Information processing device, information processing method and program

The information processing apparatus addresses the challenge of homogenizing character setting information in large-scale worldviews by generating default settings and prompts based on user-defined worldviews, resulting in consistent and high-quality character settings across multiple characters.

JP2025080681APending Publication Date: 2025-05-26SONY GROUP CORP
View PDF 1 Cites 0 Cited by

Patent Information

Application Number
JP2023193992
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-11-14
Publication Date
2025-05-26

AI Technical Summary

Technical Problem

In large-scale worldviews like the metaverse, designing a large number of characters using large language models makes it difficult to homogenize the amount and quality of setting information for all characters.

Method used

An information processing apparatus and method that acquires a worldview as user setting information, generates default settings for character setting items and contents, and creates prompts for character setting based on these default settings, ensuring homogenization of character setting information.

Benefits of technology

The solution enables homogeneous character setting according to the worldview of the virtual world, ensuring consistency and quality in character setting information across multiple characters.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025080681000001_ABST
    Figure 2025080681000001_ABST
Patent Text Reader

Abstract

To provide an information processing device, an information processing method and a program capable of equalizing the setting information on characters.SOLUTION: An information processing device includes a UI display unit, a default setting generating unit and a generative model instruction generating unit. The UI display unit obtains, as user setting information, the interpretation of the world set for a virtual space. The default setting generating unit generates, based on the user setting information, set items on a target character and the default setting for the details of the item both applied in the virtual space. The generative model instruction generating unit generates, based on the default setting, a prompt to execute a character setting for the target character.SELECTED DRAWING: Figure 1
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 a program.

Background Art

[0002] When creating characters that appear in virtual spaces such as stories like novels, games, and the metaverse, designers create characters in consideration of the worldview set in the virtual space. Recently, by using large language models and inputting the worldview as prompt information, character setting information has also been generated.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a large-scale worldview such as the metaverse, the number of necessary characters also increases. When designing a large number of characters using a large language model, it is difficult to homogenize the amount and quality of setting information for all characters.

[0005] Therefore, the present disclosure proposes an information processing apparatus, an information processing method, and a program capable of homogenizing character setting information.

Means for Solving the Problems

[0006] According to the present disclosure, there is provided an information processing apparatus including a UI display unit that acquires a worldview set in a virtual space as user setting information, a default setting generation unit that generates a default setting regarding setting items and item contents of a target character applied to the virtual space based on the user setting information, and a generation model instruction creation unit that generates a prompt for performing character setting of the target character based on the default setting. Further, according to the present disclosure, there are provided an information processing method in which the information processing of the information processing apparatus is executed by a computer, and a program that causes a computer to realize the information processing of the information processing apparatus.

Brief Description of Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Embodiments for Carrying Out the Invention

[0008] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the following embodiments, the same parts are denoted by the same reference numerals, and redundant descriptions are omitted.

[0009] Note that the description will be given in the following order. [1. System configuration example] [2. UI display example] [3. Prompt examples] [4. Adjustment examples of setting items] [5. Processing flow] [6. Hardware configuration example] [7. Effects]

[0010] [1. System configuration example] FIG. 1 is a diagram showing an example of the system configuration of a character generation system.

[0011] The character generation system generates characters that appear in virtual spaces such as stories, games, and the metaverse. Processing related to settings (character settings) such as the name, gender, hobby, age, occupation, and personality of the character is performed by the information processing apparatus 1. For example, the information processing apparatus 1 includes a UI display unit 10, a default setting generation unit 20, a setting information management unit 30, a generation model instruction creation unit 40, a character setting generation unit 50, a similarity calculation unit 60, and an existing character database 70. Hereinafter, a character to be newly generated in this character generation system may be described as a "target character".

[0012] The UI display unit 10 receives user input related to character settings and displays various types of information. The user inputs, edits, and modifies setting information via the UI display unit 10. For example, the UI display unit 10 acquires the worldview set in the virtual space as user setting information. The worldview includes the background of the story and the background of the era. The UI display unit 10 displays the user setting information input by the user and the result of character setting (character setting information) performed based on the user setting information. The character setting information can be output as text information.

[0013] The setting information management unit 30 holds a list of setting items and item contents for the target character applied to the virtual space (see FIG. 8). Examples of setting items include "name", "gender", "age", "constellation", "blood type", "occupation", "personality", "hobby", "goal", "tone of voice", "race", "skill", "special move", etc. Examples of item contents for the "name" item include "Suzuki", "Sato", "Yamada", "Kaien", "Sarah", etc.

[0014] The default setting generation unit 20 acquires setting items and item contents that conform to the user setting information (worldview) from the setting information management unit 30. The default setting generation unit 20 generates default settings regarding the setting items and item contents for the target character applied to the virtual space based on the user setting information. For example, when a worldview close to the real world is input, general setting items and item contents that conform to the real world are selected. In a virtual world where myths and magic appear, "special move" may be selected as a setting item, or fictional races such as elves and dwarves may be selected as item contents.

[0015] The generation model instruction creation unit 40 acquires the customized setting items and item contents based on the user setting information as the default settings. The generation model instruction creation unit 40 generates a prompt for character setting of the target character based on the default settings generated based on the user setting information. A prompt means an instruction sentence for inputting into the character setting generation model which is a large language model. The character setting generation unit 50 generates character setting information corresponding to the prompt using the character setting generation model.

[0016] The existing character database 70 holds the feature information of the existing character group. The existing character means a character existing in the world at the time when the setting of a newly generated target character is started. The feature information means, for example, what is obtained by quantifying character setting information into a vector (feature vector). The user can recognize the existence of a character similar to the target character by comparing the feature information of the target character with the existing character database 70.

[0017] For example, the existing character group includes a past character group and a public character group. The past character group means a character group generated based on other user setting information before the target character is generated. The public character group means a character group publicly available through existing media (such as comics, anime, novels, etc.). The data of the public character group may be automatically collected from the web or manually input by the user.

[0018] The similarity calculation unit 60 quantifies the character setting information of the newly generated target character based on the prompt. The similarity calculation unit 60 compares the feature information of the target character obtained by the quantification with the feature information of the existing character group to obtain the similarity between the target character and the existing character group. In the calculation of similarity, for example, the cosine distance of the feature vector is used.

[0019] Feature quantization is performed for both the setting items and the item contents. For example, in the calculation of similarity, when two character settings to be compared include the same setting item, the item contents of the matching setting items are compared. If there are no matching setting items, the similarity of the expressions of the setting items is calculated, and based on the calculation result, similar setting items are considered. As a result of the consideration, when the two character settings to be compared include setting items that meet the similarity criteria, the item contents of the most similar setting items are compared. If there are no setting items that meet the similarity criteria, the item contents of that setting item are not used in the similarity calculation.

[0020] The similarity calculation unit 60 registers the feature information of the target character in the existing character database 70. The registered feature information is used as the feature information of past characters when setting the character of another target character hereafter. The similarity calculation unit 60 acquires the data of public characters from the Web and the user. The similarity calculation unit 60 extracts the feature information from the acquired data and registers it in the existing character database 70.

[0021] [2.UI Display Example] Hereinafter, the display example of the UI display unit 10 will be described with reference to FIGS. 2 to 5.

[0022] FIG. 2 is a diagram showing an input example of user setting information. Input fields and buttons for inputting various information are displayed on the input screen. In the example of FIG. 2, an input field C1 for inputting the worldview and an input field C2 for inputting a character example are displayed in the center of the input screen.

[0023] The worldview is essential information that determines the direction of character setting. The user is required to input the worldview as user setting information in the input field C1. When the generate execution button B2 is pressed without the worldview being input, the UI display unit 10 can notify the user to prompt for input.

[0024] The character example defines information such as the name and gender of the target character. In the input field C2, for each target character, setting items and item contents (examples) conforming to the worldview are input. The input can be automatically performed by using the default settings. The user can manually add and delete setting items and modify the item contents as needed. The setting items can be added and deleted by the "+" button and the "-" button.

[0025] The UI display unit 10 displays, for example, at the lower part of the input screen, a switch button B1 for using the default settings, an input field C4 for the number of generated target characters, and a generation execution button B2. The switch button B1 is a button for switching whether to apply the default settings. The generation execution button B2 is a button for executing the character setting.

[0026] When the user turns on the switch button B1 (uses the default settings) and presses the generation execution button B2, information on the number of generated target characters corresponding to the input worldview is automatically input into the input field C2. The user can manually add and delete setting items and modify the item contents as needed.

[0027] When the user turns off the switch button B1 (does not use the default settings), the user needs to manually input the setting items and item contents. If the prompt generation work is performed without any input, the generated prompt will become unstable. Therefore, when the default settings are not applied (switch button B1: OFF) and the user does not select setting items or input item contents, the UI display unit 10 can give a notice to prompt the input or prompt the use of the default settings.

[0028] When the user makes a manual input, they can make settings relatively freely without being restricted by the worldview. The examples that can be input as item contents are not limited to one. For non-exclusive examples, multiple examples can be set for one target character. For example, for the setting item of "hobby", three examples of "drinking party", "gambling", and "horseback riding" can be input as the item contents.

[0029] The user can add or delete target characters by operating the "+" button or "-" button. The user can set different setting items for character settings for each target character. For example, for the first target character, "name", "gender", and "hobby" can be set as the setting items, and for the second target character, "name" and "tone" can be set as the setting items.

[0030] In this case, the setting items of each character setting are processed by aggregation. Through the aggregation process, the default setting generation unit 20 can commonly apply the setting items applied to a certain target character to other target characters generated based on the same user setting information.

[0031] For example, assume that "name", "gender", "age", "occupation", "personality", "past experience", "goal", "routine work", and "tone" are selected as the setting items of the default setting. In this case, when the setting item of "hobby" is added to a certain target character, the setting item of "hobby" is also added to all other target characters generated based on the same user setting information. Thereby, combined with the default setting items, the result can be obtained.

[0032] The UI display unit 10 can display a result confirmation button B3 and a download button B4 at the lower part of the input screen. The result confirmation button B3 is a button for displaying the character setting information obtained in the character setting. The download button B4 is a button for downloading the character setting information. The user can obtain the character setting information as an output file by pressing the download button B4. FIG. 11 is a diagram showing an example of the character setting recorded in the output file. The character setting in FIG. 11 is generated based on the input information in FIG. 2.

[0033] In the part where a plurality of cases are set, there may be a sense of incongruity in the content. For example, this applies to a case where two cases, "Ray" and "Yamada", are set for the setting item "Name", and two cases, "female" and "male", are set for the setting item "Gender".

[0034] In this setting, two contradictory properties, male and female, are assigned to the same target character. Such a contradiction is also reflected in the automatically generated character setting. As a result, as an output setting, a situation occurs where a contradictory target character with "Name" being "Kaigen" and "Suzuki" and "Gender" being "male" and "female" is generated. If the output setting is not what the user intends, the user can correct the input cases and regenerate the character setting.

[0035] FIG. 3 is a diagram showing an example of the confirmation screen of the character setting information. In the example of FIG. 3, the character setting information is displayed at the upper part of the confirmation screen. The character setting information of each character is displayed in a list on the browsing screen D1. Analysis information regarding the character setting is displayed at the lower part of the confirmation screen. For example, the analysis information includes information regarding the distribution of the character setting and similar characters.

[0036] In the example of FIG. 3, as the distribution of character settings, the ratio of characters for each item content is displayed. The UI display unit 10 classifies a plurality of target characters generated based on the same user setting information for each item content. The UI display unit 10 displays a graph D2 indicating the ratio for each item content as the distribution of character settings. For example, when the user inputs "occupation" in the input field C5, the UI display unit 10 displays the ratio of target characters by occupation. The user can check the balance of the characters based on the distribution of character settings.

[0037] On the confirmation screen, a similarity confirmation button B5 for displaying similar characters can be displayed. For example, the user can specify a target character to be the subject of similarity analysis within the browsing screen D1. When the user specifies a target character and presses the similarity confirmation button B5, the UI display unit 10 displays one or more existing characters selected in descending order of similarity to the target character among the plurality of existing characters included in the existing character group as similar characters.

[0038] The similar characters are displayed in the similar character list D3. The UI display unit 10 can display one or more similar characters that are more similar than the allowable level to the target character in the similar character list D3 in a distinguishable manner from other similar characters. The distinguishable manner means indicating by color coding, surrounding frames, etc. By displaying with color coding, etc., the user can be made aware of the existence of existing characters that are overly similar.

[0039] The allowable level can be arbitrarily set by the system developer. For example, from the perspective of copyright, a level that does not remind of famous characters such as comics and anime can be set as the allowable level. Regarding the determination of similarity between characters generated within the same game, a level at which no problems occur in the progress of the game can be set as the allowable level.

[0040] The generated character setting information can be manually modified by the user. The modification is carried out by the feedback button B6. For example, when the user selects a specific target character in the browsing screen D1 and presses the feedback button B6, a feedback screen (see Fig. 5) is displayed. The user can edit the character setting information using the feedback screen.

[0041] Fig. 4 is a diagram showing an example of the distribution of character settings.

[0042] When the user enters "occupation" in the input field C5, the ratio of target characters by occupation is shown in the graph D2. When the user presses the "list" button, a list of the occupations of the target characters is displayed in the distribution list D4. When a specific occupation in the graph D2 or a specific occupation in the distribution list D4 (in the example of Fig. 4, "blacksmith") is selected, a list of the target characters with the selected occupation and their character setting information is displayed on the browsing screen D5.

[0043] Similar processing is also applicable to other setting items. For example, when "goal" is entered in the input field C5, the ratio of target characters by goal is shown in the graph D2. When the item content is described on a word basis, the words used can be directly displayed as data labels. When the item content is expressed in a sentence or the number of characters in the item content is large, a summary expression can be used. For example, the UI display unit 10 can summarize the item content exceeding the setting standard and display the summarized item content as a data label. The setting standard can be arbitrarily set by the system developer.

[0044] On the confirmation screen, as analysis information, it is also possible to display the classification result of the target characters according to the similarity of the character settings. For example, when the user inputs "similarity" in input field C5, input field C6 is displayed on the confirmation screen. The user inputs in input field C6 the number of groups into which the target characters are to be classified. When the user inputs the number of groups in input field C6, the similarity calculation unit 60 calculates a threshold value that serves as a criterion for judging the similarity between the target characters based on the number of groups. The similarity calculation unit 60 classifies a plurality of target characters generated based on the same user setting information based on the similarity of the feature information. The UI display unit 10 displays the classification result as the distribution of the character settings.

[0045] The classification result is displayed in graph D2. The UI display unit 10 can display the details of each group on a browsing screen D5 or the like. For example, when the user selects a specific group within graph D2, or selects a specific group within the distribution list D4 obtained by pressing the list button, a list of the target characters belonging to the selected group and their character setting information is displayed on the browsing screen D5.

[0046] Based on the classification result, it is possible to check whether there are similar settings among the generated character settings. For example, when the number of groups is set to the same number as the number of generated target characters, the number of target characters belonging to each group is one, that is, all target characters are displayed as independent characters. When the number of groups is set to a number one less than the number of generated characters, two target characters with similar settings are included in one group. In this way, it is possible to check for similar character settings.

[0047] Note that when the number of groups is set to a number larger than the number of generated target characters, the UI display unit 10 corrects the number of groups to a value that matches the number of generated characters, and feedbacks to the user that the maximum value that can be set as the number of groups is limited to the number of generated characters.

[0048] FIG. 5 is a diagram showing an example of a feedback screen in character settings.

[0049] When the expected results cannot be obtained when using the default settings, feedback can be provided. By pressing the feedback button B6 on the confirmation screen, a feedback screen as shown in FIG. 5 is displayed. The user can add and delete setting items using the “+” button and the “-” button. The UI display unit 10 sends the content of the feedback to the setting information management unit 30.

[0050] The user controls the character settings by specifying unnecessary setting items or unwanted item contents. By excluding unwanted setting items and item contents from the prompt, these pieces of information will not be reflected in the character settings.

[0051] [3. Prompt Examples] FIG. 6 is a diagram showing an example of a prompt.

[0052] The generation model instruction creation unit 40 creates a prompt for sending to the character setting generation unit 50. The prompt is composed of a setting part that explains what task the character setting generation model is desired to execute, an example part that serves as a sample of the output form, and a process part that indicates which part the character setting generation model is desired to create.

[0053] The worldview applied to the virtual space requires user input. The task to be executed is automatically set by the UI display unit 10. The generation model instruction creation unit 40 creates a setting part in which the necessary configuration information is described based on the user input information sent from the UI display unit 10. The generation model instruction creation unit 40 obtains information considered to be minimally required for character settings from the default setting generation unit 20 and incorporates the content into the setting part and the example part.

[0054] When there is an overlap between the user's input information and the information from the default setting generation unit 20, the generation model instruction creation unit 40 validates the user's input information. When the UI display unit 10 is set not to use the default settings, the generation model instruction creation unit 40 does not reflect the content from the default setting generation unit 20. The process unit is automatically set by the UI display unit 10.

[0055] [4. Example of Adjusting Setting Items] FIG. 7 is a diagram showing an example of setting items used in the default settings. FIGS. 8 and 9 are diagrams showing examples of default settings generated based on user setting information.

[0056] The setting information management unit 30 stores a list of setting items and item contents used in the default settings. In the example of FIG. 7, the setting items include "Name", "Gender", "Occupation", "Personality", "Goal", but the setting items are not limited to these. Other setting items such as "Age", "Zodiac Sign", "Blood Type", "Hobby", "Tone of Voice", "Race", "Skills", "Special Skill", etc. may be registered.

[0057] For each setting item, various cases are registered as the item content. In the example of FIG. 7, for the "Name" case, "Title (name used in address)", "Surname", "Given Name", "Full Name", etc. are registered. For the "Gender" case, "Male", "Female", "None", "Unknown", etc. are registered. For the "Occupation" case, "Villager", "Farmer", "Merchant", "Warrior", etc. are registered. For the "Personality" case, "Kind", "Quiet", "Warlike", etc. are registered. For the "Goal" case, "Sell one's own name", "Create a world where everyone is happy", etc. are registered.

[0058] The UI display unit 10 acquires information from the user regarding the worldview of the virtual space. The default setting generation unit 20 extracts setting items and item details along with the worldview from the setting information management unit 30. The default setting generation unit 20 generates default settings based on the extracted setting items and item details. When there is user feedback, the default setting generation unit 20 reflects the content of the feedback in the default settings.

[0059] In the example of FIG. 8, a worldview closer to the real world where company employees and the like appear is input. Therefore, the default setting generation unit 20 sets the setting items to those in line with the real world such as "blood type" and "astrological sign", and also sets the item details to those commonly seen in the real world such as "Yamada" and "win the lottery". For "occupation" as well, job types existing in the real world such as company employee, security guard, and driver are selected as candidates.

[0060] In the example of FIG. 9, a worldview closer to the virtual world where fairies and the like appear is input. Therefore, as setting items, items closer to the virtual world such as "race", "skill", and "ultimate technique" are incorporated. As examples, those commonly seen in the virtual world such as "poplar", "fairy", "find traveling companions", and "wind magic" are used. For "occupation" as well, candidates such as "magician", "warrior", and "hero" are selected.

[0061] For example, the default setting generation unit 20 uses a mathematical model to obtain the appearance probabilities of each setting item and each item detail for the set worldview. The mathematical model can use countless contents such as comics, animations, and novels in the world as learning data to learn in what kind of worldview, what kind of setting items and item details appear with what kind of appearance probabilities.

[0062] For calculating the appearance probability, methods such as TF-IDF (Term Frequency - Inverse Document Frequency) are used. The default setting generation unit 20 calculates the appearance frequency of words existing in the list of setting items and item contents, and rearranges the words in the order of the words with high frequency. Then, the default setting generation unit 20 selects, for example, the top 5 from the ones with high appearance frequency in the setting items as candidates, and for the item contents, randomly selects 1 from the top 10 as a candidate.

[0063] FIG. 10 is a diagram showing an example of ranking setting items and item contents according to the world view and the like. On the left side of FIG. 10, an example of the data held by the setting information management unit 30 is shown. On the right side of FIG. 10, an example of the arrangement order of the setting items and item contents when the world view closer to the virtual world shown in FIG. 2 is input is shown. For the setting items, the ones higher in the list have higher priority as candidates (item candidates) for the setting items. For the item contents, the ones on the right side of the list have higher priority as candidates (content candidates) for the item contents. As can be seen from FIG. 10, the setting items and item contents in accordance with the world view are preferentially used.

[0064] The content used for generating the character setting can be changed for each generation. Thereby, the possibility of creating variations in the character setting can be improved. For example, the default setting generation unit 20 can take the form of randomly reselecting one selected from the top 10 candidates again. Setting items such as "tone", "experience", and "routine work" are used in the character setting regardless of the appearance frequency. It is also possible to set other setting items that are always used.

[0065] [5. Processing Flow] FIG. 12 is a diagram showing an example of a processing flow related to the character setting.

[0066] The user sets the worldview applied to the virtual space as user setting information (step S1). If there are setting items for the target character desired by the user (step S2: Yes), the user turns on the switching button B1 (using the default settings) and manually sets the desired setting items and item contents (step S3). After the user has set all the desired setting items and item contents, the user presses the generation execution button B2. Thereby, the generation model instruction creation unit 40 creates a prompt for using the character setting generation model based on the setting items and item contents set by the user (step S4).

[0067] If there are no setting items for the target character desired by the user (step S2: No), the user turns on the switching button B1 (using the default settings) and presses the generation execution button B2. Thereby, the default setting generation unit 20 generates a default setting having setting items and item contents that conform to the user setting information. The generation model instruction creation unit 40 creates a prompt for using the character setting generation model based on the default setting (step S4).

[0068] When the prompt is generated by the generation model instruction creation unit 40, the character setting generation unit 50 applies the prompt to the character setting generation model to perform character setting (step S5).

[0069] If the user provides feedback on the generated character setting (step S6: Yes), the user presses the feedback button B6 to display the feedback screen. The user edits the character setting information on the feedback screen (step S7). If the user wants to modify the character setting (step S8: Yes), the process returns to step S1 and the above-described processing is repeated. If the user does not want to modify the character setting (step S8: No), the character setting process ends.

[0070] If the user does not provide feedback on the generated character settings (step S6: No), the process proceeds to step S8, where the user determines whether character settings need to be modified. If the user wants to modify the character settings (step S8: Yes), the process returns to step S1 and repeats the above-described processing. If the user does not want to modify the character settings (step S8: No), the processing of the character settings ends.

[0071] [6. Hardware Configuration Example] FIG. 13 is a diagram showing an example of the hardware configuration of the information processing apparatus 1.

[0072] The information processing of the information processing apparatus 1 is realized, for example, by a computer 1000. The computer 1000 includes a CPU (Central Processing Unit) 1100, a RAM (Random Access Memory) 1200, a ROM (Read Only Memory) 1300, an HDD (Hard Disk Drive) 1400, a communication interface 1500, and an input / output interface 1600. Each part of the computer 1000 is connected by a bus 1050.

[0073] The CPU 1100 operates based on a program (program data 1450) stored in the ROM 1300 or the HDD 1400 and controls each part. For example, the CPU 1100 expands the program stored in the ROM 1300 or the HDD 1400 into the RAM 1200 and executes processing corresponding to various programs.

[0074] The ROM 1300 stores a boot program such as BIOS (Basic Input Output System) executed by the CPU 1100 when the computer 1000 is started, and programs dependent on the hardware of the computer 1000.

[0075] The HDD 1400 is a computer-readable non-transitory recording medium that non-transitorily records programs executed by the CPU 1100, data used by such programs, and the like. Specifically, the HDD 1400 is a recording medium that records an information processing program according to an embodiment as an example of the program data 1450.

[0076] The communication interface 1500 is an interface for the computer 1000 to connect to an external network 1550 (for example, the Internet). For example, the CPU 1100 receives data from other devices or transmits data generated by the CPU 1100 to other devices via the communication interface 1500.

[0077] The input / output interface 1600 is an interface for connecting the input / output device 1650 and the computer 1000. For example, the CPU 1100 receives data from input devices such as a keyboard and a mouse via the input / output interface 1600. Also, the CPU 1100 transmits data to output devices such as a display device, a speaker, and a printer via the input / output interface 1600. Further, the input / output interface 1600 may function as a media interface that reads programs and the like recorded on a predetermined recording medium (media). The media is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0078] For example, when the computer 1000 functions as the information processing apparatus 1 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the respective units described above by executing an information processing program loaded on the RAM 1200. Further, the HDD 1400 stores the information processing program, various models, and various data according to the present disclosure. Note that the CPU 1100 reads and executes the program data 1450 from the HDD 1400, but as another example, these programs may be acquired from other devices via the external network 1550.

[0079] [7. Effects] The information processing apparatus 1 includes a UI display unit 10, a default setting generation unit 20, and a generation model instruction creation unit 40. The UI display unit 10 acquires the worldview set in the virtual space as user setting information. The default setting generation unit 20 generates default settings regarding setting items and item contents of the target character applied to the virtual space based on the user setting information. The generation model instruction creation unit 40 generates a prompt for performing character setting of the target character based on the default setting. In the information processing method of the present disclosure, the processing of the information processing apparatus 1 is executed by the computer 1000. The program of the present disclosure causes the computer 1000 to realize the processing of the information processing apparatus 1.

[0080] According to this configuration, it is possible to perform homogeneous character setting according to the worldview of the virtual world.

[0081] The information processing apparatus 1 includes an existing character database 70 and a similarity calculation unit 60. The existing character database 70 holds feature information of an existing character group. The similarity calculation unit 60 compares the feature information of the newly generated target character based on the prompt with the feature information of the existing character group, and acquires the similarity between the target character and the existing character group.

[0082] According to this configuration, it is possible to recognize the existence of an existing character similar to the target character and its similarity.

[0083] The existing character group includes a past character group and a public character group. The past character group is a character group generated based on other user setting information before the target character is generated. The public character group is a character group that has been published through existing media.

[0084] According to this configuration, similarities with various existing characters can be recognized.

[0085] The UI display unit 10 displays, as similar characters, one or more existing characters selected in descending order of similarity to the target character among the plurality of existing characters included in the existing character group.

[0086] According to this configuration, existing characters with a high similarity to the target character can be recognized.

[0087] The UI display unit 10 displays one or more similar characters that are overly similar to the target character in a manner distinguishable from other similar characters.

[0088] According to this configuration, the existence of existing characters that are overly similar to the target character can be recognized.

[0089] The similarity calculation unit 60 classifies a plurality of target characters generated based on the same user setting information based on the similarity of feature information. The UI display unit 10 displays the classification result as a distribution of character settings.

[0090] According to this configuration, it becomes easier to recognize the overall image of the virtual world based on the classified feature information.

[0091] The default setting generation unit 20 applies the setting items applied to a certain target character uniformly to other target characters generated based on the same user setting information.

[0092] According to this configuration, the setting information of the target character can be homogenized.

[0093] The UI display unit 10 displays a switching button for switching whether to apply the default setting.

[0094] According to this configuration, the degree of freedom in character setting can be increased.

[0095] The UI display unit 10 gives a notification when the default setting is not applied and the user does not select a setting item or input the item content.

[0096] According to this configuration, it is possible to suppress the generation of an unstable target character due to insufficient information.

[0097] The UI display unit 10 classifies a plurality of target characters generated based on the same user setting information for each item content. The UI display unit 10 displays a graph showing the ratio for each item content as the distribution of character settings.

[0098] According to this configuration, it becomes easier to understand the distribution of character settings.

[0099] The UI display unit 10 summarizes the item content having a character count exceeding the setting standard, and displays the summarized item content as a data label.

[0100] According to this configuration, the item content can be displayed in a compact and easy-to-understand manner.

[0101] Note that the effects described in this specification are merely examples and are not limited, and there may be other effects.

[0102] [Appendix] Note that this technology can also adopt the following configuration. (1) A UI display unit that acquires the worldview set in the virtual space as user setting information, A default setting generation unit that generates default settings regarding the setting items and item contents of the target character applied to the virtual space based on the user setting information, A generation model instruction creation unit that generates a prompt for character setting of the target character based on the default setting, An information processing apparatus having the above. (2) An existing character database that holds feature information of an existing character group, A similarity calculation unit that compares the feature information of the target character newly generated based on the prompt with the feature information of the existing character group, and acquires the similarity between the target character and the existing character group, The information processing apparatus according to (1) above having the above. (3) The existing character group includes a past character group generated based on other user setting information before the target character is generated, and a public character group publicly disclosed through existing media, The information processing apparatus according to (2) above. (4) The UI display unit displays, as similar characters, one or more of the existing characters selected in descending order of the similarity to the target character among the plurality of existing characters included in the existing character group, The information processing apparatus according to (2) or (3) above. (5) The UI display unit displays one or more similar characters that are more similar to the target character than the allowable level in a manner distinguishable from other similar characters, The information processing apparatus according to (4) above. (6) The similarity calculation unit classifies a plurality of target characters generated based on the same user setting information based on the similarity of the feature information, The UI display unit displays the classification result as a distribution of character settings. The information processing apparatus according to any one of (2) to (5) above. (7) The default setting generation unit commonly applies the setting items applied to a certain target character to other target characters generated based on the same user setting information. The information processing apparatus according to any one of (1) to (6) above. (8) The UI display unit displays a switching button for switching the necessity of applying the default setting. The information processing apparatus according to any one of (1) to (7) above. (9) When the default setting is not applied and the user does not select the setting item or input the item content, the UI display unit gives a notification. The information processing apparatus according to (8) above. (10) The UI display unit classifies a plurality of target characters generated based on the same user setting information for each item content, and displays a graph showing the ratio for each item content as a distribution of character settings. The information processing apparatus according to any one of (1) to (9) above. (11) The UI display unit summarizes the item content having a character count exceeding the setting standard, and displays the summarized item content as a data label. The information processing apparatus according to (10) above. (12) Obtain the worldview set in the virtual space as user setting information. Generate default settings regarding the setting items and item content of the target character applied to the virtual space based on the user setting information. Generate a prompt for performing character setting of the target character based on the default setting. An information processing method executed by a computer, comprising the above. (13) Acquire the worldview set in the virtual space as user setting information, Generate default settings regarding the setting items and item contents of the target character applied to the virtual space based on the user setting information, Generate a prompt for character setting of the target character based on the default settings. A program that causes a computer to realize the above.

Explanation of Signs

[0103] 1 Information processing device 10 UI display unit 20 Default setting generation unit 40 Generation model instruction creation unit 60 Similarity calculation unit 70 Existing character database

Claims

1. A UI display unit that acquires a worldview set in a virtual space as user setting information, A default setting generation unit that generates a default setting regarding setting items and item contents of a target character applied to the virtual space based on the user setting information, A generation model instruction creation unit that generates a prompt for character setting of the target character based on the default setting, An information processing apparatus having the above.

2. An existing character database that holds feature information of an existing character group, A similarity calculation unit that compares the feature information of the target character newly generated based on the prompt with the feature information of the existing character group, and acquires the similarity between the target character and the existing character group, The information processing apparatus according to Claim 1, having the above.

3. The existing character group includes a past character group generated based on other user setting information before the target character is generated, and a public character group publicly disclosed through existing media, The information processing apparatus according to Claim 2.

4. The UI display unit displays, as similar characters, one or more of the existing characters selected in descending order of the similarity to the target character among a plurality of existing characters included in the existing character group, The information processing apparatus according to Claim 2.

5. The UI display unit displays one or more similar characters that are similar to the target character beyond an acceptable level in a manner distinguishable from other similar characters, The information processing apparatus according to Claim 4.

6. The similarity calculation unit classifies a plurality of target characters generated based on the same user setting information based on the similarity of the feature information, The UI display unit displays the classification result as a distribution of character settings, The information processing apparatus according to Claim 2.

7. The default setting generation unit commonly applies the setting items applied to a certain target character to other target characters generated based on the same user setting information, The information processing apparatus according to Claim 1.

8. The UI display unit displays a switching button for switching the necessity of applying the default setting, The information processing apparatus according to Claim 1.

9. The UI display unit notifies when the default settings are not applied and the user does not select the setting item or input the item content. The information processing apparatus according to claim 8.

10. The UI display unit classifies a plurality of target characters generated based on the same user setting information for each item content, and displays a graph indicating the ratio for each item content as a distribution of character settings. The information processing apparatus according to claim 1.

11. The UI display unit summarizes the item content having a number of characters exceeding the setting standard, and displays the summarized item content as a data label. The information processing apparatus according to claim 10.

12. Acquire the worldview set in the virtual space as user setting information. Generate default settings regarding the setting items and item content of the target character applied to the virtual space based on the user setting information. Generate a prompt for character setting of the target character based on the default settings. An information processing method executed by a computer, comprising the above.

13. Acquire the worldview set in the virtual space as user setting information. Generate default settings regarding the setting items and item content of the target character applied to the virtual space based on the user setting information. Generate a prompt for character setting of the target character based on the default settings. A program causing a computer to realize the above.

Citation Information

Patent Citations

  • Virtual character generation apparatus and program

    JP2021043841A