JP2023092063A - Content recommendation device - Google Patents

Abstract

To provide a technique for recommending a content that a user is highly satisfied with.SOLUTION: A content recommendation device 1 is used to recommend a content to be provided for a user. The content recommendation device 1 uses an evaluation model, having a first evaluation axis J1 for evaluating a level of awakening and a second evaluation axis J2 for evaluating a level of discomfort to gather a user state representing a state of the user. Namely, the evaluation model is used to gather the user state to be used to recommend the content. Consequently, the content that the user is highly satisfied with can be selected and recommended based upon the gathered user state.SELECTED DRAWING: Figure 1

Description

The present disclosure relates to technology for recommending content to users.

In recent years, as a method of recommending content such as videos (that is, the content of information provided) to users, based on the user's video viewing history and emotion tags attached to the videos viewed, the user's preferences have been proposed. and recommends content according to this preference (for example, see Patent Document 1 below).

Apart from this, there is also known a method of detecting a change from a first emotion to a second emotion when a user views content, and recommending content based on this detection result ( For example, see Patent Document 2 below).

JP 2015-228142 A JP 2018-414660 A

However, as a result of detailed studies by the inventors, the following problems were found in the conventional techniques.
Specifically, the above-described conventional technology recommends content according to the user's feelings when viewing a moving image or the like, but the recommended content may not be the content desired by the user.

For example, even if the user is currently feeling sad, the content desired by the user may be different depending on whether the user wants to be relaxed or excited next time. Also, even if the current emotion and the target emotion are the same, the desired content may differ depending on the scene (that is, the scene).

One aspect of the present disclosure is to provide a technology capable of recommending content that satisfies the user.

(1) A content recommendation device (1) according to one aspect of the present disclosure is a content recommendation device used to recommend content to be provided to a user.
This content recommendation device uses an evaluation model having a first evaluation axis for evaluating the degree of arousal and a second evaluation axis for evaluating the degree of pleasure and discomfort, and indicates the user's situation used when recommending content. configured to collect user context;

With such a configuration, the present disclosure can recommend content that satisfies the user.
Specifically, in the present disclosure, an evaluation model (for example, Russell's circular model of emotion) having a first evaluation axis for evaluating the degree of arousal and a second evaluation axis for evaluating the degree of pleasure and displeasure is used. Therefore, it is possible to grasp the user situation that matches the actual user situation with high accuracy.

Therefore, it is possible to recommend content that is comfortable (that is, has a high degree of satisfaction) for the user based on the actual user situation collected in this way.
(2) A content recommendation device (1) according to another aspect of the present disclosure has a first acquisition unit (11, S100), a second acquisition unit (11, S120), and an acquisition recommendation unit (25, S160).

The first acquisition unit is configured to acquire the user's current situation (eg, current emotion, scene, etc.) input by the user.
The second acquisition unit is configured to acquire a target situation (for example, target emotion or scene) input by the user.

The acquisition recommendation unit is configured to recommend content to be provided to the user based on the current situation acquired by the first acquisition unit and the target situation acquired by the second acquisition unit.

With such a configuration, the present disclosure can recommend content that satisfies the user.
Specifically, in the present disclosure, the first acquisition unit acquires the current situation input by the user, so that the actual situation that matches the current situation of the user can be grasped with high accuracy.

In addition, the second acquisition unit acquires the target status input by the user, thereby being able to grasp the target status actually desired by the user with high accuracy.
Therefore, the acquisition recommendation unit recommends content that is comfortable (that is, highly satisfying) for the user based on the current situation acquired by the first acquisition unit and the target situation acquired by the second acquisition unit. can do.

Note that the content indicates the content of various types of information provided to the user, such as moving images. In addition, the situation indicates a condition or state that changes with time and space, and includes not only the environment in which a person is placed but also the state of the person's mind. The user situation refers to a situation regarding the user, that is, the user's situation including the user's own state (eg, state of mind) and the external situation in which the user is placed. The user situation includes the current situation of the user and the intended situation of the user. The user situation includes, for example, the user's feelings at present or in the future (eg, a desired future) and a scene (ie, scene) in which the user is placed.

In addition, the symbols in parentheses described in this column and the scope of claims indicate the correspondence relationship with specific means described in the embodiments described later as one aspect, and the technical scope of the present disclosure is It is not limited.

1 is a block diagram showing the configuration of a content recommendation estimation device according to a first embodiment; FIG. FIG. 10 is an explanatory diagram of an input screen using an emotion cyclic diagram of current emotions according to the first embodiment; It is an explanatory view showing pictograms of emotions of the first embodiment. FIG. 11 is an explanatory diagram of an input screen using an emotional cyclical diagram of a target scene according to the first embodiment; It is an explanatory view showing a scene pictogram of the first embodiment. 4 is a flowchart showing processing performed in the first embodiment; FIG. 11 is an explanatory diagram of an input screen using an emotional cyclical diagram of the current scene according to the second embodiment; FIG. 11 is an explanatory diagram of an input screen using an emotion cyclic diagram of current emotions according to the third embodiment; FIG. 20 is an explanatory diagram of an input screen using an emotional cyclical diagram of the current scene according to the fifth embodiment; FIG. 21 is an explanatory diagram of an input screen using an emotional cyclical diagram of a target scene in the fifth embodiment; FIG. 21 is an explanatory diagram of an input screen displaying a pictogram of a current scene on the emotion circumflex of the fifth embodiment; It is an explanatory view showing a scene pictogram of the fifth embodiment. It is a pie chart showing experimental results.

Embodiments of the present disclosure will be described below with reference to the drawings.
[1. First Embodiment]
[1-1. overall structure]
First, the overall configuration of the content recommendation device according to the first embodiment will be described.

An example of this content recommendation device is a device mounted on a vehicle. Devices installed at homes, offices, etc., and mobile information terminal devices such as smartphones are also included.

As shown in FIG. 1, the content recommendation device 1 of the first embodiment mainly includes an information collection section 3, a control section 5, and an actuator section 7. FIG.
The information collection unit 3 is a device that allows a user to manually input a user situation indicating a situation regarding the user.

The control unit 5 is a device capable of selecting and recommending content to be provided to the user based on the information indicating the user situation input by the information collecting unit 3 .
The actuator unit 7 is a device capable of providing the user with content recommended by the control unit 5 using various actuators.

Here, the user situation includes the user's current emotion, the user's current scene (that is, the scene in which the user is currently placed), and the user's target emotion (that is, the user's target emotion, which is the emotion that the user wants to be, target scene (ie, target scene, which is the scene that the user wants to be placed in the future).

Each configuration will be described in detail below.
[1-2. Information gathering department]
As shown in FIG. 1, the information collection unit 3 includes a user input unit 11 and an information transmission unit 13. As shown in FIG.

The user input unit 11 is, for example, a display 15 (see, for example, FIG. 2) having a touch panel function. can be entered.

That is, as will be described in detail later, by touching the image displayed on the display 15, the user can input information about the user's emotions and scenes. That is, by touching a predetermined portion of an emotional cyclical diagram (hereinafter referred to as an emotional cyclical diagram) showing Russell's emotional cyclical model as shown in FIG. You can enter information.

The information transmission unit 13 is a transmission device that transmits information on the touched position to the control unit 5 when the user input unit 11 is operated (that is, when the display 15 is touched).

The information on the position includes information on the position (that is, the coordinates) indicated by two orthogonal axes in the emotional circumflex, which will be described later.
<User input part>
Here, the user input section 11 will be described in detail.

The user input unit 11 is a device for manually inputting the user's own emotions and scenes using an emotional ring diagram.
That is, as shown in FIG. 2, the user input unit 11 displays an emotion cyclone on the display 15 having a touch panel function, and allows the user to touch pictograms of emotions and scenes displayed on the emotion cyclone. It is a device for inputting the user's emotions and scenes.

A pictogram is a typical graphic symbol, and means a symbol that uses the shape of a sign to make the meaning concept understandable.
In the first embodiment, an example of inputting a current emotion and a target scene using an emotion ring diagram will be described.

a) First, the input of the user's current emotion will be described.
As shown in FIG. 2, the emotional circumflex is defined by setting the first evaluation axis J1 indicating (that is, evaluating) the degree of arousal (that is, the degree of arousal) on the vertical axis, and setting the horizontal axis perpendicular to the vertical axis. A second evaluation axis J2 is set as an axis to indicate the degree of pleasure and discomfort (that is, to evaluate), and these two axes indicate the state of emotions (that is, emotions including human mind and spirit).

On the first evaluation axis J1, the degree of arousal increases as it goes upward in the figure. On the other hand, the lower the figure, the lower the degree of arousal (that is, the higher the degree of sedation and the deeper the drowsiness). Note that the center of the first evaluation axis J1 in the vertical direction is the origin indicating the calm state between wakefulness and sedation.

On the second evaluation axis J2, the degree of pleasure increases toward the right side of the figure. On the other hand, the degree of discomfort increases toward the left in the figure. The center of the second evaluation axis J2 in the left-right direction (that is, the point of intersection with the first evaluation axis J1) is the origin indicating the calm state between pleasant and unpleasant.

Note that the first evaluation axis J1 and the second evaluation axis J2 correspond to the y-axis and the x-axis that are perpendicular to each other on the YX plane. The position can be indicated by a y-coordinate and an x-coordinate. Therefore, the first coordinate indicating the magnitude of the first evaluation axis J1 corresponds to the y-coordinate, and the second coordinate indicating the magnitude of the second evaluation axis J2 corresponds to the x-coordinate.

In addition, in the first embodiment, as shown in FIG. 2, the emotional circumflex is divided into six regions, that is, the first to sixth regions R1 to R6 according to the degree of arousal and the degree of pleasure and displeasure. there is
The first region R1 is a 1/4 circle region with an upper left center angle of 90° between arousal and displeasure, and is a region indicating the feeling of frustration. In addition, in FIG. 2, a circular pictogram (that is, an irritated pictogram) indicating the feeling of "irritated" is displayed in the first region R1. See FIG. 3 for pictograms of emotions.

In addition, in FIG. 2, the pictograms showing emotions are shown dark (for example, in black), and the pictograms showing scenes to be described later are shown lightly (for example, in gray). good.

The range in which the frustration pictogram is displayed (that is, the face mark portion) is set so that the user can input the emotion (that is, frustration) indicated by the frustration pictogram by touching it.

Note that the range in which the user touches to input the feeling of “irritated” includes not only the range in which the frustrated pictogram is displayed, but also the range in which the frustrated pictogram is displayed (with a predetermined width, for example). may be in the range of The same applies to other pictograms of emotions below.

Specifically, as will be described later, the memory of the control unit 5 stores the coordinates of each pictogram displayed in the emotion circumflex and each emotion in association with each other. Therefore, when a certain pictogram is touched, the coordinates of the touched position are transmitted to the control unit 5, so which pictogram has been touched can be detected from the transmitted coordinates. That is, it is possible to detect what kind of emotion is input.

Therefore, for example, by touching the frustration pictogram, the emotion of "frustration" can be input.
The second region R2 is a 1/4 circle region with a lower left center angle of 90° between discomfort and sedation, and is a region showing a feeling of "dejection." In FIG. 2, the second region R2 displays a pictogram indicating the feeling of "dejection" (that is, a dejection pictogram).

As with the frustration pictogram, the depressed pictogram is also set so that the user can input the emotion (ie, depression) indicated by the depressed pictogram by touching the range of the depressed pictogram.

Also, the right half area of the emotional circumflex is divided into three areas with central angles of, for example, 60°. Specifically, a third region R3, a fourth region R4, and a fifth region R5 are set in the clockwise direction from the position where the awakening degree is maximum.

The third area R3 is an area showing the emotion of "exciting", and a pictogram showing the emotion of "exciting" (that is, an exciting pictogram) is displayed so as to overlap the third area R3.
Like other pictograms, the exciting pictogram is set so that the user can input the emotion (that is, excitement) indicated by the exciting pictogram by touching the range of the exciting pictogram.

The fourth area R4 is an area showing the emotion of "happiness", and a pictogram showing the emotion of "happiness" (that is, a happy pictogram) is displayed so as to overlap the fourth area R4.
As with other pictograms, the happy pictogram is set so that the user can input the emotion (that is, happiness) indicated by the happy pictogram by touching the range of the happy pictogram.

The fifth area R5 is an area showing the feeling of "relaxation", and a pictogram showing the feeling of relaxation without tension (that is, relaxation) is displayed so as to overlap the fifth region R5. be.

As with other pictograms, the relax pictogram is set so that the user can input the emotion (ie, relax) indicated by the relax pictogram by touching the region of the relax pictogram.

Further, around the origin of the emotional circumflex, a sixth region R6 is set within a circle centered at the origin. This sixth region R6 is a region showing the feeling of "calmness (ie, neutral)", and a pictogram showing the feeling of "neutral" (ie, neutral pictogram) is displayed so as to overlap the sixth region R6. be.

As with other pictograms, the neutral pictogram is set so that the user can input the emotion (that is, neutral) indicated by the neutral pictogram by touching the range of the neutral pictogram.

Although the sixth area R6 overlaps the portions of the first to fifth areas R1 to R5 near the origin, the operation of the sixth area R6 is set to have priority.
As described above, in the first embodiment, the user manually inputs the user's current emotion by touching each pictogram representing the current emotion in the emotion ring diagram as shown in FIG. be able to.

b) Next, the input of the scene desired by the user will be described.
Here, the scene indicates a scene in which the user is placed, so the target scene indicates a situation such as a scene in which the user wishes to be placed in the future (i.e., intended). ing.

As shown in FIG. 4, a pictogram indicating a target scene is displayed in each area of the emotional circumflex.
In addition, in FIG. 4, the pictogram indicating the target scene is darkened (for example, in black). Pictograms representing emotions are shown lightly (for example, in gray), but only pictograms representing emotions input in FIG. 2 are shown dark.

In the first embodiment, as shown in FIG. 4, pictograms representing "muscle training", "stretching", and "work" as shown in FIG. 5 are displayed in the third region R3. Similarly, in the fourth area R4, pictograms indicating "drive", "play with pet", "tea time", and "mindfulness" are displayed. Similarly, in the fifth area R5, pictograms indicating "a moment before going to bed" and "sleep" are displayed.

Here, the desired scene is, for example, in the case of a pictogram of "driving", a scene in which a person wants to drive and change his/her mood. indicates that you want to have a coffee or tea and relax. In other words, it indicates that the user desires the situation of such a target scene or a situation suitable for it.

Also, the range in which the pictogram indicating the target scene is displayed is set so that the contents of the target scene can be input by the user's touch. Note that the range in which the content of the target scene is input by the user's touch includes not only the range in which the pictogram is displayed, but also the range in which the pictogram is displayed (for example, with a predetermined width). A predetermined range may be used.

Therefore, as will be described later, when the pictogram is touched, the coordinates of the touched position are transmitted to the control unit 5. From these transmitted coordinates, which pictogram was touched (that is, which pictogram is touched) can be determined. It can be detected whether a desired scene such as the above has been input.

As described above, in the first embodiment, the user manually inputs the scene desired by the user by touching the pictogram indicating the scene desired in the emotional ring diagram as shown in FIG. be able to.

[1-3. control section]
Next, the controller 5 will be explained.
<Functional configuration>
As shown in FIG. 1, the control unit 5 includes, as a functional configuration, a current user situation determination unit 21, a target user situation determination unit 23, a recommendation generation unit 25, a provision space determination unit 27, and a sensory stimulation control unit. 29.

When the user input unit 11 is set to input the current emotion, the current user situation determination unit 21 displays the current emotion input screen (for example, see FIG. 2) on the display 15. In this case, based on the information input by the user input unit 11, it is determined what kind of current emotion has been input.

That is, what kind of current emotion is input based on the information as to which position (that is, the coordinates in the emotion cyclone) is touched in the emotion cyclone displayed on the display 15 having the function of a touch panel. determine whether or not

Specifically, as described above, the memory of the control unit 5 stores the coordinates of the pictograms of each emotion displayed in the emotion circumflex in association with each emotion. Therefore, when a pictogram of a certain emotion is touched, the coordinates of the touched position (that is, the first coordinates and the second coordinates) are transmitted to the control unit 5. Therefore, from the transmitted coordinates, which emotion It can be seen that it is determined whether the pictogram of is touched.

In this way, since it is possible to know which pictogram of emotion in the emotion circumflex has been touched, it is possible to determine what kind of current emotion has been input.
When the user input unit 11 is set to input the target scene, the target user situation determination unit 23 is displayed on the input screen of the target scene on the display 15 (for example, see FIG. 4). In this case, based on the information input by the user input unit 11, it is determined what kind of target scene has been input.

That is, what kind of target scene has been input is determined based on the information as to which position (that is, the coordinates in the emotional circumflex) has been touched in the emotional circumflex displayed on the display 15 .

Specifically, the memory of the control unit 5 stores the coordinates of the pictograms of each scene displayed in the emotional ring diagram in association with each scene. Therefore, similarly to the input of emotions, when a pictogram of a certain scene is touched, the coordinates of the touched position (that is, the first coordinates and the second coordinates) are transmitted to the control unit 5. From the touched coordinates, it can be determined which scene pictogram was touched.

In this way, since it is possible to know which scene pictogram of the emotion circumflex has been touched, it is possible to determine what kind of target scene has been input.
The recommendation generation unit 19 recommends content to the user based on the user's current emotion determined by the current user situation determination unit 21 and the user's desired scene determined by the target user situation determination unit 23. to select.

For example, if the current emotion is "dejected" and the target scene is "tea time", the content corresponding to the current emotion and target scene is selected. In other words, choose content where your current emotion is one that fits a restful situation like "tea time."

Such content is each set to match a combination of multiple current emotions (e.g., 6 emotion pictograms) and multiple target scenes (e.g., 9 scene pictograms). there is In addition, a plurality of contents are set in the case of one emotional pictogram and one target scene pictogram. In addition, one combination may be sufficient.

Therefore, when the current emotion is "dejected" and the target scene is "tea time", a plurality of contents corresponding to this combination are selected.
The provision space determination unit 27 determines one content to be actually provided to the user from the plurality of contents selected by the recommendation generation unit 19 .

For example, the user may be prompted to select a content by presenting a description of the contents of the plurality of contents selected by the recommendation generating unit 19 to the user. Specifically, images of a plurality of contents are displayed as images on the display 15, or main points and explanations of the contents are displayed, and the user can select (that is, decide) the contents by touching the displayed part. You may do so.

For example, if the current emotion is "dejected" and the desired scene is "tea time", the content may be "enjoying tea in the room" or "enjoying tea in the garden". It is also possible to display an image that allows the user to imagine what is going on, or to display an explanation of ``enjoying tea in the room'' or ``enjoying tea in the garden,'' so that the user can determine the content.

Alternatively, when there are a plurality of contents, the content may be randomly determined by the provision space determination unit 27 .
Note that user selection and random determination may be selectable by the user.

The sensory stimulation control unit 29 controls driving the actuator unit 7 in order to stimulate the user's senses (that is, the five senses) when providing the user with the content determined by the provision space determination unit 27. .

<Hardware configuration>
Here, the hardware configuration of the control unit 5 will be described.
As well known, the control unit 5 is configured mainly by a microcomputer (hereinafter referred to as a microcomputer) having a CPU and memory (for example, semiconductor memory such as ROM, RAM, and flash memory).

Various functions of the control unit 5 are realized by the CPU executing a program stored in a non-transitional substantive recording medium. In this example, the memory corresponds to a non-transitional substantive recording medium storing programs. Also, by executing this program, a method corresponding to the program is executed. Note that the memory stores, for example, information input by the user input unit 11, data used as judgment materials for selecting recommended content, and the like.

The number of microcomputers constituting the control unit 5 may be one or plural. Further, the method of realizing various functions of the control unit 5 is not limited to software, and some or all of the elements may be realized using one or more pieces of hardware. For example, when the above functions are realized by an electronic circuit that is hardware, the electronic circuit may be realized by a digital circuit including many logic circuits, an analog circuit, or a combination thereof.

[1-4. Actuator part]
Next, the actuator section 7 will be described.
The actuator section 7 is configured to stimulate the five senses of the user and includes a visual action section 31 , an auditory action section 33 , an olfactory action section 35 and a tactile action section 37 .

The visual action unit 31 uses, for example, the display 15 to provide images to the user. That is, an image corresponding to the content determined by the provision space determination unit 27 is displayed on the display 15 .

For example, if the content is "enjoy tea in the garden", the display 15 displays an image of a beautiful garden. As a device for displaying an image, a display other than the display 15 may be used.

The auditory action unit 33 drives a speaker (not shown) to provide the user with sounds, music, etc. corresponding to the content. For example, if the content is "enjoying tea in the garden", the sounds of birds or classical music that gives an image of nature may be played.

The olfactory action unit 35, for example, drives a device (not shown) that supplies scent to provide the user with the scent corresponding to the content. For example, if the content is "enjoy tea in the garden", the fragrance of flowers and the like may be provided.

The haptic action section 37 can provide the user with a tactile sensation corresponding to the content as needed. For example, an air conditioner or the like may be used to supply cool air or warm air to the user according to the contents of the content. Further, when giving the user a tactile sensation due to vibration, a motor or the like arranged in the user's seat may be driven to give the user a feeling of vibration.

[1-4. process]
Next, the processing performed by the control unit 5 will be described using the flowchart of FIG. 6 and the like.

As shown in FIG. 6, in step (hereinafter referred to as S) 100, the display 15 displays a current emotion input screen as shown in FIG.
In the following S110, it is determined whether or not an operation for inputting the current emotion has been performed on the current emotion input screen. Specifically, it is determined whether or not the range of each pictogram indicating the current emotion has been touched on the current emotion input screen. Specifically, it is determined whether or not the touched position (that is, the coordinates) is within the range of each pictogram. If the determination is affirmative here, the process proceeds to S120, and if the determination is negative, the process waits.

In S120, the current input screen is switched to display the input screen of the target scene on the display 15 as shown in FIG.
In the following S130, it is determined whether or not an operation for inputting a target scene has been performed on the input screen where the target scene exists. Specifically, it is determined whether or not the range of each pictogram indicating the target scene has been touched on the target scene input screen. Specifically, it is determined whether or not the touched position (that is, coordinates) is within the range of each pictogram. If the determination here is affirmative, the process proceeds to S140, and if the determination is negative, the process waits.

In S140, the current emotion is determined from the coordinates input on the current emotion input screen. That is, on the current emotion input screen, the coordinates of the input screen correspond to the pictograms of each emotion, so the current emotion can be determined from the input coordinates.

In the following S150, the target scene is determined from the coordinates input on the input screen of the target scene. That is, on the input screen of the target scene, the coordinates of the input screen correspond to the pictograms of each scene, so the target scene can be determined from the input coordinates.

In the subsequent S160, a plurality of contents recommended to the user are selected according to the current emotion and the desired scene. That is, as described above, a plurality of contents are prepared in advance according to the combination of the current emotion corresponding to the pictogram of each emotion and the target scene corresponding to the pictogram of each scene. content as recommended content.

Such content may be stored in the memory of the control unit 5 or the like, or may be obtained from a predetermined server or the like via the Internet or the like.
Moreover, each content may be selected in advance by a psychology expert or the like, or may be selected by questionnaires or the like of a large number of subjects through experiments or the like.

At S170, the content to be provided to the user is determined from the plurality of contents recommended at S160. That is, as described above, a plurality of recommended contents may be presented to the user and determined by the user. Alternatively, it may be randomly determined mechanically.

In the following S180, the content determined in S170 is provided to the user by driving the actuator section 7, and this process is once terminated.
[1-5. effect]
In the first embodiment described above, the following effects can be obtained.

(1a) In the first embodiment, the user's current emotion manually input by the user is acquired using the current emotion input screen. In addition, the user's target scene manually input by the user is acquired using the input screen of the target scene. Contents to be provided to the user are selected and recommended based on the current emotion and the target scene thus acquired.

With such a configuration, in the first embodiment, it is possible to recommend content that is highly satisfying to the user.
Specifically, in the first embodiment, by acquiring the current emotion information input by the user, it is possible to grasp the current actual emotion of the user with high accuracy. In addition, by acquiring the information of the target scene input by the user, the user's actual target scene can be grasped with high accuracy.

Therefore, by selecting content based on such realistic current emotions and desired scenes, it is possible to recommend content that is comfortable (that is, has a high degree of satisfaction) for the user.

(1b) In the first embodiment, pictograms of each emotion are displayed on the emotion ring diagram as the current emotion input screen. Therefore, the user can easily input the current emotion by touching the emotion pictogram on the emotion ring diagram.

Similarly, in the first embodiment, pictograms of each scene are displayed on the emotional ring diagram as the input screen for the target scene. Therefore, the user can easily input the desired scene by touching the pictogram of the scene in the emotion circumflex.

As described above, in the first embodiment, pictograms representing emotions and scenes are displayed on the display 15, so that the user can intuitively understand and input emotions and scenes. Therefore, there is a remarkable effect that an interface with good usability (that is, ease of use) can be realized.

In addition, by displaying scene pictograms in a dark color and emotion pictograms in a light color on the scene input screen, it is possible to easily grasp what kind of emotion each scene corresponds to.

(1c) In the first embodiment, the content is configured to stimulate at least one of the five senses of the user. For example, as this stimulus, one of visual stimulus, auditory stimulus, olfactory stimulus, and tactile stimulus can be adopted. Therefore, it is possible to provide users with effective content that can give them desired emotions.

[1-6. Correspondence of wording]
In the relationship between the first embodiment and the present disclosure, the content recommendation device 1 corresponds to the content recommendation device, the emotion cyclic model corresponds to the evaluation model, and the evaluation diagram corresponds to the emotional cyclic diagram.

Also, the user input unit 11 and the processes of S100 and S120 correspond to the collection unit, and the recommendation generation unit 25 and the processing of S160 correspond to the collection recommendation unit.
Alternatively, the user input section 11 and S100 correspond to the first acquisition section, the user input section 11 and S120 correspond to the second acquisition section, and the recommendation generation section 25 and the process of S160 correspond to the acquisition recommendation section. Note that the display 15 corresponds to the display device.

[1-7. Modification]
In the above-described first embodiment, the emotion circumflex is used to display and input the current emotion, which is the current situation, and the target scene, which is the target situation. As shown in Table 1 below, various current situations and various target situations are input using the emotional ring diagram, and the input current situation and the content are recommended. Content may be recommended according to the desired situation.

Table 1 below shows combinations of the current situation and the target situation to be displayed and input in the emotional ring diagram. In addition, No. of "Table 1". Example 2 is the example shown in the first embodiment.

In the case shown in Table 1 as well, emotions and scenes can be input by displaying various pictograms on the emotional ring diagram, as in the first embodiment.
For example, No. in "Table 1". In example 3, a pictogram indicating the current scene is displayed on the emotional ring diagram, and the current scene can be input from the input screen. In addition, a pictogram indicating the target emotion can be displayed on another emotion ring diagram, and the target emotion can be input from the input screen.

Therefore, one or a plurality of recommended contents can be selected from a large number of pre-stored contents based on the input current scene and target emotion.
In addition, No. in Table 1. As in 5 to 9, when inputting emotions and scenes in the current situation and the target situation, separate emotion cyclic diagrams are used for emotions and scenes. Alternatively, as shown in a second embodiment, which will be described later, the same emotional ring diagram in which pictograms of emotions and pictograms of scenes are displayed at the same time may be used. In this case, emotions and scenes can be input simultaneously.

For example, No. in "Table 1". In example 5, a pictogram indicating the current emotion is displayed on the emotion ring diagram, and the current emotion can be input from the input screen. Also, a pictogram showing the current scene can be displayed on another emotional ring diagram, and the current scene can be input from the input screen.

Alternatively, a pictogram representing the current emotion and a pictogram representing the current scene may be displayed on the same emotion ring diagram, and the current emotion and the current scene may be input.
A pictogram indicating a target emotion can be displayed using another emotion ring diagram, and the target emotion can be input from the input screen.

Therefore, No. In example 5, one or more recommended contents can be selected from a large number of pre-stored contents based on the input current emotion, current scene, and target emotion.

In this case, based on three parameters (that is, "current emotion", "current scene", and "desired emotion"), one or more contents to be recommended from a large number of contents stored in advance are selected. can be selected.

Also, No. 9, based on four parameters (i.e., "current emotion", "current scene", "target emotion", and "target scene"), 1 Alternatively, multiple contents can be selected.

[2. Second Embodiment]
Since the basic configuration of the second embodiment is similar to that of the first embodiment, differences from the first embodiment will be mainly described below. The same reference numerals as in the first embodiment indicate the same configurations, and the preceding description is referred to.

In the second embodiment, as shown in FIG. 7, an example will be described in which the display 15 displays an input screen for an emotional ring diagram of a target scene as shown in FIG.
In this emotion ring diagram, the target scene pictograms are displayed in a dark color, and the target emotion pictograms are displayed in a light color.

In the second embodiment, the position of the pictogram of the target scene (that is, the coordinates of the pictogram) corresponds to the area in which the target emotion pictogram is arranged (that is, the coordinates of the areas R1 to R6). .

That is, when a target scene pictogram is touched and selected (ie, input), the target emotion pictogram corresponding to the area in which the pictogram is placed is also selected (ie, input). is configured as

Therefore, in the second embodiment, when the user touches and selects the pictogram of the target scene arranged in the emotion circumflex, the target emotion is also displayed from the position where the pictogram of the target scene is arranged. can be entered at the same time.

Here, an example of simultaneously inputting the target scene and target emotion has been given, but the current scene and current emotion may be simultaneously input in a similar manner. Specifically, the pictogram of the current scene is displayed darkly and the pictogram of the current emotion is lightly displayed on the emotion ring diagram. The current emotion may be simultaneously input from the position (that is, the area) where the pictogram of the scene is arranged.

Therefore, in the second embodiment, the same effects as those of the first embodiment can be obtained, and there is an effect that emotions and scenes can be input more efficiently.
[3. Third Embodiment]
Since the basic configuration of the third embodiment is the same as that of the first embodiment, differences from the first embodiment will be mainly described below. The same reference numerals as in the first embodiment indicate the same configurations, and the preceding description is referred to.

In the third embodiment, as shown in FIG. 8, an example will be described in which the display 15 displays an input screen for an emotional ring diagram of current emotions as shown in FIG.
The third embodiment is configured such that various emotions can be extracted by selecting an arbitrary location on the emotion circumflex.

Specifically, the coordinates (i.e., first coordinates, second coordinates) of an arbitrary position touched by the user (for example, the dashed-line circular area in FIG. 8) on the emotion circumflex in which the current emotion can be input. can be entered. Since these coordinates are indices indicating the degree of arousal and the degree of pleasure and displeasure, it is possible to extract emotions corresponding to the degree of arousal and the degree of pleasure and displeasure from these coordinates.

For example, when the dashed circular area in FIG. 8 is touched, it can be seen that the consciousness is very clear and the mind is calm (that is, emotions).
In the third embodiment, since it is possible for the user to input an emotion corresponding to an arbitrary position touched by the user, even if the pictogram of emotion is touched, the emotion of the pictogram will not be input. there is That is, the emotion pictogram is a reference display for user input.

As another example, touching an emotion pictogram may input the emotion of the pictogram. In other words, it may be configured to allow input at an arbitrary location and input using pictograms of emotions.

Here, an example of inputting a current emotion using an emotion cyclone has been described. A target emotion may be input in the same manner as described above using a diagram.

Therefore, in the third embodiment, the same effects as those of the first embodiment can be obtained, and various emotions can be input, that is, emotions can be input with higher accuracy.
[4. Fourth Embodiment]
Since the basic configuration of the fourth embodiment is the same as that of the first embodiment, differences from the first embodiment will be mainly described below. The same reference numerals as in the first embodiment indicate the same configurations, and the preceding description is referred to.

In the fourth embodiment, the position of the pictogram indicating the current scene and the position of the pictogram indicating the target scene can be moved to arbitrary positions in the emotional circumflex.

For example, as shown in FIG. 4, when pictograms of a target scene are displayed in each of regions R3 to R5, the position of each pictogram can be moved by the user's operation.

Examples of the method of moving the pictogram include the following methods.
A switching button (not shown) for switching to a movement screen for moving the pictogram is provided at a predetermined position of the input screen or the like on which the pictogram is displayed on the display 15 . Further, the movement screen is provided with a return button (not shown) for returning to the original input screen. Note that the movement screen immediately after switching is the same as the input screen before switching.

The user touches (that is, taps) the switching button of the input screen to switch to the movement screen. Next, on the movement screen, the pictogram to be moved is touched with, for example, a fingertip and dragged to a predetermined position to be moved. This completes the movement of the pictogram. After that, by touching the return button, the screen is switched to the input screen. In this input screen, an input screen after movement of the pictogram is displayed. Therefore, on this input screen, it is possible to input various scenes including scenes corresponding to the moved pictogram.

The fourth embodiment has the same effect as the first embodiment. Furthermore, in the fourth embodiment, since the pictogram can be moved to any position of the user, it is possible to input a scene that matches the user's actual feeling.

Here, the movement of the pictogram of the target scene has been described, but the pictogram of the current scene can be similarly moved on the movement screen.
<Modification 1>
In the fourth embodiment, movement of scene pictograms has been described, but it is also possible to delete pictograms.

For example, a delete button (not shown) is provided on an input screen or the like, and the touched pictogram can be deleted by first touching the delete button and then touching the pictogram to be deleted.

<Modification 2>
In the fourth embodiment, movement of scene pictograms has been described, but it is also possible to add pictograms to the input screen.

For example, it is possible to select an arbitrary pictogram from many scene pictograms stored in the memory and display the selected pictogram on the input screen (that is, add it).

Methods for adding pictograms include, for example, the following methods.
An add button (not shown) for switching to an add screen for adding a pictogram is provided at a predetermined position of the input screen or the like on which the pictogram is displayed on the display 15 . Further, the additional screen is provided with a return button (not shown) for returning to the original input screen.

The user touches the add button on the input screen to switch to the add screen. Since pictograms of many scenes are displayed on this additional screen, the user can determine the pictograms to be added by touching the pictograms to be added. After determining the pictogram to be added, touch the return button to switch to the input screen. On this input screen, for example, the added pictogram is displayed outside the emotional cyclone, so that the outer pictogram can be dragged with a finger and placed at a predetermined position on the emotional cyclone.

Therefore, on this input screen, it is possible to input various scenes including scenes corresponding to the added pictograms.
[5. Fifth Embodiment]
Since the basic configuration of the fifth embodiment is the same as that of the first embodiment, differences from the first embodiment will be mainly described below. The same reference numerals as in the first embodiment indicate the same configurations, and the preceding description is referred to.

(1) In the fifth embodiment, as shown in FIG. 9, a pictogram of the current scene displayed in the emotion circumflex is used to input the current scene and the current emotion at the same time.
FIG. 9 is an emotion ring diagram for simultaneously inputting the current scene and current emotion. mark), and the content of the scene is displayed in characters.

For example, the pictogram of "I'm in a hurry because I can't make progress at work" is in the first region R1 of the emotion of "Irritated". Therefore, when the user touches the pictogram of "I'm in a hurry because I can't make progress in my work", the user can simultaneously input the scene of "I'm in a hurry because I can't make progress in my work" and the feeling of "frustration".

A pictogram or characters of the current scene may be displayed in a part (eg, left half) of the emotion ring diagram, and the current emotion may be input at the same time as the current scene is input.
(2) In addition, in the fifth embodiment, as shown in FIG. 10, using the pictogram of the target scene displayed in a part (for example, the right half) of the emotional circumflex, You can enter the desired emotion.

FIG. 10 is an emotion ring diagram for simultaneously inputting a target scene and target emotion.

For example, the pictogram "relax and work" is in the fifth region R5 of the emotion "happiness". Therefore, by touching the pictogram of "relax and work", the user can simultaneously input the scene of "relax and work" and the emotion of "happiness".

(3) In addition, in FIG. 9 described above, characters or the like are written on the display 15 to indicate the current scene, but as shown in FIGS. can be displayed explicitly. Note that FIG. 12 shows pictograms that can be used in each of the current and target scenes.

In this way, when a pictogram indicating the current scene is displayed on the display 15, the user can intuitively understand the current scene, so that input can be performed more effectively than when characters are displayed.

As in FIG. 10, a pictogram indicating the target scene may be displayed on the right half of the emotional ring diagram. Also in this case, the user can intuitively understand the target scene, so that the input can be performed more appropriately than when the scene is indicated by characters or the like.

As described above, the fifth embodiment has the same effect as the first embodiment, and also has the effect of being able to input emotions and scenes efficiently.
[6. Experimental example]
Next, an experimental example will be described.

<Experimental example 1>
Using the content recommendation device of the first embodiment, the inventor conducted an experiment in which a plurality (that is, 24 persons) of subjects input their current emotions using an emotion cyclic diagram.

As a result, 75% of all subjects were able to smoothly perform input that matches their current emotions after performing the test twice or less. It should be noted that "twice" here means that the process has been redone once.

Similarly, 75% of all subjects (that is, 24 subjects) were able to smoothly input the desired scene in 3 or less trials. It should be noted that 3 times here means that the process has been redone twice.

<Experimental example 2>
In addition, the present inventor conducted an experiment on usability when inputting a user's situation using the content recommendation device of the first embodiment for a plurality of (that is, 23) subjects.

As a result, when the content recommendation device is used, it is possible to intuitively understand from point A (e.g., current emotion) to point B (e.g., desired scene), and "pictograms are intuitively I can answer,” was a positive response.

The experimental results are shown in FIG. In FIG. 13, usability evaluation is indicated by the number of star marks, and the greater the number of star marks, the higher the evaluation. The maximum number of star marks is 5, and in the experiment, 90% or more of the cases were 3 or more.

From this, it can be seen that the usability of the content recommendation device is very high.
[7. Other embodiments]
Although the embodiments of the present disclosure have been described above, the present disclosure is not limited to the above-described embodiments, and various modifications can be made.

(7a) In the above-described embodiment, Russell's Circle of Emotions has a first evaluation axis for evaluating the degree of arousal and a second evaluation axis for evaluating the degree of pleasure and displeasure as an evaluation model indicating a situation such as a person's emotions. Although the ring model is used, other evaluation models that indicate, for example, the user's current situation or target situation may be used. For example, different contents of the evaluation axis or different number of evaluation axes can be adopted. Further, other shapes (for example, polygonal shapes such as squares) can be adopted instead of the circular emotional circumflex.

(7b) The content recommendation apparatus and techniques described in this disclosure are provided by configuring a processor and memory programmed to perform one or more functions embodied by a computer program. It may be implemented by a computer.

Alternatively, the content recommendation apparatus and techniques described in this disclosure may be implemented by a dedicated computer provided by configuring a processor with one or more dedicated hardware logic circuits.

Alternatively, the content recommendation device and method described in this disclosure is a combination of a processor and memory programmed to perform one or more functions and a processor configured by one or more hardware logic circuits. may be implemented by one or more dedicated computers configured by

Computer programs may also be stored as computer-executable instructions on a computer-readable non-transitional tangible storage medium. The method of realizing the function of each unit included in the control unit does not necessarily include software, and all the functions may be realized using one or a plurality of pieces of hardware.

(7c) A plurality of functions possessed by one component in the above embodiment may be realized by a plurality of components, or a function possessed by one component may be realized by a plurality of components. . Also, a plurality of functions possessed by a plurality of components may be realized by a single component, or a function realized by a plurality of components may be realized by a single component. Also, part of the configuration of the above embodiment may be omitted. Also, at least part of the configuration of the above embodiment may be added or replaced with respect to the configuration of the other above embodiment.

(7d) In addition to the content recommendation device described above, a system having the content recommendation device as a component, a program for operating the computer of the content recommendation device, a non-transition tangible recording medium such as a semiconductor memory recording this program, The present disclosure can also be implemented in various forms, such as methods (eg, content recommendation methods).

For example, "a content recommendation method used to recommend content to be provided to users, an evaluation model having a first evaluation axis for evaluating the degree of arousal and a second evaluation axis for evaluating the degree of pleasure and discomfort a content recommendation method, which collects a user situation indicating the user's situation, which is used when recommending the content. In addition, "acquisition of the current situation of the user input by the user, acquisition of the target situation of the user input by the user, and acquisition of the current situation and the target situation A content recommendation method for recommending content to be provided to the user based on the content can be adopted.

1: content recommendation device, 3: information collection unit, 5: control unit, 7: actuator unit, 11: user input unit, 15: display, 25: recommendation generation unit

Claims (15)

A content recommendation device (1) used to recommend content to be provided to a user,
Using an evaluation model having a first evaluation axis that evaluates the degree of arousal and a second evaluation axis that evaluates the degree of pleasure and discomfort, user situations indicating the user's situation used when recommending the content are collected. configured to
Content recommendation device. The content recommendation device according to claim 1,
A collecting unit (11, S100, S120) and
a collection recommendation unit (25, S160) configured to recommend content to be provided to the user based on the user situation collected by the collection unit;
a content recommendation device. The content recommendation device according to claim 1 or claim 2,
Having a configuration for displaying a pictogram indicating the user situation on a display device (15),
configured to input the user situation corresponding to the selected pictogram when the user selects the pictogram displayed on the display device;
Content recommendation device. The content recommendation device according to any one of claims 1 to 3,
The user situation is at least one of a current situation of the user and a target situation desired by the user,
Content recommendation device. a first acquisition unit (11, S100) configured to acquire the user's current situation input by the user;
a second acquisition unit (11, S120) configured to acquire a target situation input by the user;
an acquisition recommendation unit ( 25, S160) and
A content recommendation device (1), comprising: The content recommendation device according to claim 5,
Having a configuration for displaying a pictogram indicating the current situation and a pictogram indicating the target situation on a display device (15),
When each of the pictograms displayed on the display device is selected by the user, the current situation and the target situation corresponding to each of the selected pictograms are input. was
Content recommendation device. The content recommendation device according to claim 5 or claim 6,
configured to acquire the current situation and the target situation using an evaluation model having a first evaluation axis for evaluating the degree of arousal and a second evaluation axis for evaluating the degree of pleasure and displeasure;
Content recommendation device. The content recommendation device according to any one of claims 4 to 7,
the current situation includes at least one of a current scene and a current emotion;
Content recommendation device. The content recommendation device according to any one of claims 4 to 8,
the target situation includes at least one of a target scene and a target emotion;
Content recommendation device. The content recommendation device according to claim 9,
The display showing at least one of the current scene and the target scene is an evaluation diagram showing an evaluation model having a first evaluation axis for evaluating the degree of arousal and a second evaluation axis for evaluating the degree of pleasure and discomfort. Deploy,
Content recommendation device. The content recommendation device according to claim 10,
When at least one of the current scene and the target scene is placed in the evaluation model, the current scene is changed to the current scene based on the current emotion set corresponding to the current scene. determining an emotion, and determining the target emotion from the target scene based on the target emotion set corresponding to the target scene;
Content recommendation device. The content recommendation device according to any one of claims 4 to 11,
When the current situation is the current emotion and the target situation is the target emotion,
Any position of an evaluation diagram showing an evaluation model having a first evaluation axis for evaluating the degree of arousal and a second evaluation axis for evaluating the degree of pleasure and displeasure for at least one of the current emotion and the target emotion. configured to determine by selecting the
Content recommendation device. The content recommendation device according to any one of claims 4 to 12,
if the current situation is a current scene and the target situation is a target scene,
In an evaluation diagram showing an evaluation model having a first evaluation axis for evaluating the degree of arousal and a second evaluation axis for evaluating the degree of pleasure and discomfort, at least one of the current scene and the target scene is displayed. , configured to allow at least one of arbitrarily moving and arbitrarily increasing or decreasing,
Content recommendation device. The content recommendation device according to any one of claims 1 to 13,
the content is configured to stimulate at least one of the user's five senses;
Content recommendation device. The content recommendation device according to claim 14,
The configuration that stimulates the five senses is at least one of visual stimulation, auditory stimulation, olfactory stimulation, and tactile stimulation.
Content recommendation device.

Images