Content evaluation device and content evaluation method

Abstract

A storage unit (14) stores a group correspondence table (14a) in which a plurality of stimuli to be processed are mapped to each stimulus group classified by a user. An acquisition unit (15b) acquires biometric information when stimuli are presented to the user. A calculation unit (15c) calculates a distance matrix representing the correlation between sets of biometric information. A presentation unit (15d) uses the calculated distance matrix to present each stimulus corresponding to biometric information, and the positional relationship between each group.

Description

Content evaluation device and content evaluation method

[0001] The present invention relates to a content evaluation device and a content evaluation method.

[0002] Conventionally, a method has been proposed for evaluating the quality of content by taking into consideration differences in content genres using biological information such as electroencephalograms (see Patent Literature 1). For example, content evaluation is performed by using electroencephalogram data of a subject (user) while viewing content, and giving a high rating if the subject (user) shows a specific tendency for each content genre, or determining an evaluation value based on similarity with the electroencephalogram data of other subjects.

[0003] Japanese Patent Application Laid-Open No. 2017-192416

[0004] However, with conventional technologies, it may be difficult to evaluate how each user perceives content when viewing it. For example, while conventional technologies evaluate the quality of content taking into account differences in genre, they cannot evaluate content across multiple genres or express how the user perceives the differences between genres.

[0005] The present invention has been made in view of the above, and has an object to evaluate how each user perceives content when viewing the content.

[0006] In order to solve the above-mentioned problems and achieve the object, the content evaluation device of the present invention is characterized by having a memory unit that stores multiple stimuli to be processed in correspondence with groups of each stimulus classified by a user, an acquisition unit that acquires biometric information when the stimuli are presented to the user, a calculation unit that calculates a distance matrix that represents the correlation between the biometric information, and a presentation unit that uses the calculated distance matrix to present the positional relationship of each stimuli and each group that corresponds to the biometric information.

[0007] According to the present invention, it is possible to evaluate how each user perceives content when viewing the content.

[0008] Fig. 1 is a schematic diagram illustrating a general configuration of a content evaluation device according to this embodiment. Fig. 2 is a diagram illustrating the data configuration of a group correspondence table. Fig. 3 is a diagram illustrating processing by an acquisition unit. Fig. 4 is a diagram illustrating a distance matrix. Fig. 5 is a diagram illustrating processing by a presentation unit. Fig. 6 is a flowchart illustrating a content evaluation processing procedure. Fig. 7 is a diagram illustrating an example of a computer that executes a content evaluation program.

[0009] Hereinafter, an embodiment of the present invention will be described in detail with reference to the drawings. Note that the present invention is not limited to this embodiment. In addition, in the description of the drawings, the same parts are designated by the same reference numerals.

[0010] [Configuration of Content Evaluation Device] Fig. 1 is a schematic diagram illustrating the general configuration of a content evaluation device of this embodiment. As illustrated in Fig. 1, a content evaluation device 10 of this embodiment is realized by a general-purpose computer such as a personal computer, and includes an input unit 11, a biological information measurement unit 11a, an output unit 12, a communication control unit 13, a storage unit 14, and a control unit 15.

[0011] The input unit 11 is realized using input devices such as a keyboard and a mouse, and inputs various instruction information such as a command to start processing to the control unit 15 in response to input operations by an operator.

[0012] The biological information measurement unit 11a measures biological information such as movements and reactions expressed in the user's behavior. For example, it is an electroencephalograph that measures brain waves on the scalp, and measures the brain waves of the user wearing the electroencephalograph in real time. Note that the biological information measurement unit 11a is not limited to an electroencephalograph, and may be, for example, an eye tracker that measures eye movement or an electrical skin resistance meter.

[0013] The output unit 12 is realized by a display device such as a liquid crystal display, a printing device such as a printer, etc. For example, the output unit 12 presents to the user a stimulus to be processed in the content evaluation process described below, and displays the results of the content evaluation process. Note that in this embodiment, the output unit 12 has a function of switching between and displaying multiple images, which are examples of the stimulus to be processed, at regular intervals.

[0014] The communication control unit 13 is realized by a NIC (Network Interface Card) or the like, and controls communication between the control unit 15 and external devices via telecommunication lines such as a LAN (Local Area Network) or the Internet. For example, the communication control unit 13 controls communication between the control unit 15 and a management device that manages various types of information, a measurement device equipped with the biological information measurement unit 11a, or the like.

[0015] The storage unit 14 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 14 stores in advance processing programs that operate the content evaluation device 10, data used during execution of the processing programs, and the like, or temporarily stores them each time processing is performed. The storage unit 14 may be configured to communicate with the control unit 15 via the communication control unit 13.

[0016] In this embodiment, the storage unit 14 stores a group correspondence table 14a, biological information 14b, etc. The group correspondence table 14a indicates the correspondence between each stimulus (content) and the group of each stimulus classified by the user.

[0017] Here, Fig. 2 is a diagram for explaining the data configuration of the group correspondence table 14a. As illustrated in Fig. 2, the group correspondence table 14a defines to which group each stimulus belongs, and is specified by the user. In Fig. 2, images of strawberries, grapefruits, watermelons, tomatoes, pumpkins, cabbages, and carrots are shown as examples of "vegetable and fruit images." Of these, strawberries and grapefruits are defined by the user as the △ group. Furthermore, carrots, cabbages, and pumpkins are defined by the user as the ☆ group. On the other hand, tomatoes and watermelons are set as not belonging to either group.

[0018] Each group may be assigned an appropriate label based on the user's sensibility. For example, the △ group may be assigned a fruit label and the ☆ group a vegetable label, or the △ group may be assigned a likes label and the ☆ group a dislikes label. Furthermore, the number of groups and stimuli is not particularly limited, and each stimulus may be set to belong to multiple groups.

[0019] For example, the group selection unit 15a, which will be described later, receives input from the user specifying the group of each stimulus via the input unit 11 or the communication control unit 13 in advance of the content evaluation process, which will be described later, or at the beginning of the content evaluation process, and generates the group correspondence table 14a.

[0020] Then, in the content evaluation process described later, the content evaluation device 10 refers to the group correspondence table 14a and presents the positional relationship and group of each stimulus to the user.

[0021] Furthermore, the group correspondence table 14a is not limited to being set in advance of the content evaluation process described below or at the beginning of the content evaluation process. For example, the content evaluation process may generate the group correspondence table 14a by presenting the positional relationships of the stimuli to the user without displaying the groups and having the user specify the groups of the stimuli.

[0022] Returning to the explanation of FIG. 1 , the control unit 15 is realized using a CPU (Central Processing Unit), an NP (Network Processor), an FPGA (Field Programmable Gate Array), or the like, and executes a processing program stored in memory. As a result, the control unit 15 functions as a group selection unit 15a, an acquisition unit 15b, a calculation unit 15c, and a presentation unit 15d, as exemplified in FIG. 1 , and executes content evaluation processing. Note that these functional units may each be implemented in different hardware, or some of them may be implemented in different hardware. The control unit 15 may also include other functional units.

[0023] The group selection unit 15a receives input from the user specifying a group of each stimulus, and generates the group correspondence table 14a. Specifically, as described above, the group selection unit 15a receives input from the user specifying a group of each stimulus to be processed via the input unit 11 or the communication control unit 13 in advance of the content evaluation process described below, or at the beginning of the content evaluation process, and generates the group correspondence table 14a. The group selection unit 15a stores the generated group correspondence table 14a in the storage unit 14.

[0024] The acquisition unit 15b acquires biological information when the stimulus to be processed is presented to the user. Specifically, the acquisition unit 15b presents the stimulus to be processed to the output unit 12 and acquires the biological information output from the biological information measurement unit 11a worn by the user who is gazing at the output unit 12.

[0025] FIG. 3 is a diagram for explaining the processing of the acquisition unit. The stimulus to be processed is, for example, an image in a genre such as fruits and vegetables, living things, or fashion. The stimulus is not limited to an image, but may be music, video, or the like. In this case, the content evaluation device 10 is equipped with a speaker. In the example shown in FIG. 3, a strawberry from among the "images of fruits and vegetables" is presented to the user, and electroencephalograms are acquired as bioinformation from an electroencephalograph, which is a bioinformation measurement unit 11a worn by the user.

[0026] The acquiring unit 15b stores the acquired biometric information in the storage unit 14. For example, the acquiring unit 15b acquires electroencephalogram data, which is time-series data of electroencephalogram waveforms themselves, and stores the electroencephalogram data as biometric information 14b in the storage unit 14 in association with a content identifier that identifies the stimulus for each section in which a stimulus is displayed.

[0027] The acquiring unit 15b may acquire biological information multiple times for presentation of one type of stimulus. Furthermore, the acquiring unit 15b may present the stimuli in a random order to reduce the influence of the order on measurement accuracy.

[0028] Returning to the description of Fig. 1, the calculation unit 15c calculates a distance matrix that represents the correlation between pieces of biological information. At that time, the calculation unit 15c calculates the distance matrix by using an average value of the biological information of the stimulation corresponding to a group as the biological information of the group.

[0029] Specifically, the calculation unit 15c first filters the electroencephalogram data of the biological information 14b to reduce the influence of noise. Next, when electroencephalogram data is acquired multiple times in response to one type of stimulus, the calculation unit 15c averages the electroencephalogram data for each stimulus, and sets this as the electroencephalogram data for each stimulus.

[0030] Furthermore, the calculation unit 15c uses the group correspondence table 14a to calculate the arithmetic mean of the electroencephalogram data corresponding to each stimulus group. For example, in the example shown in Fig. 2, the calculation unit 15c calculates the arithmetic mean of all the electroencephalogram data when strawberries and grapefruits in the △ group are presented as stimuli. Similarly, the calculation unit 15c calculates the arithmetic mean of all the electroencephalogram data when carrots, cabbage, and pumpkins in the ☆ group are presented as stimuli, and this is used as the electroencephalogram data for each group.

[0031] The calculation unit 15c then calculates a distance matrix from the correlation coefficients between the electroencephalogram data for each stimulus and each group, which is an index indicating how far the electroencephalogram data corresponding to each stimulus and each group is from other electroencephalogram data.

[0032] Here, Figure 4 is a diagram for explaining the distance matrix. As shown in Figure 4, the number of rows and the number of columns of the distance matrix correspond to the sum of the number of stimuli and the number of groups, respectively, and the diagonal elements are 0.0. For example, when Pearson's product-moment correlation coefficient is applied as the correlation coefficient r, -1≦r≦1, and the value range of the distance matrix is ​​from 0 to 1, as expressed by (1-r) / 2.

[0033] In the example shown in Figure 4, the electroencephalogram data corresponding to carrots perfectly match, with the distance calculated to be 0.00. The distance between the electroencephalogram data corresponding to carrots and the electroencephalogram data corresponding to cabbage is calculated to be 0.25. The distance between the electroencephalogram data of the △ group and the electroencephalogram data corresponding to strawberries of the △ group is calculated to be 0.10. In contrast, the distance between the electroencephalogram data corresponding to strawberries and the electroencephalogram data corresponding to grapefruit of the same △ group is calculated to be 0.13, with the distance to the △ group electroencephalogram data derived from the average value being a smaller value.

[0034] The processing by the calculation unit 15c is not limited to the above. For example, it is not necessary to treat all EEG data equally, and only a portion may be extracted and used. Furthermore, the EEG data may be subjected to preprocessing such as power spectral density estimation to convert the data into frequency components. For example, the calculation unit 15c may use only a portion of the frequency components, or may weight specific frequency components to strongly influence them.

[0035] In this case, the calculation unit 15c may prepare in advance variations in a list of frequency components to be referenced and preprocessing methods, and switch between them for each group and its label setting. For example, when calculating the distance of a group, the calculation unit 15c may use, instead of all EEG data, the stimuli of the group that have the smallest total distance. Alternatively, the calculation unit 15c may increase the weight of different frequency components for each label setting. For example, the calculation unit 15c may increase the weight of the 8-13 Hz frequency component of the EEG data for the label "like / dislike," and increase the weight of the 4-7 Hz frequency component of the EEG data for the label "red / blue." In this way, the calculation unit 15c may perform different processing for each label setting.

[0036] Returning to the description of Fig. 1, the presentation unit 15d presents the positional relationship between each stimulus and each group corresponding to the biological information using the calculated distance matrix. The presentation unit 15d also presents the range of the group using the average value of the group and the biological information corresponding to the stimuli of the group that is farthest from the average value.

[0037] 5 is a diagram illustrating the processing of the display unit. For example, the display unit 15d first calculates the positional relationship of each stimulus and each group as one-dimensional coordinates using multidimensional scaling (MDS). As a result, the one-dimensional coordinates of each stimulus and each group are calculated so that the more similar the EEG data, the closer the stimulus and the group, and conversely, the more different the stimulus and group, the farther the stimulus and group.

[0038] Furthermore, the presentation unit 15d calculates the radius of each group so that all stimuli in each group are included. For example, the presentation unit 15d calculates the absolute value of the difference between the coordinates of the group and the coordinates of the farthest stimulus in this group as the radius of the group.

[0039] The coordinates of each stimulus and each group and the radius of the group are not limited to one-dimensional coordinates. The presentation unit 15d may calculate the coordinates of each stimulus and each group and the radius of the group using a dimension reduction method such as UMAP (Uniform Manifold Approximation and Projection).

[0040] The presentation unit 15d then illustrates the positional relationship between each stimulus and each group using the calculated coordinates of each stimulus and each group and the radius of each group, as illustrated in FIG. 5 . In FIG. 5 , icons representing each stimulus and each group are arranged on a one-dimensional coordinate system, and the range of each group is indicated by an ellipse. In the example shown in FIG. 5 , it can be seen that the triangle group, which includes strawberries and grapefruit, includes watermelon and tomatoes, and that tomatoes are also included in the star group, which includes carrots, cabbage, and pumpkins. Therefore, it can be seen that the user evaluates watermelon as belonging to the same group as strawberries and grapefruit, and evaluates tomatoes as belonging to both the triangle group and the star group.

[0041] In this way, the content evaluation device 10 sets a virtual item called a group by averaging all of the electroencephalogram data corresponding to stimuli linked to a user-defined group. Then, the center coordinates and radius of the group are determined by calculating a correlation coefficient and a distance matrix, and the range of the group is visually illustrated. In this case, by averaging all of the electroencephalogram data linked to the group, particularly for electroencephalogram data containing a lot of noise, it becomes possible to perform a noise-robust analysis.

[0042] This makes it possible to express, for example, that a certain stimulus belongs to both of two groups, that a certain stimulus does not belong to either group, that a certain group is included in another group, or that there is no overlap between the two groups. In this way, it becomes possible to illustrate the user's subjective perception in more detail.

[0043] [Content Evaluation Process] Next, the content evaluation process performed by the content evaluation device 10 according to this embodiment will be described with reference to Fig. 6. Fig. 6 is a flowchart showing the procedure of the content evaluation process. The flowchart in Fig. 6 starts, for example, when the user performs an operation input to instruct the start of the process.

[0044] First, the group selection unit 15a receives an input from the user specifying the group of each stimulus, and generates the group correspondence table 14a (step S1).

[0045] Next, the acquisition unit 15b acquires biological information when the target stimulus is presented to the user (steps S2 to S4). Specifically, the acquisition unit 15b presents the target stimulus to the output unit 12 and acquires the biological information output from the biological information measurement unit 11a worn by the user who is gazing at the output unit 12. For example, the acquisition unit 15b selects the target stimulus in a random order, and repeats the process of acquiring the measurement value of the biological information when the stimulus is presented from the biological information measurement unit 11a for all stimuli.

[0046] Next, when EEG data is acquired multiple times for one type of stimulus, the calculation unit 15c calculates an arithmetic average of the EEG data for each stimulus, and sets this as the EEG data for that stimulus. Furthermore, the calculation unit 15c calculates an arithmetic average of the EEG data corresponding to each stimulus group using the group correspondence table 14a, and sets this as the EEG data for that group (step S5).

[0047] Furthermore, the calculation unit 15c calculates a distance matrix from the correlation coefficients between the electroencephalogram data of each stimulus and each group (step S6).

[0048] The presenter 15d then presents the positional relationship between each stimulus and each group corresponding to the biometric information using the calculated distance matrix. The presenter 15d also presents the range of the group using the average value of the group and the biometric information corresponding to the stimuli of the group that is farthest from the average value (step S7). This completes the content evaluation process.

[0049] [Effects] As described above, in the content evaluation device 10 of this embodiment, the storage unit 14 stores the group correspondence table 14a that associates multiple stimuli to be processed with groups of stimuli classified by the user. The acquisition unit 15b acquires biometric information when the stimuli are presented to the user. The calculation unit 15c calculates a distance matrix that represents the correlation between the biometric information. The presentation unit 15d uses the calculated distance matrix to present the positional relationship between each stimuli and each group that corresponds to the biometric information.

[0050] Specifically, the calculation unit 15c calculates the distance matrix by using the average value of the biological information of the stimulation corresponding to the group as the biological information of the group.

[0051] Furthermore, the presenting unit 15d presents the range of the group using the average value of the group and the biological information that is furthest from the average value among the biological information corresponding to the stimuli of the group.

[0052] This allows the content evaluation device 10 to indicate overlapping or inclusive relationships between groups of stimuli defined by the user through similarities in the user's biometric information at the time of stimuli presentation, thereby enabling evaluation of how each user perceives content when viewing it.

[0053] [Program] A program written in a computer-executable language may be created to execute the processes performed by the content evaluation device 10 according to the above embodiment. In one embodiment, the content evaluation device 10 can be implemented by installing a content evaluation program that executes the content evaluation process described above as package software or online software on a desired computer. For example, by executing the content evaluation program described above on an information processing device, the information processing device can function as the content evaluation device 10. The information processing device referred to here includes desktop and notebook personal computers. Other examples of information processing devices include mobile communication terminals such as smartphones, mobile phones, and PHS (Personal Handyphone Systems), as well as slate terminals such as PDAs (Personal Digital Assistants). The functions of the content evaluation device 10 may also be implemented on a cloud server.

[0054] 7 is a diagram showing an example of a computer that executes a content evaluation program. The computer 1000 includes, for example, a memory 1010, a CPU 1020, a hard disk drive interface 1030, a disk drive interface 1040, a serial port interface 1050, a video adapter 1060, and a network interface 1070. These components are connected by a bus 1080.

[0055] The memory 1010 includes a ROM (Read Only Memory) 1011 and a RAM 1012. The ROM 1011 stores a boot program such as a BIOS (Basic Input Output System). The hard disk drive interface 1030 is connected to a hard disk drive 1031. The disk drive interface 1040 is connected to a disk drive 1041. A removable storage medium such as a magnetic disk or optical disk is inserted into the disk drive 1041. The serial port interface 1050 is connected to a mouse 1051 and a keyboard 1052, for example. The video adapter 1060 is connected to a display 1061, for example.

[0056] Here, the hard disk drive 1031 stores, for example, an OS (Operating System) 1091, an application program 1092, a program module 1093, and program data 1094. The various pieces of information described in the above embodiments are stored in the hard disk drive 1031 or the memory 1010, for example.

[0057] The content evaluation program is stored in the hard disk drive 1031 as a program module 1093 in which instructions to be executed by the computer 1000 are written. Specifically, the program module 1093 in which each process executed by the content evaluation device 10 described in the above embodiment is written is stored in the hard disk drive 1031.

[0058] Furthermore, data used for information processing by the content evaluation program is stored as program data 1094, for example, in the hard disk drive 1031. Then, the CPU 1020 reads the program module 1093 and program data 1094 stored in the hard disk drive 1031 into the RAM 1012 as necessary, and executes each of the above-described procedures.

[0059] The program module 1093 and program data 1094 related to the content evaluation program are not limited to being stored in the hard disk drive 1031, and may be stored in, for example, a removable storage medium and read by the CPU 1020 via the disk drive 1041. Alternatively, the program module 1093 and program data 1094 related to the content evaluation program may be stored in another computer connected via a network such as a LAN or a WAN (Wide Area Network), and read by the CPU 1020 via the network interface 1070.

[0060] Although the present invention has been described above as an embodiment, the present invention is not limited to the description and drawings that form part of the disclosure of the present invention. In other words, other embodiments, examples, and operational techniques that can be made by those skilled in the art based on the present invention are all included in the scope of the present invention.

[0061] REFERENCE SIGNS LIST 10 Content evaluation device 11 Input unit 11a Biometric information measurement unit 12 Output unit 13 Communication control unit 14 Storage unit 14a Group correspondence table 14b Biometric information 15 Control unit 15a Group selection unit 15b Acquisition unit 15c Calculation unit 15d Presentation unit

Claims

1. A content evaluation device, comprising: a storage unit that stores, in association with each other, a plurality of stimuli to be processed and groups of each stimulus classified by a user; an acquisition unit that acquires biological information when presenting the stimuli to the user; a calculation unit that calculates a distance matrix representing the correlation between the biological information; and a presentation unit that presents the positional relationship between each stimulus and each group corresponding to the biological information by using the calculated distance matrix.

2. The content evaluation device according to claim 1, wherein the calculation unit calculates the distance matrix by using, as the biological information of the group, the average value of the biological information of the stimuli corresponding to the group.

3. The content evaluation device according to claim 1, wherein the presentation unit presents the range of the group by using the average value of the group and the biological information farthest from the average value among the biological information corresponding to the stimuli of the group.

4. A content evaluation method executed by a content evaluation device, the content evaluation device having a storage unit that stores, in association with each other, a plurality of stimuli to be processed and groups of each stimulus classified by a user, the method including: an acquisition step of acquiring biological information when presenting the stimuli to the user; a calculation step of calculating a distance matrix representing the correlation between the biological information; and a presentation step of presenting the positional relationship between each stimulus and each group corresponding to the biological information by using the calculated distance matrix.

Images