Terminal device and method for displaying advertisement image

Abstract

To surely mask an advertisement image of a mask object included in an image displayed on a display device.SOLUTION: A terminal device 10 includes an extraction unit 150b, a determination unit 150c, and a mask unit 150d. The extraction unit 150b outputs a first advertisement image by extracting the advertisement image from the first image displayed on a display device 120 in accordance with an application program AP1. The determination unit 150c determines whether or not a type of the first advertisement image corresponds to a type set as a mask target by a first user based on correspondence relationship between a feature of the advertisement image and a type of the advertisement image. When the determination unit 150c determines that the type of the first advertisement image corresponds to the type set as the mask target, the mask unit 150c displays a mask image for masking the first advertisement image on the display device 120.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to a terminal device and a method for displaying an advertising image. [Background technology]

[0002] Patent Document 1 discloses an information processing device that provides advertising content that is highly appealing to caregivers raising children. The information processing device includes an acquisition unit, a selection unit, and a determination unit. The acquisition unit acquires attribute information of a childcare recipient for the childcare provider to whom the advertising content is provided. The childcare recipient is the child of the caregiver. The attribute information is information indicating the child's age in months, gender, address, height, weight, diaper size, shoe size, or preferences (e.g., favorite colors, plants, animals, toys), etc. The selection unit selects advertising content to be provided to the caregiver based on the attribute information acquired by the acquisition unit. The determination unit determines a delivery mode for delivering the advertising content to be provided based on the use status of the caregiver so that the advertising content selected by the selection unit is provided to the caregiver. The technology disclosed in Patent Document 1 makes it possible to reliably provide advertising content according to the attribute information of the child to a user who is in the position of a caregiver because they have children. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-11155 Summary of the Invention [Problem to be solved by the invention]

[0004] In recent years, images displayed in accordance with application programs executed on terminal devices may include various types of advertising images. These advertising images may include inappropriate advertising images. Inappropriate advertising images refer to advertising images that are undesirable for users of terminal devices to see, such as advertising images that include violent or sexual content. However, the technology disclosed in Patent Document 1 has the problem of being unable to prevent the display of inappropriate advertising images. [Means for solving the problem]

[0005] A terminal device according to one embodiment of the present disclosure includes an extraction unit that outputs a first advertising image by extracting the advertising image from a first image displayed on a display device, a determination unit that determines whether the type of the first advertising image corresponds to a type set by a first user as a target to be masked based on a correspondence between the characteristics of the advertising image and the type of the advertising image, and a mask unit that displays a mask image that masks the first advertising image on the display device when the determination unit determines that the type corresponds to the type set as a target to be masked.

[0006] In addition, a method for displaying an advertising image according to one embodiment of the present disclosure includes outputting a first advertising image by extracting the advertising image from a first image displayed on a display device, determining whether the type of the first advertising image corresponds to a type set by a first user as a target to be masked based on a correspondence between the characteristics of the advertising image and the type of the advertising image, and, if it is determined that the type corresponds to the type set as a target to be masked, displaying a mask image that masks the first advertising image on the display device. [Effects of the Invention]

[0007] According to the present disclosure, it is possible to mask the type of advertising image set by the user as the mask target. [Brief explanation of the drawings]

[0008] [Figure 1]1 is a diagram illustrating an example of the configuration of a communication system 1 including a terminal device 10 according to an embodiment of the present disclosure. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of a terminal device 10. [Figure 3] 10 is a diagram showing an example of an image G1 displayed on the display device 120 in accordance with an application program. FIG. [Figure 4] FIG. 10 is a diagram showing a display example of a mask image G2. [Figure 5] 10 is a flowchart showing the flow of an advertising image display method executed by the processing device 150 according to the program PR1. DETAILED DESCRIPTION OF THE INVENTION

[0009] (A. Embodiment) 1 is a diagram illustrating an example configuration of a communication system 1 including terminal devices 10(1), 10(2)...10(N) according to an embodiment of the present disclosure and a management device 20. Note that N is an integer of 2 or greater.

[0010] Each of the terminal devices 10(1), 10(2)...10(N) is a computer device having the function of executing an application program. Each of the terminal devices 10(1), 10(2)...10(N) is, for example, a smartphone. The configurations of the terminal devices 10(1), 10(2)...10(N) are all identical. The following description will be given using the terminal device 10(1) as an example. When there is no need to distinguish the terminal device 10(1) from the terminal devices 10(2)...10(N), the terminal device 10(1) will be referred to as the "terminal device 10." The terminal device 10 is wirelessly connected to a communication network NW. The terminal device 10 communicates with the management device 20 via the communication network NW. An application program is an application that displays images. Examples of application programs include a web browser, a game application, and a video application. The management device 20 provides a service of masking an advertising image designated by a user from among advertising images included in an image displayed on the terminal device 10 based on an application program. Masking an advertising image means covering the advertising image with another image so that the advertising image cannot be viewed.

[0011] Each user of the terminal devices 10(1), 10(2), ... 10(N) can register in the management device 20 the types of advertising images that they wish to mask or the types of advertising images that are not to be masked among the advertising images displayed when an application program is executed. The user of the terminal device 10(1) is an example of a first user. Examples of types of advertising images that are registered as being to be masked include advertising images containing violent content, advertising images containing sexual content, and advertising images related to gambling. Note that types of advertising images containing violent content may be further subdivided according to the level of inappropriateness, such as advertising images containing destruction of objects, advertising images containing bloody content, and advertising images containing content related to the killing of animals. The same applies to advertising images containing sexual content and advertising images related to gambling. The management device 20 is a device that manages the types of advertising images that are set as being to be masked or not to be masked, in association with each user of the terminal devices 10(1), 10(2), ... 10(N). The management device 20 determines a common first learning model MDL1 for each user of the terminal devices 10(1), 10(2)...10(N), and determines a second learning model MDL2 for each user. That is, the management device 20 stores one first learning model MDL1 and N second learning models MDL2.

[0012] The first learning model MDL1 functions as an AI (Artificial Intelligence) for estimating whether an image represented by input image data is an advertising image based on the image characteristics of the image. The first learning model MDL1 is determined, for example, by performing machine learning such as deep learning using learning data that pairs learning images (advertising images or images other than advertising images) with labels indicating whether the images are advertising images. When an image to be estimated is input to the first learning model MDL1, the first learning model MDL1 outputs an estimation result for the input image (a label indicating whether the image is an advertising image) and an index indicating the accuracy (likelihood) of the estimation result. In this embodiment, the index indicating the accuracy of the estimation result is a value greater than 0 and less than 1, and the closer the index value is to 1, the higher the accuracy of the estimation.

[0013] The second learning model MDL2 functions as an AI for estimating, based on the characteristics of an advertising image represented by input image data, whether the type of the advertising image corresponds to a type set by a user corresponding to the second learning model MDL2 as a mask target. The second learning model MDL2 is determined, for example, by performing machine learning such as deep learning using learning data that pairs learning images (advertising images of a type set as a mask target or advertising images of a type not corresponding to the type set) with labels indicating whether the images are to be masked. When an image to be estimated is input to the second learning model MDL2, the second learning model MDL2 outputs an estimation result for the input image (a label indicating whether the image is to be masked) and an index indicating the likelihood of the estimation result. The index output from the second learning model MDL2 is also a value greater than 0 and less than 1, and the closer the index value is to 1, the higher the likelihood of the estimation. In this embodiment, the user of the terminal device 10(1) pre-registers "advertising images related to gambling" in the management device 20 as a type of advertising image to be masked. For this reason, the management device 20 stores, as a second learning model corresponding to the user of the terminal device 10, a learning model that estimates whether or not an image is an "advertising image related to gambling."

[0014] The terminal device 10 communicates with the management device 20 via the communication network NW to acquire a first learning model MDL1 and a second learning model MDL2 corresponding to the user of the terminal device 10. Then, the terminal device 10 uses the first learning model MDL1 to determine whether an advertisement image is included in an image displayed during execution of an application program. Furthermore, if the terminal device 10 determines that an advertisement image is included, it uses the second learning model MDL2 to determine whether the type of the advertisement image is a type set by the user of the terminal device 10 as a type to be masked. Then, the terminal device 10 masks the advertisement image determined to be a masked image.

[0015] Fig. 2 is a diagram showing an example of the configuration of the terminal device 10. As shown in Fig. 2, the terminal device 10 includes a communication device 110, a display device 120, an input device 130, a storage device 140, a processing device 150, and a bus 160 that interconnects these devices.

[0016] The communication device 110 is connected to a communication network NW by wire or wirelessly. The communication device 110 includes a communication circuit for communicating with other devices via the communication network NW. An example of the other devices that communicate with the communication device 110 is a management device 20.

[0017] The display device 120 displays information to the outside under the control of the processing device 150. The display device 120 is, for example, a display panel such as a liquid crystal display panel or an organic electroluminescence (EL) display panel. An image G1 is displayed on the display device 120 by the processing device 150 operating in accordance with an application program AP1. Note that in FIG. 2, the application program is abbreviated as "app." The application program AP1 is stored in the storage device 140. FIG. 3 is a diagram illustrating an example of image G1. As shown in FIG. 3, image G1 includes partial images G11, G12, and G13. Partial image G11 is an application image containing information provided in accordance with the application program. The application program in this embodiment is an action game in which a character C jumps upward using clouds as footholds. Partial image G11 is an image of a game screen for the action game. Partial images G12 and G13 are both advertising images. More specifically, partial image G12 is an advertising image related to gambling. Partial image G13 is an advertising image related to games.

[0018] The input device 130 is an input device that accepts input from the outside. Specific examples of the input device 130 include a switch, a button, etc. The input device 130 may be a touch sensor that is integrated with the display device 120 to form a touch panel.

[0019] The storage device 140 is a recording medium readable by the processing device 150. The storage device 140 includes, for example, a nonvolatile memory and a volatile memory. The nonvolatile memory is, for example, a ROM (Read Only Memory), an EPROM (Erasable Programmable Read Only Memory), and an EEPROM (Electrically Erasable Programmable Read Only Memory). The volatile memory is, for example, a RAM (Random Access Memory). The storage device 140 stores the first learning model MDL1 and the second learning model MDL2 acquired from the management device 20. The storage device 140 also stores the above-mentioned application program AP1 and a program PR1 for realizing the OS (Operating System).

[0020] The processing device 150 includes one or more central processing units (CPUs). The one or more CPUs are an example of one or more processors. Each of the processors and CPUs is an example of a computer. The processing device 150 reads a program PR1 from the storage device 140 when the terminal device 10 is powered on. The processing device 150 executes the read program PR1 to realize an OS. When the processing device 150 is instructed to execute an application program AP1 by an operation on the input device 130 while the OS is being implemented, the processing device 150 reads the application program AP1 from the storage device 140. The processing device 150 executes the read application program AP1 to display an image G1 (see FIG. 3 ) on the display device 120.

[0021] Furthermore, the processing device 150 operating in accordance with the program PR1 functions as an acquisition unit 150a, an extraction unit 150b, a determination unit 150c, a mask unit 150d, and an upload unit 150e.

[0022] The acquisition unit 150a acquires the first learning model MDL1 and the second learning model MDL2 by communicating with the management device 20. The acquisition unit 150a stores the acquired first learning model MDL1 and second learning model MDL2 in the storage device 140. The acquisition of the first learning model MDL1 and the second learning model MDL2 by the acquisition unit 150a may be performed, for example, every time execution of the program PR1 starts, or may be performed periodically, for example, once a week. Furthermore, the acquisition of the first learning model MDL1 may be performed only once when the program PR1 is initially executed, and the acquisition of the second learning model MDL2 may be performed every time execution of the program PR1 starts, or may be performed periodically, for example, once a week. This is because it is expected that the second learning model MDL2 will be updated more frequently due to the specification of new mask targets, etc.

[0023] The extraction unit 150b extracts an advertisement image from a first image, which is an image displayed on the display device 120, according to an application program. The extraction unit 150b outputs the first advertisement image, which is the advertisement image extracted from the first image, to the determination unit 150c. More specifically, the extraction unit 150b includes a division unit 150b1 and a selection unit 150b2, as shown in FIG.

[0024] The dividing unit 150b1 divides the first image into a plurality of partial images by performing segmentation on the first image. Segmentation is a technique for dividing an image into a plurality of regions based on the characteristics of each region. In this embodiment, each region divided by segmentation becomes a partial image. Existing segmentation techniques are appropriately adopted. For example, when the above-mentioned image G1 is input to the dividing unit 150b1, the dividing unit 150b1 divides the image G1 into partial images G11, G12, and G13.

[0025] The selection unit 150b2 selects an advertisement image from among the plurality of partial images based on the characteristics of each of the plurality of partial images. The selection unit 150b2 estimates whether each partial image is an advertisement image by inputting each of the plurality of partial images obtained by division by the division unit 150b1 to the first learning model MDL1. Then, the selection unit 150b2 selects as advertisement images partial images for which an estimation result that the partial image is an advertisement image is obtained and the index of the likelihood of the estimation result is equal to or greater than a first threshold. An example of the first threshold is 0.5. A suitable value for the first threshold may be set through experiments or the like. The extraction unit 150b outputs the advertisement image selected by the selection unit 150b2 to the discrimination unit 150c as a first advertisement image.

[0026] For example, when partial image G11 is input to the selection unit 150b2, the selection unit 150b2 outputs an inference that partial image G11 is not an advertisement image because it is an application image. When partial image G12 is input to the selection unit 150b2, the selection unit 150b2 outputs an inference that partial image G12 is an advertisement image because it is an advertisement image. Similarly, when partial image G13 is input to the selection unit 150b2, the selection unit 150b2 outputs an inference that partial image G13 is an advertisement image because it is an advertisement image. Note that in this embodiment, it is assumed that a value exceeding the first threshold is output as an index of the likelihood of the inference result for partial image G12, and that a value exceeding the first threshold is also output as an index of the likelihood of the inference result for partial image G13. In other words, the following describes a case where partial image G12 and partial image G13 are output as first advertisement images.

[0027] The determination unit 150c determines whether or not the type of the first advertisement image corresponds to the type set as a target to be masked by the user of the terminal device 10, based on the correspondence between the features of the advertisement image and the type of the advertisement image. More specifically, the determination unit 150c first identifies the type of the first advertisement image based on the correspondence between the features of the advertisement image and the type of the advertisement image. Second, the determination unit 150c determines whether or not the identified type of the first advertisement image corresponds to the type set as a target to be masked by the user of the terminal device 10.

[0028] Hereinafter, an advertising image of a type corresponding to the type set as a mask target by the user of the terminal device 10 is referred to as a "mask target image." In this embodiment, the discrimination unit 150c uses the second learning model MDL2 to determine whether the first advertising image extracted by the extraction unit 150b is a mask target image. More specifically, the discrimination unit 150c inputs image data representing the first advertising image into the second learning model MDL2. Then, if an estimation result indicating that the first advertising image is a mask target is obtained and the index of likelihood of the estimation result is equal to or greater than a second threshold, the discrimination unit 150c determines that the first advertising image is a mask target image. An example of the second threshold is 0.5. The second threshold may also be set to an appropriate value through experiments or the like. In this embodiment, the discrimination unit 150c determines that the first advertising image is not a mask target image if an estimation result indicating that the first advertising image is a mask target is obtained but the index of likelihood of the estimation result is less than the second threshold, or if an estimation result indicating that the first advertising image is a mask target is not obtained.

[0029] As described above, in this embodiment, the user of the terminal device 10 sets "advertising image related to gambling" as the type of advertising image to be masked. As described above, since the partial image G12 is an advertising image related to gambling, an estimation result that the partial image G12 is to be masked is obtained, and an index exceeding the second threshold value is obtained. In this case, the discrimination unit 150c determines that the partial image G12 is an image to be masked. On the other hand, since the partial image G13 described above is an advertising image related to games, an estimation result that the partial image G13 is not to be masked is obtained, and an index exceeding the second threshold value is obtained. In this case, the discrimination unit 150c determines that the partial image G13 is not an image to be masked.

[0030] When the determination unit 150c determines that the first advertisement image is a mask target image, the mask unit 150d displays a mask image that masks the first advertisement image on the display device 120. In this embodiment, the mask unit 150d displays the mask image in the area of ​​the first image that is occupied by the mask target image. Examples of the mask image include an image filled with a predetermined color such as red or black, or an image with a message such as "Masked due to inappropriate advertisement" with the background filled with a predetermined color. As described above, when the partial image G12 is determined to be a mask target image and the partial image G13 is determined not to be a mask target image, the mask unit 150d masks the partial image G12 by displaying a mask image G2 overlaid on the image G1 in the area of ​​the image G1 that is occupied by the partial image G12, as shown in FIG. 4.

[0031] When the first advertisement image is designated by the user as a target to be masked, the upload unit 150e uploads image data representing the first advertisement image to the management device 20. For example, when the partial image G13 in FIG. 3 is designated as a target to be masked and the type of the partial image G13 (such as including violent content) is also designated, the upload unit 150e transmits image data representing the partial image G13 and the type of the partial image G13 to the management device 20. The management device 20 adds the image data and a tag indicating the type to the learning data and performs machine learning again, thereby re-determining the second learning model MDL2 corresponding to the user of the terminal device 10.

[0032] Furthermore, the processing device 150 operating in accordance with the program PR1 executes a method for displaying advertising images that prominently demonstrates the features of the present disclosure. Figure 5 is a flowchart showing the flow of this display method. As shown in Figure 5, this display method includes an extraction process SA110, a determination process SA120, a first display process SA130, and a second display process SA140.

[0033] In the extraction process SA110, the processing device 150 functions as an extraction unit 150b. In the extraction process SA110, the processing device 150 extracts an advertising image from a first image, which is an image displayed on the display device 120, according to an application program. In the determination process SA120, the processing device 150 functions as a determination unit 150c. In the determination process SA120, the processing device 150 determines whether or not an image to be masked is included in the advertising image extracted in the extraction process SA110. When M (M is an integer equal to or greater than 1) advertising images are extracted in the extraction process SA110, if none of the M advertising images are images to be masked, the determination result of the determination process SA120 is "No". On the other hand, if at least one of the M advertising images is an image to be masked, the determination result of the determination process SA120 is "Yes".

[0034] If the determination result of the determination process SA120 is "Yes," the processing device 150 executes a first display process SA130. In the first display process SA130, the processing device 150 functions as a mask unit 150d. That is, in the first display process SA130, the processing device 150 displays a mask image in the area of ​​the first image occupied by the image to be masked. In contrast, if the determination result of the determination process SA120 is "No," the processing device 150 executes a second display process SA140. In the second display process SA140, the processing device 150 displays the first image on the display device 120 without displaying a mask image.

[0035] According to this embodiment, a mask image is displayed superimposed on an advertising image of a type set by the user as a target to be masked. In this embodiment, the function for masking an advertising image of a type set by the user as a target to be masked is realized by the program PR1 that realizes the OS. Therefore, according to this embodiment, when an advertising image of a type set by the user as a target to be masked is included in an image displayed on the display device 120 in accordance with an arbitrary application program executed on the OS, the advertising image can be reliably masked.

[0036] (B: Transformation) The above embodiment can be modified as follows. (B-1: Variation 1) In the above embodiment, the selection unit 150b2 selected an advertising image from among a plurality of partial images using the first learning model MDL1. However, the use of the first learning model MDL1 is not essential, and any configuration may be used as long as an advertising image is selected from among a plurality of partial images based on the features of each of the plurality of partial images and the features of the advertising image. Similarly, the use of the second learning model MDL2 is not essential, and any configuration may be used as long as it determines whether or not an extracted advertising image is a target to be masked based on the correspondence between the features of the advertising image and the type of advertising image. Furthermore, if it is not necessary to specify a new target to be masked, the upload unit 150e may be omitted. Furthermore, in a configuration in which the first learning model MDL1 and the second learning model MDL2 are not used, the acquisition unit 150a may be omitted.

[0037] (B-2: Variation 2) In the above-described embodiment, the program PR1 is stored in the storage device 140, but the program PR1 may be manufactured or sold as a standalone program. When selling the program PR1, the program PR1 may be provided to a purchaser by writing the program PR1 to a computer-readable recording medium such as a flash ROM and distributing it, or by downloading it via a telecommunications line.

[0038] (C:Other) (1) In the above-described embodiment, ROM and RAM are exemplified as storage device 140, but storage device 140 may also be a flexible disk, a magneto-optical disk (e.g., a compact disk, a digital versatile disk, a Blu-ray (registered trademark) disc), 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.

[0039] (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.

[0040] (3) In the above-described embodiment, input and output information may be stored in a specific location (for example, memory) or may be managed using a 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.

[0041] (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).

[0042] (5) The order of the process procedures, sequences, flowcharts, etc. illustrated in the above-described embodiments may be rearranged unless inconsistent. 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.

[0043] (6) Each function illustrated in FIG. 2 is realized by any combination of at least one of hardware and 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 (for example, by wire, wirelessly, etc.) and these multiple devices. A functional block may also be realized by combining software with the single device or the multiple devices.

[0044] (7) The programs exemplified in the above-described embodiments should be broadly construed 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 they are called software, firmware, middleware, microcode, hardware description language, or by other names.

[0045] 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.

[0046] (8) In each of the foregoing embodiments, the terms "system" and "network" are used interchangeably.

[0047] (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.

[0048] (10) In the above-described embodiments, the terms "connected," "coupled," or any variation thereof refers 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 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.

[0049] (11) 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."

[0050] (12) 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 in a table, database, or other data structure), ascertaining, and the like. "Determining" and "determining" may also 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.

[0051] (13) In the above embodiments, when "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.

[0052] (14) In this disclosure, where articles are added by translation, such as a, an, and the in English, the disclosure may include that the nouns following these articles are plural.

[0053] (15) 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."

[0054] (16) Each aspect / embodiment 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 explicit notification, but may be implicit (e.g., not notifying the predetermined information).

[0055] (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.

[0056] A terminal device according to a first aspect of the present disclosure includes: an extraction unit that outputs a first advertisement image by extracting the advertisement image from a first image displayed on a display device; a determination unit that determines whether the type of the first advertisement image corresponds to a type set by a first user as a target to be masked based on a correspondence between a feature of the advertisement image and a type of the advertisement image; and a mask unit that displays a mask image that masks the first advertisement image on the display device when the determination unit determines that the first advertisement image corresponds to the type set as a target to be masked. According to this aspect, the advertisement image to be masked included in the image displayed on the display device can be reliably masked.

[0057] The extraction unit in the terminal device according to a second aspect (an example of the first aspect) of the present disclosure may include a division unit that divides the first image into a plurality of partial images by performing segmentation on the first image, and a selection unit that selects the first advertisement image from the plurality of partial images based on features of each of the plurality of partial images and features of the advertisement image. According to this aspect, the first image can be divided into an advertisement image and other images (for example, an image of a game screen), and the first advertisement image can be extracted from the former.

[0058] A terminal device according to a third aspect (an example of the first aspect or an example of the second aspect) of the present disclosure may further include an acquisition unit that manages types of advertising images set as targets to be masked or not to be masked in association with the first user, and acquires a determined learning model by communicating with a management device that determines a learning model for determining whether the type of the first advertising image corresponds to the type set as targets to be masked by the first user, using learning data corresponding to the type set as targets to be masked by the first user from among multiple learning data that each represent a correspondence between characteristics of advertising images and types of advertising images. Furthermore, the determination unit in this aspect may use the learning model acquired by the acquisition unit to determine whether the type of the first advertising image corresponds to the type set as targets to be masked by the first user. According to this aspect, a learning model suitable for the first user can be generated.

[0059] The terminal device according to a fourth aspect (an example of the third aspect) of the present disclosure may further include an upload unit that uploads image data representing the first advertisement image to the management device when the first user designates the first advertisement image as a mask target. According to this aspect, accumulation of learning data becomes easy.

[0060] An advertising image display method according to a sixth aspect of the present disclosure includes: outputting a first advertising image by extracting an advertising image from a first image displayed on a display device; determining whether the type of the first advertising image corresponds to a type set by a first user as a target to be masked based on a correspondence between a feature of the advertising image and a type of the advertising image; and displaying a mask image that masks the first advertising image on the display device if it is determined that the first advertising image corresponds to the type set as a target to be masked. According to the advertising image display method of the sixth aspect, as with the terminal device of the first aspect, it is possible to reliably mask an advertising image to be masked that is included in an image displayed on a display device. [Explanation of symbols]

[0061] 10...terminal device, 20...management device, 110...communication device, 120...display device, 130...input device, 140...storage device, 150...processing device, 150a...acquisition unit, 150b...extraction unit, 150b1...division unit, 150b2...selection unit, 150c...discrimination unit, 150d...mask unit, 150e...upload unit, 160...bus, PR1...program, MDL1...first learning model, MDL2...second learning model.

Claims

1. an extracting unit that extracts an advertisement image from a first image displayed on the display device and outputs a first advertisement image; a determination unit that determines whether or not the type of the first advertisement image corresponds to a type set as a mask target by a first user based on a correspondence relationship between a feature of the advertisement image and a type of the advertisement image; a masking unit that displays a mask image that masks the first advertising image on the display device when the determining unit determines that the first advertising image corresponds to a type set as a mask target; A terminal device comprising:

2. The extraction unit a division unit that divides the first image into a plurality of partial images by performing segmentation on the first image; a selection unit that selects the first advertisement image from among the plurality of partial images based on features of each of the plurality of partial images and features of the advertisement image, 2. The terminal device according to claim 1, wherein:

3. The apparatus further includes an acquisition unit that acquires a determined learning model by communicating with a management device that manages types of advertising images that are set as targets to be masked or not to be masked in association with the first user, and determines a learning model for determining whether or not the type of the first advertising image corresponds to the type that is set as a target to be masked by the first user, using learning data corresponding to the type that is set as a target to be masked by the first user from among a plurality of learning data that each represent a correspondence relationship between a feature of an advertising image and a type of advertising image, and acquires the determined learning model; The determination unit determines whether or not a type of the first advertisement image corresponds to a type set as a mask target by the first user, using the learning model acquired by the acquisition unit. The terminal device according to claim 1 .

4. an upload unit that uploads image data representing the first advertisement image to the management device when the first user designates the first advertisement image as a mask target; The terminal device according to claim 3 .

5. outputting a first advertising image by extracting the advertising image from the first image displayed on the display device; determining whether or not the type of the first advertisement image corresponds to a type set as a mask target by a first user based on a correspondence relationship between a feature of the advertisement image and a type of the advertisement image; When it is determined that the first advertisement image corresponds to a type set as a mask target, a mask image that masks the first advertisement image is displayed on the display device; and a method for displaying advertising images, including:

Images