Information processing device, information processing method, and information processing program

JP7914041B2Active Publication Date: 2026-09-01LY CORP
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2023024644
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2023-02-20
Publication Date
2026-09-01
Estimated Expiration
2043-02-20

AI Technical Summary

Benefits of technology

【0007】 実施形態の一態様によれば、コンテンツの登場人物を演じる俳優を適切に決定することができるという効果を奏する。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007914041000001
    Figure 0007914041000001
  • Figure 0007914041000002
    Figure 0007914041000002
  • Figure 0007914041000003
    Figure 0007914041000003
Patent Text Reader

Abstract

To provide an information processing apparatus, an information processing method, and an information processing program capable of properly determining an actor who plays a character in content.SOLUTION: An information processing apparatus includes a first specifying unit, a second specifying unit, and a proposal unit. The first specifying unit specifies characteristics of a character in content which is an adaptation source. The second specifying unit specifies characteristics of an actor on the basis of actor information including information on the actor. The proposal unit proposes an actor who plays the character in adapted content, which is content formed by adapting the content, on the basis of a result of comparing the characteristics of the character specified by the first specifying unit with the characteristics of the actor specified by the second specifying unit.SELECTED DRAWING: Figure 3
Need to check novelty before this filing date? Find Prior Art

Description

[Technical Field]

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program. [Background Art]

[0002] Conventionally, techniques related to casting work for determining performers in movies, dramas, stage plays, and the like have been proposed. For example, Patent Document 1 discloses a technique that enables video production staff to improve the efficiency of casting work for determining performers of a video work by checking the available schedules and performer information of performers via a network. [Prior Art Documents] [Patent Documents]

[0003] [Patent Document 1] Japanese Unexamined Patent Application Publication No. 2005-044258 [Summary of the Invention] [Problem to be Solved by the Invention]

[0004] However, although the above-mentioned conventional technique can improve the efficiency of casting work, it does not consider the appropriateness of casting at all. Therefore, for example, when live-action adapting content such as novels and manga, or when remaking content such as overseas dramas, the casting of actors may be inappropriate. Inappropriate casting of actors may give a sense of discomfort to fans of the original content.

[0005] The present application has been made in view of the above, and an object of the present application is to provide an information processing apparatus, an information processing method, and an information processing program that can appropriately determine an actor to play a character in content. [Means for Solving the Problem]

[0006] The information processing device according to the present application comprises a first identification unit, a second identification unit, and a proposal unit. The first identification unit identifies the characteristics of characters appearing in the source content. The second identification unit identifies the characteristics of actors based on actor information, which includes information about actors. The proposal unit proposes actors to play the characters in the adapted content, which is the content that adapts the source content, based on the comparison result between the characteristics of the characters identified by the first identification unit and the characteristics of the actors identified by the second identification unit. [Effects of the Invention]

[0007] According to one embodiment, the effect is that actors who play characters in the content can be appropriately determined. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of information processing according to the embodiment. [Figure 2] Figure 2 shows an example of the configuration of an information processing system according to the embodiment. [Figure 3] Figure 3 shows an example of the configuration of an information processing device according to the embodiment. [Figure 4] Figure 4 shows an example of a character information table stored in the character information storage unit according to the embodiment. [Figure 5] Figure 5 shows an example of an actor information table stored in the actor information storage unit according to the embodiment. [Figure 6] Figure 6 is a flowchart showing an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 7] Figure 7 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing apparatus, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing apparatus, information processing method, and information processing program according to the present application. Furthermore, each embodiment can be appropriately combined as long as the processing content is not inconsistent. Also, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0010] [1. An example of information processing] First, an example of information processing according to the embodiment will be described using Figure 1. Figure 1 is a diagram showing an example of information processing according to the embodiment, which is executed by the information processing device 1.

[0011] The information processing device 1 shown in Figure 1 determines the actors who will play the characters in the content being adapted from the source content. The source content may include, but is not limited to, novels, manga, animated works, foreign dramas, and foreign films. In the following, the source content may be referred to as the original content for convenience.

[0012] Content that is adapted from original content includes, but is not limited to, live-action adaptations of novels, manga, and animated works, and remakes of foreign dramas and films. In the following, content that is adapted from original content, such as live-action adaptations and remakes, may be referred to as "adapted content" for convenience.

[0013] First, the information processing device 1 receives adaptation information from a terminal device 2 such as an adaptation planning company P that plans to adapt the original content, which includes content identification information that identifies the original content and regional information that identifies the area in which the adapted content will be provided (step S1).

[0014] Subsequently, the information processing apparatus 1 acquires information of the original content specified by the content specifying information (step S2). The information of the original content includes, for example, original character information including information related to characters in the original content, posted character information including posted information related to characters of the original content on a Social Networking Service (SNS), and the like. Hereinafter, the social networking service may be referred to as SNS.

[0015] The original character information includes, for example, information related to characters of the novel when the original content is a novel, and includes information related to characters of the manga when the original content is a manga. Furthermore, the original character information includes, for example, information related to characters of the animation work when the original content is an animation work, and includes information related to characters of the overseas drama or overseas movie when the original content is an overseas drama or overseas movie.

[0016] The information related to characters included in the original character information includes, for example, information such as the gender, age, appearance, personality, and remarks of the character, or information for specifying such information, but is not limited to such examples. For example, the information related to a character may further include information such as the character's occupation, family structure, hobby, place of residence, annual income, or information for specifying such information.

[0017] The posted character information includes, for example, information indicating a poster's comment about a character in the original content. The poster's comment about the character includes information for specifying the character (e.g., information such as the character's name or nickname), information for specifying the poster's impression of the character (e.g., character strings such as good-looking, cute, or appealingly mature), and the like.

[0018] Further, the information processing apparatus 1 can analyze original content and acquire such analysis results as original character information. The information processing apparatus 1 can also acquire, as original character information, a result obtained by an external information processing apparatus analyzing the original content from the external information processing apparatus.

[0019] Subsequently, the information processing apparatus 1 identifies, for each character, characteristics of a character appearing in the original content based on information of the original content acquired in step S2 (step S3). For example, the information processing apparatus 1 identifies, for each character, at least one of a physical characteristic, a psychological characteristic, and an impressive characteristic of the character as the characteristic of the character.

[0020] The physical characteristics of a character include, but are not limited to, the character's height, weight, body shape, face shape, and hairstyle. The psychological characteristics of a character include, but are not limited to, optimistic, pessimistic, sociable, introverted, steady, serious, and patient.

[0021] An impressive characteristic is at least one characteristic selected from among an impression of the character's appearance, an impression of the character's inner self, and an impression of the character's utterances. The impression of the character's appearance is an impression of the character's body shape and face (e.g., plump, slim, chubby, good-looking, cute, has a high bridge of the nose, etc.). The impression of the character's inner self is an impression of the character's personality (e.g., violent, scary, gentle, weak, timid, etc.). The impression of the character's utterances is, for example, an impression of the character's way of speaking, word usage, and the like.

[0022] For example, the information processing apparatus 1 identifies the physical characteristics and psychological characteristics of the character based on original character information that is information about characters in the original content. For example, the information processing apparatus 1 performs morphological analysis on a character string included in the original character information or a character string obtained by converting speech included in the original character information.

[0023] The information processing device 1 then identifies the physical and psychological characteristics of the characters based on words (for example, nouns, adjectives, adverbs, etc.) included in the original character information, such as specific words related to the body and psychology.

[0024] Furthermore, if the original content is a manga, drama, animation, or film, the information processing device 1 can identify the physical and psychological characteristics of the characters by analyzing the images of the characters included in the original character information.

[0025] For example, the information processing device 1 can identify the physical characteristics of characters by comparing images of each character included in the original character information, or by performing pattern matching processing between the character's image and body shape patterns or face shape patterns. In addition, the information processing device 1 can identify the psychological characteristics of characters by performing pattern matching processing between the character's image and facial expression patterns.

[0026] Furthermore, the information processing device 1 identifies the poster's impression of the characters as distinctive characteristics of the characters, based on the posted character information, which is information posted on social media about the characters of the original content.

[0027] For example, the information processing device 1 performs morphological analysis on strings and other elements contained in the posted character information. Then, based on specific words (e.g., specific nouns, specific adjectives, specific adverbs, etc.) contained in the posted character information, the information processing device 1 identifies the poster's impression of the character as the character's impressionistic characteristics.

[0028] Next, the information processing device 1 acquires actor information for each actor, which includes information about the actor (step S4). The actor information includes, for example, actor-related information which includes information about the actor, and posting actor information which includes information about the actor posted on social media.

[0029] Actor-related information includes, for example, actor profiles featured on the websites of the production companies to which the actors belong, actor information published in online encyclopedias such as Wikipedia, actor information published onまとめサイト (summary sites), and actor information published on fan club websites. Furthermore, actor-related information may also include, for example, information about the parts of dramas and films in which the actors appear.

[0030] The posted actor information includes, for example, information showing comments made by users about the actor. These comments include information that identifies the actor (for example, the actor's name or nickname) and information that identifies the user's impression of the actor (for example, strings of characters such as handsome, cute, or cool).

[0031] Next, the information processing device 1 identifies the characteristics of each actor based on the actor information obtained in step S4 (step S5). For example, based on the actor information, the information processing device 1 identifies at least one of the actor's physical characteristics, psychological characteristics, and impressionistic characteristics as the actor's characteristics for each actor.

[0032] For example, the information processing device 1 identifies the actor's physical and psychological characteristics based on the actor-related information acquired in step S4. For example, the information processing device 1 performs morphological analysis on strings included in the actor-related information or strings converted from speech included in the actor-related information.

[0033] The information processing device 1 then identifies the actor's physical and psychological characteristics based on words (e.g., nouns, adjectives, adverbs, etc.) included in the actor-related information, such as specific words related to the body and psychology.

[0034] Furthermore, if the original content is a manga, drama, animation, or film, the information processing device 1 can identify the actor's physical and psychological characteristics by analyzing the actor's images included in the actor-related information.

[0035] For example, the information processing device 1 can identify an actor's physical characteristics by comparing images of each actor included in actor-related information, or by performing pattern matching processing between the actor's image and body shape patterns or face shape patterns. In addition, the information processing device 1 can identify an actor's psychological characteristics by performing pattern matching processing between the actor's image and facial expression patterns.

[0036] Furthermore, based on the submitted actor information, the information processing device 1 identifies the impression of the actor by the submitter in the adaptation region, which is the region where the adapted content is provided, as the impression characteristics of the actor. The adaptation region is the region identified by the regional information included in the adaptation information received in step S1. For example, if the adapted content is a film, it is the region where it will be screened; if the adapted content is a drama, it is the region where it will be broadcast; and if the adapted content is a play, it is the region where the play will be performed.

[0037] For example, the information processing device 1 performs morphological analysis on strings and other elements contained in the submitted actor information. Then, based on specific words (e.g., specific nouns, specific adjectives, specific adverbs, etc.) contained in the submitted actor information, the information processing device 1 identifies the impression of the actor by the submitter in the adaptation region as the actor's impressionistic characteristics.

[0038] Next, based on the comparison results between the characteristics of the characters identified in step S3 and the characteristics of the actors identified in step S5, the information processing device 1 determines, for each character, the actors who will play the characters in the adapted content, which is content that adapts the original content, as the actors to be proposed (step S6).

[0039] For example, the information processing device 1 determines, for each character, the actor who will play the character in the adapted content as the proposed actor, based on the results of a comparison between the character and the actor regarding at least one of the following: physical characteristics, psychological characteristics, and impressionistic characteristics.

[0040] The information processing device 1 calculates the similarity between the characteristics of the characters and the characteristics of the actors as a result of comparing the characteristics of the characters and the characteristics of the actors, and based on the calculated similarity, it determines which actors will play the characters in the adapted content to be proposed as actors. For example, the information processing device 1 determines which actors will be proposed as actors whose calculated similarity is above a threshold or whose calculated similarity is the highest.

[0041] For example, the information processing device 1 can calculate the similarity score by counting the number of feature items that match between the characters and the actors, or by assigning different weights to each matching feature item and adding them together to calculate the similarity score.

[0042] A characteristic item is an item that is included in at least one of the following characteristics: physical characteristics, psychological characteristics, and impression characteristics. For example, if the characteristic is a physical characteristic, it could be various items such as height range, weight range, body type, face shape type, or hairstyle type. If the characteristic is a psychological characteristic, it could be various items such as optimistic, pessimistic, sociable, introverted, steady, serious, patient, etc.

[0043] Furthermore, if the characteristics are impressive characteristics, they may include items related to impressions of body type and face, impressions of personality, and impressions of speech. Items related to impressions of body type and face include various items such as plump, slender, chubby, beautiful, cute, and having a straight nose. Items related to impressions of personality include various items such as violent, scary, gentle, weak, and timid. Items related to impressions of speech include items such as manner of speaking and word choice. Items related to impressions of face may also include the range of facial expression changes.

[0044] Furthermore, the information processing device 1 can calculate the appropriateness of an actor for a character using a learning model that outputs an appropriateness score from information on multiple characteristic items of the character and information on multiple characteristic items of the actor, and based on this appropriateness score, it can also determine the actor who will play the character in the adapted content as the actor to be proposed.

[0045] For example, the information processing device 1 determines the actor whose calculated appropriateness is above a threshold or the actor with the highest calculated appropriateness as the actor to be proposed. In this case, the information processing device 1 uses, for example, an appropriateness estimation model, which is a learning model that outputs a score indicating the appropriateness of an actor's casting based on the actor's information and the character's information, to determine the actor who will play the character in the adapted content as the actor to be proposed.

[0046] Appropriateness estimation models can be created, for example, based on ratings of actors. These ratings can be obtained, for example, from fan reviews of the original content, or from sales figures of other content (movies, dramas, plays, etc.) in which the actor appears.

[0047] Information processing device 1 creates a ground truth dataset containing multiple data points: information on highly-rated actors (actors who received high ratings in other content they appeared in) and information on characters corresponding to highly-rated actors in the original content. Information processing device 1 also creates an incorrect dataset containing multiple data points: information on low-rated actors (actors who received low ratings in other content they appeared in) and information on characters corresponding to low-rated actors in the original content. Then, using the datasets created as described above, information processing device 1 creates an appropriateness estimation model using machine learning.

[0048] Next, the information processing device 1 transmits the proposal information, which includes the information of the actor to be proposed as determined in step S6, to a terminal device 2 such as an adaptation planning company P, thereby proposing the proposal information to the adaptation planning company P (step S7).

[0049] The proposal information includes, for example, information about the actor being proposed and information about the character that the actor is proposed to play. If multiple actors are selected as candidates in step S6, the proposal information will include multiple pieces of information that associate the actor's information with the character's information.

[0050] In this way, the information processing device 1 identifies the characteristics of the characters appearing in the source content and identifies the characteristics of the actors based on actor information, which includes information about the actors. Then, based on the comparison result between the identified character characteristics and the actor characteristics, the information processing device 1 proposes actors who will play the characters in the adapted content, which is the content that adapts the source content. As a result, the information processing device 1 can appropriately determine the actors who will play the characters in the content.

[0051] The configuration of the information processing system, including the information processing device 1 and terminal device 2 that perform such processing, will be described in detail below.

[0052] [2. Configuration of the Information Processing System] Figure 2 shows an example of the configuration of an information processing system according to the embodiment. As shown in Figure 2, the information processing system 100 according to the embodiment includes an information processing device 1 and a plurality of terminal devices 2.

[0053] Multiple terminal devices 2 are used by different adaptation and planning companies P, etc. Terminal devices 2 are, for example, smartphones, tablet PCs, and wearable devices. Wearable devices include, but are not limited to, smart glasses or smartwatches.

[0054] The information processing device 1 and the multiple terminal devices 2 are connected to each other via a network N, either by wire or wireless, enabling communication between them. Note that the information processing system 100 shown in Figure 2 may include multiple information processing devices 1.

[0055] Network N includes, for example, WANs (Wide Area Networks) such as the Internet, and mobile communication networks such as LTE (Long Term Evolution), 4G (4th Generation), and 5G (5th Generation: 5th Generation Mobile Communication System).

[0056] Terminal device 2 can connect to network N via a mobile communication network or short-range wireless communication such as Bluetooth® or Wi-Fi (Local Area Network), and communicate with information processing device 1.

[0057] [3. Configuration of Information Processing Device 1] Figure 3 shows an example of the configuration of an information processing device 1 according to an embodiment. As shown in Figure 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0058] [3.1. Communications Section 10] The communication unit 10 is implemented, for example, by a NIC (Network Interface Card). The communication unit 10 is connected to the network N by wire or wireless connection and transmits and receives information with various other devices. For example, the communication unit 10 transmits and receives information with terminal devices 2, etc., via the network N.

[0059] [3.2. Storage section 11] The memory unit 11 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as hard disks and optical discs. The memory unit 11 has a character information memory unit 20 and an actor information memory unit 21.

[0060] [3.2.1.Character information storage unit 20] The character information storage unit 20 stores information about the characters in the original content. Figure 4 shows an example of a character information table stored in the character information storage unit 20 according to this embodiment.

[0061] In the example shown in Figure 4, the character information table stored in the character information storage unit 20 includes information such as "Character ID (Identifier)", "Original Character Information", and "Submitted Character Information". The "Character ID" is an identifier that identifies a character in the original content, and is assigned to each character.

[0062] "Original Character Information" includes information about the character in the original content in which the character corresponding to the "Character ID" appears. For example, if the original content is a novel, the original character information includes information about the characters in the novel; if the original content is a manga, it includes information about the characters in the manga.

[0063] Furthermore, information on characters from the original work includes, for example, information on characters from the animated work if the original content is an animated work, and information on characters from the foreign drama or film if the original content is a foreign drama or film.

[0064] The information about the characters included in the original work's character information includes, but is not limited to, information such as the character's gender, age, appearance, personality, statements, etc., or information used to identify such information. For example, the information about the character may further include information such as the character's occupation, family structure, hobbies, place of residence, annual income, etc., or information used to identify such information.

[0065] "Posted Character Information" includes information about posts made on social media regarding characters from the original content. For example, posted character information includes information showing comments made by posters regarding characters in the original content.

[0066] Comments from posters about characters include information that identifies the character (e.g., the character's name or nickname) and information that identifies the impression of the character (e.g., strings of characters such as handsome, cute, or cool).

[0067] [3.2.2. Actor Information Memory Section 21] The actor information storage unit 21 stores information about actors. Figure 5 shows an example of an actor information table stored in the actor information storage unit 21 according to this embodiment.

[0068] In the example shown in Figure 5, the actor information table stored in the actor information storage unit 21 includes information such as "Actor ID," "Actor-related information," and "Contributing Actor Information." The "Actor ID" is an identifier that identifies the actor and is assigned to each actor.

[0069] "Actor-related information" includes information about actors. Such actor-related information may include, for example, actor profiles posted on the website of the production company to which the actor belongs, actor information published in online encyclopedias such as Wikipedia, actor information published on summary sites, and actor information published on fan club websites. In addition, actor-related information may also include, for example, information about the parts in which the actor appears in dramas or movies.

[0070] "Posted actor information" includes information posted about actors on social media. Such posted actor information includes, for example, information showing comments made by posters about actors. Comments made by posters about actors include information that identifies the actor (for example, the actor's name or nickname) and information that identifies the impression of the actor (for example, strings of characters such as handsome, cute, or cool).

[0071] [3.3. Processing Unit 12] The processing unit 12 is a controller, and is realized by a processor such as a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in the memory device inside the information processing device 1, using RAM or the like as a working area.

[0072] Furthermore, the processing unit 12 is a controller, and may be implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), or GPGPU (General Purpose Graphic Processing Unit).

[0073] As shown in Figure 3, the processing unit 12 includes an acquisition unit 30, a reception unit 31, a first identification unit 32, a second identification unit 33, a proposal unit 34, and a learning unit 35, and realizes or executes the information processing functions and operations described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in Figure 3, and other configurations are also acceptable as long as they perform the information processing described later.

[0074] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various types of information. For example, the acquisition unit 30 acquires various types of information from external information processing devices or terminal devices 2 via the communication unit 10, and stores the acquired information in the storage unit 11.

[0075] For example, the acquisition unit 30 acquires original content from an external information processing device, analyzes the acquired original content, and obtains the analysis results as information about the characters in the original work. The acquisition unit 30 stores the acquired information about the characters in the original work in the character information storage unit 20.

[0076] Furthermore, the acquisition unit 30 acquires user-submitted information about the characters of the original content from an external information processing device or the like as user-submitted character information, and stores the acquired user-submitted character information in the character information storage unit 20.

[0077] Furthermore, the acquisition unit 30 can also acquire the results of an external information processing device's analysis of the original content as original character information from the external information processing device. In this case as well, the acquisition unit 30 stores the acquired original character information in the character information storage unit 20.

[0078] Furthermore, the acquisition unit 30 acquires information about actors from an external information processing device or the like, and stores the acquired information about actors in the actor information storage unit 21. Also, the acquisition unit 30 acquires posted information about actors from an external information processing device or the like, and stores the acquired posted information about actors in the actor information storage unit 21.

[0079] Furthermore, the acquisition unit 30 acquires various types of information from the memory unit 11. For example, the acquisition unit 30 acquires information about characters from the original work and information about characters posted on social media from the character information memory unit 20, etc. Information about characters posted on social media is an example of information about characters posted on social media. The acquisition unit 30 also acquires information about actors and information about actors who have posted on social media from the actor information memory unit 21, etc.

[0080] [3.3.2. Reception Department 31] The reception unit 31 receives various types of information and requests. For example, the reception unit 31 receives information and requests from external information processing devices or terminal devices 2 via the communication unit 10.

[0081] For example, the reception unit 31 receives adaptation information from a terminal device 2 such as an adaptation planning company P that plans to adapt the original content, which includes content identification information that identifies the original content and regional information that identifies the area in which the adapted content will be provided.

[0082] [3.3.3. First Specific Part 32] The first identification unit 32 identifies the characteristics of each character appearing in the original content, which is the source content from which the adaptation is made. For example, the first identification unit 32 identifies at least one of the following as a characteristic of the character: physical characteristics, psychological characteristics, and impressionistic characteristics.

[0083] The physical characteristics of the characters include, but are not limited to, their height, weight, build, facial features, and hairstyle. The psychological characteristics of the characters include, but are not limited to, optimistic, pessimistic, sociable, introverted, steady, serious, patient, etc.

[0084] An impressive characteristic is at least one of the following: the impression of a character's appearance, the impression of a character's inner self, and the impression of a character's speech. The impression of a character's appearance is the impression of the character's physique and face (e.g., plump, slender, chubby, beautiful, cute, straight nose, etc.). The impression of a character's inner self is the impression of the character's personality (e.g., violent, scary, gentle, weak, cowardly, etc.). The impression of a character's speech is, for example, the impression of their tone of voice and word choice.

[0085] The first identification unit 32 identifies the physical and psychological characteristics of a character based on, for example, the original character information, which is information about the character in the original content. For example, the first identification unit 32 performs morphological analysis on a string of characters included in the original character information or a string of characters obtained by converting the voice included in the original character information.

[0086] The first specific section 32 then identifies the physical and psychological characteristics of the characters based on words (for example, nouns, adjectives, adverbs, etc.) included in the original character information, such as specific words related to the body and psychology.

[0087] Furthermore, if the original content is a manga, drama, animation, or film, the first identification unit 32 can identify the physical and psychological characteristics of the characters by analyzing the images of the characters included in the original character information.

[0088] For example, the first identification unit 32 can identify the physical characteristics of a character by comparing images of each character included in the original character information, or by performing pattern matching processing between the character's image and body shape patterns or face shape patterns. Furthermore, the first identification unit 32 can identify the psychological characteristics of a character by performing pattern matching processing between the character's image and facial expression patterns.

[0089] Furthermore, the first specific unit 32 identifies the impression of the characters as distinctive characteristics of the characters, based on the posted character information, which is information posted on social media about the characters of the original content.

[0090] For example, the first identification unit 32 performs morphological analysis on strings and other elements included in the posted character information. The information processing device 1 then identifies the poster's impression of the character as an impressionistic characteristic of the character, based on specific words (e.g., specific nouns, specific adjectives, specific adverbs, etc.) included in the posted character information.

[0091] Furthermore, the impressions of the characters shared by contributors may be those of contributors in the region where the adapted content is provided, or those of contributors in the region where the original content is provided. Additionally, the impressions of the characters shared by contributors in the region where the adapted content is provided, as well as those of contributors in the region including the region where the adapted content is provided, may also be those of contributors in that region.

[0092] [3.3.4.Second Specification Section 33] The second identification unit 33 identifies the characteristics of each actor based on actor information, which includes information about the actor. For example, the second identification unit 33 identifies at least one of the following characteristics of each actor: physical characteristics, psychological characteristics, and impressionistic characteristics.

[0093] For example, the second identification unit 33 identifies the physical and psychological characteristics of an actor based on the actor-related information acquired by the acquisition unit 30. For example, the second identification unit 33 performs morphological analysis on strings of characters included in the actor-related information or strings of characters obtained by converting the voices included in the actor-related information.

[0094] The second identification section 33 then identifies the actor's physical and psychological characteristics based on words (for example, nouns, adjectives, adverbs, etc.) included in the actor-related information, including specific words related to the body and psychology.

[0095] Furthermore, if the original content is a manga, drama, animation, or film, the second specific unit 33 can identify the actor's physical and psychological characteristics by analyzing the actor's images included in the actor-related information.

[0096] For example, the second identification unit 33 can identify the physical characteristics of an actor by comparing images of each actor included in the actor-related information, or by performing pattern matching processing between the actor's image and body shape patterns or face shape patterns. In addition, the information processing device 1 can identify the psychological characteristics of an actor by performing pattern matching processing between the actor's image and facial expression patterns.

[0097] Furthermore, the second identification unit 33 identifies the impression of the actor as an impression characteristic of the actor, based on the submitted actor information, which is the impression of the actor by the submitter in the adaptation region, which is the region where the adapted content will be provided. The adaptation region is a region identified by the regional information included in the adaptation information received by the reception unit 31. For example, if the adapted content is a film, it is the region where it will be screened; if the adapted content is a drama, it is the region where it will be broadcast; and if the adapted content is a play, it is the region where the play will be performed.

[0098] For example, the second identification unit 33 performs morphological analysis on strings and other elements included in the submitted actor information. Then, based on specific words (e.g., specific nouns, specific adjectives, specific adverbs, etc.) included in the submitted actor information, the second identification unit 33 identifies the impression of the actor by the submitter in the adaptation region as the actor's impressionistic characteristics.

[0099] [3.3.5. Proposal Department 34] Based on the comparison results between the characteristics of the characters identified by the first identification unit 32 and the characteristics of the actors identified by the second identification unit 33, the proposal unit 34 proposes actors to play each character in the adapted content, which is content that adapts the original content.

[0100] For example, the proposal unit 34 determines which actor will play each character in the adapted content based on the results of comparing the character with the actor based on at least one of the following characteristics: physical characteristics, psychological characteristics, and impressionistic characteristics.

[0101] The proposal unit 34 comprises a calculation unit 40, a decision unit 41, and a provision unit 42. The calculation unit 40 calculates the degree of similarity between the characteristics of the character and the characteristics of the actor as a result of comparing the characteristics of the character and the characteristics of the actor.

[0102] For example, the calculation unit 40 can calculate the similarity score by counting the number of feature items that match between the characters and the actors, or by assigning different weights to each matching feature item and adding them together to calculate the similarity score.

[0103] A characteristic item is an item that is included in at least one of the following characteristics: physical characteristics, psychological characteristics, and impression characteristics. For example, if the characteristic is a physical characteristic, it could be various items such as height range, weight range, body type, face shape type, or hairstyle type. If the characteristic is a psychological characteristic, it could be various items such as optimistic, pessimistic, sociable, introverted, steady, serious, patient, etc.

[0104] Furthermore, if the characteristics are impressive characteristics, they may include items related to impressions of body type and face, impressions of personality, and impressions of speech. Items related to impressions of body type and face include various items such as plump, slender, chubby, beautiful, cute, and having a straight nose. Items related to impressions of personality include various items such as violent, scary, gentle, weak, and timid. Items related to impressions of speech include items such as manner of speaking and word choice. Items related to impressions of face may also include the range of facial expression changes.

[0105] Furthermore, the calculation unit 40 can also calculate the appropriateness of an actor for a character by using a learning model that outputs an appropriateness score from information on multiple characteristic items of the character and information on multiple characteristic items of the actor.

[0106] The decision unit 41 determines, based on the similarity calculated by the calculation unit 40, which actors will play characters in the adapted content, as actors to be proposed. For example, the decision unit 41 determines, as actors to be proposed, which actors have a similarity score equal to or greater than a threshold calculated by the calculation unit 40, or which actor has the highest calculated similarity score.

[0107] Furthermore, the decision unit 41 can also determine actors to be proposed as actors to play characters in the adapted content, based on the appropriateness calculated by the calculation unit 40. For example, the decision unit 41 determines actors whose appropriateness calculated by the calculation unit 40 is above a threshold, or actors with the highest calculated similarity, as actors to be proposed.

[0108] The decision unit 41 can also calculate the suitability of an actor for a character using a learning model that outputs a degree of suitability from information on multiple characteristic items of the character and information on multiple characteristic items of the actor, and then decide on an actor to be proposed based on this degree of suitability.

[0109] For example, the decision unit 41 determines the actor whose calculated appropriateness is above a threshold or the actor with the highest calculated appropriateness as the actor to be proposed. In this case, the decision unit 41 uses, for example, an appropriateness estimation model, which is a learning model that outputs a score indicating the appropriateness of the actor's casting based on the actor's information and the character's information, to determine the actor to be proposed.

[0110] The provision unit 42 proposes the proposal information to the adaptation planning company P by transmitting the proposal information, which includes information on the actors to be proposed, as determined by the decision unit 41, to a terminal device 2 such as the adaptation planning company P.

[0111] The proposal information includes, for example, information about the actor being proposed and information about the character that the actor is proposed to play. If there are multiple actors selected as candidates by the decision unit 41, the proposal information includes multiple pieces of information that associate the actor's information with the character's information.

[0112] [3.3.6. Learning Section 35] The learning unit 35 creates the appropriateness estimation model described above. For example, the learning unit 35 creates the appropriateness estimation model based on evaluations of actors. Evaluations of actors can be obtained, for example, from evaluations by fans of the original content, sales of other content (movies, dramas, plays, etc.), etc.

[0113] Learning Unit 35 creates a ground truth dataset that includes multiple data points: information on highly-rated actors who have received high ratings in other content in which they have appeared, and information on characters corresponding to highly-rated actors in the original content.

[0114] Furthermore, the learning unit 35 creates a dataset of incorrect answers that includes multiple pieces of data: information on low-rated actors (actors who received low ratings in other content in which they appeared) and information on characters corresponding to low-rated actors in the original content.

[0115] Then, the learning unit 35 creates an appropriateness estimation model using machine learning with the dataset created as described above. The appropriateness estimation model may be, but is not limited to, GBDT (Gradient Boosting Decision Tree), random forest, regression model, or neural network.

[0116] [4. Processing Procedure] Next, the procedure for information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Figure 6 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0117] As shown in Figure 6, the processing unit 12 of the information processing device 1 determines whether or not it has received content specification information from the terminal device 2 (step S10). If the processing unit 12 determines that it has received content specification information (step S10: Yes), it obtains information about the original content (step S11). Then, based on the information about the original content obtained in step S11, the processing unit 12 identifies the characteristics of each character appearing in the original content (step S12).

[0118] Furthermore, the processing unit 12 acquires actor information, including actor information (step S13). Then, based on the actor information acquired in step S13, the processing unit 12 identifies the characteristics of each actor (step S14).

[0119] Next, the processing unit 12 compares the characteristics of the characters identified in step S12 with the characteristics of the actors identified in step S14 for each combination of characters and actors, and determines the actors to be proposed based on the results of the comparison (step S15). Then, the processing unit 12 provides the proposal information, including the information of the actors determined to be proposed, to the adaptation planner P (step S16).

[0120] If the processing in step S16 is completed, or if it is determined that content specification information has not been received (step S10: No), the processing unit 12 determines whether or not it is time to terminate the operation (step S17). For example, the processing unit 12 determines that it is time to terminate the operation if the power to the information processing device 1 is turned off, or if it is determined that a termination operation has been performed by operating on an unillustrated control unit of the information processing device 1.

[0121] If the processing unit 12 determines that it is not yet time to terminate the operation (step S17: No), it proceeds to step S10. If it determines that it is time to terminate the operation (step S17: Yes), it terminates the process shown in Figure 6.

[0122] [5. Variations] In the example described above, the acquisition unit 30 analyzes the original content and acquires the results of this analysis as information about the characters in the original work. Furthermore, it can analyze the locations where the characters appear in the original content and acquire the results of this analysis as information about the locations where the characters appear. The locations where the characters appear are the places where they appear in the original content, and the information about the locations where the characters appear is information about the locations where the characters appear. The acquisition unit 30 stores the information about the locations where the characters appear in the storage unit 11 or acquires it from the storage unit 11.

[0123] The first identification unit 32 can identify the characteristics of a location based on the location information acquired by the acquisition unit 30. The characteristics of a location include, but are not limited to, topography (e.g., mountains, sea, valleys, plains, etc.), structures (e.g., buildings, bridges, roads, factories, schools, tunnels, etc.), and agricultural land.

[0124] Furthermore, the acquisition unit 30 acquires location candidate information, which is information about locations that have similar characteristics to the locations in the original content, from an external information processing device, and stores the acquired location candidate information in the storage unit 11. In addition, the acquisition unit 30 acquires posted information related to location candidates as posted location information from an external information processing device, and stores the acquired posted location information in the storage unit 11. Furthermore, the acquisition unit 30 acquires location candidate information and posted location information from the storage unit 11.

[0125] The decision unit 41 can determine potential filming locations that have similar characteristics to the location in question as proposed filming locations. For example, the decision unit 41 uses a known image generation AI (Artificial Intelligence) to create an image of the information indicating the characteristics of the location in question that was identified by the first identification unit 32. The decision unit 41 then searches for images similar to the image of the location in question using a similar image search, and can determine the location indicated by the searched similar image as a filming location.

[0126] Furthermore, the acquisition unit 30 acquires posted information regarding the locations where the original content appears from an external information processing device or the like as posted location information, and stores the acquired posted location information in the storage unit 11. The acquisition unit 30 then retrieves the posted location information from the storage unit 11. The posted location information is, for example, posted information by contributors in the adaptation region, but is not limited to this example; for example, it may be posted information by contributors in the region where the original content was provided.

[0127] The first identification unit 32 identifies the characteristics and impression of a location based on the posted location information. In this case as well, the decision unit 41 uses a known image generation AI to create an image of the information indicating the characteristics and impression of the location identified by the first identification unit 32. The decision unit 41 then searches for images similar to the image of the location using similar image search, and can determine the location indicated by the searched similar image as the filming location.

[0128] [6. Hardware Configuration] The information processing device 1 according to the above embodiment is implemented by a computer 80 having a configuration such as that shown in Figure 7. Figure 7 is a hardware configuration diagram showing an example of a computer 80 that implements the functions of the information processing device 1 according to the embodiment. The computer 80 has a CPU 81, RAM 82, ROM (Read Only Memory) 83, HDD (Hard Disk Drive) 84, communication interface (I / F) 85, input / output interface (I / F) 86, and media interface (I / F) 87.

[0129] The CPU 81 operates based on programs stored in the ROM 83 or HDD 84, and controls various parts of the system. The ROM 83 stores boot programs executed by the CPU 81 when the computer 80 starts up, as well as programs that depend on the computer 80's hardware.

[0130] HDD84 stores programs executed by CPU81 and data used by such programs. The communication interface85 receives data from other devices via network N (see Figure 2) and sends it to CPU81, and transmits the data generated by CPU81 to other devices via network N.

[0131] The CPU 81 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input / output interface 86. The CPU 81 acquires data from input devices via the input / output interface 86. The CPU 81 also outputs data it has generated to output devices via the input / output interface 86.

[0132] The media interface 87 reads a program or data stored in the recording medium 88 and provides it to the CPU 81 via the RAM 82. The CPU 81 loads the program from the recording medium 88 onto the RAM 82 via the media interface 87 and executes the loaded program. The recording medium 88 can be, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or 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.

[0133] For example, when computer 80 functions as an information processing device 1 according to the embodiment, the CPU 81 of computer 80 realizes the functions of processing unit 12 by executing a program loaded on RAM 82. Also, data from storage unit 11 is stored in HDD 84. The CPU 81 of computer 80 reads and executes these programs from recording medium 88, but as another example, these programs may be obtained from other devices via network N.

[0134] [7. Other] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0135] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0136] For example, the information processing device 1 described above may be implemented using multiple server computers, and the configuration can be flexibly changed, such as by calling external platforms via APIs or network computing depending on the function.

[0137] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent.

[0138] [8. Effects] As described above, the information processing device 1 according to this embodiment comprises a first identification unit 32, a second identification unit 33, and a suggestion unit 34. The first identification unit 32 identifies the characteristics of characters appearing in the source content. The second identification unit 33 identifies the characteristics of actors based on actor information, including information about actors. The suggestion unit 34 proposes actors to play the characters in the adapted content, which is the content that adapts the source content, based on the comparison result between the characteristics of the characters identified by the first identification unit 32 and the characteristics of the actors identified by the second identification unit 33. As a result, the information processing device 1 can appropriately determine the actors to play the characters in the content.

[0139] Furthermore, the first identification unit 32 identifies at least one of the character's physical characteristics, psychological characteristics, and impressionistic characteristics as the character's characteristics. This allows the information processing device 1 to more appropriately determine the actor who will play the character in the content.

[0140] Furthermore, the first identification unit 32 identifies the physical and psychological characteristics of the characters based on the content. This allows the information processing device 1 to more appropriately determine the actors who will play the characters in the content.

[0141] Furthermore, the information processing device 1 includes an acquisition unit 30 that acquires posting information about characters on social networking services, and the first identification unit 32 identifies the distinctive characteristics of the characters based on the posting information acquired by the acquisition unit 30. This allows the information processing device 1 to more appropriately determine the actors who will play the characters in the content.

[0142] Furthermore, the second identification unit 33 identifies at least one of the actor's physical characteristics, psychological characteristics, and impressionistic characteristics as the actor's characteristics. This allows the information processing device 1 to more appropriately determine which actor will play which character in the content.

[0143] Furthermore, the actor information includes actor-related information, which is information about the actor, and the second identification unit 33 identifies the actor's physical and psychological characteristics based on the actor-related information. This allows the information processing device 1 to more appropriately determine which actor will play which character in the content.

[0144] Furthermore, the actor information includes information posted about the actor on social networking services, and the second identification unit 33 identifies the actor's distinctive characteristics based on the posted information about the actor. This allows the information processing device 1 to more appropriately determine which actor will play which character in the content.

[0145] Furthermore, the proposal unit 34 proposes actors to play the characters in the adapted content based on the comparison results between the characters and actors for at least one of the following characteristics: physical characteristics, psychological characteristics, and impression characteristics. This allows the information processing device 1 to more appropriately determine the actors to play the characters in the content.

[0146] Furthermore, the information processing device 1 includes a proposal unit 34 which comprises a calculation unit 40 that calculates the similarity between the characteristics of the characters and the characteristics of the actors as a comparison result, and a determination unit 41 that determines the actors who will play the characters in the adapted content based on the similarity calculated by the calculation unit 40. As a result, the information processing device 1 can more appropriately determine the actors who will play the characters in the content.

[0147] Although embodiments of the present application have been described in detail based on the drawings, these are illustrative examples, and the present invention can be implemented in various other forms, including those described in the disclosure section of the invention, based on the knowledge of those skilled in the art.

[0148] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, the acquisition unit can be replaced with acquisition means or acquisition circuit. [Explanation of Symbols]

[0149] 1. Information Processing Device 2 Terminal devices 10 Communications Department 11 Storage section 12 Processing Units 20 Character information storage section 21 Actor Information Memory Department 30 Acquisition Department 31 Reception Department 32 First Specific Part 33 Second Specific Part 34 Proposal Department 35. Learning Department 40 Calculation Unit 41 Decision Section 42 Providing Department 100 Information Processing Systems

Claims

1. The first identification section identifies the characteristics of the characters appearing in the source content from which the adaptation is based, A second identification unit identifies the characteristics of the actor based on actor information, which includes information about the actor. The system comprises a proposal unit that proposes an actor to play the character in an adapted content, which is content that adapts the content, based on the characteristics of the character identified by the first identification unit and the characteristics of the actor identified by the second identification unit, The aforementioned proposal section is, Using a machine learning model called an appropriateness estimation model, which outputs the appropriateness of an actor's casting based on actor information and character information, the appropriateness of the actor for the character is calculated, and based on the calculated appropriateness, the actor who will play the character in the adapted content is determined. This model is created using a ground truth dataset that includes multiple data points of highly-rated actors (actors who were highly rated in other content) and character information corresponding to the highly-rated actors in the source content from which the other content is adapted, and an incorrect truth dataset that includes multiple data points of low-rated actors (actors who were poorly rated in other content) and character information corresponding to the low-rated actors in the source content from which the other content is adapted. An information processing device characterized by the following:

2. The first specified part is, Based on specific words obtained by morphological analysis of strings contained in the source content, at least one of the physical and psychological characteristics of the character is identified as a characteristic of the character. The information processing apparatus according to feature 1.

3. The characteristics of the characters are, Including the physical and psychological characteristics of the aforementioned characters, The first specified part is, The physical characteristics of the character are identified by pattern matching between the character's image and body shape pattern and face shape pattern included in the source content, and the psychological characteristics of the character are identified by pattern matching between the character's image and facial expression pattern included in the source content. The information processing apparatus according to feature 1.

4. It includes an acquisition unit that acquires information posted to social networking services regarding the aforementioned characters, The characteristics of the aforementioned characters are, Including the memorable characteristics of the aforementioned characters, The first specified part is, Based on specific words obtained by morphological analysis of the strings contained in the posted information acquired by the acquisition unit, the impressionistic characteristics of the characters are identified. The information processing apparatus according to feature 1.

5. The second specified part is, Based on specific words obtained by morphological analysis of the strings contained in the actor information, at least one of the actor's physical and psychological characteristics is identified as the actor's characteristic. The information processing apparatus according to any one of claims 1 to 4.

6. The aforementioned actor's characteristics are, Including the physical and psychological characteristics of the aforementioned actor, The second specified part is, The actor's physical characteristics are identified by pattern matching between the actor's image included in the actor information and his body shape and face shape patterns, and the actor's psychological characteristics are identified by pattern matching between the actor's image included in the actor information and his facial expression patterns. The information processing apparatus according to any one of claims 1 to 4.

7. The characteristics of the actor are: Including the distinctive features of the aforementioned actor, The aforementioned actor information is, This includes information posted on social networking services concerning the aforementioned actor, The second specified part is, Based on specific words obtained by morphological analysis of strings contained in the posted information relating to the actor, the actor's distinctive characteristics are identified. The information processing apparatus according to any one of claims 1 to 4.

8. The first specific part is, Identify the characteristics of the locations that appear in the aforementioned source content, The aforementioned proposal section is, The first identification unit identifies information indicating the characteristics of the location where the actor appears, which is then converted into an image using an image generation AI. Similar images to the image of the location are searched for using a similar image search, and the locations indicated by the searched similar images are proposed as filming locations along with the actor. The information processing apparatus according to any one of claims 1 to 4.

9. A method of information processing performed by a computer, The first step is to identify the characteristics of the characters appearing in the source content from which the adaptation will be made, A second identification step involves identifying the characteristics of the actor based on actor information, which includes information about the actor. The process includes a proposal step, which proposes an actor to play the character in an adapted content that adapts the content, based on the characteristics of the character identified by the first identification step and the characteristics of the actor identified by the second identification step, The proposed process is as follows: Using a machine learning model called an appropriateness estimation model, which outputs the appropriateness of an actor's casting based on actor information and character information, the appropriateness of the actor for the character is calculated, and based on the calculated appropriateness, the actor who will play the character in the adapted content is determined. This model is created using a ground truth dataset that includes multiple data points of highly-rated actors (actors who were highly rated in other content) and character information corresponding to the highly-rated actors in the source content from which the other content is adapted, and an incorrect truth dataset that includes multiple data points of low-rated actors (actors who were poorly rated in other content) and character information corresponding to the low-rated actors in the source content from which the other content is adapted. An information processing method characterized by the following:

10. The first identification step involves identifying the characteristics of the characters appearing in the source content from which the adaptation will be made, A second identification procedure for identifying the characteristics of the actor based on actor information including information about the actor, A computer is instructed to execute a proposal procedure that proposes an actor to play the character in an adapted content, which is content that adapts the content, based on the characteristics of the character identified by the first identification procedure and the characteristics of the actor identified by the second identification procedure. The proposed procedure is, Using a machine learning model called an appropriateness estimation model, which outputs the appropriateness of an actor's casting based on actor information and character information, the appropriateness of the actor for the character is calculated, and based on the calculated appropriateness, the actor who will play the character in the adapted content is determined. This model is created using a ground truth dataset that includes multiple data points of highly-rated actors (actors who were highly rated in other content) and character information corresponding to the highly-rated actors in the source content from which the other content is adapted, and an incorrect truth dataset that includes multiple data points of low-rated actors (actors who were poorly rated in other content) and character information corresponding to the low-rated actors in the source content from which the other content is adapted. An information processing program characterized by the following features.

Citation Information

Patent Citations

  • Casting support work system

    JP2005044258A

  • Information analyzing apparatus, information analysis method, and information analysis program

    JP2017117130A

  • Casting apparatus, method and program

    JP2022184465A