Evaluation device, evaluation program, evaluation method

Abstract

This invention provides an evaluation device, evaluation program, and evaluation method that support the creation of advertisements that comply with various rules. [Solution] In a system in which a server device is connected to a user terminal via a network, the server device 1, which is an evaluation device for evaluating material information that is advertising material, comprises an advertising rule determination unit 113 that determines advertising rules related to advertisements in which the material information is used based on the material information, and an evaluation unit 114 that evaluates the material information based on the advertising rules.

Description

Technical Field

[0001] The present invention relates to an evaluation device, an evaluation program, and an evaluation method.

Background Art

[0002] Techniques for evaluating the performance of advertisements and providing suggestions to make the content of advertisements more effective have been disclosed.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0008] According to the present invention, it is possible to support the creation of advertisements that do not violate various rules. [Brief explanation of the drawing]

[0009] [Figure 1] This figure shows an example of the overall configuration of an evaluation system according to one embodiment of the present invention. [Figure 2] This figure shows an example of the hardware configuration of the server device 1 according to the same embodiment. [Figure 3] This figure shows an example of the functional configuration of the server device 1 according to the same embodiment. [Figure 4] This figure shows an example of consumption history information stored in the material information storage unit 131 according to the same embodiment. [Figure 5] This figure shows an example of inventory trend information stored in the advertising rule information storage unit 132 according to the same embodiment. [Figure 6] This figure shows an example of the modified material information stored in the modified material information storage unit 133 according to the same embodiment. [Figure 7] This figure shows an example of processing by the server device 1 according to the same embodiment. [Modes for carrying out the invention]

[0010] <Summary of the Invention> The embodiments of the present invention will be described by listing them. The present invention has, for example, the following configuration. [Item 1] An evaluation device for evaluating material information, which is material for advertising, An advertising rule determination unit that determines advertising rules related to advertisements in which the aforementioned material information is used, based on the aforementioned material information, An evaluation unit that evaluates the material information based on the aforementioned advertising rules, An evaluation device equipped with the following features. [Item 2] The aforementioned material includes text information and image information. The advertisement rule determination unit analyzes the text information to determine the advertisement rules. The evaluation device according to Item 1. [Item 3] The evaluation unit evaluates the material information based on the advertisement rules. The evaluation device according to Item 1 or 2. [Item 4] When the evaluation unit evaluates that the material information has a problem in the advertisement rules, a corrected material information generation unit that generates corrected material information without problems, The evaluation device according to Item 3, further comprising. [Item 5] A presentation unit that presents the problematic material information and the corrected material information to the user based on the evaluation result of the evaluation unit, The evaluation device according to Item 4, comprising. [Item 6] An evaluation program for evaluating material information for advertisements, Causing a computer to, An advertisement rule determination step of determining an advertisement rule related to an advertisement in which the material information is used based on the material, An evaluation step of evaluating the material based on the advertisement rule, An evaluation program for causing execution. [Item 7] An evaluation method for evaluating material information for advertisements, Causing a computer to, An advertisement rule determination step of determining an advertisement rule related to an advertisement in which the material information is used based on the material, An evaluation step of evaluating the material based on the advertisement rule, An evaluation method for causing execution. <Details of the Embodiment>

[0011] Hereinafter, preferred embodiments of the present disclosure will be described in detail with reference to the accompanying drawings. In the present specification and drawings, components having substantially the same functional configuration are denoted by the same reference numerals, and redundant description is omitted.

[0012] ==Overview== Figure 1 shows the overall configuration of the evaluation system. As shown in Figure 1, the evaluation system has a server device 1 and user terminals 3. Server device 1 is connected to user terminals 3 via network 2. Only one server device 1 and one user terminal 3 are shown, but it goes without saying that there may be more.

[0013] ==Server Device 1== Server device 1 may be a general-purpose computer such as a workstation or personal computer, or it may be logically implemented through cloud computing.

[0014] ==User Terminal 3== User terminal 3 is a computer used by the user to evaluate advertisements. Examples include smartphones, tablet computers, and personal computers. The user can access server device 1, for example, through applications or web browsers running on user terminal 3.

[0015] Figure 2 shows an example of the hardware configuration of server device 1. Note that the illustrated configuration is just one example, and other configurations are also possible. Server device 1 includes a CPU 101, memory 102, storage device 103, communication interface 104, input device 105, and output device 106. The storage device 103 stores various data and programs, such as a hard disk drive, solid-state drive, or flash memory. The communication interface 104 is an interface for connecting to the communication network 2, such as an adapter for connecting to Ethernet®, a modem for connecting to a public telephone network, a wireless communication device for wireless communication, or a USB (Universal Serial Bus) connector or RS232C connector for serial communication. The input device 105 is for inputting data, such as a keyboard, mouse, touch panel, button, or microphone. The output device 106 is for outputting data, such as a display, printer, or speaker. Furthermore, each functional unit of the server device 1, as described later, is realized by the CPU 101 reading a program stored in the storage device 103 into memory 102 and executing it, and each storage unit of the server device 1 is realized as part of the storage area provided by memory 102 and storage device 103.

[0016] Figure 3 also shows the functional configuration of the server device 1. As shown in Figure 3, the server device 1 comprises storage units: a material information storage unit 131, an advertising rule information storage unit 132, and a modified material information storage unit 133, as well as processing units: a material information acquisition unit 111, a material information analysis unit 112, an advertising rule determination unit 113, an evaluation unit 114, a modified material information generation unit 115, and a presentation unit 116.

[0017] The following describes each of the storage units: the material information storage unit 131, the advertising rule information storage unit 132, and the modified material information storage unit 133.

[0018] The material information storage unit 131 stores the material information of an advertisement, as shown in Figure 4, which has been acquired by the material information acquisition unit 111. As shown in Figure 4, the material information includes text information used in the advertisement, such as catchphrases, taglines, descriptions, and image text information obtained by reading characters contained in the image information used in the advertisement, as well as image information (including video) used in the advertisement. The material information analysis unit 112, which will be described later, analyzes the target field or target product, and this information is stored in association with each piece of material information.

[0019] The advertising rule information storage unit 132 stores rules related to advertising. As shown in Figure 5 as an example, the advertising rule information is linked to the target field of the advertisement or the target product of the advertisement and includes information such as relevant laws and regulations, regulations of industry associations, internal rules and guidelines of users, how readers feel (sentimental evaluation and marketing elements), as well as information such as prohibited expressions and expressions that should be avoided.

[0020] The modified material information storage unit 133 stores the modified material information generated by the modified material information generation unit 115. As shown in an example in Figure 6, the modified material may include text information, image information, and combined image information that combines text information and image information.

[0021] The following describes the processing units for each of the following: material information acquisition unit 111, material information analysis unit 112, advertising rule determination unit 113, evaluation unit 114, modified material information generation unit 115, and presentation unit 116.

[0022] The material information acquisition unit 111 acquires, for example, material information for an advertisement. The material information acquisition unit 111, for example, presents an input form for material information to the user terminal 3 via the network 2, accepts the user's input, and acquires the material information. The communication in this transmission and reception can be wired or wireless, and any communication protocol can be used as long as communication between the two devices is possible. The material information acquisition unit 111 may, for example, accept and acquire uploaded document files, image files, etc., containing advertisement materials using the method described above, or it may acquire the URL of a website containing advertisement information from the user terminal and acquire the information on that website as material information, but it is not limited to these methods. The material information acquisition unit 111 stores the acquired material information in the material information storage unit 131.

[0023] The material information acquisition unit 111 acquires text information (specifically, image text information) from image information included in the material information, for example. The material information acquisition unit 111 acquires character information contained in the image as image text information using existing image analysis technologies such as OCR. The material information acquisition unit 111 stores the image text information in the material information storage unit 131 as part of separately acquired text information.

[0024] As an example, the material information analysis unit 112 analyzes the material information acquired by the material information acquisition unit 111.

[0025] The material information analysis unit 112 generates prompt information based on material information, for example. The prompt information may include prompts or prerequisite conditions. The material information analysis unit 112 generates prompt information using, for example, a language model.

[0026] The material information analysis unit 112, for example, inputs prompt information generated based on the text information contained in the material information into an existing text generation model (for example, a large-scale language model such as ChatGPT), and based on the output information, identifies basic advertising information such as the target field of the advertisement in which the material information is used and the target products targeted by the material information, and stores this information in the material information storage unit 131 in association with the material information.

[0027] The material information analysis unit 112 may, for example, perform morphological analysis on text information using existing morphological analysis technology to divide it into words, vectorize each word, identify the basic advertising information of the advertisement in which the material information is used, and store the vector information in the material information storage unit 131, linking it to the material information.

[0028] The material information analysis unit 112 may, for example, analyze the image information contained in the material information using existing image analysis technology, identify the basic advertising information of the advertisement in which the material information is used, and store it in the material information storage unit 131 in association with the material information.

[0029] The material information analysis unit 112 may, for example, identify the basic advertising information using a model that takes image information as input information and outputs at least one of the basic advertising information of the advertisement in which the material information is used. This model may be generated by machine learning, deep learning, etc., or it may be a large-scale image language model, multimodal AI, etc., but is not limited to these.

[0030] The advertising rule determination unit 113 determines advertising rules that may be related to the material information being evaluated, based on the analysis results of the material information analysis unit 112. For example, the advertising rule determination unit 113 may determine advertising rules that may be related to the material being evaluated based on at least one piece of information from the basic advertising information identified by the analysis of the material information analysis unit 112. For example, the advertising rule determination unit 113 may determine advertising rules as those stored in association with the presence or absence of a predetermined word identified by the material information analysis unit 112, the target field, the target product, etc. For example, if the analysis of the material information analysis unit 112 identifies the target field as the food field or the target product as a health food, the advertising rule determination unit 113 may identify the Pharmaceutical Affairs Law stored in association with the target field or target product as an advertising rule.

[0031] As an example, the advertising rule determination unit 113 may input prompt information generated based on material information acquired by the material information acquisition unit 111 into an existing text generation model, and based on the output information, identify advertising rules that may be related to the advertisement in which that material information is used.

[0032] The advertising rule determination unit 113 may, for example, identify advertising rules using a model that learns information linking material information to advertising rules as training data, takes material information as input information, and outputs advertising rules that may be related to the advertisement in which that material information is used. This model may be generated by machine learning, deep learning, etc., or it may be a large-scale image language model, multimodal AI, etc., but is not limited to these.

[0033] The evaluation unit 114 evaluates the material information based on the advertising rules determined by the advertising rule determination unit 113. For example, the evaluation unit 114 evaluates whether there are any problems with the material information, such as whether there are any expressions that cannot be used in order to comply with the advertising rules, or expressions that may violate the advertising rules. Note that the determination of whether or not there are problems in the evaluation performed by the evaluation unit 114 may be the result of determining whether or not the material contains expressions that could be considered problematic.

[0034] The evaluation unit 114 evaluates whether there are any problems with the material information by determining, for example, whether or not prohibited words, prohibited expressions, etc., which are stored in association with advertising rules, are included in the material information.

[0035] The evaluation unit 114 may, for example, generate prompt information using a language model that includes at least material information and information on advertising rules determined by the advertising rule determination unit 113, input the prompt information into an existing text generation model, and evaluate the material information based on the output information.

[0036] The evaluation unit 114 evaluates, for example, whether the image information included in the material information contains expressions that cannot be used in order to comply with advertising rules, or parts that may violate advertising rules. In this case, the evaluation unit 114 may, for example, generate prompt information that includes the material information and the advertising rule information determined by the advertising rule determination unit 113, input the prompt information into an existing large-scale image language model, and evaluate the image information based on the output information.

[0037] The evaluation unit 114 may evaluate the image information using a model in which, for example, image information containing expressions that cannot be used to comply with advertising rules or parts that may violate advertising rules is used as training data, image information is used as input information, and expressions that cannot be used to comply with advertising rules or parts that may violate advertising rules are used as output information. This model may be generated by machine learning, deep learning, etc., or it may be a large-scale image language model, multimodal AI, image recognition model, etc., or it may use existing image processing technology, but is not limited to these.

[0038] For example, if the material information analysis unit 112 determines that the target field of material information is the health and healthcare field, and the advertising rule determination unit 113 determines the Pharmaceuticals and Medical Devices Act as the advertising rule, the evaluation unit 114 will evaluate that the material information may violate the advertising rule if it contains prohibited expressions such as "Anyone can lose weight!" or "Hair will grow dramatically!".

[0039] The modified material information generation unit 115 generates modified material information, which is a proposed revision, for material information that the evaluation unit 114 has determined may violate advertising rules. For example, the modified material information generation unit 115 generates prompt information that includes material information and advertising rule information (including information such as prohibited expressions) determined by the advertising rule determination unit 113, inputs the prompt information into a large-scale language model, a large-scale image language model, etc., and generates modified material information that does not violate advertising rules based on the output information, and stores it in the modified material information storage unit 133.

[0040] The modified material information generation unit 115 may generate modified material information using a model that uses information linking material information and modified material information as training data, with material information as input information and modified material information as output information. This model may be generated by machine learning, deep learning, etc., or it may be a large-scale image language model, multimodal AI, image recognition model, etc., or it may use existing image processing technology, but is not limited to these.

[0041] The presentation unit 116 presents the basic advertising information, advertising rules, evaluation results, and revised material information output by each of the processing units described above to the user terminal 3. For example, based on the evaluation results of the evaluation unit 114, the presentation unit 116 may present to the user terminal 3 as proposed revisions material information that may violate the advertising rules and revised material information generated by the revised material information generation unit 115.

[0042] The presentation unit 116 may send the revised material information to the user terminal 3 if the user accepts the revised proposal.

[0043] Using Figure 7, a typical processing flow of the server device 1 of this embodiment will be explained. The material information acquisition unit 111 acquires material information (1001). The material information analysis unit 112 analyzes the material information (1002). The advertising rule determination unit 113 determines advertising rules from the analyzed material information (1003). The evaluation unit 114 evaluates the material information based on the advertising rules (1004). The modified material information generation unit 115 generates modified material information (1005). The presentation unit 116 presents the material information that violates the advertising rules and the modified material information to the user (1006).

[0044] The following are other examples.

[0045] The server device 1 may, for example, use video information as image information. In this case, the material information analysis unit 112 may acquire frames of the video information at predetermined intervals and analyze them as image information using the method described above. The material information analysis unit 112 may also analyze frames containing text as image information using the method described above.

[0046] Furthermore, server device 1 may evaluate advertising materials using video information in the following manner. Note that the video information includes multiple media elements such as each frame image, text information contained in the images, audio information, and text information obtained from the audio through speech recognition description.

[0047] Server device 1 acquires text information from the frame images that make up the video using character recognition technology such as OCR, and evaluation unit 114 checks the text information as described above. Furthermore, evaluation unit 114 performs image checks on the frame images and checks the text information acquired from the audio contained in the video using speech recognition technology.

[0048] In addition to checking the video itself, Server Device 1 also evaluates supplementary information associated with the video, such as the title, description, thumbnail (title image), hashtags, icon, user reviews, and comments, and performs an overall evaluation that combines the evaluation of the video information and the supplementary information.

[0049] Furthermore, the server device 1 may use multimodal AI or the like to verbalize the constituent information that makes up the advertising video, namely the video, frame images, audio information, etc., and the evaluation unit 114 may evaluate this as text information using the evaluation method described above. This method allows the server device 1 to utilize the advertising check mechanism while also being able to evaluate combinations of constituent information.

[0050] Furthermore, the server device 1 may directly translate the entire video containing the configuration information into language using a multimodal AI or the like, and check the generated text (text information).

[0051] In the text (text information) check performed by the evaluation unit 114 in the evaluation of advertising materials using video information, it is sufficient to use large-scale language models (LLM), natural language processing, AI-based learning of unacceptable sentences, vector detection, keyword detection, etc., to detect violations of various laws and regulations such as the Pharmaceutical Affairs Law and the Act against Unjustifiable Premiums and Misleading Representations.

[0052] In the image check performed by the evaluation unit 114 when evaluating advertising materials using video information, it is sufficient to use multimodal AI, image search, object detection, object classification, image processing technology, etc., to detect violation patterns such as "Is there a person wearing a white coat?" or "Is a person wearing a white coat advertising cosmetics?".

[0053] One way to improve the accuracy of advertising evaluation performed by Server Device 1 is to employ complex preprocessing and stepwise analysis methods. For example, Server Device 1 can perform person detection from advertising material information and then conduct analysis using LLM or multimodal AI. Specifically, Server Device 1 first identifies people in the image using, for example, an object detection algorithm, and extracts attributes such as clothing type (lab coat, uniform, etc.), age group, and facial expression. Then, by inputting the detected person information and the original image into the multimodal AI, Server Device 1 can more accurately detect expressions that may violate the Pharmaceutical Affairs Law, such as "a person who looks like a doctor is recommending a product."

[0054] Furthermore, methods for analyzing the continuity of actions and behaviors are also effective. Server device 1 tracks the actions of people in the video in chronological order and automatically detects sequences that suggest before-and-after comparisons, such as "before product use → after use." For example, server device 1 identifies scenes in which skin condition, body shape, hair condition, etc., change, and evaluates the possibility that the change pattern can be interpreted as "emphasis on effects and benefits." After performing such chronological behavior detection as preprocessing, server device 1 inputs the video along with the detected behavior pattern information into a multimodal AI, enabling highly accurate identification of regulatory violation risks that are difficult to detect with simple image analysis.

[0055] Furthermore, methods utilizing object relationship analysis can also be mentioned. Server device 1 detects the positional relationships and interactions between products and other objects (e.g., fruits, measuring instruments, comparison objects, etc.) in advertising images and videos as a preprocessing step. For example, if a health food and a specific fruit are always displayed together, it may be interpreted as indirectly promoting the efficacy of that fruit. By structuring this relationship information between objects and inputting it into a multimodal AI, server device 1 can more accurately detect complex patterns such as implicit efficacy claims.

[0056] Text-to-image consistency analysis is also an important preprocessing step. Server device 1 analyzes the consistency between the text (extracted by OCR, etc.) within an image and the image content, and pre-evaluates the possibility of inconsistencies or exaggerations. For example, if the text "clinically tested" is displayed, server device 1 verifies whether the image contains backgrounds or props that evoke a laboratory or research institution. By structuring this consistency information and inputting it into LLM, misleading expressions and context-dependent regulatory infringement risks can be detected more accurately.

[0057] Sentiment analysis preprocessing is also an effective technique. Server device 1 detects emotional states (joy, surprise, relief, etc.) from the facial expressions and postures of people in advertisements and structures patterns of emotional change before and after product use. For example, Server device 1 may interpret patterns such as showing expressions of dissatisfaction or worry before product use and expressions of joy or relief after use as an indirect appeal to the product's effectiveness. By extracting such emotional change information as preprocessing and inputting it into LLM, Server device 1 can appropriately evaluate the risk of regulatory infringement due to indirect emotional appeals.

[0058] In its language processing, Server Device 1 may describe not only the physical descriptions of objects and people in images and videos, but also the impressions and emotions that viewers might feel. For example, in the language processing of advertising material that includes "before / after" images of a thin person, it will not only describe the physical description such as "the image on the left shows a fat woman, and the image on the right shows a thin woman," but also the psychological reactions of viewers, such as "I feel admiration for the woman on the right" and "It gives me the expectation that I can change dramatically in a short period of time." This improves the accuracy of evaluating advertising expressions that influence human emotions and psychology compared to when the multimodal AI processes them directly.

[0059] In particular, the depiction of viewer emotions in the language processing of server device 1 is effective in evaluating advertising materials that, even if the images appear neutral on the surface, may evoke specific interpretations or emotions depending on the cultural background and social context. For example, in advertisements where a person in a specific posture or attire is displayed with a product, by verbalizing viewer interpretations such as "they give the impression of a trustworthy expert" or "they seem authoritative and guarantee the product's effectiveness," it is possible to detect expressions that evoke doctors or experts even if the person is not wearing a white coat. This makes it possible to identify advertising expressions that may give viewers a false impression, even if they do not directly violate regulations.

[0060] Furthermore, in its language processing, server device 1 can depict a variety of impressions and emotions that viewers with different attributes (age, gender, cultural background, etc.) may have. For example, server device 1 verbalizes the differences in emotional responses among different viewer groups to the same advertising material, such as "younger generations are more likely to perceive it as something to aspire to or an ideal," or "middle-aged and older generations may feel that it evokes health anxieties." This allows server device 1 to detect advertising expressions that may have an inappropriate impact only on specific vulnerable groups, enabling more nuanced advertising evaluations tailored to the target audience.

[0061] Furthermore, the language processing of server device 1 can also describe emotional changes within the temporal context of an advertisement. For example, in an advertising video with a story development from problem identification to solution, server device 1 can verbalize the flow of emotions, such as "initially evoking feelings of anxiety and worry, but after the product introduction, leaving the viewer with a sense of reassurance and hope." This allows server device 1 to evaluate regulatory infringement risks that depend on the temporal context, such as indirect appeals of effectiveness and benefits through storytelling, which cannot be detected by single-frame analysis. This verbalized information on emotional changes is also used by the advertising rule determination unit 113 in selecting advertising rules, leading to the application of more appropriate evaluation criteria.

[0062] Server device 1 evaluates combinations of multiple media elements and detects violations such as displaying an image of a slim person while saying in audio, "Eating this has these effects too!"

[0063] To improve processing efficiency, server device 1 employs techniques in frame processing such as decimation, which checks only one image for each instance of the same text or for similar images, or conversely, combining multiple images to perform OCR.

[0064] The checks performed by Server Device 1 include compliance with laws (such as the Pharmaceuticals and Medical Devices Act and the Act against Unjustifiable Premiums and Misleading Representations), verification of copyrights and registered trademarks, confirmation of materials used, presence of essential kanji characters, compliance with platform terms of service, legality of content, ethical compliance, risk of online backlash, accuracy and reliability of content (video fact-checking), video and audio quality, final check of title, thumbnail and description, protection of privacy and personal information, advertising display rules and PR notation, overall review, timing check (synchronization of audio and subtitles), and script check.

[0065] Furthermore, Server Device 1 incorporates several features to improve the accuracy and efficiency of advertising material evaluation. For example, by employing a field-specific evaluation model in the evaluation process, Server Device 1 can make highly accurate judgments regarding regulations and expressions specific to certain industries (pharmaceuticals, cosmetics, health foods, etc.). Server Device 1 may also have a mechanism to accumulate past evaluation results and user feedback and continuously improve the evaluation model through machine learning. In addition, to improve processing speed, Server Device 1 may employ a two-stage evaluation method in which a low-resolution pre-scan is performed, and only the parts where problems are detected are examined in detail at high resolution. Server Device 1 may also implement a function to pre-classify the format and composition patterns of advertising materials and automatically select an optimized evaluation flow for each pattern, thereby enabling efficient evaluation of a wide variety of advertising materials.

[0066] Furthermore, to improve the reliability of the evaluation results, server device 1 may also perform ensemble evaluation using multiple AI models, enabling the detection of subtle expressions and regulatory violations that are difficult to detect with a single model with a high probability. In addition, server device 1 may incorporate metadata such as the advertiser's industry, advertising media, and target audience into the evaluation process to understand the context of the material, thereby enabling the selection and evaluation of more appropriate advertising rules.

[0067] Another embodiment of the present invention is a real-time advertising video production support system. This system immediately detects problems during the advertising video production process and proposes corrections before the content is completed. Server device 1 works in conjunction with digital tools used to create advertisements, such as video editing software, and performs real-time evaluations at each stage of editing work, such as material placement, transition settings, and text generation. It has the function of immediately highlighting parts that may violate legal regulations, issuing alerts, and suggesting alternative expressions. This reduces the risk of needing to make significant revisions after completion and improves production efficiency. For example, a warning is displayed immediately after audio material containing effect expressions that violate the Pharmaceuticals and Medical Devices Act is inserted, and alternative expressions are suggested.

[0068] Another embodiment is an AI prompt optimization system for ad generation. This system has a function to optimize the prompts themselves for the AI ​​that generates ad materials. Server device 1 analyzes the original prompt entered by the user, automatically converts it into a legally compliant expression, and proposes expressions that maintain or improve the effectiveness of the ad. For example, if server device 1 analyzes the prompt "Create an ad for a supplement that is highly effective for weight loss," it detects the possibility of violating the Pharmaceuticals and Medical Devices Act and automatically generates an alternative prompt such as "Create an ad that conveys the appeal of a nutritional supplement that supports a healthy lifestyle." This increases the probability that the generated ad material complies with legal regulations and significantly reduces the amount of work required for correction.

[0069] Another possible implementation is a multi-region regulatory compliance system. Server device 1 is designed for advertising deployment in multiple countries and regions and has an evaluation function that takes into account the differences in advertising regulations in each region. When analyzing advertising materials, server device 1 allows users to specify the countries or regions where deployment is planned, and then performs an evaluation based on the advertising laws and industry guidelines of those regions, and presents regional revision proposals. For example, when evaluating advertising material information for health foods, it provides evaluation results and revision proposals that take into account the rules that must be referenced in each region, such as the Pharmaceuticals and Medical Devices Act in Japan, FDA regulations in the United States, and country-specific regulations and EU common regulations in the EU.

[0070] Furthermore, embodiments equipped with an advertising target audience suitability evaluation function can also be described. Server device 1 has the function of applying evaluation criteria according to the target audience of the advertisement (age, gender, interests, etc.). For example, particularly strict criteria are applied to advertisements aimed at young people, and excessive implication of health benefits or misleading expressions are detected more sensitively. For advertisements targeting the elderly, expressions that exploit cognitive biases and elements that incite anxiety are analyzed in detail. This makes it possible to support the creation of advertisements that not only comply with legal regulations but also take social responsibility into consideration, and to prevent misunderstandings and disadvantages for specific vulnerable groups.

[0071] Another embodiment of the present invention is a predictive compliance evaluation system. Server device 1 has the function of analyzing the trends in legal and regulatory changes in each country based on historical information on changes in past laws and regulations, events that triggered changes, and similar legal amendments in other countries, and detecting in advance expressions that may become problematic in the future. Server device 1 evaluates expressions in areas that do not currently violate regulations but are trending toward stricter regulations (such as environmental appeals and health appeals), including future risks, based on past legal amendment patterns and administrative guidance cases. For example, if an expression about the effects of a particular ingredient is currently permitted, but may become subject to regulation in the future due to the accumulation of relevant scientific knowledge or increased social interest, Server device 1 will warn the user and propose more sustainable alternative expressions.

[0072] Furthermore, an embodiment of context-dependent expression evaluation can also be described. Server device 1 has the function of evaluating the overall impression created not by individual words or images, but by combinations thereof. For example, it detects the possibility that the combination of the phrase "research suggests" and "rising graph" may be perceived as an exaggeration of scientific evidence. Server device 1 also analyzes the possibility that the use of certain music or colors, when combined with the displayed text, may be interpreted as implying a specific effect. By comprehensively evaluating the impression created by the interaction of multiple media elements such as text, images, audio, and video, Server device 1 can identify advertising expressions that, while not directly violating regulations, may be misleading overall, and propose revisions in advance.

[0073] Another possible implementation of personalized ad evaluation is also conceivable. Server device 1 has the function of automatically generating multiple possible display patterns for personalized ads that display different content based on the viewer's profile, and evaluating regulatory compliance for each. Server device 1, for example, works in conjunction with the advertising platform's API to extract or predict variations that may be displayed based on the set personalization rules, and verifies the compliance of each pattern with laws and regulations. This makes it possible to detect regulatory violation content that may only be displayed to some users in advance and to comprehensively manage regulatory risks.

[0074] Another embodiment involves a system equipped with an emotion and impact prediction and analysis function. Server device 1 predicts the psychological impact of an advertisement, such as its emotional effect and memorability, and has the function of supporting the creation of advertisements that comply with legal regulations while maintaining a strong effect. For example, if an expression that evokes "surprise" violates regulations, server device 1 will propose an alternative expression that has a similar emotional impact but is legally compliant, based on neuroscience and psychological insights. This makes it possible to maximize advertising effectiveness while ensuring compliance, and to achieve both an improvement in the advertiser's brand value and a reduction in legal risks.

[0075] The server device 1 may, for example, include a translation unit that translates text information. The translation unit accepts the user's specification of the target language for translation. In this case, each of the processing units described above may perform their respective processes using the translated text information, either before or after the translation unit has translated the text information acquired by the server device 1.

[0076] For example, the material information analysis unit 112 analyzes basic advertising information from the translated text information obtained by the server device 1, either before or after the translation unit translates it. The advertising rule determination unit 113 may determine advertising rules based on this basic advertising information and information about the country or region where the target language is used, or the country or region specified by the user. In this case, for example, if the text information obtained by the server device 1 is in English, the target language obtained by the translation unit is Korean, and the basic advertising information analyzed by the material information analysis unit 112 indicates that the target product is food, then the advertising rule determination unit 113 may determine, for example, the advertising guidelines for food in Korea as the advertising rules.

[0077] Furthermore, the translation unit may change the words, sentences, and expressions of the translated text based on the basic advertising information analyzed by the material information analysis unit 112, or the advertising rules determined by the advertising rule determination unit 113. In this case, for example, if the target product analyzed by the material information analysis unit 112 is cosmetics for men in their 20s, the translation unit may change the translated text to include words, sentences, and expressions that are more likely to appeal to men in their 20s. Similarly, if the advertising rules determined by the advertising rule determination unit 113 are the Pharmaceuticals and Medical Devices Act, the translation unit may change the translated text to exclude expressions that are not permitted in pharmaceutical advertisements.

[0078] The translation unit may translate the information output by each processing unit into a language specified by the user. In that case, the presentation unit 116 presents the basic advertising information, advertising rules, evaluation results, and revised material information translated by the translation unit to the user terminal 3.

[0079] While preferred embodiments of the present disclosure have been described in detail above with reference to the attached drawings, the technical scope of the present disclosure is not limited to such examples. It is clear to any person with ordinary skill in the art of the present disclosure that various modifications or alterations may be conceived within the scope of the technical idea set forth in the claims, and these will naturally also fall within the technical scope of the present disclosure.

[0080] The apparatus described herein may be implemented as a single device, or it may be implemented by multiple devices (e.g., cloud servers) that are partially or entirely connected by a network. For example, the CPU and storage device of the management server 20 may be implemented by different servers that are connected to each other by a network.

[0081] The series of processes performed by the apparatus described herein may be implemented using software, hardware, or a combination of software and hardware. Computer programs for implementing each function of the management server 20 according to this embodiment can be created and implemented on a PC or the like. Furthermore, a computer-readable recording medium containing such a computer program can also be provided. Examples of recording media include magnetic disks, optical disks, magneto-optical disks, and flash memory. Alternatively, the computer program may be distributed without using a recording medium, for example, via a network.

[0082] Furthermore, the processes described herein do not necessarily have to be performed in the order described. Some processing steps may be performed in parallel. Additional processing steps may be employed, and some processing steps may be omitted.

[0083] Furthermore, the effects described herein are merely descriptive or illustrative and not limiting. In other words, the technology relating to this disclosure may produce other effects that are obvious to those skilled in the art from the description herein, in addition to or in lieu of the effects described herein. [Explanation of Symbols]

[0084] 1 Server device 2 Network 3. User terminals 101 CPU 102 memory 103 Storage device 104 Communication Interface 105 Input device 106 Output device 111 Material Information Acquisition Unit 112 Material Information Analysis Department 113 Advertising Rules Determination Department 114 Evaluation Department 115 Modified material information generation section 116 Presentation section 131 Material Information Storage Unit 132 Advertising Rules Information Storage Unit 133 Modified Material Information Storage Unit

Claims

1. An evaluation device for evaluating material information, which is material for advertising, An advertising rule determination unit that determines advertising rules related to advertisements in which the aforementioned material information is used, based on the aforementioned material information, An evaluation unit that evaluates the material information based on the aforementioned advertising rules, An evaluation device equipped with the following features.

2. The aforementioned material includes text information and image information. The advertising rule determination unit analyzes the text information to determine the advertising rule. The evaluation apparatus according to claim 1.

3. The evaluation unit evaluates the material information based on the advertising rules. The evaluation apparatus according to claim 1 or 2.

4. If the evaluation unit evaluates that the material information has a problem in the advertising rules, the revised material information generation unit generates revised material information that does not have a problem. The evaluation apparatus according to claim 3, further comprising:

5. Based on the evaluation results of the evaluation unit, a presentation unit presents the problematic material information and the corrected material information to the user. The evaluation apparatus according to claim 4, comprising:

6. An evaluation program for evaluating advertising material information, On the computer, An advertising rule determination step in which advertising rules related to advertisements in which the material information is used are determined based on the aforementioned material, An evaluation step in which the aforementioned materials are evaluated based on the aforementioned advertising rules, An evaluation program that executes the program.

7. An evaluation method for evaluating material information for advertising, Computers An advertising rule determination step, which determines advertising rules related to an advertisement in which the material information is used based on the aforementioned material, An evaluation step in which the aforementioned materials are evaluated based on the aforementioned advertising rules, An evaluation method for performing this task.

Images