Evaluation device

Abstract

This evaluation device includes a first acquisition unit, a second acquisition unit, and an evaluation unit. The first acquisition unit acquires first image data representing an original image which is to be evaluated for the presence or absence of copyright infringement. The second acquisition unit acquires a description describing the content of the original image by inputting the first image data into a trained model that has learned the relationship between image data and a description describing the content of an image represented by the image data. The evaluation unit evaluates the degree of probability of copyright infringement on the first image data on the basis of the number of words related to existing work, from among the words included in the description acquired by the second acquisition unit.

Description

Evaluation equipment

[0001] The present invention relates to an evaluation device.

[0002] In virtual spaces such as the Metaverse, various virtual objects are installed by operators or users of the virtual space for various purposes of decoration or sale. It is anticipated that the relationship between the virtual objects installed in the virtual space and the copyrights of other people's works may become an issue. Patent Literature 1 discloses a technology for avoiding copyright infringement. In this technology, when a virtual object includes a portion that may infringe the copyright of another person, image processing or other processing is performed to blur the relevant portion.

[0003] JP 2016-082201 A

[0004] It is inefficient for a person to determine whether a virtual object may infringe the copyright of an existing work, and there is a problem in that the criteria for determining whether an infringement occurs may differ depending on the knowledge and subjectivity of the person making the determination. This problem does not only arise in situations where the possibility of a virtual object infringing copyright is being evaluated, but can also arise in situations where the possibility of an illustration or video posted on a posting site or the like infringing copyright is being evaluated.

[0005] An evaluation device according to a preferred aspect of the present disclosure includes a first acquisition unit, a second acquisition unit, and an evaluation unit. The first acquisition unit acquires first image data representing an original image to be evaluated for copyright infringement. The second acquisition unit acquires explanatory text describing the content of the original image by inputting the first image data into a learning model that has trained the relationship between image data and explanatory text describing the content of the image represented by the image data. The evaluation unit evaluates the degree of possibility of copyright infringement regarding the first image data based on the number of words related to existing works among the words included in the explanatory text acquired by the second acquisition unit.

[0006] According to the present disclosure, the degree of possibility of copyright infringement regarding an existing work is evaluated based on a description generated from an image that is the subject of evaluation of the degree of possibility of copyright infringement, thereby enabling the degree of possibility of copyright infringement to be objectively and efficiently evaluated using certain criteria.

[0007] It is a figure which shows the example of the configuration of the evaluation device 10 by one embodiment of the present disclosure. It is a figure which shows the example of the configuration of the record included in the management table TBL. It is a figure which shows an example of the original image and the derived image. It is a flowchart which shows an example of the evaluation method which the processing device 160 of the evaluation device 10 executes according to the program PR1.

[0008] A. Embodiment FIG. 1 is a diagram illustrating an example configuration of an evaluation device 10 according to an embodiment of the present disclosure. The evaluation device 10 is a device that evaluates the degree of likelihood that a three-dimensional virtual object placed in a virtual space, such as a metaverse space, by a virtual space operator or user will infringe the copyright of an existing work. In this embodiment, the degree of likelihood of copyright infringement of an existing work is evaluated using an image generated based on a virtual object that is the subject of evaluation of the degree of likelihood of copyright infringement. An image generated based on a virtual object is an image obtained by capturing an image of a virtual object placed in a virtual space with a virtual camera installed in the virtual space. Hereinafter, a virtual object that is the subject of evaluation of the degree of likelihood of copyright infringement is referred to as a target object. An image generated based on the target object is referred to as an original image.

[0009] 1, the evaluation device 10 includes a communication device 130, a storage device 150, a processing device 160, and a bus 190. The communication device 130, the storage device 150, and the processing device 160 are connected to each other by the bus 190 for communicating information. The bus 190 may be configured using a single bus, or may be configured using different buses for each device.

[0010] The communication device 130 is hardware (transmission / reception device) for wired or wireless communication with other devices via a communication line. The communication device 130 is also referred to as, for example, a network device, a network controller, a network card, or a communication module. Examples of other devices that communicate with the communication device 130 via a communication line include a terminal device used by the operator of the virtual space, a terminal device used by a user, and a server providing other communication services. A user who wishes to evaluate whether a target object infringes copyright can obtain an evaluation value indicating the degree of possibility of copyright infringement by transmitting first image data representing an original image generated based on the target object from the user's terminal device to the evaluation device 10.

[0011] An example of a server that communicates with the communication device 130 via a communication line is a server 20 that stores a learning model 210 that has learned the relationship between image data and explanatory text that explains the content of the image represented by the image data. When the server 20 receives image data via a communication line, the server 20 recognizes objects depicted in the image represented by the image data. The server 20 then generates explanatory text data representing explanatory text related to the recognized objects using the learning model 210 and returns the generated explanatory text data to the sender of the image data. Note that the learning model 210 generates explanatory text using the official name of the object for which explanatory text is to be generated, even if the object for which explanatory text is to be generated has multiple names, such as an abbreviation or a nickname, in addition to the official name.

[0012] The storage device 150 is a recording medium readable by the processing device 160. The storage device 150 includes, for example, a nonvolatile memory and a volatile memory. The nonvolatile memory includes, for example, a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or an electrically erasable programmable read-only memory (EEPROM). The volatile memory is, for example, a random access memory (RAM). The nonvolatile memory of the storage device 150 stores a program PR1 that causes the processing device 160 to realize functions that prominently exhibit the characteristics of the present disclosure. The volatile memory of the storage device 150 is used as a work area when the processing device 160 executes the program PR1.

[0013] The storage device 150 also stores a management table TBL in advance. The management table TBL is a collection of multiple records. FIG. 2 is a diagram showing an example of the configuration of records included in the management table TBL. As shown in FIG. 2, one record includes a work identifier that uniquely identifies an existing work, a rights holder identifier that uniquely identifies the copyright holder of the work, and a group of related words. The work identifier is, for example, a character string representing the official name of the work. The rights holder identifier is a character string representing the name or full name of the copyright holder. The group of related words is a collection of multiple words related to the work. Specific examples of words related to the work include words representing the official name of the work, words representing the official name of a character appearing in the work, words representing the appearance characteristics of the character (such as color, shape, or gender), and words representing place names related to the work (such as the location of a building in the case of a work of art, or the name of a place where the film is set in the case of a work of art).

[0014] The processing device 160 includes one or more central processing units (CPUs). The one or more CPUs are examples of one or more processors. Each of the processors and CPUs is an example of a computer. When the processing device 160 is instructed to execute the program PR1 by operating an input device (not shown), the processing device 160 reads the program PR1 from non-volatile memory to volatile memory. The processing device 160 then executes the program PR1 read into the volatile memory. The processing device 160 operating in accordance with the program PR1 functions as the first acquisition unit 160a, the generation unit 160b, the second acquisition unit 160c, and the evaluation unit 160d shown in FIG. 1. In other words, the first acquisition unit 160a, the generation unit 160b, the second acquisition unit 160c, and the evaluation unit 160d in FIG. 1 are software modules realized by operating the processing device 160 in accordance with software. The functions of the first acquisition unit 160a, the generation unit 160b, the second acquisition unit 160c, and the evaluation unit 160d are as follows.

[0015] The first acquisition unit 160a acquires first image data representing an original image by communicating with a user's terminal device via a communication line. The generation unit 160b generates, based on the first image data, multiple pieces of second image data representing multiple derivative images obtained by modifying the original image. The multiple pieces of second image data correspond one-to-one to the multiple derivative images. In this embodiment, the generation unit 160b generates 100 derivative images, but the number of derivative images generated by the generation unit 160b may be one or more.

[0016] Specific examples of modifying an original image include changing the surface color of a target object appearing in the original image, adding or deleting a pattern from the target object, enlarging or reducing the target object, such as changing the target object's proportions, deleting some components of the target object or adding new components, and combinations thereof. FIG. 3 is a diagram showing examples of an original image and a derived image in this embodiment. For example, if the target object is a monster figurine and image G01 in FIG. 3 is the original image, images G02, G03, and G04 in FIG. 3 are examples of derived images. Image G02 is an image obtained by adding polka dots to the surface of the target object. Image G03 is an image obtained by reducing the proportions of the target object. Image G04 is an image obtained by removing the dorsal fin from the target object.

[0017] The second acquisition unit 160c acquires explanatory data related to the original image by transmitting the first image data via a communication line to the server 20. The second acquisition unit 160c also acquires a plurality of explanatory data related to a plurality of derived images by transmitting each of the plurality of second image data to the server 20. The plurality of explanatory data corresponds one-to-one to the plurality of derived images.

[0018] The evaluation unit 160d evaluates the degree of possibility of copyright infringement by the target object for each of the description data acquired by the second acquisition unit for each of the multiple images composed of the original image and multiple derivative images. That is, in this embodiment, the degree of possibility of copyright infringement for the target object is evaluated based on the original image and the multiple derivative images. Evaluating the degree of possibility of copyright infringement using the multiple derivative images in addition to the original image is performed so that the degree of possibility of copyright infringement by the target object can be evaluated even if the target object has been intentionally modified for the purpose of avoiding copyright infringement.

[0019] More specifically, the evaluation unit 160d extracts words contained in the description by performing morphological analysis on the description represented by the description data acquired by the second acquisition unit 160c for each of the plurality of images. The evaluation unit 160d evaluates the degree of possibility of copyright infringement for the target object based on the words extracted from the description and the related word group stored in the management table TBL for each copyrighted work.

[0020] 1, the evaluation unit 160d in this embodiment includes a determination unit 160d1 and a calculation unit 160d2. If a word included in a related word group related to any copyrighted work is included in the multiple words extracted from the description represented by the description data acquired by the second acquisition unit 160c for each of the multiple images described above, the determination unit 160d1 determines that there is a possibility of copyright infringement for the copyrighted work corresponding to the related word group. Conversely, if none of the multiple words extracted from the description is included in any related word group, the determination unit 160d1 determines that there is no possibility of copyright infringement for an existing copyrighted work.

[0021] The calculation unit 160d2 calculates an evaluation value representing the degree of possibility of copyright infringement by the target object based on the ratio between the number N of explanatory sentences determined by the determination unit 160d1 to the total number M of explanatory sentences acquired by the second acquisition unit. In this embodiment, since M = 101, when N = 80, the calculation unit 160d2 calculates an evaluation value representing the degree of possibility of copyright infringement of 79.2%. The calculation unit 160d2 transmits the calculated evaluation value, the work identifier of the existing work determined to have the possibility of copyright infringement, and the right holder identifier associated with the work identifier to the sender of the first image data via a communication line.

[0022] Furthermore, the processing device 160 operating in accordance with the program PR1 executes an evaluation method specific to the present disclosure. Figure 4 is a flowchart showing the process flow of this evaluation method. As shown in Figure 4, this evaluation method includes a first acquisition process SA110, a generation process SA120, a second acquisition process SA130, and an evaluation process SA140. The processing contents of each of the first acquisition process SA110, the generation process SA120, the second acquisition process SA130, and the evaluation process SA140 are as follows.

[0023] In the first acquisition process SA110, the processing device 160 functions as a first acquisition unit 160a. In the first acquisition process SA110, the processing device 160 acquires first image data.

[0024] In the generation process SA120, the processing device 160 functions as a generation unit 160b. In the generation process SA120, the processing device 160 generates, based on the first image data, a plurality of second image data representing a plurality of derived images obtained by modifying the original image. In this embodiment, the processing device 160 generates 100 pieces of second image data representing different derived images.

[0025] In the second acquisition process SA130, the processing device 160 functions as a second acquisition unit 160c. In the second acquisition process SA130, the processing device 160 acquires explanatory text data by transmitting the first image data to the server 20 that stores a learning model 210 that has learned the relationship between image data and explanatory text that explains the content of the image represented by the image data. Also, in the second acquisition process SA130, the processing device 160 acquires multiple explanatory text data by transmitting multiple pieces of second image data generated in the generation process SA120 to the server. The multiple explanatory text data correspond one-to-one to the multiple derived images.

[0026] In the evaluation process SA140, the processing device 160 functions as the evaluation unit 160d. In the evaluation process SA140, the processing device 160 evaluates the degree of possibility of copyright infringement by the target object for each of the descriptions acquired in the second acquisition process SA130 for each of the multiple images consisting of the original image and 100 derivative images. The evaluation unit 160d determines whether or not there is copyright infringement based on the number of words related to existing works among the words included in the descriptions acquired by the second acquisition unit 160c for each of the multiple images consisting of the original image and 100 derivative images. Next, the processing device 160 calculates an evaluation value representing the degree of possibility of copyright infringement by the target object based on the ratio between the number of descriptions determined to be likely to infringe copyright and the total number of descriptions acquired in the second acquisition process SA130. The processing device 160 then transmits the calculated evaluation value, the work identifier of the existing work determined to be likely to infringe copyright, and the rights holder identifier to the sender of the first image data.

[0027] As described above, according to this embodiment, a description of a virtual object to be evaluated for copyright infringement is generated from an image generated based on the virtual object, and the degree of likelihood of copyright infringement of an existing work is evaluated based on words contained in the description. This enables more objective and efficient evaluation based on a set standard than when a person determines whether or not there is infringement. Furthermore, according to this embodiment, the degree of likelihood of copyright infringement for a virtual object is quantified as an evaluation value. Therefore, for virtual objects that have an evaluation value calculated to be equal to or greater than a predetermined threshold (e.g., 70%), a detailed evaluation of the likelihood of copyright infringement may be conducted by an expert.

[0028] B: Variations The present disclosure is not limited to the above-exemplified embodiments. Specific variations are as follows. Two or more variations arbitrarily selected from the following examples may be combined. B-1: Variation 1 While the original image in the above embodiment is an image generated based on a three-dimensional virtual object, the original image may also be an image of a two-dimensional object, such as a painting, illustration, or image of a cartoon character.

[0029] B-2: Modification 2 The generation of a derivative image is not required, and the generation unit 160b may be omitted. In an embodiment in which the generation unit 160b is omitted, the second acquisition unit 160c only needs to acquire a description for the original image, and the evaluation unit 160d only needs to evaluate whether or not there is copyright infringement of an existing work based on the description for the original image. Furthermore, in an embodiment in which the generation of a derivative image is omitted, the calculation unit 160d2 is unnecessary. In other words, the evaluation of the degree of possibility of copyright infringement according to the present disclosure includes a binary evaluation, such as whether or not there is infringement, in addition to a quantitative evaluation such as the calculation of the evaluation value in the above embodiment.

[0030] B-3: Modification 3 In the above embodiment, the first acquisition unit 160a, the generation unit 160b, the second acquisition unit 160c, and the evaluation unit 160d are software modules. However, any one, any two, any three, or all of the first acquisition unit 160a, the generation unit 160b, the second acquisition unit 160c, and the evaluation unit 160d may be hardware modules. Specific examples of hardware modules include a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a PLD (Programmable Logic Device), and an FPGA (Field Programmable Gate Array). Even if any one, any two, any three, or all of the first acquisition unit 160a, the generation unit 160b, the second acquisition unit 160c, and the evaluation unit 160d are hardware modules, the same effects as those of the above embodiment can be achieved.

[0031] B-4: Variation 4 In the above embodiment, the program PR1 is stored in the storage device 150 of the evaluation device 10. However, the program PR1 may be manufactured or sold as a standalone program. The program PR1 may be provided to a purchaser, for example, by distributing a computer-readable recording medium such as a flash ROM on which the program PR1 is written, or by distributing the program PR1 by downloading it via a telecommunications line.

[0032] C: Others (1) In the above-described embodiment, ROM, RAM, etc. are exemplified as storage device 150, but storage device 150 may also be a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disk), a smart card, a flash memory device (e.g., a card, a stick, a key drive), a CD-ROM (Compact Disc-ROM), a register, a removable disk, a hard disk, a floppy (registered trademark) disk, a magnetic strip, a database, a server, or other suitable storage medium.

[0033] (2) In the above-described embodiments, the described information, signals, etc. may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc. that may be referred to throughout the above description may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0034] (3) In the above-described embodiment, input and output information may be stored in a specific location (for example, a memory) or may be managed using a management table. Input and output information may be overwritten, updated, or added to. Output information may be deleted. Input information may be transmitted to another device.

[0035] (4) In the above-described embodiment, the determination may be made based on a value represented by one bit (0 or 1), a Boolean value (true or false), or a comparison of numerical values ​​(e.g., comparison with a predetermined value).

[0036] (5) The order of the process procedures, sequences, flowcharts, etc. illustrated in the above-described embodiments may be rearranged unless it is consistent. For example, the methods described in this disclosure present elements of various steps using an example order, and are not limited to the particular order presented.

[0037] (6) Each function illustrated in FIG. 1 is realized by any combination of hardware and / or software. Furthermore, the method for realizing each functional block is not particularly limited. That is, each functional block may be realized using a single device that is physically or logically coupled, or may be realized using two or more physically or logically separated devices that are directly or indirectly connected (e.g., wired, wireless, etc.) and these multiple devices. A functional block may be realized by combining software with the single device or the multiple devices.

[0038] (7) The programs exemplified in the above-described embodiments should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, procedures, functions, etc., regardless of whether software is called software, firmware, middleware, microcode, hardware description language, or by other names.

[0039] Software, instructions, information, etc. may also be transmitted or received over a transmission medium. For example, if software is transmitted from a website, server, or other remote source using wired technologies (such as coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL)), and / or wireless technologies (such as infrared, microwave), then these wired and / or wireless technologies are included within the definition of transmission media.

[0040] (8) In the above embodiments, the terms "system" and "network" are used interchangeably.

[0041] (9) The information, parameters, etc. described in this disclosure may be expressed using absolute values, relative values ​​from a predetermined value, or corresponding other information.

[0042] (10) In the above-described embodiments, the mobile terminal includes a mobile station (MS). A mobile station may also be referred to by those skilled in the art as a subscriber station, mobile unit, subscriber unit, wireless unit, remote unit, mobile device, wireless device, wireless communication device, remote device, mobile subscriber station, access terminal, mobile terminal, wireless terminal, remote terminal, handset, user agent, mobile client, client, or some other suitable term. In this disclosure, the terms "mobile station," "user terminal," "user equipment (UE)," "terminal," etc. may be used interchangeably.

[0043] (11) In the above-described embodiments, the terms "connected," "coupled," or any variations thereof refer to any direct or indirect connection or coupling between two or more elements, and may include the presence of one or more intermediate elements between two elements that are "connected" or "coupled" to each other. The coupling or connection between elements may be physical, logical, or a combination thereof. For example, "connected" may be read as "access." As used in this disclosure, two elements may be considered to be "connected" or "coupled" to each other using at least one of one or more electric wires, cables, and printed electrical connections, as well as electromagnetic energy having wavelengths in the radio frequency range, microwave range, and optical (both visible and invisible) range, as some non-limiting and non-exhaustive examples.

[0044] (12) In the above embodiments, the phrase "based on" does not mean "based only on," unless otherwise specified. In other words, the phrase "based on" means both "based only on" and "based at least on."

[0045] (13) As used in this disclosure, the terms "determining" and "determining" may encompass a wide variety of actions. "Determining" and "determining" may include, for example, judging, calculating, computing, processing, deriving, investigating, looking up, searching, inquiring (e.g., searching a table, database, or other data structure), and ascertaining something that is considered to be a "determining." Also, "determining" and "determining" may include receiving (e.g., receiving information), transmitting (e.g., sending information), input, output, accessing (e.g., accessing data in memory), and the like. Furthermore, "judgment" and "decision" can include regarding resolving, selecting, choosing, establishing, comparing, etc. as having been "judgment" or "decision." In other words, "judgment" and "decision" can include regarding some action as having been "judgment" or "decision." Furthermore, "judgment (decision)" can be interpreted as "assuming," "expecting," "considering," etc.

[0046] (14) In the above embodiments, when the terms "include," "including," and variations thereof are used, these terms are intended to be inclusive, similar to the term "comprising." Furthermore, the term "or," as used in this disclosure, is not intended to be an exclusive or.

[0047] (15) In this disclosure, where articles are added by translation, such as a, an, and the in English, this disclosure may include the nouns following these articles being plural.

[0048] (16) In this disclosure, the term "A and B are different" may mean "A and B are different from each other." The term may also mean "A and B are each different from C." Terms such as "separate" and "combined" may also be interpreted in the same way as "different."

[0049] (17) The aspects / embodiments described in this disclosure may be used alone, in combination, or switched depending on the implementation. Notification of predetermined information (e.g., notification that "X is true") is not limited to being explicit, but may be implicit (e.g., not notifying the predetermined information).

[0050] D: Aspects Understood from the Above-described Embodiments or Modifications Although the present disclosure has been described in detail above, it is clear to those skilled in the art that the present disclosure is not limited to the embodiments described herein. The present disclosure can be implemented in modified and altered forms without departing from the spirit and scope of the present disclosure as defined by the claims. Therefore, the description of the present disclosure is intended to be illustrative and does not have any limiting meaning on the present disclosure. The following aspects can be understood from at least one of the above-described embodiments or modifications.

[0051] An evaluation device according to a first aspect of the present disclosure includes a first acquisition unit, a second acquisition unit, and an evaluation unit. The first acquisition unit acquires first image data representing an original image to be evaluated for copyright infringement. The second acquisition unit acquires explanatory text describing the content of the original image by inputting the first image data into a learning model that has learned the relationship between image data and explanatory text describing the content of the image represented by the image data. The evaluation unit evaluates the degree of likelihood of copyright infringement related to the first image data based on the number of words related to existing works among the words included in the explanatory text acquired by the second acquisition unit. The evaluation device of the first aspect can efficiently evaluate the degree of likelihood of copyright infringement related to existing works based on a certain standard, based on the first image data representing the original image to be evaluated for copyright infringement.

[0052] In a second aspect (an example of the first aspect) of the present disclosure, the first image data is generated based on a three-dimensional virtual object. In the example of the second aspect, the evaluation unit evaluates the degree of possibility of copyright infringement by the virtual object. According to the second aspect, it is possible to evaluate the degree of possibility of copyright infringement by the three-dimensional virtual object.

[0053] An evaluation device according to a third aspect (an example of the second aspect) of the present disclosure includes a generation unit that generates, based on the first image data, one or more second image data representing one or more derived images obtained by modifying the original image. The second acquisition unit in the evaluation device according to the third aspect inputs the one or more second image data to the learning model to acquire one or more explanatory sentences describing the content of the one or more derived images. The one or more explanatory sentences correspond one-to-one to the one or more derived images. The evaluation unit in the evaluation device of the third aspect evaluates the degree of likelihood of copyright infringement by the virtual object for each explanatory sentence acquired by the second acquisition unit for each of a plurality of images consisting of the original image and the one or more derived images. According to the evaluation device of the fourth aspect, the degree of likelihood of copyright infringement by the virtual object is evaluated, including the derivative image obtained by modifying the original image. Therefore, even if the virtual object is intentionally modified to avoid copyright infringement, the degree of likelihood of copyright infringement by the virtual object can be evaluated.

[0054] The evaluation unit in the evaluation device according to a fourth aspect (an example of the third aspect) of the present disclosure further includes a determination unit and a calculation unit. The evaluation unit determines whether or not there is a possibility of copyright infringement by the virtual object for each of the descriptions acquired by the second acquisition unit for each of the plurality of images. The calculation unit calculates an evaluation value representing the degree of possibility of copyright infringement by the virtual object based on the ratio between the number of descriptions determined by the determination unit to be likely to infringe copyright and the total number of descriptions acquired by the second acquisition unit. According to the evaluation device of the fourth aspect, an evaluation value representing the degree of possibility of copyright infringement by the virtual object is calculated, thereby quantifying the degree of possibility of copyright infringement by the virtual object.

[0055] 10...evaluation device, 130...communication device, 150...storage device, 160...processing device, 160a...first acquisition unit, 160b...generation unit, 160c...second acquisition unit, 160d...evaluation unit, 160d1...determination unit, 160d2...calculation unit, 190...bus, PR1...program, TBL...management table.

Claims

1. An evaluation device comprising: a first acquisition unit that acquires first image data representing an original image to be evaluated for copyright infringement; a second acquisition unit that acquires an explanatory text explaining the content of the original image by inputting the first image data into a learning model that has learned the relationship between image data and an explanatory text explaining the content of the image represented by the image data; and an evaluation unit that evaluates the degree of possibility of copyright infringement regarding the first image data based on the number of words related to existing works among the words included in the explanatory text acquired by the second acquisition unit.

2. The evaluation device according to claim 1, wherein the first image data is generated based on a three-dimensional virtual object, and the evaluation unit evaluates the degree of possibility of copyright infringement by the virtual object.

3. The evaluation device according to claim 2, further comprising: a generation unit that generates, based on the first image data, one or more second image data representing one or more derived images obtained by modifying the original image; wherein the second acquisition unit acquires one or more explanatory sentences explaining the contents of the one or more derived images by inputting the one or more second image data into the learning model, the one or more explanatory sentences having a one-to-one correspondence with the one or more derived images; and wherein the evaluation unit evaluates the degree of possibility of copyright infringement by the virtual object for each explanatory sentence acquired by the second acquisition unit for each of a plurality of images constituted by the original image and the one or more derived images.

4. The evaluation device described in claim 3, wherein the evaluation unit comprises: a determination unit that determines whether or not there is a possibility of copyright infringement by the virtual object for each of the descriptions acquired by the second acquisition unit for each of the plurality of images; and a calculation unit that calculates an evaluation value representing the degree of the possibility of copyright infringement by the virtual object based on the ratio between the number of descriptions determined by the determination unit to be likely to infringe copyright and the total number of descriptions acquired by the second acquisition unit.

Images