Information processing apparatus

Abstract

The present application is to properly classify an image including a sensitive element. An information processing apparatus includes a conversion unit that converts image data into a graph structure, a determination unit that determines whether a sensitive element set in advance is included in the graph structure, and a classification unit that, in a case where the sensitive element is included, gives the image data a sensitive label and classifies the image data.

Description

Technical Field

[0001] This invention relates to the technical field of an information processing device. Background Technology

[0002] As such a device, for example, a system has been proposed that enables a large-scale language model (LLM) to generate document-based query data and uses the pairing of documents and query data to learn the search model of a chatbot (see Patent Document 1).

[0003] Patent Document 1: Japanese Patent Application Publication No. 2023-076413 Summary of the Invention

[0004] In machine learning, training models requires preparing large amounts of training data (e.g., large amounts of image data). When processing large amounts of image data, there is a possibility of viewing sensitive images within it. Since sensitive images can sometimes have a negative psychological impact on viewers, it is preferable to take preventative measures to avoid unintentional viewing. However, it is difficult to determine whether an image is sensitive without viewing it.

[0005] The present invention was made in view of the above-mentioned problems, and its objective is to provide an information processing apparatus capable of appropriately classifying sensitive images.

[0006] An information processing apparatus according to one aspect of the present invention includes: a conversion unit that converts image data into a graph structure; a determination unit that determines whether the graph structure contains a pre-defined sensitive element; and a classification unit that, if the sensitive element is contained, assigns a sensitive label to the image data and classifies it. Attached Figure Description

[0007] Figure 1 This is a block diagram illustrating the hardware structure of the information processing device involved in the implementation method.

[0008] Figure 2 This is a block diagram illustrating the functional structure of the information processing apparatus involved in the implementation method.

[0009] Figure 3 It is a flowchart illustrating the process of classifying operations of the information processing apparatus based on the implementation method.

[0010] Figure 4 This is a top view representing an example of a sensitive image and graph structure.

[0011] Figure 5 It is a flowchart illustrating the process of a search operation based on the information processing apparatus involved in the implementation method. Detailed Implementation

[0012] Hereinafter, embodiments of the information processing apparatus will be described with reference to the accompanying drawings.

[0013] (Hardware structure)

[0014] First, refer to Figure 1 The hardware structure of the information processing device involved in the implementation method will be described. Figure 1 This is a block diagram illustrating the hardware structure of the information processing device involved in the implementation method.

[0015] exist Figure 1 In this embodiment, the information processing apparatus 10 includes an arithmetic unit 110, a storage unit 120, a communication unit 130, an input unit 140, and an output unit 150. The arithmetic unit 110, the storage unit 120, the communication unit 130, the input unit 140, and the output unit 150 are connected to each other via a data bus.

[0016] The arithmetic processing unit 110 is configured to perform various arithmetic operations in the information processing unit 10. The arithmetic processing unit 110 may have a processor. The arithmetic processing unit 110 may have a single processor or multiple processors. That is, the arithmetic processing unit 110 may have more than one processor. Furthermore, the processor may be a multi-core processor. In the case where the arithmetic processing unit 110 has a single processor that functions as a multi-core processor, it can be said that the arithmetic processing unit 110 logically has multiple processors.

[0017] The processor included in the computing device 110 may be at least one of a central processing unit (CPU), a graphics processing unit (GPU), a field-programmable gate array (FPGA), and a tensor processing unit (TPU).

[0018] Storage device 120 may be at least one of random access memory (RAM), read-only memory (ROM), hard disk drive, magneto-optical disk drive, solid-state drive (SSD), and optical disk array. That is, storage device 120 may be implemented by a single device or by multiple devices.

[0019] Storage device 120 is capable of storing desired data. The computer program CP executed by the arithmetic unit 110 can be stored in storage device 120. When the arithmetic unit 110 executes the computer program CP, storage device 120 can temporarily store data temporarily used by the arithmetic unit 110.

[0020] Furthermore, the computer program CP can be recorded on a computer-readable and non-temporary recording medium. In this case, the computer program CP can be stored in the storage device 120 by reading the recording medium using a recording medium reading device (not shown) included in the information processing device 10. Additionally, at least one of optical discs, magnetic media, magneto-optical discs, semiconductor memory, and any medium capable of storing other programs can be used as the recording medium. The computer program CP can also be obtained from an external (not shown) device outside the information processing device 10 via the communication device 130. In other words, the computer program CP can be downloaded from an external device to the storage device 120 of the information processing device 10.

[0021] The arithmetic unit 110 (e.g., a processor) can perform the processing to be performed by the information processing unit 10 together with the storage device 120 storing the computer program CP (in other words, together with the storage device 120 and the computer program CP stored in the storage device 120). For example, the arithmetic unit 110 can implement logical function blocks for performing the processing to be performed by the information processing unit 10 within the arithmetic unit 110 (e.g., within the processor) by executing the computer program CP.

[0022] The communication device 130 is configured to communicate with external devices of the information processing device 10. Furthermore, the communication device 130 can perform both wired and wireless communication.

[0023] Input device 140 is a device capable of accepting information input from an external source to information processing device 10. Input device 140 may include user-operable devices (e.g., keyboard, mouse, touch panel, etc.) of information processing device 10. Input device 140 may include, for example, a recording medium reading device capable of reading information recorded on a recording medium removable from information processing device 10, such as a Universal Serial Bus (USB) memory. Furthermore, when information is input to information processing device 10 via communication device 130 (in other words, when information processing device 10 obtains information via communication device 130), communication device 130 may function as an input device.

[0024] Output device 150 is a device capable of outputting information to an external device of information processing device 10. Output device 150 may include a display device capable of outputting visual information such as characters and images as the aforementioned information. Additionally, output device 150 may include a speaker capable of outputting auditory information such as sound as the aforementioned information. Output device 150 may be configured to output the aforementioned information to other devices (e.g., control information of other devices). Output device 150 may, for example, output information to a recording medium removable from information processing device 10, such as a USB memory. Furthermore, when information processing device 10 outputs information via communication device 130, communication device 130 may function as an output device.

[0025] <Functional Structure>

[0026] Next, refer to Figure 2 The functional structure of the information processing device 10 involved in the implementation method will be explained. Figure 2 This is a block diagram illustrating the functional structure of the information processing apparatus involved in the implementation method.

[0027] exist Figure 2 In this embodiment, the information processing apparatus 10 is configured to classify images containing sensitive elements. Furthermore, the information processing apparatus 10 is configured to search for a desired image from an image data set containing sensitive images. The information processing apparatus 10 includes an image conversion unit 210, a determination unit 220, an image classification unit 230, an image database (DB) 240, and a search unit 250 as components for implementing its functions. Additionally, the image conversion unit 210, the determination unit 220, the image classification unit 230, and the search unit 250 can each be a processing block implemented by the aforementioned computing device 110. Furthermore, the image DB 240 can be a database implemented by the aforementioned storage device 120.

[0028] The image conversion unit 210 is configured to convert an input unclassified image into a graph structure. Here, a graph structure can refer to data consisting of groups of nodes representing the relationships between each part of an object within an image and groups of edges representing the relationships between nodes. The image conversion unit 210 may also have the function of vectorizing graph structure features. The image conversion unit 210 can convert image data into a graph structure using a machine learning model. This model can be a model that takes image data as input and outputs a graph structure (or feature vectors of the graph structure).

[0029] The determination unit 220 determines whether the original image (i.e., the image before it is converted into a graph structure in the image conversion unit 210) contains sensitive elements based on the graph structure (or the feature vector of the graph structure) returned by the image conversion unit 210. For example, the determination unit 220 may pre-store judgment criteria for sensitive elements in the graph structure and determine whether the image contains sensitive elements based on these criteria. For instance, the sensitive elements in the graph structure can be set based on the category and positional relationship of objects. Alternatively, the sensitive elements in the graph structure can be set based on the actions of a person.

[0030] The image classification unit 230 is configured to classify unclassified images based on the determination result of the determination unit 220. Specifically, if the determination unit 220 determines that an image contains sensitive elements, the image classification unit 230 assigns a sensitive label to the image and stores it in the image DB 240. On the other hand, if the determination unit 220 determines that an image does not contain sensitive elements, the image classification unit 230 does not assign a sensitive label and stores the image in the image DB 240.

[0031] Image DB240 is configured to store multiple images. Image DB stores images assigned sensitive labels (hereinafter appropriately referred to as "sensitive images") and images not assigned sensitive labels in the image classification unit 230. Image DB240 may also be configured to store graph structures in addition to images. For example, image DB240 may store images and graph structures converted from those images by the image conversion unit 210 in a mutually related manner.

[0032] The search unit 250 is configured to search for a desired image from a plurality of images stored in the image DB240. The search unit 250 can, for example, search for images based on search criteria input by the user. The search unit 250 can output the image obtained as a search result to the user. For example, the search unit 250 can display the image obtained as a search result on a display screen or the like. If the search results include a sensitive image, the search unit 250 may not display the sensitive image. However, the search unit 250 may display the sensitive image if the user allows its display.

[0033] (Classification of actions)

[0034] Next, refer to Figure 3 and Figure 4 The process of the classification operation (i.e., the operation of classifying images according to the graph structure) of the information processing apparatus 10 according to the implementation method will be described. Figure 3 It is a flowchart illustrating the process of classifying operations of the information processing apparatus based on the implementation method. Figure 4 This is a top view representing an example of a sensitive image and graph structure.

[0035] like Figure 3 As shown, if the classification operation based on the information processing apparatus 10 according to the embodiment begins, the image conversion unit 210 first acquires an unclassified image (step S101). Then, the image conversion unit 210 converts the image data of the acquired unclassified image into a graph structure (step S102).

[0036] Next, the determination unit 220 determines whether the image contains sensitive elements based on the image structure converted by the image conversion unit 210 (step S103). For example, such as Figure 4 As shown, suppose there is an image of a car colliding with a person. In this case, the graph structure obtained from the converted image shows that the car and the person are in a very close position. Therefore, the determination unit 220 can determine whether the image contains sensitive elements (i.e., contains the moment of the traffic accident) based on the category and positional relationship of the objects in the graph structure. Furthermore, the determination unit 220 can determine whether the image contains sensitive elements based on information related to the actions of the person contained in the graph structure. For example, if the graph structure contains information related to "the person making a gesture of holding a knife," the determination unit 220 can determine that the image contains sensitive elements.

[0037] If an image is determined to contain sensitive elements (step S103: Yes), the image classification unit 230 assigns a sensitive label to the image (step S104) and stores it in the image DB250 (step S105). On the other hand, if an image is determined not to contain sensitive elements (step S103: No), the image classification unit 230 does not assign a sensitive label and stores the image in the image DB250.

[0038] (Search action)

[0039] Next, refer to Figure 5 The process of the search operation (i.e., the operation of searching for a desired image from the classified images) of the information processing apparatus 10 according to the implementation method will be described. Figure 5 It is a flowchart illustrating the process of a search operation based on the information processing apparatus involved in the implementation method.

[0040] like Figure 5 As shown, if a search operation based on the information processing device 10 according to the embodiment is initiated, the search unit 250 first searches for the desired image from a plurality of images stored in the image DB (step S201). When searching for an image, the user can input text information representing the search criteria.

[0041] Next, the search unit 250 determines whether the images obtained as search results contain sensitive images (i.e., images with sensitive tags) (step S202). Alternatively, if the search results do not contain sensitive images (step S202: No), the search unit 250 directly outputs the images obtained as search results to the user (step S204).

[0042] On the other hand, if the search results contain sensitive images (step S202: Yes), the search unit 250 determines whether to allow the display of the sensitive images (step S203). Furthermore, the permission to display sensitive images can be preset by the user or confirmed by the user at the time. For example, the search unit 250 can output the message "Can I display sensitive images?" to the user, and if it receives a "Yes" response from the user, it determines that the display of sensitive images is allowed.

[0043] If displaying sensitive images is permitted (step S203: Yes), the search unit 250 directly outputs the images obtained as search results to the user (step S204). That is, even if the images are sensitive, they are displayed to the user. On the other hand, if displaying sensitive images is not permitted (step S203: No), the search unit 250 excludes sensitive images from the images obtained as search results before outputting them (step S205). In this case, sensitive images are not displayed to the user.

[0044] (Technical effect)

[0045] Next, the technical effects obtained by the information processing apparatus 10 according to the implementation method will be explained.

[0046] like Figures 1 to 5 As explained, in the information processing apparatus 10 according to the embodiment, it is determined whether an image contains sensitive elements based on a graph structure, and then classified according to the determination result. In this way, images containing sensitive elements can be automatically classified (e.g., without human visual confirmation). Furthermore, by using a graph structure, the apparatus can easily interpret the elements contained in the image, thus improving classification accuracy.

[0047] Furthermore, in the information processing apparatus 10 according to the embodiment, sensitive images are not output (displayed) when searching for categorized images. This prevents users searching for images from unintentionally viewing sensitive images. Moreover, in this embodiment, even if an image is sensitive, it will be displayed if the user allows it to be displayed. Therefore, sensitive images can be displayed to users who have permission to view them.

[0048] The invention described below is an embodiment derived from the above-described implementation.

[0049] An information processing apparatus according to one aspect of the present invention includes: a conversion unit that converts image data into a graph structure; a determination unit that determines whether the graph structure contains a pre-defined sensitive element; and a classification unit that, if the sensitive element is contained, assigns a sensitive label to the image data and classifies it. In the above embodiment, "image conversion unit 210" is equivalent to an example of "conversion unit", "determination unit 220" is equivalent to an example of "determination unit", and "image classification unit 230" is equivalent to an example of "classification unit".

[0050] In the information processing apparatus described above, the sensitive elements can be set according to the categories and positional relationships of objects in the graph structure. In this way, sensitive elements can be appropriately determined based on the categories and positional relationships of objects in the graph structure.

[0051] In the information processing apparatus described above, the sensitive elements can be set based on the actions of the figures in the graph structure. In this way, sensitive elements can be appropriately determined based on the actions of the figures in the graph structure.

[0052] The information processing apparatus described above may further include: a storage unit that stores the image data classified by the classification unit; and a search unit that searches the image data in the storage unit based on the user's input, wherein the search unit is configured not to output image data with the sensitive tags as search results. This prevents images containing sensitive elements from being unintentionally viewed. In the above embodiment, "image DB240" is one example of a "storage unit," and "search unit 250" is one example of a "search unit."

[0053] In the information processing apparatus described above, the search unit can output the image data with the sensitive tag as a search result when the user allows the output of image data containing the sensitive elements. In this way, images containing sensitive elements can be displayed to a subset of users who are authorized to view them.

[0054] The present invention is not limited to the embodiments described above, and appropriate modifications can be made without departing from the spirit or idea of ​​the invention as read in its entirety from the claims and description. Information processing apparatuses that accompany such modifications are also included within the technical scope of the present invention.

[0055] Symbol Explanation

[0056] 10-Information processing device, 110-Arithmetic processing device, 120-Storage device, 130-Communication device, 140-Input device, 150-Output device, 210-Image conversion unit, 220-Decision unit, 230-Image classification unit, 240-Image database, 250-Search unit.

Claims

1. An information processing device, characterized in that, have: A conversion unit that converts image data into a graph structure; The determination unit determines whether the graph structure contains pre-defined sensitive elements; and A classification unit, which assigns sensitive labels to the image data and classifies it when the sensitive elements are included.

2. The information processing device according to claim 1, characterized in that, The sensitive elements are set according to the categories and positional relationships of objects in the graph structure.

3. The information processing device according to claim 1, characterized in that, The sensitive elements are set based on the actions of the characters in the graph structure.

4. The information processing apparatus according to any one of claims 1 to 3, characterized in that, It also has: Storage unit, which stores the image data classified by the classification unit; and The search unit searches the image data within the storage unit based on user input. The search unit is configured not to output the image data with the sensitive tags as search results.

5. The information processing apparatus according to claim 4, characterized in that, When the user allows the output of image data containing the sensitive elements, the search unit will output the image data with the sensitive tag as the search result.

Images