JP6034926B1 - Index output device, index output method, and computer program - Google Patents

Abstract

The present invention provides an index output device capable of facilitating the evaluation of effects due to attractions. An acquisition unit for acquiring biological information of a user and acceleration information related to a user's movement, and a change in the user's state with respect to the attraction of the attraction based on the acquired biological information and acceleration information. An index acquisition unit that acquires an index related to any of movement fluctuations, and an output unit 209 that outputs the acquired index. [Selection] Figure 1

Description

  The present invention relates to a human state estimation technique.

  Conventionally, a system has been proposed that can perform an effect in a haunted house in accordance with the degree of fear desired by a customer (see, for example, Patent Document 1). With such a system, the customer can experience an effect tailored to the degree of fear he desires.

JP 2008-86545 A

  However, in order to evaluate the effect of the production in accordance with the fear level, it is necessary to conduct a survey such as a questionnaire for customers who actually experienced it. In such a case, it takes time and effort to collect questionnaires and questionnaires. Therefore, there is a problem that the haunted house operator and director cannot easily evaluate the effect of the production. Such a problem is not limited to a haunted house, but is a problem common to all attractions that produce effects that affect the state of people.

  In view of the above circumstances, an object of the present invention is to provide a technique capable of facilitating the evaluation of effects due to the attraction of attractions.

  One aspect of the present invention is an acquisition unit that acquires user's biological information and acceleration information related to the user's movement, and the user's response to the attraction based on the acquired biological information and the acceleration information. An index output device comprising: an index acquisition unit that acquires an index related to either state fluctuation or user movement change; and an output unit that outputs the acquired index.

  One aspect of the present invention is the above-described index output device, the first feature quantity calculation unit that calculates a plurality of first feature quantities used to calculate the index obtained from the biological information, and the acceleration A second feature quantity calculation unit that calculates a plurality of second feature quantities used to calculate the index obtained from information, and the index acquisition unit includes the first feature quantity and the second feature quantity. Using either of the quantities, either the value related to the state of the user or the value related to the user's movement is acquired, and the index is acquired by normalizing the acquisition result.

  One aspect of the present invention is the above-described index output device, wherein the index is a momentary fear degree representing a degree when a person is released from being terrified, and the index acquisition unit includes: Using the first feature value and the second feature value, obtain a value related to the user's state and a value related to the user's movement, and obtain the instantaneous fear level by normalizing each obtained result and performing weighted averaging. To do.

  One aspect of the present invention is the above-described index output device, wherein the index further includes a degree of achievement indicating a degree of having enjoyed the effect, and the index acquisition unit uses the second feature amount, The achievement level is acquired by acquiring a value related to the user's movement and normalizing the acquisition result.

  One aspect of the present invention is the above-described index output device, wherein the index further includes a degree of security that represents a degree of relief that is released from anxiety and fear, and the index acquisition unit includes the first feature. A plurality of values related to the state of the user are acquired using the quantity, and the degree of security is acquired by normalizing each acquisition result and performing a weighted average.

  One aspect of the present invention is the above-described index output device, wherein the index further includes an anxiety level representing a degree of feeling anxiety or fear, and the index acquisition unit uses the first feature amount to The anxiety level is acquired by acquiring a plurality of values related to the user's state, normalizing each acquisition result, and performing a weighted average.

  One aspect of the present invention is the above-described index output device, wherein the index further includes a degree of enjoyment indicating a degree to which the attraction is enjoyed, and the index acquisition unit includes the instantaneous fear level, the achievement level, and the safety level. And the said enjoyment degree is acquired by performing predetermined calculation to an anxiety degree.

  One aspect of the present invention is an acquisition step of acquiring biological information of a user and acceleration information related to the user's movement, and the user's action on the attraction based on the acquired biological information and the acceleration information. An index output method comprising: an index acquisition step of acquiring an index related to any of a change in state and a change in movement of the user; and an output step of outputting the acquired index.

  One aspect of the present invention is an acquisition step of acquiring biological information of a user and acceleration information related to the user's movement, and the user's action on the attraction based on the acquired biological information and the acceleration information. It is a computer program for causing a computer to execute an index acquisition step of acquiring an index related to either state fluctuation or user movement fluctuation, and an output step of outputting the acquired index.

  According to the present invention, it is possible to easily evaluate the effect of the attraction effect.

It is a figure which shows the system configuration | structure of the parameter | index output system 100 in this invention. 4 is a flowchart showing a flow of processing of the index output device 20. 6 is a flowchart showing a flow of first feature value calculation processing by a first feature value calculation unit 205; 10 is a flowchart showing a flow of second feature value calculation processing by a second feature value calculation unit 206; It is a figure showing the fluctuation | variation of a heart rate and an example of the estimation result of a motion. 4 is a flowchart showing a flow of evaluation value calculation processing by the index output device 20. It is a figure which shows the specific example of the normalization table for chatter degree calculation. It is a figure which shows the specific example of the normalization table for achievement degree calculation. It is a figure which shows the specific example of the normalization table for comfort level calculation. It is a figure which shows the specific example of the normalization table for anxiety degree calculation.

Hereinafter, an embodiment of the present invention will be described with reference to the drawings.
(Outline)
The index output system in the present embodiment is a system that facilitates the evaluation of the effect of an attraction effect that produces an effect that affects a person's condition. Specifically, the index output system acquires and acquires an index related to any one of a change in a person's state and a change in a person's movement with respect to an effect using three-axis acceleration information related to the human biological information and the user's movement. The obtained index is output as the user's state result for the attraction effect. In the present embodiment, the user is an attraction user. By being configured in this way, an attraction operator and a director can evaluate the effect of the performance only by confirming the output index. Here, the attraction which produces the production which influences a person's state is a haunted house, a roller coaster, etc., for example. In the present embodiment, a haunted house will be described as an example of the attraction. Further, in the present embodiment, five indexes of the degree of chatter (instant fear), the degree of achievement, the degree of security, the degree of anxiety, and the degree of fun are used as indicators relating to any of the fluctuations in the state of the person and fluctuations in the movement of the person. . Hereinafter, each index will be described in detail.

The degree of chatter represents the degree of instantaneous fluctuation of the user's state when released from being in fear. More specifically, the degree of chatter is an index relating to fluctuations in the heart rate and changes in movement of the user when released from being driven by anxiety and fear. The degree of chattering is estimated from fluctuations in the heart rate that change from rising to falling, and in movements from fluctuations in the speed of movement in the haunted house.
The degree of achievement represents the degree to which the production of the haunted house was fully enjoyed.
The degree of security represents the degree of relief that has been released from anxiety and fear. More specifically, the degree of security is an index related to the magnitude of fluctuation in heart rate when released from anxiety and fear. The degree of relief is estimated from the downward trend of the heart rate and the downward trend.
The degree of anxiety represents the degree of anxiety or fear. The degree of anxiety is an index relating to the magnitude of fluctuation in heart rate when driven by anxiety or fear. The degree of anxiety is estimated from the degree of heart rate rise and the tendency to rise.
The degree of fun represents how much you enjoyed the haunted house. The degree of fun is calculated using the degree of chatter, the degree of achievement, the degree of security, and the degree of anxiety.
Hereinafter, a specific example will be described.

(Details)
FIG. 1 is a diagram showing a system configuration of an index output system 100 according to the present invention.
The index output system 100 includes a sensor terminal 10 and an index output device 20.
The sensor terminal 10 is a sensor that a user wears and uses. The sensor terminal 10 acquires the user's biological information and triaxial acceleration information. The biological information is, for example, values such as heart rate, cardiac action potential, body temperature, voice output level, and blood pressure.
The index output device 20 acquires each index based on the user's biological information and triaxial acceleration information acquired by the sensor terminal 10. In the following description, an example in which the index output device 20 calculates each index based on the user's biological information and triaxial acceleration information acquired by the sensor terminal 10 will be described.

Next, it is a schematic block diagram showing a functional configuration of the index output device 20.
The index output device 20 includes a CPU (Central Processing Unit), a memory, an auxiliary storage device, and the like connected by a bus, and executes an index output program. By executing the index output program, the index output device 20 includes an acquisition unit 201, an identification unit 202, a biological information storage unit 203, an acceleration information storage unit 204, a first feature quantity calculation unit 205, a second feature quantity calculation unit 206, and a table. It functions as a device including a storage unit 207, an index calculation unit 208, and an output unit 209. All or some of the functions of the index output device 20 may be realized using hardware such as an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA). . The index output program may be recorded on a computer-readable recording medium. The computer-readable recording medium is, for example, a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, or a storage device such as a hard disk built in the computer system. The index output program may be transmitted / received via a telecommunication line.

The acquisition unit 201 acquires user's biological information and triaxial acceleration information from the sensor terminal 10.
The identification unit 202 identifies the information acquired by the acquisition unit 201. Specifically, the identification unit 202 identifies whether the acquired information is biological information or triaxial acceleration information.
The biological information storage unit 203 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The biometric information storage unit 203 stores biometric information in chronological order.
The acceleration information storage unit 204 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The acceleration information storage unit 204 stores the triaxial acceleration information in chronological order.

The first feature amount calculation unit 205 reads the biological information stored in the biological information storage unit 203, and calculates a plurality of first feature amounts used to calculate each index obtained from the biological information. Specific examples of the first feature amount, RRI (RR Interval), HR , HRD, HRD max_s (s is an integer of 1 or _{more), HRD min_s, Fright _1,} HR SCOPE (t) can be mentioned. HR represents heart rate. HRD represents a difference value between the heart rate at time t and the heart rate at time t-1. HRD _{max_s} represents the maximum value of HRD in the past s seconds (for example, s = 10 seconds). HRD _{min_s} represents the minimum value of HRD for the past s seconds. Fright _{_1} represents the value of the sudden change in heart rate of between several seconds to several tens of seconds (rising and falling). HR _SCOPE (t) represents the difference between the maximum value and the minimum value of the heart rate in the past s seconds.

  The second feature amount calculation unit 206 reads the triaxial acceleration information stored in the acceleration information storage unit 204 and calculates a plurality of second feature amounts used to calculate each index obtained from the triaxial acceleration information. To do. Specific examples of the second feature amount include ACV, a standard deviation in three-dimensional directions (x, y, and z directions), an inner product of feature amounts obtained from the standard deviation, and a state estimation result. ACV represents a composite value of acceleration in a three-dimensional direction (hereinafter referred to as “composite acceleration”). The estimation result of the state represents an estimation result of the state of the user among the running state, the walking state, and the stopped state.

  The table storage unit 207 is configured using a storage device such as a magnetic hard disk device or a semiconductor storage device. The table storage unit 207 stores a plurality of normalization tables. The normalization table is a table for normalizing values (hereinafter referred to as “index candidate values”) calculated using either the first feature value or the second feature value in order to calculate each index. It is. In the following explanation, the normalization table used for calculating the degree of chatter is the normalization table for calculating the degree of chatter, the normalization table used for calculating the degree of achievement is the normalization table for calculating the degree of achievement, The normalization table used for the calculation is referred to as a normalization table for calculating the degree of security, and the normalization table used for calculating the degree of anxiety is referred to as the normalization table for calculating the anxiety level. The configuration of the normalization table will be described later.

  The index calculation unit 208 calculates an index related to either the change in the user's state with respect to the effect of the haunted house or the change in the user's movement based on the acquired biological information and the three-axis acceleration information. More specifically, the index calculation unit 208 determines the state of the user with respect to the effect of the haunted house based on the first feature value obtained from the acquired biological information and the second feature value obtained from the triaxial acceleration information. An index relating to any of fluctuation and fluctuation of the user's movement is calculated.

  The output unit 209 outputs each calculated index to the output device. The output unit 209 outputs each index to an operator of the index output device 20 (for example, an operator of the index output system 100) via an output device (not shown) connected to the index output device 20. The output device may be configured using, for example, a device that outputs images and characters on a screen. For example, the output device can be configured using a CRT (Cathode Ray Tube), a liquid crystal display, an organic EL (Electro-Luminescent) display, or the like. The output device may be configured using a device that prints (prints) an image or a character on a sheet. For example, the output device can be configured using an ink jet printer, a laser printer, or the like. In addition, the output device may be configured using a device that converts characters into speech and outputs the speech. In this case, the output device can be configured using a voice synthesizer and a voice output device (speaker).

FIG. 2 is a flowchart showing a process flow of the index output device 20.
The acquisition unit 201 acquires biological information and acceleration information from the sensor terminal 10 (step S101). The acquisition unit 201 outputs the acquired information to the identification unit 202. The identification unit 202 identifies the output information (step S102). When the output information is biometric information (step S102-biometric information), the identification unit 202 stores the output information in the biometric information storage unit 203 (step S103). On the other hand, when the output information is acceleration information (step S102—acceleration information), the identification unit 202 stores the output information in the acceleration information storage unit 204 (step S104).

Thereafter, the first feature quantity calculation unit 205 performs a first feature quantity calculation process based on the biological information stored in the biological information storage unit 203 (step S105). Specific processing of the first feature amount calculation processing will be described later. The first feature value calculation unit 205 outputs the first feature value acquired by the first feature value calculation process to the index calculation unit 208.
Further, the second feature quantity calculation unit 206 performs a second feature quantity calculation process based on the triaxial acceleration information stored in the acceleration information storage unit 204 (step S106). Specific processing of the second feature amount calculation processing will be described later. The second feature quantity calculation unit 206 outputs the second feature quantity acquired by the second feature quantity calculation process to the index calculation unit 208.

The index calculation unit 208 acquires the first feature value output from the first feature value calculation unit 205 and the second feature value output from the second feature value calculation unit 206. The index calculation unit 208 executes index calculation processing based on the acquired first feature quantity and second feature quantity and the normalization table stored in the table storage unit 207 (step S107). Specific processing of the index calculation processing will be described later. Thereafter, the output unit 209 outputs each acquired index to the output device (step S108) .

FIG. 3 is a flowchart showing the flow of the first feature amount calculation process by the first feature amount calculation unit 205. Note that all values calculated in the first feature amount calculation process are included in the first feature amount.
First, based on the biological information stored in the biological information storage unit 203, the first feature amount calculation unit 205 sets RRl _i that is an RR interval as R (i), where R (i) is the peak of the heartbeat wave at time i. Calculation is performed based on Equation 1 (step S201).

Next, the first feature amount calculation unit 205 calculates the heart rate HR based on the following equation 2 using the RRl _i obtained by the above equation 1 (step S202).

  The first feature amount calculation unit 205 calculates the HRD based on the following Equation 3 (Step S203). For example, the first feature amount calculation unit 205 calculates a difference value HRD between the current heart rate HR (t) and the heart rate HR (t−1) one second ago based on the following Equation 3.

The first feature amount calculation unit 205 calculates the maximum HRD value HRD _{max_S} in the past s seconds (for example, 10 seconds) based on the following Equation 4 (step S204).

The first feature amount calculation unit 205 calculates the minimum HRD value HRD _{min_s} in the past s seconds based on the following Equation 5 (step S205).

The first feature quantity calculating unit 205, by using the maximum value _{HRD Max_s} and the minimum value _{HRD Min_s,} calculates the Fright _{_1} based on Equation 6 below (step S206).

The first feature amount calculation unit 205 calculates a minimum value HR _min (t) of HR in the past s seconds and a maximum value HR _max (t) of HR in the past s seconds based on the following Expression 7. Further, a difference HR _SCOPE (t) between the maximum value HR _min (t) and the minimum value HR _min (t) of the heart rate in the past s seconds from the present time is calculated based on the following Expression 7 (step S207).

  FIG. 4 is a flowchart showing the flow of the second feature amount calculation process by the second feature amount calculation unit 206. Note that all values calculated in the second feature amount calculation process are included in the second feature amount. In the second feature amount calculation process, from the three-axis acceleration information stored in the acceleration information storage unit 204, a state in which the user is stopped, walking, running, or the like in the haunted house is estimated. For the estimation, a machine learning algorithm (for example, SVM (Support Vector Machine)) is used based on the feature amount obtained from the triaxial acceleration information. As a premise, the x, y, and z directions in the triaxial acceleration information are ACX, ACY, and ACZ, respectively.

  First, the second feature amount calculation unit 206 calculates the composite acceleration ACV based on the following equation 8 using the triaxial acceleration information stored in the acceleration information storage unit 204 (step S301).

Next, the second feature quantity calculation unit 206 calculates standard deviations in the x, y, and z directions based on the following formulas 9 to 12 (step S302). Here, each feature amount is assumed to be ACX _SD , ACY _SD , ACZ _SD , and ACV _SD . In Expressions 9 to 12, p is a natural number. P in the following description is also a natural number.

  Next, the second feature amount calculation unit 206 calculates a feature amount to be machine-learned by obtaining an inner product of each feature amount. Specifically, the second feature quantity calculation unit 206 calculates a feature quantity to be machine-learned based on the following formulas 13 to 18 (step S303).

  Based on the feature amount calculated in the process of step S301, the user's movement in the haunted house is classified into three states, that is, walking, and running, by machine learning. Here, an example classified into three states by machine learning is shown in FIG.

FIG. 5 is a diagram illustrating an example of a heart rate variation and a motion estimation result.
In FIG. 5, the horizontal axis represents time, the left vertical axis represents the heart rate, and the right vertical axis represents the motion estimation result. In FIG. 5, the transition line 30 represents the fluctuation of the heart rate, and the transition line 40 represents the fluctuation of the motion estimation result. As shown in FIG. 5, it is estimated by the machine learning what kind of movement the user was at. Further, the value of the heart rate of the user at that time is also shown.

After that, the second feature quantity calculation unit 206 calculates the ratio of each state in the estimation result based on the following formulas 19 to 21 (step S304). Here, the estimation result of the running state is Result _R , the estimation result of the walking state is Result _W , the estimation result of the stopped state is Result _S , and the respective ratios are Run _p , Walk _p , Stand _p and To do.

FIG. 6 is a flowchart showing a flow of evaluation value calculation processing by the index output device 20.
The index calculation unit 208 calculates the chatter degree (step S401). Specifically, first, the index calculation unit 208 uses the first feature value calculated in the first feature value calculation process and the second feature value calculated in the second feature value calculation process, from the following Expression 22. Each index candidate value is calculated based on Expression 24.

Next, the index calculation unit 208 normalizes each index candidate value using the index candidate value calculated by each of Expressions 22 to 24 and the normalization table for calculating the chatter degree. Here, the normalization table for calculating the chatter degree will be described with reference to FIG. FIG. 7 is a diagram illustrating a specific example of the normalization table for calculating the chatter degree. As shown in FIG. 7, the normalization table for calculating the degree of chatter includes index candidate values (Flight — ₁ , HR _SCOPE and Run _p ) and normalized values (1, 2, 3, 4 and 5). Composed of a combination.

In the example illustrated in FIG. 7, when the value of the index candidate value “Flight — ₁ ” is T ≦ a1 (a1 or less), the normalized value of the index candidate value “Flight — ₁ ” is “1”. It has been shown. a1 Similarly, the value of the index candidate value "Fright _{_1"} is, in the case of a1 <T ≦ a2 (a1 or a2 or less), the value of the normalized value of index candidate value "Fright _{_1"} is "2" It has been shown. The same applies to other index candidate values. After that, the index calculation unit 208 calculates the degree of chatter by taking a weighted average of each normalized value (normalized _{Flight_1} , normalized HR _SCOPE, normalized Run _p ). In FIG. 7, a1 to a4, b1 to b4, and c1 to c4 are all integers.

Next, the index calculation unit 208 calculates the achievement level (step S402). Specifically, first, the index calculation unit 208 calculates the value of the index candidate value Run _p based on the above equation 24. Next, the index calculation unit 208 normalizes the index candidate value Run _p using the calculated index candidate value Run _p and the achievement level calculation normalization table. Here, the achievement degree calculation normalization table will be described with reference to FIG. FIG. 8 is a diagram illustrating a specific example of the achievement degree normalization table. As shown in FIG. 8, the achievement degree calculation normalization table includes a combination of index candidate values (Run _p ) and normalized values (1, 2, 3, 4, and 5).

In the example illustrated in FIG. 8, when the value of the index candidate value “Run _p ” is T ≦ d1 (d1 or less), the normalized value of the index candidate value “Run _p ” is “1”. It has been shown. Similarly, when the value of the index candidate value “Run _p ” is d1 <T ≦ d2 (d1 or more and d2 or less), the normalized value of the index candidate value “Run _p ” is “2”. It is shown. After that, the index calculation unit 208 acquires the normalized value of Run _p as the achievement level. In FIG. 8, d1 to d4 are integers.

Next, the index calculation unit 208 calculates the safety level (step S403). Specifically, first, the index calculation unit 208 uses the first feature value calculated in the first feature value calculation process and the second feature value calculated in the second feature value calculation process, from the following Expression 25: Each index candidate value is calculated based on Equation 27. Here, it is assumed that HRD is a continuous function. It is assumed that HRD has an extreme value at time a when HRD ′ (a) = 0 holds. The total number of extreme values is K, the total number of local maximums is α, and the total number of local minimums is β (K = α + β). Also, the difference value at time a in the measurement time T seconds is A = α _i −α _i−1 (2 <i ≦ K), and the difference value between the extreme values at this time is B _i = f (α _i ) −f. (Α _i-1 ) (2 <i ≦ K). )

Next, the index calculation unit 208 normalizes each index candidate value by using each index candidate value calculated by each of Expression 25 to Expression 27 and the normalization table for safety level calculation. Here, the normalization table for calculating the safety level will be described with reference to FIG. FIG. 9 is a diagram illustrating a specific example of a normalization table for calculating a certainty level. As shown in FIG. 9, the normalization table for calculating the degree of security includes candidate index values (min (HRD _{min_s} ), RT _max and RT _mean ) and normalized values (1, 2, 3, 4 and 5). ). Here, RT _max is Relief Time _max calculated by Expression 26, and RT _mean is Relief Time _mean calculated by Expression 27.

In the example shown in FIG. 9, when the value of the index candidate value “min (HRD _{min_s} )” is T ≦ e1 (e1 or less), the value of the index candidate value “min (HRD _{min_s} )” is normalized. Is “1”. Similarly, when the value of the index candidate value “min (HRD _{min_s} )” is e1 <T ≦ e2 (e1 or more and e2 or less), the normalized value of the index candidate value “min (HRD _{min_s} )” is It is shown that it is “2”. The same applies to other index candidate values. Thereafter, the index calculation unit 208 calculates the degree of security by taking a weighted average of each normalized value (normalized min (HRD _{min_s} ), normalized RT _max, normalized RT _mean ). In FIG. 9, e1 to e4, f1 to f4, and g1 to g4 are all integers.

Next, the index calculation unit 208 calculates the degree of anxiety (step S404). Specifically, first, the index calculation unit 208 uses the first feature value calculated in the first feature value calculation process and the second feature value calculated in the second feature value calculation process, from the following Expression 28: Each index candidate value is calculated based on Equation 30. Here, it is assumed that HRD is a continuous function. It is assumed that HRD has an extreme value at time a when HRD ′ (a) = 0 holds. The total number of extreme values is K, the total number of local maximums is α, and the total number of local minimums is β (K = α + β). Also, the difference value at time a in the measurement time T seconds is A = α _i −α _i−1 (2 <i ≦ K), and the difference value between the extreme values at this time is B _i = f (α _i ) −f. (Α _i-1 ) (2 <i ≦ K). )

Next, the index calculation unit 208 normalizes each index candidate value using the index candidate values calculated from Expression 28 to Expression 30 and the anxiety degree calculation normalization table. Here, the normalization table for anxiety degree calculation will be described with reference to FIG. FIG. 10 is a diagram illustrating a specific example of a normalization table for calculating anxiety level. As shown in FIG. 10, the normalization table for anxiety degree calculation includes index candidate values (max (HRD _{max_s)} , ST _max and ST _mean ) and normalized values (1, 2, 3, 4 and 5). ). Here, ST _max is a Scaled Time _max calculated by Expression 29, and ST _mean is a Scaled Time _mean calculated by Expression 30.

In the example shown in FIG. 10, when the value of the index candidate value “max (HRD _{max_s)} ” is T ≦ h1 (h1 or less), the value after normalization of the value of the index candidate value “max (HRD _{max_s)} ” Is “1”. Similarly, when the value of the index candidate value “max (HRD _{max_s)} ” is h1 <T ≦ h2 (from h1 to h2), the normalized value of the index candidate value “max (HRD _{max_s)} ” is It is shown that it is “2”. The same applies to other index candidate values. After that, the index calculation unit 208 calculates the degree of anxiety by taking a weighted average of each normalized value (normalized max (HRD _{max_s)} , normalized ST _max, normalized ST _mean ). In FIG. 10, h1 to h4, i1 to i4, and j1 to j4 are all integers.
After that, the index calculation unit 208 calculates the degree of pleasure Pleasure based on the following formula 31 using the index obtained by the processing in steps S401 to S404 (step S405). Note that a, b, c, and d in Equation 31 are natural numbers.

According to the index output system 100 configured as described above, it is possible to easily evaluate the effect of the attraction effect. Hereinafter, this effect will be described in detail.
The index output device 20 calculates an index related to any one of the change in the user's state and the change in the user's movement with respect to the attraction, using the biological information and the three-axis acceleration information of the user experiencing the attraction. Here, the index regarding any of the fluctuation of the user's state and the fluctuation of the user's movement is the degree of chatter, achievement, security, anxiety, and fun. In this way, the index output device 20 can digitize the state of the user experiencing the attraction during the attraction experience by calculating each index. Therefore, it becomes possible to easily evaluate the effect of the attraction effect. As a result, the operator or director of the attraction can easily evaluate the effect of the attraction by looking at the index. Furthermore, an attraction operator and a director can study effective production by feeding back the result.

  In addition, the user can experience an unprecedented experience such that the user can know the state of the attraction experience by receiving data for each index after the attraction experience.

(Modification)
In the present embodiment, the configuration in which the index output system 100 includes one sensor terminal 10 is shown, but the index output system 100 may be configured to include a plurality of sensor terminals 10. Moreover, although the sensor terminal 10 showed the structure which acquires biometric information and 3-axis acceleration information in this embodiment, it may be comprised so that biometric information and 3-axis acceleration information may each be acquired by another apparatus. . For example, the first sensor terminal may acquire biological information, and the second sensor terminal may acquire triaxial acceleration information. In this case, the first sensor terminal may be a wearable sensor, and the second sensor terminal may be a smartphone or the like.
The attraction that produces an effect that affects a person's condition may be other than a haunted house and a roller coaster. For example, an attraction that produces an effect that affects the state of a person may be an attraction installed in equipment such as an amusement park, or may be equipment or an event that changes the state of the person.

The acquisition unit 201 may be configured to acquire position information related to the position where each piece of information is acquired together with the biological information and the triaxial acceleration information. When configured in this way, the sensor terminal 10 includes a position information acquisition unit that acquires position information. The position information acquisition unit acquires the position information of the own apparatus from a system that measures position information such as GPS (Global Positioning System).
By comprising in this way, the operator and director of an attraction can grasp | ascertain the user's state change for every production more correctly. As a result, a more effective presentation can be studied.

  The embodiment of the present invention has been described in detail with reference to the drawings. However, the specific configuration is not limited to this embodiment, and includes designs and the like that do not depart from the gist of the present invention.

DESCRIPTION OF SYMBOLS 10 ... Sensor terminal, 20 ... Index output device, 201 ... Acquisition part, 202 ... Identification part, 203 ... Biological information storage part, 204 ... Acceleration information storage part, 205 ... 1st feature-value calculation part, 206 ... 2nd feature-value Calculation unit, 207 ... Table storage unit, 208 ... Index calculation unit (index acquisition unit), 209 ... Output unit

Claims (9)

An acquisition unit for acquiring biological information of the user and acceleration information relating to the movement of the user;
Based on the acquired biological information and acceleration information, an index relating to any one of fluctuations in the state of the user and fluctuations in the movement of the user with respect to an attraction for performing an effect that affects the state of the person as a play facility An index acquisition unit for acquiring
An output unit for outputting the acquired index;
An indicator output device comprising: A first feature amount calculation unit for calculating a plurality of first feature amounts used for calculating the index obtained from the biological information;
A second feature amount calculation unit that calculates a plurality of second feature amounts used to calculate the index obtained from the acceleration information;
The index acquisition unit acquires either the value related to the user state or the value related to the user's movement using either the first feature value or the second feature value, and normalizes the acquisition result. The index output device according to claim 1, wherein the index is acquired. The indicator is a momentary fear degree that represents the degree to which a person is released from being in fear.
The index acquisition unit acquires a value related to the user's state and a value related to the user's movement using the first feature value and the second feature value, normalizes each acquisition result, and performs weighted averaging. The index output device according to claim 2, wherein the instantaneous fear level is acquired. The indicator further includes a degree of achievement that represents the degree of enjoyment of the production,
The index output device according to claim 3, wherein the index acquisition unit acquires a value related to the user's movement using the second feature amount, and acquires the achievement level by normalizing an acquisition result. The indicator further includes a degree of security representing a degree of relief from being freed from anxiety and fear,
5. The index acquisition unit according to claim 4, wherein the index acquisition unit acquires a plurality of values related to the state of the user by using the first feature amount, normalizes each acquisition result, and performs weighted averaging to acquire the degree of security. Indicator output device. The indicator further includes an anxiety level representing the degree of anxiety or fear,
The said index acquisition part acquires the said anxiety degree by acquiring multiple values regarding the said user's state using the said 1st feature-value, normalizing each acquisition result, and carrying out a weighted average. Indicator output device. The indicator further includes a degree of enjoyment representing the degree of enjoyment of the attraction,
The index output device according to claim 6, wherein the index acquisition unit acquires the enjoyment level by performing a predetermined calculation on the instantaneous fear level, achievement level, reassurance level, and anxiety level. An acquisition step of acquiring biometric information of the user and acceleration information relating to the movement of the user;
Based on the acquired biological information and acceleration information, an index relating to any one of fluctuations in the state of the user and fluctuations in the movement of the user with respect to an attraction for performing an effect that affects the state of the person as a play facility An index acquisition step for acquiring
An output step of outputting the acquired index;
An indicator output method having An acquisition step of acquiring biometric information of the user and acceleration information relating to the movement of the user;
Based on the acquired biological information and acceleration information, an index relating to any one of fluctuations in the state of the user and fluctuations in the movement of the user with respect to an attraction for performing an effect that affects the state of the person as a play facility An index acquisition step for acquiring
An output step of outputting the acquired index;
A computer program for causing a computer to execute.

Images