JP2023001477A - Activity amount calculation device and activity amount calculation method - Google Patents

Abstract

To calculate an activity amount based on an actual condition of an analysis object.SOLUTION: In order to solve an above-mentioned problem, an active amount calculation device 1 of the present invention calculates an activity amount of an analysis object, and has: an information acquisition unit 11 that acquires a result of measurement of the activity of the analysis object from a sensor 21; and an operation unit 12 that calculates first speed information and second speed information on the analysis object on the basis of, the measurement result, and calculates the activity amount of the analysis object by using the first speed information and the second speed information. In the activity amount calculation device 1, the operation unit 12 calculates at least one of the first speed information and the second speed information by using positional information on point group information that is included in the measurement result and indicates the analysis object.SELECTED DRAWING: Figure 1

Description

The present invention relates to a technique for calculating the amount of activity of an action subject such as a human. Among these, the present invention particularly relates to a technique for calculating the amount of activity based on human activities, actions, and movements (hereinafter referred to as activities) measured by a sensor or the like.

In recent years, communication technology and sensor technology have advanced, and it has become possible to measure human activities in daily life for the purpose of health management. As a background art in this technical field, there is Patent Document 1. In Patent Document 1, "estimating apparatus for estimating at least one of exercise intensity and activity amount by estimating at least one of exercise intensity and activity amount of a pedestrian using a pedestrian distance image obtained from a distance image It is possible to estimate the effect of exercise on pedestrians walking in buildings without attaching a

JP 2018-99267 A

In Patent Literature 1, at least one of a pedestrian's exercise intensity and activity amount can be estimated using a pedestrian distance image obtained from a distance image. Therefore, according to Patent Document 1, it is possible to grasp an individual's amount of exercise and the like without using a wearable device that may be forgotten to be worn or run out of battery, leading to health management.

However, Patent Literature 1 focuses on the problem of forgetting to wear the sensor, and does not consider the accuracy of grasping the amount of exercise or the like. Human activity is complicated, and it was difficult to calculate the amount of activity in accordance with the actual situation by a single measurement with an image as in Patent Document 1.

In order to solve the above problems, in the present invention, a plurality of pieces of speed information are used to calculate the amount of activity of a person to be analyzed who is an activity subject. Then, at least one of the plurality of speed information is calculated based on the position information of the person to be analyzed. Note that it is desirable to use local speed information indicating the local characteristics of the activity of the person to be analyzed and overall speed information indicating the overall characteristics of the activity of the person to be analyzed as the plurality of pieces of speed information.

As a more specific configuration, for example, a configuration described in the claims below is adopted. In an activity amount calculation device for calculating an activity amount of an analysis subject, an information acquisition unit that acquires a measurement result of the activity of the analysis subject; a calculation unit that calculates two pieces of speed information and calculates the amount of activity of the person to be analyzed using the first speed information and the second speed information, and the calculation unit calculates the first speed information In the active mass calculation device, at least one of the speed information and the second speed information is calculated using the position information of the point cloud information that is included in the measurement result and indicates the person to be analyzed.

The present invention also includes an activity amount calculation method using an activity amount calculation device and an activity amount calculation system having the method. Furthermore, the present invention also includes an activity amount calculation program that causes the activity amount calculation device to function as a computer.

According to the present invention, it is possible to calculate a more realistic amount of activity with respect to the activity of the person to be analyzed, and to ensure the accuracy thereof, thereby enabling more appropriate health management.
Problems, configurations, and effects other than those described above will be clarified by the following description of the embodiments.

1 is a block diagram showing the configuration of an active mass calculation system in Example 1. FIG. 4 is a flowchart for explaining processing of the active mass calculation device in Example 1. FIG. FIG. 11 is a block diagram showing the configuration of an active mass calculation system in Example 2; FIG. 11 is a block diagram showing the configuration of an active mass calculation system in Example 3; FIG. 11 is a first example of a display unit of an external terminal in Example 3. FIG. FIG. 13 is a second example of the display unit of the external terminal in Example 3. FIG. 13 is an example of a display unit for feedback of an external terminal in Example 3. FIG. 4A and 4B are diagrams showing display contents in the first embodiment; FIG. It is a block diagram which shows implementation of the active mass calculation system in Examples 2 and 3. FIG.

Hereinafter, each embodiment of the present invention will be described in detail with reference to the drawings, but the present invention is not limited to the following embodiments, and various modifications and applications within the technical concept of the present invention. Also included in the scope.

FIG. 1 is a block diagram showing the configuration of the activity amount calculation system according to the first embodiment. Example 1 is an example having a basic configuration compared to other examples. The active mass calculation system is composed of an active mass calculation device 1 and a sensor 21 .

The active mass calculation device 1 is composed of an information acquisition unit 11 , a calculation unit 12 , an accumulation unit 13 and a display unit 14 . These will be described after sensor 21 .

The sensor 21 has a function of measuring the activity of the person to be analyzed and outputting the measurement result. As an example of measurement, the sensor 21 perceives the person to be analyzed as a set of at least two points. That is, the sensor 21 measures a point group composed of a plurality of points for the person to be analyzed, and obtains point group information including position information of each point. A typical example of this is the radio wave sensor 22 . The radio wave sensor 22 is defined herein as a generic term for sensors that detect the presence and movement of objects using radio waves, such as microwave sensors, millimeter wave sensors, and TOF sensors. By using the radio wave sensor 22, the person to be analyzed can be measured as a point group in a non-contact or non-wearing manner. In this point group, each point has coordinate information, which is a type of position information, and as the frequency of the radio wave sensor 22 increases, the number of points constituting the point increases and the spatial resolution can be improved. Moreover, since the radio wave sensor 22 does not infringe on privacy, it can be installed in a space where people live, such as inside a house or a facility. It should be noted that the installation locations of various sensors are not limited to these, and may include the garden of one's home, an out-of-town location, and the like. Furthermore, by not wearing the sensor 21, various measurements can be performed without having to wear it. In other words, it is possible to prevent forgetting to wear it. Furthermore, by using a sensor that can be measured without being worn, it is possible to reduce the subject's awareness of measurement, making it possible to measure more natural activities. In other words, it is possible to calculate the amount of activity that is more realistic.

Alternatively, an image sensor 23 may be used as the sensor 21 . The image sensor 23 can measure and record the person to be analyzed as a still image or moving image using a camera. Since these images are collections of pixels, each pixel that captures the person to be analyzed corresponds to the point cloud of the radio wave sensor 22, and likewise the point cloud information can include coordinate information.

Also, by utilizing the techniques disclosed in the following papers, etc., it is possible to estimate the three-dimensional shape of the invisible portion of the two-dimensional image that can be acquired by the image sensor 23 .
SM Ali Eslami et al., “Neural scene representation and rendering”, Science 15 Jun 2018: Vol. 360, Issue 6394, pp. 1204-1210
Then, the estimated three-dimensional shape may also be used to estimate the three-dimensional distribution shape of the point group.

Note that the sensor 21 may output not only the point group information but also the movement speed of each point of the point group and the center of gravity calculated by a calculation device mounted inside the sensor 21 . Furthermore, the point group information may be the result itself measured by the sensor 21, or may be created by the sensor 21 or the active mass calculation device 1 using the measurement result.

Next, the active mass calculation device 1 will be described. The active mass calculation device 1 is implemented by a so-called computer, and has an information acquisition unit 11 , a calculation unit 12 , an accumulation unit 13 and a display unit 14 . Each of these configurations will be described below.

First, the information acquisition unit 11 has an interface function and receives input of various information and data. Therefore, for example, it has a communication function with other devices such as the sensor 21 and an input function from the user. As an example of this, the point cloud information of the sensor 21 and the body information of the person to be analyzed (hereinafter referred to as body information 41) are acquired. The physical information 41 includes, for example, height, weight, date of birth, BMI, body fat percentage, visceral fat level, muscle mass, body water percentage, body age, and the like. Furthermore, the physical information 41 may include information indicating the presence or absence of equipment (for example, equipment for the elderly) related to activities, shoes, clothes, and other conditions related to activities.

Note that the information acquisition unit 11 may be implemented as a plurality of components. For example, it can be realized by a plurality of components such as an input device used by the user and an interface having a communication function. Here, as a method for the information acquisition unit 11 to acquire the point group information of the sensor 21, for example, there is a method of directly connecting to the sensor 21 via Ethernet, wireless communication, or the like. As another example, when sensor data is collected in a locally installed PC via a gateway, the information acquisition unit 11 acquires sensor data by accessing the PC via a local network or the Internet. As still another example, when sensor data is collected in a server directly or via a gateway, the information acquisition unit 11 acquires sensor data by accessing the server via the Internet. Alternatively, the sensor data may be stored in a server of an external company and the data may be received in a file format such as csv. good.

As for the method by which the information acquisition unit 11 acquires the physical information 41, the information input by the system administrator, who is the user, is input by referring to the application documents that the person to be analyzed describes when applying for the service. are accumulated in the accumulation unit 13 and referred to.

Furthermore, the information acquisition unit 11 may acquire information other than the point cloud information from the sensor 21 . For example, presence/absence information estimated based on point cloud information, information on falls estimated from the posture of the subject of analysis estimated from the spread of the point cloud in the height direction, and sudden changes in that posture, point The respiration rate, heart rate, etc. of the subject to be analyzed, which are estimated from minute fluctuations in the group, may be acquired.

Next, the calculation unit 12 uses the information acquired by the information acquisition unit 11 to calculate the amount of activity. Therefore, the calculation unit 12 can be realized by a processor such as a CPU, and executes the calculation described later according to the activity amount calculation program stored in the accumulation unit 13 . Moreover, the calculation unit 12 may be realized by dedicated hardware or an FPGA (Field-Programmable Gate Array). An example of calculation by the calculation unit 12 will be described below. Note that the activity amount calculation program can be stored in a storage medium, and may be distributed to the activity amount calculation device 1 via a network.

The calculation unit 12 calculates the amount of activity using a plurality of pieces of speed information, more preferably two types of speed information. For example, the calculation unit 12 calculates the amount of activity E having a unit of energy using two types of speed information and the body weight of the person to be analyzed, as shown in (Equation 1) below. In (Equation ₁ ), t1, t2, m, V1, and V2 are _respectively the time to start calculating the amount of activity, the time to finish calculating the amount of activity, the weight of the person to be analyzed, the first speed information, A second velocity information is shown.

As the first speed information in this embodiment, it is desirable to use speed information that indicates the local characteristics of the subject's activity. In this embodiment, for example, it is local velocity information, which is local velocity information of each of a plurality of points where the sensor 21 captures the person to be analyzed. When calculating the amount of activity E, it is more desirable to use the maximum value of the local velocity information at each point as a representative value. A specific example of the local velocity information may be the velocity of the extremities of the body such as limbs and head.

Note that the local velocity information can also be expressed as "the degree of vibration of the person to be analyzed". That is, the speed of the point moving fastest among the measured points may be used.

Moreover, it is desirable to use the overall speed information indicating the overall characteristics of the activity of the person to be analyzed as the second speed information. In this embodiment, the overall velocity information is, for example, velocity components in a plane perpendicular to the vertical direction of the velocities at the position of the center of gravity of a plurality of points where the sensor 21 captures the person to be analyzed. and so on. Another expression of the overall speed information is "the degree of movement of the person to be analyzed", which can be described as the moving speed in the plane (XY direction) if the vertical direction is the Z-axis direction.

It should be noted that the fact that there are two types of first speed information and second speed information has the advantage that the amount of activity of the person to be analyzed can be grasped from various angles. For example, when the person is not moving on the spot and is exercising, the local speed information may have a value greater than zero, but the overall movement speed information may be zero. If the activity amount E is evaluated only by the overall movement speed information, there is a concern that the activity amount may be underestimated and calculated for gymnastics that does not move from the spot. Similarly, there is a possibility that the person will walk indoors without vibrating their limbs excessively. In that case, there is a concern that the amount of activity E will be underestimated if it is calculated based only on the local velocity information.

Here, the definition of the amount of activity is not limited as long as it is an index that correlates with the degree of human activity (activity). For example, the minimum value, maximum value, average value, variance, standard deviation, etc. of the velocity of each point in the point group may be used, or the position of the center of gravity of the point group is calculated, and the minimum value and maximum value are calculated for that point. , average value, variance, standard deviation, etc. may be calculated and used as the amount of activity. Furthermore, the amount of activity may be calculated using these speeds and the physical information 41. For example, a value having a unit of the amount of exercise obtained by multiplying any one type of speed information of the person to be analyzed by the body weight. Also good.

Furthermore, V ₁ and V ₂ in (Equation 1) may be speed information calculated by different methods, such as averaging the time between times t1 and t2 at which the amount of activity is calculated. One may substitute for the other. Taking the time average value can reduce the influence of noise that enters the sensor for a short period of time. Also, depending on the specifications of the sensor, it may not be possible to calculate two types of speed information, and in such cases, it is effective to substitute one of them for the other. (Formula 1) has a unit of (J: joule) before dividing by 4.184, and becomes (cal) by dividing. Which of these units to use can be calculated according to the application.

Note that the amount of activity may be calculated for each part of the person to be analyzed. For this reason, the calculation unit 12 calculates the amount of activity using (Equation 2).

In (Equation 2), _mX0 indicates the mass (weight) of an arbitrary portion. V _X1 and V _X2 respectively indicate the first velocity information and the second velocity information at the corresponding site. Arms, legs, torso, etc. can be set as each part. As a result, it is possible to calculate the amount of activity that is more in line with the actual state of the activity. In addition, in order to specify the first speed information and the second speed information of each part, the calculation unit 12 performs machine learning on the measurement result (for example, image) by the sensor 21, and the planned point It is desirable to specify the site of The mass _mx0 of each part may be obtained by the information obtaining unit 11 as the physical information 41, or may be estimated from the standard mass balance of each part of the human body and the total weight.

Moreover, the calculating part 12 may calculate values other than the amount of activity. For example, the calculation unit 12 may calculate a value indicating the presence/absence estimated by utilizing the point cloud information or a value indicating the posture of the person to be analyzed estimated from the spread of the point cloud in the height direction. Furthermore, the calculation unit 12 may calculate information about a fall estimated from a sudden change in posture, and the respiration rate, heart rate, etc. of the person to be analyzed estimated from minute changes in the point cloud. Furthermore, the calculation unit 12 may estimate the physique of the person to be analyzed from the point cloud information, and estimate the weight based on average human data that associates the physique with the weight.

The storage unit 13 has a function of storing information. Therefore, the storage unit 13 can be realized by a storage such as a memory or a hard disk drive. In this embodiment, the accumulation unit 13 accumulates at least one of the information acquired by the information acquisition unit 11 and the amount of activity calculated by the calculation unit 12 . Moreover, when the calculating part 12 calculates according to an activity amount calculation program, the storage part 13 memorize|stores this activity amount calculation program. The acquired information and the calculated amount of activity are accumulated for each person to be analyzed. At this time, the accumulation unit 13 may accumulate the information and the amount of activity by tagging them with attributes such as the age, sex, origin, language, religion, tastes and preferences of the person to be analyzed. By using religion and origin as attributes, it is possible to consider customs that involve activities such as worship.

Further, the calculation unit 12 may perform time-series analysis on the accumulated information. Here, time-series analysis refers to visualization of various types of data using graphs with time on the horizontal axis, calculation of the rate of change in the time direction of data values, moving averages, variances, standard deviations, etc., and error analysis, polynomial It is defined as performing operations such as approximation. These time-series analyzes may include comparison with average values of persons belonging to the same category in terms of age, sex, origin, religion, lifestyle, occupation, medical history, and the like.

The display unit 14 displays information calculated by the calculation unit 12 and information of the storage unit 13 . The targets to be displayed are the administrator of the activity amount calculation device 1, the user of the system, the person to be analyzed, and the like. In addition, any format such as numbers, characters, tables, graphs, etc. can be used as the display method. Note that the display unit 14 may be realized by an independent terminal device such as a mobile terminal.

FIG. 2 is a flowchart for explaining the processing of the active mass calculation device 1 in this embodiment. The active mass calculation device 1 starts processing on condition that a system administrator or an operator who is a user of the system operates (step S1).

First, the information acquisition unit 11 acquires sensor data, which is the measurement result of the sensor 21, and physical information 41 (step S2). It should be noted that the sensor data and the physical information 41 do not have to be acquired at the same timing. For example, the physical information 41 is acquired in advance as preparation work, and the sensor data is acquired when the sensor 21 measures.

Next, the accumulation unit 13 accumulates the acquired sensor data and physical information 41 (step S3). Note that this step may be omitted, and the following processing may be performed on the sensor data and physical information 41 acquired in step S2.

Next, the calculation unit 12 calculates the amount of activity using the sensor data and the physical information 41 (step S4). This activity amount is calculated using (Equation 1) and (Equation 2) as described above.

Next, the calculation unit 12 outputs the calculated amount of activity. As a result, the display unit 14 displays the calculated amount of activity. Also, the accumulation unit 13 accumulates the amount of activity. (Step S5).

Further, the calculation unit 12 receives an instruction to calculate a time-series change from the user via the information acquisition unit 11 . Then, the calculation unit 12 reads the activity amount used for calculating the time-series change from the storage unit 13 (step S6). The amount of activity to be read is the amount of activity of the subject for the calculation of the time-series change. This amount of activity is not limited to the amount of activity of the person to be analyzed calculated in step S4, and can include the amount of activity of other persons. As a result, it is possible to compare the activity status for each person to be analyzed.

Further, the amount of activity to be read out is the amount of current activity calculated in step S4 and the amount of past activity accumulated in the past, in order to calculate the chronological change.

Next, the calculation unit 12 calculates a time-series change using the activity amount read in step S6. Calculation of the time-series change is as described above (step S7).

In step S7, the calculation unit 12 may calculate the amount of activity for each physical information 41, particularly for each activity condition. Moreover, the calculating part 12 may calculate the amount of activity for every content of activity. In this case, the calculation unit 12 identifies the content of the activity based on the first speed information, the second speed information, the designation from the user, the image processing of the sensor data, and the like. In this case, the accumulation unit 13 accumulates the contents and conditions of the activities of the person to be analyzed and others for each time period.

Next, the display unit 14 displays the current amount of activity calculated in step S4 and the chronological change in the amount of activity calculated in step S7 (step S8). Note that the display unit 14 may display only one of the current amount of activity and the time-series change, or may display the activity amount and the time-series change of others together. It is desirable that these display contents correspond to instructions input by the user via the information acquisition unit 11 .

Here, FIG. 8 shows an example of display contents in this step. FIG. 8(a) is a graph showing the amount of activity for each activity content of the person to be analyzed. In FIG. 8(a), exercise (gymnastics), exercise (walking), cleaning, eating, relaxing (reading), relaxing (email), and relaxing (TV) are used as activity contents. In addition, in FIG. 8(a), the amount of activity in the presence or absence of the elderly wearer, which is one type of activity condition, is displayed for each content of these activities. Although the amount of activity of one person to be analyzed is displayed in FIG. 8A, it may be displayed in a form that allows comparison with the amounts of activity of others. Furthermore, chronological changes may be displayed.

In addition, FIG. 8B plots the first speed information and the second speed information of the person to be analyzed for each of the presence or absence of the elderly person's orthosis. In FIG. 8B, the moving speed in the xy plane is used as the first speed information, and the tip speed of the hand is used as the second speed information. Here, in FIG. 8(b), the area of the rectangle having the origin and the plotted points as vertices indicates the relationship between the first velocity information and the second velocity information. Specifically, this relationship means that, in order to increase the area, it is effective to increase not only one of them but also both of them. You may treat this relationship as an "activity amount." As described above, in this embodiment, it is sufficient to calculate and output some index related to the activity of the person to be analyzed, without being limited to the amount of activity. Also, the display shown in FIG. 8 may be performed in the second or third embodiment described later.

Furthermore, in step S8, the display unit 14 may display an alert. In this case, in step S7, the calculation unit 12 compares the calculated time-series change with the threshold value set in the storage unit 13. FIG. Then, when the comparison result satisfies a predetermined condition, an alert is displayed on the display unit 14 . Predetermined conditions include a case where the amount or degree of decrease in the amount of activity is less than or equal to a predetermined amount. In other words, an alert can be output according to the change in activity of the person to be analyzed. Furthermore, an alert may be output when the amount of activity is equal to or less than a preset threshold.

The active mass calculation device 1 may end the process in step S8 as it is, or may return to execute the above-described steps immediately after the start of the process (step S1).

Next, Example 2 will be described. Example 2 is an example of cooperation with businesses that provide services and products to the elderly, such as insurance companies and day service providers.
In this embodiment, first, the business prepares services and products in cooperation with the activity amount calculation device 1 . Then, when a service provider applies for a subscription to a service or product, the provider sends various sensors to the subscriber's home. After installation, each sensor secures a power source by connecting to a power source, batteries, or energy harvesting such as sunlight or vibration, and starts measurement.

FIG. 3 shows a block diagram showing the configuration of the active mass calculation system in the second embodiment based on the above premise. In FIG. 3, an external server 51 is a computer device managed and used by the operator, and 22 to 32 are various sensors. These are connected to the active mass calculation device 1 . Sensor data measured by various sensors are transmitted to the external server 51 directly or via a gateway.

Note that the type of sensor used can be changed according to the service and product. For example, a radio wave sensor 22, an image sensor 23, a human sensor 24, an illuminance sensor 25, a temperature/humidity pressure sensor 26, a door opening/closing sensor 27, a plurality of vibration sensors 28, a pressure sensor 29, and a wearable sensor 30 are used in combination. You can Here, some or all of the human sensor 24, the illuminance sensor 25, and the temperature/humidity/pressure sensor 26 may be combined into one as an environment sensor. Data linkage with other commercially available devices such as the weight scale 31 and the body composition meter 32 that can be connected online may also be included. It is desirable that the physical information 41 is output from the weight scale 31 and the body composition monitor 32 to the information acquisition unit 11 .

Also, the administrator of the external server 51 is not limited, and may be a server managed by a business operator, a server managed by a sensor manufacturer, or a server that can be generally rented. Here, in this embodiment, a third party such as a system builder may also be involved in addition to the business operator. In this case, the physical information 41 and sensor data may be stored in different environments in the external server 51 and a third party server, and may be read by the activity amount calculation device 1 and made available. However, these servers need to be able to communicate with the activity amount calculation device 1 built in any of the third party's internal environment, the business's internal environment, and the cloud environment.

Here, the information acquisition unit 11 of the activity amount calculation device 1 acquires sensor data collected by the external server 51 or a third party server. The information acquisition unit 11 also acquires physical information 41 . As for the acquisition method of the physical information 41, input from the sensor 21, reading of the content described in the subscription application form for services and products, and input to my page of the company's home page in the external server 51 can be assumed. In addition, separately, measuring instruments such as a grip strength meter and a body composition meter are prepared, and the result is obtained by the activity amount calculation device 1, and cooperation with other third parties such as other business operators, local governments, non-profit organizations, etc. It is possible to acquire the physical information 41 by doing so. As described above, the physical information 41 may be acquired from each of the servers described above, or may be acquired by the activity amount calculation device 1 from the user or other devices/apparatuses. The sensor data and physical information 41 acquired by the information acquisition unit 11 are stored in the storage unit 13 .

The calculation unit 12 also calculates the amount of activity from the sensor data and the physical information 41 acquired by the information acquisition unit 11 . This devising is carried out in the same way as in Example 1. Here, in addition to the radio wave sensor 22 and the image sensor 23, the sensor 21 uses at least one or more of a human sensor 24, an illuminance sensor 25, a temperature/humidity/pressure sensor 26, a door open/close sensor 27, and a vibration sensor 28. be done. In this case, the moving speed of the person to be analyzed may be calculated based on the difference in time when those sensors reacted, and the moving speed may be used to calculate the amount of activity.

The storage unit 13 also stores the physical information 41 acquired by the information acquisition unit 11 . Then, the calculation unit 12 searches the storage unit 13 for history data such as past physical information and activity amount of the same person. Then, the calculation unit 12 can perform time-series analysis using the search results. That is, step S7 of the first embodiment is executed.

Further, the calculation unit 12 outputs the calculated current amount of activity and the time-series analysis result. As a result, the accumulation unit 13 stores the amount of activity and the results of time-series changes calculated by the calculation unit 12 for each person to be analyzed according to their age, gender, origin, religion, lifestyle, occupation, medical history, etc. Accumulate by category.

In addition, the display unit 14 displays the amount of activity calculated by the calculation unit 12 and the time-series analysis result. This makes it possible to present the amount of activity and the results of time-series analysis to system operators and operators. Here, it is desirable that the display for the person in charge of the business be displayed on the external server 51 or a terminal connected thereto. Note that the display contents may differ between the system operator and the service provider. For the system operator, for example, it is desirable to display the following information in addition to the current activity amount of the person to be analyzed and the chronological change in the activity amount.
・Information about the operating state of the sensor 21 ・Information about the battery status of the sensor 21 ・Indicated value of the sensor 21 not through the processing of the calculation unit 12 ・Information about the date, number of times, time and content of the business operator's reference to the system.

For the business operator, for example, in addition to the current activity amount of the person to be analyzed and the chronological change in the activity amount, the information may be converted into information particularly required for each business operator and displayed. Specifically, if it is an insurer, it is desirable to show the history of insurance coverage of others in the past and chronological changes in the amount of activity. can provide materials analogous to Based on this information, the insurer can consider intervention measures to correct the chronological changes in the amount of activity of the person to be analyzed in the direction of lowering the applicability of insurance. For this intervention method, in order to increase the amount of activity of the analysis target, recommendations such as "Let's take a walk for about 30 minutes every day" and "Would you like to participate in the bazaar held in the town?" includes doing.

In the case of a day service provider, by showing the schedule of the day service and chronological changes in the amount of activity, it will be possible to provide material for examining the effect of the content of the day service on the amount of activity of the person to be analyzed. can be Based on this information, the day service provider can consider a program for correcting the chronological change in the amount of activity for each person to be analyzed in the desired direction.

Operators can provide feedback to system administrators on display content. Means of feedback include verbal communication, email, and posting via the system administrator's home page. The system administrator may change the display contents based on the feedback from the business. This completes the description of the second embodiment.

Next, Example 3 will be described. A third embodiment is an example in which the present invention is applied to a so-called watching service. FIG. 4 shows a block diagram showing the configuration of the active mass calculation system according to the third embodiment. FIG. 4 shows a case where an individual who wants to watch over an elderly parent utilizes the activity amount calculation system. , which are connected via a network. At this time, it is desirable that the activity amount calculation device 1, the external server 51, and the external terminal 52 are connected inside the business operator such as an intranet. Although the external server 51 is drawn separately in FIG. 4, it is desirable to configure it in one housing.

Here, the present embodiment differs from the first and second embodiments in that the storage unit 13 and the display unit 14 are provided in other devices. That is, the storage unit 13 is provided in the external server 51 and the display unit 14 is provided in the external terminal 52 . In the following description, the content overlapping with the first and second embodiments will be omitted, and only different parts will be described.

First, an individual who wants to watch over an elderly parent subscribes to a watching service that utilizes an activity amount calculation system. Upon subscribing to this service, various types of sensors 21 are sent to individuals wishing to watch over their elderly parents, depending on the service plan. After the sensor 21 is installed in the home 54 of the elderly parent, the sensor 21 secures a power supply, starts measurement, and saves the data in the external server 51 or the like.

In FIG. 4 , the information acquisition unit 11 of the activity amount calculation device 1 communicates with the accumulation unit 13 and the action recognition unit 15 of the external server 51 . Specifically, the information acquisition unit 11 acquires sensor data, physical information 41, and activity information indicating daily behavior of the person to be analyzed. Here, the subject of analysis in this embodiment is an elderly parent.

Here, the behavior recognition unit 15 has a function of recognizing the daily behavior of the person to be analyzed in the home based on the data of the sensor 21 . This recognition utilizes measurement results from sensors capable of detecting the presence of a person at a specific location, such as a human sensor, a millimeter wave sensor, and an image sensor. And the action recognition part 15 will perform the following recognition methods.
・Methods for recognizing places and actions in relation to each other.
A method of clustering data from at least two or more types of sensors 21, and recognizing by associating the characteristics of the sensors reacting in each cluster with actions.
・Method of creating a classifier that classifies sensor data into behaviors by learning the relationship between behaviors self-reported by the person to be analyzed and sensor data by machine learning or the like.

Here, with regard to the activity recognition method by clustering, specifically, for data belonging to a certain cluster, if there is no response from the human sensor, the human sensor will respond, and the human sensor will respond at night in the bedroom. If the indicated value is small, it can be recognized as sleep.

Further, the calculation unit 12 acquires information from the information acquisition unit 11 or the storage unit 13 provided in the external server 51, calculates the amount of activity, and calculates the time-series change for each unit time and each activity content.

Further, as described above, the accumulation unit 13 is provided in the external server 51 separate from the activity amount calculation device 1, and the information acquisition unit 11, the calculation unit 12, the display unit 14 provided in the external terminal 52 and the data can be given and received. This external terminal 52 may be a smart device 55 such as a smart phone or a tablet that can be used by individuals who want to watch over their elderly parents.

The calculation unit 12 outputs the calculation result to the storage unit 13 provided in the external server 51 and the display unit 14 provided in the external terminal 52 . Note that the calculation results are the above-mentioned amount of activity and time-series changes, and these are calculated by the same calculations as in the first and second embodiments. Therefore, description of this calculation method is omitted.

Next, FIG. 5 shows a first example of the display unit 14 in the external terminal 52 of this embodiment. This example is a display for individuals watching over their elderly parents. The display unit 14 displays "current daily behavior", "activity amount", and "time-series change in activity amount" of the elderly parent who is the subject of analysis, and recommendations that are the results of these analyses. Here, the unit of "activity" can be freely selected by the user from (J), (cal.) and (METs). However, (METs) is calculated by measuring (J) or (cal.) and (METs) separately with the sensor 21 in a preliminary measurement test, approximating their relationship with a formula, and using that approximation formula. You can

Furthermore, as shown in Fig. 5, when the chronological change in the amount of activity is on a downward trend, the recommendation is "Mr. It is conceivable to display Note that FIG. 5 shows graphs for overall life, cooking, and cleaning as examples of time-series changes in the amount of activity, and graphs for sleeping, eating, relaxing, bathing, toileting, washing, etc. are also shown. I don't mind.

FIG. 6 shows a second example of the display unit 14 of the external terminal 52 of the present embodiment. This example is also a display for individuals watching over their elderly parents. As shown in FIG. 6, the display unit 14 displays "current daily behavior", "today's daily behavior", "activity amount", "time-series change in activity amount" recognized by the activity recognition unit 15, and feedback considering these contents. is displayed. Then, "today's daily activity" is displayed in the form of a pie chart. Here, as a feedback, as shown in Fig. 6, when the time-series change in the amount of activity tends to increase and sufficient sleep time is secured, "Recently, Mr. ○○ is sleeping enough. For this reason, an individual who wants to watch over his/her elderly parents can confirm the above contents through the display unit 14, and can also evaluate the displayed result. Feedback can be provided through the display unit 14 of the external terminal 52 . FIG. 7 shows an example of the display unit 14 for feedback on the external terminal 52 in this embodiment. In this example, a touch panel in which the display screen and the input section are integrated is used as the display section 14, but the display screen and the input section may be separately provided. The display unit 14 in FIG. 7 can change the physical information 41 in addition to feeding back the 10-level evaluation of the display result according to the input from the user. In other words, these pieces of information are reflected in the contents of the storage unit 13 .

5 to 7 may be periodically distributed from the activity amount calculation device 1, or may be distributed from the external terminal 52 upon request. Furthermore, the activity amount calculation device 1 may deliver to the external terminal 52 when the activity amount and the time-series change satisfy predetermined conditions. For example, the active mass calculation device 1 may output an alert when the active mass is equal to or less than a predetermined threshold.
<Example of implementation>
Finally, implementation examples in the second and third embodiments will be described. FIG. 9 is a configuration diagram showing the implementation of the active mass calculation system in each embodiment. In each embodiment, the activity amount calculation system includes an activity amount calculation device 1, a sensor 21, an external terminal 52, an external server 51-1 and an external server 51-2 connected to each other via a network such as the Internet. there is

Here, the activity amount calculation device 1 has an information acquisition unit 11 , a calculation unit 12 , an accumulation unit 13 and a display unit 14 . Here, the storage unit 13 and the display unit 14 may be provided in another device as described in the third embodiment. Further, the calculation unit 12 calculates the above-described activity amount calculation and time-series change according to an activity amount calculation program (not shown). Further, the activity amount calculation device 1 may be connected to the terminal devices 16-1 and 16-2 and display similar to the display unit 14. FIG. Therefore, the display unit 14 may be omitted from the activity amount calculation device 1 . It is desirable that the activity amount calculation device 1 and the terminal devices 16-1 and 16-2 be connected via a local network such as an intranet.

Also, it is a server used by the insurer of the external server 51-1, and is connected to the external terminal 52-1 via a local network. The external server 51-1 has a storage unit 13 and an action recognition unit 15. FIG. Here, the action recognition unit 15 executes the above-described processing according to the action recognition program. Therefore, the action recognition unit 15 can also be realized by a processor. The action recognition program can be stored in a storage medium and distributed to the external server 51 via a network. Furthermore, the external terminal 52-1 is a terminal device used by employees of the insurance company.

The external server 51-2 is different from the external server 51-1 only in that the user is a day service provider, and the description thereof is omitted. Similarly, description of the external terminal 52-2 is also omitted. Furthermore, explanations of the sensor 21 and the external terminal 52 are omitted since they have already been explained in each embodiment.

Note that the implementation example shown in FIG. 9 is merely an example, and the activity amount calculation device 1 can also be implemented as a so-called personal computer. In this case, the activity amount calculation device 1 may be installed in the home 54, or may be realized by another device including home appliances used as the external terminal 52 or by the user.

This completes the description of the embodiments and implementation examples of the present invention, but the present invention is not limited to these. For example, by using sensor data from the sensor 21 in consideration of privacy, it is possible to secure the privacy of the analyst subject.

The above embodiment also has the following effects. That is, by making the sensor 21 non-contact or non-wearable to the person to be analyzed, the amount of activity can be calculated for natural activities such as at home. As a result, it is possible to determine the content of the activity more in line with the actual situation. In addition, by calculating a value having a unit of energy, it is possible to relatively compare the amount of activity even if the person to be analyzed and the activity are different.

1: Activity calculation device 11: Information acquisition unit 12: Calculation unit 13: Storage unit 14: Display unit 15: Action recognition unit 21: Sensor 22: Radio wave sensor 23: Image sensor 24: Human sensor 25: Illuminance sensor 26: Temperature and humidity pressure sensor 27: Open/close sensor 28: Vibration sensor 29: Pressure sensor 30: Wearable sensor 31: Weight scale 32: Body composition meter 41: Physical information 51: External server 52: External terminal 54: Home

Claims (14)

In an activity amount calculation device that calculates the amount of activity of a person to be analyzed,
an information acquisition unit that acquires measurement results for the activity of the person to be analyzed;
Based on the measurement result, the first speed information and the second speed information of the analysis subject are calculated, and the activity amount of the analysis subject is calculated using the first speed information and the second speed information. has a calculation unit that calculates
The calculation unit calculates at least one of the first speed information and the second speed information using position information of point cloud information indicating the person to be analyzed, which is included in the measurement result. Device. In the active mass calculation device according to claim 1,
The first speed information is local speed information indicating local characteristics of the activity of the subject to be analyzed,
Said 2nd speed information is an active mass calculation apparatus which is the whole speed information which shows the whole characteristic of said analysis subject's activity. In the active mass calculation device according to claim 2,
The calculation unit is an active mass calculation device that calculates the local velocity information using the position information of the point group information. In the active mass calculation device according to claim 2,
The active mass calculation device, wherein the local velocity information is a maximum value of velocities of points included in the point group information. In the active mass calculation device according to claim 2,
The active mass calculation device, wherein the overall speed information is calculated as speed information indicating the speed of the position of the center of gravity in the point group information. In the active mass calculation device according to claim 5,
The active mass calculation device, wherein the overall speed information is speed information indicating a speed component in a plane perpendicular to the vertical direction at the position of the center of gravity. In the active mass calculation device according to any one of claims 1 to 6,
The activity amount calculation device, wherein the calculation unit further specifies the activity amount using the weight of the person to be analyzed. In an activity calculation method using an activity amount calculation device for calculating an activity amount of an analysis subject,
an information acquisition unit acquires measurement results for the activity of the person to be analyzed;
The calculation unit calculates the first speed information and the second speed information of the analysis subject based on the measurement result, and uses the first speed information and the second speed information to calculate the analysis subject Calculate the amount of activity of the person,
The calculation unit calculates at least one of the first speed information and the second speed information using position information of point cloud information indicating the person to be analyzed, which is included in the measurement result. Method. In the activity amount calculation method according to claim 8,
The first speed information is local speed information indicating local characteristics of the activity of the subject to be analyzed,
The activity amount calculation method, wherein the second speed information is overall speed information indicating overall characteristics of the activity of the person to be analyzed. In the activity amount calculation method according to claim 9,
A method for calculating the amount of activity, in which the calculation unit calculates the local velocity information using the position information of the point group information. In the activity amount calculation method according to claim 9,
The activity amount calculation method, wherein the local velocity information is the maximum velocity of each point included in the point group information. In the activity amount calculation method according to claim 9,
The activity amount calculation method, wherein the overall speed information is calculated as speed information indicating the speed of the center of gravity position in the point group information. In the activity amount calculation method according to claim 12,
The activity amount calculation method, wherein the overall speed information is speed information indicating a speed component in a plane perpendicular to the vertical direction at the position of the center of gravity. In the activity amount calculation method according to any one of claims 8 to 13,
A method of calculating the amount of activity, wherein the calculation unit further uses the weight of the person to be analyzed to specify the amount of activity.

Images