 73, the device control algorithm 74, and the action recommendation algorithm 75 to the user can be fed back to the algorithm and customized according to the user, so that the user can be supported more accurately. be able to.

FIG. 3 shows an example of the time change of the index calculated by the index calculation unit. In the example of this figure, the index calculation unit 63 calculates the degree of fatigue of the user as an index based on the information indicating the state of the user acquired by the user information acquisition unit 61. The degree of fatigue of the user goes up and down depending on the behavior of the user. In the example of FIG. 3, after the user wakes up, the degree of fatigue increases due to actions such as commuting, work, eating, bathing, and watching TV, and the degree of fatigue decreases due to sleep.

FIG. 4 shows an example of analysis by the analysis unit 65. In the example shown in FIG. 3, the analysis unit 65 estimates the accumulated amount of fatigue of the user by calculating the difference in the degree of fatigue at the same time on different days. In the example of this figure, the degree of fatigue at 6:00 am is Δa higher than that of the previous day. That is, it can be seen that the degree of fatigue increased by the user's behavior on this day does not recover to the same level as the previous day even by sleep, and the fatigue is accumulated more than the previous day. In this case, the action recommendation unit 66 uses, for example, as an action after the user wakes up the next morning, ingests a supplement or a drug for recovering from fatigue, or uses a coating agent or a patch for recovering from fatigue. Actions such as doing may be recommended to the user. In addition, the action recommendation unit 66 takes actions before the user goes to bed the next day, such as going to bed earlier than the previous day in order to take a longer sleep time, performing a light exercise before sleeping in order to improve the quality of sleep, and the like. Actions may be recommended to the user. In order to improve the quality of sleep, the device control unit 67 may output background music, a scent, or the like that has the effect of promoting sleep onset, or may control the temperature, humidity, brightness, and the like during sleep.

FIG. 5 shows another example of analysis by the analysis unit 65. In the example shown in FIG. 3, the analysis unit 65 calculates the amount of change in the degree of fatigue for each action. For example, it can be seen that the increase in fatigue due to commuting was Δb. The analysis unit 65 can accurately grasp the content of the behavior in which the amount of change in the degree of fatigue is large by statistically analyzing the type and content of the behavior and the correlation between the time and the amount of change in the degree of fatigue. As a result, the action recommendation unit 66 recommends to the user an action having a large recovery effect on the fatigue level, or predicts the transition of the fatigue level in advance from the user's action schedule and recommends an appropriate recovery action. Can be done. In addition, by presenting the analysis result by the information presenting unit 68, the user grasps the behavior that is the main cause of his / her fatigue and the behavior that is effective for recovering from the fatigue, and takes an appropriate action. You can select the type, content, and time of.

FIG. 6 shows yet another example of analysis by the analysis unit 65. In the example shown in FIG. 3, the analysis unit 65 calculates the rate of change in the degree of fatigue for each action. For example, the rate of change in the degree of fatigue due to commuting is θa, and the rate of change in the degree of fatigue due to PC work is θb, indicating that the rate of change in the degree of fatigue was greater in commuting. By statistically analyzing the type and content of the behavior and the correlation between the content and the rate of change in the degree of fatigue, the analysis unit 65 can accurately grasp the content of the behavior having a large rate of change in the degree of fatigue. As a result, the action recommendation unit 66 can recommend to reduce the duration or encourage a break when the user is executing an action having a high rate of increase in the degree of fatigue. In addition, the action recommendation unit 66 recommends an action with a high rate of decrease in the degree of fatigue, or an action with a large amount of decrease in the degree of fatigue, depending on the degree of fatigue of the user and the time during which the action can be executed. can do.

FIG. 7 shows yet another example of analysis by the analysis unit 65. The upper part of FIG. 7 shows the time change of the degree of fatigue when the user takes a bath. This is the same as the time change of the degree of fatigue shown in FIG. The lower part of FIG. 7 shows an example of the time change of the degree of fatigue when the user does not take a bath. The behavior other than bathing is the same as the example shown in the upper part of FIG. Comparing the rate of change in fatigue due to sleep on the day of bathing θc and the rate of change in fatigue due to sleep on the day without bathing θd, those who slept after taking a bath did not take a bath. It can be seen that the rate of decrease in the degree of fatigue is higher than when sleeping in the bath. Comparing the accumulated amount of fatigue Δa from the day before the day of bathing and the accumulated amount of fatigue Δc from the day before the day of not taking a bath, it is better to sleep after taking a bath. It can be seen that the amount of accumulated fatigue is smaller than when sleeping without taking a bath. Therefore, it can be inferred that this user recovers from sleep fatigue faster when taking a bath. In this way, the analysis unit 65 may analyze the correlation between the combination, order, interval, timing, etc. of two or more actions and the amount of change or the rate of change in the degree of fatigue. As a result, the action recommendation unit 66 can recommend a combination, order, interval, timing, and the like of two or more actions that can maintain or improve the degree of fatigue.

FIG. 8 shows yet another example of analysis by the analysis unit 65. The upper part of FIG. 8 shows the time change of the daily fatigue degree of the user when the body fat percentage of the user is 20%. The lower part of FIG. 8 shows the time change of the user's fatigue degree when the user's body fat percentage was 25%. The user's behavior history is the same. Comparing the time change of the fatigue degree shown in the upper part of FIG. 8 with the time change of the fatigue degree shown in the lower part of FIG. 8, the body fat percentage is 25% when the body fat percentage is 20%. It can be seen that the recovery of the fatigue level due to sleep is faster and the accumulated amount of fatigue level from the previous day is smaller than that in the case of. Therefore, it can be inferred that this user can recover from fatigue faster and lead a healthy life when the body fat percentage is 20% than when the body fat percentage is 25%. In this way, the analysis unit 65 may analyze the correlation between the content of the action, the state or attribute of the user, and the amount of change or the rate of change of the index. As a result, it is possible to accurately grasp the state of the user who can satisfactorily maintain or improve the amount of change or the rate of change of the index due to the behavior, present it to the user, and recommend an appropriate behavior.

In the present embodiment, an example of providing the support device 50 that comprehensively supports a plurality of users has been described, but the support device 50 may be provided for each user. In this case, for example, the user's mobile terminal or home server 41 may have the function of the support device 50. The functions may be shared between the home server 41 and the support device 50. The home server 41 may not be provided.

Generalization of the invention embodied by the above embodiments and modifications leads to the following technical ideas.

One aspect of the present invention is a support device. This support device is composed of a user information acquisition unit that continuously acquires information detected by a sensor that detects information indicating the user's state, an action history acquisition unit that acquires the user's action history, and an action history acquisition unit. The behavior is represented by the index from the correspondence between the acquired content of the user's behavior and the value of the index based on the information acquired by the user information acquisition unit before, during, or after the execution of the behavior. It includes an analysis unit that analyzes the effect on the user's condition. According to this aspect, the user's behavior can be appropriately supported, so that the user's convenience can be improved.

The analysis unit may analyze the correspondence between the content of the action and the amount or rate of change of the index due to the execution of the action. According to this aspect, it is possible to accurately grasp the content of the action that can maintain or improve the user's condition satisfactorily.

The analysis unit analyzes the correspondence between the content of the action, the timing when the action is executed, the value of the index when the action is executed, the attribute or state of the user, and the amount or rate of change of the index. You may. According to this aspect, it is possible to accurately grasp the timing of actions and the attributes of the user who can maintain or improve the state of the user.

The analysis unit may analyze the correspondence between the content of the action, the content or timing of another action executed before or after the action, and the amount or rate of change of the index. According to this aspect, it is possible to accurately grasp the combination of actions that can maintain or improve the user's condition satisfactorily.

The support device further includes an environment information acquisition unit that acquires information about the user's surrounding environment, and the analysis unit includes the content of the action, the environment around the user when the action is executed, and the amount of change in the index. Alternatively, the correspondence with the rate of change may be analyzed. According to this aspect, it is possible to accurately grasp the environment suitable for the behavior that can maintain or improve the user's condition satisfactorily.

The support device may further include an action recommendation unit that recommends the content or timing of the action that can maintain or improve the index based on the result analyzed by the analysis unit and the value of the index. According to this aspect, since the user's behavior can be appropriately supported, the user's convenience can be further improved.

The support device may further include a presentation unit that presents the content or timing of actions that may aggravate the index based on the results analyzed by the analysis unit. According to this aspect, since the user's behavior can be appropriately supported, the user's convenience can be further improved.

Another aspect of the invention is a support program. This support program uses an information acquisition unit that continuously acquires information detected by a sensor that detects information indicating the user's status, an action history acquisition unit that acquires the user's action history, and an action history acquisition unit. It functions as a recording unit that records the correspondence between the acquired content of the user's action and the value of the index based on the information acquired by the information acquisition unit before, during, or after the execution of the action. According to this aspect, the user's behavior can be appropriately supported, so that the user's convenience can be improved.

1 Assist system, 2 Residential, 20 users, 30 image sensor, 31 load sensor, 32 thermo camera, 33 electrodes, 34 odor sensor, 35 piezoelectric sensor, 36 hyperspectral camera, 37 sound sensor, 38 brightness sensor, 39 wearable sensor , 40 Internet, 41 Home server, 50 Support device, 60 Control device, 61 User information acquisition unit, 62 Environmental information acquisition unit, 63 Index calculation unit, 64 Action history acquisition unit, 65 Analysis unit, 66 Action recommendation unit, 67 Equipment Control unit, 68 information presentation unit, 69 information transmission unit, 70 storage device, 71 user database, 72 device information holding unit, 73 index calculation algorithm, 74 device control algorithm, 75 action recommendation algorithm, 76 history information holding unit, 80 learning Department.

Claims (8)

A user information acquisition unit that continuously acquires information detected by a sensor that detects information indicating the user's status,
The behavior history acquisition unit that acquires the behavior history of the user, and
From the correspondence between the content of the user's action acquired by the action history acquisition unit and the value of the index based on the information acquired by the user information acquisition unit before, during, or after the execution of the action. An analysis unit that analyzes the effect of the behavior on the user's condition represented by the index, and
A support device equipped with. The support device according to claim 1, wherein the analysis unit analyzes the correspondence between the content of the action and the amount or rate of change of the index due to the execution of the action. The analysis unit includes the content of the action, the timing at which the action is executed, the value of the index when the action is executed, the attribute or state of the user, and the amount or rate of change of the index. The support device according to claim 1 or 2, which analyzes the correspondence between the two. The analysis unit analyzes the correspondence between the content of the action, the content or timing of another action executed before or after the action, and the amount or rate of change of the index according to claims 1 to 3. The support device described in either. It also has an environment information acquisition unit that acquires information about the environment around the user.
The analysis unit is any one of claims 1 to 4 that analyzes the correspondence between the content of the action, the environment around the user when the action is executed, and the amount of change or the rate of change of the index. The support device described in. Any of claims 1 to 5, further comprising an action recommendation unit that recommends the content or timing of an action capable of maintaining or improving the index based on the result analyzed by the analysis unit and the value of the index. The support device described in. The support device according to any one of claims 1 to 6, further comprising a presenting unit that presents the content or timing of an action that may aggravate the index based on the result analyzed by the analysis unit. Computer,
Information acquisition unit that continuously acquires information detected by a sensor that detects information indicating the user's status,
Behavior history acquisition unit that acquires the behavior history of the user,
Record the correspondence between the content of the user's action acquired by the action history acquisition unit and the value of the index based on the information acquired by the information acquisition unit before, during, or after the execution of the action. Recording part,
A support program to function as.

Images