JP2020072907A - Content evaluation device, content evaluation method, and program - Google Patents

Abstract

To provide a content evaluation device which can evaluate a content by using an event related potential.SOLUTION: A content evaluation device includes: a data input unit for acquiring time series data of brain waves in which stimulation which a person can perceive is made into a content, and when contents of a plurality of evaluators when perceiving the contents are presented; an event related potential extracting unit for extracting an event related potential from an addition average of the acquired time series data of brain waves; and a content evaluation unit for evaluating the contents based on the number of times of occurrence of the event related potentials.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a content evaluation device, content evaluation method, and program for evaluating content using event-related potentials.

  There is a technique of estimating sound quality using event-related potentials (ERPs, Event-Related Potentials) of brain waves (for example, Patent Document 1).

JP2012-98643A

  However, when the event-related potentials (ERPs) are used for evaluation, it is necessary to repeatedly present the stimuli that are supposed to generate the event-related potentials (ERPs), and to compare the magnitudes of the responses, and a special presentation order is used. There was a problem that it was difficult to evaluate normal content because it had to be done.

  Therefore, it is an object of the present invention to provide a content evaluation device that can evaluate content using event-related potentials.

  The content evaluation device of the present invention includes a data input unit, an event-related potential extraction unit, and a content evaluation unit. The content is a stimulus that can be perceived by humans.

  The data input unit acquires time series data of electroencephalograms of a plurality of evaluators who are perceiving the content and when the content is being presented. The event-related potential extraction unit extracts the event-related potential from the arithmetic mean of the acquired time series data of the electroencephalogram. The content evaluation unit evaluates the content based on the number of occurrences of the event-related potential.

  According to the content evaluation device of the present invention, it is possible to evaluate content using the event-related potential.

3 is a block diagram showing the configuration of a content evaluation system of Example 1. FIG. 3 is a flowchart showing the operation of the content evaluation device of the first embodiment. 3 is a block diagram showing the configuration of a content evaluation system of Example 2. FIG. 9 is a flowchart showing the operation of the content evaluation device of the second embodiment. 9 is a block diagram showing the configuration of a content evaluation system of Example 3. FIG. 9 is a flowchart showing the operation of the content evaluation device of the third embodiment. The figure which illustrates the waveform of the time series data of an event-related electric potential template and an electroencephalogram.

The terms used in this specification are defined below.
<< Contents >>
Refers to all stimuli that humans can perceive with their five senses. For example, the content may be a group of art expressions, products or media that can be evaluated. The content typically includes video, audio, music, still images (paintings, photographs), and the like. Signals and information including contents are called contents data.

≪EEG measurement device≫
In the present specification, the electroencephalogram measurement device means a device that measures an electroencephalogram of an evaluator and an interface device thereof. The electroencephalogram measuring device measures and outputs a weak electric potential generated by the brain activity of the evaluator from an exploration electrode attached to the head of the evaluator. The measurement points may be in accordance with, for example, the international 10-20 method and the extended 10-20 method (10% method). It is preferable to set Fz (median frontal region) or Cz (median central portion) where the event-related potential is easily observed as a measurement target. For example, an existing brain wave measuring device such as BrainAmp manufactured by Brain Products can be used.

≪Event-related potential≫
It is a transient voltage fluctuation in the brain that occurs temporally in relation to external or internal events. When looking at the response to an external stimulus, it is measured starting from the timing of occurrence of the external stimulus. Famous reactions include P300 and the like (Patent Document 1, Reference Non-Patent Document 1: Hiroshi Miyata, "New Physiology of Psychology 2-Applications of Physiology Psychology", Kitaoji Shobo, September 1997, pp.10-17).

  It is known that when the brain is affected by the presented stimulus, an event-related potential is generated after a predetermined time from the stimulus, and this phenomenon has little individual difference. It is known that the event-related potential becomes larger as the attention is paid to the stimulus. Therefore, the more the brain is affected by the presentation of the content, the more the number of occurrences of the event-related potential increases and the greater the reaction thereof. Therefore, the event-related potential is considered to be suitable as an index for evaluating the content.

  Hereinafter, embodiments of the present invention will be described in detail. It should be noted that components having the same function are denoted by the same reference numeral, and redundant description will be omitted.

<< Content Evaluation System 100 >>
The configuration of the content evaluation system of the first embodiment will be described below with reference to FIG. FIG. 1 is a block diagram showing the configuration of the content evaluation system 100 of this embodiment. In the content evaluation system 100 according to the present embodiment, M pieces of content 91-1, ..., 91-m, ..., 91-M, N evaluators 94-1, ..., 94-n ,. N is prepared. Note that items that do not distinguish the M contents (equivalent to all the M contents) may be simply referred to as contents 91. Similarly, a matter that does not distinguish the N evaluators (equally applies to all the N evaluators) may be simply referred to as an evaluator 94. A brain wave measuring device 93 is attached to the heads of the N evaluators 94-1, ..., 94-n ,. The brain wave measuring device 93 continues to transmit the time series data of the brain wave of the evaluator 94 to the content evaluating device 1. The content evaluation apparatus 1 continues to receive the time-series data of the electroencephalogram of the evaluator 94 from the electroencephalogram measurement apparatus 93.

≪Content presentation method≫
In the first to third embodiments, the same content is not presented to one evaluator 94 a plurality of times, but once to N evaluators 94-1, ..., 94-n, ..., 94-N. Only, the method of presenting the same content (for example, content 91-1) at the same time is adopted. Even if the presenting is performed only once for each evaluator as in the present example, if the statistical value of the electroencephalogram data of a plurality of evaluators (in the simplest example, the average value) is taken, the evaluation is performed. It is possible to extract the number of occurrences and strength of event-related potentials in a group of persons.

  As an example of content evaluation, for example, a dance performed by a dance team of M team (what is performed live) is used as the evaluation target content, and the dance team of M team is based on the influence on the brain of the evaluator 94 who saw the dance. An actual example of wanting to decide the superiority or inferiority can be considered. This example will appear after this. Note that “presentation” and “presentation” have almost the same meaning, but in the present specification, when the evaluator perceives the content, it is referred to as “presentation”.

<< Content Evaluation Device 1 >>
The content evaluation device 1 according to the present embodiment includes a data input unit 11, an event-related potential extraction unit 12, a content evaluation unit 13, and a threshold storage unit 14. The threshold storage unit 14 stores in advance a threshold used in step S12 described below.

  The operation of the content evaluation device 1 of this embodiment will be described below with reference to FIG. FIG. 2 is a flowchart showing the operation of the content evaluation device 1 of this embodiment.

  The data input unit 11 acquires the time series data of the brain waves of the evaluator 94 who perceives the content (S11). The event-related potential extraction unit 12 extracts the event-related potential based on the acquired time series data of the electroencephalogram (S12). The event-related potential extraction unit 12 elapses with time, for example, at predetermined time intervals (for example, for each frame) of the arithmetic mean value of the electroencephalograms of N evaluators 94-1, ..., 94-n ,. When the added average value exceeds the threshold value stored in advance in the threshold value storage unit 14, it is estimated to be a reaction to the content, and it is considered that the event-related potential has occurred.

Using the above-mentioned example, the arithmetic mean value of the brain waves of N evaluators while watching the dance (content 91-m) of the dance team m is obtained over time, and the T frame is calculated in the past from the current frame. [S] (for example, T = 10) The number of times the arithmetic mean value exceeds the threshold value (xP _T ) is set as an event-related value, with x times (for example, x = 2) of the average power P _T up to the time point traced back. It can be the number of times the potential is generated. Furthermore, the peak value of the arithmetic mean value recorded within t [s] (for example, t = 0.5) after exceeding the threshold value (xP _T ) is extracted as an index corresponding to the intensity of the event-related potential. You can

  The content evaluation unit 13 evaluates the content based on at least one of the number of occurrences of the event-related potential and the intensity of the event-related potential (in the above example, the peak value of the addition average value) (S13).

  In addition to the above, it is more preferable that the content evaluation unit 13 evaluates the content with an evaluation index that reflects the temporal length of the content.

  For example, the content evaluation unit 13 may set the number of occurrences of the event-related potential per unit time of the content as the evaluation value of the content, and the higher the value, the higher the evaluation.

  Using the above-mentioned example, assuming that the dance team 1 has a total dance time of 10 minutes, the number of event-related potential occurrences from the beginning to the end of this dance is 10 (for example, the average of brain waves). If the value exceeds the threshold value 10 times), the evaluation value is 10/10 = 1.0 [times / minute]. On the other hand, for example, assuming that the dance team 2 has a total dance time of 5 minutes, the number of event-related potentials generated from the beginning to the end of this dance is 7 times (for example, the average value of brain waves exceeds the threshold value). When the number of times of contact is 7), the evaluation value is 7/5 = 1.4 [times / minute]. Therefore, in this example, the dance of the dance team 2 is evaluated higher than the dance of the dance team 1.

As another method, for example, the average of the peak value of the average value of the electroencephalogram (per occurrence number or per unit time) for each content may be used as the evaluation value. Using the above-mentioned example, for the dance of the dance team 1 (10 minutes), the average value of the electroencephalogram exceeds the threshold value twice, and the peak value of each average value is P ₁ = 1.0, P ₂ = 2.0, the average peak value (per occurrence number) is P _ave1 = 1.5 [strength / time]. On the other hand, the average of peak values (per unit time) becomes P _ave2 = 0.3 [strength / min]. On the other hand, for the dance of the dance team 2 (5 minutes), the average value exceeds the threshold value three times, and the peak values of the respective average values are P ₁ = 1.0, P ₂ = 1.0, P ₃ = 1.0, the average of peak values (per number of occurrences) is P _ave1 = 1.0 [strength / time]. On the other hand, the average of the peak values (per unit time) becomes P _ave2 = 0.6 [strength / min].

Therefore, when viewed from the average [strength / time] P _ave1 of the peak value, the dance of the dance team 1 is highly evaluated. On the other hand, when viewed from the average [strength / min] P _ave2 of the peak value, the dance of the dance team 2 is highly evaluated.

  According to the content evaluation apparatus 1 of this embodiment, it is possible to evaluate the content using the event-related potential. Further, in the present embodiment, instead of repeatedly presenting the same content to one evaluator to acquire an EEG, a plurality of evaluators simultaneously perceive a common content and acquire an EEG simultaneously. Since the number of occurrences and the strength of event-related potentials are indexed using their arithmetic mean value, even if the content can be viewed only once such as live or live performance, it should be evaluated. You can

  Event-related potentials are said to be prone to occur when there is a large change in stimulus. Therefore, the event-related potentials (ERPs) can be extracted more efficiently by using the time when the brightness, the sound pressure, the optical flow, etc. have changed significantly in the content as a reference. The configuration of the content evaluation system of the second embodiment, which is a modification of the content evaluation system 100 of the first embodiment, will be described below with reference to FIG.

<< Content Evaluation System 200 >>
FIG. 3 is a block diagram showing the configuration of the content evaluation system 200 of this embodiment. The only difference from the first embodiment is that the content evaluation system 200 of the present embodiment includes a content acquisition device 95, and that the content evaluation device 1 in the first embodiment is replaced by the content evaluation device 2 in the present embodiment. Is.

<< Content Acquisition Device 95 >>
In this embodiment, an apparatus for acquiring the content data may be required because it is used for the processing described later. For example, if the content is to be demonstrated live and not electronic data, the content acquisition device 95 may be, for example, a video camera. On the other hand, when the content is electronic data, the content acquisition device 95 may be a personal computer or other electronic device capable of transmitting the electronic data to the content evaluation device 2. If the content already exists as electronic data, the content acquisition device 95 may be unnecessary, and in that case, the content acquisition device 95 may be omitted. In FIG. 3, the content acquisition device 95 is illustrated as a video camera in accordance with the above example.

<< Content Evaluation Device 2 >>
The content evaluation device 2 of the present embodiment includes a data input unit 21, an event-related potential extraction unit 22, a content evaluation unit 23, a threshold value storage unit 14, and a change detection unit 25. The threshold storage unit 14 is a constituent element common to the first embodiment. Hereinafter, the difference from the first embodiment will be mainly described with reference to FIG. FIG. 4 is a flowchart showing the operation of the content evaluation device 2 of this embodiment.

  The change detection unit 25 acquires the content data that is electronic data of the content 91, detects a change in the content data that affects the event-related potential, and obtains timing information indicating the time at which the change is detected as event-related timing information. The signal is output to the potential extraction unit 22 (S25).

  For example, the content to be evaluated is recorded by the video camera (content acquisition device 95) concurrently with the evaluation by the evaluator and transmitted to the content evaluation device 2. The data input unit 21 of the content evaluation device 2 receives the recorded content data and transfers it to the change detection unit 25. The change detection unit 25 regards the timing (time) at which the audio level, the brightness, the optical flow and the hue in the recorded content data change above a certain threshold as the timing (time) at which the content changes, and uses the event-related potential as the timing information. Output to the extraction unit 22. For example, it is considered that the event-related potential occurs in the evaluator 94 at the time when the intensity of the movement suddenly changes in the dance. The change detection unit 25 detects this time based on a change in the optical flow of a video recorded in parallel with the evaluation by the evaluator 94, and outputs the timing (time) as timing information.

The event-related potential extraction unit 22 specifies the corresponding time in the time-series data of the electroencephalogram based on the time indicated by the timing information, and extracts the event-related potential in a predetermined time range determined according to the specified time ( S22). For example, the event-related potential extraction unit 22 may move from a time corresponding to the time indicated by the timing information (for example, a time at which the intensity of dance changes) to a time T _b [ms] (for example, T _b = 200) back in time. When the time-series data of the electroencephalogram of the section from the time to T _f [ms] (for example, T _f = 500) in the future to the future is cut out and the average is exceeded between the evaluators, and the average value exceeds the threshold. Can be the occurrence of an event-related potential. Further, the peak value of the arithmetic mean value in the section may be output to the content evaluation unit 23 as an index corresponding to the strength of the event-related potential.

  The content evaluation unit 23 evaluates the content based on at least one of the number of occurrences of the event-related potential, the intensity of the event-related potential, and the number of times the change is detected (S23).

  For example, the content evaluation unit 23 may evaluate the content using the number of changes detected (which is the same as the number of times the timing information is output) as a denominator and the value with the output of the event-related potential estimation unit 22 as the numerator as an evaluation index. it can. For example, the content may be evaluated by using the number of times of change detection as a denominator and the number of times when the threshold is exceeded (the number of times of occurrence of event-related potential) as a numerator. Further, the content may be evaluated using, for example, the number of change detections as a denominator and the sum of peak values of the arithmetic mean value (corresponding to the intensity of the event-related potential) as a numerator.

  According to the content evaluation apparatus 2 of the present embodiment, in addition to the effect of the first embodiment, the content evaluation is performed by focusing on the section where the event-related potential is likely to occur, so that the event-related potential (ERPs) is extracted more efficiently. it can.

  By measuring the changes in typical event-related potentials in advance and storing them as event-related potential templates in advance, and using the difference between the EEG time-series data and the event-related potential template, the event-related potentials can be more highly accurate. Can be extracted. The configuration of the content evaluation system of the third embodiment, which is a modification of the content evaluation system 200 of the second embodiment, will be described below with reference to FIG.

<< Content Evaluation System 300 >>
FIG. 5 is a block diagram showing the configuration of the content evaluation system 300 of this embodiment. The only difference from the second embodiment is that the content evaluation device 2 in the second embodiment is replaced with the content evaluation device 3 in the present embodiment.

<< Content Evaluation Device 3 >>
The content evaluation device 3 of the present embodiment includes a data input unit 21, an event-related potential extraction unit 32, a content evaluation unit 23, a threshold storage unit 14, a change detection unit 25, and a template storage unit 36. The data input unit 21, the content evaluation unit 23, the threshold value storage unit 14, and the change detection unit 25 are the same as those in the second embodiment. Hereinafter, the difference from the second embodiment will be mainly described with reference to FIG. FIG. 6 is a flowchart showing the operation of the content evaluation device 3 of this embodiment.

«Template storage unit 36»
This is a storage unit that stores an event-related potential template described later in advance.

≪Event-related potential template≫
A template of the typical event-related potential response of the evaluator. The event-related potential template is created, for example, by letting N assessors hear a light pulse stimulus or a click sound, record brain responses before and after that, and take an arithmetic mean. Note that the event-related potential template may be created one for each evaluator. In this case, when obtaining the difference to be described later, it is preferable to obtain the difference between the time series data of the electroencephalogram of the predetermined evaluator 94-m and the event-related potential template of the same evaluator 94-m.

<< Event-related potential extraction unit 32 >>
The event-related potential extraction unit 32 cuts out the time-series data of the electroencephalogram before and after the timing information sent from the change detection unit 25, and calculates the difference between the cut-out data and the event-related potential template. For example, the event-related potential extraction unit 32 determines that the event-related potential is generated when the difference value exceeds a preset threshold value (threshold value previously stored in the threshold value storage unit 14), and outputs the number of occurrences. Further, for example, as shown in FIG. 7, the event-related potential extraction unit 32 determines the difference value (related to the strength of the event-related potential) between the event-related potential template and the peak value of the time series data (arithmetic mean value) of the electroencephalogram. It may be used as an index (see “peak” in FIG. 7). Further, the number of times that the difference value of the peak values exceeds the threshold value may be used as an index.

  Further, as indicated by the hatched lines in FIG. 7, the integrated value of the difference value between the event-related potential template and the time-series data of the electroencephalogram may be used as an index corresponding to the intensity of the event-related potential.

  According to the content evaluation apparatus 3 of the present embodiment, in addition to the effects of the first and second embodiments, the difference between the event-related potential template and the time series data of the electroencephalogram is used, so that the event-related potential is extracted with higher accuracy. be able to.

<Additional notes>
The device of the present invention is, for example, as a single hardware entity, an input unit to which a keyboard or the like can be connected, an output unit to which a liquid crystal display or the like can be connected, and a communication device (for example, a communication cable) capable of communicating with the outside of the hardware entity. Connectable communication unit, CPU (Central Processing Unit, cache memory and registers may be provided), memory RAM and ROM, hard disk external storage device and their input unit, output unit, communication unit , A CPU, a RAM, a ROM, and a bus connected so that data can be exchanged among external storage devices. If necessary, the hardware entity may be provided with a device (drive) capable of reading and writing a recording medium such as a CD-ROM. A physical entity having such hardware resources includes a general-purpose computer.

  The external storage device of the hardware entity stores a program necessary to realize the above-mentioned functions and data necessary for the processing of this program (not limited to the external storage device, for example, the program is read). It may be stored in a ROM that is a dedicated storage device). Further, data and the like obtained by the processing of these programs are appropriately stored in the RAM, the external storage device, or the like.

  In the hardware entity, each program stored in an external storage device (or ROM, etc.) and the data necessary for the processing of each program are read into the memory as needed, and interpreted and executed / processed by the CPU as appropriate. .. As a result, the CPU realizes a predetermined function (each constituent element represented by the above, ... Unit, ... Means, etc.).

  The present invention is not limited to the above-described embodiments, and can be modified as appropriate without departing from the spirit of the present invention. Further, the processes described in the above embodiments may be executed not only in time series according to the order described, but also in parallel or individually according to the processing capability of the device that executes the processes or the need. ..

  As described above, when the processing functions of the hardware entity (the apparatus of the present invention) described in the above embodiments are realized by a computer, the processing contents of the functions that the hardware entity should have are described by a program. Then, by executing this program on the computer, the processing functions of the hardware entity are realized on the computer.

The program describing the processing contents can be recorded in a computer-readable recording medium. The computer-readable recording medium may be, for example, a magnetic recording device, an optical disc, a magneto-optical recording medium, a semiconductor memory, or the like. Specifically, for example, a hard disk device, a flexible disk, a magnetic tape or the like is used as a magnetic recording device, and a DVD (Digital Versatile Disc), a DVD-RAM (Random Access Memory), or a CD-ROM (Compact Disc Read Only) is used as an optical disc. Memory), CD-
R (Recordable) / RW (ReWritable) or the like can be used as a magneto-optical recording medium, MO (Magneto-Optical disc) or the like, and semiconductor memory can be an EEP-ROM (Electronically Erasable and Programmable-Read Only Memory) or the like. ..

  The distribution of this program is performed by, for example, selling, transferring, or lending a portable recording medium such as a DVD or a CD-ROM in which the program is recorded. Further, the program may be stored in a storage device of a server computer and transferred from the server computer to another computer via a network to distribute the program.

A computer that executes such a program first stores, for example, the program recorded on a portable recording medium or the program transferred from the server computer in its own storage device. Then, when executing the process, this computer reads the program stored in its own recording medium and executes the process according to the read program. As another execution form of this program, a computer may directly read the program from a portable recording medium and execute processing according to the program, and the program is transferred from the server computer to this computer. Each time, the processing according to the received program may be sequentially executed. In addition, a configuration in which the above-described processing is executed by a so-called ASP (Application Service Provider) type service that realizes a processing function only by the execution instruction and result acquisition without transferring the program from the server computer to this computer May be Note that the program in this embodiment includes information that is used for processing by an electronic computer and that conforms to the program (such as data that is not a direct command to a computer but has the property of defining computer processing).

  Further, in this embodiment, the hardware entity is configured by executing a predetermined program on the computer, but at least a part of the processing content may be implemented by hardware.

Claims (5)

The content is a stimulus that can be perceived by humans,
A plurality of evaluators when perceiving the content, a data input unit that respectively acquires time-series data of an electroencephalogram when the content is being presented,
An event-related potential extraction unit that extracts an event-related potential from the arithmetic mean of the acquired time series data of the electroencephalogram,
A content evaluation unit that evaluates the content based on the number of occurrences of the event-related potential,
Content evaluation device including. The content evaluation device according to claim 1, wherein
The content evaluation unit,
A content evaluation device, wherein the number of occurrences of the event-related potential per unit time of the content is used as an evaluation value of the content, and the larger the evaluation value, the higher the content is evaluated. The content is a stimulus that can be perceived by humans,
A plurality of evaluators when perceiving the content, respectively acquiring the time series data of the electroencephalogram when the content is being presented,
Extracting the event-related potential from the arithmetic mean of the time-series data of the acquired electroencephalogram,
Evaluating the content based on the number of occurrences of the event-related potential,
A content evaluation method in which a content evaluation apparatus executes. The content evaluation method according to claim 3,
A content evaluation method in which the number of occurrences of the event-related potential per unit time of the content is used as an evaluation value of the content, and the content is evaluated higher as the evaluation value is larger.   A program that causes a computer to function as the content evaluation device according to claim 1.

Images