JP2013180076A - Analysis supporting device and program - Google Patents

Abstract

A measurement result of both an electroencephalograph and a viewpoint tracking device is output for easy analysis.
A control unit of an analysis support apparatus generates time-series graph data from an interest degree 80 calculated at a predetermined sampling interval (S51), and viewpoint coordinate data 55 is framed in a scene video 62 frame by frame. Corresponding (S52), synchronizing the time series based on the time difference 61, the curve data of the degree of interest 80 generated in S51 and the scene video to which the viewpoint coordinates are associated in S52 are displayed on the same screen. (S53).
[Selection] Figure 9

Description

  The present invention relates to an analysis support device that supports analysis of measurement results by an electroencephalograph and a viewpoint tracking device for market research.

  Conventionally, effect measurement (an example of market research) such as TVCM and magazine advertisement has been performed using an electroencephalograph and a viewpoint tracking device alone. Patent Document 1 discloses an example using an electroencephalograph alone, and Patent Document 2 discloses an example using a viewpoint tracking device alone.

  According to Patent Document 1, an answer that provides an honest answer of a respondent is obtained by analyzing an answer to a question such as a questionnaire in accordance with a result of monitoring a brain activity of the respondent (corresponding to the “subject” of the present invention). An acquisition device is disclosed. In Patent Document 1, the respondent A puts on his head a brain hat 1 having a first sensor 2 that measures an electric field generated along with brain activity and a second sensor 3 that detects a state of cerebral blood flow. The analysis device 11 is based on information indicating the brain activity of the respondent A (a signal indicating the intracerebral electric field obtained by the first sensor 2 and a signal indicating the state of cerebral blood flow obtained by the second sensor 3). The answer of the respondent A to the questionnaire question is analyzed.

  Patent Document 2 discloses a gaze point measuring device for a consumer to take a paper medium such as a pamphlet and analyze the behavior until the product is recognized. In Patent Document 2, a markerless eye tracking device 2 (viewpoint tracking device) is used. The gazing point measurement device 1 disclosed in Patent Document 2 has a gazing point 7 even if the end of the target object 5 is curved or an unevenness is generated inside the target object 5 and the target object 5 is deformed. The position of can be measured automatically and accurately.

JP 2006-305334 A JP 2011-194105 A

  By the way, the analyst can analyze from different viewpoints from the measurement results of the electroencephalograph and the viewpoint tracking device. Therefore, it is meaningful to analyze the measurement results of both the electroencephalograph and the viewpoint tracking device. However, at present, an electroencephalograph or a viewpoint tracking device is used alone, and there is no mechanism for outputting both measurement results of the electroencephalograph and the viewpoint tracking device so that they can be easily analyzed.

  The present invention has been made in view of the above-described problems, and an object of the present invention is to provide an analysis support device capable of easily outputting both measurement results by an electroencephalograph and a viewpoint tracking device. And so on.

  A first invention for achieving the above-described object is an analysis support device that supports analysis of measurement results by an electroencephalograph and a viewpoint tracking device for a subject who is browsing content, and is measured by the electroencephalograph The subject's brain wave data, the subject's viewpoint coordinate data measured by the viewpoint tracking device, the scene video or snapshot image related to the content imaged by the viewpoint tracking device, and the measurement start time by the electroencephalograph And a storage means for storing a time difference in measurement start time by the viewpoint tracking device, a subconscious degree calculating means for calculating a subconscious degree of the subject based on the electroencephalogram data, and the subject based on the viewpoint coordinate data An association means for associating the viewpoint coordinates with the scene image or the snapshot image, and A display means for synchronizing the time series based on the difference and displaying the scene video or the snapshot image associated with the subject's viewpoint coordinates and the subconsciousness degree on the same screen. It is a characteristic analysis support device. According to the first invention, it is possible to output both measurement results by the electroencephalograph and the viewpoint tracking device so as to be easily analyzed.

  In the first invention, the electroencephalogram data includes a measurement start time by the electroencephalograph, and the viewpoint coordinate data includes a measurement start time by the viewpoint tracking device. Based on the electroencephalogram data and the viewpoint coordinate data, It is desirable to further comprise time difference calculation means for calculating a time difference and storing the time difference in the storage means. Thereby, the time difference between the electroencephalogram data and the viewpoint coordinate data can be automatically calculated. As a result, the load on the analyst is reduced. Here, the degree of subconsciousness is data obtained by quantifying the consciousness (unconsciousness) of the subject who is browsing the content on a certain scale based on the electroencephalogram data acquired by the electroencephalograph.

  For example, the association means in the first invention associates the viewpoint coordinates with the scene image frame by frame, and the display means reproduces the scene image while superimposing a viewpoint mark indicating the position of the viewpoint coordinates. At the same time, the subconsciousness variation is drawn as a time-series graph while superimposing a timeline indicating the playback position of the scene video. Thus, in the case of a dynamic image such as a moving image such as a TVCM or a subject moving, the analyst can view the subject's subconsciousness and the change in viewpoint at the same time. For example, the analyst can easily visually recognize which scene and which position of the dynamic content the subject is viewing when the subconsciousness is at the peak.

  Further, for example, the association means in the first invention associates the viewpoint coordinates with the scene image frame by frame, and further determines the degree of decoration of the viewpoint mark indicating the position of the viewpoint coordinates according to the subconsciousness level. The display means reproduces the scene video while superimposing the viewpoint marks decorated according to the degree of decoration, and superimposes the subconsciousness while superimposing a timeline indicating the playback position of the scene video. Draw the degree variation as a time-series graph. Thus, in the case of a dynamic image such as a moving image such as a TVCM or a subject moving, the analyst can view the subject's subconsciousness and the change in viewpoint at the same time. In particular, since the viewpoint mark is decorated and displayed according to the degree of subconsciousness, the analyst can visually recognize the change in the subconscious degree on the dynamic content.

  Further, for example, the associating means according to the first aspect of the present invention performs coordinate transformation of the viewpoint coordinates into a coordinate system of the snapshot image and associates the viewpoint coordinates with a single snapshot image, and further determines the position of the viewpoint coordinates. The degree of decoration of the viewpoint mark to be displayed is determined according to the subconscious degree, the viewing time is calculated for each viewpoint coordinate, the area degree of the viewpoint mark is determined according to the browsing time, and the display means For each of the viewpoint coordinates, the snapshot image is displayed by superimposing the viewpoint mark having the area of the area degree decorated according to the decoration degree. As a result, in the case of static content such as magazine advertisements and leaflets, the analyst can simultaneously view the subject's subconsciousness and changes in viewpoint. For example, the analyst can easily visually recognize which position of the static content the subject is viewing for what time and for what degree of subconsciousness.

  A second invention is a program for causing a computer to function as an analysis support device that supports analysis of measurement results by an electroencephalograph and a viewpoint tracking device for a subject who is browsing content, and is measured by the electroencephalograph The subject's brain wave data, the subject's viewpoint coordinate data measured by the viewpoint tracking device, the scene video or snapshot image related to the content imaged by the viewpoint tracking device, and the start of measurement by the electroencephalograph Storage means for storing a time and a time difference between measurement start times by the viewpoint tracking device; subconsciousness calculating means for calculating a subconsciousness degree of the subject based on the electroencephalogram data; and A pair that associates the viewpoint coordinates of the subject with the scene image or the snapshot image. Function as display means for displaying the scene video or the snapshot image associated with the subject's viewpoint coordinates and the subconscious degree on the same screen in synchronization with time series based on the time difference It is a program to make it. By installing the program of the second invention in a general-purpose computer, it is possible to obtain an analysis support apparatus capable of outputting both measurement results by the electroencephalograph and the viewpoint tracking apparatus so as to be easily analyzed.

  According to the present invention, it is possible to provide an analysis support apparatus and the like that can output both measurement results obtained by the electroencephalograph and the viewpoint tracking apparatus so as to be easily analyzed.

Overview of market research system 1 An example of data stored in the analysis support apparatus 2 Flow chart showing overall processing of market research system 1 Flow chart showing an example of filter calculation processing The figure explaining S41 The figure explaining S42 The figure explaining S43 The figure explaining S44 The flowchart which shows the process of the analysis assistance apparatus 2 in 1st Embodiment. Display example in the first embodiment The flowchart which shows the process of the analysis assistance apparatus 2 in 2nd Embodiment. Display example in the second embodiment The flowchart which shows the process of the analysis assistance apparatus 2 in 3rd Embodiment. Display example in the third embodiment

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. First, the definition of terms will be explained.

  Market research means that companies that provide products and services, companies that produce advertisements for products and services, etc. investigate consumer behavior in the market. Here, in the embodiment of the present invention, the content of the target product or service is not questioned. Hereinafter, the product and service content, the product packaging, and the advertisement of the product and service are collectively referred to as “content”.

  Examples of the content include moving images such as TVCM, paper or electronic media such as magazine advertisements and leaflets, and product placement including furniture such as product shelves and book shelves. In the case of product placement, it is assumed that the subject is moving. Content with motion, such as moving images, is referred to as “dynamic content”. Content that does not move, such as paper or electronic media, is referred to as “static content”. A first embodiment and a second embodiment to be described later target dynamic content and static content, and a third embodiment targets static content.

  The subconsciousness level is data obtained by quantifying the consciousness (unconsciousness) of the subject who is browsing the content on a certain scale based on the electroencephalogram data acquired by the electroencephalograph. The subconsciousness level may be considered to indicate, for example, an interest level indicating the degree of the subject's potential interest and an understanding level indicating the degree of the subject's potential understanding. In addition, the degree of subconsciousness is not limited to these examples, and there are various ways of understanding depending on the contents of market research. In the first embodiment, the second embodiment, and the third embodiment described later, this is regarded as the degree of interest.

  The contents common to all the embodiments will be described with reference to FIGS.

  FIG. 1 is a schematic diagram of a market research system 1. As shown in FIG. 1, the market research system 1 includes an analysis support device 2, an electroencephalograph 3, a viewpoint tracking device 4, and the like. The market research system 1 measures the electroencephalogram data and viewpoint coordinate data of the subject who is browsing the content, and assists the analyst to analyze the measurement results.

  In the example illustrated in FIG. 1, the analysis support apparatus 2 and the electroencephalograph 3 perform data transmission / reception via a wired cable. When the analysis support apparatus 2 and the electroencephalograph 3 are provided with a wireless communication device, the analysis support apparatus 2 and the electroencephalograph 3 may perform data transmission / reception via a radio wave.

  In the example illustrated in FIG. 1, the analysis support apparatus 2 and the viewpoint tracking apparatus 4 transmit and receive data via the storage medium 47. Examples of the storage medium 47 include a storage card typified by an SD memory card, a storage disk typified by a CD-R (Compact Disk-Recordable), and a USB (Universal Serial Bus) memory. There are auxiliary storage devices with terminals. When the analysis support apparatus 2 and the electroencephalograph 3 are provided with a wired cable I / O (Input / Output interface), the analysis support apparatus 2 and the electroencephalograph 3 may transmit and receive data via the wired cable. . When the analysis support apparatus 2 and the electroencephalograph 3 are provided with a wireless communication device, the analysis support apparatus 2 and the electroencephalograph 3 may perform data transmission / reception via a radio wave.

  The analysis support apparatus 2 supports the analysis of the measurement result by the electroencephalograph 3 and the viewpoint tracking apparatus 4 for the subject who is browsing the content. The analysis support apparatus 2 is a computer. Examples of the computer include a desktop PC (Personal Computer), a notebook PC, a smartphone, a tablet terminal, a mobile phone terminal, and a game terminal. Hereinafter, the analysis support apparatus 2 will be described as a general-purpose computer such as a desktop PC or a notebook PC.

  The analysis support apparatus 2 includes a control unit 21, a storage unit 22, a display unit 23, an input unit 24, an I / O 25, and the like.

  The control unit 21 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like. The CPU calls a program stored in the storage unit 22, ROM, storage medium, or the like to a work memory area on the RAM, executes it, controls the drive of each device, and realizes the processing described later performed by the analysis support device 2. The ROM is a non-volatile memory, and permanently stores programs such as a boot program and BIOS of the analysis support apparatus 2, data, and the like. The RAM is a volatile memory, and temporarily holds a program, data, and the like loaded from the storage unit 22, ROM, storage medium, and the like, and includes a work area used by the control unit 21 to perform various processes.

  The storage unit 22 is an HDD (Hard Disk Drive), for example, and stores a program executed by the control unit 21, data necessary for program execution, an OS (Operating System), and the like. As for the program, a control program corresponding to the OS and an application program for causing the analysis support apparatus 2 to execute processing described later are stored. Each of these program codes is read by the control unit 21 as necessary, transferred to the RAM, read by the CPU, and executed as various means.

  The display unit 23 includes a display device such as a liquid crystal panel and a logic circuit (such as a video adapter) for realizing the video function of the analysis support device 2 in cooperation with the display device. The input unit 24 inputs data and includes, for example, a keyboard, a pointing device such as a mouse, and an input device such as a numeric keypad. An operation instruction, an operation instruction, data input, and the like can be performed on the analysis support apparatus 2 via the input unit 24. The display unit 23 and the input unit 24 may be integrated like a touch panel display.

  The I / O 25 is a port or a transceiver for connecting peripheral devices (for example, an external storage device such as an electroencephalograph 3 and a storage medium 47, a printer (not shown), a network device (not shown)) to the analysis support device 2 It is. The analysis support apparatus 2 transmits / receives data to / from peripheral devices via the I / O 25. Examples of the I / O 25 include USB, IEEE 1394, RS-232C, and other ports, a drive device for reading and writing the storage medium 47, a wireless LAN device, a Bluetooth (registered trademark) transceiver, and the like. The connection form with the peripheral device may be wired or wireless.

  The electroencephalograph 3 includes a headband 31, an electrode 32, a converter 33, an amplifier 34, and the like. The electroencephalograph 3 has a structure in which an electrode 32 fixed by a headband 31 is in contact with the head of a subject, specifically, a position corresponding to Fp1 in the international 10-20 method (left frontal lobe). Fp1 is generally known to be able to measure reactions related to emotions and emotions. The converter 33 converts the analog signal output from the electrode 32 into a digital signal. The amplifier 34 amplifies the digital signal output from the converter 33 and outputs it to the I / O 25 of the analysis support apparatus 2. The sampling frequency in A / D conversion is, for example, 1024 Hz.

  Details of the electroencephalograph 3 are described in, for example, Japanese Unexamined Patent Application Publication No. 2010-131328 and Japanese Unexamined Patent Application Publication No. 2011-45541. As an example of the electroencephalograph 3, for example, a simple electroencephalograph such as “alphatec-IV” or “Brain Builder Unit” of the Brain Power Development Laboratory Co., Ltd. may be mentioned. In the electroencephalogram by a simple electroencephalograph, for example, one electrode 32 is attached to an electrically inactive earlobe, and the other electrode 32 is attached to an electrically active scalp to derive a potential difference between two electrodes. Measured by monopolar induction method.

  The viewpoint tracking device 4 includes a main body 41 and a recorder 42. The main body 41 and the recorder 42 may be integrated or separate.

  The main body 41 includes a scene camera 43, a viewpoint tracking sensor 44, a marker sensor 45, and the like. The marker sensor 45 is not essential. When the marker sensor 45 is used, a plurality of markers (not shown) are also required. The marker is an infrared marker, for example, and is installed to define an area to be analyzed.

  The scene camera 43 captures content and scenery that the subject is viewing. In the present embodiment, the scene camera 43 is a camera that captures a scene video and a snapshot image described later.

  The viewpoint tracking sensor 44 is a sensor for tracking the viewpoint of the subject. The viewpoint tracking sensor 44 includes, for example, an infrared light source and a receiver, and tracks the subject's viewpoint based on the principle of infrared corneal reflection detection. Since the principle of infrared corneal reflection detection is known, the description thereof is omitted.

  The marker sensor 45 communicates with the marker and detects the analysis area. The content that needs to detect the analysis area using the marker is, for example, a paper medium such as a magazine advertisement or a flyer (see the third embodiment). However, even if the content is a paper medium, there is a technique that does not use a marker as disclosed in Japanese Patent Application Laid-Open No. 2011-194105.

  The recorder 42 includes a control unit 46, a storage medium 47, and the like. The storage medium 47 is as described above. The control unit 46 stores, in the storage medium 47, scene images and snapshot images captured by the scene camera 43, subject coordinate data of the subject tracked by the viewpoint tracking sensor 44, analysis area data detected by the marker sensor 45, and the like. To do.

  As an example of the viewpoint tracking device 4, there are, for example, a spectacle type represented by “Tobii Glass Eye Tracker” of Toby Technology, and a display type represented by “Tobii TX300 Eye Tracker” of Toby Technology . When content can be output to a display, such as a TV commercial or a website, the subject may use a glasses type or a display type. When the subject is assumed to move (see the first and second embodiments) or when viewing an object such as a paper medium, the subject uses a glasses type (see the third embodiment).

  FIG. 2 is an example of data stored in the analysis support apparatus 2. The data stored in the storage unit 22 of the analysis support apparatus 2 includes the electroencephalogram data 50, the viewpoint coordinate data 55, the time difference 61 between the electroencephalogram measurement start time and the viewpoint measurement start time (hereinafter referred to as “time difference 61”), the scene. A video 62, a snapshot image 63, and the like.

  The electroencephalogram data 50 has a header portion and a main body portion. The main body is data with repetition. The header part includes at least an electroencephalogram measurement start time 51. The electroencephalogram measurement start time 51 is a time when measurement by the electroencephalograph 3 is started. The main body includes at least a measurement elapsed time 52 and an electroencephalogram 53. The measurement elapsed time 52 is an elapsed time from the electroencephalogram measurement start time 51. The electroencephalogram 53 is a digital signal that is A / D converted by the converter 33 and the amplifier 34. As will be described later, since the electroencephalogram 53 is converted into the subconsciousness level at a predetermined time interval (for example, 1 second), the main body portion of the electroencephalogram data 50 also has a data structure collected at each predetermined time interval. good.

  The viewpoint coordinate data 55 has a header part and a main body part. The main body is data with repetition. The header portion includes at least the viewpoint measurement start time 56. The viewpoint measurement start time 56 is a time when measurement by the viewpoint tracking device 4 is started. The main body includes at least a measurement elapsed time 57, a viewpoint x coordinate 58, and a viewpoint y coordinate 59. The measurement elapsed time 57 is an elapsed time from the viewpoint measurement start time 56. The viewpoint x-coordinate 58 and the viewpoint y-coordinate 59 are an x-coordinate and a y-coordinate indicating the viewpoint position of the subject in the coordinate system of the scene video 62 or the snapshot image 63, respectively, measured by the viewpoint tracking sensor 44. The viewpoint x coordinate 58 and the viewpoint y coordinate 59 are stored at the sampling interval of the viewpoint tracking sensor 44 (for example, 30 frames / second).

  The time difference 61 is the difference between the time when the electroencephalograph 3 starts measurement and the time when the viewpoint tracking device 4 starts measurement. There are two methods for measuring the time difference 61.

  In the first method, a subject or an analyst visually confirms when the electroencephalograph 3 starts measurement and when the viewpoint tracking device 4 starts measurement, and analyzes the time difference 61 of the relative time. Input to support device 2. For example, the subject or the analyst starts either the electroencephalograph 3 or the viewpoint tracking device 4 first, and the 0th second of the device started later corresponds to the second of the first started device. Is input to the analysis support apparatus 2. In the first method, the above-described electroencephalogram measurement start time 51 of the electroencephalogram data 50 and the viewpoint measurement start time 56 of the viewpoint coordinate data 55 are unnecessary. Therefore, the subject or the analyst does not need to match the clock of the electroencephalograph 3 with the clock of the viewpoint tracking device 4.

  In the second method, the control unit 21 of the analysis support apparatus 2 calculates the time difference 61 based on the electroencephalogram measurement start time 51 of the electroencephalogram data 50 and the viewpoint measurement start time 56 of the viewpoint coordinate data 55. For example, a value obtained by subtracting the viewpoint measurement start time 56 of the viewpoint coordinate data 55 from the brain wave measurement start time 51 of the brain wave data 50 is set as the time difference 61. When the time difference 61 is positive, it means that the electroencephalogram measurement start time 51 is earlier than the viewpoint measurement start time 56 by the time difference 61. When the time difference 61 is negative, it means that the viewpoint measurement start time 56 is earlier than the electroencephalogram measurement start time 51 by the time difference 61. In the second method, the analysis support apparatus 2 can automatically calculate the time difference 61 between the electroencephalogram data 50 and the viewpoint coordinate data 55, so that the burden on the analyst is reduced. However, the subject or the analyzer needs to match the clock of the electroencephalograph 3 with the clock of the viewpoint tracking device 4.

  The scene video 62 is a moving image file (for example, an avi file) captured by the scene camera 43. The scene image 62 is stored at a sampling interval comparable to the sampling interval of the viewpoint tracking sensor 44 (for example, 30 frames / second). In the case of the first embodiment and the second embodiment, the scene image 62 is essential.

  The snapshot image 63 is a still image file (for example, a jpeg file) captured by the scene camera 43. The snapshot image 63 is a single image file in which the entire content is included in the imaging range. In the case of the third embodiment, the snapshot image 63 is essential.

  FIG. 3 is a flowchart showing processing of the entire market research system 1. Although the measurement process of the time difference 61 is not illustrated in FIG. 3, the time difference 61 is measured by the first measurement method or the second measurement method described above, and the time difference 61 is stored in the storage unit 22 of the analysis support apparatus 2. Shall be stored in Further, it is premised that the filter calculation process illustrated in FIG. 4 is performed in advance and the filter used for the subconsciousness calculation process is obtained before the measurement process illustrated in FIG. 3 is performed.

  The electroencephalograph 3 measures the subject's electroencephalogram based on the measurement start and measurement end instructions from the analysis support apparatus 2 (S11). In the electroencephalograph 3, the converter 33 performs AD conversion at predetermined sampling intervals (S 12), the amplifier 34 amplifies (S 13), and transmits the amplified result to the analysis support apparatus 2 as the electroencephalogram data 50 ( S14).

  The main body 41 of the viewpoint tracking device 4 measures the viewpoint of the subject based on an instruction to start or end the measurement from the analyst or the subject (S21). Then, the recorder 42 of the viewpoint tracking device 4 stores the viewpoint coordinate data 55 in the storage medium 47 at predetermined sampling intervals (S22).

  The control unit 21 of the analysis support apparatus 2 receives the electroencephalogram data 50 from the electroencephalograph 3 and stores the electroencephalogram data 50 in the storage unit 22 (S31). Then, the control unit 21 performs frequency analysis by fast Fourier transform on the electroencephalogram data 50 (S32), calculates the subconscious degree of the subject's content by factor analysis, and adds the subject and content information to the subconscious degree. And it memorize | stores in RAM or the memory | storage part 22 (S33). The fast Fourier transform in S44 is performed, for example, with a window length of 1 second and a window time shift width of 1 second. The subconsciousness calculation process in S45 will be described later with reference to FIGS.

  The control unit 21 of the analysis support apparatus 2 inputs data from the storage medium 47 and stores the viewpoint coordinate data 55 and the scene video 62 or the snapshot image 63 in the storage unit 22 (S34). Next, the control unit 21 associates the subject's viewpoint coordinates with the scene image 62 or the snapshot image 63 based on the viewpoint coordinate data 55 (S35). Then, the control unit 21 of the analysis support apparatus 2 synchronizes the time series based on the time difference 61 to display the scene video 62 or the snapshot image 63 associated with the subject's viewpoint coordinates and the subconsciousness level on the display unit 23. Are displayed on the same screen (S36). The control unit 21 may not only display on the display unit 23 but also output it to a printer or send it to another computer. The display process will be described in detail in each embodiment.

  FIG. 4 is a flowchart illustrating an example of the filter calculation process. 3 and 4 are not processes for the same subject. The process illustrated in FIG. 4 is a preprocess of the measurement process illustrated in FIG. In the following, the degree of subconsciousness is regarded as “interesting level” in particular.

  As shown in FIG. 4, the control unit 21 of the analysis support apparatus 2 calculates the average of each frequency of data that is assumed to be uninteresting (S41). The data assumed to be uninterested is, for example, the EEG data 50 measured by an unspecified number of subjects without viewing video or music, or video or music that is clearly known to be uninterested. It is the electroencephalogram data 50 measured at the time. An unspecified number of subjects may be arbitrarily selected.

  FIG. 5 is a diagram for explaining S41. The table 70a in FIG. 5 illustrates the electroencephalogram data 50 processed for the plurality of subjects A, B,... In the same manner as S11 to S14 and S31 in FIG. Further, in Table 70b of FIG. 5, as an example of the result of the frequency analysis of the electroencephalogram data shown in Table 70a by the same method as S32 of FIG. 3, 1 second to 60 seconds every 1 second and 1 Hz every A power spectrum from 1 Hz to 24 Hz is shown. The control unit 21 calculates an average for each frequency from these power spectrum data. In Table 70b, the average of 1 Hz is “0.0”, the average of 2 Hz is “3.2”,..., And the average of 24 Hz is “1.2”.

  Returning to the description of FIG. The control unit 21 calculates the difference between the average of data assumed to be uninteresting and the data of each subject used for filter calculation (S42). Each subject's data used for filter calculation is also data of a power spectrum obtained by performing frequency analysis in the same manner as S11 to S14, S31, and S32 in FIG.

  FIG. 6 is a diagram for explaining S42. Table 71 in FIG. 6 shows an average for each frequency of the data of the power spectrum that is assumed to have no interest calculated in S41. Table 72 shows power spectrum data of a subject (= subject A) from 1 second to 60 seconds per second and from 1 Hz to 24 Hz every 1 Hz. The control unit 21 calculates the difference between the data in Table 71 and the data in Table 72 for each time and frequency. Table 73 shows the difference results for each time and frequency. In Table 73, 1 second at 1 Hz is “0.0”, 2 seconds at 1 Hz is “0.0”,... 60 seconds at 1 Hz is “0.0”, 1 second at 2 Hz is “0.2”, 2 Hz second second is “0.8”,... 2 Hz 60 second is “0.8”,..., 24 Hz first second is “1.8”, The second second of 24 Hz is “0.2”,..., And the second second of 24 Hz is “0.8”.

  Returning to the description of FIG. The control unit 21 calculates the correlation matrix and eigenvalue of the difference data calculated in S42, and determines the initial factor number (S43). The initial factor number is required for the factor analysis performed in S44.

FIG. 7 is a diagram for explaining S43. A table 74 in FIG. 7 shows the difference data calculated in S42. The control unit 21 calculates a correlation matrix between the column vectors in Table 74. In Table 74, the 1 Hz column vector is (0.0, 0.0,..., 0.0) ^t , and the 2 Hz column vector is (0.2, 0.8,..., 0.8). A column vector of ^{t 1} ,..., 60 Hz is (1.8, 0.2,..., 0.8) ^t .

  Table 75 in FIG. 7 shows a correlation matrix between the column vectors in Table 74. In Table 75, the matrix component (1,1) is “1”, the matrix component (1,2) is “0.81”,..., The matrix component (1,24) is “0.12”, and the matrix component (2,1) is “0.81”, matrix component (2,2) is “1”,..., Matrix component (2,24) is “0.20”,. , 1) is “0.12”, the matrix component (2, 2) is “0.20”,..., And the matrix component (24, 24) is “1”. Next, the control unit 21 calculates eigenvalues for the correlation matrix in Table 75.

  Table 76 of FIG. 7 shows eigenvalues for the correlation matrix of Table 75. In Table 76, the eigenvalue of 1 Hz is “13.50”, the eigenvalue of 2 Hz is “2.160”,..., And the eigenvalue of 24 Hz is “0.008”. Next, the control unit 21 plots the eigenvalues in Table 76 on a graph (scree plot).

  A graph 77 in FIG. 7 shows a line graph of the eigenvalues in Table 76. For example, the user determines a part where the slope is gentle from the graph 77 and determines the initial factor number. In the graph 77, since the slope between the frequency of 3 Hz and 4 Hz (dotted line 78) is gentle, the initial factor number is determined to be “3”. In addition, for example, the control unit 21 compares the slope of the line graph with a predetermined threshold value from the lower frequency, and determines that the slope is gentle when the frequency becomes equal to or less than the threshold value, and the initial factor. The number may be determined.

  Returning to the description of FIG. The control unit 21 increases the factor number by 1 from the initial factor number, and executes factor analysis until the cumulative contribution rate reaches a predetermined ratio (S44). About a predetermined ratio, although you may determine arbitrarily, it is 0.8, for example.

  FIG. 8 is a diagram for explaining S44. Table 79 in FIG. 8 shows the results of the factor analysis. Table 79 shows a calculation result by “R” which is an open source statistical analysis software. The factor loading indicates how much the common factor affects the observed variable. The commonality is the sum of squares of the factor load for each observation variable. A high value of commonality means that the observed variable is well explained by common factors.

  Table 79 shows factor loadings and cumulative contribution rates up to the second factor for illustrative purposes. If the number of factors is “3”, the factor loading and cumulative contribution rate of the third factor are also calculated. If the cumulative contribution ratio of the third factor does not exceed the predetermined ratio, the control unit 21 sets the number of factors to “4” and executes the factor analysis again. Note that details of the processing of S43 and S44 are also described in Japanese Patent Application Laid-Open Nos. 2010-131328 and 2011-45541.

  Returning to the description of FIG. The control unit 21 calculates a filter weighted by the factor load amount considering the contribution rate for each frequency (S45). The calculation formula of the filter calculated | required from N test subjects is as follows.

Here, z: frequency, i: number of subjects, j: number of factors, H (z): filter (weight) of frequency z, F _ij (z): frequency z, subject i, factor loading of factor j, P _ij : Subject i, contribution ratio of j-th factor.

  The control unit 21 calculates the degree of interest in S45 of FIG. 3 using the filter calculated in this way. The formula for calculating the degree of interest is as follows.

  Here, z: frequency, t: time, R (t): degree of interest in t seconds, B (z, t): amplitude of electroencephalogram frequency z in t seconds, H (z): filter of frequency z is there.

  In this way, the control unit 21 calculates the degree of subconscious awareness (degree of interest) of the subject based on the electroencephalogram data 50 measured by the electroencephalograph 3. As in the first to third embodiments to be described later, the market research system 1 is configured such that the analyst analyzes both the subconscious degree (interest degree) of the subject and the viewpoint tracking result by the viewpoint tracking device 4. Output as easy as possible.

<First Embodiment>
The first embodiment will be described with reference to FIGS. 9 and 10.

  FIG. 9 is a flowchart showing the processing of the analysis support apparatus 2 in the first embodiment. As shown in FIG. 9, the control unit 21 of the analysis support apparatus 2 generates time-series graph data from the degree of interest 80 calculated every predetermined sampling interval (for example, 1 second) (S51).

  The control unit 21 associates the viewpoint coordinate data 55 with the scene image 62 frame by frame (S52). If the sampling intervals of the viewpoint coordinate data 55 and the scene video 62 are the same, the control unit 21 associates them one by one in time series. When the sampling intervals of the viewpoint coordinate data 55 and the scene video 62 are different, the control unit 21 performs an appropriate interpolation process or thinning process, and then associates them in a one-to-one order in time series.

  The control unit 21 synchronizes the time series based on the time difference 61, and displays the curve data of the degree of interest 80 generated in S51 and the scene video 62 associated with the viewpoint coordinates in S52 on the same screen display unit 23. (S53). The “same screen” does not need to have the same display area (window), and any display area (window) can be used as long as the analyzer can visually recognize the curve data of the degree of interest 80 and the scene video 62 at the same time. ) May be different.

  FIG. 10 is a display example in the first embodiment. In the example illustrated in FIG. 10, the content is dynamic content on the assumption that the subject moves. In this example, a plurality of types of pamphlets are placed on the shelf, and for example, it is investigated which pamphlet the subject is interested in.

  The measurement result display screen 81a shown in FIG. 10 includes an interest curve display area 82, a scene video display area 83, and a measurement information display area 84. The interest degree curve display area 82 is an area for displaying the curve data of the interest degree 80. The scene video display area 83 is an area for displaying the scene video 62. The measurement information display area 84 is an area for displaying various information of measurement results obtained by the electroencephalograph 3 and the viewpoint tracking device 4.

  The analysis support apparatus 2 displays a graph of time on the horizontal axis and interest level (%) or interest level change graph on the vertical axis in the interest level curve display area 82. The degree of interest (%) indicated by the solid line is curve data of the degree of interest 80 generated in S51. The interest level change indicated by a dotted line is a change amount of interest level (corresponding to a differential value). In the example shown in FIG. 10, the interest level change indicates a difference from the interest level one second ago. The timeline 85 shows the playback position of the scene video 62 played back in the scene video display area 83. If the scene video 62 is being continuously reproduced, the timeline 85 follows the playback position of the scene video 62 and slides from left to right.

  The analysis support apparatus 2 embeds, for example, a general-purpose video playback module in the scene video display area 83. The scene video display area 83 has buttons for playback, pause, fast forward, rewind, mute (silence), volume adjustment, and the like. The viewpoint mark 86a indicates the position of the viewpoint coordinate data 55 associated in S52. In FIG. 10, there are two viewpoint marks 86a. This shows how the position of the viewpoint coordinate data 55 is switched. When the position of the viewpoint coordinate data 55 does not change, there is one viewpoint mark 86a.

  The analysis support apparatus 2 displays, for example, an interest level (%) and an interest level change display / non-display setting (Change Chart Visible), an interest level 80, and an interest level change statistical value (Information ), The playback time (movie length) of the scene video 62, the EEG data shift time, and the like are displayed. The electroencephalogram shift time (EEG data shift) corresponds to a time difference 61.

  As illustrated in FIG. 10, in the first embodiment, the control unit 21 of the analysis support apparatus 2 associates the viewpoint coordinates of the subject with the scene image 62 frame by frame. Then, the control unit 21 reproduces the scene video 62 on the display unit 23 while superimposing the viewpoint mark 86a indicating the position of the viewpoint coordinates, and also superimposes the timeline 85 indicating the reproduction position of the scene video 62 while substituting the subconsciousness degree. Are plotted on the display unit 23 as a time-series graph.

  According to the first embodiment, in the case of a moving image such as a TVCM or dynamic content such as a subject moving, the analyst can simultaneously view the subject's subconsciousness and the change in viewpoint. For example, the analyst can easily visually recognize which scene and which position of the dynamic content the subject is viewing when the subconsciousness is at the peak.

Second Embodiment
The second embodiment will be described with reference to FIGS. 11 and 12. In 2nd Embodiment, the same number is attached | subjected to the element same as the element of 1st Embodiment, and duplication description is abbreviate | omitted.

  FIG. 11 is a flowchart showing the processing of the analysis support apparatus 2 in the second embodiment. As shown in FIG. 11, the control unit 21 of the analysis support apparatus 2 generates time-series graph data from the degree of interest 80 calculated at predetermined sampling intervals (for example, 1 second) (S61).

  The control unit 21 associates the viewpoint coordinate data 55 with the scene image 62 frame by frame (S62). Furthermore, the control unit 21 decorates the mapped viewpoint coordinates according to the degree of interest 80 (S63). As the decoration mode, it is conceivable to change the shape, pattern, and color of the viewpoint mark or add another mark according to the degree of interest 80.

  Based on the time difference 61, the control unit 21 synchronizes the time series with the curve data of the degree of interest 80 generated in S61 and the scene image 62 on which the viewpoint mark decorated in S63 is superimposed on the same screen. This is displayed on the display unit 23 (S64).

  FIG. 12 is a display example in the second embodiment. In the example illustrated in FIG. 12, the content is dynamic content on the assumption that the subject moves as in the example illustrated in FIG. 10.

  The measurement result display screen 81b shown in FIG. 12 includes an interest curve display area 82, a scene video display area 83, a measurement information display area 84, and a decoration degree 87. The decoration degree 87 indicates the degree of decoration in S63.

  The analysis support apparatus 2 superimposes the decorated viewpoint mark 86 b on the scene video 62 in the scene video display area 83. In the example shown in FIG. 12, the decoration degree 87 is expressed by the difference in the pattern of the viewpoint mark. That is, the pattern of the viewpoint mark 86b is changed according to the degree of interest 80. Although the example of changing the color cannot be illustrated due to restrictions of the patent drawing, for example, “red”, “orange”, “yellow”, “yellowish green” in order from the one with the highest degree of interest 80, such as thermography. When the color is changed such as “” or “green”, it is easy to understand intuitively.

  As shown in FIG. 12, in the second embodiment, the control unit 21 of the analysis support apparatus 2 associates the viewpoint coordinates of the subject with the scene image 62 frame by frame, and further sets the viewpoint mark 86b indicating the position of the viewpoint coordinates. The degree of decoration is determined according to the degree of subconsciousness. Then, the control unit 21 reproduces the scene video 62 while superimposing the viewpoint marks 86b decorated according to the degree of decoration, and also changes the subconsciousness degree while superimposing the timeline 85 indicating the reproduction position of the scene video 62. Is drawn on the display unit 23 as a time-series graph.

  According to the second embodiment, in the case of a dynamic image such as a moving image such as a TV commercial or a subject moving, the analyst can visually recognize the subject's subconsciousness and changes in the viewpoint at the same time. In particular, since the viewpoint mark 86b is decorated and displayed according to the subconsciousness level, the analyst can visually recognize the change in the subconsciousness level on the dynamic content.

<Third Embodiment>
The third embodiment will be described with reference to FIGS. 13 and 14. In 3rd Embodiment, the same number is attached | subjected to the element same as the element of 1st Embodiment or 2nd Embodiment, and duplication description is abbreviate | omitted.

  FIG. 13 is a flowchart showing the processing of the analysis support apparatus 2 in the third embodiment. As shown in FIG. 13, the control unit 21 of the analysis support apparatus 2 converts the coordinates of the viewpoint coordinate data 55 into the coordinate system of the snapshot image 63 (S71). When the marker is used, the control unit 21 performs coordinate conversion using a function realized by “Tobii Studio software” of Toby Technology, for example. Moreover, when not using a marker, the control part 21 performs coordinate conversion using the technique currently disclosed by Unexamined-Japanese-Patent No. 2011-194105, for example. Since both are well-known techniques, detailed description is omitted. In addition, when using the x coordinate and y coordinate which show a test subject's viewpoint position in the coordinate system of the snapshot image 63, the coordinate conversion in S71 is unnecessary.

  The control unit 21 associates the viewpoint coordinates converted into the coordinate system of the snapshot image 63 with the snapshot image 63 (S72). That is, a plurality of viewpoint coordinates are associated with a single snapshot image 63.

  The control unit 21 synchronizes the time series based on the time difference 61, decorates the viewpoint mark indicating the viewpoint coordinates according to the degree of interest 80, and displays the snapshot image 63 on which the decorated viewpoint mark is superimposed on the display unit 23. (S73). The decoration mode is the same as in the second embodiment.

  FIG. 14 is a display example in the third embodiment. In the example shown in FIG. 14, the content is a static content of a paper medium. In this example, the leaflet is a home appliance, and for example, it is investigated to which position of the leaflet the subject is interested.

  The measurement result display screen 81c shown in FIG. 14 includes a snapshot image 63, a decoration degree 87, and a plurality of viewpoint marks 86c. When decorating the viewpoint mark 86c, the control unit 21 of the analysis support apparatus 2 further calculates the viewing time for each viewpoint coordinate, and determines the area degree of the viewpoint mark 86c according to the viewing time. In FIG. 14, five viewpoint marks 86c are superimposed on the snapshot image 63 with different decorations and areas.

  As shown in FIG. 14, in the third embodiment, the control unit 21 of the analysis support apparatus 2 performs coordinate conversion of the subject's viewpoint coordinates into the coordinate system of the snapshot image 63 and associates it with a single snapshot image 63. Further, the degree of decoration of the viewpoint mark 86c indicating the position of the viewpoint coordinate is determined according to the degree of subconsciousness, the viewing time is calculated for each viewpoint coordinate, and the area degree of the viewpoint mark 86c is determined according to the viewing time. . Then, the control unit 21 displays a snapshot image 63 on the display unit 23 by superimposing a viewpoint mark 86c having an area degree decorated according to the degree of decoration for each viewpoint coordinate.

  According to the third embodiment, in the case of a static content such as a magazine advertisement or a flyer, the analyst can simultaneously recognize the subject's subconsciousness and the change in viewpoint. For example, the analyst can easily visually recognize which position of the static content the subject is watching for how long.

  The preferred embodiments of the analysis support apparatus and the like according to the present invention have been described above with reference to the accompanying drawings, but the present invention is not limited to such examples. It will be apparent to those skilled in the art that various changes or modifications can be conceived within the scope of the technical idea disclosed in the present application, and these naturally belong to the technical scope of the present invention. Understood.

1 ... Market research system 2 ... Analysis support device 3 ... Electroencephalograph 4 ... Perspective tracking device 50 ... Electroencephalogram data 55 ... Perspective coordinate data 61 ......... EEG measurement start time and viewpoint Time difference between measurement start times 62 ......... Scene image 63 ......... Snapshot image 80 ......... Interest level

Claims (6)

An analysis support device that supports analysis of measurement results by an electroencephalograph and a viewpoint tracking device for a subject who is browsing content,
The subject's electroencephalogram data measured by the electroencephalograph, the subject's viewpoint coordinate data measured by the viewpoint tracking device, the scene video or snapshot image relating to the content imaged by the viewpoint tracking device, and Storage means for storing the time difference between the measurement start time by the electroencephalograph and the measurement start time by the viewpoint tracking device;
Subconsciousness calculating means for calculating the subconsciousness of the subject based on the electroencephalogram data;
Association means for associating the subject's viewpoint coordinates with the scene image or the snapshot image based on the viewpoint coordinate data;
Display means for synchronizing the time series based on the time difference, displaying the scene video or the snapshot image associated with the subject's viewpoint coordinates, and the subconsciousness on the same screen,
An analysis support apparatus comprising: The electroencephalogram data includes a measurement start time by the electroencephalograph, and the viewpoint coordinate data includes a measurement start time by the viewpoint tracking device,
Calculating the time difference based on the electroencephalogram data and the viewpoint coordinate data, and storing the time difference in the storage means;
The analysis support apparatus according to claim 1, further comprising: The association means associates the viewpoint coordinates with the scene image frame by frame,
The display means reproduces the scene video while superimposing a viewpoint mark indicating the position of the viewpoint coordinates, and superimposes a timeline indicating a reproduction position of the scene video while displaying a change in the subconsciousness in a time series. The analysis support apparatus according to claim 1, wherein the analysis support apparatus is drawn as a graph. The association means associates the viewpoint coordinates with the scene image frame by frame, and further determines the degree of decoration of a viewpoint mark indicating the position of the viewpoint coordinates according to the subconsciousness level,
The display means reproduces the scene video while superimposing the viewpoint marks decorated according to the degree of decoration, and superimposes a timeline indicating a playback position of the scene video to change the subconsciousness level. The analysis support apparatus according to claim 1, wherein the analysis support apparatus is drawn as a time-series graph. The association means performs coordinate conversion of the viewpoint coordinates into a coordinate system of the snapshot image and associates the viewpoint coordinates with a single snapshot image, and further determines the degree of decoration of the viewpoint mark indicating the position of the viewpoint coordinates as the latent image. While determining according to the degree of consciousness, calculating the viewing time for each viewpoint coordinate to determine the area degree of the viewpoint mark according to the viewing time,
The display means displays the snapshot image by superimposing the viewpoint mark having an area of the area degree decorated according to the degree of decoration for each viewpoint coordinate. The analysis support apparatus according to claim 2. A program for causing a computer to function as an analysis support device that supports analysis of measurement results by an electroencephalograph and a viewpoint tracking device for a subject who is browsing content,
The subject's electroencephalogram data measured by the electroencephalograph, the subject's viewpoint coordinate data measured by the viewpoint tracking device, the scene video or snapshot image relating to the content imaged by the viewpoint tracking device, and Storage means for storing the time difference between the measurement start time by the electroencephalograph and the measurement start time by the viewpoint tracking device;
Subconsciousness calculating means for calculating the subconsciousness of the subject based on the electroencephalogram data;
Association means for associating the subject's viewpoint coordinates with the scene image or the snapshot image based on the viewpoint coordinate data;
A program for functioning as a display unit that synchronizes time series based on the time difference and displays the scene video or the snapshot image associated with the subject's viewpoint coordinates and the subconscious degree on the same screen. .

Images