JP2021163292A - Method for presenting story development to user, story development presenting device, computer program thereof, story development analysis method, story development analyzer, and computer program thereof - Google Patents

Abstract

To allow a user to grasp story development, without depending on presentation of a story itself.SOLUTION: A disclosed method is a method for presenting to a user, development of a story in which plural objects make their appearance, in which a processor 110 reads time series data 201M from a database 200 storing time series data 201M which indicates time variant change of an appearance degree of each object out of the plural objects, and the processor 110 creates a graphical image 512 which indicates time variant change of the appearance degree of one or more objects included in the plural objects, on the basis of the time series data 201M read, and then the processor 110 sets the graphical image 512 to the user, as the development of the story.SELECTED DRAWING: Figure 4

Description

The present disclosure relates to a method of presenting story development to a user, a story development presentation device, its computer program, a method of analyzing story development, a story development analysis device, and its computer program.

Patent Document 1 meets the conditions from a plurality of scenes in which a plurality of media are spatially and temporally combined by using temporal changes in appearance time-related information of various media such as characters, images, figures, and sounds. It discloses to search the scene.

Japanese Unexamined Patent Publication No. 8-137900

It may be desirable to understand and analyze the story development of content such as manga, novels, and movies. In order to grasp the story development, an explanation that describes the outline of the story itself in sentences, that is, a "synopsis" may be used.

However, the explanation that describes the outline of the story itself in sentences may lack an objective grasp of the story development. Moreover, the easy presentation of sentences explaining the story may lead to so-called spoilers to unreaders or unviewed viewers.

Therefore, it is desirable to be able to grasp or analyze the story development without relying on the sentences that explain the story itself.

The present inventors have come up with the idea that the temporal change in the appearance of objects (characters, etc.) appearing in the story is a basic factor for story development. Therefore, by using the temporal change of the appearance degree of the object, it is possible to grasp or analyze the story development without relying on the sentence explaining the story itself. The present disclosure is based on such an idea.

One aspect of the disclosure is how to present the storyline to the user. The disclosure method is a method of presenting the development of a story in which a plurality of objects appear to the user, from a database in which a processor stores time-series data indicating a temporal change in the appearance degree of each of the plurality of objects. , The processor reads the time-series data, and based on the read time-series data, generates a graphical image showing the temporal change of the appearance degree of one or more objects included in the plurality of objects. The processor comprises presenting the graphical image to the user as said development of the story.

Another aspect of the disclosure is a story development presentation device. The disclosed device is a database in which time-series data indicating the temporal change of the appearance degree of each of the plurality of objects appearing in the story is stored, and the plurality of objects based on the time-series data read from the database. It comprises a processor configured to generate a graphical image showing the temporal change of the appearance of one or more objects included, and to execute the process of presenting the graphical image to the user as the development of the story. ..

Another aspect of the disclosure is a computer program. The disclosed computer program is included in the plurality of objects based on the time-series data read from the database in which the time-series data indicating the temporal change of the appearance degree of each of the plurality of objects appearing in the story is stored. A computer is made to generate a graphical image showing the temporal change of the appearance degree of one or more objects, and present the graphical image to the user as the development of the story.

Another aspect of the disclosure is how to analyze the evolution of a story in which multiple objects appear. In the method of disclosure, the processor reads the time-series data from a database in which the time-series data, which is non-negative matrix data and shows the temporal change of the appearance degree of each of the plurality of objects, is stored, and the processor reads the time-series data. In order to analyze the story, it is provided to apply a non-negative matrix factorization algorithm to the time series data.

Another aspect of the disclosure is a story development analysis device. The disclosed device shows the temporal change of the appearance degree of each of the plurality of objects appearing in the story, and for the database in which the time-series data which is the non-negative matrix data is stored and the time-series data read from the database. It comprises a processor configured to perform processing that applies a non-negative matrix factorization algorithm.

Another aspect of the disclosure is a computer program. The disclosed computer program shows the temporal change of the appearance degree of each of the plurality of objects appearing in the story, and is non-negative with respect to the time-series data read from the database in which the time-series data which is the non-negative matrix data is stored. Have the computer perform the process of applying the value matrix factor decomposition algorithm.

Further details will be described as embodiments described below.

FIG. 1 is a schematic configuration diagram of a system including a story development presentation device according to the first embodiment. FIG. 2 is a data structure diagram of time-series data showing changes in the appearance of each of the plurality of objects over time. FIG. 3 is a flowchart of the story development presentation process. FIG. 4 is a schematic view showing an example of a screen displayed on the user terminal. FIG. 5 is a schematic view showing another example of the screen displayed on the user terminal. FIG. 6 is a schematic view showing still another example of the screen displayed on the user terminal. FIG. 7 is a data structure diagram of time series data according to the second embodiment. FIG. 8 is a data structure diagram of the first non-negative matrix data (base matrix). FIG. 9 is a data structure diagram of the second non-negative matrix data (activation matrix). FIG. 10 is a schematic configuration diagram of a system including the story development analysis device according to the third embodiment. FIG. 11 is a flowchart of the story development analysis process according to the third embodiment. FIG. 12 is a schematic view showing an example of a screen displayed on the user terminal. FIG. 13 is a schematic view showing an example of a screen displayed on the user terminal.

<1. How to present story development to users, story development presentation device, computer program for story development presentation, method to analyze story development, story development analysis device, computer program overview for story development analysis>

(1) The method according to the embodiment is a method of presenting to the user the development of a story in which a plurality of objects appear. The method comprises reading the time-series data from a database in which the processor stores the time-series data indicating the temporal changes in the appearance of each of the plurality of objects. Time-series data showing the temporal changes in the appearance of each of the plurality of objects indicates story development. In the method, the processor generates a graphical image showing the temporal change of the appearance degree of one or more objects included in the plurality of objects based on the time-series data read by the processor. A graphical image is provided to the user as the development of the story. By presenting the appearance degree of the object to the user by a graphical image, the user can easily grasp the story development.

(2) It is preferable that the graphical image is presented to the user without accompanying a sentence explaining the story. Spoilers can be prevented while showing the story development by showing the temporal change of the appearance degree of the object without attaching a sentence explaining the story.

(3) It is preferable that the method according to the embodiment further comprises selecting the one or more objects from the plurality of objects by the processor. In this case, even if the number of objects included in the time series data is huge, only the temporal change of the appearance degree of the selected objects is presented as a graphical image. Therefore, even if the number of objects is huge, it is possible to prevent the visibility from being lowered.

(4) The one or more objects may be selected based on the data input from the user. In this case, the user can arbitrarily select the object.

(5) The one or more objects may be selected based on the result of analyzing the time series data. In this case, the object is selected according to the contents of the time series data.

(6) The one or more objects may be selected based on the appearance degree indicated by the time series data. In this case, the objects are selected according to the appearance degree indicated by the time series data.

(7) The time series data may be non-negative matrix data. The one or more objects are preferably selected based on at least one of the two non-negative matrices obtained from the time series data by the non-negative matrix factorization algorithm. In this case, the object is selected based on the analysis result by the non-negative matrix factorization algorithm.

(8) It is preferable that the method according to the embodiment further comprises selecting a time range of a part of the entire time range of the time series data by the processor. The graphical image may be generated based on the partial time series data in the partial time range of the time series data. In this case, even if the story is long, the user is shown a graphical image of the partial time series data in a selected part of the time range, so that the deterioration of visibility can be prevented.

(9) The part of the time range may be selected based on the data input from the user. In this case, the user can arbitrarily select a part of the time range.

(10) The part of the time range may be selected based on the result of analyzing the time series data. In this case, a part of the time range is selected according to the contents of the time series data.

(11) The time series data may be non-negative matrix data. The partial time range is preferably selected based on at least one of the two non-negative matrices obtained from the time series data by the non-negative matrix factorization algorithm. In this case, some time ranges are selected based on the results of analysis by the non-negative matrix factorization algorithm.

(12) In the method according to the embodiment, the processor selects the one or more objects from the plurality of objects, and the processor selects one of the entire time ranges of the time series data. It can be further provided to select the time range of the unit. The graphical image is preferably generated to show the temporal variation of the appearance of the one or more objects in the part of the time range.

(13) The story development presenting device according to the embodiment has a database in which time-series data indicating the temporal change of the appearance degree of each of a plurality of objects appearing in the story is stored, and the time-series data read from the database. Based on this, a graphical image showing the temporal change of the appearance degree of one or more objects included in the plurality of objects is generated, and the process of presenting the graphical image to the user as the development of the story is executed. It includes a configured processor.

(14) The computer program according to the embodiment is based on the time-series data read from the database in which the time-series data indicating the temporal change of the appearance degree of each of the plurality of objects appearing in the story is stored. A computer is made to generate a graphical image showing a time change of the appearance degree of one or more objects included in the object, and present the graphical image to the user as the development of the story.

(15) The method according to the embodiment is a method of analyzing the development of a story in which a plurality of objects appear. In the method, the processor reads the time-series data from a database in which the time-series data, which is non-negative matrix data and shows the temporal change of the appearance degree of each of the plurality of objects, is stored, and the processor reads the time-series data. In order to analyze the story, it is provided to apply a non-negative matrix factorization algorithm to the time series data. In this case, as an analysis method for story development, a new method, that is, an analysis method using a non-negative matrix factorization algorithm can be obtained. As will be described later, the present inventors have found that an analysis method using a non-negative matrix factorization algorithm is useful for analyzing story development.

(16) The story development analysis device according to the embodiment shows a temporal change in the appearance degree of each of a plurality of objects appearing in the story, and from a database in which time-series data which is non-negative matrix data is stored and the database. It includes a processor configured to execute a process of applying a non-negative matrix factorization algorithm to the read time-series data.

(17) The computer program according to the embodiment shows the temporal change of the appearance degree of each of the plurality of objects appearing in the story, and the time-series data read from the database in which the time-series data which is the non-negative matrix data is stored. On the other hand, the computer is made to execute the process of applying the non-negative matrix factor decomposition algorithm.

<2. Example of how to present story development to users, story development presentation device, computer program for story development presentation, method to analyze story development, story development analysis device, computer program for story development analysis>

<2.1 First Embodiment>

FIG. 1 shows the system 10 according to the first embodiment. The system 10 according to the first embodiment includes a story development presentation device 100. The story development presentation device 100 presents data indicating the story development of the content to the user via the network 400. The content is, for example, comics, novels, movies, television programs, and the like. The content is not limited to comics and the like, and any content with a story is sufficient. Another example of story-like content is conversation data in a chat app. The flow of conversation in the chat application has a story, similar to the conversation in a cartoon or a novel.

In the first embodiment, the user is, for example, a reader of a cartoon or a novel, or a viewer of a movie or a television program. The user can access the story development presentation device 100 by using the user terminal 300. The user terminal 300 is, for example, a smartphone, tablet, desktop computer, or laptop computer. The user terminal 300 includes a processor 310, a storage device 320, and an input / output device 330.

The system 10 includes a user terminal 300 connected to the story development presentation device 100 via the network 400. The network 400 is, for example, the Internet. The story development presentation device 100 is, for example, a server installed on the Internet.

The story development presentation device 100 is composed of a computer including a processor 110 and a storage device 120. The processor 110 is, for example, a CPU. The storage device 120 includes, for example, a primary storage device and a secondary storage device. The primary storage device is, for example, a RAM. The secondary storage device is, for example, a hard disk drive (HDD) or a solid state drive (SDD).

The storage device 120 stores a computer program 121 for operating the computer as the story development presentation device 100. The computer program 121 includes a program code for causing the processor 110 to execute the story development presentation process 111. The story development presentation process 111 is a process including presenting data indicating the story development of the content to the user via the network 400. The story development presentation process 111 will be described later.

The story development presentation device 100 includes a database 200. The database 200 may be stored in the storage device 120, or may be stored in another computer (for example, a database server on the Internet) connected to the computer equipped with the processor 110 and the storage device 120.

The database 200 includes a plurality of content data 201, 202, 203. If the content is a cartoon, the content data includes the image data of the cartoon and the work information such as the work name. If the content is a novel, the content data includes the text data of the novel and the work information such as the work name. If the content is a movie or a television program, the content data includes video / audio data and work information such as a work name. In embodiments, the content may be digital content or content in paper or other media.

In FIG. 1, the first content data 201 of the first content (work name: xxx), the second content data 202 of the second content (work name: yyy), and the third content (work name: zzz) are the first. 3 Content data 203 and.

The content data 201, 202, 203 according to the embodiment further includes time series data 201M, 202M, 203M, respectively. Each time-series data 201M, 202M, 203M indicates a temporal change in the appearance degree of each of the plurality of objects appearing in the content. For example, the first content data 201 includes the first time series data 201M indicating the temporal change of the appearance degree of each of the plurality of objects appearing in the first content. The second content data 202 includes the second time series data 202M showing the temporal change of the appearance degree of each of the plurality of objects appearing in the second content. The third content data 203 includes the third time series data 203M indicating the temporal change of the appearance degree of each of the plurality of objects appearing in the third content.

Objects are, for example, people (characters), animals, other objects, concepts, deciding words, other words, sounds, landscapes, and backgrounds that appear in the content. The object may be an object represented as a figure or an object in an image, or may be an object or a concept represented by words in a sentence or conversation.

Appearance indicates the degree to which an object appears in the content. The appearance degree may be the number of appearances of the object or the appearance ratio of the object. The degree of appearance may simply indicate the presence or absence of appearance.

The "time" in the content need not be a physical time, as long as it is an index showing the progress of the story of the content. For example, if the content is a manga or a novel, the page number, the number of stories, and the volume number are indicators of the progress of the story, and can be treated as "time" in the content. If the content is a movie or a television program, the elapsed time from the start of the content can be treated as "time" in the content. Further, when the story of the content is developed while indicating a specific date and time, the date or the like may be treated as "time" in the content.

The degree of appearance is, for example, the number of appearances per unit period, the appearance ratio, or the presence or absence of appearance in the flow of the story of the content. The unit period may be a unit length based on the form of the medium on which the content is posted, such as one page, one episode, one volume, or a unit time length such as one minute, ten minutes, or one hour. It may be.

The number of appearances in a unit period indicates how many times a specific object has appeared in the unit period. The frequency of appearance in a unit period is the ratio of the number of appearances of a specific object in the unit period to the total number of appearances of all objects that appeared in the unit period. The presence or absence of appearance in the unit period indicates whether or not a specific object has appeared in the unit period.

FIG. 2 shows an example of the data structure of the first time series data 201M of the first content. The other time series data 202M and 203M have the same data structure, although not shown. Here, the first content is a cartoon.

The first time series data 201M includes time information T and object information S. The time information T is an index indicating the progress (progress position) of the story of the first content, and is represented by a combination of the page number, the number of stories, and the volume number. That is, the time information T includes a page number T1 which is the first time information, a number of talks T2 which is the second time information, and a volume number T3 which is the third time information. Here, the unit period for the appearance degree is one page, which is the minimum time unit in the time information T. In FIG. 2, time progresses from t1 to tx.

The object information S indicates the appearance degree of each of the plurality of objects. The object information S includes the appearance degree of all the objects appearing in the first content. In FIG. 2, character A, character B, character C, character D, building E, building F, tool G, and tool H are shown as objects.

The appearance degree is associated with each unit period (each page). For example, the first line P1 of FIG. 2 shows the appearance degree (number of appearances) of each object in the unit period of the first volume, the first episode, and the first page of the first content. Specifically, in the first line p1 of FIG. 2, in Volume 1, Episode 1, and Page 1, character A is twice, character B is once, character C is once, and character D is 0. It shows that the building E appeared 0 times, the building F 0 times, the tool G 0 times, and the tool H appeared 1 time. In this way, in the first line P1 of FIG. 2, the appearance degree of each object within the unit period of the first volume, the first episode, and the first page of the first content is associated with each other. There is. Similarly, the appearance degree of each object in the other unit period is associated with the other unit period.

Since the first time series data 201M is configured as described above, the temporal changes in the appearance degrees of each of the plurality of objects A, B, C, D, E, F, G, and H appearing in the first content. Is shown. Such time-series data 201M, 202M, 203M show the temporal change of the appearance degree of the object and quantitatively represent the story development. Therefore, the time series data 201M, 202M, and 203M are useful for grasping and analyzing the story development.

FIG. 3 shows an example of story development presentation processing 111 using time series data. The story development presentation process 111 is executed by the processor 110 of the story development presentation device 100. The story development presentation device 100 according to the embodiment generates a graphical image showing the story development from the time series data read in response to the query input from the user. The story development presentation device 100 presents a graphical image to the user as information indicating the story development of the content.

By presenting the time series data to the user as a graphical image, the user can easily recognize the story development indicated by the temporal change of the appearance degree of the object through the graphical image. The presentation of the story development by the graphical image can be visually and intuitively understood as compared with the presentation of the story development by the text or the numerical value.

In the story development presentation process 111 according to the first embodiment, first, the processor 110 of the story development presentation device 100 executes the search process (step S111). The search process is a process of searching for the content that the user is looking for. In the search process, the story development presentation device 100 receives the content search request from the user terminal 300 and executes the search in the database 200. In the following, the searched content may be referred to as target content.

The content search request includes, for example, a query for searching. The query contains search data used to search for content. The search data is data for identifying the content, for example, data indicating a work name. The query may be a document in natural language.

The processor 110 acquires specific content data that matches the search data as the search result in the database 200. That is, the processor 110 reads the content data of the target content from the database 200. The read content data includes the above-mentioned time series data. The content data including the time series data is stored in the storage device 120 (step S112).

The processor 110 generates image data (graphical image) that graphically represents the time series data from the stored time series data (step S115). In an embodiment, the graphical image is image data of a graph showing the temporal change of the appearance degree (see FIG. 4).

The time-series data stored in the database 200 includes data indicating the temporal change of the appearance degree of all the objects of the corresponding contents. However, from the viewpoint of the user's visibility or the ease of grasping the story development, the time change of the appearance degree of a small number of objects is shown rather than the time change of the appearance degree of all the objects in the target content. It may be better.

Therefore, the processor 110 according to the embodiment selects an object to be used for generating the graphical image in order to narrow down the objects shown in the graphical image (step S113). The object selected in step S113 is referred to as a target object. In the embodiment, the graphical image is generated as image data of a graph showing the temporal change of the appearance degree of the target object. All objects may be selected as the target objects.

The selection of the target object may be an automatic selection selected by the processor 110 executing a predetermined selection algorithm, or a manual selection selected by user input from the terminal 300. The automatic selection reduces the burden on the user, and the manual selection enables free selection according to the user's interests. The result of the search process in step S111 or the search data may be used for the automatic selection of the target object.

The automatic selection of the target object can be based on the result of analyzing the time series data of the target content. The analysis of time series data is, for example, an analysis of the appearance degree of each object. The processor 110 can analyze the appearance degree of each object and select the target object based on the magnitude of the appearance degree of the object or the change degree of the appearance degree. The analysis of the time series data may be performed by non-negative matrix factorization as described in the second embodiment described later.

The selection criteria for the target object are, for example, that the appearance degree of the object is larger than the threshold value, or that the appearance degree of the object is within the upper predetermined number (for example, the appearance degree is within the top 3). ,. Objects with a high degree of appearance can be said to be the main objects in the target content. By showing the change in the appearance of the main objects over time, it is possible to show the story development centered on the main objects.

Other selection criteria of the target object are that the appearance degree of the object is smaller than the threshold value, or that the appearance degree of the object is within the lower predetermined number (for example, the appearance degree is within the lower 3rd place). ,. Since low-appearance objects may be key objects that occupy an important position in story development, it is also useful to show the temporal changes in the appearance of low-appearance objects.

Further, the time-series data stored in the database 200 includes data indicating a temporal change in the appearance degree of the corresponding content in the entire time range (from the start to the end of the content). However, from the viewpoint of user visibility or ease of grasping the story development, the appearance in a shorter time range (a part of the time range in the whole time range) than showing the temporal change of the appearance degree in the whole time range. It may be better to show a change in degree over time.

Therefore, the processor 110 according to the embodiment selects the time range used for the graphical image generation in order to narrow down the time range shown in the graphical image to a part of the time range (step S114). The time range selected in step S114 is referred to as a target time range. In the time series data, the data showing the temporal change of the appearance degree in the target time range is called the partial time series data. In the embodiment, the graphical image is generated from the partial time series data as image data of a graph showing the temporal change of the appearance degree of the object in the target time range. The entire time range of the target content may be selected as the target time range. The full time range indicates, for example, the entire volume, the entire story, and the entire page of the content. Some time ranges that are the target time range are, for example, specific one or more volume numbers, one or more episodes in a specific volume, and specific one or more page numbers.

The selection of the target time range may be an automatic selection selected by the processor 110 executing a predetermined selection algorithm, or a manual selection selected by user input from the terminal 300. The automatic selection reduces the burden on the user, and the manual selection enables free selection according to the user's interests. The result of the search process in step S111 or the search data may be used for the automatic selection of the target time range.

The automatic selection of the target time range can be based on the result of analyzing the time series data of the target content. The analysis of time series data is, for example, an analysis of the appearance degree of each object. The processor 110 can analyze the appearance degree of each object and select the target time range based on the magnitude of the appearance degree of the object or the change degree of the appearance degree. The object to be analyzed may be a target object or may include an object other than the target object. The analysis of the time series data may be performed by non-negative matrix factorization as described in the second embodiment described later.

The target time range is selected, for example, as a time range that includes the time when the target object appears more than the threshold value. Further, the target time range is selected as a time range including the time when the degree of change in the appearance degree of the target object becomes larger than the threshold value. By selecting the time range in which many target objects appear, an appropriate story development presentation will be made. In addition, the timing at which the appearance of the target object changes (increases or decreases) may be an important timing for story development, so it is appropriate to select a time range in which the appearance of the target object changes significantly. It will be a story development presentation.

In FIG. 3, after reading the time series data in step S112, the target object is selected (step S113) and the target time range (step S114) is selected, but the reverse is also possible. That is, after selecting the target object and the target time range, only the data indicating the temporal change of the appearance degree of the target object in the target time range is read out from the time series data stored in the database 200. May be good.

In step S115, the processor 110 generates image data (graphical image) of a graph showing the temporal change of the appearance degree of the target object in the target time range.

In step S116, the processor 110 transmits the image data constituting the graphical image to the user terminal 300 together with other necessary data. The user terminal 300 receives data including image data for a graphical image. In the user terminal 300, a graphical image or the like is displayed on the display (input / output device 330) included in the user terminal 300 as data indicating the story development of the content to be presented (step S131).

After that, the processor 110 can accept the user operation on the user terminal 300 and update the graphical image or the like displayed on the user terminal 300 at any time (step S117).

FIG. 4 shows an example of the screen 500 displayed on the display of the user terminal 300. The screen 500 is a graphical user interface (GUI) screen. On the screen 500, the graphical image 512 and the like of the time series data are displayed, and the user operation is accepted.

The screen 500 includes a display area 501 of data received from the story development presentation device 100. The display area 501 has a graphical image 512 of time series data. The graphical image 512 shows the story development from the viewpoint of the change in the appearance of the object in the target content.

In addition to the graphical image 512, the display area 501 includes a work name display unit 510, a target object name display unit 511, and a seek bar 516.

The work name display unit 510 is an area for displaying the work name of the target content. The name display unit 511 is an area for displaying the name of the target object in the target content. The name of the target object is, for example, a character name. FIG. 4 shows a case where three objects, character A, character B, and character C, are selected as the target objects. In the display area 501 shown in FIG. 4, the character A is given a reference symbol of "O-1", the character B is given a reference symbol of "O-2", and the character C is given a reference symbol of "O-2". The reference symbol of "-3" is attached.

The graphical image 512 shown in FIG. 4 is configured as a graph showing the temporal variation of the appearance degree of the target object in the target time range. The horizontal axis of the graph, which is the graphical image 512, indicates the time, and the vertical axis indicates the appearance degree (appearance ratio) of each target object. Here, a plurality of (three) target objects are selected, and the target time range is from the first episode to the twentieth episode.

The graphical image 512 shown in FIG. 4 is shown as a ratio of the number of appearances of each target object to the total number of appearances of all the selected target objects in each time range (range for one episode). That is, when the total number of appearances of the three target objects in each time range (range for one episode) is 100, it indicates the rate at which each target object appears. For example, in the ninth episode, of the three characters A, B, and C, the appearance rate of the character A (O-1) is 53.77%, and the appearance rate of the character B (O-2) is 46. It is 23%, which indicates that the appearance rate of character C (O-3) was 0%.

In the graphical image 512 shown in FIG. 4, the temporal change in the size of the appearance ratio of each target object is shown by the temporal change in the size of the area occupied by each target object in the graph. Therefore, it is easy to visually and intuitively understand the temporal change of the appearance rate. Moreover, in the graphical image 512 shown in FIG. 4, since the time change of the appearance ratio is shown only for the plurality of selected target objects, the change in the story development due to the plurality of selected target objects can be seen. It can be grasped visually and intuitively.

According to the story development presenting device 100 according to the embodiment, the user can visually and intuitively grasp the change in the story development, so that a specific part (specific scene) in the story can be grasped without directly viewing the content. It becomes possible to search for. For example, even if the user cannot remember where the specific scene where character A and character B co-star is, by referring to the graphical image 512, both character A and character B appear. You can find such a scene from a high place.

On the screen 500 shown in FIG. 4, a graphical image 512 of the appearance degree is presented to the user without attaching a sentence (for example, a synopsis) explaining the story of the target content. Therefore, it is possible to present the story development to the user while preventing spoilers to the user.

For example, the user uses the user terminal 300 to read the 18th episode of the content viewed online (for example, a cartoon that can be read online), mistakenly skips the 19th episode, and tries to read the 20th episode. Sometimes. When the possibility of such an error is detected by the server that provides the content, the story development presenting device 100 gives a warning of the possibility of the error by changing the appearance of each object in the 19th episode over time. The graphical image 512 to be shown can be shown to the user terminal 300.

If the user who sees the graphical image 512 has already read the 19th episode, the story of the 19th episode is inspired by the information (the appearance ratio of each object and its temporal change) shown by the graphical image 512. Can be easily remembered. On the contrary, if the user has not read the 19th episode, the information shown by the graphical image 512 does not remind the story of the 19th episode. In this way, by using the graphical image 512, the user can confirm whether a specific part of the content has been read or viewed.

If the method of checking the synopsis of the 19th episode is adopted to confirm whether the 19th episode has been read, the user knows the synopsis of the 19th episode that has not been read in advance, so-called. Spoilers occur. However, according to the present embodiment, it is possible to confirm whether or not a specific part of the content has been read or viewed while preventing spoilers.

In the above case, the server itself that provides the content may have a function as the story development presentation device 100, or the server that provides the content and the story development presentation device 100 are connected via the network. It may have been done. When the story development presenting device 100 detects the necessity of confirming whether the story has been read or has been viewed, the story development presenting device 100 transmits a graphical image 512 of the portion requiring confirmation to the user terminal 300.

Further, in the embodiment, in order to more accurately grasp the appearance ratio at each time point on the horizontal axis of the graph, the screen 500 can display the appearance ratio of each target object numerically. The screen 500 includes a seek bar 516 and a selection line R for numerically displaying the appearance ratio. The seek bar 516 includes a slider 516A that is movable along the horizontal axis direction of the graph.

The user can select each time point (number of talks) on the horizontal axis of the graph by performing an operation of moving the slider 516A by the GUI function. In FIG. 4, the ninth episode is selected. The selection line R moves in conjunction with the slider 516A. The user can also move the selection line by the GUI function. While the seek bar 516 is arranged outside the graph, the selection line R is arranged on the graph, and it is possible to more clearly indicate which number of episodes is selected.

The screen 500 can display the display units 513, 514, 515 showing the appearance degree (appearance ratio) at the selected time point (number of talks). The display units 513, 514 and 515 can have, for example, the shape of a balloon. In FIG. 4, a first display unit 513, a second display unit 514, and a third display unit 515 showing the appearance ratio in the selected episode 9 are shown. The first display unit 513 indicates the appearance ratio of the character A (O-1) as a numerical value (53.77%). The second display unit 514 indicates the appearance ratio of the character B (O-2) as a numerical value (46.23%). The third display unit 515 indicates the appearance ratio of the character C (O-3) as a numerical value (0%). As a result, it can be seen that in Volume 9 of the target content, character A and character B appear frequently, and character C does not appear.

FIG. 5 shows the display area 501 of the screen 500 after the user operation to move the slider 516A to the position of the thirteenth episode is performed. In the thirteenth episode, the appearance ratio of the character A indicated by the first display unit 513 is 58.77%, the appearance ratio of the character B indicated by the second display unit 514 is 23.16%, and the third The appearance ratio of the character C indicated by the display unit 515 is 21.35%. In the thirteenth episode, it can be seen that character C appears in addition to character A and character B. Further, according to the graphical image 512 shown in FIG. 5, it can be seen that the character C did not appear until the 12th episode, but appeared from the 13th episode.

In this way, by presenting the temporal change of the appearance degree to the user as image data, the number of appearance stories (at the time of appearance) of the target object can be presented to the user without showing the story itself. Further, even if the number of objects included in the time series data is enormous, only the temporal change of the appearance degree of the selected target object is presented as image data, so that the visibility is improved.

FIG. 6 shows another example of the display area 501 on the screen 500. FIG. 6 shows a case where an object other than the character is also selected as the target object. FIG. 6 shows a case where three objects, a character D, a building E, and a tool G, are selected as target objects. In the display area 501 shown in FIG. 6, the character D is given a reference symbol of "O-1", the building E is given a reference symbol of "O-2", and the tool G is given a reference symbol of "O-2". The reference symbol of "-3" is attached.

As described above, according to the embodiment, since the time series data of the appearance degree of the target object automatically selected or arbitrarily selected by the user can be displayed as the graphical image 512, it is easy to develop the story from the viewpoint of any object. Can be presented to.

<2.2 Second Embodiment>

In the second embodiment, at least one of the selection of the target object (step S113 in FIG. 3) and the selection of the target time range (step S114 in FIG. 3) is performed with respect to the time series data 201M of the target content. It is based on the result of applying a non-negative matrix factorization (NMF) algorithm. That is, in the second embodiment, the analysis of the time series data 201M in the first embodiment is performed by NMF. The points not particularly described in the second embodiment are the same as those in the first embodiment.

FIG. 7 shows the data structure of the time series data 201M used in the story development presentation process 111 according to the second embodiment. In the second embodiment, the time series data 201M is treated as matrix data.

In the time-series data 201M shown in FIG. 7, each of the plurality of rows indicates the temporal change of the appearance degree of each object, and each of the plurality of columns indicates the "time" in the content. In FIG. 7, as the first embodiment, the character A, the character B, the character C, the character D, the building E, the building F, the tool G, and the tool H are included as the objects. Although the time is indicated by an integer of 1 or more for simplification, it may be represented by a combination of a page number, a number of talks, and a volume number as in the time information T in the first embodiment. In the following, it is assumed that the numerical value indicating the time represents the number of stories.

For example, for character A, the degree of appearance in the first episode is _{represented by mA1} , the degree of appearance in the second episode is _{represented by mA2} , the degree of appearance in the third episode is _{represented by mA3} , and the degree of appearance in the fourth episode is represented by mA3. appeared degree is represented by _{m A4,} appeared degree in the fifth episode is represented by _{m A5,} appeared degree in the tx story is represented by _{m Ax.} As a result, the time change of the appearance degree of the character A is represented. The temporal change in the appearance of character A is represented as an x-dimensional vector. Similarly, for other objects, the change in appearance over time is shown.

In the second embodiment, the time series data 201M is treated as matrix data having a size of the number of objects × the number of hours (1 to tx). The matrix element in the matrix data indicates the degree of appearance _{of the above-mentioned mA1 and the like.}

The time-series data 201M treated as matrix data is created as non-negative matrix data in which _{all the matrix elements (appearance degree mA1 and the like) are non-negative values.} Since the time series data 201M is non-negative matrix data, the non-negative matrix factorization (NMF) algorithm can be applied.

In the NMF algorithm, two non-negative matrices, a first non-negative matrix W and a second non-negative matrix H, can be obtained from a given non-negative matrix X. That is, the NMF algorithm is an algorithm for approximating a given non-negative matrix X by the product of two non-negative matrices, a first non-negative matrix W and a second non-negative matrix H.

When the given non-negative matrix X is an N × M matrix, the first non-negative matrix W becomes an N × r matrix, and the second non-negative matrix H becomes an r × M matrix. r is a value given in advance, preferably an integer of 2 or more. The first non-negative matrix W is a basis matrix having r basis vectors. The second non-negative matrix H is an activation matrix showing the weights of each basis vector.

FIG. 8 shows an example of the first non-negative matrix data W (base matrix) obtained by applying the NMF algorithm to the time-series data 201M which is the non-negative matrix data. Here, r = 3. Therefore, the first non-negative matrix data W shown in FIG. 8 has three basis vectors F1, F2, and F3. Here, a plurality of basis vectors F1, F3, and F3 are referred to as topics.

By applying NMF to the time-series data showing the temporal change of the appearance degree of each of the plurality of objects appearing in the story, the present inventors apply NMF to a plurality of topics F1, F2, F3 that are important in story development. It was found that can be decomposed and extracted. The extracted topics F1, F2, and F3 are important factors that are the basis of the story development of the content. By applying NMF to the time-series data 201M, it is possible to easily obtain a story development analysis result that cannot be easily obtained even if a human directly reads or views the content.

The plurality of topics F1, F2, and F3 can also be interpreted as the main story and the sub-story that compose the story. This is true when multiple stories are mixed, even for a single piece of content. For example, in the case of manga, a one-shot story may be completed for each episode or several episodes, but a basic story may be set throughout the content. In such a case, the story progresses by mixing a single story and a basic story in one content. By using NMF, a plurality of stories mixed in one content can be extracted as topics F1, F2, and F3.

The first topic F1 (base vector) shown in FIG. 8 shows the appearance degree of each object in the first topic F1, and the appearance degree of the character B is the largest among all the objects. Therefore, it can be seen that the first topic F1 is a topic mainly composed of the character B.

The second topic F2 (base vector) shows the appearance degree of each object in the second topic F2, and the appearance degree of the character A is the largest among all the objects. Therefore, it can be seen that the second topic F2 is a topic mainly composed of the character A.

The third topic F3 (base vector) shows the appearance degree of each object in the third topic F3, and among all the objects, the appearance degree of the character C is the largest, and the character B also appears to some extent. Therefore, it can be seen that the third topic is mainly character B and character C, and character C is more important than character B.

FIG. 9 shows an example of the second non-negative matrix data H (activation matrix) obtained by applying the NMF algorithm to the time-series data 201M which is the non-negative matrix data. Here, since r = 3, the second non-negative matrix data H shows the weights (activation degree) of each of the three topics F1, F2, and F3 at each time. That is, the second non-negative matrix data H (activation matrix) is a temporal change of how much weight each topic F1, F2, F3 has at each time (number of talks), in other words, how active it is. It shows the temporal change of whether or not it has become.

In the story development presentation process 111 of the second embodiment, the processor 110 selects the target object using the first non-negative matrix W (step S113 in FIG. 3). For example, the processor 110 automatically selects any topic from a plurality of topics F1, F2, and F3.

The topics F1, F2, and F3 may be manually selected by the user's operation with reference to the NMF result displayed on the user terminal 300. In this case, the result of NMF is displayed on the user terminal 300 prior to the selection by the user (see the third embodiment described later).

Then, the processor 110 selects one or a plurality of objects having a high appearance in the selected topic in the first non-negative matrix W. In addition, one or a plurality of objects having a low appearance degree may be selected. By the above processing, the object related to the selected topic is automatically selected as the target object.

Further, in the story development presentation process 111 of the second embodiment, the processor 110 selects the target time range using the second non-negative matrix H (step S114 in FIG. 3). For example, the processor 110 refers to the second non-negative matrix H, and selects a time range including a time in which the weight (activation degree) of the topic selected as described above is larger than the threshold value as the target time range. .. The selection of the target time range may be a manual selection by the user's operation referring to the result of the NMF displayed on the user terminal 300.

The graphical image 512 generated in the second embodiment can show the temporal change of the appearance degree of the target object selected by using the NMF result in the target time range selected by using the NMF result. .. That is, in the second embodiment, the story development on the selected specific topic is presented.

<2.3 Third Embodiment>

FIG. 10 shows the system 10 according to the third embodiment. In the third embodiment, the points not particularly described are the same as those in the first embodiment and the second embodiment.

The system 10 according to the third embodiment includes a story development analysis device 100A. The story development analysis device 100A analyzes the story development of the content and generates data indicating the story development as the analysis result. The story development analysis device 100A according to the third embodiment analyzes the story development of the content by using non-negative matrix factorization (NMF) as an example. The story development analysis device 100A also operates as a story development presentation device that presents the data indicating the story development obtained as the analysis result to the user via the network 400.

In the second embodiment, the analysis result obtained by applying NMF to the time series data was used for selecting the target object or the target time range, but in the third embodiment, the NMF is applied to the time series data. The analysis result obtained by applying is used as data showing the story development. The story development analysis device 100A generates a graphical image showing the story development from the analysis result obtained by the NMF. The story development analysis device 100A presents a graphical image to the user as information indicating the story development of the content.

In the third embodiment, the user is a person involved in the production of the content, for example, the author and the editor of the content. The user may be a reader of a cartoon or a novel, or a viewer of a movie or television program. The story development analysis device 100A supports the user who proposes or changes the story development by presenting the analysis result of the story development to the user.

The system 10 includes a user terminal 300 connected to the story development analysis device 100A via the network 400. The user can access the story development analysis device 100A by using the user terminal 300. The user terminal 300 includes a processor 310, a storage device 320, and an input / output device 330.

The story development analysis device 100A is composed of a computer including a processor 110 and a storage device 120. The storage device 120 stores a computer program 121A for operating the computer as a story development analysis device 100A (story development presentation device). The computer program 121A includes a program code for causing the processor 110 to execute the story development analysis process 111A (story development presentation process). The story development analysis process 111A is a process including analyzing the story development of the content. The story development analysis process 111A will be described later.

The story development analysis device 100A includes a database 200. The database 200 includes a plurality of content data 201, 202, 203. In FIG. 10, similarly to FIG. 1, the first content data 201 of the first content (work name: xxx), the second content data 202 of the second content (work name: yyy), and the third content (work). The third content data 203 of the name: zzz) is shown. The content data 201, 202, 203 according to the embodiment further includes time series data 201M, 202M, 203M, respectively. Each time-series data 201M, 202M, 203M indicates a temporal change in the appearance degree of each of the plurality of objects appearing in the content.

The data structure of each time series data 201M, 202M, 203M according to the third embodiment is the same as the data structure of the time series data 201M in the second embodiment (see FIG. 7). The time series data 201M, 202M, and 203M according to the third embodiment are non-negative matrix data as in the second embodiment.

FIG. 11 shows an example of the story development analysis process 111A using the time series data. The story development analysis process 111A is executed by the processor 110 of the story development analysis device 100A. The story development analysis device 100A according to the embodiment applies the NMF algorithm to the time series data 201M, 202M, 203M which are non-negative matrix data for the analysis of the story development.

In the story development analysis process 111A according to the third embodiment, the processor 110 first executes the search process (step S311). The search process is the same as that of the first embodiment, and the search process is a process of searching the database 200 for the content (target content) that the user is looking for.

The processor 110 acquires data of specific contents matching the search data as the search result in the database 200. That is, the processor 110 reads the data of the target content from the database 200. The read content data includes the above-mentioned time series data. The content data including the time series data is stored in the storage device 120 (step S312).

The processor 110 applies the NMF algorithm to the stored time series data (see FIG. 7) (step S313). The processor 110 obtains the first non-negative matrix data W shown in FIG. 8 and the second non-negative matrix data H shown in FIG. 9 as the analysis result by the NMF. As described above, the first non-negative matrix W is a basis matrix having r basis vectors. The second non-negative matrix H is an activation matrix showing the weights of each basis vector.

The processor 110 generates image data (graphical image) indicating the story development of the target content from the first non-negative matrix data W and the second non-negative matrix data H (step S314). The processor 110 transmits the image data constituting the graphical image to the user terminal 300 together with other necessary data.

The user terminal 300 receives data including image data for a graphical image. In the user terminal 300, a graphical image or the like is displayed on a display (input / output device 300) included in the user terminal 300 as data showing an analysis result of story development of the content to be presented.

FIG. 12 shows an example of the screen 500A displayed on the display of the user terminal 300. The screen 500A is a graphical user interface (GUI) screen. On the screen 500A, the analysis result is displayed and the user operation is accepted.

The screen 500A has a work name display unit 510, a topic display unit 601 and a story development display unit 602.

The topic display unit 601 displays one or a plurality of topics included in the target content. The topic display unit 601 is also a legend display of the graph displayed in the story development display unit 602.

The topic displayed in the topic display unit 601 is generated from the first non-negative matrix data W. The first non-negative matrix data W shown in FIG. 8 has three basis vectors F1, F2, and F3. Therefore, three topics F1, F2, and F3 are displayed on the topic display unit 601.

The topic display unit 601 indicates an object in each topic F1, F2, F3. In the topic display unit 601 shown in FIG. 12, the main object in the first topic F1 is the character B, the main object in the second topic F2 is the character A, and the main objects in the third topic F3 are the character B and It is shown to be character C. Since the main objects in each topic F1, F2, F3 are displayed on the topic display unit 601, the user can grasp the main objects contributing to each topic F1, F2, F3.

The processor 110 determines the main objects displayed on the topic display unit 601 based on the first non-negative matrix W. The main object is determined based on the value of the matrix element of the first nonnegative matrix W. The value of the matrix element of the first non-negative matrix W indicates the contribution of the object in each topic. Therefore, in each basis vector (topic), the processor 110 can determine, for example, the object having the largest contribution or the object having the contribution greater than the threshold value as the main object in the topic.

The story development display unit 602 shows the temporal change of the activation degree (hereinafter, also referred to as “activation value”) of each topic F1, F2, F3 by a graph which is a graphical image. In the story development display unit 602 of FIG. 10, the horizontal axis indicates the number of stories as an example of time, and the vertical axis indicates the degree of activation. In the story development display unit 602 of FIG. 10, it is shown as image data of a line graph that visualizes the temporal change of the activation degree of each of the three topics F1, F2, and F3.

In the story development display unit 602 of FIG. 12, the first topic F1 in which the character B is the main object and the second topic F2 in which the character A is the main object show a time-stable activation degree. .. Therefore, the user who observes the story development display unit 602 can grasp that the character A and the character B are the main objects (so-called heroes) that always appear in the target content. Further, in the target content, the topics F1 and F2 related to the characters A and B show a stable degree of activation in time. Therefore, in the target content, the characters A and B, which are the main characters, have undulations in the story development. Regardless, it can be seen that it has appeared stably.

Further, in the story development display unit 602, the third topic F3 shows that the undulations occur due to a large change in time. Therefore, the user who observes the story development display unit 602 can grasp that the undulations of the story development are created by the entanglement of the character C (main) and the character B (sub).

That is, the user can objectively grasp that the characters A and B are the main characters, while the heart of the story development lies in the entanglement of the characters C (main) and the character B (sub). In this way, the user can easily grasp the story development pattern of the target content. Such a story development pattern may not be easily obtained even if a human directly reads or views the content, but it is possible to easily obtain a story development pattern by analysis using an NMF algorithm. Can be done.

Moreover, since the analysis result of the story development obtained by the NMF algorithm is numerical data, it is useful for examining the similarity of the story development between different contents. For example, when the content to be produced is desired to resemble the story of other content, or when the content to be produced does not want to resemble the story of other content, the creator who is the user can use another content obtained by the story development analysis device 100A. With reference to the story development of the content, it is possible to think about the story development of the content to be constrained.

Further, the analysis result of the story development obtained by the NMF algorithm is numerical data and quantitatively represents the story development of the content. Therefore, it is also possible to search for other contents similar to one content by using the sameness or similarity between the analysis results of the contents.

The screen 500A may include a display showing the first non-negative matrix data W shown in FIG. 8 and the second non-negative matrix H shown in FIG. 9 as numerical data. In this case, the user can confirm the details of the analysis result.

Further, the story development analysis device 100A according to the third embodiment has a function of displaying a value of how to adjust the appearance degree of an object (character) in the target content in order to review or correct the story development. Also has. With such a function, a user such as a creator can perform a simulation when the story development is changed. In addition, the user can obtain hints for suggesting story development.

In order to support the adjustment of the appearance degree of the object, the processor 110 according to the third embodiment can execute the processes after step S315 in the story development analysis process 111A. Here, the adjusted object appearance degree is obtained by changing the activation value (activation degree) of each topic obtained by NMF.

FIG. 13 shows a screen 500A including a function for supporting adjustment of the appearance degree of the object. Similar to FIG. 12, the screen 500A includes a work name display unit 510, a topic display unit 601 and a story development display unit 602. Further, the screen 500A shown in FIG. 13 includes an object contribution display unit 701, a story development adjustment unit 702, and an adjustment result display unit 703.

The object contribution display unit 701 is an area for displaying numerical data indicating the first non-negative matrix W. The user can grasp the analysis result by the NMF algorithm in more detail by referring to the object contribution display unit 701 in addition to the story development display unit 602.

The story development adjustment unit 702 includes a selection unit 702A for the topic to be adjusted, a selection unit 702B for the number of episodes to be adjusted (target time range), and an activation value input unit 702C. In the topic selection unit 702A, a topic whose activation value (activation degree) is adjusted is selected from a plurality of topics F1, F2, and F3 obtained by NMF. In the topic selection unit 702A, the extracted topics F1, F2, and F3 are shown so as to be selectable by using radio buttons or the like.

The processor 110 of the story development analysis device 100A receives the data shown in the selected target topic F3 from the user terminal 300. The processor 110 selects, for example, the third topic F3 as the target topic whose activation value is changed in the second non-negative matrix H based on the data received from the user terminal 300 (step S315).

In the story number selection unit 702B, the target story number for which the appearance degree of the object is adjusted in the target content is input by the user, for example, numerically. The processor 110 receives data indicating the number of selected target talks (target time range) from the user terminal 300. The processor 110 selects, for example, the third episode as the number of episodes (time range) in which the activation value is changed in the second non-negative matrix H based on the data received by the user terminal 300 (step S316).

In the activation value input unit 702C, the changed activation value is input by the user, for example, as a numerical value. As the activation value after the change, an arbitrary value is input by the user. The changed activation value is set to a value (for example, 0.7) different from the activation value (for example, 0) of the target topic obtained by NMF, for example.

The processor 110 receives the changed activation value from the user terminal 300. In the second non-negative matrix H, the processor 110 changes only the activation value of the number of target episodes (episode 3) of the target topic F3 from 0 before the change (see FIG. 9) to the value after the change (0.7). The changed second non-negative matrix H is generated. The processor 110 executes a matrix operation in which the first non-negative matrix W shown in FIG. 8 is multiplied by the changed second non-negative matrix. By this matrix operation, the appearance degree of each object in the third episode, which is the number of target episodes, is updated in the time series data 201M (non-negative matrix data) shown in FIG. 7 (step S317). Since there is no change in the appearance degree of each object other than the target story number in the updated time series data 201M, the operation of updating the appearance degree other than the target story number may be omitted in the matrix operation.

The processor 110 transmits the updated appearance degree of each object in the third episode, which is the number of target episodes, to the user terminal 300 as an adjustment result (step S318). The user terminal 300 receives the adjustment result and displays the adjustment result on the adjustment result display unit 703 of the screen 500A. The adjustment result display unit 703 displays the appearance degree (number of appearances) of each object for setting the activation value of the third topic F3 in the third episode, which is the number of target episodes, to 0.7. The user can grasp the appearance degree of the adjusted object by referring to the adjustment result display unit 703.

<3. Addendum>

The present invention is not limited to the above embodiment, and various modifications are possible.

10: System 100: Story development presentation device 100A: Story development analysis device 110: Processor 111: Story development presentation process 111A: Story development analysis process 120: Storage device 121: Computer program 121A: Computer program 200: Database 201: First content Data 201M: First time series data 202: Second content data 202M: Second time series data 203: Third content data 203M: Third time series data 300: User terminal 310: Processor 320: Storage device 330: Input / output device 400: Network 500: Screen 500A: Screen 501: Display area 510: Work name display unit 511: Name display unit 512: Graphical image 513: First display unit 514: Second display unit 515: Third display unit 516: Seek bar 516A : Slider 601: Topic display unit 602: Story development display unit 701: Object contribution display unit 702: Story development adjustment unit 702A: Selection unit 702B: Selection unit 702C: Input unit 703: Adjustment result display unit A: Character B: Character C: Character D: Character E: Building F: Building G: Tool H: Tool F1: First topic F2: Second topic F3: Third topic R: Selection line S: Object information T: Time information

Claims (17)

It is a method of presenting the development of a story in which multiple objects appear to the user.
The processor reads the time-series data from the database in which the time-series data indicating the temporal change of the appearance degree of each of the plurality of objects is stored.
Based on the time-series data read by the processor, the processor generates a graphical image showing the temporal change of the appearance degree of one or more objects included in the plurality of objects.
A method of presenting a story development to a user, wherein the processor presents the graphical image to the user as the development of the story. The graphical image is a method of presenting a user with the development of the story according to claim 1, which is presented to the user without being accompanied by a sentence explaining the story. The method of presenting a storyline development according to claim 1 or 2, wherein the processor further comprises selecting the one or more objects from the plurality of objects. The method of presenting the user with a storyline according to claim 3, wherein the one or more objects are selected based on data input by the user. The method of presenting the user with the development of the story according to claim 3, wherein the one or more objects are selected based on the result of analyzing the time series data. The method of presenting to the user the development of the story according to claim 3, wherein the one or more objects are selected based on the appearance degree indicated by the time series data. The time series data is non-negative matrix data and is
The story development according to claim 3, wherein the one or more objects are selected based on at least one of two non-negative matrices obtained from the time series data by a non-negative matrix factorization algorithm. How to present. The processor further comprises selecting a time range of a portion of the entire time range of the time series data.
The graphical image tells the user the development of the story according to any one of claims 1 to 6, which is generated based on the partial time series data in the partial time range of the time series data. How to present. The method of presenting the user with the development of the story according to claim 8, wherein the partial time range is selected based on the data input by the user. The method of presenting the user with the development of the story according to claim 8, wherein the partial time range is selected based on the result of analyzing the time series data.
The time series data is non-negative matrix data and is
The development of the story according to claim 8, wherein the partial time range is selected based on at least one of two non-negative matrices obtained from the time series data by a non-negative matrix factorization algorithm. How to present. The processor selects the one or more objects from the plurality of objects.
The processor selects a time range of a part of the entire time range of the time series data.
Further prepare
The method of presenting the user with the story development according to claim 1 or 2, wherein the graphical image is generated to indicate a temporal change in the appearance of the one or more objects in the part of the time range. A database that stores time-series data that shows the temporal changes in the appearance of each of the multiple objects that appear in the story, and
Based on the time-series data read from the database, a graphical image showing the temporal change of the appearance degree of one or more objects included in the plurality of objects is generated, and the graphical image is used as the development of the story. , A processor configured to perform the processing presented to the user,
A story development presentation device equipped with. Appearance of one or more objects included in the plurality of objects based on the time series data read from the database in which the time series data indicating the temporal change of the appearance degree of each of the plurality of objects appearing in the story is stored. A computer program for causing a computer to generate a graphical image showing a change over time and present the graphical image to a user as a development of the story. It is a method to analyze the development of a story in which multiple objects appear.
The processor reads the time-series data from the database in which the time-series data, which is the non-negative matrix data and shows the temporal change of the appearance degree of each of the plurality of objects, is stored.
A method of analyzing story evolution, comprising the processor applying a non-negative matrix factorization algorithm to the time series data to analyze the story. A database that shows the temporal changes in the appearance of each of the multiple objects that appear in the story and stores time-series data that is non-negative matrix data.
A processor configured to execute a process that applies a non-negative matrix factorization algorithm to the time series data read from the database.
A story development analysis device equipped with. A non-negative matrix factor decomposition algorithm is applied to the time-series data read from the database in which the time-series data, which is non-negative matrix data, is stored while showing the temporal change of the appearance degree of each of the plurality of objects appearing in the story. A computer program that lets a computer perform the processing it applies.

Images