Information processing device, information processing method and storage medium

Abstract

The present invention provides an information processing device, an information processing method and a storage medium for determining the presence or absence of noise contained in motion data related to motion. The information processing device (100) comprises: an acquisition unit (12) for acquiring motion data from a detection unit (30) for detecting motion data related to a user's motion; and a determination unit (13) for determining the presence or absence of noise caused by collision based on data indicating acceleration in a specific direction contained in the motion data acquired by the acquisition unit (12).

Description

[0001] References to related applications

[0002] This application claims priority based on patent application No. 2020-113791 filed in Japan on July 1, 2020, and all the contents of the basic application are incorporated into this application. Technical Field

[0003] The present disclosure relates to an information processing device, an information processing method, and a storage medium. Background Art

[0004] Japanese Patent Publication No. 2016-34479

[0005] For example, Japanese Patent Application Publication No. 2016-34479 discloses a technology in which a device attached to the waist of a user detects the timing of a user leaving the ground and landing on the ground with high accuracy based on the value of acceleration. Summary of the invention

[0006] The present invention provides an information processing device, comprising a processor, wherein the processor executes: obtaining motion data from a sensor that detects motion data related to a user's motion, and determining the presence or absence of noise caused by a collision based on data representing acceleration in a specific direction contained in the obtained motion data. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 This is a schematic diagram showing a state in which the information processing device according to the embodiment is equipped to a user.

[0008] Figure 2 This is a block diagram showing the structure of an information processing device according to an embodiment.

[0009] Figure 3 This is a graph showing the time change of acceleration in the Y-axis direction during running.

[0010] Figure 4 This is a scatter diagram based on the feature quantity calculated from the acceleration in the Y-axis direction.

[0011] Figure 5 This is a graph showing the time change of the acceleration in the Z-axis direction during running.

[0012] Figure 6 This is a scatter diagram based on the feature quantity calculated from the acceleration in the Z-axis direction.

[0013] Figure 7 This is a flowchart of the index calculation process involved in the embodiment.

[0014] Figure 8This is a flowchart of the indicator calculation process involved in the implementation mode.

[0015] Fig. 9 This is a flowchart of the first determination process according to the embodiment.

[0016] Fig.10 This is a flowchart of the second determination process according to the embodiment. DETAILED DESCRIPTION

[0017] The information processing device of the embodiment is described with reference to the accompanying drawings. In addition, the same reference numerals are marked on the same or corresponding parts in the figures. The information processing device involved in the embodiment is a device as follows: it is equipped on the waist of the user, obtains data related to the user's movement (motion data), and calculates indicators related to the user's movement (such as the size of the body's up and down movement, the rotation angle of the waist, etc.) based on the obtained motion data.

[0018] like Figure 1 As shown in FIG. 1 , the information processing device 100 is mounted on the user's waist, and the acceleration sensor detects the accelerations in the up-down direction (along the Z-axis), the front-back direction (along the Y-axis), and the left-right direction (along the X-axis) at the mounted part, and calculates the index related to the user's movement based on the acceleration values. Figure 1 In the case where the storage bag 201 is worn around the waist with the storage bag belt 202 as shown in the figure. In this case, for example, when the user is doing sports such as running or skipping, the storage bag 201 hits the information processing device 100 at the moment when the foot lands, and the acceleration sensor of the information processing device 100 detects a value affected by the collision of the storage bag 201. In addition, the value affected by the collision of the storage bag 201 contains noise caused by the impact, and there is a possibility that it is difficult to correctly calculate the index related to the user's exercise. In other words, the value of the acceleration sensor in the state without the collision of the storage bag 201 can accurately calculate the index related to the user's exercise.

[0019] like Figure 2 As shown, the information processing device 100 includes a control unit 10 , a storage unit 20 , a detection unit 30 , a communication unit 40 , and a UI unit 50 .

[0020] The control unit 10 is composed of a processor such as a CPU (Central Processing Unit) and functions as a timing unit 11, an acquisition unit 12, a determination unit 13, and a calculation unit 14 by executing a program stored in the storage unit 20, and the details of these will be described later.

[0021] The storage unit 20 stores programs executed by the control unit 10, calculated data, data detected by the detection unit 30, etc. The storage unit 20 can include RAM (Random Access Memory), ROM (Read Only Memory), flash memory, etc., but is not limited thereto. In addition, the storage unit 20 can be provided inside the control unit 10.

[0022] The detection unit 30 includes an acceleration sensor 31 for detecting acceleration, an angular velocity sensor 32 for detecting angular velocity, and other sensors for obtaining motion data required for calculating an index related to the user's motion. The angular velocity sensor 32 is, for example, a gyro sensor, but is not limited thereto. In addition, the detection unit 30 only needs to include the acceleration sensor 31, and may include, for example, the angular velocity sensor 32. The detection unit 30 functions as a detection unit.

[0023] The communication unit 40 is a communication interface that outputs the index and other data calculated by the control unit 10 to the outside (e.g., a smart watch, a smartphone, etc.). The communication unit 40 can include, for example, a wireless communication interface or a wired communication interface, but is not limited thereto. The information processing device 100 can send the calculated index related to the user's exercise to an external device such as a smart watch via the communication unit 40.

[0024] The UI unit 50 includes an output device (e.g., a display panel) and an input device (e.g., a touch panel integrated with the display panel). The UI unit 50 displays the index related to the user's exercise calculated by the information processing device 100, or accepts the user's operation. In addition, the UI unit 50 is not limited to the touch panel, and for example, a button switch may be included as an input device, and a speaker or an LED (Light Emitting Diode) may be included as an output device. The UI unit 50 functions as a notification unit.

[0025] The timing unit 11 of the control unit 10 measures time. The time measured by the timing unit 11 is associated with each detection value (acceleration, angular velocity, etc.) detected by the detection unit 30. Therefore, the control unit 10 can obtain each detection value detected by the detection unit 30 as time series data in which the detected time is associated.

[0026] The acquisition unit 12 acquires motion data related to the user's motion, such as acceleration and angular velocity, detected by the detection unit 30. The time measured by the timing unit 11 is associated with each motion data. Therefore, the motion data is acquired as time series data. The acquisition unit 12 functions as an acquisition unit.

[0027] The determination unit 13 determines the presence or absence of an object (storage bag 201, etc.) that has collided with the detection unit 30 (the presence or absence of noise caused by the collision) based on the data indicating the acceleration of the axis along a specific direction (e.g., the direction of gravity) included in the motion data acquired by the acquisition unit 12. How the determination unit 13 performs this determination will be described later. The determination unit 13 functions as a determination unit. In addition, the collision with the "detection unit 30" here includes the situation where the object collides with a device having the detection unit 30 (e.g., the information processing device 100).

[0028] The calculation unit 14 analyzes the motion data obtained by the acquisition unit 12 to calculate an index related to the user's motion (for example, the size of the up and down movement of the body, the rotation angle of the waist, etc.). The calculation unit 14 functions as a calculation unit. In addition, the calculation unit 14 changes the calculation method of the index according to the presence or absence of an object (storage bag 201, etc.) determined by the determination unit 13 (the presence or absence of noise). That is, in the case where there is no object colliding with the detection unit 30 (in the case of no noise), the calculation unit 14 calculates the index using the usual calculation method. However, in the case where there is an object colliding with the detection unit 30 (in the case of noise), the calculation unit 14 can change the calculation method of the index so that the motion data affected by the collision of the object is masked, or the contribution rate to the calculation of the index is reduced to calculate the index.

[0029] In addition, the calculation unit 14 can collect a large amount of motion data when calculating the index, perform deep learning, and use the result of deep learning to calculate the index. In this case, a large amount of learning data when there is no object (storage bag 201, etc.) colliding with the detection unit 30 (no noise) and learning data when there is an object (storage bag 201, etc.) colliding with the detection unit 30 (noise) are respectively learned to perform deep learning.

[0030] By changing the calculation method of the indicator according to the presence or absence of an object determined by the determination unit 13 (the presence or absence of noise), the information processing device 100 can calculate the indicator related to the user's movement with relatively high accuracy regardless of whether there is an object colliding (interfering) with the detection unit 30 (whether the value of the motion data obtained by the detection unit 30 (acceleration sensor 31, etc.) exists or not).

[0031] Next, a mechanism for the determination unit 13 to determine the presence or absence of an object (such as the storage bag 201 ) that collides with the detection unit 30 (the presence or absence of noise) will be described.

[0032] If the user Figure 1When the user performs running or other exercises while the information processing device 100 (sensor device) and the storage bag 201 (object) are both mounted on the waist as shown in the figure, the storage bag 201 collides with the information processing device 100 from behind every time the foot lands. And, due to this collision, an impact from the back to the front is applied to the direction in front of the user (Y-axis direction), so if the back of the user is set to a positive value, the absolute value of the negative value of the acceleration in the Y-axis direction acquired by the acquisition unit 12 becomes larger.

[0033] In addition, when running, every time the foot lands, braking is applied and acceleration is generated in the Y-axis direction. Every time the foot pushes off, acceleration is applied and acceleration is generated in the Y-axis direction. Therefore, if the acceleration in the Y-axis direction is represented as a graph along the time series, it will be as follows: Figure 3 As shown in FIG. 1 , the graph repeats a cycle of taking a positive maximum value at the time of landing and then taking a negative value due to the impact of the storage bag 201 and the pedaling of the foot each time the user lands. Among them, it is believed that the acceleration caused by the braking and pedaling of the foot when landing is almost unaffected by the presence or absence of the storage bag 201. Therefore, it is believed that the area of ​​the negative region of the graph increases due to the impact of the storage bag 201 only when the storage bag 201 is present.

[0034] In addition, by analyzing the acceleration in this way, the length of one cycle of exercise (for example, the time from when one foot pushes off to when the other foot pushes off during running) can be calculated.

[0035] Here, in order to easily grasp the change in acceleration caused by the impact of landing, the timing when the acceleration reaches the maximum value within one cycle of the movement is regarded as the timing of landing, and the data representing the acceleration in the time width of the first reference time Wy (for example, a constant value of 0.02 seconds to 0.1 seconds) from this time is obtained. Figure 3 The area of ​​the negative area 301 is the area of ​​the shaded area by the oblique lines shown in FIG. 2 (the integral of the negative area). When the storage bag 201 is present, it is considered that the area of ​​the negative area 301 becomes larger (since it is a negative area, the value of the integral becomes smaller). In addition, as the first reference time Wy, a constant value such as the above may be used, or a value obtained by dividing the time of one cycle by the first reference number (for example, a constant value of 3 to 8) may be used.

[0036] However, since the value of the integral of the negative region 301 varies depending on the user's running posture (running style), the standard deviation is used as described below. If there is no storage bag 201, it is considered that the value of the acceleration of the Y axis becomes a relatively stable value, but if there is a storage bag 201, it is considered that the acceleration of the Y axis becomes an unstable value due to its impact. And, if the value is unstable, the value of the standard deviation becomes larger. That is, the larger the unstable impact (such as the impact caused by the storage bag 201) with a larger standard deviation, the larger the area of ​​the negative region, and conversely, the smaller the monotonous impact (such as the impact caused by falling without the storage bag 201) with a smaller standard deviation, the smaller the area of ​​the negative region.

[0037] Therefore, regarding the acceleration value in the Y-axis direction, the relationship between the standard deviation and the integral of the negative area can be utilized. When the area of ​​the negative area is relatively large relative to a certain standard deviation (since it is a negative area, the integral value is small), it is determined that there is a storage bag 201 (noise).

[0038] The information processing device 100 is mounted on the waist. When the storage bag 201 is mounted on the waist (with the storage bag 201) and when it is not mounted (without the storage bag 201), experiments are conducted to obtain the value of acceleration in the Y-axis direction. The standard deviation of the data representing the acceleration obtained at this time and the integral of the negative area are formed into a scatter diagram. Figure 4 In Figure 4 In the example, "○" indicates the data of the case where the storage bag 201 is present, and "×" indicates the data of the case where the storage bag 201 is not present. Such a large amount of data is used as learning data, and a classifier (first classifier) ​​such as a support vector machine (SVM) is trained, and the learned classifier is used to determine the presence or absence of the storage bag 201. By using the learned classifier (first classifier), the determination unit 13 can, for example, classify the presence of the storage bag 201 in the Figure 4 The data on the upper right side of the dotted line 302 shown is determined as “no storage bag”, and the data on the lower left side of the dotted line 302 is determined as “there is a storage bag”.

[0039] Back to Figure 1 Whenever the foot lands during running, the storage bag 201 collides with the information processing device 100 from behind. However, the acceleration in the gravity direction (Z-axis direction) acquired by the acquisition unit 12 becomes unstable due to the collision. If the value becomes unstable, the standard deviation becomes larger. In addition, when running, a large acceleration from bottom to top is generated at the timing of the foot landing. During the period when the body is naturally falling before landing, the influence of the gravity acceleration is offset, and the acceleration becomes a value approximately close to 0.

[0040] Therefore, if the vertical upward direction is set to a positive value, and the acceleration in the Z-axis direction is represented as a graph along the time series, then Figure 5 As shown in FIG. 1 , the acceleration takes a positive maximum value when the impact from the bottom is received at the time of landing. Also, before and after landing, the graph shows a cycle in which the impact of the storage bag 201 (for example, the storage bag 201 collides with the information processing device 100 from above) is repeated every time the storage bag 201 lands, and the acceleration takes an unstable small value.

[0041] Regarding the Z axis, in order to grasp the change in acceleration caused by the impact of landing, the timing with the maximum value within one cycle of motion is regarded as the timing of landing, and the data representing the acceleration in the time range of the positive and negative second reference time Wz (for example, a constant value of 0.05 seconds to 0.2 seconds) from this time is calculated as the standard deviation. In the case of the storage bag 201, it is considered that the standard deviation becomes larger because the acceleration becomes an unstable value. In addition, as the second reference time Wz, a constant value such as the above can be used, or a value obtained by dividing the time of one cycle by the second reference number (for example, a constant value of 2 to 7) can be used.

[0042] The standard deviation varies according to the running style of the user, and as described below, the central value is used. As for the acceleration in the Z-axis direction, if the storage bag 201 collides with the information processing device 100, it is often impacted from top to bottom (becoming a negative acceleration), so in the ±Wz time range, there are many small values ​​caused by impacts other than the ground impact, and the central value becomes smaller. On the contrary, in the case where there is no impact of the storage bag 201, the proportion of the ground impact in the ±Wz time range becomes larger (in the case of the maximum acceleration in one cycle), and the central value becomes larger.

[0043] Therefore, regarding the value of the acceleration in the Z-axis direction, the relationship between the standard deviation and the median value is used, and when the standard deviation is relatively large with respect to a certain median value, it is determined that the storage bag 201 exists.

[0044] The information processing device 100 is equipped on the waist. Experiments are conducted to obtain the acceleration value in the Z-axis direction in the case where the storage bag 201 is equipped on the waist (with the storage bag 201) and the case where the storage bag 201 is not equipped (without the storage bag 201). The standard deviation and the central value of the acceleration data obtained at this time are made into a scatter diagram and are plotted on the graph. Figure 6 Shown. Figure 6In the example, "○" indicates the data of the case where the storage bag 201 is present, and "×" indicates the data of the case where the storage bag 201 is not present. Such a large amount of data is used as learning data, for example, a classifier (second classifier) ​​such as a support vector machine is trained, and the learned classifier can be used to determine the presence or absence of the storage bag 201. By using the learned classifier (second classifier), the determination unit 13 can, for example, classify the presence of the storage bag 201. Figure 6 The data on the upper right side of the dotted line 303 shown is determined as "there is a storage bag", and the data on the lower left side of the dotted line 303 is determined as "there is no storage bag".

[0045] Next, refer to Figure 7 The following describes the index calculation process of the control unit 10. When the user instructs to start the index calculation process, the information processing device 100 starts the index calculation process.

[0046] First, the control unit 10 determines whether the user's exercise is finished (step S101). For this determination, for example, if only the values ​​of acceleration and angular velocity that are small enough to indicate that no exercise is performed are detected from the detection unit 30 within a given time (e.g., 3 seconds), the control unit 10 determines that the exercise is finished. In addition, when the user instructs the UI unit 50 to stop the index calculation process, the control unit 10 also determines that the exercise is finished.

[0047] If the control unit 10 determines that the user's exercise is finished (step S101 "Yes"), the index calculation process is terminated. If it is determined that the user's exercise is not finished (step S101 "No"), the acquisition unit 12 acquires data indicating the acceleration detected by the acceleration sensor 31 and stores it in the storage unit 20 together with the time measured by the timing unit 11 (the timing when the data is detected) (step S102). Step S102 is also called an acquisition step.

[0048] Then, the calculation unit 14 analyzes the data accumulated in the storage unit 20 so far, and determines whether the data of one cycle of exercise has been obtained (step S103). If the data of one cycle has not been obtained (step S103 "No"), the process returns to step S102. If the data of one cycle has been obtained (step S103 "Yes"), the index calculation process described later is performed (step S104), and the process returns to step S102.

[0049] Next, refer to Figure 8 The index calculation process performed in step S104 is described below. First, the determination unit 13 performs the first determination process described later (step S201). Then, in the first determination process, it is determined whether the storage bag 201 (object) is present (noise is present or absent) (step S202).

[0050] If it is determined that the storage bag 201 is present (noise is present) (step S202 "Yes"), the calculation unit 14 adds the equipment of the storage bag 201 (set to be noisy) to calculate the index related to the user's movement (step S203), and the index calculation process ends. If it is determined that there is no storage bag 201 (no noise) in the first determination process (step S202 "No"), the determination unit 13 performs the second determination process described later (step S204). Then, in the second determination process, it is determined whether there is a storage bag 201 (object) (whether there is noise or not) (step S205).

[0051] If it is determined that the storage bag 201 is present (noise is present) (step S205 "Yes"), the process proceeds to step S203. If it is determined that the storage bag 201 is not present (no noise is present) (step S205 "No"), the calculation unit 14 calculates the index related to the user's exercise without adding the equipment of the storage bag 201 (assuming no noise) (step S206), and the index calculation process ends. In addition, step S201 and step S204 are also referred to as determination steps.

[0052] Next, refer to Fig. 9 First, the determination unit 13 refers to the data indicating the acceleration of the Y axis stored in the storage unit 20 and obtains the timing T1 at which the maximum value is detected in the most recent cycle as the landing timing (step S301).

[0053] Then, the determination unit 13 calculates the standard deviation stdy of the data set (first data group) near the landing (the first time span from the landing timing T1 to the landing timing T1+the first reference time Wy) from the data (step S302). Next, the determination unit 13 calculates the integral sumy of the negative area (the area in the direction in front of the user) near the landing (the first time span from the landing timing T1) from the data (step S303). The integral sumy is calculated by, for example, comparing the integral sumy with the Figure 3 The portion corresponding to the negative region 301 shown is integrated to calculate.

[0054] Then, the determination unit 13 determines the presence or absence of the storage bag 201 (object) (the presence or absence of noise) using a classifier such as a support vector machine learned in advance using the standard deviation stdy and the integral sumy as feature quantities (step S304), and ends the first determination process.

[0055] Next, refer to Fig.10 The second determination process executed in step S204 will be described. First, the determination unit 13 refers to the data indicating the acceleration of the Z axis stored in the storage unit 20, and obtains the timing T2 at which the maximum value is detected in the most recent cycle as the landing timing (step S401).

[0056] Then, the determination unit 13 calculates the standard deviation stdz of the set of data (second data group) near the landing (the second time span from before the second reference time Wz of the landing timing T2 to after the second reference time Wz) from the data (step S402). Next, the determination unit 13 calculates the median value medz of the set of data near the landing (the second time span centered on the landing timing T2) from the data (step S403).

[0057] Then, the determination unit 13 determines the presence or absence of the storage bag 201 (object) (the presence or absence of noise) using a classifier such as a support vector machine learned in advance using the standard deviation stdz and the median medz as feature quantities (step S404), and ends the second determination process.

[0058] In addition, in step S203 of the index calculation process, the user may be notified of the presence of the storage bag 201 (noise) through the UI unit 50, etc. Through this notification, the user can perceive that the storage bag 201 has collided with the information processing device 100, and can take measures such as changing the position of the storage bag 201 or taking off the storage bag 201 and continuing to run or other exercises.

[0059] For example, in the publication No. 2016-34479 of the patent application in Japan, the following technology is disclosed: in a device equipped on the user's waist, the timing of the user's departure from the ground and landing is detected with high accuracy based on the value of acceleration. Such a sensor device is usually equipped at the user's waist. On the other hand, in order to carry small objects, the user sometimes wraps a storage bag around the waist while running. Although the sensor device and the storage bag can be equipped at different positions of the waist (for example, left and right) so that they do not interfere with each other, in actual running, in order not to get in the way, both are often equipped at the part directly behind the waist. In this case, during running, the storage bag collides with the sensor device, and due to the influence of the collision, it is confirmed that some of the running index values ​​detected in the sensor device become unexpected values. It is also believed that the collision with the sensor device is part of the noise that prevents the correct determination of the running index value.

[0060] However, through the index calculation process described above, the information processing device 100 of the embodiment can determine the presence or absence of an object (storage bag 201, etc.) interfering with the detection unit 30 (the presence or absence of noise contained in the motion data obtained by the detection unit 30 (acceleration sensor 31, etc.)). Then, the information processing device 100 can calculate the index by adding the presence or absence of the object (the presence or absence of noise).

[0061] In the above-mentioned embodiment, running is assumed as the exercise performed by the user, but the type of exercise is not limited to running. For example, this embodiment can be applied to any exercise in which the user periodically performs the action of landing the feet, such as walking or rope skipping.

[0062] In addition, the information processing device 100 is assumed to be equipped on the user's waist, but the installation location is not limited to the waist, and it can also be equipped on the user's neck, wrist, ankle, etc. Even if it is equipped on a part of the body other than the user's waist, the information processing device 100 can obtain data related to the user's movement. In addition, even if it is equipped on a part of the body other than the user's waist, the information processing device 100 can determine the presence or absence of an object that collides with the detection unit 30 (the presence or absence of noise contained in the motion data obtained by the detection unit 30 (acceleration sensor 31, etc.) based on the data representing acceleration contained in the motion data obtained by the acquisition unit 12.

[0063] In addition, the storage bag 201 is assumed to be equipped to the user in a state where the storage bag belt 202 is wrapped around the waist, but the storage bag 201 is not limited to the waist, and the storage bag 201 can also be equipped in a state where the storage bag belt 202 is hung diagonally from the user's shoulder. In this case, there is also a possibility that the storage bag 201 collides with the information processing device 100 due to the user's movement, and the information processing device 100 can determine the presence or absence of an object that collides with the detection unit 30 based on the data indicating acceleration included in the motion data obtained by the acquisition unit 12 (the presence or absence of noise included in the motion data obtained by the detection unit 30 (acceleration sensor 31, etc.)).

[0064] (Variation Example)

[0065] The embodiments of the present invention have been described above, but these embodiments are examples, and the scope of application of the present invention is not limited thereto. That is, the embodiments of the present invention can be applied in various ways, and all of them are within the scope of the present invention.

[0066] For example, in the indicator calculation process ( Figure 8 ), the first determination process and the second determination process are performed, but the presence or absence of the storage bag 201 (object) (the presence or absence of noise) may be determined in only one of the two determination processes. For example, when the presence or absence of the storage bag 201 (the presence or absence of noise) is determined only in the first determination process, the second determination process does not need to be performed. Conversely, when the presence or absence of the storage bag 201 (the presence or absence of noise) is determined only in the second determination process, the first determination process does not need to be performed.

[0067] In addition, only when it is determined that "storage bag exists (noise exists)" in both of the two determination processes, it is assumed that storage bag 201 exists (noise exists), and storage bag 201 (noise) is added to perform index calculation. That is, if it is determined that "storage bag does not exist (no noise)" in any of the two determination processes, the index calculation may be performed without adding storage bag 201 (noise). In addition, the index calculation may be performed based on a value that is a weighted average of the results of the two determination processes.

[0068] In addition, in the first determination process ( Fig. 9 ), the timing T1 at which the maximum value of the data representing the acceleration of the Y axis is detected is set as the landing timing, and in the second determination processing ( Fig.10 ), the timing T2 at which the maximum value of the data representing the acceleration of the Z axis is detected is set as the landing timing, but the method for obtaining the landing timing is not limited to this. The landing timing may also be obtained based on any acceleration or angular velocity data that can be obtained in the detection unit 30 in either the first determination process or the second determination process.

[0069] In addition, in the first determination process, the value obtained by integrating the data representing the acceleration of the Y axis in the range of T1+Wy from the landing timing T1 with respect to the negative region (region in the front direction) is used as the feature amount, but as in the second determination process, the central value (the central value in the range of T1+Wy from the landing timing T1 of the data representing the acceleration of the Y axis) may be used as the feature amount. Conversely, in the second determination process, the value integrated with respect to the negative region may be used as the feature amount instead of the central value.

[0070] In addition, regarding the acceleration of the Y axis, the range of the data for obtaining the characteristic amount is set from the landing timing T1 to T1+Wy, and regarding the acceleration of the Z axis, the range of the data for obtaining the characteristic amount is set from the landing timing T2-Wz to T2+Wz, but it is not limited to this range. For example, the acceleration of the Y axis may be set from the landing timing T1-Wy to T1+Wy, and the acceleration of the Z axis may be set from the landing timing T2 to T2+Wz.

[0071] In addition, in the first determination process ( Fig. 9 ) and the second determination process ( Fig.10 ), when determining the presence or absence of the storage bag 201 (the presence or absence of noise), the standard deviation of the data representing the acceleration of the Y axis and the standard deviation of the data representing the acceleration of the Z axis are used respectively, but this is an example and the present invention is not limited thereto. As the value representing the deviation of the data, for example, the variance of the data representing the acceleration of the Y axis and the variance of the data representing the acceleration of the Z axis can be used.

[0072] In addition, the type of exercise (running, walking, rope skipping, etc.), the nature of the ground (concrete, soil, floor, rubber mat, etc.), the slope (flat ground, uphill, downhill, etc.), the user's habits (landing method, travel speed, etc.), etc. can also be analyzed, and the one with higher accuracy between the judgment based on the Y-axis acceleration and the judgment based on the Z-axis acceleration can be used, or the value of the two judgment results can be digitized (for example, using Figure 4 , Figure 6 The judgment is made by taking the weighted sum of the distances from the boundary line of the support vector machine in the scatter diagram as shown.

[0073] In addition, the detection unit 30 may be used as a component of the information processing device 100, and the information processing device 100 may obtain the detection value (sensor data) detected by the detection unit 30 in real time or after exercise from another device (sensor device) equipped with the detection unit 30 through wireless communication, etc., to perform index calculation processing. In this case, as long as the sensor device equipped with the detection unit 30 is equipped on the waist of the user, etc., there is no limitation on the location where the information processing device 100 without the detection unit 30 is kept.

[0074] In addition, the information processing device 100 has a communication interface, i.e., a communication unit 40, for outputting the calculated index and other data to the outside, but the present invention is not limited thereto. The information processing device 100 may also have an interface for detaching a storage medium, so that the storage medium stores data, and the calculated index and other data are provided to the external device by connecting the storage medium to the external device.

[0075] In the embodiment of the present invention, as an example of a processing method for determining the presence or absence of noise caused by collision, a processing method when the storage bag 201 collides with the information processing device 100 when the storage bag 201 is arranged on the waist with the storage bag belt 202 is described, but the present invention is not limited to this. For example, even if a backpack carried by the user, clothes worn by the user, a part of the body of a person equipped with the information processing device 100 and located around the user, an object flying from the surroundings of the user equipped with the information processing device 100, etc. collides with the information processing device 100, the present invention can be applied. In addition, even if the information processing device 100 equipped on the waist of the user collides with a part of the user's own body (for example, the back, waist, hand, etc.), the present invention can be applied. In addition, even if the information processing device 100 itself does not collide with anything, there is a possibility that the vibration when the storage bag collides with a part of the user's body (the back, waist, etc.) due to the impact of the user's landing is transmitted to the information processing device 100, and the present invention can be applied in this case.

[0076] In addition, each function of the information processing device 100 can also be implemented by a computer such as a general PC (Personal Computer). Specifically, in the above embodiment, it is described that the program of the index calculation process performed by the information processing device 100 is pre-stored in the ROM of the storage unit 20. However, it is also possible to store the program in a computer-readable recording medium such as a floppy disk, CD-ROM (Compact Disc Read Only Memory), DVD (Digital Versatile Disc), MO (Magneto-Optical Disc), memory card, USB (Universal Serial Bus) memory and distribute it, read the program into the computer and install it, so as to constitute a computer that can realize the above functions.

[0077] Furthermore, the program can be superimposed on a carrier wave and operated via a communication medium such as the Internet. For example, the program can be posted and published on a bulletin board (BBS: Bulletin Board System) on a communication network. And it is configured so that when the program is started, it can be executed in the same way as other application programs under the control of the OS (Operating System) to perform the above-mentioned processing.

[0078] Although preferred embodiments of the present invention have been described above, the present invention is not limited to the specific embodiments and is intended to include the inventions described in the claims and their equivalents.

Claims

1. An information processing device comprising a processor, characterized in that: The processor performs: obtaining the motion data from a sensor that detects motion data related to the user's motion, determining the presence or absence of noise caused by the collision based on data indicating acceleration in a specific direction, which is at least one of a direction in front of the user and a gravity direction, included in the acquired motion data; The processor performs at least any one of the following processes: Extracting data indicating acceleration in a direction in front of the user detected within a first time range including the landing timing of the user's movement, i.e., the landing timing, as a first data group, and determining the presence or absence of the noise based on an index indicating a deviation of the data of the first data group and a value obtained by integrating an area in the direction in front of the user in the first data group within the first time range; and Data indicating acceleration along the gravity direction detected in a second time width range including the landing timing are extracted as a second data group, and the presence or absence of the noise is determined based on an index indicating a deviation of the data of the second data group and a median value.

2. The information processing device according to claim 1, characterized in that The processor performs: The presence or absence of noise caused by collision of an object with the user or the sensor or noise caused by collision of the sensor with a part of the user's body is determined based on data indicating acceleration in the specific direction included in the acquired motion data.

3. The information processing device according to claim 1 or 2, characterized in that: The processor performs: The presence or absence of the noise is determined by at least one of the first classifier and the second classifier, wherein: In the first classifier, an index representing a deviation of the data of the first data group and a value obtained by integrating the area in the direction of the front front in the first data group within the range of the first time width are learned in advance as feature quantities; In the second classifier, an index indicating a deviation of the data of the second data group and a median value are learned in advance as feature quantities.

4. The information processing device according to claim 3, characterized in that: The classifier is a support vector machine based classifier.

5. The information processing device according to claim 1 or 2, characterized in that: The device including the sensor is mounted on the waist of the user.

6. The information processing device according to claim 1 or 2, characterized in that: The processor performs: Calculating an index related to the user's exercise based on the acquired exercise data, The calculation method of the index is changed according to the result of the determination of the presence or absence of the noise.

7. The information processing device according to claim 1 or 2, characterized in that: The information processing device further comprises: If the result of the determination of the presence or absence of the noise is that the noise is present, a notification unit notifies that the noise is present.

8. An information processing method, which is an information processing method in an information processing device, characterized in that: have: A step of acquiring the motion data from a sensor that detects motion data related to the user's motion; and a determination step of determining the presence or absence of noise caused by collision based on data indicating acceleration in a specific direction, which is at least one of a direction in front of the user and a gravity direction, included in the motion data acquired in the acquisition step, The determination step includes at least any one of the following steps: A step of extracting data indicating acceleration in a direction in front of the user detected within a first time range including the landing timing of the user's movement, i.e., the landing timing, as a first data group, and determining the presence or absence of the noise based on an index indicating a deviation of the data of the first data group and a value obtained by integrating an area in the direction in front of the user in the first data group within the first time range; and The step of extracting data indicating acceleration along the gravity direction detected in a second time width range including the landing timing as a second data group, and determining the presence or absence of the noise based on an index indicating a deviation of the data of the second data group and a median value.

9. A storage medium storing a program, wherein the program causes a processor of an information processing device to execute: A step of acquiring the motion data from a sensor that detects motion data related to the user's motion; and a determination step of determining the presence or absence of noise caused by collision based on data indicating acceleration in a specific direction, which is at least one of a direction in front of the user and a gravity direction, included in the motion data acquired in the acquisition step, The determination step includes at least any one of the following steps: A step of extracting data indicating acceleration in a direction in front of the front of the user detected within a first time range including the landing timing of the user's movement, i.e., the landing timing, as a first data group, and determining the presence or absence of the noise based on an index indicating a deviation of the data of the first data group and a value obtained by integrating an area in the direction in front of the front in the first data group within the first time range; and The step of extracting data indicating acceleration along the gravity direction detected in a second time width range including the landing timing as a second data group, and determining the presence or absence of the noise based on an index indicating a deviation of the data of the second data group and a median value.

Images