JP2018161167A - Data processing device, data processing method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technique capable of recording sensor data having higher continuity in the case where operation characteristics of a plurality of sensors are different in each model or even in the case where non-carrying occurs in any of the plurality of sensors.SOLUTION: Provided is a data processing device that includes: an activity detection part for detecting data interlocking information showing whether first sensor data acquired from a first sensor and second sensor data acquired from a second sensor are each interlocked with activities of a first user; and a data integration part for generating data to be outputted on the basis of a relationship between the first sensor data and the second sensor data, and the second sensor data in the case where the data interlocking information satisfies a prescribed condition.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a data processing device, a data processing method, and a program.

  In general, one user can record the user's behavioral information and biological information using multiple sensors of the same type, and complement each other in detail to understand the user's daily living situation in detail. It is. For example, the user's calorie consumption is measured indoors with exercise equipment, the user's calorie consumption is measured outdoors with an activity meter, and both are combined to present the information to the user. It becomes possible to grasp the state of physical activity (see, for example, Patent Document 1).

  In such a technique, a form in which a plurality of same type sensors are switched and used in time series is usually adopted. On the other hand, a form in which a plurality of same type sensors are simultaneously used may be adopted. For example, when a smartphone and an activity meter are used at the same time, the smartphone and the activity meter may have a function of measuring the same measurement data (for example, the number of steps, calories consumed). In such a case, a difference may occur in the measurement data due to a difference in function or characteristic of each sensor, a lifestyle or intention of the user, or the like. Examples of specific factors that bring about such changes are shown below.

・ When a smartphone is used by a user, the user often carries the smartphone when going out, but often does not carry it at home.
When an activity meter is used by a user, the user often carries the activity meter for 24 hours, but sometimes forgets to wear it on his body.
When the activity meter is used by a user, there is a difference in measurement values depending on the model of the activity meter (for example, there is a difference in measurement values of about 500 kcal per day).
-When an activity meter is used by a user, a difference may occur in a measured value depending on a wearing position on the user's body or a user's walking habit.

JP 2014-161514 A

  As described above, when a plurality of the same type of sensors are simultaneously carried by a user and used, there may be a difference in measurement data. Therefore, when a plurality of similar sensors are simultaneously carried by a user and used, the following situation can occur as an example.

-When a user forgets to carry a sensor, correct sensor data cannot be acquired from the sensor.
When the operation characteristics of a plurality of sensors are different for each model, it is difficult to determine which of the plurality of sensors should be used. In addition, when a plurality of sensor data are simply switched and used, continuity between the plurality of sensor data does not increase.
・ Since the continuity between multiple sensor data does not increase, for example, when implementing a physical activity improvement plan using multiple sensor data, is the plan correctly implemented from multiple sensor data? It becomes difficult to judge.

  Therefore, even when the operational characteristics of multiple sensors differ from model to model, or even when non-portability occurs in any of the multiple sensors, it is possible to record sensor data with higher continuity. Is desired to be provided.

  In order to solve the above problem, according to an aspect of the present invention, each of the first sensor data acquired from the first sensor and the second sensor data acquired from the second sensor is used for the first use. An activity detection unit for detecting data linkage information indicating whether or not the activity of the person is linked, and when the data linkage information satisfies a predetermined condition, the first sensor data and the second sensor data There is provided a data processing device including a data integration unit that generates data to be output based on the relationship and the second sensor data.

  The data integration unit generates the output target data based on the relationship and the second sensor data when the first sensor data is not linked to the activity of the first user. May be.

  The data integration unit may generate the output target data based on the first sensor data when the first sensor data is linked to the activity of the first user.

  The activity detection unit determines whether the first sensor data is an activity of the first user according to whether or not the predetermined first data acquired from the first sensor is within a predetermined range. You may detect whether it is interlocking.

  The activity detection unit authenticates the first user based on data acquired from sensing means that is the same as or different from the first sensor, and authenticates the first user. It may be detected whether the first sensor data is linked to the activity of the first user according to whether it is successful.

  The first sensor data may include data related to physical activity or life activity of the first user.

  The data processing apparatus detects that the third sensor data acquired from the third sensor and the fourth sensor data acquired from the fourth sensor are linked to the activity of the second user. In such a case, a relationship estimation unit for estimating the relationship may be provided.

  The relationship estimation unit acquires the third sensor data and the fourth sensor data in time series from the third sensor when it is detected that each of the third sensor data and the fourth sensor data is linked to the activity of the second user. The relationship may be estimated on the basis of the first time series data to be obtained and the second time series data obtained in time series from the fourth sensor.

  The relationship estimation unit calculates a first error due to a first relationship between the first time-series data and a first generation data group generated based on detection by the fourth sensor, and Calculating a second error due to a second relationship between the first time-series data and the second generation data group corresponding to the data generated in the previous stage of the first generation data group; Either the first relationship or the second relationship may be selected as the relationship according to the magnitude relationship between the error and the second error.

  The first generation data group includes a final data group generated based on detection by the fourth sensor, and the second generation data group includes data generated in a stage before the final data group. A corresponding intermediate data group may be included.

  The first time series data may include a data group related to physical activity or life activity of the second user.

  The second time-series data includes at least one of a final data group generated based on detection by the fourth sensor and an intermediate data group corresponding to data generated in a previous stage of the final data group. May be included.

  Even if it is detected that the third sensor data and the fourth sensor data are linked to the activity of the second user, the relationship estimation unit may If the data and the fourth sensor data are not similar, the relationship need not be estimated.

  According to another aspect of the present invention, each of the first sensor data acquired from the first sensor and the second sensor data acquired from the second sensor is linked to the activity of the first user. Detecting the data linkage information indicating whether or not the data linkage information satisfies the predetermined condition, and the relationship between the first sensor data and the second sensor data and the second A data processing method is provided that includes generating data to be output based on sensor data.

  According to another aspect of the present invention, the first sensor data acquired from the first sensor and the second sensor data acquired from the second sensor are respectively stored in the first user's computer. An activity detection unit that detects data linkage information indicating whether or not it is linked to an activity, and a relationship between the first sensor data and the second sensor data when the data linkage information satisfies a predetermined condition And a data integration unit that generates data to be output based on the second sensor data and a program for causing the program to function as a data processing device.

  As described above, according to the present invention, even when the operation characteristics of a plurality of sensors are different for each model, or even when non-portability occurs in any of the plurality of sensors, a sensor with higher continuity is provided. A technique capable of recording data is provided.

It is a figure which shows the structural example of the data processing system which concerns on this embodiment. It is a block diagram which shows the detailed structural example of the conversion rule determination part which concerns on this embodiment. It is a flowchart which shows the operation example of the data processing system which concerns on this embodiment. It is operation | movement explanatory drawing of a 1st conversion rule estimation part. It is operation | movement explanatory drawing of a 2nd conversion rule estimation part. It is a figure which shows the specific example of operation | movement of the data processing system which concerns on this embodiment. It is a figure which shows the hardware constitutions of the data processor which concerns on embodiment of this invention.

  Exemplary embodiments of the present invention will be described below in detail with reference to the accompanying drawings. In addition, in this specification and drawing, about the component which has the substantially same function structure, duplication description is abbreviate | omitted by attaching | subjecting the same code | symbol.

  In the present specification and drawings, a plurality of constituent elements having substantially the same functional configuration may be distinguished by attaching different numerals to the same reference numerals. However, when there is no need to particularly distinguish each of a plurality of constituent elements having substantially the same functional configuration, only the same reference numerals are given. In addition, similar components in different embodiments may be distinguished by attaching different alphabets after the same reference numerals. However, in the case where it is not necessary to particularly distinguish each of similar components of different embodiments, only the same reference numerals are given.

[1-1. System overview]
First, a configuration example of the data processing system according to the present embodiment will be described.

  FIG. 1 is a diagram illustrating a configuration example of a data processing system according to the present embodiment. As shown in FIG. 1, the data processing system 1 according to the present embodiment includes a first activity meter 110-1, a second activity meter 110-2, an activity detection unit 120, a conversion rule determination unit 130, data An integration unit 140 and a presentation unit 150 are provided.

  In the present embodiment, the activity detection unit 120 has the first sensor data acquired from the first sensor and the second sensor data acquired from the second sensor linked to the activity of the first user. The data linkage information indicating whether or not it is being detected is detected. From this data linkage information, it is grasped whether or not the first user carries each of the first sensor and the second sensor. Then, when the data linkage information satisfies the predetermined condition, the data integration unit 140 determines the output target data based on the relationship between the first sensor data and the second sensor data and the second sensor data. Generate.

  More specifically, when the first sensor data is linked to the activity of the first user, it is considered that the activity of the first user is more accurately reflected in the first sensor data. . Therefore, in this case, the data integration unit 140 generates output target data based on the first sensor data.

  On the other hand, when the first sensor data is not linked to the activity of the first user, and when the second sensor data is linked to the activity of the first user, the second sensor data It is considered that the activity of the first user is reflected more accurately. Therefore, in this case, the data integration unit 140 generates output target data based on the relationship between the first sensor data and the second sensor data and the second sensor data.

  In the following description, the first activity meter 110-1 is given as an example of the first sensor, and the first activity data (for example, calories burned based on acceleration) is given as an example of the first sensor data. . However, as will be described later, another sensor may be used instead of the first sensor, or other sensor data may be used instead of the first sensor data.

  In the present embodiment, the activity detection unit 120 acquires second sensor data from the second sensor. In the following description, the second activity meter 110-2 is given as an example of the second sensor, and the second activity data (for example, calorie consumption based on acceleration) or the second sensor data is given as an example of the second sensor data. 2 acceleration index data (for example, acceleration dispersion value). However, another sensor may be used instead of the second sensor, and other sensor data may be used instead of the second sensor data.

  Here, the relationship between the first sensor data and the second sensor data is estimated by the conversion rule determination unit 130. The conversion rule determination unit 130 indicates that the third sensor data acquired from the third sensor and the fourth sensor data acquired from the fourth sensor are linked to the activity of the second user. If detected, the relationship between the first sensor data and the second sensor data is estimated.

  More specifically, when it is detected that the third sensor data and the fourth sensor data are linked to the activity of the second user, the conversion rule determination unit 130 starts from the third sensor. The relationship between the first sensor data and the second sensor data based on the first time series data acquired in time series and the second time series data acquired in time series from the fourth sensor. Is estimated.

  In the following description, the first activity amount data acquired from the first activity meter 110-1 is used as the “third sensor data” acquired from the “third sensor”. As the “time series data”, the first activity amount data group acquired in time series from the first activity meter 110-1 will be used. Further, as the “fourth sensor data” acquired from the “fourth sensor”, the second activity amount data or the second acceleration index data acquired from the first activity meter 110-2 is used. The second activity amount data group or the second acceleration index data group is used as the “second time series data”.

  Note that the conversion rule determination unit 130 can function as a relationship estimation unit that estimates the relationship between the first sensor data and the second sensor data. In the following description, the “first user” when the output target data is generated and the “second user” when the relationship is generated are the same “user”. Assume a certain case. However, the “second user” and the “first user” may be different users. In the following description, the relationship between the first sensor data and the second sensor data may be particularly referred to as “conversion rule” or “conversion rule data”.

  As shown in FIG. 1, the first activity meter 110-1 outputs the first activity data to the conversion rule determination unit 130. The first activity amount data will be described later. In addition, the first activity meter 110-1 outputs the first acceleration index data to the activity detection unit 120. The first acceleration index data will also be described later. In addition, the first activity meter 110-1 outputs the first activity data to the data integration unit 140.

  Also, as shown in FIG. 1, the second activity meter 110-2 outputs the second activity data and the second acceleration index data to the conversion rule determination unit 130. The second activity amount data and the second acceleration index data will be described later. In addition, the second activity meter 110-2 outputs the second acceleration index data to the activity detection unit 120. In addition, the second activity meter 110-2 outputs the second activity data and the second acceleration index data to the data integration unit 140.

  Moreover, as shown in FIG. 1, the activity detection part 120 inputs 1st acceleration parameter | index data from the 1st active mass meter 110-1. Moreover, as shown in FIG. 1, the activity detection part 120 inputs 2nd acceleration parameter | index data from the 2nd active mass meter 110-2. As shown in FIG. 1, the activity detection unit 120 outputs conversion rule update instruction data to the conversion rule determination unit 130. The conversion rule update instruction data will be described later. As shown in FIG. 1, the activity detection unit 120 outputs activity meter selection instruction data to the data integration unit 140. The activity meter selection instruction data will be described later.

  Moreover, as shown in FIG. 1, the conversion rule determination part 130 inputs 1st activity amount data from the 1st activity amount meter 110-1. Moreover, as shown in FIG. 1, the conversion rule determination part 130 inputs 2nd activity amount data and 2nd acceleration parameter | index data from the 2nd activity amount meter 110-2. Further, as shown in FIG. 1, the conversion rule determination unit 130 inputs conversion rule update instruction data from the activity detection unit 120. As shown in FIG. 1, the conversion rule determination unit 130 outputs the conversion rule data to the data integration unit 140. The conversion rule data will be described later.

  As shown in FIG. 1, the data integration unit 140 inputs first activity data from the first activity meter 110-1. As shown in FIG. 1, the data integration unit 140 inputs the second activity amount data and the second acceleration index data from the second activity meter 110-2. As shown in FIG. 1, the data integration unit 140 inputs conversion rule data from the conversion rule determination unit 130. As shown in FIG. 1, the data integration unit 140 inputs activity meter selection instruction data from the activity detection unit 120. As shown in FIG. 1, the data integration unit 140 outputs activity amount integration data to the presentation unit 150.

  As shown in FIG. 1, the presentation unit 150 inputs activity amount integration data from the data integration unit 140.

  The configuration example of the data processing system 1 according to the present embodiment has been described above.

[1-2. Detailed configuration example of conversion rule determination unit]
Subsequently, a detailed configuration example of the conversion rule determination unit 130 according to the present embodiment will be described. FIG. 2 is a block diagram illustrating a detailed configuration example of the conversion rule determination unit 130 according to the present embodiment. As shown in FIG. 2, the conversion rule determination unit 130 according to the present embodiment includes a first conversion rule estimation unit 131-1, a second conversion rule estimation unit 131-2, and a conversion rule update unit 132.

  As shown in FIG. 2, the first conversion rule estimation unit 131-1 receives the first activity data from the first activity meter 110-1. As shown in FIG. 2, the first conversion rule estimation unit 131-1 receives the second activity data from the second activity meter 110-2. As shown in FIG. 2, the first conversion rule estimation unit 131-1 receives conversion rule update instruction data from the activity detection unit 120. As shown in FIG. 2, the first conversion rule estimation unit 131-1 outputs the first conversion parameter to the conversion rule update unit 132.

  Further, as shown in FIG. 2, the second conversion rule estimation unit 131-2 receives the first activity data from the first activity meter 110-1. Also, as shown in FIG. 2, the second conversion rule estimation unit 131-2 receives the second acceleration index data from the second activity meter 110-2. As shown in FIG. 2, the second conversion rule estimation unit 131-2 receives conversion rule update instruction data from the activity detection unit 120. As shown in FIG. 2, the second conversion rule estimation unit 131-2 outputs the second conversion parameter to the conversion rule update unit 132.

  Further, as illustrated in FIG. 2, the conversion rule update unit 132 receives the first conversion parameter from the first conversion rule estimation unit 131-1. In addition, as illustrated in FIG. 2, the conversion rule update unit 132 inputs the second conversion parameter from the second conversion rule estimation unit 131-2. Further, as shown in FIG. 2, the conversion rule update unit 132 inputs conversion rule update instruction data from the activity detection unit 120. As shown in FIG. 2, the conversion rule update unit 132 outputs the conversion rule data to the data integration unit 140.

  Note that each functional block included in the data processing system 1 illustrated in FIG. 1 may be realized by any hardware configuration. As an example, in the present embodiment, the first activity meter 110-1 and the presentation unit 150 are built in a mobile terminal (for example, a smartphone), and the second activity meter 110-2 is a wristband type activity meter. It is assumed that the activity detection unit 120, the conversion rule determination unit 130, and the data integration unit 140 are built in a data processing device (for example, a server). In addition, it is assumed that data can be transmitted and received between the mobile terminal and the data processing device and between the wristband type activity meter and the data processing device via the network.

  The detailed configuration example of the conversion rule determination unit 130 according to the present embodiment has been described above.

[1-3. Example of operation of data processing system 1]
Subsequently, an operation example of the data processing system 1 according to the present embodiment will be described. FIG. 3 is a flowchart showing an operation example of the data processing system 1 according to the present embodiment. FIG. 4 is an explanatory diagram of the operation of the first conversion rule estimation unit 131-1. FIG. 5 is an explanatory diagram of the operation of the second conversion rule estimation unit 131-2.

  In the present embodiment, it is assumed that the user normally carries both the first activity meter 110-1 and the second activity meter 110-2. In the present embodiment, it is assumed that a situation occurs in which the user sometimes does not carry one of the first activity meter 110-1 and the second activity meter 110-2. Data input from the activity meter carried by the user can be linked to the activity of the user. On the other hand, data input from an activity meter that is not carried by the user cannot be linked to the activity of the user.

(1-3-1. Data acquisition of the first activity meter and the second activity meter)
As shown in FIG. 3, in the data processing system 1, when sensor data processing is started (S10), data is acquired from each of the first activity meter 110-1 and the second activity meter 110-2. (S11).

  Specifically, the first active mass meter 110-1 calculates a calorie consumption per predetermined time and an acceleration dispersion value per predetermined time based on the acceleration measured by the built-in acceleration sensor. Accumulate calorie and acceleration dispersion values. Although the length of the predetermined time is not limited, “1 minute” is used as an example of the predetermined time below. When the user operates the first activity meter 110-1, the accumulated calorie consumption is output as the first activity amount data to the conversion rule determination unit 130 and the data integration unit 140, respectively, and the accumulated acceleration. The variance value is output to the activity detection unit 120 as the first acceleration index data.

  Similarly, the second active mass meter 110-2 calculates the calorie consumption per minute and the acceleration dispersion value per minute based on the acceleration measured by the built-in acceleration sensor, and calorie consumption. And acceleration dispersion value are accumulated. When the user operates the second activity meter 110-2, the accumulated calorie consumption is output as second activity amount data to the conversion rule determination unit 130 and the data integration unit 140, respectively, and the accumulated acceleration. The variance value is output as second acceleration index data to the activity detection unit 120, the conversion rule determination unit 130, and the data integration unit 140, respectively.

  In addition, you may comprise so that the data output from the 1st active mass meter 110-1 and the 2nd active mass meter 110-2 may be performed regularly irrespective of a user's operation. Further, the first activity meter 110-1 relays the data from the second activity meter 110-2, and the first activity meter 110-1 receives the first activity meter 110-1. Alternatively, the data of each of the second activity meter 110-2 may be output.

(1-3-2. Detection of user activity)
Subsequently, the user activity is detected (S12).

  Specifically, when the activity detection unit 120 inputs the first acceleration index data from the first activity meter 110-1, the first acceleration index data is also referred to as a predetermined range (hereinafter referred to as “variation range”). ), It is detected whether or not the first activity amount data is linked to the activity of the user. For example, the activity detection unit 120 detects a time interval in which the first acceleration index data falls within the fluctuation range as a time interval in which the first activity amount data is linked to the user activity.

  For example, in the fluctuation range, at least one of the upper limit value and the lower limit value is experimentally set in advance on the basis of the acceleration dispersion value during the activity of a general person. In the present embodiment, the first acceleration index data indicates an acceleration dispersion value per minute. The acceleration dispersion value per minute indicates whether the user's activity is stop or walking. It depends on whether it is running. Therefore, for example, the variation range is set to include ranges corresponding to walking and running.

  In the present embodiment, a case will be mainly described in which whether or not the first activity amount data is linked to the activity of the user is detected based on the first acceleration index data. However, whether or not the first activity amount data is linked to the activity of the user is based on some predetermined first value acquired from the first activity meter 110-1 instead of the first acceleration index data. May be detected based on the data (for example, the first activity amount data).

  Similarly, when the second acceleration index data is input from the second activity meter 110-2, the activity detection unit 120 determines whether the second acceleration index data falls within the fluctuation range. It is detected whether the activity amount data and the second acceleration index data are linked to the activity of the user. For example, the activity detection unit 120 detects a time interval in which the second acceleration index data falls within the fluctuation range as a time interval in which the second activity amount data and the second acceleration index data are linked to the user activity. To do.

  As described above, the activity detection unit 120 detects whether or not the first acceleration index data falls within the fluctuation range, and detects whether or not the second acceleration index data falls within the fluctuation range. At this time, these fluctuation ranges may be the same or different.

  In the present embodiment, it is mainly a case where whether or not the second activity amount data and the second acceleration index data are linked to the user activity is detected based on the second acceleration index data. explain. However, whether or not the second activity amount data is linked to the activity of the user is based on some predetermined second value acquired from the second activity meter 110-2 instead of the second acceleration index data. May be detected based on the data (for example, the second activity amount data).

  The activity detection unit 120 determines whether the first activity data is linked to the user's activity, and whether the second activity data and the second acceleration index data are linked to the user's activity. Based on whether or not, the active mass meter selection instruction data for selecting either the first active mass meter 110-1 or the second active mass meter 110-2 is output to the data integration unit 140. Thereby, the activity meter in which the user's activity is more correctly recorded can be selected from the first activity meter 110-1 and the second activity meter 110-2.

  In the present embodiment, the activity detecting unit 120 detects the selection of the first activity meter 110-1 when it is detected that only the first activity data is linked to the activity of the user. The selection instruction data is output to the data integration unit 140. On the other hand, when the activity detection unit 120 detects that only the second activity amount data and the second acceleration index data are linked to the activity of the user, the activity detection unit 120 selects the second activity amount meter 110-2. The activity meter selection instruction data shown is output to the data integration unit 140.

  It is also assumed that the activity detection unit 120 detects that all of the first activity amount data, the second activity amount data, and the second acceleration index data are linked to the user activity. In such a case, the activity detection unit 120 outputs activity meter selection instruction data indicating selection of the first activity meter 110-1 to the data integration unit 140.

  As described above, when the activity of the user is detected, the operation is shifted to S13. As described above, the activity detection unit 120 sends the conversion rule update instruction data to the conversion rule determination unit 130. In some cases, it is output (“Yes” in S20). In such a case, the conversion rule update process is also started by the conversion rule determination unit 130 (S30), and S31 is also executed in parallel with S13.

(1-3-3.2 Two types of conversion rules and conversion error calculation)
When the operation is shifted to S31, two types of conversion rules and calculation of conversion error are executed.

  Specifically, the conversion rule determination unit 130 inputs conversion rule update instruction data from the activity detection unit 120, inputs first activity data from the first activity meter 110-1, and outputs a second activity amount. When the second activity amount data and the second acceleration index data are input from the total 110-2, one or both of the two types of conversion rules are updated, and an error due to the updated conversion rules is calculated. In the present embodiment, it is assumed that the various data input to the conversion rule determination unit 130 is data for each time interval of 1 minute as an example. The two types of conversion rules include a rule for estimating the first activity amount data from the second activity amount data, and a rule for estimating the first activity amount data from the second acceleration index data. Applies to the rules.

  First, a rule calculation method for estimating the first activity data from the second activity data will be described with reference to FIGS. 2 and 4. As described above, since the conversion rule update instruction data is data for each time interval of 1 minute, the first conversion rule estimation unit 131-1 in the conversion rule determination unit 130 determines the first conversion rule corresponding to this time interval. A new set of activity amount data and second activity amount data is accumulated.

  And the 1st conversion rule estimation part 131-1 is the 1st active mass data group (1st time series data) currently accumulate | stored, and the 2nd active mass data group (1st production | generation data group). Are used to obtain the relationship between the first activity amount data and the second activity amount data (first relationship) as a conversion function by linear approximation. For example, the conversion function is calculated as first activity amount data = a1 × (second activity amount data). Furthermore, the first conversion rule estimation unit 131-1 calculates an error (first error) when the second activity amount data is converted into the first activity amount data by the conversion function. For example, the error may be a standard deviation.

  The first conversion rule estimation unit 131-1 outputs the approximate parameter and the error thus obtained to the conversion rule update unit 132 as the first conversion parameter. For example, the approximate parameter corresponds to a coefficient “a1” when the conversion function is set to the first activity amount data = a1 × (second activity amount data). In FIG. 4, a state in which a set of currently accumulated data is plotted in a space constituted by the first activity amount data and the second activity amount data is shown by hatching, and the conversion function is a straight line. It is shown in

  Subsequently, a rule calculation method for estimating the first activity amount data from the second acceleration index data will be described with reference to FIGS. 2 and 5. As described above, since the conversion rule update instruction data is data for each time interval of 1 minute, the second conversion rule estimation unit 131-2 in the conversion rule determination unit 130 sets the first corresponding to this time interval. A set of the activity amount data and the second acceleration index data is newly accumulated.

  Then, the second conversion rule estimation unit 131-2 includes the first accumulated active mass data group (first time series data) and the second acceleration index data group (second generated data group). Are used to determine the relationship between the first activity amount data and the second acceleration index data (second relationship) as a conversion function by linear approximation. For example, the conversion function is calculated as first activity amount data = a × (second acceleration index data). Furthermore, the second conversion rule estimation unit 131-2 calculates an error (second error) when the second acceleration index data is converted into the first activity amount data by the conversion function. For example, the error may be a standard deviation.

  The second conversion rule estimation unit 131-2 outputs the approximate parameter and the error thus obtained to the conversion rule update unit 132 as the second conversion parameter. For example, the approximate parameter corresponds to the coefficient “a2” when the conversion function is set to the first activity amount data = a2 × (second acceleration index data). In FIG. 5, a state in which a set of currently accumulated data is plotted in a space constituted by the first activity amount data and the second acceleration index data is shown by hatching, and the conversion function is a straight line. It is shown in

  In the above description, the case where the conversion rule determining unit 130 obtains each relationship using a conversion function based on linear approximation has been mainly described. However, the conversion rule determination unit 130 may obtain each relationship by other than linear approximation. For example, the conversion rule determination unit 130 may obtain each relationship using a conversion function based on curve approximation. The conversion function by curve approximation may be an exponential function or a quadratic function.

  In the above description, the case has been mainly described where the conversion rule determination unit 130 obtains each relationship each time a data set is newly accumulated by inputting conversion rule update instruction data. However, the timing at which each relationship is determined by the conversion rule determination unit 130 is not limited to this case. For example, the conversion rule determination unit 130 may obtain each relationship based on a currently stored data set after a certain amount of new data set has been stored.

(1-3-4. Conversion rule update)
Subsequently, the conversion rule is updated (S32), and the conversion rule update process ends (S33).

  Specifically, the conversion rule update unit 132 in the conversion rule determination unit 130 receives the first conversion parameter from the first conversion rule estimation unit 131-1, and the second conversion rule estimation unit 131-2 receives the second conversion parameter. When the conversion parameter is input, the error included in the first conversion parameter is compared with the error included in the second conversion parameter. Then, the conversion rule update unit 132 selects an approximate parameter based on the magnitude relationship between the two errors. For example, the conversion rule update unit 132 selects the approximate parameter with the smaller error, updates the conversion rule data by this, and outputs it to the data integration unit 140.

(1-3-5. Estimation of activity data)
When the operation is shifted to S13, the activity amount data is estimated.

  Specifically, the data integration unit 140 inputs activity meter selection instruction data from the activity detection unit 120, inputs first activity data from the first activity meter 110-1, and receives a second activity amount. When the second activity amount data and the second acceleration index data are input from the total 110-2, the activity amount data is calculated based on the activity meter selection data, and the calculated activity amount data is the activity amount integrated data (output target) To the presentation unit 150.

Here, the calculation method of the activity data based on the activity meter selection data is as follows.
When the activity meter selection instruction data indicates selection of the first activity meter 110-1, the first activity amount data is output as activity amount integrated data.
When the activity meter selection instruction data indicates the selection of the second activity meter 110-2, the second activity amount data or the second acceleration index data according to the conversion rule data input from the conversion rule determination unit 130 The activity amount data is calculated based on the activity amount data, and the calculated activity amount data is output to the presentation unit 150 as activity amount integrated data (output target data).

(1-3-6. Presentation of activity data)
Subsequently, presentation of activity data is executed (S14).

  Specifically, when the activity amount integration data is input from the data integration unit 140, the presentation unit 150 presents the activity amount integration data to the user. The timing at which the activity amount integrated data is presented to the user by the presentation unit 150 may be a timing when a certain amount of the activity amount integrated data is input, or a timing when an explicit instruction is given by the user. Also good. For example, the presentation of the activity amount integrated data by the presentation unit 150 can be visually recognized by the user using a screen or the like.

  In the present embodiment, it is assumed that the presentation unit 150 generates a time series transition of calorie consumption based on the activity amount integrated data and presents the generated time series transition of the calorie consumption using a graph or the like. To do. When the presentation of the activity amount data by the presentation unit 150 is completed, if there is no instruction for termination by the user (“No” in S15), the operation is shifted to S11. On the other hand, if there is a termination instruction from the user (“Yes” in S15), the sensor data processing is terminated (S16).

  The operation example of the data processing system 1 according to the present embodiment has been described above.

[1-4. Specific example of operation of data processing system 1]
Subsequently, a specific example of the operation of the data processing system 1 according to the present embodiment will be described. FIG. 6 is a diagram illustrating a specific example of the operation of the data processing system 1 according to the present embodiment. FIG. 6 shows an example in which the states of the first activity meter 110-1 and the second activity meter 110-2 carried by the user transition in time series.

  In the first time zone, it is assumed that the user carries both the first activity meter 110-1 and the second activity meter 110-2. In such a case, the activity detector 120 outputs activity meter selection instruction data indicating selection of the first activity meter 110-1 to the data integration unit 140. 1 is output (in FIG. 6, “activity integrated data” in the first time zone is indicated as “A”).

  In addition, since the conversion rule update instruction data is first output from the activity detection unit 120 in the time zone, the conversion rule data is updated. In FIG. 6, “conversion rule data based on the second activity data” is selected as “conversion rule data” until the middle of the first time period, but the conversion rule data is updated in the middle of the first time period. In this example, “conversion rule data based on second acceleration index data” is selected.

  In the second time zone, it is assumed that the user keeps the first activity meter 110-1 on the desk and carries only the second activity meter 110-2. In such a case, the activity detection unit 120 outputs activity meter selection instruction data indicating selection of the second activity meter 110-2 to the data integration unit 140. Second activity amount data using the “conversion rule data based on the second acceleration index data” is output (FIG. 6 shows that “activity amount integrated data” in the second time zone is “(second Acceleration index data) ”(shown as conversion data based on G)).

  Further, since the conversion rule update instruction data is not output from the activity detection unit 120, the conversion rule data is not updated. FIG. 6 shows an example in which “conversion rule data based on second acceleration index data” is selected as “conversion rule data” in the second time zone following the first time zone. .

  In the third time zone, it is assumed that the user leaves the second activity meter 110-2 on the desk and carries only the first activity meter 110-1. In such a case, the activity detector 120 outputs activity meter selection instruction data indicating selection of the first activity meter 110-1 to the data integration unit 140. 1 is output (in FIG. 6, “activity amount integrated data” in the third time zone is indicated as “(first activity amount data) C”).

  Further, since the conversion rule update instruction data is not output from the activity detection unit 120, the conversion rule data is not updated. FIG. 6 shows an example in which “conversion rule data based on second acceleration index data” is selected as “conversion rule data” in the third time zone, following the second time zone. ing.

  The specific example of the operation of the data processing system 1 according to the present embodiment has been described above.

[1-5. Hardware configuration example]
Subsequently, a hardware configuration example of the data processing apparatus according to the present embodiment will be described. FIG. 7 is a diagram illustrating a hardware configuration of the data processing apparatus according to the present embodiment.

  As shown in FIG. 7, the data processing apparatus includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, a host bus 904, a bridge 905, and an external bus. 906, an interface 907, an input device 908, an output device 909, a storage device 910, and a communication device 911.

  The CPU 901 functions as an arithmetic processing device and a control device, and controls the overall operation in the data processing device according to various programs. Further, the CPU 901 may be a microprocessor. The ROM 902 stores programs used by the CPU 901, calculation parameters, and the like. The RAM 903 temporarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution, and the like. These are connected to each other by a host bus 904 including a CPU bus or the like.

  The host bus 904 is connected to an external bus 906 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 905. Note that the host bus 904, the bridge 905, and the external bus 906 are not necessarily configured separately, and these functions may be mounted on one bus.

  The input device 908 includes an input means for inputting information such as a mouse, a keyboard, a touch panel, a button, a microphone, a switch, and a lever, and an input control circuit that generates an input signal based on the input by the user and outputs the input signal to the CPU 901. Etc. A user who operates the data processing apparatus can input various data and instruct a processing operation to the data processing apparatus by operating the input device 908.

  The output device 909 includes, for example, a CRT (Cathode Ray Tube) display device, a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Diode) device, a display device such as a lamp, and an audio output device such as a speaker.

  The storage device 910 is a device for storing data. The storage device 910 may include a storage medium, a recording device that records data on the storage medium, a reading device that reads data from the storage medium, a deletion device that deletes data recorded on the storage medium, and the like. The storage device 910 is configured with, for example, an HDD (Hard Disk Drive). The storage device 910 drives a hard disk and stores programs executed by the CPU 901 and various data.

  The communication device 911 is a communication interface configured with, for example, a communication device for connecting to a network. Further, the communication device 911 may support either wireless communication or wired communication.

  Heretofore, the hardware configuration example of the data processing apparatus according to the present embodiment has been described.

[1-6. effect]
As described above, according to the data processing system 1 according to the present embodiment, the first acceleration index data acquired from the first activity meter 110-1 by the activity detection unit 120, or the second When the second acceleration index data acquired from the activity meter 110-2 does not match the activity pattern of a general person, the data integration unit 140 operates to discard the data of the activity meter. Therefore, even when one activity meter is not carried, only more accurate activity data can be recorded.

  Also, the first acceleration index data acquired from the first activity meter 110-1 and the second acceleration index data acquired from the second activity meter 110-2 by the activity detector 120. When both match the activity pattern of a general person, the conversion rule determination unit 130 estimates the relationship between the second activity amount data or the second acceleration index data and the first activity amount data, and the data integration unit 140 corrects the second activity amount data or the second acceleration index data based on this relationship. Therefore, even when one activity meter is not carried, it is possible to absorb the difference in the characteristics of the two types of activity meters and record the activity data with improved continuity.

  Furthermore, in the above correction, the estimation accuracy is higher among the relationship between the second activity amount data and the first activity amount data and the relationship between the second acceleration index data and the first activity amount data. Correction is made based on this relationship. Therefore, the accuracy of the goodwill attribute of the activity amount data can be improved.

  As described above, according to the data processing system 1 according to the present embodiment, even if the operation characteristics of the plurality of activity meters are different for each model, or any one of the plurality of activity meters. Even when non-portability occurs, it is possible to record more continuous activity data.

[1-7. Description of modification]
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field to which the present invention pertains can come up with various changes or modifications within the scope of the technical idea described in the claims. Of course, it is understood that these also belong to the technical scope of the present invention.

(1-7-1. Hardware configuration)
For example, in the above, the first activity meter 110-1 and the presentation unit 150 are built in a mobile terminal (for example, a smartphone), the second activity meter 110-2 is built in the wristband type activity meter, The case where the activity detection unit 120, the conversion rule determination unit 130, and the data integration unit 140 are built in a data processing device (for example, a server) has been mainly described. However, each functional block included in the data processing system 1 illustrated in FIG. 1 may be realized by any hardware configuration.

  For example, the activity detection unit 120, the conversion rule determination unit 130, and the data integration unit 140 may not all be built in the same data processing device (for example, a server), but a plurality of data processing devices (for example, servers). May be distributed. Alternatively, part or all of the activity detection unit 120, the conversion rule determination unit 130, and the data integration unit 140 may be incorporated in at least one of the mobile terminal and the wristband type activity meter. In addition, the presentation unit 150 may be incorporated in a communication terminal (for example, a PC (Personal Computer) or the like) different from the mobile terminal.

(1-7-2. Activity meter form)
The above has mainly described the case where the center data is acquired from each of the first activity meter 110-1 and the second activity meter 110-2. However, the number of activity meters is not limited to two. For example, the number of activity meters may be three or more. Even if the number of activity meters is three or more, the same effect as in the case where the number of activity meters is two can be enjoyed.

(1-7-3. Activity data)
In the above, each of the first activity data acquired from the first activity meter 110-1 and the second activity data acquired from the second activity meter 110-2 is calorie consumption. The case was mainly explained. However, each of the first activity amount data and the second activity amount data is not limited to the calorie consumption.

  For example, each of the first activity amount data and the second activity amount data may include data related to the physical activity of the user. For example, the data related to the physical activity of the user may include at least one of the number of steps, medium intensity activity time, and exercise intensity (for example, exercise intensity based on oxygen intake or heart rate). Further, each of the first activity amount data and the second activity amount data may include data related to other than the physical activity of the user (for example, data related to life activity), and includes conversation amount, meal amount, sleep amount, and stress level. At least one of the above may be included.

(1-7-4. Acceleration index data)
In the above, each of the first acceleration index data acquired from the first active mass meter 110-1 and the second acceleration index data acquired from the second active mass meter 110-2 is an acceleration variance value. Mainly explained in some cases. However, each of the first acceleration index data and the second acceleration index data is not limited to the acceleration dispersion value.

  For example, when the first activity amount data is final data generated based on detection (for example, detection of acceleration) by the first activity meter 110-1, the first acceleration index data is Any intermediate data (for example, a frequency component (fundamental frequency) of the acceleration waveform) corresponding to the data generated before the final data may be used. Similarly, when the second activity amount data is final data generated based on detection (for example, acceleration detection) by the second activity meter 110-2, the second acceleration index data is Any intermediate data (for example, a frequency component (fundamental frequency) of the acceleration waveform) corresponding to data generated in the previous stage of the final data may be used.

(1-7-5. Activity detection method)
In the above description, the case where the activity detection unit 120 detects whether or not the first activity amount data is linked to the activity of the user based on the first acceleration index data has been mainly described. However, when the first activity meter 110-1 has sensing means other than the acceleration sensor, the activity detection unit 120 further determines that the first activity data is based on the data detected by the sensing means. It may be detected whether or not it is linked to the activity.

  For example, when the first activity meter 110-1 is equipped with sensing means for measuring a heart rate or skin temperature, the activity detection unit 120 is further based on the data detected by the sensing means. It may be detected whether or not one activity amount data is linked to the activity of the user. Alternatively, when it is possible to input that the activity is being performed to the first activity meter 110-1, the activity detection unit 120 determines whether the first activity data is the user's It may be detected whether or not the activity is linked.

  Similarly, in the above, the activity detection unit 120 detects whether each of the second activity amount data and the second acceleration index data is linked to the activity of the user based on the second acceleration index data. Mainly explained when to do. However, when the second activity meter 110-2 has sensing means other than the acceleration sensor, the activity detection unit 120 further determines the second activity amount data and the second activity data based on the data detected by the sensing means. It may be detected whether each of the acceleration index data is linked to the activity of the user.

  Further, even when the activity detection unit 120 detects the linkage with the user's activity from both the first acceleration index data and the second acceleration index data, the activity detection unit 120 and the second acceleration index data Whether the first acceleration index data and the second acceleration index data are not similar to each other in the time series. The update instruction data may not be output. If the conversion rule update instruction data is not output from the activity detection unit 120 to the conversion rule determination unit 130, the conversion rule determination unit 130 does not update the conversion rule data (no relationship estimation is performed). become).

  This is because when the user carries both the first active mass meter 110-1 and the second active mass meter 110-2, the first acceleration index data and the second acceleration index data are different from each other. This is because it should be similar to the series (that is, when the first acceleration index data and the second acceleration index data are not similar to the time series, the user can use the first activity meter 110-1 and the second activity meter 110-2. This is because it is considered that at least one of the activity meter 110-2 is not carried. The determination of whether or not they are similar is not performed between the first acceleration index data and the second acceleration index data, but may be performed between other data (for example, between activity data and acceleration data). May be performed between each other).

  Moreover, when the sensing means for authenticating a user is mounted in the 1st activity meter 110-1, the activity detection part 120 is a user based on the characteristic of the data acquired from this sensing means. And whether the first activity amount data is linked to the activity of the user may be detected according to whether or not the user has been successfully authenticated. Similarly, when the sensing unit for authenticating the user is mounted on the second activity meter 110-2, the activity detection unit 120 uses the data based on the characteristics of the data acquired from the sensing unit. The user may be authenticated, and whether the second activity amount data and the second acceleration index data are linked to the user's activity may be detected according to whether the user has been successfully authenticated. .

  For example, the data detected by the sensing means may be acceleration detected by an acceleration sensor built in the first activity meter 110-1 (or the second activity meter 110-2). Alternatively, if the first activity meter 110-1 (or the second activity meter 110-2) is equipped with other sensors (for example, a heart rate sensor, a sweat sensor, an odor sensor, etc.), sensing is performed. The data detected by the means may be a heart rate detected by a heart rate sensor, a sweat component detected by a sweat sensor, or a body odor component detected by an odor sensor. May be.

(1-7-6. Conversion rules)
In the above description, the case has been mainly described in which the conversion rule determining unit 130 adopts a conversion rule with a small estimation error among the two types of conversion rules and configures the conversion rule data such that the conversion rule data is applied weekly. However, the conversion rule determining unit 130 may use only one of the two types of conversion rules fixedly. When only one type of conversion rule is used in a fixed manner, there is a possibility of a reduction in estimation error compared to the case where a conversion rule with a small estimation error is adopted from the two types of conversion rules. The amount can be reduced.

  In the above description, the case where the conversion rule determining unit 130 generates conversion rule data for converting the second activity amount data so as to match the first activity amount data has been mainly described. However, the conversion rule determination unit 130 may generate conversion rule data for converting the second activity amount data so as to match the first activity amount data.

DESCRIPTION OF SYMBOLS 1 Data processing system 110-1 1st activity meter 110-2 2nd activity meter 120 Activity detection part 130 Conversion rule determination part 131-1 1st conversion rule estimation part 131-2 2nd conversion rule estimation Unit 132 conversion rule update unit 140 data integration unit 150 presentation unit

Claims (15)

Detect data linkage information indicating whether each of the first sensor data obtained from the first sensor and the second sensor data obtained from the second sensor is linked to the activity of the first user. An activity detector to perform,
Data integration for generating data to be output based on the relationship between the first sensor data and the second sensor data and the second sensor data when the data linkage information satisfies a predetermined condition And
A data processing apparatus. The data integration unit
When the first sensor data is not linked to the activity of the first user, the output target data is generated based on the relationship and the second sensor data.
The data processing apparatus according to claim 1. The data integration unit
When the first sensor data is linked to the activity of the first user, the output target data is generated based on the first sensor data.
The data processing apparatus according to claim 1. The activity detection unit determines whether the first sensor data is an activity of the first user according to whether or not the predetermined first data acquired from the first sensor is within a predetermined range. Detect whether it is linked,
The data processing apparatus according to claim 1. The activity detection unit authenticates the first user based on data acquired from sensing means that is the same as or different from the first sensor, and authenticates the first user. Detecting whether the first sensor data is linked to the activity of the first user, depending on whether it is successful;
The data processing apparatus according to claim 1. The first sensor data includes data relating to physical activity or life activity of the first user.
The data processing apparatus according to claim 1. The data processing device includes:
When it is detected that the third sensor data acquired from the third sensor and the fourth sensor data acquired from the fourth sensor are linked to the activity of the second user, the relationship A relationship estimation unit for estimating sex,
The data processing apparatus according to claim 1. The relationship estimation unit
When it is detected that each of the third sensor data and the fourth sensor data is linked to the activity of the second user, a first time acquired from the third sensor in time series Estimating the relationship based on series data and second time series data acquired in time series from the fourth sensor;
The data processing apparatus according to claim 7. The relationship estimation unit
While calculating the 1st error by the 1st relation of the 1st generation data group generated based on detection by the 1st time series data and the 4th sensor, the 1st time series data And calculating a second error due to a second relationship between the first generation data group and the second generation data group according to the data generated in the previous stage of the first generation data group,
Selecting one of the first relationship and the second relationship as the relationship according to the magnitude relationship between the first error and the second error;
The data processing apparatus according to claim 8. The first generation data group includes a final data group generated based on detection by the fourth sensor,
The second generation data group includes an intermediate data group corresponding to data generated in a previous stage of the final data group.
The data processing apparatus according to claim 9. The first time series data includes a data group related to physical activity or life activity of the second user.
The data processing apparatus according to claim 8. The second time-series data includes at least one of a final data group generated based on detection by the fourth sensor and an intermediate data group corresponding to data generated in a previous stage of the final data group. Including,
The data processing apparatus according to claim 8. The relationship estimation unit
Even if it is detected that each of the third sensor data and the fourth sensor data is linked to the activity of the second user, the third sensor data and the fourth sensor data If the sensor data is not similar, the relationship is not estimated.
The data processing apparatus according to claim 7. Detect data linkage information indicating whether each of the first sensor data obtained from the first sensor and the second sensor data obtained from the second sensor is linked to the activity of the first user. To do
Generating data to be output based on the relationship between the first sensor data and the second sensor data and the second sensor data when the data linkage information satisfies a predetermined condition; ,
Including a data processing method. Computer
Detect data linkage information indicating whether each of the first sensor data obtained from the first sensor and the second sensor data obtained from the second sensor is linked to the activity of the first user. An activity detector to perform,
Data integration for generating data to be output based on the relationship between the first sensor data and the second sensor data and the second sensor data when the data linkage information satisfies a predetermined condition And
A program for functioning as a data processing apparatus.

Images