JP7387970B2 - Calculation device, calculation method, calculation program - Google Patents

Description

The present invention relates to a calculation device, a calculation method, and a calculation program.

2. Description of the Related Art Conventionally, in SNS (Social Network Service), technology has been provided that provides a service that allows users to find users who have common hobbies and preferences, with the aim of supporting connections between users.

Japanese Patent Application Publication No. 2010-250528

However, in the above-mentioned conventional technology, the index value regarding the content is not necessarily the index value indicating the appeal of the content. For example, in the above-mentioned conventional technology, the user merely adds an emotion tag indicating the user's emotion to a video scene, and the index value related to the content is not necessarily the index value indicating the appeal of the content.

The present application has been made in view of the above, and aims to provide a calculation device, a calculation method, and a calculation program that can calculate an index value that enables evaluation of content appeal.

The calculation device according to the present application includes an acquisition unit that acquires information regarding the user, and an index value indicating the appeal of the content based on the information regarding the user acquired by the acquisition unit, the index value for each user; The present invention is characterized by comprising a calculation unit that calculates the index value and statistical values for a plurality of users of the index value to be compared.

According to one aspect of the embodiment, it is possible to calculate an index value that makes it possible to evaluate the appeal of content.

FIG. 1 is a diagram illustrating an example of a calculation process executed by a calculation device according to an embodiment. FIG. 2 is a diagram illustrating a configuration example of a calculation device according to an embodiment. FIG. 3 is a diagram illustrating an example of a video information storage unit according to the embodiment. FIG. 4 is a diagram illustrating an example of an index value information storage unit according to the embodiment. FIG. 5 is a flowchart illustrating an example of the flow of calculation processing executed by the calculation device according to the embodiment. FIG. 6 is a diagram illustrating an example of a generation process executed by a calculation device according to a modification. FIG. 7 is a diagram illustrating an example of a generation process executed by a calculation device according to a modification. FIG. 8 is a diagram illustrating an example of a generation process executed by a calculation device according to a modification. FIG. 9 is a hardware configuration diagram showing an example of a computer that implements the functions of the calculation device.

DESCRIPTION OF THE PREFERRED EMBODIMENTS Below, a calculation device, a calculation method, and an embodiment of a calculation program (hereinafter referred to as "embodiments") according to the present application will be described in detail with reference to the drawings. Note that this embodiment does not limit the calculation device, calculation method, and calculation program according to the present application. Moreover, each embodiment can be combined as appropriate within the range that does not conflict with the processing contents. Further, in each of the embodiments below, the same parts are given the same reference numerals, and redundant explanations will be omitted.

[1. Example of provision processing indicated by the calculation device]
An example of the provision process executed by the calculation device according to the embodiment will be described using FIG. 1. FIG. 1 is a diagram illustrating an example of a providing process executed by a calculation device according to an embodiment. Specifically, the calculation device 100 calculates an index value indicating the appeal of the content based on information about the user, an index value for each user, and statistics for a plurality of users of index values to be compared with the index value. Calculate the value. Note that in the following, a case where the content is a video will be taken as an example.

As shown in FIG. 1, the calculation system 1 includes a terminal device 10, an external device 50, and a calculation device 100. The terminal device 10, the external device 50, and the calculation device 100 are communicably connected by wire or wirelessly via a predetermined communication network (not shown). Note that the calculation system 1 shown in FIG. 1 may include a plurality of terminal devices 10, a plurality of external devices 50, and a plurality of calculation devices 100.

The terminal device 10 according to the embodiment is a calculation device used by a user who accesses content such as a web page displayed on a browser or content for an application. For example, the terminal device 10 is a desktop PC (Personal Computer), a notebook PC, a tablet terminal, a mobile phone, a PDA (Personal Digital Assistant), or the like. The example in FIG. 1 shows a case where the terminal device 10 is a smartphone used by a user. Note that below, the terminal device 10 may be referred to as a user. That is, in the following, the user can also be read as the terminal device 10.

The external device 50 according to the embodiment is an information providing device that provides information about videos and information about users for videos. For example, in the example shown in FIG. 1, the external device 50 stores information regarding videos and information regarding users for videos. The external device 50 then provides the calculation device 100 with information regarding the video and information regarding the user. Further, for example, the external device 50 stores information regarding the user for the video every predetermined period (for example, the most recent week).

Further, for example, the external device 50 stores information regarding the user based on advertising content of the video, comments on the video, and the like. Further, for example, the external device 50 stores information regarding the user based on the number of clicks on information regarding videos, the time spent viewing information regarding videos, and the like. Further, for example, the external device 50 stores information regarding the user based on a positive impression or a negative impression based on the user's response to predetermined advertising content.

Note that the information regarding the user here refers to a positive impression regarding the scene of the video. For example, a positive impression of a scene in a video is a user's positive impression of a scene such as a family gathering. Further, the information regarding the user is a negative impression regarding the scene of the video. For example, a negative impression of a scene in a video is a user's negative impression of a cruel scene. Further, the information regarding the user is information regarding the user's interests and the like.

The calculation device 100 according to the embodiment is realized by, for example, a server device or the like. Specifically, the calculation device 100 acquires information regarding the user from the external device 50. Based on the information regarding the user, the calculation device 100 calculates an index value indicating the appeal of the video, an index value for each user, and a statistical value for a plurality of users of the index value to be compared with the index value. Calculate. Then, the calculation device 100 calculates the user's index value (hereinafter, the index value of one user may be referred to as an individual index value) and the average value of the index values of all users (hereinafter, among the statistical values). , the average value of index values for all users is sometimes referred to as a statistical index value), and characteristic content indicating the characteristics of the video is generated. The calculation device 100 then provides the characteristic content to the user.

Note that the plurality of users here refers to all users who use the video distribution service. Further, for example, the plurality of users may be all users who have viewed the video. Further, for example, the plurality of users may be all users who have viewed the video. Further, for example, the plurality of users may be all users who viewed the video within a predetermined period. Further, for example, the plurality of users may be a user group having information regarding attributes similar to the target user. In the following description, it is assumed that the plurality of users are all users who have viewed the video.

Hereinafter, an example of the provision processing by the calculation device 100 will be explained along the flow using FIG.

First, as shown in FIG. 1, the calculation device 100 receives information regarding the video MO1 from the external device 50 (step S1). Subsequently, the calculation device 100 acquires information regarding the user from the external device 50 (step S2).

Then, the calculation device 100 calculates the individual index value and the statistical index value based on the information regarding the user acquired from the external device 50 (step S3). Specifically, the calculation device 100 calculates, as an individual index value, an index value indicating the user's degree of interest in the video, based on information regarding the user. Moreover, specifically, the calculation device 100 calculates, as an individual index value, an index value indicating the degree of the user's emotion regarding the video, based on information regarding the user. More specifically, the calculation device 100 calculates, as an individual index value, an index value indicating the degree of emotion of the user who has a positive impression regarding the video, based on information regarding the user. More specifically, the calculation device 100 calculates, as an individual index value, an index value indicating the degree of emotion of the user who has a negative impression regarding the video, based on information regarding the user.

For example, as shown in the example of FIG. 1, the calculation device 100 calculates the individual index value corresponding to the first scene of the video MO1 as "0.1" and the statistical index value as "0.1". Further, for example, the calculation device 100 calculates the individual index value corresponding to the second scene of the video MO1 as "0.3" and the statistical index value as "0.5". Further, for example, the calculation device 100 calculates the individual index value corresponding to the third scene of the video MO1 as "0.8" and the statistical index value as "0.6". Further, for example, the calculation device 100 calculates the individual index value corresponding to the fourth scene of the video MO1 as "0.9" and the statistical index value as "0.7". Further, for example, the calculation device 100 calculates the individual index value corresponding to the fifth scene of the video MO1 as "0.2" and the statistical index value as "0.7".

Note that the calculation device 100 calculates the individual index value and the statistical index value based on information about the user using conventional techniques such as machine learning. For example, the calculation device 100 inputs information about the user and a positive or negative impression based on the user's response to predetermined content, thereby creating a positive or negative impression of the video scene. Generate a learning model that outputs a score of a certain impression. Further, for example, the calculation device 100 inputs information about the user and a positive impression or a negative impression based on the content of the user's comments regarding the predetermined content of the user, thereby creating a positive impression about the scene of the video. A learning model is generated that outputs an impression or negative impression score. Then, the calculation device 100 calculates the individual index value and the statistical index value based on this learning model. Further, for example, the calculation device 100 generates a learning model that outputs a score regarding the user's interests by inputting information regarding the user and information regarding the user's interests based on the user's response to a predetermined content. do. Further, for example, the calculation device 100 can generate a learning model that outputs a score related to the user's interests by inputting information related to the user and information related to the user's interests based on the contents of the user's comments on a predetermined content. generate. Then, the calculation device 100 calculates the individual index value and the statistical index value based on this learning model.

Subsequently, the calculation device 100 generates a video digest EM1 as the feature content based on the individual index value and the statistical index value (step S4). Specifically, the calculation device 100 generates an edited video based on a scene corresponding to a magnitude relationship between a predetermined individual index value and a predetermined statistical index value for each time variation of the video.

For example, in the example of FIG. 1, it is assumed that the calculation device 100 selects a scene of a video when either the threshold value of the individual index value or the statistical index value is greater than or equal to the individual index value or the statistical index value. Further, it is assumed that the predetermined threshold value between the individual index value and the statistical index value is "0.6". In this case, the calculation device 100 calculates that the individual index value "0.1" corresponding to the first scene of the video MO1 is smaller than the threshold value, and the statistical index value "0.1" corresponding to the first scene of the video MO1. is smaller than the predetermined threshold, it is determined that the first scene of the video MO1 is not selected. Further, the calculation device 100 calculates that the individual index value "0.3" corresponding to the second scene of the video MO1 is smaller than the threshold value, and the statistical index value "0.5" corresponding to the second scene of the video MO1 is smaller than the threshold value. Since it is smaller than the predetermined threshold, it is determined that the second scene of video MO1 is not selected.

Further, the calculation device 100 determines that the individual index value "0.8" corresponding to the third scene of the video MO1 is equal to or greater than the threshold value, and the statistical index value "0.6" corresponding to the third scene of the video MO1 is Since it is greater than or equal to the predetermined threshold, it is determined that the third scene of video MO1 is to be selected. Further, the calculation device 100 determines that the individual index value "0.9" corresponding to the fourth scene of the video MO1 is equal to or higher than the threshold value, and the statistical index value "0.7" corresponding to the fourth scene of the video MO1 is Since it is greater than or equal to the predetermined threshold, it is determined that the fourth scene of video MO1 is to be selected.

Further, the calculation device 100 calculates that the individual index value "0.2" corresponding to the fifth scene of the video MO1 is smaller than the threshold value, and the statistical index value "0.7" corresponding to the fifth scene of the video MO1 is smaller than the threshold value. Since it is greater than or equal to the predetermined threshold, it is determined that the fifth scene of video MO1 is to be selected. In this way, the calculation device 100 selects the scenes of the video MO1 that are equal to or higher than the predetermined threshold, and selects the third scene of the video MO1, the fourth scene of the video MO1, and the fourth scene of the video MO1 as characteristic contents. A video digest EM1 including the fifth scene is generated.

Then, the calculation device 100 provides the user with the video digest EM1 as the feature content (step S5). For example, in the example of FIG. 1, the calculation device 100 provides a video digest EM1 to the user who has acquired information about the user.

In this way, the calculation device 100 according to the embodiment acquires information regarding the user. The calculation device 100 calculates an index value indicating the appeal of the video for each user and a statistical value for a plurality of users of the index value to be compared with the index value based on the information regarding the user. do. Then, the calculation device 100 generates characteristic content indicating the characteristics of the video based on the index value and the average value of the statistical values. The calculation device 100 then provides the characteristic content to the user. Thereby, the calculation device 100 according to the embodiment can calculate an index value related to a positive impression or a negative impression of a scene of a video, and an index value related to a user's interest. It is possible to calculate an index value that makes it possible to

This point will be explained. To explain using the example of FIG. 1, the calculation device 100 calculates, as an individual index value, an index value indicating the user's degree of interest in videos, based on information about the user. Further, the calculation device 100 calculates, as an individual index value, an index value indicating the degree of the user's emotion regarding the video, based on the information regarding the user. Then, the calculation device 100 generates a video digest EM1 as the feature content based on the individual index value and the statistical index value. Thereby, the calculation device 100 can generate a digest of the video indicating the appeal of the video based on the magnitude relationship between the individual index value calculated based on the information about the user and the statistical index value. From this, the calculation device 100 can generate characteristic content based on individual index values and statistical index values that take into account the user's interests and emotions, so that the content appeals to the user. It is possible to provide highly distinctive content.

In addition, the calculation device 100 can prevent the possibility that fair evaluation will be hindered due to overlooking a specific scene if the information is from only one user. Then, the calculation device 100 can determine a scene with a high appeal effect that prevents overlooking of a specific scene, etc., based on the individual index value of one user while referring to the statistical index value. Thereby, the calculation device 100 can generate characteristic content by comparing the statistical evaluation and the user-individual evaluation, so that it is possible to efficiently provide characteristic content that is highly appealing to the user. . Furthermore, different users may have different impressions of the same video, such as some users having a positive impression and some users having a negative impression. In this case as well, the calculation device 100 generates characteristic content based on individual index values and statistical index values that take into account the emotions of a user who has a positive impression and the emotions of other users who have a negative impression. Therefore, it is possible to provide characteristic content that is highly appealing to users.

[2. Configuration of calculation device]
Next, the configuration of the calculation device 100 according to the embodiment will be described using FIG. 2. FIG. 2 is a diagram illustrating a configuration example of the calculation device 100 according to the embodiment. As shown in FIG. 2, the calculation device 100 includes a communication section 110, a storage section 120, and a control section 130.

(About communication department 110)
The communication unit 110 is realized by, for example, a NIC (Network Interface Card). The communication unit 110 is connected to a network by wire or wirelessly, and transmits and receives information between the terminal device 10 and the external device 50.

(About storage unit 120)
The storage unit 120 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 120 includes a video information storage unit 121 and an index value information storage unit 122.

(About the video information storage unit 121)
The video information storage unit 121 according to the embodiment stores information regarding videos received from the external device 50. Here, FIG. 3 shows an example of the video information storage unit 121 according to the embodiment. In the example shown in FIG. 3, the video information storage unit 121 has items such as "video ID" and "video".

"Video ID" is an identifier that identifies a video. “Video” is information regarding a video received from the external device 50 associated with “Video ID”. For example, in FIG. 3, the product "M1" identified by the video ID is "MO1". In the example shown in FIG. 3, the moving image is expressed by an abstract code such as "MO1", but the moving image may be information indicating a specific file format of the moving image.

(Regarding the index value information storage unit 122)
The index value information storage unit 122 according to the embodiment stores an index value that is calculated based on information regarding the user and indicates the appeal of the content. Here, FIG. 4 shows an example of the index value information storage unit 122 according to the embodiment. In the example shown in FIG. 4, the index value information storage unit 122 has items such as "video ID", "time", "user ID", "individual index value related to interest", and "individual index value related to emotion". .

"Video ID" is an identifier that identifies a video. “Time” is information regarding the time within the video associated with the “video ID”. “User ID” is an identifier that identifies a user. The "individual index value related to interest" is an individual index value calculated based on information related to the user's interest associated with the "user ID." For example, the "individual index value regarding interest" indicates a larger value as the user's interest in the scene of the video is higher, and a smaller value as the user's interest in the scene of the video is lower. The "individual index value regarding emotion" is an individual index value calculated based on information regarding the user's emotion associated with the "user ID." For example, the "individual index value regarding emotion" indicates a larger value as the user's positive impression of the video scene is stronger, and a smaller value as the user's negative impression of the video scene is stronger.

For example, in FIG. 4, when the time in "M1" identified by the video ID is "T1", the "individual index value regarding interest" corresponding to "U1" identified by the user ID is "0. 8'', and the ``individual index value regarding emotion'' is ``0.8''. Note that in the example shown in FIG. 4, the time is expressed by an abstract code such as "T1", but the time may be information indicating a specific time within the video.

(About the control unit 130)
The control unit 130 is a controller, and for example, uses a CPU (Central Processing Unit), an MPU (Micro Processing Unit), etc. to execute various programs (an example of a calculation program) stored in a storage device inside the calculation device 100. (equivalent) is realized by executing the RAM as a work area. Further, the control unit 130 is a controller, and is realized by, for example, an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

As shown in FIG. 2, the control unit 130 includes a reception unit 131, an acquisition unit 132, a calculation unit 133, a generation unit 134, and a provision unit 135, and has information processing functions and operations described below. to realize or carry out. Note that the internal configuration of the control unit 130 is not limited to the configuration shown in FIG. 2, and may be any other configuration as long as it performs information processing to be described later. Further, the connection relationship between the respective processing units included in the control unit 130 is not limited to the connection relationship shown in FIG. 2, and may be other connection relationships.

(About reception department 131)
The reception unit 131 receives information regarding videos. For example, in the example of FIG. 1, the reception unit 131 receives information regarding the video MO1 from the external device 50. Then, the reception unit 131 stores information regarding the video MO1 in the video information storage unit 121.

(About the acquisition unit 132)
The acquisition unit 132 acquires various information. Specifically, the acquisition unit 132 acquires information regarding the user. For example, in the example of FIG. 1, the acquisition unit 132 acquires information about the user from the external device 50 based on the number of clicks on information about videos, the time spent viewing information about videos, and the like. Further, for example, the acquisition unit 132 acquires information about the user from the external device 50 based on a positive impression or a negative impression based on the user's response to predetermined advertising content. Further, for example, the acquisition unit 132 acquires information regarding the user's interests from the external device 50.

Note that the acquisition unit 132 may acquire attribute information that is information regarding attributes of the user, location information of the user, content viewing history of the user, advertising content viewing history of the user, etc. as information regarding the user.

(About the calculation unit 133)
The calculation unit 133 calculates an index value indicating the appeal of the content based on the information regarding the user acquired by the acquisition unit 132, an index value for each user, and a plurality of users whose index values are to be compared with the index value. Calculate the statistical value for. Specifically, the calculation unit 133 calculates, as an index value, an index value indicating the user's degree of interest in the content, based on the information regarding the user acquired by the acquisition unit 132. Moreover, specifically, the calculation unit 133 calculates, as an index value, an index value indicating the degree of the user's emotion regarding the content, based on the information regarding the user acquired by the acquisition unit 132.

For example, as shown in the example of FIG. 1, the calculation unit 133 calculates the individual index value corresponding to the first scene of the video MO1 as "0.1" and the statistical index value as "0.1". Further, for example, the calculation unit 133 calculates the individual index value corresponding to the second scene of the video MO1 as "0.3" and the statistical index value as "0.5". Further, for example, the calculation unit 133 calculates the individual index value corresponding to the third scene of the video MO1 as "0.8" and the statistical index value as "0.6". Further, for example, the calculation unit 133 calculates the individual index value corresponding to the fourth scene of the video MO1 to be "0.9" and the statistical index value to be "0.7". Further, for example, the calculation unit 133 calculates the individual index value corresponding to the fifth scene of the video MO1 as "0.2" and the statistical index value as "0.7".

Note that the calculation unit 133 calculates the individual index value and the statistical index value based on information regarding the user using conventional techniques such as machine learning. For example, by inputting information about the user and a positive or negative impression based on the user's response to predetermined content, the calculation unit 133 can create a positive or negative impression of the video scene. Generate a learning model that outputs a score of a certain impression. Further, for example, the calculation unit 133 inputs information about the user and a positive impression or a negative impression based on the content of the user's comments regarding the predetermined content of the user, thereby creating a positive impression about the scene of the video. A learning model is generated that outputs an impression or negative impression score. Then, the calculation unit 133 calculates the individual index value and the statistical index value based on this learning model. Further, for example, the calculation unit 133 generates a learning model that outputs a score regarding the user's interests by inputting information regarding the user and information regarding the user's interests based on the user's response to a predetermined content. do. Further, for example, the calculation unit 133 inputs information regarding the user and information regarding the user's interests based on the content of the user's comments on a predetermined content, thereby creating a learning model that outputs a score regarding the user's interests. generate. Then, the calculation unit 133 calculates the individual index value and the statistical index value based on this learning model.

(About the generation unit 134)
The generation unit 134 generates characteristic content indicating the characteristics of the content based on the index value calculated by the calculation unit 133 and the average value of the statistical values. Specifically, based on the index value and the average value calculated by the calculation unit 133, the generation unit 134 generates feature content corresponding to the index value when the index value is larger than the average value. Further, specifically, based on the index value and the average value calculated by the calculation unit 133, when the average value is larger than the index value, the generation unit 134 generates feature content corresponding to the average value. .

For example, in the example of FIG. 1, the generation unit 134 selects a scene of a video when either the threshold value of the individual index value or the statistical index value is greater than or equal to the individual index value or the statistical index value. Further, it is assumed that the predetermined threshold value between the individual index value and the statistical index value is "0.6". In this case, the generation unit 134 generates an individual index value "0.1" corresponding to the first scene of the video MO1 that is smaller than the threshold value, and a statistical index value "0.1" corresponding to the first scene of the video MO1. is smaller than the predetermined threshold, it is determined that the first scene of the video MO1 is not selected. Furthermore, the generation unit 134 determines that the individual index value "0.3" corresponding to the second scene of the video MO1 is smaller than the threshold value, and the statistical index value "0.5" corresponding to the second scene of the video MO1 is smaller than the threshold value. Since it is smaller than the predetermined threshold, it is determined that the second scene of video MO1 is not selected.

In addition, the generation unit 134 determines that the individual index value "0.8" corresponding to the third scene of the video MO1 is equal to or greater than the threshold, and the statistical index value "0.6" corresponding to the third scene of the video MO1 is Since it is greater than or equal to the predetermined threshold, it is determined that the third scene of video MO1 is to be selected. In addition, the generation unit 134 determines that the individual index value "0.9" corresponding to the fourth scene of the video MO1 is equal to or greater than the threshold, and the statistical index value "0.7" corresponding to the fourth scene of the video MO1 is Since it is greater than or equal to the predetermined threshold, it is determined that the fourth scene of video MO1 is to be selected.

In addition, the generation unit 134 determines that the individual index value "0.2" corresponding to the fifth scene of video MO1 is smaller than the threshold value, and the statistical index value "0.7" corresponding to the fifth scene of video MO1 is smaller than the threshold value. Since it is greater than or equal to the predetermined threshold, it is determined that the fifth scene of video MO1 is to be selected. In this way, the generation unit 134 selects the scenes of the video MO1 that are equal to or higher than the predetermined threshold, so that the generation unit 134 selects the third scene of the video MO1, the fourth scene of the video MO1, and the fourth scene of the video MO1 as characteristic contents. A video digest EM1 including the fifth scene is generated.

(About the provision section 135)
The providing unit 135 provides the characteristic content generated by the generating unit 134 to the user. For example, in the example of FIG. 1, the providing unit 135 provides the digest EM1 of the video to the user who has acquired information about the user.

[3. Processing procedure]
Next, the procedure of the calculation process executed by the calculation device 100 according to the embodiment will be described using FIG. 5. FIG. 5 is a flowchart illustrating an example of the flow of calculation processing executed by the calculation device according to the embodiment.

As shown in FIG. 5, the receiving unit 131 receives information regarding moving images (step S101). For example, in the example of FIG. 1, the reception unit 131 receives information regarding a video from the external device 50. Then, if the reception unit 131 has not received the information regarding the video (step S101; No), the acquisition unit 132 waits until the reception unit 131 receives the information regarding the video.

On the other hand, when the reception unit 131 receives information regarding the video (step S101; Yes), the acquisition unit 132 acquires information regarding the user for the video from the external device 50 (step S102).

Then, the calculation unit 133 calculates an individual index value indicating the appeal of the video based on the information regarding the user acquired by the acquisition unit 132 (step S103). For example, as shown in the example of FIG. 1, the calculation unit 133 calculates the individual index value corresponding to the first scene of the video MO1 to be "0.1". Further, for example, the calculation unit 133 calculates the individual index value corresponding to the second scene of the video MO1 to be "0.3". Further, for example, the calculation unit 133 calculates the individual index value corresponding to the third scene of the video MO1 to be "0.8". Further, for example, the calculation unit 133 calculates the individual index value corresponding to the fourth scene of the video MO1 to be "0.9". Further, for example, the calculation unit 133 calculates the individual index value corresponding to the fifth scene of the video MO1 to be "0.2".

Then, the calculation unit 133 calculates statistical index values of index values for a plurality of users based on the individual index values (step S104). For example, as shown in the example of FIG. 1, the calculation unit 133 calculates the statistical index value corresponding to the first scene of the video MO1 to be "0.1". Further, for example, the calculation unit 133 calculates the statistical index value corresponding to the second scene of the video MO1 to be "0.5". Further, for example, the calculation unit 133 calculates the statistical index value corresponding to the third scene of the video MO1 to be "0.6". Further, for example, the calculation unit 133 calculates the statistical index value corresponding to the fourth scene of the video MO1 to be "0.7". Further, for example, the calculation unit 133 calculates the statistical index value corresponding to the fifth scene of the video MO1 to be "0.7".

Then, the generation unit 134 generates a digest of the video based on the individual index value and the statistical index value calculated by the calculation unit 133 (step S105). For example, in the example of FIG. 1, the generation unit 134 selects a scene of a video when either the threshold value of the individual index value or the statistical index value is greater than or equal to the individual index value or the statistical index value. Further, it is assumed that the predetermined threshold value between the individual index value and the statistical index value is "0.6". In this case, the generation unit 134 generates an individual index value "0.1" corresponding to the first scene of the video MO1 that is smaller than the threshold value, and a statistical index value "0.1" corresponding to the first scene of the video MO1. is smaller than the predetermined threshold, it is determined that the first scene of the video MO1 is not selected. Furthermore, the generation unit 134 determines that the individual index value "0.3" corresponding to the second scene of the video MO1 is smaller than the threshold value, and the statistical index value "0.5" corresponding to the second scene of the video MO1 is smaller than the threshold value. Since it is smaller than the predetermined threshold, it is determined that the second scene of video MO1 is not selected.

In addition, the generation unit 134 determines that the individual index value "0.8" corresponding to the third scene of the video MO1 is equal to or greater than the threshold, and the statistical index value "0.6" corresponding to the third scene of the video MO1 is Since it is greater than or equal to the predetermined threshold, it is determined that the third scene of video MO1 is to be selected. In addition, the generation unit 134 determines that the individual index value "0.9" corresponding to the fourth scene of the video MO1 is equal to or greater than the threshold, and the statistical index value "0.7" corresponding to the fourth scene of the video MO1 is Since it is greater than or equal to the predetermined threshold, it is determined that the fourth scene of video MO1 is to be selected.

In addition, the generation unit 134 determines that the individual index value "0.2" corresponding to the fifth scene of video MO1 is smaller than the threshold value, and the statistical index value "0.7" corresponding to the fifth scene of video MO1 is smaller than the threshold value. Since it is greater than or equal to the predetermined threshold, it is determined that the fifth scene of video MO1 is to be selected. In this way, the generation unit 134 selects the scenes of the video MO1 that are equal to or higher than the predetermined threshold, so that the generation unit 134 selects the third scene of the video MO1, the fourth scene of the video MO1, and the fourth scene of the video MO1 as characteristic contents. A video digest EM1 including the fifth scene is generated.

The providing unit 135 then provides the digest of the video to the user (step S106). For example, in the example of FIG. 1, the providing unit 135 provides the digest EM1 of the video to the user who has acquired information about the user.

[4. Modified example]
The calculation device 100 described above may be implemented in various different forms other than the above embodiment. Therefore, other embodiments of the calculation device 100 will be described below.

[4-1. content〕
In the above embodiment, an example was given in which the calculation device 100 executes calculation processing targeting a video, but the target content may be any content. For example, the content targeted by the calculation device 100 may be a still image, an article, advertising content, or the like.

[4-2. Featured content]
In the above embodiment, an example was given in which the calculation device 100 executes a generation process to generate a digest of a moving image as a feature content, but the target feature content may be any content. For example, the characteristic content generated by the calculation device 100 may be a still image such as a thumbnail, a summary of an article, advertising content, or the like.

For example, in the example of FIG. 6, the generation unit 134 of the calculation device 100 determines that the user's individual index values for some articles AR1 and AR2 among the content C1 including articles are larger than a predetermined threshold and are lower than the statistical index value. is also large, a summary of the article is generated as feature content based on part AR1 and A2 of the article.

[4-3. Individual index value]
In the above embodiment, an example was given in which the calculation device 100 executes a calculation process to calculate an individual index value indicating the appeal of a video based on information about the user, but any information can be used as the information about the user. good. For example, the acquisition unit 132 of the calculation device 100 acquires, as information regarding the user, attribute information that is information regarding attributes of the user, location information of the user, browsing history, and the like. Then, the calculation unit 133 of the calculation device 100 may calculate the individual index value after taking attribute information, which is information related to the user's attributes, the user's location information, browsing history, etc., into consideration as weights.

[4-4. Statistics〕
In the above embodiment, an example was given in which the calculation device 100 executes calculation processing to calculate an individual index value and a statistical index value based on information about the user, but any value may be calculated as the statistical value. . For example, the calculation unit 133 of the calculation device 100 may calculate the standard deviation of individual index values for all users as a statistical value based on information regarding the users. Further, for example, it is assumed that the information regarding the user includes attribute information that is information regarding the attributes of the user. In this case, the calculation unit 133 of the calculation device 100 may calculate a weighted average using attribute information as a weight as a statistical value based on information regarding the user.

[4-5. Generation process (1) Thresholds for individual index values and statistical index values (1)]
In the embodiment described above, the calculation device 100 executes a generation process in which it is determined that a video scene is selected when either the threshold value of the individual index value or the statistical index value is greater than or equal to the individual index value or the statistical index value. However, the threshold value is not limited to the case where the individual index value and the statistical index value are the same. For example, the generation unit 134 of the calculation device 100 may have a predetermined threshold value of "0.6" for the individual index value and a predetermined threshold value of "0.7" for the statistical index value.

[4-6. Generation processing (2) Thresholds for individual index values and statistical index values (2)]
In the embodiment described above, the calculation device 100 executes a generation process in which it is determined that a video scene is selected when either the threshold value of the individual index value or the statistical index value is greater than or equal to the individual index value or the statistical index value. However, the threshold value between the individual index value and the statistical index value may be greater than or equal to the individual index value and the statistical index value. For example, assume that the generation unit 134 of the calculation device 100 selects a scene of a video when the threshold value of the individual index value and the statistical index value is greater than or equal to the individual index value and the statistical index value. Further, it is assumed that the predetermined threshold value between the individual index value and the statistical index value is "0.6". In this case, the generation unit 134 generates an individual index value "0.1" corresponding to the first scene of the video MO1 that is smaller than the threshold value, and a statistical index value "0.1" corresponding to the first scene of the video MO1. is smaller than the predetermined threshold, it is determined that the first scene of the video MO1 is not selected. Furthermore, the generation unit 134 determines that the individual index value "0.3" corresponding to the second scene of the video MO1 is smaller than the threshold value, and the statistical index value "0.5" corresponding to the second scene of the video MO1 is smaller than the threshold value. Since it is smaller than the predetermined threshold, it is determined that the second scene of video MO1 is not selected.

In addition, the generation unit 134 determines that the individual index value "0.8" corresponding to the third scene of the video MO1 is equal to or greater than the threshold, and the statistical index value "0.6" corresponding to the third scene of the video MO1 is Since it is greater than or equal to the predetermined threshold, it is determined that the third scene of video MO1 is to be selected. In addition, the generation unit 134 determines that the individual index value "0.9" corresponding to the fourth scene of the video MO1 is equal to or greater than the threshold, and the statistical index value "0.7" corresponding to the fourth scene of the video MO1 is Since it is greater than or equal to the predetermined threshold, it is determined that the fourth scene of video MO1 is to be selected.

In addition, the generation unit 134 determines that the individual index value "0.2" corresponding to the fifth scene of video MO1 is smaller than the threshold value, and the statistical index value "0.7" corresponding to the fifth scene of video MO1 is smaller than the threshold value. Since it is greater than or equal to the predetermined threshold, it is determined that the fifth scene of video MO1 is not selected. In this way, the generation unit 134 selects the scene of the video MO1 that is equal to or higher than the predetermined threshold, thereby generating a video that includes the third scene of the video MO1 and the fourth scene of the video MO1 as the characteristic content. A digest EM1 may also be generated.

Thereby, the generation unit 134 of the calculation device 100 according to the embodiment can generate characteristic content suitable for the user with higher precision, and thus can enhance the appeal effect of the characteristic content.

[4-7. Providing process (1) Providing ranking (1)]
In the embodiment described above, an example of the providing process in which the providing unit 135 of the calculation device 100 provides a digest of a video to the user has been described, but the present invention is not limited to this process. Specifically, the providing unit 135 may provide the user with a ranking of the characteristic content generated by the generating unit 134, which is determined based on the magnitude relationship between the individual index value and the statistical index value. good.

For example, in the example of FIG. 7, the generation unit 134 selects an article when either the threshold value of the individual index value or the statistical index value is greater than or equal to the individual index value or the statistical index value. Further, it is assumed that the predetermined threshold value between the individual index value and the statistical index value is "0.6". In this case, the generation unit 134 determines that the individual index value "0.1" corresponding to the first article is smaller than the threshold value, and the statistical index value "0.1" corresponding to the first article is smaller than the predetermined threshold value. Since it is small, it is determined that the first article is not selected. In addition, the generation unit 134 determines that the individual index value “0.3” corresponding to the second article is smaller than the threshold value, and the statistical index value “0.5” corresponding to the second article is smaller than the predetermined threshold value. Therefore, it is determined that the second article is not selected.

In addition, the generation unit 134 determines that the individual index value "0.8" corresponding to the third article is equal to or higher than the threshold value, and the statistical index value "0.7" corresponding to the third article is equal to or higher than the predetermined threshold value. Therefore, it is determined that the third article is selected. In addition, the generation unit 134 determines that the individual index value "0.9" corresponding to the fourth article is equal to or higher than the threshold value, and the statistical index value "0.8" corresponding to the fourth article is equal to or higher than the predetermined threshold value. Therefore, it is determined that the fourth article is selected.

In addition, the generation unit 134 determines that the individual index value "0.2" corresponding to the fifth article is smaller than the threshold value, and the statistical index value "0.6" corresponding to the fifth article is greater than or equal to the predetermined threshold value. Therefore, it is determined that the fifth article is selected. In this way, the generation unit 134 selects the third article, the fourth article, and the fifth article as characteristic contents, which are articles that are equal to or higher than the predetermined threshold.

The providing unit 135 then provides the articles generated by the generating unit 134 to the user in a ranking format. For example, in the example shown in FIG. 7, the providing unit 135 determines that the individual index value of the fourth article is larger than the individual index value of the third article and the individual index value of the fifth article, and that the statistical index of the fourth article Since the value is larger than the statistical index value of the third article and the statistical index value of the fifth article, the fourth article is determined to be ranked first. Then, since the individual index value of the third article is larger than the individual index value of the fifth article, and the statistical index value of the third article is larger than the statistical index value of the fifth article, the providing unit 135 The third article is determined to be in second place. Then, the providing unit 135 determines that the fifth article ranks third. In this way, the providing unit 135 provides the user with the content C2 in which rankings such as the fourth article is ranked first, the third article is ranked second, and the fifth article is ranked third. Note that, when ranking articles, the providing unit 135 may rank articles with a large individual index value or a statistical index value high.

Thereby, the providing unit 135 of the calculation device 100 according to the embodiment can provide the user with characteristic content suitable for the user in a ranking format, thereby increasing the appeal effect of the characteristic content.

[4-8. Provision processing (2) Providing ranking (2)]
In the embodiment described above, an example of the providing process in which the providing unit 135 of the calculation device 100 provides a digest of a video to the user has been described, but the present invention is not limited to this process. Specifically, the providing unit 135 provides a ranking of the feature content generated by the generating unit 134, which includes the magnitude relationship between the individual index value and the statistical index value, and the difference between the individual index value and the statistical index value. Rankings determined based on size relationships may be provided to the user.

For example, in the example of FIG. 8, the generation unit 134 selects an article when either the threshold value of the individual index value or the statistical index value is greater than or equal to the individual index value or the statistical index value. Further, it is assumed that the predetermined threshold value between the individual index value and the statistical index value is "0.6". In this case, the generation unit 134 determines that the individual index value "0.1" corresponding to the first article is smaller than the threshold value, and the statistical index value "0.5" corresponding to the first article is smaller than the predetermined threshold value. Since it is small, it is determined that the first article is not selected. In addition, the generation unit 134 generates information such that the individual index value “0.2” corresponding to the second article is smaller than the threshold value, and the statistical index value “0.4” corresponding to the second article is smaller than the predetermined threshold value. Therefore, it is determined that the second article is not selected.

In addition, the generation unit 134 determines that the individual index value "0.8" corresponding to the third article is equal to or greater than the threshold value, and the statistical index value "0.2" corresponding to the third article is smaller than the predetermined threshold value. Therefore, it is determined that the third article is selected. In addition, the generation unit 134 determines that the individual index value "0.5" corresponding to the fourth article is smaller than the threshold value, and the statistical index value "0.7" corresponding to the fourth article is greater than or equal to the predetermined threshold value. Therefore, it is determined that the fourth article is selected.

In addition, the generation unit 134 determines that the individual index value "0.9" corresponding to the fifth article is equal to or higher than the threshold value, and the statistical index value "1.0" corresponding to the fifth article is equal to or higher than the predetermined threshold value. Therefore, it is determined that the fifth article is selected. In this way, the generation unit 134 selects the third article, the fourth article, and the fifth article as characteristic contents, which are articles that are equal to or higher than the predetermined threshold.

Furthermore, for example, in the example of FIG. 8, it is assumed that the predetermined threshold value for the difference between the individual index value and the statistical index value is "0.5", but the ranking rank is moved up by one. In this case, the generation unit 134 determines that the difference "-0.4" corresponding to the first article is smaller than the threshold value. Furthermore, the generation unit 134 determines that the difference "-0.2" corresponding to the second article is smaller than the threshold value. Furthermore, the generation unit 134 determines that the difference “0.6” corresponding to the third article is greater than or equal to a predetermined threshold. Furthermore, the generation unit 134 determines that the difference “−0.4” corresponding to the fourth article is smaller than the threshold value. Furthermore, the generation unit 134 determines that the difference “−0.1” corresponding to the fifth article is smaller than the threshold value. Based on these, the generation unit 134 determines to move up the ranking rank of the third article whose ranking is equal to or higher than the predetermined threshold value by one.

The providing unit 135 then provides the articles generated by the generating unit 134 to the user in a ranking format. For example, in the example of FIG. 8, when the providing unit 135 ranks articles, it is assumed that articles having a large individual index value or a statistical index value are ranked highly. In this case, the providing unit 135 provides the information that the statistical index value of the fifth article is larger than the individual index value of the fifth article, larger than the individual index value of the third article, and the statistical index value of the third article is larger than the individual index value of the third article. , is larger than the individual index value of the fourth article, and is larger than the statistical index value of the fourth article, so the fifth article is determined to be in first place. Then, the providing unit 135 determines that the individual index value of the third article is greater than the statistical index value of the third article, greater than the individual index value of the fourth article, and greater than the statistical index value of the fourth article. Since this is also large, the third article is determined to be in second place. Then, the providing unit 135 determines that the fourth article ranks third.

Then, the providing unit 135 advances the ranking rank of the third article that is equal to or higher than the predetermined threshold value by one based on the magnitude of the difference obtained by subtracting the statistical index value from the individual index value. In this way, the providing unit 135 provides the user with the content C3 in which rankings such as the third article is ranked first, the fifth article is ranked second, and the fourth article is ranked third.

Thereby, the providing unit 135 of the calculation device 100 according to the embodiment can provide the user with characteristic content suitable for the user in a ranking format, thereby increasing the appeal effect of the characteristic content. This point will be explained. To explain using the example of FIG. 8, an article in which the difference obtained by subtracting the statistical index value from the individual index value is greater than or equal to a predetermined threshold value, such as the third article, may have a high appeal to users. On the other hand, an article with a large individual index value and a large statistical index value, such as the fifth article, may have a high appeal effect to any user. For these reasons, by ranking the third article first, it is possible to make it easier for the user to view the third article. Thereby, the providing unit 135 of the calculation device 100 can increase the appeal effect of the characteristic content to a specific user.

[5. Hardware configuration]
Further, the terminal device 10, external device 50, and calculation device 100 according to the embodiments described above are realized by, for example, a computer 1000 having a configuration as shown in FIG. The calculation device 100 will be described below as an example. FIG. 9 is a hardware configuration diagram showing an example of a computer 1000 that implements the functions of the calculation device 100. The computer 1000 includes a CPU 1100, a RAM 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface (I/F) 1500, an input/output interface (I/F) 1600, and a media interface (I/F). ) has 1700.

CPU 1100 operates based on a program stored in ROM 1300 or HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started, programs depending on the hardware of the computer 1000, and the like.

The HDD 1400 stores programs executed by the CPU 1100, data used by the programs, and the like. Communication interface 1500 receives data from other devices via network N and sends it to CPU 1100, and sends data generated by CPU 1100 to other devices via network N.

The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and mouse via an input/output interface 1600. CPU 1100 obtains data from an input device via input/output interface 1600. Further, CPU 1100 outputs the generated data to an output device via input/output interface 1600.

Media interface 1700 reads programs or data stored in recording medium 1800 and provides them to CPU 1100 via RAM 1200. CPU 1100 loads this program from recording medium 1800 onto RAM 1200 via media interface 1700, and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory. etc.

For example, when the computer 1000 functions as the calculation device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded onto the RAM 1200. Furthermore, data in the storage unit 120 is stored in the HDD 1400. The CPU 1100 of the computer 1000 reads these programs from the recording medium 1800 and executes them, but as another example, these programs may be acquired from another device via the network N.

[6. others〕
Furthermore, among the processes described in the above embodiments and modified examples, all or part of the processes described as being performed automatically can be performed manually, or may be described as being performed manually. All or part of this processing can also be performed automatically using known methods. In addition, information including the processing procedures, specific names, and various data and parameters shown in the above documents and drawings may be changed arbitrarily, unless otherwise specified. For example, the various information shown in each figure is not limited to the illustrated information.

Furthermore, each component of each device shown in the drawings is functionally conceptual, and does not necessarily need to be physically configured as shown in the drawings. In other words, the specific form of distributing and integrating each device is not limited to what is shown in the diagram, and all or part of the devices can be functionally or physically distributed or integrated in arbitrary units depending on various loads and usage conditions. Can be integrated and configured.

Furthermore, the above-described embodiments and modifications can be combined as appropriate within a range that does not conflict with the processing contents.

Further, the above-mentioned "section, module, unit" can be read as "means", "circuit", etc. For example, the calculation unit can be read as a calculation means or a calculation circuit.

[7. effect〕
As described above, the calculation device 100 according to the embodiment includes the acquisition section 132 and the calculation section 133. The acquisition unit 132 acquires information regarding the user. The calculation unit 133 calculates an index value indicating the appeal of the content based on the information regarding the user acquired by the acquisition unit 132, an index value for each user, and a plurality of users whose index values are to be compared with the index value. Calculate the statistical value for.

Thereby, the calculation device 100 according to the embodiment can calculate an index value related to a positive or negative impression of a scene of a video, and an index value related to a user's interests, based on information related to the user. Therefore, it is possible to calculate an index value that makes it possible to evaluate the appeal of the content.

The calculation device 100 according to the embodiment further includes a generation unit 134 that generates characteristic content indicating the characteristics of the content based on the index value calculated by the calculation unit 133 and the average value of the statistical values. .

Thereby, the calculation device 100 according to the embodiment calculates the characteristic content based on the index value regarding the positive or negative impression of the scene of the video and the index value regarding the user's interests based on the information regarding the user. Since the content can be generated, the appeal effect of the content can be enhanced.

Furthermore, in the calculation device 100 according to the embodiment, based on the index value and the average value calculated by the calculation unit 133, when the index value is larger than the average value, the generation unit 134 generates a feature corresponding to the index value. Generate content.

Thereby, the calculation device 100 according to the embodiment calculates the characteristic content based on the index value regarding the positive or negative impression of the scene of the video and the index value regarding the user's interests based on the information regarding the user. Since the content can be generated, the appeal effect of the content can be enhanced.

Furthermore, in the calculation device 100 according to the embodiment, based on the index value and the average value calculated by the calculation unit 133, when the average value is larger than the index value, the generation unit 134 generates a feature corresponding to the average value. Generate content.

Thereby, the calculation device 100 according to the embodiment calculates the characteristic content based on the index value regarding the positive or negative impression of the scene of the video and the index value regarding the user's interests based on the information regarding the user. Since the content can be generated, the appeal effect of the content can be enhanced.

In addition, in the calculation device 100 according to the embodiment, the generation unit 134 edits the content, which is a video including the characteristics of the content, as the characteristic content, based on the index value and the average value calculated by the calculation unit 133. generate a video.

As a result, the calculation device 100 according to the embodiment can generate various types of characteristic content, thereby increasing the appeal effect of the content.

In addition, in the calculation device 100 according to the embodiment, the generation unit 134 generates the following information based on the scene corresponding to the magnitude relationship between the predetermined index value for each time variation of the video calculated by the calculation unit 133 and the predetermined average value. Generate an edited video.

As a result, the calculation device 100 according to the embodiment can generate various types of characteristic content, thereby increasing the appeal effect of the content.

Furthermore, in the calculation device 100 according to the embodiment, the generation unit 134 generates a still image including the characteristics of the content as the characteristic content based on the index value and the average value calculated by the calculation unit 133.

As a result, the calculation device 100 according to the embodiment can generate various types of characteristic content, thereby increasing the appeal effect of the content.

In addition, in the calculation device 100 according to the embodiment, the generation unit 134 summarizes the content, which is an article including the characteristics of the content, as the characteristic content based on the index value and the average value calculated by the calculation unit 133. Generate articles based on

As a result, the calculation device 100 according to the embodiment can generate various types of characteristic content, thereby increasing the appeal effect of the content.

Furthermore, the calculation device 100 according to the embodiment further includes a providing unit 135 that provides the characteristic content generated by the generating unit 134 to the user.

Thereby, the calculation device 100 according to the embodiment can generate characteristic content based on the index value and average value that take into account the user's interests and emotions, so that the content appeals to the user. can provide highly distinctive content.

In addition, in the calculation device 100 according to the embodiment, the providing unit 135 provides the user with the ranking of the characteristic content generated by the generating unit 134, which is determined based on the magnitude relationship between the index value and the average value. provide.

Thereby, the calculation device 100 according to the embodiment can provide a ranking determined based on the magnitude relationship between the index value and the average value, which takes into account the user's interests and emotions, and therefore the calculation device 100 of the content It is possible to enhance the appeal effect.

Furthermore, in the calculation device 100 according to the embodiment, the calculation unit 133 calculates, as an index value, an index value indicating the user's degree of interest in the content, based on the information regarding the user acquired by the acquisition unit 132.

Thereby, the calculation device 100 according to the embodiment can calculate an index value related to the user's interest in a scene of a video based on the information regarding the user, so that the calculation device 100 according to the embodiment can calculate an index value that makes it possible to evaluate the appeal of the content. It can be calculated.

Further, in the calculation device 100 according to the embodiment, the calculation unit 133 calculates, as an index value, an index value indicating the degree of the user's emotion regarding the content, based on the information regarding the user acquired by the acquisition unit 132.

As a result, the calculation device 100 according to the embodiment can calculate an index value related to a positive impression or a negative impression of a video scene based on the information about the user, and therefore can evaluate the appeal of the content. It is possible to calculate the index value.

In addition, in the calculation device 100 according to the embodiment, the calculation unit 133 uses, as an index value, an index indicating the degree of emotion of the user who has a positive impression regarding the content, based on the information regarding the user acquired by the acquisition unit 132. Calculate the value.

As a result, the calculation device 100 according to the embodiment can calculate an index value related to a positive impression of a scene of a video based on information about the user, so that the calculation device 100 according to the embodiment can calculate an index value that makes it possible to evaluate the appeal of the content. It can be calculated.

In addition, in the calculation device 100 according to the embodiment, the calculation unit 133 uses, as an index value, an index indicating the degree of emotion of the user who has a negative impression regarding the content, based on the information regarding the user acquired by the acquisition unit 132. Calculate the value.

Thereby, the calculation device 100 according to the embodiment can calculate an index value related to a negative impression of a scene of a video based on information about the user, and therefore can calculate an index value that enables evaluation regarding the appeal of the content. It can be calculated.

Some of the embodiments of the present application have been described above in detail based on the drawings, but these are merely examples, and various modifications and variations may be made based on the knowledge of those skilled in the art, including the embodiments described in the disclosure section of the invention. It is possible to carry out the invention in other forms with modifications.

1 calculation system 10 terminal device 50 external device 100 calculation device 110 communication unit 120 storage unit 121 video information storage unit 122 index value information storage unit 130 control unit 131 reception unit 132 acquisition unit 133 calculation unit 134 generation unit 135 provision unit

Claims (15)

Contains at least one of the following: information regarding the user's interests or impressions based on the user's response to or comment on the predetermined content, the user's attribute information, the user's location information, and the user's viewing history of the content. an acquisition unit that acquires information about the user;
Using a learning model that outputs an index value indicating the appeal of content to the user by inputting information about the user acquired by the acquisition unit, the index value for each user and the target for comparison with the index value are calculated. a calculation unit that calculates statistical values for a plurality of users of the index value;
Equipped with
The calculation unit is
The index value is calculated using a learning model that outputs an index value indicating the appeal of the content to the user by inputting the impression of the user based on the response or comment content of the user to the predetermined content acquired by the acquisition unit. calculating an index value indicating the degree of the user's feelings regarding the content;
A calculation device characterized by: Further comprising a generation unit that generates characteristic content indicating characteristics of the content based on the index value calculated by the calculation unit and an average value of the statistical values.
The calculation device according to claim 1, characterized in that: The generation unit is
Based on the index value and the average value calculated by the calculation unit, when the index value is larger than the average value, generating the feature content corresponding to the index value;
The calculation device according to claim 2, characterized in that: The generation unit is
Based on the index value and the average value calculated by the calculation unit, when the average value is larger than the index value, generating the feature content corresponding to the average value;
The calculation device according to claim 2 or 3, characterized in that: The generation unit is
generating, as the feature content, a video that includes the characteristics of the content and that is an edited version of the content, based on the index value and average value calculated by the calculation unit;
The calculation device according to any one of claims 2 to 4, characterized in that: The generation unit is
generating an edited video based on a scene corresponding to a magnitude relationship between the index value for each time variation of the video calculated by the calculation unit and a predetermined average value;
The calculation device according to claim 5, characterized in that: The generation unit is
generating a still image including features of the content as the feature content based on the index value and average value calculated by the calculation unit;
The calculation device according to any one of claims 2 to 6, characterized in that: The generation unit is
Generating, as the feature content, an article that includes features of the content and that summarizes the content, based on the index value and average value calculated by the calculation unit;
The calculation device according to any one of claims 2 to 7, characterized in that: further comprising a providing unit that provides the characteristic content generated by the generating unit to the user;
The calculation device according to any one of claims 2 to 8, characterized in that: The provision department is
providing the user with a ranking of characteristic content generated by the generation unit, the ranking determined based on a magnitude relationship between the index value and the average value;
The calculation device according to claim 9, characterized in that: The calculation unit further includes:
The index value is calculated by using a learning model that outputs an index value indicating the appeal of the content to the user by inputting information regarding interests based on the response or comment content of the user to the predetermined content acquired by the acquisition unit. calculating an index value indicating the degree of interest of the user regarding the content;
The calculation device according to any one of claims 1 to 10, characterized in that : The calculation unit is
using the learning model to calculate, as the index value, an index value indicating the degree of emotion of the user who has a positive impression regarding the content;
The calculation device according to claim 1, characterized in that: The calculation unit is
using the learning model to calculate, as the index value, an index value indicating a degree of emotion of the user who has a negative impression regarding the content;
The calculation device according to claim 1, characterized in that: A calculation method performed by a computer,
Contains at least one of the following: information regarding the user's interests or impressions based on the user's response to or comment on the predetermined content, the user's attribute information, the user's location information, and the user's viewing history of the content. an acquisition step of acquiring information about the user;
Using a learning model that outputs an index value indicating the appeal of the content to the user by inputting the information about the user acquired in the acquisition step, the index value for each user and the target for comparison with the index value are calculated. a calculation step of calculating statistical values for a plurality of users of the index value;
including;
The calculation step is
The index value is calculated by using a learning model that outputs an index value indicating the appeal of the content to the user by inputting the user's impression based on the user's response or comment content to the predetermined content acquired in the acquisition step. calculating an index value indicating the degree of the user's feelings regarding the content;
A calculation method characterized by including. Contains at least one of the following: information regarding the user's interests or impressions based on the user's response to or comment on the predetermined content, the user's attribute information, the user's location information, and the user's viewing history of the content. an acquisition procedure for acquiring information about the user;
Using a learning model that outputs an index value indicating the appeal of the content to the user by inputting the information about the user acquired by the acquisition procedure, the index value for each user and the target for comparison with the index value are calculated. a calculation procedure for calculating statistical values for a plurality of users of an index value;
make the computer run
The calculation procedure is
The index value is calculated by using a learning model that outputs an index value indicating the appeal of the content to the user by inputting the user's impression based on the response or comment content of the user to the predetermined content acquired by the acquisition procedure. calculating an index value indicating the degree of the user's feelings regarding the content;
A calculation program characterized by:

Images