Advertisement creative design method and system based on advertisement sample analysis

Abstract

The invention relates to the field of advertisement creativity design, and discloses an advertisement creativity design method and system based on advertisement sample analysis, and the method comprises the steps: obtaining a plurality of competitive product video advertisements of a target product, key frame screenshots, forward comment time and forward comment keyword clouds of high-completion-rate fragments corresponding to the multiple competitive product video advertisements are obtained; clustering the plurality of competitive product video advertisements according to the key frame screenshots, the forward comment time and the forward comment keyword clouds of the high completion rate segments corresponding to the plurality of competitive product video advertisements to obtain a plurality of competitive product video advertisement categories, and determining a target competitive product video advertisement category in the plurality of competitive product video advertisement categories; and through the advertisement creativity design model, determining an advertisement creativity design scheme corresponding to the target product according to the plurality of competitive product video advertisements in the target competitive product video advertisement category. According to the method and the device, strategies, advantages and innovation points of competitors in the aspect of advertisement creativity can be automatically analyzed and designed in a targeted manner.

Description

Technical Field

[0001] The present application relates to the technical field of advertising creative design, and more specifically, to an advertising creative design method and system based on advertising sample analysis. Background Art

[0002] Throughout the development of the advertising industry, traditional creative design methods primarily relied on the designer's personal experience, inspiration, and basic market research. For example, designers might draw on past successes, combined with a general understanding of the target audience, to brainstorm creative proposals, which they then screened and optimized. This experience- and inspiration-based design model provided strong support for the development of the advertising industry for a period of time, helping numerous companies achieve their advertising goals.

[0003] However, traditional advertising creative design methods suffer from a significant flaw: they can only target competitors' creative ideas based on the designer's experience. Under this traditional model, designers often lack the ability to acquire, deeply analyze, and effectively utilize competitors' creative ideas in real time. They focus more on their own brand's characteristics and target audience, while analyzing and designing targeted advertising strategies, advantages, and innovations based on past experience. This can lead to a company's creative designs becoming similar to those of its competitors, making it difficult to accurately highlight its own differentiated advantages, making it difficult to stand out in the fierce market competition. This also fails to fully meet the higher demands of companies for creative advertising in a competitive environment and the development of information technology. Summary of the Invention

[0004] The purpose of this application is to provide an advertising creative design method and system based on advertising sample analysis, which solves the technical problem that competitors' strategies, advantages and innovations in advertising creativity can only be analyzed and targeted designed based on past experience, and achieves the technical effect of automatically analyzing and targeted designing competitors' strategies, advantages and innovations in advertising creativity.

[0005] An embodiment of the present application provides an advertising creative design method based on advertising sample analysis, the method comprising: obtaining multiple competing video advertisements of a target product, and obtaining key frame screenshots, positive comment times, and positive comment keyword word clouds of high completion rate segments corresponding to the multiple competing video advertisements; clustering the multiple competing video advertisements according to the key frame screenshots, positive comment times, and positive comment keyword word clouds of high completion rate segments corresponding to the multiple competing video advertisements, obtaining multiple competing video advertisement categories, and determining a target competing video advertisement category among the multiple competing video advertisement categories; and determining an advertising creative design scheme corresponding to the target product according to the multiple competing video advertisements in the target competing video advertisement category through an advertising creative design model.

[0006] In one possible implementation, multiple competing video advertisements are clustered based on key frame screenshots, positive comment times, and positive comment keyword word clouds of the high completion rate segments corresponding to the multiple competing video advertisements to obtain multiple competing video advertisement categories, including: determining the advertising segment features corresponding to the multiple competing video advertisements based on the key frame screenshots of the high completion rate segments corresponding to the multiple competing video advertisements through a key frame recognition model corresponding to the target product, the advertising segment features representing the image content features of the key frame screenshots of the high completion rate segments; determining the causal relationship features based on the timestamps, positive comment times, and positive comment keyword word clouds corresponding to the key frame screenshots of the high completion rate segments through a causal relationship inference model, the causal relationship features representing the causal relationship between the key frame screenshots of the high completion rate segments and the positive comment times and positive comment keyword word clouds; clustering the multiple competing video advertisements based on the advertising segment features and causal relationship features corresponding to the multiple competing video advertisements to obtain multiple competing video advertisement categories.

[0007] In another possible implementation, multiple competing video advertisements are clustered based on key frame screenshots of high completion rate clips corresponding to the multiple competing video advertisements, positive comment times, and positive comment keyword clouds to obtain multiple competing video advertisement categories, which also includes: determining the product similarity between the competing products and the target products corresponding to the multiple competing video advertisements; and clustering the multiple competing video advertisements based on the product similarity, advertising clip characteristics, and causal relationship characteristics corresponding to the multiple competing video advertisements to obtain multiple competing video advertisement categories.

[0008] In another possible implementation, multiple competing video ads are clustered based on key frame screenshots of high completion rate clips corresponding to the multiple competing video ads, positive comment times, and positive comment keyword clouds to obtain multiple competing video ad categories, further comprising: determining the similarity of core selling points, packaging methods, and delivery strategies between the competing products and the target products corresponding to the multiple competing video ads, and determining the reciprocal of the similarity of core selling points, the reciprocal of the similarity of packaging methods, and the reciprocal of the similarity of delivery strategies of the competing products corresponding to the multiple competing video ads as the difference of competitive factors corresponding to the multiple competing video ads; clustering the multiple competing video ads based on the difference of competitive factors, advertising clip features, and causal relationship features corresponding to the multiple competing video ads to obtain multiple competing video ad categories.

[0009] In another possible implementation, a target competing video advertising category among multiple competing video advertising categories is determined, including: obtaining user comment density, positive comment sentiment index, and completion growth rate index of competing video advertisements in the multiple competing video advertising categories within a preset time period; determining advertising performance evaluation values ​​corresponding to the multiple competing video advertising categories according to the user comment density, positive comment sentiment index, and completion growth rate index of competing video advertisements in the multiple competing video advertising categories within a preset time period; determining the maximum advertising performance evaluation value among the advertising performance evaluation values ​​corresponding to the multiple competing video advertising categories, and using the competing video advertising category corresponding to the maximum advertising performance evaluation value as the target competing video advertising category.

[0010] In another possible implementation, determining a target competing video advertising category among multiple competing video advertising categories also includes: obtaining a target budget factor corresponding to a target product, and obtaining budget factors corresponding to competing video advertisements in multiple competing video advertising categories; determining a difference between the budget factors corresponding to competing video advertisements in multiple competing video advertising categories and the target budget factors as a budget factor difference value; wherein the budget factor represents the budget amount of the video advertisement; determining the sum of the advertising performance evaluation values ​​and the budget factor difference values ​​respectively corresponding to multiple competing video advertising categories as an advertising category evaluation value; determining the maximum advertising category evaluation value among the advertising category evaluation values ​​respectively corresponding to multiple competing video advertising categories, and taking the competing video advertising category corresponding to the maximum advertising category evaluation value as the target competing video advertising category.

[0011] In another possible implementation, determining a target competing video advertising category among multiple competing video advertising categories also includes: obtaining a target brand style feature value corresponding to a target product, and obtaining brand style feature values ​​corresponding to competing video advertisements in multiple competing video advertising categories; determining a difference between the brand style feature values ​​corresponding to competing video advertisements in multiple competing video advertising categories and the target brand style feature value as a brand style difference value; wherein the brand style feature value represents the low-price promotion feature and luxury feature of the video advertisement; determining the sum of the advertising performance evaluation values, budget factor difference values ​​and brand style difference values ​​corresponding to the multiple competing video advertising categories as an advertising category evaluation value; determining the maximum advertising category evaluation value among the advertising category evaluation values ​​corresponding to the multiple competing video advertising categories, and taking the competing video advertising category corresponding to the maximum advertising category evaluation value as the target competing video advertising category.

[0012] In another possible implementation, determining a target competing video advertising category among multiple competing video advertising categories also includes: obtaining historical style evaluation values ​​of historical advertisements of the target product, and obtaining style evaluation values ​​of competing video advertisements in multiple competing video advertising categories; determining the difference between the style evaluation values ​​and historical style evaluation values ​​of competing video advertisements in multiple competing video advertising categories as an advertising style innovation value; wherein the style evaluation value includes style evaluation feature values ​​of multiple dimensions; determining the sum of advertising performance evaluation values, budget factor difference values, brand style difference values ​​and advertising style innovation values ​​corresponding to multiple competing video advertising categories as an advertising category evaluation value; determining the maximum advertising category evaluation value among the advertising category evaluation values ​​corresponding to multiple competing video advertising categories, and taking the competing video advertising category corresponding to the maximum advertising category evaluation value as the target competing video advertising category.

[0013] In another possible implementation, determining a target competing video advertising category among multiple competing video advertising categories also includes: obtaining the negative evaluation rate corresponding to the competing video advertisements in the multiple competing video advertising categories; determining the quotient of the advertising category evaluation values ​​and the negative evaluation rates corresponding to the multiple competing video advertising categories and normalizing them as the advertising category evaluation adjustment value; determining the maximum advertising category evaluation adjustment value among the advertising category evaluation adjustment values ​​corresponding to the multiple competing video advertising categories, and using the competing video advertising category corresponding to the maximum advertising category evaluation adjustment value as the target competing video advertising category.

[0014] An embodiment of the present application further provides an advertising creative design system based on advertising sample analysis, comprising a unit for executing any of the methods described above.

[0015] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0016] The embodiment of the present application provides an advertising creative design method based on advertising sample analysis, the method comprising: obtaining multiple competing video ads of a target product, and obtaining key frame screenshots, positive comment times, and positive comment keyword word clouds of the high completion rate segments corresponding to the multiple competing video ads; clustering the multiple competing video ads based on the key frame screenshots, positive comment times, and positive comment keyword word clouds of the high completion rate segments corresponding to the multiple competing video ads, obtaining multiple competing video ad categories, and determining a target competing video ad category among the multiple competing video ad categories; determining an advertising creative design scheme corresponding to the target product based on the multiple competing video ads in the target competing video ad category through an advertising creative design model. The embodiment of the present application can determine an advertising creative design scheme suitable for the target product based on the multiple competing video ads in the target competing video ad category, and can enhance the attractiveness of the advertisement to the target users. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0018] Figure 1 A flowchart of a first advertising creative design method based on advertising sample analysis provided in an embodiment of the present application;

[0019] Figure 2 A schematic diagram of the workflow of the first advertising creative design method based on advertising sample analysis provided in an embodiment of the present application;

[0020] Figure 3 A flowchart of a second method for designing advertising creative ideas based on advertising sample analysis provided in an embodiment of the present application;

[0021] Figure 4 A flowchart of a third method for designing advertising creative ideas based on advertising sample analysis provided in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of the logical structure of the first advertising creative design system based on advertising sample analysis provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or collections thereof.

[0024] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0025] As used in this specification and the appended claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0026] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0027] References to "one embodiment" or "some embodiments" in this specification mean that a particular feature, structure, or characteristic described in conjunction with that embodiment is included in one or more embodiments of the present application. Thus, phrases such as "in one embodiment," "in some embodiments," "in other embodiments," and "in other embodiments" appearing in various places in this specification do not necessarily refer to the same embodiment, but rather mean "one or more but not all embodiments," unless otherwise specifically emphasized. The terms "including," "comprising," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0028] In traditional advertising creative design methods, it is impossible to analyze competitors' strategies, advantages and innovations in advertising creativity and design targeted products based on past experience.

[0029] Based on the above reasons, an embodiment of the present application provides an advertising creative design method based on advertising sample analysis, the method comprising: obtaining multiple competing video ads of a target product, and obtaining key frame screenshots, positive comment times, and positive comment keyword word clouds of the high completion rate segments corresponding to the multiple competing video ads; clustering the multiple competing video ads according to the key frame screenshots, positive comment times, and positive comment keyword word clouds of the high completion rate segments corresponding to the multiple competing video ads, obtaining multiple competing video ad categories, and determining a target competing video ad category among the multiple competing video ad categories; determining an advertising creative design scheme corresponding to the target product according to the multiple competing video ads in the target competing video ad category through an advertising creative design model. The embodiment of the present application can determine an advertising creative design scheme suitable for the target product according to the multiple competing video ads in the target competing video ad category, and can enhance the attractiveness of the advertisement to the target users.

[0030] In some scenarios, an advertising creative design method based on advertising sample analysis in an embodiment of the present application can be applied to advertising creative design methods for various daily consumer goods, electronic products and luxury goods, and can improve the speed and efficiency of the advertising creative design method.

[0031] The following describes in detail an advertising creative design method based on advertising sample analysis provided in an embodiment of the present application with reference to specific examples.

[0032] Figure 1 The flowchart of the first advertising creative design method based on advertising sample analysis provided in the embodiment of the present application is as follows: Figure 1 As shown, the advertising creative design method based on advertising sample analysis includes S110 to S130, and S110 to S130 are described in detail below.

[0033] S110: Obtain multiple competing product video advertisements of the target product, and obtain key frame screenshots, positive comment times, and positive comment keyword clouds of the high completion rate clips corresponding to the multiple competing product video advertisements.

[0034] Figure 2 The flowchart of the first advertising creative design method based on advertising sample analysis provided in the embodiment of the present application is as follows: Figure 2 As shown, in the advertising creative design method based on advertising sample analysis in this implementation, we can first obtain multiple competing video advertisements of the target product, and extract key frame screenshots, positive comment time and positive comment keyword cloud of high completion rate segments from these competing video advertisements.

[0035] When designing advertising creatives, keyframe screenshots can capture the exciting scenes with high playback rates in the advertisement and reveal the visual design that attracts user interest.

[0036] When designing advertising creatives, positive comment time is used to identify where users' positive feedback occurs, and can specifically identify the climax of the video advertisement.

[0037] When designing advertising creatives, a positive comment keyword cloud can aggregate common positive words in comments, such as "creative" or "interesting", to highlight the highlights of the advertisement.

[0038] After obtaining key frame screenshots, positive comment time, and positive comment keyword word cloud, key frame screenshots, positive comment time, and positive comment keyword word cloud can provide comprehensive advertising effect indicators for subsequent steps and help identify the core features of competing video ads.

[0039] S120. Cluster the multiple competing video advertisements based on key frame screenshots of high completion rate clips, positive comment times, and positive comment keyword clouds corresponding to the multiple competing video advertisements to obtain multiple competing video advertisement categories, and determine a target competing video advertisement category among the multiple competing video advertisement categories.

[0040] like Figure 2 As shown, after obtaining the key frame screenshots, positive comment time and positive comment keyword word cloud of the high completion rate clips, multiple competing video advertisements can be clustered and grouped according to the data features of these competing video advertisements, including the key frame screenshots, positive comment time and positive comment keyword word cloud of the high completion rate clips, to obtain multiple competing video advertisement categories.

[0041] After obtaining multiple competing video ad categories, the multiple competing video ad categories can reveal similar themes or user preference patterns between advertisements, thereby determining the most relevant target competing video ad category.

[0042] For example, during the analysis process, unsupervised learning algorithms can be used to group competing video ads. Some categories may focus on emotional marketing, while others emphasize product features. This allows for rapid screening of target categories that are highly matched with the target product and optimizes the advertising design direction of the video ads.

[0043] S130. Determine an advertising creative design plan corresponding to the target product based on a plurality of competing product video advertisements in the target competing product video advertisement category through an advertising creative design model.

[0044] like Figure 2As shown, after obtaining multiple competitor video advertising categories, the advertising creative design model can be used to generate advertising creative design solutions corresponding to the target product based on multiple competitor video advertisements in the target competitor video advertising category. When designing advertising creatives, the advertising creative design model can integrate clustered category features, such as keyframe visual elements and positive comment keyword trends, to innovatively design new advertising concepts.

[0045] For example, the ad creative design model can learn the screenshot patterns of high completion rates of target category ads and combine them with popular themes in the keyword word cloud, such as "clever plot" or "visual impact", to plan the narrative structure of the video ad, ensuring that the design plan is based on real user feedback and competitive advantages.

[0046] For example, the advertising creative design model may be an LLM (Large Language Model) model that is fine-tuned based on multiple sample competing video ads and sample advertising creative design solutions in the sample competing video ad category.

[0047] The beneficial effects of the above implementation method are that it can efficiently identify advertising trends through cluster analysis, reduce blind trial and error in the design process, and improve the accuracy and speed of creative generation; through the advertising creative design model, based on multiple competing video ads in the target competing video ad category, determine the advertising creative design plan suitable for the target product, which can enhance the attractiveness of the advertisement to the target users.

[0048] The beneficial effect of the above implementation method is that by combining visual content and user feedback word cloud to perform cluster analysis on competing advertisements, the accuracy of cluster analysis on competing advertisements is improved, and both the visual effect and communication effect of the advertisement can be taken into account.

[0049] In some implementations, in the above-mentioned S120, multiple competing video advertisements are clustered based on the key frame screenshots, positive comment times, and positive comment keyword clouds corresponding to the multiple competing video advertisements with high completion rates, to obtain multiple competing video advertisement categories, including S121 to S122. S121 to S122 are described in detail below.

[0050] S121. Using a keyframe recognition model corresponding to the target product, determine the advertising segment features corresponding to multiple competing product video ads based on the keyframe screenshots of the high completion rate segments corresponding to the competing product video ads. The advertising segment features represent the image content features of the keyframe screenshots of the high completion rate segments. Using a causal relationship inference model, determine the causal relationship features based on the timestamps, positive review times, and positive review keyword word clouds corresponding to the keyframe screenshots of the high completion rate segments. The causal relationship features represent the causal relationship between the keyframe screenshots of the high completion rate segments and the positive review times and positive review keyword word clouds.

[0051] During ad creative design based on ad example analysis, a keyframe recognition model specifically designed for the target product can be used to process keyframe screenshots from multiple competing video ads with high completion rates. This model can extract the visual content features contained within the keyframe screenshots and generate ad segment features that represent the core visual elements of the ad.

[0052] For example, when analyzing video advertisements for sports shoes, the key frame recognition model corresponding to the target product in the sports shoe category can identify the image features of slow-motion shots showing the elasticity of the shoe soles in clips with high completion rates, capturing the core visual design elements that attract users' attention.

[0053] Exemplarily, the key frame recognition model may be a multimodal visual understanding model, and the key frame recognition model is used to extract visual content features contained in the key frame screenshots.

[0054] After obtaining the characteristics of the advertising clip, the causal inference model can be used to analyze the timestamp position corresponding to the key frame screenshot, the time when the positive comments occurred, and the keyword cloud of the positive comments. The causal inference model can establish the association rules between the key frame content and the user's positive feedback, and generate a feature vector that represents the causal relationship between the three.

[0055] For example, when a product close-up keyframe appears at 15 seconds into a video ad, the causal inference model can infer that there is a strong correlation between the product close-up keyframe and positive comment keywords such as "burning" that appear at 20 seconds, indicating that the close-up image will trigger the audience's expression of excitement. The causal relationship of the advertising effect contained in the video ad is then explored through the feature vector that represents the causal relationship between the three.

[0056] Exemplarily, the causal relationship inference model can be a deep learning model based on a neural network, and the causal relationship inference model can be obtained through training of the sample timestamp position corresponding to the sample key frame screenshot, the occurrence time of the sample positive comment, the keyword cloud of the sample positive comment, and the sample causal relationship features.

[0057] S122. Cluster the multiple competing video advertisements according to the advertising segment features and causal relationship features corresponding to the multiple competing video advertisements to obtain multiple competing video advertisement categories.

[0058] After obtaining the advertising segment features and causal relationship features corresponding to multiple competing video ads, the advertising segment features and causal relationship features can be integrated to perform a joint clustering analysis on the multiple competing video ads. Then, based on the composite correlation pattern of visual content and user feedback, the ads can be divided into categories with similar success factors.

[0059] For example, based on visual features, sports shoe advertisements are divided into the "technological display" group and the "scenario experience" group. At the same time, combined with the causal relationship characteristics, it is found that the "technological display" group is associated with comment words such as "innovation" and "lightweight", and the "scenario experience" group is associated with keywords such as "comfort" and "fashion". Through further cluster analysis, a multi-dimensional category division of video advertisements is formed.

[0060] The beneficial effect brought about by the above implementation method is that the dual feature extraction mechanism can deeply analyze the internal connection of the elements of advertising success, so that the clustering results can simultaneously reflect the coupling relationship between content design and user feedback.

[0061] The beneficial effect of the above implementation method is that, by using causal relationship characteristics as the classification basis, it can accurately distinguish advertising types that are similar on the surface but have different user response mechanisms, provide a high-value reference dimension for subsequent creative design, and improve the effectiveness of advertising creative design.

[0062] In some implementations, in the above-mentioned S120, multiple competing video advertisements are clustered based on the key frame screenshots, positive comment times and positive comment keyword clouds corresponding to the high completion rate clips of the multiple competing video advertisements to obtain multiple competing video advertisement categories, which also includes S123 to S124. S123 to S124 are explained in detail below.

[0063] S123: Determine the product similarity between the competing products corresponding to the multiple competing product video advertisements and the target product.

[0064] In the process of advertising creative design based on advertising sample analysis, the product similarity between the competing products and the target products corresponding to multiple competing video ads can be determined. Product similarity represents the degree of similarity between the competing products and the target products in terms of category, function and structure, and then helps evaluate whether the competing ads have reference value through product similarity.

[0065] For example, in video advertising analysis, for a newly released target product of sports shoes, the advertising product similarities of competing sports shoes can be compared, specifically including commonalities in brand positioning and usage scenarios, so as to screen out the most relevant advertising samples for subsequent analysis. This ensures that the clustering process is based on the comparability of the products themselves and avoids grouping irrelevant advertisements.

[0066] S124. Cluster the multiple competing product video advertisements according to the product similarities, advertisement segment features, and causal relationship features corresponding to the multiple competing product video advertisements to obtain multiple competing product video advertisement categories.

[0067] In this implementation, product similarity, advertising clip features, and causal relationship features can be combined in cluster analysis to cluster and group multiple competing video ads. This can then simultaneously consider the interaction between product similarity and advertising feedback data, and comprehensively optimize the accuracy of category division.

[0068] For example, multiple competing video ads can be clustered and grouped based on the product similarity, advertising clip features, and causal relationship features of a competing sports shoe, distinguishing between a "professional sports" group and a "leisure fashion" group, accurately capturing the advertising success factors and product association patterns.

[0069] The beneficial effect of the above implementation method is that the introduction of product similarity as a key variable can filter out irrelevant interference from competing products, improve the pertinence and practicality of clustering results, and ensure that the creative design of advertising is more in line with the characteristics of the target product.

[0070] The beneficial effect of the above implementation method is that the integration of multi-dimensional data of product similarity, advertising clip characteristics and causal relationship characteristics can enhance the accuracy of category division, avoid deviations caused by relying solely on advertising performance, and improve the efficiency of the creative generation process and user preference matching.

[0071] In some implementations, in the above-mentioned S120, multiple competing video advertisements are clustered based on the key frame screenshots, positive comment times and positive comment keyword clouds corresponding to the high completion rate clips of the multiple competing video advertisements to obtain multiple competing video advertisement categories, and also include S125 to S126. S125 to S126 are explained in detail below.

[0072] S125. Determine the similarity of core selling points, similarity of packaging methods, and similarity of delivery strategies between the competing products and the target product corresponding to the multiple competing video advertisements respectively, and determine the sum of the reciprocal of the similarity of core selling points, the reciprocal of the similarity of packaging methods, and the reciprocal of the similarity of delivery strategies of the competing products corresponding to the multiple competing video advertisements respectively as the difference of competitive factors corresponding to the multiple competing video advertisements respectively.

[0073] In this implementation, the similarity of core selling points, packaging methods and delivery strategies between the competing products and the target products corresponding to multiple competing video advertisements can be further determined. These similarity indicators respectively represent the degree of matching between the competing products and the target products in terms of core product functional appeals, appearance packaging form and marketing strategy.

[0074] For example, when analyzing pet food video ads, core selling point similarity can measure whether competing ads also emphasize the core value of "natural ingredients." Packaging similarity can assess whether the visual styles of the packaging are similar. Delivery strategy similarity can compare whether both ads are placed on pet blogger channels.

[0075] In this implementation, by calculating the sum of the inverses of the core selling point similarity, packaging method similarity, and delivery strategy similarity, a competitive factor difference index representing the degree of competitive difference can be generated. The competitive factor differences corresponding to multiple competing video advertisements are as follows: the greater the competitive factor difference, the greater the difference between the competing product's competitive strategy and the target product.

[0076] For example, when a competitor uses high-end gift box packaging while the target product adopts environmentally friendly simple packaging, the decrease in packaging similarity will cause its reciprocal to increase, thereby improving the competitive factor difference score of the competitor, and then quantitatively identifying advertising cases that have significant competitive differences with the target product.

[0077] S126. Cluster the multiple competing video advertisements according to the competition factor differences, advertisement segment features, and causal relationship features corresponding to the multiple competing video advertisements to obtain multiple competing video advertisement categories.

[0078] After obtaining the degree of difference in competitive factors, the degree of difference in competitive factors, advertising segment characteristics and causal relationship characteristics can be integrated into the clustering process for comprehensive analysis. This ensures that the market differentiation competition dimension is fully considered when grouping advertisements, and avoids categorizing advertisements with significant differences in competitive strategies into the same category.

[0079] For example, when clustering pet food advertisements, vegetarian food advertisements with higher differences in competitive factors will be separated from the mainstream meat food advertisement group. At the same time, the key frame characteristics of their high completion rate segments showing vegetable ingredients and the causal relationship characteristics of the "healthy choice" keyword in user comments are combined to finally form an advertising category that reflects the competitive strategy of the market segment.

[0080] The beneficial effect of the above implementation method is that it accurately identifies differentiated competition strategies through the competition factor difference index, enables the clustering results to effectively distinguish advertising types that are similar on the surface but have completely different market competition positioning, and improves the risk avoidance ability of creative design.

[0081] The beneficial effect of the above implementation method is that the composite calculation of three-dimensional similarity indicators can present the market competition situation in three dimensions, avoid strategic misjudgments caused by relying solely on advertising content features, and enhance the adaptability of creative design solutions to the market competition environment.

[0082] Figure 3 The flowchart of the second advertising creative design method based on advertising sample analysis provided in the embodiment of the present application is as follows: Figure 3 As shown, in the above S120, determining a target competing product video advertisement category among multiple competing product video advertisement categories includes S210 to S220, and S210 to S220 are described in detail below.

[0083] S210: Obtain user review density, positive review sentiment index, and completion growth rate index for competing video ads in multiple competing video ad categories within a preset time period. Determine advertising performance evaluation values ​​corresponding to each of the multiple competing video ad categories based on the user review density, positive review sentiment index, and completion growth rate index for the competing video ads in the multiple competing video ad categories within the preset time period.

[0084] In this implementation method, for multiple competing video advertising categories, the user comment density, positive comment sentiment index and completion growth rate index of the competing video advertisements contained therein within a preset time period can be obtained respectively. These indicators can present the comprehensive performance effects of video advertisements of each advertising category in a three-dimensional manner in the short term, and then determine the target competing video advertising category that is most suitable for generating advertising creativity through the comprehensive performance effects in the short term.

[0085] In this implementation, the density of user comments reflects the discussion popularity of the advertisement, such as the number of comments generated per unit time within 72 hours after the video advertisement is released.

[0086] In this implementation, the positive comment sentiment index can quantify the proportion of users' positive emotions through the sentiment analysis model.

[0087] In this implementation, the completion growth rate measures the increase in the completion rate of advertisement playback.

[0088] Exemplarily, the preset time period may be 30 days.

[0089] After obtaining the user comment density, positive comment sentiment index and completion growth rate index, the advertising performance evaluation values ​​corresponding to multiple competing video advertising categories can be calculated based on the user comment density, positive comment sentiment index and completion growth rate index of multiple competing video advertising categories. The advertising performance evaluation value can be generated by weighted fusion of three-dimensional indicators.

[0090] It should be noted that when generating an advertising performance evaluation value by weighted fusion of three-dimensional indicators, a higher weight can be given to the completion growth rate to directly reflect the core appeal of the advertisement, thereby ensuring that the evaluation value accurately captures the true effectiveness of the advertisement category.

[0091] S220: Determine the maximum advertising performance evaluation value among the advertising performance evaluation values ​​corresponding to a plurality of competing video advertising categories, and use the competing video advertising category corresponding to the maximum advertising performance evaluation value as the target competing video advertising category.

[0092] After obtaining the advertising performance evaluation values ​​corresponding to multiple competing video advertising categories, the maximum value among the advertising performance evaluation values ​​of the multiple competing video advertising categories can be identified, and the competing video advertising category corresponding to the maximum value can be determined as the target competing video advertising category, thereby automatically screening the advertising strategy model with the best performance in the current market environment.

[0093] For example, when a food advertising category has a completion growth rate of 35% within a preset time period of 30 days and a positive comment sentiment index of 0.85, the performance evaluation value of the food advertising category is significantly higher than that of other categories. In this case, the "interesting plot + product close-up" combination contained in the food advertising category can be selected as a reference benchmark for creative design.

[0094] The beneficial effect of the above implementation method is that it quantitatively evaluates the effectiveness of advertising strategies through dynamic indicators, avoids subjective judgment bias, and ensures that the selected advertising categories have an empirical basis for success; the advertising performance evaluation value not only reflects the user's actual viewing behavior but also avoids data noise interference, thereby improving the commercial value conversion potential of advertising creative scheme design.

[0095] In some implementations, in the above-mentioned S120, determining a target competing product video advertisement category among multiple competing product video advertisement categories includes S230 to S240, and S230 to S240 are described in detail below.

[0096] S230: Obtain a target budget factor corresponding to the target product, and obtain budget factors corresponding to competing video ads in multiple competing video ad categories. Determine the difference between the budget factors corresponding to the competing video ads in the multiple competing video ad categories and the target budget factor as a budget factor difference value. The budget factor represents the budget amount for the video ad.

[0097] In this implementation method, the target budget factor corresponding to the target product can be obtained, and the target budget factor represents the budget investment intensity of the target product video advertisement. At the same time, the budget factors of competing advertisements in multiple competing product video advertisement categories can be obtained, and the budget factor represents the budget amount of the video advertisement (i.e., the budget investment intensity).

[0098] For example, in an analysis of sneaker video ads, the target budget factor may be set at a mid-range investment level. However, if a competing ad category uses celebrity endorsements and large-scale special effects production, the budget factor of the competing ad category may be significantly higher than the target budget factor; if another competing ad category uses a user-generated content model, the budget factor may be close to or lower than the target budget factor.

[0099] In this implementation, the difference between the budget factor corresponding to the competitor's advertising category and the target budget factor can be calculated as the budget factor difference value, which quantifies the degree of budget adaptation.

[0100] For example, when a smartphone ad category uses film- and television-level production, its positive difference value reflects the risk of over-investment of resources; while when a home product ad category uses a group performance live-action strategy, its negative difference value shows its cost-efficiency advantage, which enables the budget factor difference value to objectively evaluate the reference value of each category's plan in the budget dimension.

[0101] S240: Determine the sum of the advertising performance evaluation values ​​and budget factor difference values ​​corresponding to the multiple competing video advertising categories as the advertising category evaluation value. Determine the maximum advertising category evaluation value among the advertising category evaluation values ​​corresponding to the multiple competing video advertising categories, and use the competing video advertising category corresponding to the maximum advertising category evaluation value as the target competing video advertising category.

[0102] After obtaining the budget factor difference value, the sum of the advertising performance evaluation value and the budget factor difference value can be calculated as the advertising category evaluation value. The advertising performance evaluation value is related to historical performance indicators (such as user comment density and completion growth rate), and the budget factor difference value can further modify the performance score according to the budget constraint through the pre-budget feature.

[0103] For example, the advertising performance evaluation value of a cosmetics video advertising category is 0.92, but because the budget factor difference value is -0.5, it can be determined that the advertising category evaluation value is 0.42.

[0104] In this implementation method, the maximum value of all advertising category evaluation values ​​can be ultimately identified, and the competitor video advertising category corresponding to the maximum advertising category evaluation value can be used as the target competitor video advertising category. This target competitor video advertising category selection mechanism not only takes into account advertising effect data, but also ensures budget feasibility.

[0105] The beneficial effect of the above implementation method is that the advertising performance evaluation value is dynamically corrected through the budget factor difference value, which can avoid the risk of resource overspending caused by the sole pursuit of advertising effects and improve the commercial feasibility of creative plans; incorporating budget adaptability and communication effects into a unified evaluation system, so that the final selected advertising category achieves the best balance between maximizing effects and cost controllability, thereby enhancing the expected return on investment of advertising.

[0106] In some implementations, in the above-mentioned S120, determining the target competing product video advertisement category among multiple competing product video advertisement categories further includes S250 to S260, and S250 to S260 are described in detail below.

[0107] S250: Obtain a target brand style feature value corresponding to the target product, and obtain brand style feature values ​​corresponding to competing video advertisements in multiple competing product video advertisement categories. Determine the difference between the brand style feature values ​​corresponding to the competing video advertisements in the multiple competing product video advertisement categories and the target brand style feature value as a brand style difference value. The brand style feature value represents the low-price promotion characteristics and luxury characteristics of the video advertisement.

[0108] In this implementation, a target brand style feature value corresponding to the target product can be obtained. The target brand style feature value represents the performance strength of the advertising strategy in two dimensions: low-price promotion feature and luxury feature.

[0109] At the same time, brand style feature values ​​of competing advertisements in multiple competing video advertisement categories may be obtained. The brand style feature values ​​may be obtained by performing video analysis on competing advertisements in multiple competing video advertisement categories.

[0110] For example, for car video ads, if the target brand is positioned as an economical family car, the target brand style feature value can be biased towards the low-price promotion dimension; while if a competitor advertising category frequently displays diamond-encrusted car logos or celebrity endorsements, the competitor advertising category can be biased towards the high luxury feature value.

[0111] In this implementation, the difference between the brand style feature value corresponding to the competitor video advertisement category and the target brand style feature value can be further calculated as the brand style difference value. The brand style difference value can objectively reflect the degree of brand positioning matching.

[0112] For example, when the target product emphasizes cost-effectiveness, the competitive advertising category with a higher luxury feature value will produce a larger positive difference value, revealing that there is a significant deviation between the brand style of the competitive advertising category with a higher luxury feature value and the target product, and thus the synergy between advertising strategy and brand positioning can be evaluated.

[0113] S260: Determine the sum of the advertising performance evaluation values, budget factor difference values, and brand style difference values ​​corresponding to each of the multiple competing video advertising categories as an advertising category evaluation value. Determine the maximum advertising category evaluation value among the advertising category evaluation values ​​corresponding to the multiple competing video advertising categories, and use the competing video advertising category corresponding to the maximum advertising category evaluation value as the target competing video advertising category.

[0114] In this implementation method, the advertising performance evaluation value, the budget factor difference value and the brand style difference value can be further summed to obtain a comprehensive advertising category evaluation value. The advertising performance evaluation value comes from historical performance indicators, the budget factor difference value reflects the cost matching degree, and the brand style difference value measures the positioning consistency, so that the advertising category evaluation value can comprehensively reflect the advertising performance evaluation value, the budget factor difference value and the brand style difference value.

[0115] When determining the target competitor video advertising category, you can compare the advertising category evaluation values ​​of all categories and select the competitor video advertising category corresponding to the maximum value of the target competitor video advertising category as the target competitor video advertising category. This can ensure that the target competitor video advertising category achieves the optimal balance in the three dimensions of communication effect, cost control and brand positioning.

[0116] The beneficial effect of the above implementation method is that the introduction of brand style difference values ​​can avoid the risk of deviation between creative design and brand core values, and can avoid strategic mismatch caused by high-end brands misusing promotional styles or mass brands imitating luxury routes; it can simultaneously cover the three key dimensions of communication performance, cost adaptation and brand style, and can generate creative solutions that are more in line with the company's business strategy, thereby improving the overall benefits of advertising.

[0117] Figure 4 The flowchart of the third advertising creative design method based on advertising sample analysis provided in the embodiment of the present application is as follows: Figure 4 As shown, in the above S120, determining the target competing product video advertisement category among the multiple competing product video advertisement categories also includes S310 to S320, and S310 to S320 are described in detail below.

[0118] S310: Obtain historical style ratings for historical advertisements of the target product, and obtain style ratings for competing video advertisements in multiple competing video advertisement categories. Determine the difference between the style ratings of the competing video advertisements in the multiple competing video advertisement categories and the historical style ratings as the advertisement style innovation value. The style ratings include style rating feature values ​​across multiple dimensions.

[0119] In this implementation, during the creative advertising design process, a historical style evaluation value of a target product's historical advertisements may be obtained, where the historical style evaluation value represents the style characteristics of the target product's historical advertisements.

[0120] For example, the historical style evaluation value can be obtained by quantitatively analyzing the multi-dimensional style features of the historical advertisements of the target product. The historical style evaluation value may include evaluation feature values ​​of dimensions such as picture tone features, shot switching frequency, and narrative rhythm.

[0121] In this implementation, style evaluation values ​​of competing advertisements in multiple competing video advertisement categories may be obtained, and the style evaluation values ​​reflect the characteristics of the advertising strategies of competing advertisements of different styles in terms of creative expression.

[0122] For example, for beverage video advertisements, the target product's historical advertisements may mostly use bright colors and high-frequency shot switching. If a competitor's advertising category uses low-saturation cold colors and long-shot narratives, the historical style evaluation value and the style evaluation value will show significant differences.

[0123] S320: Determine the sum of the advertising performance evaluation values, budget factor difference values, brand style difference values, and advertising style innovation values ​​corresponding to each of the multiple competing video advertising categories as the advertising category evaluation value. Determine the maximum advertising category evaluation value among the advertising category evaluation values ​​corresponding to the multiple competing video advertising categories, and use the competing video advertising category corresponding to the maximum advertising category evaluation value as the target competing video advertising category.

[0124] In this implementation method, the difference between the style evaluation value corresponding to the competitor video advertising category and the historical style evaluation value can be calculated as the advertising style innovation value. The advertising style innovation value can quantitatively reflect the degree of breakthrough in the advertising strategy of the competitor video advertising category and the inherent style of the target product.

[0125] For example, when a competitor's advertising category for an electronic product adopts a documentary interview format instead of traditional product display, the difference forms a positive innovation value; if the same celebrity endorsement model is used, the innovation value approaches zero, allowing the advertising style innovation value to dynamically evaluate the balance between advertising innovation and brand continuity.

[0126] After obtaining the advertising style innovation value, the advertising performance evaluation value, budget factor difference value, brand style difference value and advertising style innovation value can be further superimposed to generate a more comprehensive advertising category evaluation value; among them, the advertising performance evaluation value measures the communication effectiveness, the budget factor difference value controls the cost risk, the brand style difference value ensures strategic synergy, and the advertising style innovation value encourages creative breakthroughs in advertising.

[0127] After obtaining the advertising category evaluation value, all advertising category evaluation values ​​can be compared, and the competitor video advertising category corresponding to the maximum advertising category evaluation value can be used as the target competitor video advertising category, thereby determining the target competitor video advertising category.

[0128] The beneficial effect of the above implementation method is that by stimulating the selection of innovative strategies through the advertising style innovation value indicator, it can avoid creative design from falling into brand historical path dependence and enhance the market freshness and topicality of advertising; it can simultaneously take into account the balanced development of communication effect, budget adaptation, brand matching and innovative breakthroughs, maximize the breakthrough value of advertising creativity while ensuring the stability of business strategy, and optimize the long-term competitiveness of advertising.

[0129] In some implementations, in the above-mentioned S120, determining the target competing product video advertisement category among multiple competing product video advertisement categories further includes S330 to S340, and S330 to S340 are described in detail below.

[0130] S330: Obtain negative review rates corresponding to competing product video advertisements in multiple competing product video advertisement categories.

[0131] In this implementation, during the creative advertising design process, the negative evaluation rates corresponding to competing video ads in multiple competing video ad categories can be obtained. The negative evaluation rates reflect the proportion of negative user feedback during the advertising dissemination process.

[0132] For example, for fast-moving consumer goods video ads, a competitor's ad category may have 30% of comments mentioning keywords such as "fake" or "over-packaging" due to exaggerated publicity. Its negative review rate is significantly higher than the industry average. The negative review rate indicator can reveal the potential public opinion risks of advertising strategies.

[0133] S340: Determine the quotient of the advertising category rating values ​​and negative rating rates corresponding to multiple competing video advertising categories, normalize the quotient, and use the quotient as the advertising category rating adjustment value. Determine the maximum advertising category rating adjustment value among the advertising category rating adjustment values ​​corresponding to the multiple competing video advertising categories, and use the competing video advertising category corresponding to the maximum advertising category rating adjustment value as the target competing video advertising category.

[0134] After obtaining the negative review rate, the quotient of the advertising category evaluation value and the negative review rate corresponding to each competing video advertising category can be calculated, and the calculation result can be normalized to obtain the advertising category evaluation adjustment value; among them, the advertising category evaluation value comes from the sum of the advertising performance evaluation value, budget factor difference value, brand style difference value and advertising style innovation value in the previous step, and the division operation will significantly reduce the advertising category evaluation adjustment value of the competing video advertising category with a high negative review rate.

[0135] For example, although a beauty video advertising category has a high advertising category rating of 8.5 (novel creativity and budget adaptation), due to an 18% negative review rate, its normalized adjustment value drops to 7.2, making the advertising category rating adjustment value significantly lower than other competing product categories with a negative rate of only 5%.

[0136] After obtaining the ad category evaluation adjustment value, you can compare the ad category evaluation adjustment values ​​of all categories and select the competitor video ad category corresponding to the maximum ad category evaluation adjustment value as the target category. This ensures that the selected plan has both effectiveness advantages and risk control capabilities.

[0137] The beneficial effect of the above implementation method is that the comprehensive evaluation value can be dynamically suppressed through the negative evaluation rate, which can effectively avoid the selection of high-transmission risk advertising strategies and prevent damage to brand reputation; incorporating public opinion monitoring indicators into the evaluation system enables the final selected advertising category to have stronger public opinion stability while maintaining creative effects, thereby improving the long-term sustainability of marketing activities.

[0138] An embodiment of the present application further provides an advertising creative design system based on advertising sample analysis, comprising a unit for executing any of the methods described above.

[0139] Figure 5 The first embodiment of the present application provides a logical structure diagram of an advertising creative design system based on advertising sample analysis, such as Figure 5 As shown, the system 1 of this embodiment includes a processing unit 11, a storage unit 12, and a transceiver unit 13. The processing unit 11 is used to process data, the storage unit 12 is used to store data, and the transceiver unit 13 is used to send and receive data. The processing unit 11, the storage unit 12, and the transceiver unit 13 cooperate with each other to implement the above method. The beneficial effects of the embodiment of the present application have been described in the above method and will not be repeated here.

[0140] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the method embodiment of this application. Their specific functions and technical effects can be found in the method embodiment section and will not be repeated here.

[0141] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0142] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process of the above-mentioned method embodiment by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can at least include: any entity or device capable of carrying computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, mobile hard drive, magnetic disk, or optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0143] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0144] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0145] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules or units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0146] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0147] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. An advertising creative design method based on advertising sample analysis, characterized in that: The method comprises: Obtain multiple competing video ads for the target product, and obtain keyframe screenshots, positive comment times, and positive comment keyword clouds for each of the high completion rate clips of the competing video ads; Clustering multiple competing video ads based on key frame screenshots, positive comment times, and positive comment keyword clouds of the high completion rate clips of multiple competing video ads to obtain multiple competing video ad categories, and determining a target competing video ad category among the multiple competing video ad categories; Through the advertising creative design model, based on multiple competing video ads in the target competing video ad category, the advertising creative design plan corresponding to the target product is determined.

2. The method according to claim 1, wherein Based on the key frame screenshots, positive comment time, and positive comment keyword cloud of multiple competing video ads with high completion rate, we clustered the multiple competing video ads and obtained multiple competing video ad categories, including: Using a key frame recognition model corresponding to the target product, based on key frame screenshots of high completion rate clips corresponding to multiple competing product video ads, the ad segment features corresponding to each of the competing product video ads are determined. The ad segment features represent the image content features of the key frame screenshots of the high completion rate clips. Using a causal relationship inference model, based on the timestamps, positive comment times, and positive comment keyword word clouds corresponding to the key frame screenshots of the high completion rate clips, the causal relationship features are determined. The causal relationship features represent the causal relationship between the key frame screenshots of the high completion rate clips and the positive comment times and positive comment keyword word clouds. The multiple competing video advertisements are clustered according to the advertising segment features and causal relationship features corresponding to the multiple competing video advertisements to obtain multiple competing video advertisement categories.

3. The method according to claim 2, wherein Based on the key frame screenshots, positive comment time, and positive comment keyword cloud of the high completion rate clips of multiple competing video ads, multiple competing video ads are clustered to obtain multiple competing video ad categories, including: Determine the product similarity between the competing products and the target product corresponding to multiple competing product video ads; The multiple competing video advertisements are clustered according to their corresponding product similarities, advertising segment features, and causal relationship features to obtain multiple competing video advertisement categories.

4. The method according to claim 3, wherein Based on the key frame screenshots, positive comment time, and positive comment keyword cloud of the high completion rate clips of multiple competing video ads, multiple competing video ads are clustered to obtain multiple competing video ad categories, including: Determine the similarity of core selling points, packaging methods, and delivery strategies of the competing products and the target product, respectively, corresponding to the multiple competing product video ads. Also determine the sum of the reciprocal of the similarity of core selling points, the reciprocal of the similarity of packaging methods, and the reciprocal of the similarity of delivery strategies of the competing products, respectively, corresponding to the multiple competing product video ads, as the competitive factor difference degree corresponding to the multiple competing product video ads. The multiple competing video advertisements are clustered according to the competition factor differences, advertisement segment features, and causal relationship features corresponding to the multiple competing video advertisements to obtain multiple competing video advertisement categories.

5. The method according to claim 4, wherein Identify target competitor video ad categories across multiple competitor video ad categories, including: Obtaining user comment density, positive comment sentiment index, and completion growth rate index of competing video advertisements in multiple competing video advertisement categories within a preset time period; determining advertising performance evaluation values ​​corresponding to each of the multiple competing video advertisement categories based on the user comment density, positive comment sentiment index, and completion growth rate index of the competing video advertisements in the multiple competing video advertisement categories within the preset time period; Determine the maximum advertising performance evaluation value among the advertising performance evaluation values ​​corresponding to multiple competing video advertising categories, and use the competing video advertising category corresponding to the maximum advertising performance evaluation value as the target competing video advertising category.

6. The method according to claim 5, wherein Identify target competitor video ad categories among multiple competitor video ad categories, including: Obtaining a target budget factor corresponding to a target product and obtaining budget factors corresponding to competing video ads in multiple competing video ad categories; determining a difference between the budget factors corresponding to competing video ads in the multiple competing video ad categories and the target budget factor as a budget factor difference value; wherein the budget factor represents the budget amount of the video ad; Determine the sum of the advertising performance evaluation values ​​and budget factor difference values ​​corresponding to multiple competing video advertising categories as the advertising category evaluation value; determine the maximum advertising category evaluation value among the advertising category evaluation values ​​corresponding to multiple competing video advertising categories, and use the competing video advertising category corresponding to the maximum advertising category evaluation value as the target competing video advertising category.

7. The method according to claim 7, wherein: Identify target competitor video ad categories among multiple competitor video ad categories, including: Obtaining a target brand style feature value corresponding to a target product, and obtaining brand style feature values ​​corresponding to competing product video advertisements in multiple competing product video advertisement categories; determining a difference between the brand style feature values ​​corresponding to competing product video advertisements in the multiple competing product video advertisement categories and the target brand style feature value as a brand style difference value; wherein the brand style feature value represents the low-price promotion feature and luxury product feature of the video advertisement; Determine the sum of the advertising performance evaluation values, budget factor difference values ​​and brand style difference values ​​corresponding to multiple competing video advertising categories as the advertising category evaluation value; determine the maximum advertising category evaluation value among the advertising category evaluation values ​​corresponding to multiple competing video advertising categories, and use the competing video advertising category corresponding to the maximum advertising category evaluation value as the target competing video advertising category.

8. The method according to claim 7, wherein Identify target competitor video ad categories among multiple competitor video ad categories, including: Obtain historical style evaluation values ​​of historical advertisements for the target product, and obtain style evaluation values ​​of competing video advertisements in multiple competing video advertisement categories; determine the difference between the style evaluation values ​​of competing video advertisements in the multiple competing video advertisement categories and the historical style evaluation values ​​as the advertisement style innovation value; wherein the style evaluation value includes style evaluation feature values ​​of multiple dimensions; Determine the sum of the advertising performance evaluation values, budget factor difference values, brand style difference values ​​and advertising style innovation values ​​corresponding to multiple competing video advertising categories as the advertising category evaluation value; determine the maximum advertising category evaluation value among the advertising category evaluation values ​​corresponding to multiple competing video advertising categories, and use the competing video advertising category corresponding to the maximum advertising category evaluation value as the target competing video advertising category.

9. The method according to claim 8, wherein Identify target competitor video ad categories among multiple competitor video ad categories, including: Obtain the negative review rates of competing video ads in multiple competing video ad categories; Determine the quotient of the advertising category evaluation values ​​and the negative evaluation rates corresponding to multiple competing video advertising categories and normalize them as the advertising category evaluation adjustment value; determine the maximum advertising category evaluation adjustment value among the advertising category evaluation adjustment values ​​corresponding to multiple competing video advertising categories, and use the competing video advertising category corresponding to the maximum advertising category evaluation adjustment value as the target competing video advertising category.

10. An advertising creative design system based on advertising sample analysis, characterized in that: Comprising means for performing the method according to any one of claims 1 to 9.

Images