Processing device, processing program, and processing method

Abstract

To output in an easily understandable manner the result of determination of whether or not accept restrictions by a prescribed regulation or guideline.SOLUTION: Provided is a processing device including at least one processor, with the at least one processor constituted so as to carry out the process of: accepting input of a content in which one or a plurality of texts are included that include at least one word which is the object of determination; acquiring the one or plurality of texts from the accepted content; determining, for each of the acquired one or plurality of texts, whether or not each text in the content can be used, on the basis of restrictions by a prescribed regulation or guideline; and outputting determination result information in such a way that determination result information associated with the result of determination is displayed together with the content.SELECTED DRAWING: Figure 15

Description

[Technical Field]

[0001] The present disclosure relates to a processing device, a processing program, and a method for determining whether text included in content is subject to regulation by a predetermined law or guideline. [Background technology]

[0002] It has been known for some time that there is an Act on Ensuring the Quality, Efficacy and Safety of Pharmaceuticals, Medical Devices, etc., which regulates inappropriate advertising for pharmaceuticals, quasi-drugs, cosmetics, medical devices, regenerative medicine products, etc., because the way the advertising is done could have a significant impact on health and hygiene. In relation to this situation, for example, Patent Document 1 describes a system that has an NG expression database in which NG sentences and NG words are registered in advance, and that compares utterance data entered as text with the NG expression database to determine whether it is NG or not, and reports the result. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2011-204178 Summary of the Invention [Problem to be solved by the invention]

[0004] Therefore, in consideration of the above-described techniques, the present disclosure provides a processing device, a processing program, or a processing method for outputting the result of a determination as to whether or not a device is subject to regulation by a predetermined law or guideline in a more understandable manner. [Means for solving the problem]

[0005] According to one aspect of the present disclosure, there is provided a processing device including at least one processor, the at least one processor being configured to perform processing to accept input of content including one or more texts that include at least one word to be judged, acquire the one or more texts from the accepted content, determine for each of the acquired one or more texts whether or not each text can be used in the content based on regulations imposed by specified laws and regulations or guidelines, and output the judgment result information related to the result of the judgment so that the judgment result information is displayed together with the content.

[0006] According to one aspect of the present disclosure, there is provided a processing program that, when executed by at least one processor, causes the at least one processor to function in the following manner: accept input of content containing text including at least one word to be judged; acquire the text from the accepted content; judge whether the acquired text can be used in the content based on regulations imposed by specified laws and regulations or guidelines; and output judgment result information related to the result of the judgment so that the judgment result information is displayed together with the content.

[0007] According to one aspect of the present disclosure, there is provided a "processing method executed by at least one processor, comprising: a step of accepting input of content containing text including at least one word to be judged; a step of acquiring the text from the accepted content; a step of judging whether the acquired text can be used in the content based on regulations imposed by predetermined laws and regulations or guidelines; and a step of outputting judgment result information related to the result of the judgment so that the judgment result information is displayed together with the content." [Effects of the Invention]

[0008] According to the embodiments of the present disclosure, it is possible to provide a processing device, a processing program, or a processing method for outputting the result of the determination as to whether or not a certain item is subject to regulation by a predetermined law or guideline in a more understandable manner.

[0009] It should be noted that the above effects are merely illustrative for the sake of convenience and are not limiting. In addition to or instead of the above effects, any effect described in this disclosure or an effect obvious to a person skilled in the art may be achieved. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a schematic diagram of a processing system 1 according to one embodiment of the present disclosure. [Figure 2] FIG. 2 is a block diagram showing a configuration of the terminal device 100 according to an embodiment of the present disclosure. [Figure 3] FIG. 3 is a block diagram showing a configuration of the server device 200 according to an embodiment of the present disclosure. [Figure 4A] FIG. 4A is a diagram conceptually illustrating a determination database stored in the server device 200 according to an embodiment of the present disclosure. [Figure 4B] FIG. 4B is a diagram conceptually illustrating a content table stored in the server device 200 according to an embodiment of the present disclosure. [Figure 5] FIG. 5 is a diagram showing a processing flow executed in the processing device 100 according to an embodiment of the present disclosure. [Figure 6] FIG. 6 is a diagram showing a processing flow executed in the server device 200 according to an embodiment of the present disclosure. [Figure 7] FIG. 7 is a diagram showing a processing flow executed in the server device 200 according to an embodiment of the present disclosure. [Figure 8] FIG. 8 is a diagram illustrating a processing flow for generating a trained model according to an embodiment of the present disclosure. [Figure 9] FIG. 9 is a diagram illustrating a processing flow for generating a trained model according to an embodiment of the present disclosure. [Figure 10] FIG. 10 is a diagram illustrating a processing flow for generating a trained model according to an embodiment of the present disclosure. [Figure 11] FIG. 11 is a diagram showing a processing flow executed in the server device 200 according to an embodiment of the present disclosure. [Figure 12] FIG. 12 is a diagram showing a processing flow executed in the terminal device 100 according to an embodiment of the present disclosure. [Figure 13] FIG. 13 is a diagram showing an example of a screen output to the terminal device 100 according to an embodiment of the present disclosure. [Figure 14] FIG. 14 is a diagram illustrating an example of content according to an embodiment of the present disclosure. [Figure 15] FIG. 15 is a diagram illustrating an example of a screen output to the terminal device 100 according to an embodiment of the present disclosure. [Figure 16] FIG. 16 is a diagram showing an example of a screen output to the terminal device 100 according to an embodiment of the present disclosure. [Figure 17] FIG. 17 is a diagram showing an example of a screen output to the terminal device 100 according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0011] Embodiments of the present disclosure will be described with reference to the accompanying drawings, in which the same reference numerals are used to designate common components.

[0012] 1. Overview of Processing System 1 The processing system 1 according to the present disclosure is primarily used to determine whether content such as advertisements uses wording or expressions regulated by laws, regulations, or guidelines, such as the Act on Ensuring the Quality, Efficacy, and Safety of Pharmaceuticals, Medical Devices, etc. When a user inputs content to be determined and the processing system 1 receives the content, it acquires text from the content. The processing system 1 then determines whether the acquired text contains wording or expressions regulated by the laws, regulations, or guidelines, and outputs the result.

[0013] In this disclosure, examples of laws, regulations, or guidelines include various laws, regulations, and guidelines that regulate inappropriate labeling, such as the "Act on Ensuring Quality, Efficacy, and Safety of Pharmaceuticals, Medical Devices, etc.," the "Specified Commercial Transactions Act," the "Act Against Unjustifiable Premiums and Misleading Representations," the "Health Promotion Act," the "Food Labeling Act," the "Food Labeling Standards," and the "Medical Advertising Guidelines." These are not limited to those enacted by national or local governments, but may also be enacted by organizations or individuals such as specific industry groups, unions, companies, or associations. Furthermore, they do not necessarily have to be explicitly called "laws" or "guidelines," but may be any standards, rules, regulations, or rules. Furthermore, they do not necessarily have to be explicitly stated and made public in writing.

[0014] In addition, in this disclosure, examples of goods that are subject to regulation by laws, regulations, or guidelines include pharmaceuticals, quasi-drugs, regenerative medicine products, medical devices, health foods, foods with functional claims, cosmetics, and mail-order products, etc. However, these are of course only examples and are not limited to these.

[0015] Furthermore, in this disclosure, content typically includes advertising content, but is not limited to this. For example, content may include, in addition to advertisements, product packaging, product introductions, packaging, company introductions, comments and messages on social media, news, newspaper articles, and various other types of content. Furthermore, the content may be in any format, as long as it contains text containing at least one word. That is, various content formats are available, including webpage formats containing HTML and image data, image data formats consisting only of image data, standardized electronic document file formats such as PDF that can be used regardless of a specific operating system or hardware, and electronic file formats used for document editing, spreadsheets, and presentations. Furthermore, the content does not necessarily need to contain text in a form that can be recognized as text data; for example, the content may contain text as image data (i.e., within the subject).

[0016] In the following example, a case will be described in which it is determined whether advertising content provided in the form of a web page contains expressions that are restricted by laws and regulations or guidelines, but the present invention is not limited to this example.

[0017] 2. Configuration of Processing System 1 Fig. 1 is a schematic diagram of a processing system 1 according to an embodiment of the present disclosure. According to Fig. 1, the processing system 1 includes a terminal device 100 held by a user and a server device 200 communicatively connected to the terminal device 100 via a network 300. In the system 1, the server device 200 and the terminal device 100 execute programs stored in memory, thereby executing processing according to this embodiment. The server device 200 and the terminal device 100 communicate with each other as needed to transmit and receive various information (e.g., Figs. 4A and 4B), programs, and the like, required for the progress of processing.

[0018] 2 illustrates only one terminal device 100, but it is also possible to include two or more terminal devices 100. Also, although the server device 200 is illustrated as a single device, it is also possible to distribute the components and processes of the server device 200 to multiple server devices or cloud server devices. Furthermore, the processing according to this embodiment is executed by a system 1 including the server device 200 and the terminal device 100, but it is also possible to execute the processing by the terminal device 100 alone without using the server device 200. That is, in the present disclosure, the processing device may be either the terminal device 100 or the server device 200 as long as it is capable of executing the processing program or processing method according to the present disclosure. In the following examples, unless otherwise specified, a case will be described in which the server device 200 functions as a processing device, but the present disclosure is not limited to this example.

[0019] 3. Configuration of Terminal Device 100 Fig. 2 is a block diagram showing a configuration of a terminal device 100 according to an embodiment of the present disclosure. The terminal device 100 does not need to include all of the components shown in Fig. 2, and may have a configuration in which some components are omitted, or may include other components.

[0020] An example of the terminal device 100 is a laptop PC, but the present disclosure can also be suitably applied to any other device capable of executing the processing program according to the present disclosure, such as a portable terminal device capable of wireless communication, such as a smartphone, a feature phone, a personal digital assistant, a PDA, or a desktop computer.

[0021] 2, the terminal device 100 includes an output interface 111, a processor 112, a memory 113 including RAM, ROM, non-volatile memory (or HDD in some cases), etc., a communication interface 114 including a communication processing circuit and an antenna, and an input interface 115 including a touch panel 116, hard keys 117, etc. These components are electrically connected to each other via control lines and data lines.

[0022] The processor 112 is configured with a CPU (microcomputer) and functions as a control unit that controls other connected components based on various programs stored in the memory 113. Specifically, the processor 112 reads out from the memory 113 programs for executing the processes according to this embodiment and programs for running the OS, and executes them. In this embodiment, the processor 112 executes processes such as selecting content to be judged based on an instruction input received from a user via the input interface 115, transmitting the selected content to the server device 200 via the communication interface 114, receiving judgment result information from the server device 200 via the communication interface 114, storing the received judgment result information in the memory 113 in association with content ID information, and outputting the stored judgment result information together with the content to be judged via the output interface 111. The processor 112 may be configured with a single CPU or multiple CPUs. Furthermore, other types of processors, such as a GPU specialized for image processing, may be appropriately combined.

[0023] The memory 113 is composed of a ROM, a RAM, a non-volatile memory, a HDD, etc., and functions as a storage unit. The ROM stores instructions and commands for executing the game application and OS according to this embodiment as a program. The RAM is used to write and read data while the program stored in the ROM is being processed by the processor 112. The non-volatile memory is a memory into which data is written and read as the program is executed, and data written therein is retained even after the program execution ends. In this embodiment, the memory 113 stores programs for selecting content to be judged based on an instruction input received from a user via the input interface 115, transmitting the selected content to the server device 200 via the communication interface 114, receiving judgment result information from the server device 200 via the communication interface 114, storing the received judgment result information in the memory 113 in association with content ID information, and outputting the stored judgment result information together with the content to be judged via the output interface 111. Although not specifically shown, the memory 113 may be connected to a removable storage medium, a database, etc. via the input interface 115.

[0024] The communication interface 114 functions as a communication unit that transmits and receives information to and from the server device 200 or other terminal devices installed remotely via a communication processing circuit and an antenna. The communication processing circuit performs processing to receive, from the server device 200, programs for executing the processing according to this embodiment and various information used in the processing, etc., according to the progress of the processing. The communication processing circuit also performs processing to transmit, to the server device 200, various information required for executing the processing. In this embodiment, in particular, content to be judged and judgment result information are transmitted and received between the server device 200 and the communication processing circuit.

[0025] The communication processing circuit processes based on a wideband wireless communication system such as the LTE system, but it can also process based on a narrowband wireless communication system such as a wireless LAN such as IEEE802.11 or Bluetooth (registered trademark). Furthermore, wired communication can be used instead of or in addition to wireless communication.

[0026] The input interface 115 is composed of a touch panel 116 and / or hard keys 117, etc., and accepts operational inputs from a user. The touch panel 116 is arranged to cover the display serving as the output interface 111, and outputs position coordinate information corresponding to image data displayed on the display to the processor 112. Known touch panel methods, such as a resistive film method, a capacitive coupling method, and an ultrasonic surface acoustic wave method, can be used. In the present embodiment, as an example, the touch panel 116 detects tapping and swiping operations performed by a pointer to select or move an object displayed on the display. Note that the touch panel 116 is one example of an input interface, and naturally, other types of input interfaces can also be used. An input interface (such as a keyboard or mouse) connected wirelessly or via a wire to a main body including the processor 112, etc., can also be used.

[0027] The output interface 111 functions as an output unit that reads image information stored in the memory 113 in response to instructions from the processor 112 and outputs various displays (e.g., FIGS. 13 and 15 to 17) generated by executing the processing according to this embodiment. An example of the output interface 111 is a display configured as a liquid crystal display or an organic EL display, but the terminal device 100 itself does not necessarily have to be equipped with a display. For example, the output interface 111 may output information for various displays to a display connected by wire or wirelessly. In other words, the communication interface 114 may also function as the output interface 111.

[0028] In addition, when the terminal device 100 functions as a processing device, the processor 112 performs processes such as accepting input of content containing one or more texts that include at least one word to be judged, extracting the text from the image data if the accepted content contains text, acquiring one or more texts from the accepted content, determining whether or not each of the acquired one or more texts can be used in the content based on regulations imposed by specified laws and regulations or guidelines, and outputting judgment result information so that judgment result information related to the results of the judgment is displayed together with the content.

[0029] Similarly, when the terminal device 100 functions as a processing device, the memory 113 stores programs for executing processes such as accepting input of content containing one or more texts including at least one word to be judged, extracting text from the image data if the accepted content contains text, acquiring one or more texts from the accepted content, determining whether or not each of the acquired one or more texts can be used in the content based on regulations imposed by specified laws and regulations or guidelines, and outputting judgment result information related to the results of the judgment so that the judgment result information is displayed together with the content.

[0030] 4. Configuration of Server Device 200 Fig. 3 is a block diagram showing the configuration of a server device 200 according to an embodiment of the present disclosure. The server device 200 does not need to include all of the components shown in Fig. 3, and may have a configuration in which some components are omitted, or may include other components.

[0031] 3, the server device 200 includes a memory 211 including RAM, ROM, non-volatile memory, and HDD, a processor 212 including a CPU, and a communication interface 213. These components are electrically connected to each other via control lines and data lines.

[0032] The memory 211 includes RAM, ROM, non-volatile memory, and HDD, and functions as a storage unit. The memory 211 stores instructions and commands for executing the processes and OS according to this embodiment as a program. Such programs are loaded and executed by the processor 212. The memory 211 (especially the RAM) is temporarily used to write and read data while the program is being executed by the processor 212. The memory 211 also stores the determination database shown in FIG. 4A and the content table shown in FIG. 4B, as well as drawing information used to output the screens shown in FIGS. 13 and 15 to 17. The memory 211 also stores programs for executing processes such as accepting input of content containing one or more pieces of text including at least one word to be determined, extracting the text from the image data if the received content contains text, acquiring one or more pieces of text from the received content, determining whether each piece of acquired text can be used in the content based on regulations imposed by predetermined laws and regulations or guidelines, and outputting determination result information so that the determination result information related to the results of the determination is displayed together with the content. The memory 212 also stores a trained text judgment model, a trained reason judgment model, and a trained alternative judgment model that are used in various judgment processes. Although not specifically shown, the judgment database stored in the memory 211 may be stored in a database device or the like that is installed remotely via a network.

[0033] The processor 212 is composed of a CPU (microcomputer) and functions as a control unit for controlling other connected components based on various programs stored in the memory 211. In this embodiment, the processor 212 particularly performs processes such as accepting input of content containing one or more pieces of text that include at least one word to be determined, extracting text from the image data if the received content contains text, acquiring one or more pieces of text from the received content, determining whether or not each piece of acquired text can be used in the content based on regulations imposed by predetermined laws and regulations or guidelines, and outputting determination result information related to the results of the determination so that the information on the determination result is displayed together with the content. The processor 212 may be composed of a single CPU or multiple CPUs.

[0034] As an example, the communication interface 213 performs processes such as modulation and demodulation to transmit and receive programs for executing the processes according to this embodiment, various information, and the like, to and from each terminal device 100 via the network 300, or to and from other server devices or database devices via the network 300. The communication interface 213 communicates with each terminal device and other server devices according to the above-mentioned wireless communication method or a known wired communication method. In this embodiment, the communication interface 213 transmits and receives content to be determined and determination result information, particularly to and from the terminal device 100.

[0035] 5. Information stored in memory 4A is a diagram conceptually illustrating a determination database stored in the server device 200 according to an embodiment of the present disclosure. The information stored in the determination database is updated as needed in accordance with various laws, regulations, and guidelines.

[0036] As shown in FIG. 4A , the assessment database stores category information, target information, availability information, reason information, and alternative information, each associated with another. "Category information" generally indicates the content of a regulation depending on the product. Therefore, the "category information" indicates the category of the product that is subject to the regulation. This product category is an example of category information and may be any information for classifying the target of the regulation. "Target information" indicates the text that is subject to the assessment. For example, if the word "fine wrinkles" is included in the content, it may be subject to assessment. "Availability information" indicates the assessment result when the text indicated as the target of assessment is used for the product indicated in the category. "Inappropriate" indicates expressions that are subject to regulation by laws and guidelines; "Caution required" indicates expressions that may be subject to regulation depending on how they are expressed, or for which a clear assessment cannot be made at this time; and "Appropriate" indicates expressions that comply with laws and guidelines or are not subject to such regulation. "Reason information" indicates the reason for the assessment of inappropriateness or requiring caution. "Alternative information" indicates alternatives to avoid the assessment of inappropriateness or requiring caution.

[0037] Although three pieces of information, inappropriate, caution required, and appropriate, are stored as the appropriate / inappropriate information, the information is not limited to these. For example, it may be only two pieces of information, "inappropriate and appropriate," "inappropriate and caution required," or "appropriate and caution required," or it may be only one of these pieces of information, or it may be further subdivided to provide multiple pieces of information, or it may be numerical or level information indicating the probability of being determined as inappropriate or appropriate. Furthermore, the wording does not have to be expressions such as inappropriate, caution required, appropriate, etc., but may be any wording, symbol, number, etc., such as NG, gray, OK, O (circle), × (x), △ (triangle), etc.

[0038] This judgment database can be used for text judgment processing, judgment reason judgment processing, and alternative judgment processing. When a trained judgment model is used in each judgment, the database can also be used as training data for training each trained judgment model.

[0039] 4B is a diagram conceptually illustrating a content table stored in the server device 200 according to an embodiment of the present disclosure. The content table is generated each time content is received from the terminal device 100 and is updated as needed.

[0040] 4B , the content table stores content ID information, category information, text information, location information, character count information, propriety information, reason information, alternative information, and the like, in association with one another. The "content ID information" is information for identifying each piece of content to be judged and is unique to each piece of content. The content ID information is newly generated each time new content is transmitted from the terminal device 100 to the server device 200 and stored in the memory 211 of the server device 200. The "category information" is information for identifying the category of a product for which the content to be judged is used as an advertisement. The "text" information is information for identifying text included in each piece of content and acquired from the content. The information may be the text data itself, or information identifying the location where the text data is stored or the text data. In this embodiment, content includes one or more pieces of text depending on the content. Therefore, multiple pieces of text may be stored in association with the same content ID information. The "location information" is information for identifying the location where each piece of text is located in the content. This information may be any information that can roughly identify the position of each piece of text, such as the coordinates where each piece of text is located in the content, the number of pixels from the edge of the content, the number of rows and columns, the number of characters, etc. "Character count information" is information that indicates the number of characters that make up the text to be judged. "Possibility information," "reason information," and "alternative information" are all types of judgment result information, and each piece of information described in FIG. 4A is stored in association with each piece of text. This information is stored in association with the text to be judged each time processor 212 performs text judgment processing, judgment reason judgment processing, and alternative judgment processing.

[0041] 6. Processing flow performed by the terminal device 100 (content output processing) Fig. 5 is a diagram showing a processing flow executed in the terminal device 100 according to an embodiment of the present disclosure. Specifically, Fig. 5 shows a processing flow executed from when the advertisement determination tool is started in the terminal device 100 until content to be determined is transmitted to the server device 200. This processing flow is mainly executed by the processor 112 of the terminal device 100 reading and executing a program stored in the memory 113.

[0042] 5, the processor 112 accepts a user's access to the advertisement determination tool via the input interface 115 and starts the advertisement determination tool (S111). Note that, while a typical example of such an advertisement determination tool is a tool provided by application software pre-installed on the terminal device 100, it is not limited to this. Another example of such a tool is a tool provided via application software for a web browser, etc.

[0043] FIG. 13 is a diagram illustrating an example of a screen output to the terminal device 100 according to an embodiment of the present disclosure. Specifically, FIG. 13 is a diagram illustrating an example of a judgment target selection screen output to the display via the output interface 111 after the advertisement determination tool is launched in S111 of FIG. 5. According to FIG. 13, the judgment target selection screen displays a format selection area 11 for selecting the format of the content to be determined, a storage location input area 12 indicating the storage location of the content to be determined, and a judgment start button 13 for transmitting a judgment start instruction to the server device 200. The user selects the format of the content to be determined from the judgment target area 12 via the input interface 115. After the selection, the corresponding check box is displayed in black. Next, the user selects the storage location input area corresponding to the content to be determined via the input interface 115 and inputs the storage location. After that, when the user selects the judgment start button 13, the content stored in the storage location input in the storage location input area is read out together with the judgment start instruction and transmitted to the server device 200.

[0044] FIG. 14 is a diagram illustrating an example of content according to an embodiment of the present disclosure. Specifically, FIG. 14 illustrates, as an example of content, an example of advertising content for cosmetics provided in the form of a webpage including HTML and image data. FIG. 14 illustrates webpage 31, which is advertising content for cosmetics. Webpage 31 includes, as hypertext written in markup language, text 32a that reads "Maybe it can improve your skin?" and text 32b that reads "It will reduce the appearance of fine wrinkles caused by dryness." Webpage 31 also includes, as image data, a human-shaped object 33a, an image object 33b that reads "Get beautiful skin like a baby!", and an image object 33c that reads "Say goodbye to fine wrinkles." Note that although other text and image data are included, their description will be omitted.

[0045] In this embodiment, the content shown in FIG. 14 as an example is stored in a predetermined storage location in the memory 113 and is used in the processing described below.

[0046] 5, processor 112 receives a user's input in format selection area 11 (FIG. 13) via input interface 115 and selects the format of the content to be judged (S112). That is, in the example of FIG. 14, since the advertising content is in web page format, "web page" is selected as the content format. Then, processor 112 enables storage location input area 12 (FIG. 13) corresponding to the selected format. Processor 112 receives a user's input in storage location input area 12 (FIG. 13) enabled via input interface 115 and selects a storage location of the content to be judged (S113). Next, processor 112 receives a user's input to judgment start button 13 (FIG. 13) via input interface 115 and reads out the content stored in the storage location entered in storage location input area 12 by referring to memory 113 (S114). Processor 112 transmits the read content together with a judgment start instruction to the server device via communication interface 114 (S115). 14, the content in the form of a web page made up of HTML and image data is sent as the object of determination to the server device 200. This completes the processing flow.

[0047] 13 does not specifically show the selection of a category of a product advertised by the content to be determined. However, in the process of S111 to S115, processor 112 accepts a user's instruction input via input interface 115 to select a category advertised by the content to be determined, and transmits the selected category together with the content to server device 200 in S115.

[0048] 7. Processing flow (determination processing) performed by the server device 200 Fig. 6 is a diagram showing a processing flow executed in the server device 200 according to an embodiment of the present disclosure. Specifically, Fig. 6 shows a processing flow performed from receiving content to be determined from the terminal device 100 to outputting a determination result. This processing flow is mainly performed by the processor 212 of the server device 200 reading and executing a program stored in the memory 211.

[0049] 6, the processor 212 receives an instruction to start judgment, content to be judged, and a category transmitted from the terminal device 100 via the communication interface 213, thereby accepting input of the content (S211). Then, upon acquiring the content, the processor 112 generates new content ID information for identifying the acquired content, and stores the content and category information in association with the content ID information in the memory 211. Here, in addition to the original data of the acquired content, data obtained by converting the acquired content into image data is stored as the content to be judged.

[0050] Next, processor 212 reads the acquired content from memory 211 and determines whether there is a portion for which various determination processes, such as text determination processes, have not yet been performed (S212). If there is a portion for which determination processes have not yet been performed, processor 212 determines whether text data is included in the portion of the content for which determination has not yet been performed (S213). If the determination results in text data being included, processor 212 acquires the text data without performing text extraction processing and stores it in the content table of memory 211 in association with content ID information (S215). On the other hand, if text data is not included, processor 212 extracts text data from the content to be determined using optical character recognition technology, such as OCR (S214). Then, processor 212 acquires the extracted text data and stores it in the content table of memory 211 in association with content ID information (S215).

[0051] 14, for example, and determines that the portion of image object 33c that reads "Say goodbye to fine lines" has not yet been judged. Since image object 33c is image data, processor 212 proceeds to S214 and extracts text data from the image object. Processor 212 then extracts the text data "Say goodbye to fine lines" from image object 33c and stores it in memory 211 in association with the content ID information.

[0052] Here, each acquired text is composed of one or more words. Therefore, the processor 212 reads the stored text from the memory 211 and performs a process of decomposing and analyzing each word that constitutes the read text (S216). One example of this process is to store dictionary data in which various words are stored in advance in the memory 211 or a database device, and check whether the read text contains any of the words stored in the dictionary data. Another example of this process is to perform morphological analysis on the read text using a morphological analysis program. This morphological analysis is a method of using dictionary data to decompose text into morphemes, which are the smallest units of words that cannot be further subdivided to make sense. For example, when processor 212 reads the text "Say goodbye to fine lines" in FIG. 14, it performs morphological analysis to break it down into "Say goodbye to fine lines / to fine lines" (" / " indicates the separator between words after the text has been broken down into morphemes), and analyzes that the text is composed of "Say goodbye to fine lines," "to," "goodbye," "Say goodbye to fine lines," "to fine lines," and "Say goodbye to fine lines." Processor 212 then stores this analysis result together with the text "Say goodbye to fine lines" as text information in the content table. In this way, not only are the smallest units of text, such as "Say goodbye to fine lines," "to," and "goodbye," but also the sentences "Say goodbye to fine lines," "to fine lines," and "Say goodbye to fine lines," which are added with preceding and following elements, are stored as the text to be judged. Therefore, the judgment described below is not simply based on the smallest unit, namely, the word, but also makes it possible to make a judgment taking into account the preceding and following context.

[0053] At this time, the processor 212 also counts the number of characters that make up each text, and stores the number of characters in the content table of the memory 211 in association with the text.

[0054] Next, processor 212 determines whether the text analyzed into one or more words is subject to regulation by law or guidelines (S217). If the determination result shows that the text is neither "inappropriate" nor "requires caution," processor 212 stores the result in the content table of memory 211 in association with the determined text, and returns to the process of S212 again (S218). On the other hand, if the determination result shows that the text is "inappropriate" or "requires caution," processor 212 stores the result in the content table of memory 211 in association with the text to be determined, and proceeds to the process of determining the reason for the determination (S218). In the process of determining the reason for the determination, processor 212 determines the reason for the determination, and stores the reason in memory 211 in association with the text to be determined (S219). Then, processor 212 determines an alternative for the text to be judged as inappropriate or requiring caution so that the text does not receive such a judgment, and stores the determined alternative in memory 211 in association with the text to be judged (S220). Details of the processes of S217 to S220 will be described later.

[0055] The processor 212 executes the processes of S212 to S220 until there are no more portions for which various determination processes such as text determination processes have not yet been performed. Then, when there are no more portions, the processor 212 outputs the determination result information, including the content as image data stored in S211, the propriety information, reason information, and alternative information stored in association with each piece of text, to the terminal device 100 via the communication interface 213 (S221). This ends the processing flow.

[0056] 6, the text to be judged includes not only the smallest units of text, such as words "fine wrinkles," "to," and "goodbye," but also sentences with preceding and following elements, such as "fine wrinkles," "to say goodbye," and "fine wrinkles to say goodbye." Therefore, it is possible to perform judgment processing based on the preceding and following contexts, rather than simply based on the smallest units of words.

[0057] 14, the processor 212 sets position coordinates on a two-dimensional coordinate system consisting of an x-axis and a y-axis for the content (image data) to be determined. That is, the processor 212 obtains position information of each text obtained in S215, where the text is arranged in the content to be determined, and stores the position information in the content table of the memory 211 in association with each text. The processor 212 then generates usability identification object information for identifying usability based on the usability information, and stores the object information in association with the content to be determined, together with placement position information corresponding to the position information of the content to be determined. When outputting the determination result information in S221, the processor 212 also outputs the usability identification object information indicating usability and its placement position information to the terminal device 100 as determination result information.

[0058] Furthermore, as described above, when breaking down and analyzing text in S216, processor 212 counts the number of characters in each text and stores the count in the content table of memory 211 in association with the text. Therefore, when outputting the determination result information in S211, processor 212 references the character count information in the content table based on the content ID information associated with the determination result information, and outputs the total number of characters associated with the content ID information as character count information, which is included in the determination result information. Note that this total value is an example of character count information, and any information related to the number of characters, such as an average value, a maximum value, or a minimum value, may be used.

[0059] 7. Processing Flow Performed by Server Device 200 (Details of Determination Processing Using Trained Model) Fig. 7 is a diagram showing a processing flow executed in server device 200 according to an embodiment of the present disclosure. Specifically, Fig. 7 shows details of the processing performed in S217 to S220 in Fig. 6. This processing flow is mainly performed by processor 212 of server device 200 reading and executing a program stored in memory 211.

[0060] 7, processor 212 reads from memory 211 the text decomposed and analyzed for each word in S216 of FIG. 6 (including the text itself and each element after analysis and decomposition) and the category associated with the text (S311). Then, processor 212 inputs the text and the category to a trained text determination model stored in memory 211 (S312). Using the trained text determination model, processor 212 outputs propriety information indicating whether the use of the input text is restricted by law or guidelines. Processor 212 stores the output propriety information as determination result information in the content table of memory 211 in association with the text to be determined (S313).

[0061] Next, processor 212 refers to the content table and determines whether "inappropriate" or "warning required" is stored in the propriety information of the text to be judged (S314). If the result is neither "inappropriate" nor "warning required," processor 212 executes the process of S112 shown in FIG. 6. On the other hand, if the text is "inappropriate" or "warning required," processor 212 inputs the text and category read out in S311 into the learned reason judgment model stored in memory 211 (S315). Processor 212 outputs reason information indicating the reason for the judgment using the learned reason judgment model. Processor 212 stores the output reason information as judgment result information in the content table of memory 211 in association with the text to be judged (S316).

[0062] Next, processor 212 inputs the text and category read in S311 into the trained alternatives determination model stored in memory 211 (S317). Processor 212 uses the trained alternatives determination model to output alternatives to prevent the text from being determined as inappropriate or requiring caution. Processor 212 stores the output alternative information as determination result information in the content table of memory 211 in association with the text that was the subject of determination (S318).

[0063] Here, Fig. 8 is a diagram showing a processing flow related to generation of a trained model according to an embodiment of the present disclosure. Specifically, Fig. 8 is a diagram showing a processing flow related to generation of a trained text determination model in S312 of Fig. 7. This processing flow may be executed by the processor 111 of the processing device 100, or may be executed by a processor of another processing device.

[0064] 8, the processor executes a step of acquiring a training text from content prepared for training and a training category of the content containing the training text, for example, by the method shown in S213 to S216 of FIG. 6 (S411). The training text is subjected to an analysis process similar to that of S216 of FIG. 6. That is, in the case of the text "Say goodbye to fine lines," not only "Say goodbye to fine lines," but also the elements "fine lines," "to," "goodbye," "fine lines," and "to" are used as the training text. The processor also executes a step of determining whether the training text can be used by referring to the determination database shown in FIG. 4A based on the training text and training category acquired in S411 (S412). The processor then executes a step of storing the determination result, i.e., whether or not the training text can be used, as a correct answer label (S413).

[0065] Once the training text, training categories, and corresponding validity information are obtained, the processor executes a step of performing machine learning of text determination patterns using the obtained information (S414). For example, the machine learning is performed by providing a set of information to a neural network that combines neurons, and repeating learning while adjusting the parameters of each neuron so that the output from the neural network is the same as the validity information, which is the correct label. The processor then executes a step of acquiring a trained text determination model and storing it in memory (S415). The acquired trained text determination model may be stored in the memory 211 of the server device 200 or in another device connected to the server device 200 via a wired or wireless network.

[0066] 9 is a diagram showing a processing flow related to generation of a trained model according to an embodiment of the present disclosure. Specifically, FIG. 9 is a diagram showing a processing flow related to generation of a trained reason determination model in S315 in FIG. 7. This processing flow may be executed by the processor 111 of the processing device 100, or may be executed by a processor of another processing device.

[0067] 9, the processor executes a step of acquiring study text and a study category of content including the study text from content prepared for study, for example, by a method similar to S411 of FIG. 8 (S421). In addition, the processor executes a step of acquiring propriety information, which is a determination result of whether or not the study text can be used, by a method similar to S412 of FIG. 8 (S421). Then, based on the study text, study category, and propriety information acquired in S421, the processor executes a step of determining the reason why the use of the study text was determined to be inappropriate or requiring caution, by referring to the determination database shown in FIG. 4A (S422). Next, the processor executes a step of storing reason information indicating the reason for the determination as a correct answer label, in association with the study text (S423).

[0068] Once the training text, training categories, and propriety information, as well as the reason information associated therewith, are obtained, the processor executes a step of performing machine learning of a judgment pattern of judgment reasons using the information (S424). For example, the machine learning is performed by providing a set of information to a neural network that combines neurons, and repeating learning while adjusting the parameters of each neuron so that the output from the neural network is the same as the reason information that is the correct label. The processor then executes a step of acquiring a trained reason judgment model and storing it in memory (S425). The acquired trained reason judgment model may be stored in memory 211 of server device 200 or another device connected to server device 200 via a wired or wireless network.

[0069] 10 is a diagram showing a processing flow related to generation of a trained model according to an embodiment of the present disclosure. Specifically, Fig. 10 is a diagram showing a processing flow related to generation of a trained alternatives determination model in S317 in Fig. 7. This processing flow may be executed by the processor 111 of the processing device 100, or may be executed by a processor of another processing device.

[0070] 10, the processor executes a step of acquiring study text and a study category of content including the study text from content prepared for study, for example, by a method similar to S411 of FIG. 8 (S431). In addition, the processor executes a step of acquiring propriety information, which is a determination result of whether or not the study text can be used, by a method similar to S412 of FIG. 8 (S431). Then, based on the study text, study category, and propriety information acquired in S431, the processor executes a step of determining an alternative to prevent the use of the study text from being determined as inappropriate or requiring caution, by referring to the determination database shown in FIG. 4A (S432). Next, the processor executes a step of storing alternative information indicating the determined alternative as a correct label in association with the study text (S433).

[0071] Once the training text, training categories, and propriety information, as well as the alternative information associated therewith, are obtained, the processor executes a step of performing machine learning of an alternative judgment pattern using the training text, training categories, and propriety information (S434). For example, the machine learning is performed by providing a set of information to a neural network that combines neurons, and repeatedly learning while adjusting the parameters of each neuron so that the output from the neural network is the same as the alternative information that is the correct label. The processor then executes a step of acquiring a trained alternative judgment model and storing it in memory (S435). The acquired trained alternative judgment model may be stored in memory 211 of server device 200 or in another device connected to server device 200 via a wired or wireless network.

[0072] 8 to 10, the correct labels are generated by the processor by referring to the determination database shown in Fig. 4A. However, this is not limiting, and any user may determine the acceptability of the learning text in light of the laws or guidelines corresponding to the learning category, determine the reason for this, or determine alternatives.

[0073] 8. Processing flow performed by the server device 200 (details of the determination process using the determination database) Fig. 11 is a diagram showing a processing flow executed in server device 200 according to an embodiment of the present disclosure. Specifically, with regard to the processing performed in S217 to S220 in Fig. 6, the example in Fig. 7 shows a case where a trained model is used to make a determination, but Fig. 11 shows a case where a determination is made using a determination database instead of a trained model. This processing flow is mainly performed by processor 212 of server device 200 reading and executing a program stored in memory 211.

[0074] 11, processor 212 reads from memory 211 the text that was broken down and analyzed for each word in S216 of Fig. 6 and the category associated with the text (S311). Processor 212 refers to the determination database in memory 211 and determines, for the corresponding category, whether the entire read text, each word and combination of words that make up the text match text registered in the target information of the determination database (S512). If there is matching text, each word, or combination of words, processor 212 stores, as determination result information, in the content table in association with the text that was the target of determination (S513).

[0075] Specifically, for example, suppose that the text "Say goodbye to fine wrinkles" (" / " indicates a separator between words after decomposition into morphemes) is read out as analyzed text in the "cosmetics" category. Next, processor 212 refers to category information in the determination database and extracts target information in which "cosmetics" is registered. Then, it determines whether each of the words "say goodbye to fine wrinkles," "say goodbye," "say goodbye to fine wrinkles," "say goodbye to fine wrinkles," and "say goodbye to fine wrinkles," which make up the read text, matches the text of the extracted target information. In this case, since "say goodbye to fine wrinkles" is registered in the target information, processor 212 refers to the appropriateness information associated with "say goodbye to fine wrinkles" in the determination database. Then, processor 212 stores "inappropriate" in the appropriateness information of the content table, in association with "say goodbye to fine wrinkles" to be determined.

[0076] Next, processor 212 refers to the content table to determine whether "inappropriate" or "warning required" is stored in the propriety information of the text to be judged (S514). If the result is neither "inappropriate" nor "warning required," processor 212 executes the process of S112 shown in FIG. 6. On the other hand, if the text is "inappropriate" or "warning required," processor 212 refers to the judgment database to extract "reason information" associated with the text of the target information (S515). Then, processor 212 stores the extracted judgment reason in the "reason information" of the content table in association with the text to be judged (S516). Similarly, processor 212 also refers to the judgment database to extract "alternative information" associated with the target information (S517). Then, processor 212 stores the extracted alternative in the "alternative information" of the content table in association with the text to be judged (S516).

[0077] Specifically, for example, if the text "Say goodbye to fine wrinkles" that is the subject of judgment is judged to be "inappropriate," processor 212 refers to reason information associated with "fine wrinkles" that was judged to be "inappropriate" in the judgment database. Then, processor 212 extracts a judgment reason that "the phrase "fine wrinkles" is inappropriate" as reason information for why the text "Say goodbye to fine wrinkles" that is the subject of judgment is "inappropriate," and stores the judgment reason that "the phrase "fine wrinkles" is inappropriate" in the reason information of the content table in association with the text "Say goodbye to fine wrinkles" that is the subject of judgment. Processor 212 also refers to alternative plan information associated with "fine wrinkles" in the judgment database. Then, processor 212 extracts an alternative plan "delete" as alternative plan information for the text "Say goodbye to fine wrinkles" that is the subject of judgment, and stores "delete" in the alternative plan information of the content table in association with the text "Say goodbye to fine wrinkles" that is the subject of judgment.

[0078] 9. Processing flow performed by the terminal device 100 (output processing of determination result information) Fig. 12 is a diagram showing a processing flow executed in the terminal device 100 according to an embodiment of the present disclosure. Specifically, Fig. 12 shows a processing flow performed in the terminal device 100 after determination result information is output from the server device 200 to the terminal device 100 in S221 of Fig. 6. This processing flow is mainly performed by the processor 112 of the terminal device 100 reading and executing a program stored in the memory 113.

[0079] First, when processor 112 receives determination result information from server device 200 via communication interface 114, it stores the received determination result information in memory 113. Then, processor 112 reads out the stored determination result information and outputs the determination result information to a display or the like via output interface 111. Note that this determination result information includes propriety information, reason information, alternative information, propriety identification object information indicating propriety of use, placement position information indicating the placement position of the propriety identification object information, and character count information associated with each text that was the subject of the determination.

[0080] FIG. 15 is a diagram illustrating an example of a screen output to the terminal device 100 according to an embodiment of the present disclosure. Specifically, FIG. 15 illustrates an example of a determination result display screen when determination result information received from the server device 200 is output to the display via the output interface 111. As illustrated in FIG. 15, the determination result display screen includes a content display area 14 in which the content to be determined is displayed. In this content display area 14, the content to be determined (e.g., FIG. 14) is displayed, and a feasibility identification object 15, a feasibility identification object 16, and a feasibility identification object 17 are displayed so as to be superimposed on the content. Specifically, based on placement position information set to a position corresponding to the position information of each piece of text included in the content to be determined, each of the feasibility identification objects 15 to 17 is displayed so as to be superimposed on the content. Here, the feasibility information stored for the text "Maybe it can improve your skin?" among the texts to be determined is "Caution required," and the feasibility information stored for the text "Get skin as beautiful as a baby!" and the text "Say goodbye to fine wrinkles" is "Inappropriate." Therefore, as shown in FIG. 15, the appropriateness identification object displayed at a position corresponding to each piece of text is also displayed in a different manner depending on whether the text is caution-required or inappropriate.

[0081] Furthermore, a judgment result list display area 21 is displayed on the right side of the content display area 14. In this judgment result list display area, text boxes 21a to 21f are displayed corresponding to each text that was judged. The text boxes 21a to 21f contain reason information and alternative information associated with each text, but in the example of FIG. 15, these are displayed in a reduced size, and only information indicating the text that was judged is displayed. Furthermore, each text box 21a to 21f is displayed in a manner that makes it possible to identify the result of the judgment on whether or not to use the text, based on the suitability information associated with each text. For example, in the example of FIG. 15, the suitability information for the text "Get beautiful skin like a baby!" and the text "Say goodbye to fine wrinkles" is "inappropriate," and these text boxes 21a and 21b are displayed in a manner that surrounds them with a thick line. On the other hand, the suitability information for the text "Maybe it can improve your skin?" is stored as "Caution," and this text box 21c is displayed in a manner that surrounds it with a dashed line.

[0082] Furthermore, a character count display area 22, an inappropriate passage display area 23, and a cautionary passage display area 24 are displayed at the top of the content display area 14. The character count display area 22 displays character count information received as judgment result information. The inappropriate passage display area 23 displays the number of texts judged to be inappropriate in the content to be judged, which is added up based on the propriety information. The cautionary passage display area 24 displays the number of texts judged to be cautionary in the content to be judged, which is added up based on the propriety information. Note that in this embodiment, the character count information, the number of texts judged to be inappropriate, and the number of texts judged to be cautionary are displayed as their respective cumulative values. However, the displayed numerical values ​​may be values ​​other than cumulative values ​​as long as they are related to each numerical value. For example, the character count information may be any information related to the number of characters, such as an average value, a maximum value, or a minimum value, other than a cumulative value (total value).

[0083] Additionally, a download icon 19 and a print icon 20 are displayed above the judgment result list display area 21. When either icon is selected by operating the pointer 18 via the input interface 115, the corresponding process is executed. For example, when an operation input is made to the download icon 19, each text to be judged and its associated propriety information, reason information, and alternative information can be downloaded in a list format in a standardized electronic file format such as a spreadsheet file format or PDF. When an operation input is made to the print icon 20, the judgment result display screen can be output to a paper medium or downloaded in a standardized electronic file format such as PDF or as image data. Although not specifically illustrated, for example, a share icon can be displayed, and when an operation input is made to the icon, the judgment result can be shared with desired other users in a desired format. In this way, other functional icons can be displayed in addition to the download icon 19 and the print icon 20.

[0084] 12 again, after the determination result information is output to the determination result display screen, processor 112 determines whether or not an instruction input to expand any of the text boxes included in determination result list display area 21 has been accepted via input interface 115 (S611). Specifically, processor 112 determines whether or not an interrupt signal indicating that a click operation has been performed at a position corresponding to any of the text boxes has been received from input interface 115. Then, when it is determined that an instruction input has been accepted, processor 212 updates and displays the determination result list display area so that the success / failure information, reason information, and alternative information are displayed for the text box in the determination result list display area for which an instruction to expand has been issued (S612).

[0085] FIG. 16 is a diagram illustrating an example of a screen output to the terminal device 100 according to an embodiment of the present disclosure. Specifically, FIG. 16 is a diagram illustrating a screen after the determination result list display area 21 has been updated in S612 of FIG. 12. According to FIG. 16, the user moves the pointer 18 onto a desired text box (here, the text box 21a) via the input interface 115 and performs a click operation. As a result, the size of the text box 21a is expanded vertically and displayed. As a result, for example, the text box 21a, which was displayed reduced in size in FIG. 15, is expanded, and the reason information and alternative information associated with the text are each visibly displayed. Furthermore, as the text box 21a is expanded vertically, the other text boxes 21b to 21f are slid downward in the determination result list display area 21 and displayed.

[0086] 12 again, processor 112 determines whether an instruction input to select any of the texts included in the content display area has been accepted via input interface 115 (S613). Specifically, processor 112 determines whether an interrupt signal indicating that the pointer has been detected continuously for a certain period of time at a position corresponding to any of the texts has been received from input interface 115. Then, when it is determined that an instruction input has been accepted, processor 212 updates and displays the determination result list display area so that the text box corresponding to the selected text in the determination result list display area is positioned at the top of the determination result list display area and so that the propriety information, reason information, and alternative information are displayed (S614).

[0087] FIG. 17 is a diagram illustrating an example of a screen output to the terminal device 100 according to an embodiment of the present disclosure. Specifically, FIG. 17 is a diagram illustrating a screen after the determination result list display area 21 has been updated in S614 of FIG. 12. According to FIG. 17, the user moves the pointer 18 via the input interface 115 onto desired text (here, "Maybe it can improve your skin?") and stops there for a certain period of time or longer. As a result, the position of the text box 21c corresponding to the text is displayed so as to be positioned at the top in the determination result list display area 21. Furthermore, the size of the text box 21c is expanded vertically. As a result, for example, the text box 21c, which was displayed in a reduced size in the middle of the determination result list display area 21 in FIG. 15, is expanded to the top, and the reason information and alternative information associated with the text are each visibly displayed. Furthermore, as the text box 21c is positioned at the top and expanded vertically, the other text boxes 21a and 21b to 21f are slid downward and displayed in the determination result list display area 21.

[0088] 12, processor 112 determines whether an instruction input to select the download icon has been received via input interface 115 (S615). Specifically, processor 112 determines whether an interrupt signal indicating that a click operation of the pointer has been detected at a position corresponding to the download icon has been received from input interface 115. If it is determined that an instruction input has been received, processor 212 creates a list of each of the texts to be judged and the propriety information, reason information, and alternative information associated with each text, and downloads the list to a storage location designated by the user in a standardized electronic file format such as a spreadsheet file format or PDF (S616).

[0089] Processor 112 determines whether an instruction input to select the print icon has been received via input interface 115 (S617). Specifically, processor 112 determines whether an interrupt signal indicating that a click operation of the pointer at a position corresponding to the print icon has been detected has been received from input interface 115. If it is determined that an instruction input has been received, processor 212 outputs the determination result display screen to a paper medium or downloads it to a storage location designated by the user in a standardized electronic file format such as PDF or as image data (S618). This ends the processing flow.

[0090] 9. Variations In the example of FIG. 16, a case has been described in which the user moves the pointer 18 over a desired text box via the input interface 115, clicks, and the text box expands vertically. However, this is not limiting. When a selection operation on a text box is detected, a pop-up window containing reason information and alternative information may be displayed. Furthermore, when the selection operation is detected, the reason information and alternative information may be displayed in a display area previously provided in a separate position. Furthermore, each text box may be constantly expanded so that the reason information and alternative information are always displayed.

[0091] In the example of FIG. 17 , a case has been described in which a user moves the pointer 18 to desired text via the input interface 115 and stops the pointer 18 for a certain period of time, thereby moving the corresponding text box and expanding it vertically. However, by moving the pointer 18 to the desired text and stopping it for a certain period of time, the corresponding text box may be expanded in place without moving. Furthermore, by moving the pointer 18 to the desired text and stopping it for a certain period of time, the corresponding text box may be highlighted, for example, by blinking. Furthermore, by moving the pointer 18 to the desired text and stopping it for a certain period of time, only the display order of the corresponding text boxes may be changed. Furthermore, by moving the pointer 18 to the desired text and stopping it for a certain period of time, a pop-up window containing reason information and alternative information may be displayed at a position corresponding to the text.

[0092] In the examples of FIGS. 15 to 17, the possible / probable identification object indicating whether or not the text to be determined can be used is formed using a star-shaped decorative object. However, the shape of the possible / probable identification object is not limited to this, and it may be an object of any shape, such as a circle or a square. Also, in the examples of FIGS. 15 to 17, the possible / probable identification object is displayed in a position that does not overlap the text to be determined, but it may be displayed so that it overlaps behind or above the text. Also, in the examples of FIGS. 15 to 17, the possible / probable identification object is displayed in a static state, but it may be displayed as a dynamic possible / probable identification object or a possible / probable identification object whose color tone changes. Also, in the examples of FIGS. 15 to 17, the possible / probable identification object is displayed separately from the text to be determined, but the text may be highlighted using bold, an underscore, highlighting, etc.

[0093] 15 to 17, the determination result list display area has been described as showing whether or not the corresponding text can be used by changing the frame of each text box. However, this is not limiting, and whether or not the text can be used may be shown by highlighting the characters in the text box, changing the color of the text box, or overlaying a decorative object on the text box.

[0094] 15 to 17, the case where the selection of text or a text box is performed using the pointer 18 has been described. However, this is not limiting, and the selection may be performed using an input interface such as a touch panel and a touch operation using a pointing device such as a user's finger or a stylus.

[0095] 15 to 17, the case has been described in which the judgment result display screen includes the content display area 14, which includes the content and the yes / no identification object, and the judgment result list display area 21. However, this is not limiting, and the judgment result display area may display only the content display area 14, or may display only the content and the judgment result list display area 21. Furthermore, the judgment result display area may not include the judgment result list display area 21, and may display only the judgment result list display area 21.

[0096] 15 to 17, the judgment result display screen has been described as displaying only the judgment result information of inappropriate and caution required. However, depending on the judgment result information received, only one of the information two or three levels after "inappropriate and appropriate" or "appropriate and caution required" may be displayed. Also, depending on the judgment result information received, a display corresponding to a more detailed classification may be displayed, or information indicating a numerical value or level indicating the probability of being judged as inappropriate or appropriate may be displayed.

[0097] The determination processes of S217, S219, and S220 in Fig. 6 have been described as being executed by the processor 212. However, the present invention is not limited to this, and the determination itself may be performed by a person such as a user using a determination base, and the processor 212 may perform the determination based on a memory of the determination result.

[0098] 1 to 17, the server device 200 functions as a processing device, and executes the processes according to Figures 6 to 11. However, the present invention is not limited to this, and the terminal device 100 may function as a processing device, and the processor 112 of the terminal device 100 may execute the processes according to Figures 6 to 11.

[0099] As described above, in this embodiment, it is possible to provide a processing device, a processing program, and a processing method that can output the result of the determination as to whether or not a device is subject to regulation by a predetermined law or guideline in a more understandable manner.

[0100] The processes and procedures described herein can be realized not only by those explicitly described in the embodiments, but also by software, hardware, or a combination thereof. Specifically, the processes and procedures described herein can be realized by implementing logic corresponding to the processes in media such as integrated circuits, volatile memory, nonvolatile memory, magnetic disks, and optical storage. Furthermore, the processes and procedures described herein can be implemented as computer programs and executed by various computers, including terminal devices and server devices.

[0101] Although processes and procedures described herein are described as being performed by a single device, software, component, or module, such processes or procedures may be performed by multiple devices, multiple software, multiple components, and / or multiple modules. Furthermore, although various information described herein is described as being stored in a single memory or storage unit, such information may be stored in multiple memories within a single device or multiple memories distributed across multiple devices. Furthermore, software and hardware elements described herein may be realized by integrating them into fewer components or by decomposing them into more components. [Explanation of symbols]

[0102] 100 Terminal Device 200 Server device 300 Network

Claims

1. at least one processor; the at least one processor: Accepting input of content including one or more pieces of text that include at least one word to be determined; obtaining the one or more texts from the received content and a category of the received content; For each of the one or more texts obtained, determine whether or not each text can be used in the content based on laws and regulations or guidelines for determining whether or not the use of the one or more texts in the content is restricted; determining an alternative for each of the texts that is not determined to be usable in the determination; outputting the determination result information so that the determination result information, which includes at least availability information indicating whether the text can be used or not and alternative information indicating different alternatives depending on the category, is displayed together with the content; a processing device configured to process the

2. The processing device according to claim 1 , wherein the determination result information is displayed so as to be superimposed on the content.

3. The processor acquires position information of the one or more pieces of text in the content; the determination result information is displayed so as to be superimposed on the content at a position corresponding to the position information. The processing device according to claim 1 or 2.

4. 4. The processing device according to claim 1, wherein the determination result information is displayed in a list-like display area provided in a display area separate from an area in which the content is displayed.

5. 5. The processing device according to claim 1, wherein the determination result information further includes reason information indicating a reason for the determination.

6. The processing device according to claim 5 , wherein the propriety information, the reason information, and the alternative information are determined by referring to a database in which each piece of information is associated with each piece of text based on the law or guideline.

7. The processing device according to claim 5, wherein the applicability information is determined by inputting the one or more texts into a trained text determination model for determining whether each of the one or more texts included in the content can be used based on the laws and regulations or guidelines.

8. The processing device according to claim 5, wherein the reason information is determined by inputting the one or more texts into a trained reason determination model for determining the reason for determining whether or not each of the one or more texts included in the content can be used based on the law or guidelines.

9. The processing device according to claim 5, wherein the alternative information is determined by inputting the one or more texts into a trained alternative determination model for determining alternatives for text that indicates usability information other than usability among the one or more texts included in the content.

10. The processing device according to any one of claims 1 to 9, wherein the content is a web page including HTML and image data.

11. The processing device according to any one of claims 1 to 10, wherein the laws and regulations or guidelines define regulations for at least one of pharmaceuticals, quasi-drugs, regenerative medicine products, medical devices, health foods, functional food products, cosmetics, and mail-order products.

12. The processing device according to any one of claims 1 to 11, wherein the at least one processor is further configured to perform processing for outputting, in addition to the determination result information, information related to the number of texts that were not determined to be usable, calculated based on the usability information.

13. When executed by at least one processor, Accepting input of content including text containing at least one word to be judged; obtaining the text from the received content and a category of the received content; determining whether the acquired text can be used in the content based on laws and regulations or guidelines for determining whether the use of the one or more texts in the content is restricted; determining an alternative for each of the texts that is not determined to be usable in the determination; outputting the determination result information so that the determination result information, which includes at least availability information indicating whether the text can be used or not and alternative information indicating different alternatives depending on the category, is displayed together with the content; A processing program that causes the at least one processor to function in such a manner.

14. A processing method executed by at least one processor, comprising: receiving an input of content including text containing at least one word to be determined; obtaining the text from the received content and a category of the received content; determining whether the acquired text can be used in the content based on laws and regulations or guidelines for determining whether the use of the one or more texts in the content is restricted; determining an alternative for each of the texts that is not determined to be usable in the determination; outputting the determination result information, the determination result information including at least information indicating whether the text can be used or not and information indicating different alternatives according to the category, so that the determination result information is displayed together with the content; A processing method comprising:

Images