Taste information collection device and taste information collection method

Abstract

To more accurately grasp taste information for which many users prefer most.SOLUTION: A taste information collection device comprises: an image display unit on which images are displayed; an input unit which inputs a selection operation for a selected image selected by a user; a line-of-sight detection unit which detects a line of sight of the user when the user gazes at the image display unit; a gaze area determination unit which determines an area that user gases at for the longest time during a predetermined period of time, and outputs an image based on this area, as an image of interest; and a determination unit which determines whether the selected image is identical with the image of interest.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a preference information collecting device and a preference information collecting method. [Background technology]

[0002] Conventionally, lists and icons related to content are displayed on the screen, and these lists and icons By detecting the user's selection of images containing the There is known a technique for collecting user preference information by using the above method (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2008-191702 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, the preference information selected based on the result of the user's thinking is Although it is possible to collect information, it is not possible to obtain information on the preferences that users intuitively select. Therefore, it is difficult to grasp the most preferred preference information of many users more accurately. I did.

[0005] The present invention has been made in view of the above, and is intended to provide a method that is most preferred by many users. The purpose is to grasp preference information more accurately. [Means for solving the problem]

[0006] In order to solve the above problems and achieve the object, a preference information collecting device according to the present invention comprises: An image display unit for displaying an image and an input unit for inputting a selection operation for a selected image selected by a user. a gaze detection unit that detects a gaze of a user when the user gazes at the image display unit; The area where the user's gaze was the longest in a given period of time is determined, and images based on this area are displayed. A gaze area determination unit that outputs an eye image and determines whether the selected image and the image of interest match and a determination unit for determining whether or not the

[0007] The present invention also provides a method for collecting preference information, comprising the steps of: displaying an image; A step of inputting a selection operation for a selected image selected by a user; detecting a line of sight of the user when the user gazes at a part; determining an area that has existed the longest, and outputting an image based on this area as an image of interest; and determining whether or not the selected image matches the image of interest. Effect of the Invention

[0008] According to the present invention, it is possible to more accurately grasp preference information that is most preferred by many users. It is possible. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a block diagram showing an example of the configuration of a preference information collecting device according to this embodiment. [Diagram 2] FIG. 2 is a flowchart showing the flow of processing for investigating user preferences in the preference information collecting device according to this embodiment. [Diagram 3] FIG. 3 is a diagram for explaining feature points common to a selected image and an image of interest. [Figure 4] FIG. 4 is a flowchart showing the flow of processing for identifying an image that many users find most favorable in the preference information collecting device according to this embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, a preference information collecting device and a preference information collecting method according to the present invention will be described with reference to the accompanying drawings. The following embodiments will be described in detail. Note that the present invention is not limited to the following embodiments. stomach.

[0011] FIG. 1 is a block diagram showing an example of the configuration of a preference information collecting device according to the present embodiment. The information collection device 10 selects an image actually selected by the user from among a plurality of comparison images displayed on the screen. The selected image is then compared to the image that the user focused on based on the user's line of sight (the image of interest). ,The favorite images (preferences) of this user are investigated and the preference that most users find to be the most ,desirable image is selected. This allows for a more accurate understanding of the information.

[0012] The preference information collecting device 10 is an information processing device such as a personal computer. A computing device consisting of a central processing unit (CPU) and other components. The preference information collecting device 10 includes a memory for storing a program. The preference information collecting device 10 includes a program, which is loaded into the memory and executes the instructions contained in the program. The internal memory includes a program for the preference information collecting device 10. The preference information collecting device 10 is used for temporary storage of image data, etc., as shown in FIG. An image display unit 11, a gaze detection unit 12, an input unit 13, a gaze area determination unit 14, and a user information unit 15, judgment unit 16, counting unit 17, analysis unit 18, image control unit 19, and image storage unit 20 and more.

[0013] The image display unit 11 is a display device provided in the preference information collecting device 10. 1 is, for example, a liquid crystal display (LCD). ay) or organic EL (Electro-Luminescence) displays, etc. The image display unit 11 displays the composite image input via the image control unit 19. In the example of FIG. 1, the image display unit 1 1 is divided into four regions 30A to 30D, and each of the regions 30A to 30D has Comparison images (images) 31A to 31D of a given product (e.g., a passenger car) are displayed. The images 31A to 31D are still images, but may be moving images. It shows the product image and highlights the color, shape, and other characteristics of the product as a whole or in parts. The feature points are included in the comparison images 31A to 31D. This is an interesting point to note. We will discuss this feature later. Although a passenger car is given as an example, it is not limited to this as long as it expresses the characteristic points of shape and color. It is not.

[0014] The line-of-sight detection unit 12 is disposed adjacent to the image display unit 11. The gaze detection unit 12 detects the user's gaze when the user looks at the camera. The camera 2A captures the user's eyes, and the direction of the user's line of sight is detected. Information regarding the detected gaze direction is output to the gaze area determination unit 14. do.

[0015] The input unit 13 is an input device for inputting various information to the preference information collecting device 10. The input device 13 may be, for example, a keyboard or a mouse. Button switches (not shown) are formed so as to overlap each of the areas 30A to 30D provided on the display unit 11. The user can then use the mouse to select a user image from the comparison images 31A to 31D. For the image that is most favorable, the user can input the image (e.g., image 3) 1B) is selected as the selected image. Information about the selected image is output to the decision unit 16. Be encouraged.

[0016] The gaze area determination unit 14 determines the image based on the user's gaze detected by the gaze detection unit 12. The time during which the line of sight is present on each of the areas 30A to 30D of the image display unit 11 is measured. The fixation area determination unit 14 determines which of the areas 30A to 30D of the image display unit 11 the user is looking at at a given time. The gaze area determination unit 14 determines the area where the user's gaze was the longest (for example, area 30C). The image 31C displayed in the determined area 30C is acquired as an image of interest. The information about the image is output to the determination unit 16. In addition, the gaze area determination unit 14 determines whether each area 30A Information regarding the time when the line of sight was present at each of the points 1 to 30D is output to the analysis unit 18. Here, For example, the comparative images 31A to 31D are displayed in the areas 30A to 30D of the image display unit 11 for the predetermined time. This refers to the time from when an image is displayed to when the user performs an input operation to select an image. The area where the user's gaze was present for the longest time is the area where the user gazed within the above-mentioned predetermined time. For example, when comparing images of two areas, In addition, the presence of the user's gaze in the area may be a discontinuous time. This refers to the state in which the line of sight of a person is continuously observed in the area for a certain period of time (for example, 0.1 seconds). This eliminates the situation where the user accidentally sees an area regardless of their intention. This makes it possible to accurately determine the area (image) that the user is gazing at.

[0017] The user information section 15 stores information about the user, such as the user's gender, age, and preferences (areas of interest). The information about the user's attributes is obtained from the above-mentioned multiple When performing a series of operations to select a selected image from among the comparison images, for example, The acquired user attribute information is output to the analysis unit 18.

[0018] The determination unit 16 determines whether the selected image is selected via the input unit 13 or not by the gaze area determination unit 14. The determination unit 16 determines whether the output image of interest matches the image of interest. The information is output to the counting unit 17.

[0019] The counting unit 17 counts (counts) the images based on the input judgment results. For example, If it is determined that the selected image matches the image of interest, the tabulation unit 17 adds the selected image to the user's The selected image is counted as a representative image that the user is interested in. Also, if the selected image does not match the image of interest, If it is determined that the selected image does not match the target image, the counting unit 17 counts the image that does not match the selected image as a sensory image. The selected images that do not match the image of interest are counted as logical images. The counting unit 17 also counts the number of representative images, sensory images, and logical images for each user. The result of the analysis is output to the analysis unit 18. Here, the representative image is selected from among the multiple comparison images. These are images that users have selected as being of interest to them, and are the most frequently selected images by multiple users. The selected representative image is treated as a recommended image, which will be described later.

[0020] The analysis unit 18 includes the representative image, the sensory image, and the logical image counted by the counting unit 17. Information regarding the total number of each image and information regarding the attributes of the user obtained from the user information unit 15 Based on the information, statistical information tailored to the user's attributes is generated. Various representative images in the preference survey, the management numbers of these representative images, the number of representative images, and logical images The time when the line of sight was present in each of the regions 30A to 30D is included in the number of times the line of sight was present in each of the regions 30A to 30D. The generated statistical information is output to the image control unit 19. The analysis unit 18 also Based on the statistical information, the representative image with the highest count is selected as the recommended image. This indicates the image (preference information) that most users find most desirable. In this embodiment, the image selected by the user as being of interest from among multiple comparison images is designated as the representative image. Since it is determined to be an image, it is possible to detect multiple The representative image selected most frequently by a number of users is the image that these users find most favorable. This can be seen as a recommended image.

[0021] The image control unit 19 displays a plurality of comparative images of the target product in a predetermined area 3 of the image display unit 11. The comparison images are controlled to be displayed on the screens 0A to 30D. In addition, a new set of comparison images is set depending on the user's image selection. Specifically, the image control unit 19 may determine that the selected image does not match the image of interest. When the selected image and the target image are selected, feature points that are set in advance are extracted from the selected image and the target image, and matching feature points are and displaying the newly selected images on the image display unit 11. The image displayed on the image display unit 11 replaces the image that was previously displayed.

[0022] The image storage unit 20 stores a plurality of comparative images of the target product, and performs image control. The image storage unit 20 outputs the image selected under the control of the image control unit 19. By controlling No. 9, statistical information tailored to user attributes is stored.

[0023] Next, a process flow of the preference information collecting device 10 will be described. 1 is a flowchart showing a process flow of a user preference survey in the preference information collecting device 10. 3 is a diagram for explaining feature points common to a selected image and an image of interest.

[0024] The preference information collecting device 10 displays comparative images to be the subject of the preference survey in each area of ​​the image display unit 11. Specifically, the preference information collecting device 10 displays the image by the image control unit 19. Then, a plurality of comparative images relating to the target product are read out from the image storage unit 20, and these comparative images are The images are displayed in the respective areas of the image display unit 11.

[0025] Next, the preference information collecting device 10 inputs the selected image selected by the user (step S2 Specifically, the preference information collecting device 10, based on the user's operation via the input unit 13, The image that the user considers to be the most preferable is selected as the selected image from among the plurality of comparison images. A selected image is input, and information about the selected image is output to the determination unit 16.

[0026] Next, the preference information collecting device 10 acquires attribute information of the user (step S3). The user information unit 15 of the information collecting device 10 collects user information based on the user's operation through the input unit 13. Obtain user attribute information such as the user's gender, age, preferences (hobbies or areas of interest) In the example of FIG. 2, after the selected image is input, the attribute information of the user is acquired as follows. However, the timing for acquiring user attribute information may be before the selection image is input. good.

[0027] Next, the preference information collecting device 10 acquires the image of interest of the user based on the gaze detection (s Specifically, the preference information collecting device 10 determines, by the gaze area determining unit 14, Based on the user's line of sight, the area of ​​the image display unit 11 that is the user's line of sight at a predetermined time is selected from among the areas 30A to 30D. The area where the line exists the longest (for example, area 30C) is determined. In this case, the image 31C displayed on the image display 0C is acquired as the image of interest. From the time when the comparative images 31A to 31D are displayed in the areas 30A to 30D of the display unit 11, The time is the time until the input operation of the selected image is performed by the camera. The information is output to the determination unit 16.

[0028] Next, the preference information collecting device 10 judges whether the selected image matches the image of interest ( Step S5). Specifically, the preference information collecting device 10 determines whether the user's preference is satisfied based on the information input to the determining unit 16. Based on the above, the selected image selected by the user and the image that the user has been paying attention to for the longest time are identified. It is determined whether or not they match. If it is determined that the selected image and the image of interest match ( If the result of step S5 is Yes, the preference information collecting device 10 shifts the process to step S6.

[0029] On the other hand, if the selected image does not match the image of interest (step S5; No), The preference information collecting device 10 collects the non-matching selected images as a logical image (step S9). The preference information collecting device 10 counts the number of logical images by the counting unit 17. The logical image is an image that does not match the image of interest among the selected images. Images that do not match the selected image may be tallied as sensory images.

[0030] Next, the preference information collecting device 10 extracts matching feature points between the selected image and the image of interest (sequence Specifically, the image 31B displayed in the area 30B in FIG. In this embodiment, the image 31C displayed in the area 30C is the target image. In these images 31B and 31C, feature points of the product (passenger car) are set in advance. For example, for a passenger car, the overall shape of the vehicle, the color of the vehicle, the shape of the headlights, and the shape of the rear lamps. The shape of the doors, the shape of the windows (side windows), the shape of the tires and wheels, etc. are the feature points. These feature points are just examples, and feature points may be set in other places. The preference information collecting device 10 may control the image by the image control unit 19. The image control unit 19 extracts matching feature points between the selected image and the image of interest. By performing image analysis with the image, the window (side window) shapes 32B and 32C are identified. The matching feature points are extracted.

[0031] Next, the preference information collecting device 10 selects an image having feature points that match the extracted feature points. That is, the preference information collecting device 10 selects the From the images related to the product (passenger car) stored in the image storage unit 20, the selected image and the attention image are The image has a window having the same shape (matching feature points) as the window shapes 32B and 32C, which are feature points of the image. Then, the preference information collecting device 10 compares the selected image, the image of interest, and the selected image. The two images are added together to create a new comparative image, which is then replaced with the image displayed on the image display unit 11. The process returns to step S1 and the process is repeated. The preference information collecting device 10 selects four images having feature points that match the extracted feature points. The four selected images may then be used as new comparison images.

[0032] In the determination in step S5 above, if the selected image and the image of interest match (step If the user selects the selected image as an image of interest to the user, the preference information collecting device 10 selects the selected image as an image of interest to the user. The representative image is collected as a representative image (step S6). In this embodiment, the image that the user actually selected is the image that the user was most interested in. If the selected image matches the image that the user has been paying attention to for the longest time, the selected image is selected as the representative image. This eliminates the case where the selected image is selected by mistake, and the user It is possible to accurately compile representative images of interest.

[0033] Next, the preference information collecting device 10 determines whether there is an additional survey (step S7). Here, the additional survey is a comparison of the same product (passenger car) in the above-mentioned preference survey. This is done using images of the product and comparative images of other products (e.g. motorcycles). If there is an additional investigation (step S7; Yes), the process returns to step S1. Execute a repeat process.

[0034] Also, if there is no additional investigation (step S7; No), the preference information collecting device 10 The statistical information according to the user's attributes is output (step S8) and the process ends. The analysis unit 18 associates the user's attribute information with the survey results of the user, and The image control unit 19 generates statistical information according to the user's attributes. The control unit 19 stores this statistical information in the image storage unit 20 and ends the process. The following items are included in the survey: various representative images in the user preference survey, the management number of the representative images, the number of representative images, The number of logical images and the time during which the line of sight was present in each of the regions 30A to 30D are at least include.

[0035] Next, the image that most users find most favorable (preference information) is selected from the statistical information of multiple users. FIG. 4 is a flow chart of a process for acquiring preference information according to the present embodiment. A flow chart showing the process of identifying the image that most users find most favorable in the device. -Chart.

[0036] First, the preference information collecting device 10 inputs statistical information of each user (step S21). Specifically, the image control unit 19 reads the statistical information stored in the image storage unit 20 for each user. The statistical information of each user is input to the analysis unit 18.

[0037] Next, the preference information collecting device 10 generates a logical image based on the input statistical information of each user. It is determined whether there is a user whose number exceeds a predetermined threshold (step S22). and determining whether the number of logical images counted for the same user exceeds a predetermined threshold. This predetermined threshold is set appropriately, but may be set, for example, based on a series of surveys conducted on the user. It is preferable to set the number of reviews to 1 / 3 to 1 / 2. The collection device 10 determines by the analysis unit 18 that there is no user whose number of logical images exceeds a predetermined threshold. If it is determined that the number of the semaphores is 1 (step S22; No), the process proceeds to step S25.

[0038] On the other hand, the preference information collecting device 10 determines that there is a user whose number of logical images exceeds a predetermined threshold. If the determination is affirmative (step S22; Yes), the analysis unit 18 performs the following operations related to the same user: If there is an area where the user's gaze is not detected until the generation of the statistical information is completed, It is determined whether the generation of statistical information for the same user has been completed (step S23). The time period during which all images corresponding to all the images of interest output for the same user are processed is called the time period. In this case, the analysis unit 18 analyzes each of the regions 30A to 30D. Based on the time that the gaze was present in each area, it was determined whether there were any areas where the gaze was not detected. In this determination, the preference information collecting device 10 determines whether or not the preference information collecting device 10 has a statistical information It is determined that there is no area in which the user's gaze is not detected until the generation of If so (step S23; No), the process proceeds to step S25.

[0039] On the other hand, the preference information collecting device 10 continues to If it is determined that there is an area where the user's gaze is not detected between the 3; Yes), the use of the statistical information of the corresponding user is stopped (step S24). That is, the number of logical images counted for the same user exceeds a predetermined threshold and All the predetermined times corresponding to all the images of interest output for one user have elapsed. If there is an area where the user's gaze is not detected between the time It can be determined that the survey is being conducted carelessly (fraudulently). Since statistical information does not accurately reflect the preferences of users, If you use it to find the recommended image that multiple users find most favorable, it will be a noise. For this reason, in this embodiment, the preference survey is not performed correctly. By discontinuing the use of statistical information of users who are deemed to be related to the user, it is possible to accurately analyze the preferences of multiple users. It can be understood.

[0040] Next, the preference information collecting device 10 collects the representative images for each user (step S25). The most popular representative image corresponding to the user attributes is selected as the recommended image and the recommended image information is output. As described above, the representative image is the image that the user is most interested in among the comparison images. The preference information collection device 10 collects, by the analysis unit 18, the image representing a large number of users. By aggregating the table images according to user attributes (gender and age), users can be categorized. Accurately analyze (understand) the recommended images that are the images that most users are interested in based on attributes. The analysis unit 18 of the preference information collecting device 10 can provide recommendations according to user attributes. By outputting the image information to, for example, an external management device (not shown), a large number of users can It can also be proposed as a design image of the most suitable product (goods) that interests the customer.

[0041] As described above, the preference information collecting device 10 according to the present embodiment stores a plurality of images 31A to 31D in advance. An image display unit 11 that displays images in each of the determined regions 30A to 30D, and the image display unit 11 A selection operation is performed on a selected image selected by the user from the multiple images 31A to 31D displayed on the display unit 31. and an input unit 13 for inputting a user's gaze and detecting the user's gaze when the user gazes at the image display unit 11. The gaze detection unit 12 outputs a gaze signal to the user from among the areas 30A to 30D of the image display unit 11 at a predetermined time. The area where the user's gaze was the longest is determined, and the image in this area is output as the image of interest. a visual area determination unit 14; and a determination unit 16 for determining whether or not a selected image and an image of interest match each other; If it is determined that the selected image matches the image of interest, the selected image is treated as a proxy image of interest to the user. The counting unit 17 counts the number of images actually selected by the user as a table image. If the selected image matches the image that the user has been paying attention to for the longest time, the selected image is selected as the representative image. By doing so, it is possible to eliminate cases where the selected image is selected by mistake, and Therefore, it is possible to accurately collect representative images that are of interest to many users. It is possible to grasp more accurately the images that are preferred (preference information).

[0042] In addition, a plurality of characteristic points, which are characteristic shapes, are set in advance in each of the images 31A to 31D. If it is determined that the selected image does not match the image of interest, the feature points of the selected image and the image of interest are The feature points of the eye image are compared with those of the eye image to extract matching feature points, and feature points similar to the extracted feature points are extracted. A new image having the above-mentioned characteristics is selected and displayed in place of the image displayed on the image display unit 11. The image control unit 19 controls the image processing unit 16 to provide the user with an image having the feature point that the user has focused on. This allows the representative images that interest the user to be accurately collected.

[0043] The counting unit 17 also counts the representative images for each user. The representative image with the largest number of images among the table images is regarded as the recommended image that is most preferred by multiple users. In order to provide an analysis unit 18 that analyzes user attributes, a large number of users can select the most suitable This allows users to accurately identify recommended images that are of interest to many users. It can be proposed as a design image of the most suitable product that interests you the most.

[0044] In addition, the counting unit 17 counts the images selected by each user that are determined not to match the image of interest. The image is counted as a logical image, and the analysis unit 18 counts the number of images counted for the same user. If the number of logical images exceeds a threshold and all the focus images output for the same user are The user's gaze is detected in a plurality of regions until all the predetermined times corresponding to the plurality of regions have elapsed. If there is an area that is not displayed, the user's statistical information (representative image) is used to determine the recommended image. Since it does not use cookies, it can eliminate information that does not accurately reflect the user's preferences, and many It is possible to accurately grasp the user's preference information.

[0045] The preference information collecting device 10 according to the present embodiment has been described above. The configuration of the preference information collecting device 10 shown in the figure may be implemented in various different forms. The elements are functional concepts and do not necessarily have to be physically configured as shown in the drawings. In other words, the specific form of each device is not limited to that shown in the figure, and the processing load and usage of each device may vary. Depending on the situation, etc., all or part of it may be functionally or physically distributed or May be integrated.

[0046] The preference information collecting device 10 is configured, for example, as software loaded into a memory. In the above embodiment, the above hardware or software is implemented. The above explanation was given as a functional block realized by the cooperation of various software. Functional blocks may consist of hardware only, software only, or a combination of both. This can be achieved in various ways depending on the combination.

[0047] The above-mentioned components include those that a person skilled in the art can easily imagine and those that are substantially the same. Furthermore, the above-mentioned configurations can be appropriately combined. Various omissions, substitutions or modifications of the configuration are possible within the scope. [Explanation of symbols]

[0048] 10. Preference information collection device 11 Image display section 12 Gaze detection unit 12A Camera 13 Input section 14 Gaze area determination unit 15 User Information Section 16 Judgment section 17 Counting Department 18 Analysis Department 19 Image control section 20 Image storage section 30A, 30B, 30C, 30D area 31A, 31B, 31C, 31D Images 32B, 32C Window shape (feature points)

Claims

1. an image display unit for displaying an image; an input unit for inputting a selection operation for a selected image selected by a user; a gaze detection unit that detects a gaze of the user when the user gazes at the image display unit; 、 The area where the user's gaze was the longest during a predetermined period of time is determined, and an image based on this area is generated. a gaze area determination unit that outputs the image as an image of interest; a determination unit that determines whether the selected image and the image of interest match; A preference information collecting device comprising:

2. A plurality of feature points each having a characteristic shape is set in advance in the image, If it is determined that the selected image does not match the image of interest, comparing the feature points of the selected image with the feature points of the image of interest to extract matching feature points; A new image having the same feature points as the extracted feature points is selected and displayed on the image display unit.

2. The preference information according to claim 1, further comprising an image control unit for displaying the preference information in place of an image that has been displayed. Collection device.

3. A preference information collecting method executed by a preference information collecting device, comprising: an image display step of displaying an image; inputting a selection operation for a selected image selected by a user; detecting a line of sight of the user when the user gazes at the image display unit; The area where the user's gaze was the longest during a predetermined period of time is determined, and an image based on this area is generated. as an image of interest; determining whether the selected image and the image of interest match; The preference information gathering method includes the steps of:

Images