A method for generating dynamic video cover

Abstract

The present application provides a method for generating a dynamic video cover, including: obtaining static materials related to the main body of the video; classifying the obtained static materials related to the main body of the video into corresponding static material categories according to the nature of the content; arranging and combining the static materials according to a predetermined strategy and based on the obtained static material categories; the predetermined strategy at least includes using different arrangement and combination orders for different target customer objects; forming the arranged and combined static materials into a whole to generate the dynamic video cover. The present application generates a dynamic video cover through static materials according to a predetermined strategy, which can effectively reduce the production cost of high-quality dynamic video covers, and realize personalized cover display in response to different consumer needs, thereby increasing user click-through rate and page views.

Description

Technical Field

[0001] The present application relates to the field of computers, and in particular to a method, device, electronic device and storage medium for generating a dynamic video cover. Background Art

[0002] With the rapid development of Internet technology, e-commerce application platforms play an increasingly important role in people's daily lives. The display of goods in e-commerce application platforms has also become more and more diverse. The display of goods has a crucial impact on consumers' click-through rate, purchase rate, conversion rate, user stickiness, etc. Therefore, it is increasingly meaningful to explore the way of displaying goods on e-commerce application platforms.

[0003] In the existing technology, the commonly used e-commerce platform displays products mainly in the form of pictures and videos. Among them, in the product search interface and recommendation interface, displaying products in the form of pictures cannot allow consumers to intuitively feel the quality of the products. Using automatically played audio and video dynamic video covers is more visually intuitive for consumers, which can effectively improve consumers' awareness of products in the shortest time, promote consumers to make purchasing decisions, and greatly increase the click-through rate and purchase conversion rate of products. Therefore, more and more stores have begun to use dynamic short video covers to replace the original picture covers for product display and introduction, and realize the dynamic and three-dimensional display of products through the automatic playback of dynamic short videos.

[0004] In the actual application of dynamic short videos, the dynamic video covers of e-commerce platforms are usually mostly shot and uploaded by merchants themselves. Therefore, the coverage rate of high-quality dynamic short videos on e-commerce platforms is low. In addition, due to the high cost of shooting high-quality short videos and the mismatch between the key points of the product content displayed by merchants in the video and the key points of user needs, how to generate high-quality dynamic video covers at a low cost and improve the personalized display of dynamic video covers in response to different consumer needs has become an urgent problem to be solved by e-commerce application platforms. Summary of the invention

[0005] The present invention provides a method for generating a dynamic video cover, which solves the technical problems that the existing dynamic video cover generation cost is high and the dynamic video cover cannot be displayed in a targeted manner in response to different consumer needs. The present invention also provides a device, electronic device and storage medium for generating a dynamic video cover. The technical solution is as follows:

[0006] The present application embodiment provides a method for generating a dynamic video cover, including:

[0007] Get static footage related to the main body of the video;

[0008] Classify the acquired static materials related to the video subject into corresponding static material categories according to the nature of the content;

[0009] According to a predetermined strategy, the static materials are arranged and combined according to the categories of the acquired static materials; the predetermined strategy at least includes adopting different arrangement and combination orders for different target customer objects;

[0010] The arranged and combined static materials are formed into a whole to generate the dynamic video cover.

[0011] Optionally, according to different predetermined strategies, the acquired static materials related to the video body can generate multiple versions of dynamic video covers; for the same predetermined strategy, due to different selections of the static materials, multiple different versions of dynamic video covers can also be generated.

[0012] Optionally, the step of forming a whole from the arranged and combined static materials to generate the dynamic video cover includes:

[0013] Before generating the dynamic video cover, the expression method of the static material related to the video body is deformed.

[0014] Optionally, the deforming the expression method of the static material related to the video subject includes: beautifying the acquired static material by selecting a template using a design style.

[0015] Optionally, the number of dynamic video covers is at least a first number, and the method further includes:

[0016] Obtain the first number of dynamic video covers;

[0017] For the first number of dynamic video covers, a number of sample customers are selected from the target customer group to perform a first estimation test;

[0018] According to the test feedback data and predetermined evaluation criteria, a target dynamic video cover matching the target group is obtained.

[0019] Optionally, after determining the target dynamic video cover, further perform the following steps:

[0020] Obtain the target dynamic video cover;

[0021] Adjusting the target dynamic video cover to obtain a plurality of fine-tuned target dynamic video covers;

[0022] For the multiple fine-tuned target dynamic video covers, a number of sample customers are selected from the target customer group to perform a second estimation test;

[0023] Based on the test feedback data, a fine-tuned dynamic video cover matching the target group is obtained.

[0024] Optionally, the target customer group is a customer group with target attributes obtained after classifying customer groups.

[0025] Optionally, the classifying of customer groups includes: classifying customers with the same demand characteristic labels into the same type of customer group.

[0026] Optionally, the target attribute is an attribute labeled according to a customer's demand feature label.

[0027] Optionally, the number of dynamic video covers is a second number greater than the first number, and the method further includes: for a customer group with specific target attributes, before conducting a first estimation test, according to the specific target attributes, in a predetermined manner, selecting the first number of dynamic video covers for testing from a second number of multiple dynamic video covers greater than the first number.

[0028] The dynamic video cover generation method provided by the present application obtains static materials related to the video body, and classifies the obtained static materials related to the video body into corresponding static material categories according to the nature of the content; arranges and combines the static materials according to the predetermined strategy and the acquired static material categories; the predetermined strategy at least includes adopting different arrangement and combination orders for different target customer objects; the arranged and combined static materials are formed into a whole to generate the dynamic video cover. The method for generating a dynamic video cover uses existing static materials as the source of video production. The same static material group can generate multiple versions of dynamic video covers for different target customer groups according to different predetermined strategies. The technical solution can greatly reduce the cost of producing dynamic video covers, and by generating dynamic video covers according to predetermined strategies, it can meet the needs of different target customer groups and generate dynamic video covers that are suitable for them in a targeted manner, thereby achieving the effect of improving the click-through rate and page views of users.

[0029] In addition, the present application also provides a device, an electronic device and a computer-readable storage medium for a dynamic video cover generation method, which also have the above-mentioned beneficial effects.

[0030] It should be understood that the contents described in this section are not intended to represent the key or important features of the present application, nor are they intended to limit the scope of the present application. The features of the present application will be easily understood through the following specific implementations of typical examples. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments of the present application will be briefly introduced below. 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 paying any creative labor.

[0032] Figure 1 A schematic diagram of an application scenario of a method for generating a dynamic video cover provided in an embodiment of the present application;

[0033] Figure 2 A schematic diagram of a flow chart of a method for generating a dynamic video cover provided in an embodiment of the present application;

[0034] Figure 3 A flowchart of a method for generating a target dynamic video cover provided in an embodiment of the present application;

[0035] Figure 4 A flowchart of a method for generating a fine-tuned dynamic video cover that matches a target group provided in an embodiment of the present application;

[0036] Figure 5 A schematic diagram of the structure of a device for generating a dynamic video cover provided in one embodiment of the present application;

[0037] Figure 6 A schematic diagram of the structure of an electronic device provided in one embodiment of the present application;

[0038] Figure 7 A schematic diagram of the structure of a storage medium provided in one embodiment of the present application;

[0039] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, many specific details are described in the following description to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific implementation disclosed below.

[0041] It should be noted that the terms "first", "second", and "third" in the various parts and drawings of the embodiments of the present application are used to distinguish similar objects, and do not indicate any specific order or precedence between them. Such data can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0042] The terms "including" and "having" and any variations thereof in this application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to these processes, methods, products or apparatuses.

[0043] In this application, unless otherwise expressly stated, the term "or" includes all possible combinations, except those that are not feasible. For example, if it is expressed that a database may include A or B, then unless otherwise specifically specified or not feasible, it may include database A, or B, or A and B. As another example, if it is expressed that a database may include A, B, or C, then unless otherwise specifically specified or not feasible, the database may include database A, or B, or C, or A and B, or A and C, or B and C, or A, B, and C.

[0044] First, some technical terms involved in this application are explained:

[0045] AB testing is to create two (A / B) or multiple (A / B / n) versions for a Web or App interface or process, and let visitor groups (target groups) with the same (similar) composition randomly access these versions in the same time dimension, collect user experience data and business data from each group, and finally analyze and evaluate the best version and formally adopt it. Its role is to eliminate disputes over different opinions in customer experience (UX) design, determine the best solution based on actual results; find the real cause of the problem through comparative tests, improve product design and operation levels; establish a data-driven, continuously optimized closed-loop process; and reduce the risk of releasing new products or new features through A / B testing, providing guarantees for product innovation.

[0046] CTR (Click-Through-Rate) estimation is one of the core algorithms in computational advertising. It predicts the click of each advertisement and predicts whether the user will click or not. Its estimation is related to many factors, such as historical click-through rate, advertisement position, time, user, etc. The CTR estimation model is a model trained on a large amount of historical data by comprehensively considering various factors and features. Therefore, the CTR estimation model can be widely used in personalized recommendation, information retrieval, online advertising and other fields to learn and predict user feedback, among which user feedback mainly includes clicks, collections, purchases, etc.

[0047] In the era of massive information data, recommendation algorithms can screen and filter massive information and present the information that users are most concerned about and interested in to users. This not only increases work efficiency, but also saves users time in screening information. By connecting users and information, on the one hand, it helps users find valuable information for themselves, and on the other hand, it allows information to be displayed to people who are interested in them, thus achieving a win-win situation for information providers and users. Recommendation algorithms can be roughly divided into three categories: content-based recommendation algorithms, collaborative filtering recommendation algorithms, and knowledge-based recommendation algorithms.

[0048] In the following, the application scenarios of the solutions provided in this application are first illustrated.

[0049] Figure 1 Schematic diagram of an application scenario for a method for generating a dynamic video cover provided in an embodiment of the present application. Figure 1 As shown, in this application scenario, a client 101 and a server 102 are included, and the number of the client 101 is not limited. The client 101 obtains static materials related to the video body, and sends the user's static materials to the server 102. The server 102 generates a dynamic video cover according to the static materials according to a predetermined strategy, and sends the dynamic video cover to the client 101. The client 101 displays the dynamic video cover to the consumer for browsing and purchasing. The specific implementation process can refer to the solutions of the following embodiments.

[0050] It should be noted that Figure 1 This is only a schematic diagram of an application scenario of a method for generating a dynamic video cover provided in an embodiment of the present application. Figure 1 does not limit the equipment included in Figure 1 The positional relationship between the devices in the Figure 1In the application scenario shown, a data storage device may also be included. The data storage device may be an external memory relative to the client 101 or the server 102, or an internal memory integrated in the client 101 or the server 102. The client 101 may be a smart phone, a computer, a television, a wearable device, a multimedia player, an e-reader, or other devices, on which various types of shopping application software are installed; the server 102 may be a server or a centralized authority composed of several servers, or a cloud computing service center. The client 101 and the server 102 may be connected via wireless network communication, wired communication, or optical fiber cable communication.

[0051] It is understandable that according to actual needs, the above Figure 1 The number of devices in the client 101 and server 102 may vary.

[0052] Next, a method for generating a dynamic video cover is introduced through a specific embodiment.

[0053] The first embodiment of the present application provides a method for generating a dynamic video cover.

[0054] Figure 2 The flowchart of the method for generating a dynamic video cover provided in an embodiment of the present application can be used as follows: Figure 1 The implementation environment shown. Figure 2 As shown, the method of the embodiment of the present application includes the following steps:

[0055] S201, obtaining static material related to the video subject.

[0056] This step collects relevant basic information for the implementation of this embodiment, namely, static materials related to the video theme, for generating a dynamic video cover.

[0057] The video subject refers to the target object to be displayed in the form of a video, including people, objects, events, etc.; in the case of using videos for product promotion, it mainly refers to various commodities. In this embodiment, the scene is limited to the above commodity promotion occasions. The above commodities are used for display and sale on the corresponding e-commerce application platform. Static materials are materials used to display the characteristics or information of commodities.

[0058] For example, the video subject can be a mobile phone, a book, a vehicle, bread, an apple, or other main commodities for sale on an e-commerce platform, wherein the e-commerce platform is a common shopping application platform in daily life, and this application does not limit the specific form. Taking a mobile phone as an example, the above static material can be a text information introduction of the beauty function of the product mobile phone, or a picture of the appearance of the product mobile phone, or a sales data report of the product mobile phone for three consecutive quarters, and other materials related to the product mobile phone.

[0059] The above-mentioned static materials obtained are derived from existing materials of the product, including but not limited to product information, product pictures, product videos, product audio and other forms. Among them, product information can be text and charts in the product introduction, or materials selected from a special material management library for users, or text content extracted from pictures through text recognition; pictures of products can be actual pictures of real objects, virtual images constructed by application software, or portrait pictures in hand-drawn form; videos of products can also come from short video materials related to network applications, or short video materials actually recorded by users; audio of products can be actual recorded audio, or materials in an existing audio material library.

[0060] Exemplarily, the materials obtained in this step are: the text information of the beauty function of the product mobile phone "xxx model mobile phone beauty camera, help you return to the age of 18", the appearance picture of the product mobile phone, the real shot vlog short video (video weblog) of the product mobile phone, and the seller's audio commentary static material about the product mobile phone, and the sales data report of the product mobile phone for three consecutive quarters.

[0061] S202, classifying the acquired static materials related to the video subject into corresponding static material categories according to the nature of the content;

[0062] This step is used to classify the static materials collected in the previous step.

[0063] Before generating the dynamic video cover, the expression method of the static material related to the video body is deformed.

[0064] In this step, in order to enhance the user performance of the above-mentioned dynamic video cover, after obtaining multiple relevant static materials of the video body, it is necessary to deform the expression method of the above-mentioned static materials to obtain the deformed static materials, and then produce the dynamic video cover for the deformed static materials according to the predetermined strategy.

[0065] Specifically, in this step, the expression method of the static material related to the video theme is mainly deformed, and the static material obtained above is beautified by selecting and using a design style template. The above design style includes but is not limited to the deformation of product information, the font, size, color, animation, etc. of product text information; the cutout, processing, animation, special effects enhancement, etc. of product pictures; the transition, playback material, playback area adjustment, etc. of product videos; the trimming, noise reduction, reverberation, speed change, and pitch change processing of product audio. The above static materials related to various senses such as vision and hearing will be beautified and adjusted through the design style template to enhance the consumer's intuitive experience. In addition, using existing static materials as the production material of dynamic video covers can reduce the cost of video production to a certain extent.

[0066] For example, the above-obtained static materials of the beauty function text information of the product mobile phone "xxx model mobile phone beauty camera, help you return to 18 years old", the appearance picture of the product mobile phone, the real shot vlog short video (video weblog, video network log) of the product mobile phone, and the audio commentary static material of the seller about the product mobile phone, and the sales data report of the product mobile phone for three consecutive quarters are deformed. The expression method of material 1 is deformed: the beauty function text information of the product mobile phone "xxx model mobile phone beauty camera" is deformed into the deformed beauty function text information with Songti font, 20 font size, gradient color, and jumping to the right in the picture at a jumping rate of 0.2 seconds / frame. The expression method of material 2 is deformed: the appearance of the product mobile phone is defogged, contrast enhanced, and losslessly enlarged to deform the image; the expression method of material 3 is deformed: the real-life vlog short video (videoweblog, video network log) of the product mobile phone is deformed by editing, splicing, adding filters, and adding background music; the expression method of material 4 is deformed: the static material of the seller's audio commentary on the product mobile phone is deformed through amplification, filter, and equalizer processing; the expression method of material 5 is deformed: the sales data report of the product mobile phone for three consecutive quarters is deformed into a sales data report in the form of a three-dimensional bar chart. The deformation processing of the above expression methods increases the customer's overall sensory perception of the mobile phone, and uses existing materials for deformation, which has low production costs and lowers the threshold for high-quality short video production.

[0067] In the embodiments of the present disclosure, there may be a category of static material that is all possible categories classified according to the content of the static material. This category is used to express the selling point characteristics or selling point features of the product. The above possible categories include, but are not limited to: product price, product function, sales volume, cost performance, quality, brand, after-sales service, concept, process / origin advantages, configuration, core consumer groups, packaging advantages, added value, creativity, copyright, delivery services and many other categories, which are not specifically limited in the embodiments of this application.

[0068] Exemplarily, according to the examples in the above steps, the categories of commodity mobile phones can be: mobile phone appearance, mobile phone brand, mobile phone functions, mobile phone sales, mobile phone cost-effectiveness, mobile phone after-sales service, mobile phone price, mobile phone configuration, mobile phone copyright and many other categories.

[0069] Exemplarily, according to the example in the above step S201, this step classifies the 'beautification function text information of the product mobile phone "xxx model mobile phone beauty camera" obtained in step S201, the appearance picture of the product mobile phone, the real shot vlog short video (videoweblog, video network log) of the product mobile phone, and the seller's audio commentary static material about the product mobile phone, and the sales data report of the product mobile phone for three consecutive quarters' into the corresponding category according to their content information after deformation and beautification. For example, according to the content information, the above-obtained product mobile phone beauty function text information "xxx model mobile phone beauty camera" material is classified into the product function category, the appearance picture material of the product mobile phone is classified into the appearance design category, the real shot vlog short video (videoweblog, video network log) material of the product mobile phone is classified into the corresponding cost-effectiveness category, the seller's commentary audio static material is classified into the corresponding after-sales service category, and the sales data report material of the product mobile phone for three consecutive quarters is classified into the sales category.

[0070] S203, arranging and combining the static materials according to the categories of the acquired static materials in accordance with a predetermined strategy; the predetermined strategy at least includes adopting different arrangement and combination sequences for different target customer objects.

[0071] This step is the core step of this embodiment, which is used to generate a dynamic video cover using the static materials collected in the previous step.

[0072] The predetermined strategy is a specific way of arranging and combining the static materials according to the categories of the static materials that may exist.

[0073] The above-mentioned predetermined strategy is a specific way to select and arrange the static materials according to the categories of the available static materials. Specifically, the predetermined strategy refers to the way in which the materials of the above-mentioned many categories are selected and arranged. For example, the predetermined strategy A is: commodity price-core consumer group-sales volume; the selected static materials include: commodity price, core consumer group information, and sales volume information, and the specific arrangement method is: according to the arrangement method of "commodity price-core consumer group-sales volume".

[0074] Similarly, there may be a predetermined strategy B: product introduction - process / origin advantages - distribution service; predetermined strategy C: after-sales service - cost performance - product function; predetermined strategy D: product price - product function; predetermined strategy E: cost performance - brand; in short, a variety of strategies can be formulated according to the situation. Of course, a certain type of element can appear multiple times, and there can be more specific selection strategies for the specific elements selected in each type of element. The expression form of the above-mentioned strategies is only a simplified expression. There can be more detailed material selection and material arrangement and combination methods, and the specific description of these methods can also be used as part of the strategy. In this embodiment, only the above-mentioned simplified strategy description method is adopted.

[0075] Exemplarily, according to the examples in the above steps, the predetermined strategies for the mobile phone product are: predetermined strategy A: mobile phone sales volume - mobile phone functions - mobile phone appearance; predetermined strategy B: mobile phone brand - mobile phone price - mobile phone after-sales service; predetermined strategy C: mobile phone after-sales service - mobile phone appearance - mobile phone cost performance, and many other possible strategies.

[0076] The above-mentioned predetermined strategy not only refers to the arrangement order itself, but also includes adopting different arrangement and combination orders for different target customer objects. The different target customer objects refer to target customer groups with different attributes; since target customer groups with different attributes are concerned about different main information, different arrangement and combination orders can be adopted to highlight the information they are mainly concerned about. The specific method of selecting the arrangement and combination order for target customer objects with different attributes can be carried out by AB testing, which will be introduced in detail later.

[0077] In this step, in order to combine the above-mentioned deformed static materials, according to the predetermined strategy, the deformed static materials are matched to the predetermined strategy according to their own categories to form a corresponding static material group. Different predetermined strategies have significantly different corresponding static material groups. The same predetermined strategy has different static material groups generated due to different static materials used.

[0078] Exemplarily, according to the examples in the above steps, the combination is performed: first, the predetermined strategy A of the above mobile phone product is randomly selected: mobile phone sales-mobile phone function-mobile phone appearance, and the predetermined strategy C: mobile phone after-sales service-mobile phone appearance-mobile phone cost performance. Secondly, the example in the above S202-1, 'the text information of the beauty function of the product mobile phone "xxx model mobile phone beauty camera, help you return to 18 years old", the appearance picture of the product mobile phone, the real shot vlog short video (videoweblog, video network log) of the product mobile phone, and the seller's audio commentary static material about the product mobile phone, the sales data report of the product mobile phone for three consecutive quarters' materials, are combined according to the predetermined strategy A and the predetermined strategy C to form a static material group. Finally, the corresponding static material group A is formed as follows: the sales data report of the product mobile phone for three consecutive quarters - the text information of the beauty function of the product mobile phone "xxx model mobile phone beauty camera, help you return to the age of 18" - the appearance picture of the product mobile phone; the corresponding static material group C is formed as follows: the seller's audio commentary static material about the product mobile phone - the appearance picture of the product mobile phone - the actual vlog short video (video weblog) of the product mobile phone.

[0079] S204, forming a whole by arranging and combining the static materials to generate the dynamic video cover.

[0080] The dynamic video cover contains multiple shots, each of which can be used independently or in combination to express the selling features and characteristics of the product. The static material group formed by the combination is matched, transformed, and edited by the video production generation unit to form a whole as the dynamic video cover. Of course, it is not ruled out that various general video generation tools are used to generate dynamic videos. Due to the use of different permutation and combination sequences for different target customer groups, multiple dynamic video covers will be generated in this step.

[0081] Exemplarily, according to the example in the above-mentioned step S203, the formed static material group A: the sales data report of the product mobile phone for three consecutive quarters - the beauty function text information of the product mobile phone "xxx model mobile phone beauty camera" - the appearance picture of the product mobile phone; and the static material group C: the seller's audio commentary static material about the product mobile phone - the appearance picture of the product mobile phone - the actual vlog short video (videoweblog, video network log) of the product mobile phone are input into the video production generation unit, and the dynamic cover A and dynamic cover C are generated accordingly. The above-mentioned dynamic cover A presents the content related to the sales volume, function and appearance of the mobile phone of the product mobile phone, and the above-mentioned dynamic cover C presents the content related to the after-sales service, appearance and cost performance of the mobile phone of the product mobile phone.

[0082] Obviously, there are multiple generation strategies for the above-mentioned dynamic video cover, so that multiple versions of dynamic video cover can be generated for the same video. Even for the same generation strategy, different specific material selections can also result in multiple fine-tuned versions. Therefore, after generating multiple dynamic video covers for the same video subject, it may be necessary to evaluate their actual effects; through evaluation, the best version is finally selected from multiple possible versions. To this end, the embodiments of the present disclosure may further include the following steps:

[0083] Please refer to Figure 3 , Figure 3 A flowchart of a method for generating a target dynamic video cover provided in an embodiment of the present application.

[0084] S301, obtaining the first number of dynamic video covers.

[0085] The number of dynamic video covers generated is at least a first number. The first number of dynamic video covers should be understood as a plurality of dynamic video covers, and this embodiment does not impose a specific number limitation.

[0086] As mentioned above, since the static materials of the video subject come from a wide range of sources, the material forms are rich and varied, and the material content is ever-changing, the number of dynamic video covers that can be formed according to the same predetermined strategy is uncertain, and the number of dynamic video covers generated according to different predetermined strategies is also uncertain. In this step, it is assumed that the first number of dynamic video covers obtained is a certain number of dynamic video covers generated according to multiple different predetermined strategies. In some other embodiments, it may also refer to a certain number of dynamic video covers generated according to the same predetermined strategy, and the relationship between these dynamic video covers is different fine-tuned versions under the same predetermined strategy.

[0087] In the initial step of generating dynamic video covers, the number of generated dynamic video covers is a second number which is greater than the first number.

[0088] Exemplarily, the predetermined strategies for the mobile phone products in the above step S202 are obtained in this step: predetermined strategy A: mobile phone sales-mobile phone function-mobile phone appearance; predetermined strategy B: mobile phone brand-mobile phone price-mobile phone after-sales service; predetermined strategy C: mobile phone after-sales service-mobile phone appearance-mobile phone cost performance, and three types of dynamic video covers generated correspondingly under the three predetermined strategies. For example, the total number of the three types of dynamic video covers generated is 300, that is, the second number is 300. In this step, the first number of dynamic video covers obtained is 15, that is, the first number is 15, wherein the predetermined strategy A obtained: mobile phone sales-mobile phone function-mobile phone appearance dynamic video covers are 5; the predetermined strategy B obtained: mobile phone brand-mobile phone price-mobile phone after-sales service dynamic video covers are 5; the predetermined strategy C obtained: mobile phone after-sales service-mobile phone appearance-mobile phone cost performance dynamic video covers are 5. There are many methods for selecting the first number of dynamic video covers from the second number of initial dynamic video covers, including: using a specially trained machine learning model, expert selection, and even random sampling. The second number of initial dynamic video covers mentioned above can also be automatically generated using a machine learning model according to a predetermined strategy.

[0089] S302: For the first number of dynamic video covers, a number of sample customers are selected from the target customer group to perform a first estimation test.

[0090] The target customer group is the customer group with target attributes after the customer groups are classified. The target attribute refers to the attribute marked according to the customer's demand feature label.

[0091] For a customer group with specific target attributes, before conducting a first estimation test, the first number of dynamic video covers for testing are selected from a second number of multiple dynamic video covers greater than the first number in a predetermined manner based on the specific target attributes.

[0092] What needs to be understood here is that the positioning of the dynamic video cover of the e-commerce application platform is to show consumers the most core characteristics of the product and the characteristics that are most attractive to customers in a relatively short period of time. Different customers pay attention to different characteristics of the same product. For example, some customers are sensitive to price, some customers have higher requirements for after-sales service, and some customers trust soft power such as brand influence and sales. Therefore, it is necessary to label and classify users with different demand characteristics for the same product.

[0093] Among them, the method of classifying customer groups is to analyze the purchasing behavior of each customer on multiple shopping application platforms, label the customer's purchasing demand characteristics, and also label the customer's concerns and demand points for pre-purchased goods, and then divide customers with the same demand characteristic labels into the same group.

[0094] For example, on a certain shopping application platform, the product is a mobile phone, and customers whose purchasing demand label is sales volume are divided into one customer group, customers whose purchasing demand label is price are divided into one customer group, customers whose purchasing demand label is product function and sales volume are divided into one customer group, and customers whose purchasing demand label is brand, price, and process / origin advantages are divided into one customer group. The above-mentioned division forms can be varied, and the classification process can refer to the relevant existing technology, which is not elaborated in this disclosure.

[0095] Here, it should be noted that the target customer group is a customer group that matches the test content of the first estimated test. A number of sample customers are selected from the target customer group to conduct the first estimated test.

[0096] The first estimated test refers to a test based on the content features of the dynamic video cover. In this step, the dynamic video cover generated according to the predetermined strategy is matched with the corresponding target customer group according to the content features of the dynamic video cover, and some sample customers are selected to perform the first estimated test on the above dynamic video cover. The form of the first estimated test is not specifically limited in this disclosure. For example, the form of the first estimated test is an AB test.

[0097] Exemplarily, according to the example in the above step S301, the first number of 150 dynamic video covers are obtained for the first estimation test. Taking the dynamic video cover of the predetermined strategy A as an example, the first estimation test is performed on the 5 dynamic video covers of the predetermined strategy A: mobile phone sales-mobile phone functions-mobile phone appearance; according to the content characteristics of the dynamic video cover, which are the three characteristics of mobile phone sales, mobile phone functions, and mobile phone appearance, the corresponding target customer group is matched as a group that pays attention to the above three characteristics, and the weight analysis of the three content characteristics of the target customer group is not performed here. For example, there are 150,000 customers in the target customer group that pays attention to the above three characteristics. At this time, 500 sample customers are randomly selected to perform the first estimation test of the dynamic video cover content. The first estimation test is carried out in an AB test manner. The above 5 dynamic video covers of mobile phone sales-mobile phone functions-mobile phone appearance are randomly displayed to the above 500 sample customers, and the customers browse and purchase the commodity mobile phones according to their personal preferences and interests. In the same way, the first estimation test is performed on the 5 dynamic video covers of the predetermined strategy B: mobile phone brand-mobile phone price-mobile phone after-sales service; the first estimation test is performed on the 5 dynamic video covers of the predetermined strategy C: mobile phone after-sales service-mobile phone appearance-mobile phone cost-effectiveness.

[0098] S303, obtaining a target dynamic video cover that matches the target group based on the test feedback data and a predetermined evaluation standard.

[0099] A comprehensive assessment is conducted based on the test data from the first estimate test feedback, such as browsing time data of sample users during the test period, purchase order data, order payment ratio data, user forwarding recommended product data, repurchase data of purchased users, and evaluation data of purchased users.

[0100] The predetermined evaluation standard is to classify the test data fed back by the above-mentioned first estimation test into grades, and to use the dynamic video cover with the highest comprehensive score as the target dynamic video cover for such user.

[0101] For example, according to the example in the above step S302, the mobile browsing and purchasing status of the above 500 sample customers is tracked through a third-party platform, and among the five predetermined dynamic video covers of strategy A, the dynamic video cover with the highest comprehensive performance score is used as the target dynamic video cover of the target customer group of mobile phone sales-mobile phone functions-mobile phone appearance. At the same time, the target dynamic video cover of the target customer group of mobile phone brand-mobile phone price-mobile phone after-sales service can be determined from the five predetermined dynamic video covers of strategy B, and the target dynamic video cover of the target customer group of mobile phone after-sales service-mobile phone appearance-mobile phone cost performance can be determined from the five predetermined dynamic video covers of strategy C.

[0102] Among them, the target dynamic video covers determined for different categories of target customer groups are different, so that each type of user can see the dynamic video covers of the products to be purchased on the shopping application platform with real-time targeting, increase the user's stickiness, click-through rate and views of the purchased products, and further enhance the user's exposure to and purchasing behavior of the products.

[0103] Optionally, after obtaining the first estimated test data, the order or weight ratio of the logical expression of the product selling points can be optimized according to a predetermined strategy by combining the CTR estimation method, the recommendation algorithm and other methods.

[0104] Optionally, after obtaining the first estimated test data, you can combine CTR estimation methods, recommendation algorithms and other methods, and then intervene in the step of generating dynamic video covers based on the static material according to a predetermined strategy, and predict in advance the predetermined strategy with better user performance. This can reduce the second number of dynamic video covers generated, and at the same time, can also significantly reduce the number of dynamic video covers that need to be tested during the first estimated test.

[0105] After determining the target dynamic video cover, the embodiment of the present disclosure further includes the following steps:

[0106] Please refer to Figure 4 , Figure 4 A flowchart of a method for generating a fine-tuned dynamic video cover that matches a target group provided in an embodiment of the present application can be used as follows: Figure 1 The implementation environment shown;

[0107] S401, obtaining the target dynamic video cover.

[0108] Obtain the target dynamic video cover that matches the target group. It should be understood here that the target customer group has preliminarily sorted and screened the content features of the dynamic video cover based on their own satisfaction and personal preferences. However, no corresponding screening has been made in terms of the expression of the content features of the target dynamic video cover. Therefore, it is necessary to further optimize and adjust the target dynamic video cover for the target group.

[0109] Exemplarily, according to the example in the above step S303, a target dynamic video cover is obtained as a target customer group of mobile phone sales-mobile phone functions-mobile phone appearance.

[0110] S402, adjusting the target dynamic video cover to obtain a plurality of fine-tuned target dynamic video covers.

[0111] Among them, the adjustment of the target dynamic video cover refers to the adjustment of the expression form of the content features of the target dynamic video cover, and the content features that the target group is concerned about are presented in different expression forms. The above-mentioned expression form fine-tuning can be understood as, for example, changing the target dynamic video to a situational drama, a commentary, a vlog diary, a talk show, a similar style, and other forms of adjustment.

[0112] Exemplarily, according to the example in the above step S401, the target dynamic video cover of the target customer group of mobile phone sales-mobile phone functions-mobile phone appearance is fine-tuned in terms of expression form. The mobile phone target dynamic video cover can be fine-tuned into: a mobile phone target dynamic video cover of a comedy sitcom type, a mobile phone target dynamic video cover of a real-life vlog diary type, a mobile phone target dynamic video cover of an expert commentary type, and a mobile phone target dynamic video cover of a talk show type evaluated by multiple users; for example, 4 mobile phone product target dynamic video covers after fine-tuning are obtained.

[0113] S403, for the multiple fine-tuned target dynamic video covers, a number of sample customers are selected from the target customer group to perform a second estimation test.

[0114] The second estimation test refers to a test conducted based on the expression form of the content characteristics of the dynamic video cover. In this step, a number of sample customers are further selected from the above-mentioned target customer group for the multiple target dynamic video covers after the above-mentioned fine-tuning of the expression form, and the target dynamic video covers after the fine-tuning of the expression form are released to conduct an estimation test on the second expression form. The second estimation test form is not specifically limited in the present disclosure. For example, the second estimation test is in the form of an AB test.

[0115] Exemplarily, according to the example in the above step S402, 300 customers among the target customers of mobile phone sales, mobile phone functions and mobile phone appearance are randomly selected as sample customers, and the 4 fine-tuned mobile phone target dynamic video covers are delivered to the sample customers to conduct the second estimated AB test.

[0116] S404: Obtain a fine-tuned dynamic video cover that matches the target group based on the test feedback data.

[0117] A comprehensive assessment is conducted based on the test data from the second pre-estimation test, such as the browsing time data of sample users during the test, purchase order data, order payment ratio data, user forwarding recommended product data, purchase data of purchased users, and evaluation data of purchased users. The fine-tuned dynamic video cover with the highest comprehensive score is matched to this type of user.

[0118] Exemplarily, according to the example in the above-mentioned step S402, the test data of four fine-tuned funny sitcom-type mobile phone target dynamic video covers, real-life vlog diary-type mobile phone target dynamic video covers, expert commentary-type mobile phone target dynamic video covers, and multi-user evaluated talk show-type mobile phone target dynamic video covers are comprehensively analyzed and compared; for example, if a fine-tuned funny sitcom-type mobile phone target dynamic video cover ranks first in comprehensive score, then the fine-tuned funny sitcom-type mobile phone dynamic video cover is used as the fine-tuned dynamic video cover for the target customer group of mobile phone sales, mobile phone functions, and mobile phone appearance, and the dynamic video cover is displayed to such target customer group.

[0119] Optionally, after obtaining the second estimated test data, you can combine CTR estimation methods, recommendation algorithms and other methods to intervene in the step of "generating a dynamic video cover based on the static material according to a predetermined strategy" to predict in advance the expression forms that users will perform better in. This can reduce the second number of dynamic video covers generated. At the same time, it can also significantly reduce the number of dynamic video covers that need to be tested during the first estimated test, further improving the efficiency of the second estimated test.

[0120] The second embodiment above provides a method for generating a dynamic video cover. Correspondingly, the third embodiment of the present application also provides an application device for the method for generating a dynamic video cover. Since the device embodiment is basically similar to the method embodiment, the description is relatively simple. For details of the relevant technical features, please refer to the corresponding description of the method embodiment provided above. The following description of the device embodiment is merely illustrative.

[0121] Please refer to Figure 5 To understand this embodiment, Figure 5 The unit block diagram of the device provided in this embodiment is as follows: Figure 5 As shown, the device provided in this embodiment includes:

[0122] The material acquisition unit 501 is configured to acquire static materials related to the video subject.

[0123] The material processing unit 502 is configured to classify the acquired static materials related to the video subject into corresponding static material categories according to the nature of the content.

[0124] The material transformation unit 503 is configured to arrange and combine the static materials according to a predetermined strategy and based on the acquired static material categories; the predetermined strategy at least includes adopting different arrangement and combination sequences for different target customer objects.

[0125] The video generation unit 504 is configured to integrate the combined static materials into a whole to generate the dynamic video cover.

[0126] Optionally, according to different predetermined strategies, the acquired static materials related to the video body can generate multiple versions of dynamic video covers; for the same predetermined strategy, due to different selections of the static materials, multiple different versions of dynamic video covers can also be generated.

[0127] Optionally, the step of forming the arranged and combined static materials into a whole to generate the dynamic video cover includes:

[0128] Before generating the dynamic video cover, the expression method of the static material related to the video body is deformed.

[0129] Optionally, the deforming the expression method of the static material related to the video subject includes: beautifying the acquired static material by selecting a template using a design style.

[0130] Optionally, the number of dynamic video covers is at least a first number, and the method further includes:

[0131] Obtain the first number of dynamic video covers;

[0132] For the first number of dynamic video covers, a number of sample customers are selected from the target customer group to perform a first estimation test;

[0133] According to the test feedback data and predetermined evaluation criteria, a target dynamic video cover matching the target group is obtained.

[0134] Optionally, after determining the target dynamic video cover, further perform the following steps:

[0135] Obtain the target dynamic video cover;

[0136] Adjusting the target dynamic video cover to obtain a plurality of fine-tuned target dynamic video covers;

[0137] For the multiple fine-tuned target dynamic video covers, a number of sample customers are selected from the target customer group to perform a second estimation test;

[0138] Based on the test feedback data, a fine-tuned dynamic video cover matching the target group is obtained.

[0139] Optionally, the target customer group is a customer group with target attributes obtained after classifying customer groups.

[0140] Optionally, the classifying of customer groups includes: classifying customers with the same demand characteristic labels into the same type of customer group.

[0141] Optionally, the target attribute is an attribute labeled according to a characteristic label of a customer's requirement.

[0142] Optionally, the number of dynamic video covers is a second number greater than the first number, and the method further includes: for a customer group with specific target attributes, before conducting a first estimation test, according to the specific target attributes, in a predetermined manner, selecting the first number of dynamic video covers for testing from a second number of multiple dynamic video covers greater than the first number.

[0143] In the above-mentioned embodiments, a method for generating a dynamic video cover and an application device of the method for generating a dynamic video cover are provided. In addition, the fourth embodiment of the present application further provides an electronic device. The embodiment of the electronic device is as follows:

[0144] Please refer to Figure 6 To understand this embodiment, Figure 6 A schematic diagram of an electronic device provided in this embodiment.

[0145] like Figure 7 As shown, the electronic device includes: a processor 601; a memory 602;

[0146] The memory 602 is used to store application programs. When the program is read and executed by the processor 601, the following operations are performed:

[0147] Get static footage related to the main body of the video.

[0148] Classify the acquired static materials related to the video subject into corresponding static material categories according to the nature of the content;

[0149] According to a predetermined strategy, the static materials are arranged and combined according to the categories of the acquired static materials; the predetermined strategy at least includes adopting different arrangement and combination orders for different target customer objects;

[0150] The combined static materials are formed into a whole to generate the dynamic video cover. Optionally, according to different predetermined strategies, the acquired static materials related to the video body can generate multiple versions of dynamic video covers; for the same predetermined strategy, due to different selections of the static materials, multiple different versions of dynamic video covers can also be generated.

[0151] Optionally, the combining the static materials into a whole to generate the dynamic video cover includes:

[0152] Before generating the dynamic video cover, the expression method of the static material related to the video body is deformed.

[0153] Optionally, the deforming the expression method of the static material related to the video subject includes: beautifying the acquired static material by selecting a template using a design style.

[0154] Optionally, the number of dynamic video covers is at least a first number, and the method further includes:

[0155] Obtain the first number of dynamic video covers;

[0156] For the first number of dynamic video covers, a number of sample customers are selected from the target customer group to perform a first estimation test;

[0157] According to the test feedback data and predetermined evaluation criteria, a target dynamic video cover matching the target group is obtained.

[0158] Optionally, after determining the target dynamic video cover, further perform the following steps:

[0159] Obtain the target dynamic video cover;

[0160] Adjusting the target dynamic video cover to obtain a plurality of fine-tuned target dynamic video covers;

[0161] For the multiple fine-tuned target dynamic video covers, a number of sample customers are selected from the target customer group to perform a second estimation test;

[0162] Based on the test feedback data, a fine-tuned dynamic video cover matching the target group is obtained.

[0163] Optionally, the target customer group is a customer group with target attributes obtained after classifying customer groups.

[0164] Optionally, the classifying of customer groups includes: classifying customers with the same demand characteristic labels into the same type of customer group.

[0165] Optionally, the target attribute is an attribute labeled according to a characteristic label of a customer's requirement.

[0166] Optionally, the number of dynamic video covers is a second number greater than the first number, and the method further includes: for a customer group with specific target attributes, before conducting a first estimation test, according to the specific target attributes, in a predetermined manner, selecting the first number of dynamic video covers for testing from a second number of multiple dynamic video covers greater than the first number.

[0167] To facilitate understanding of this embodiment, the dynamic video cover generation method provided in the embodiment disclosed in this application is generally executed by a computer device with certain computing capabilities, such as a terminal device or a server or other processing device, and the terminal device may be a user equipment (UE), a mobile device, a user terminal, a terminal, a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. In some possible implementations, the dynamic video cover generation method may be implemented by a processor calling a computer-readable instruction stored in a memory.

[0168] The fifth embodiment of the present application provides a storage medium embodiment corresponding to the above embodiment, on which one or more computer instructions are stored; these instructions are executed by a processor to implement the method described in the above second embodiment.

[0169] Figure 7 is a schematic diagram of the structure of the storage medium provided in the fourth embodiment of the present application. Figure 7 As shown, the storage medium 700 of the present application includes: a computer-readable storage medium 701 and a processor 702 .

[0170] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0171] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0172] 1. Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include non-transitory media such as modulated data signals and carrier waves.

[0173] 2. Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems or computer program products. Therefore, the present application can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0174] Finally, it should be noted that the above implementation modes are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned implementation modes, a person of ordinary skill in the art should understand that the technical solutions described in the aforementioned implementation modes can still be modified, or some or all of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the implementation modes of the present application.

Claims

1. A method for generating a dynamic video cover, characterized in that: include: Acquire static materials related to the main body of the video, wherein the main body of the video refers to various commodities, and the static materials are materials used to display the characteristics or information of the commodities; Classifying the acquired static materials related to the main body of the video into corresponding static material categories according to the nature of the content, wherein the static material categories are used to express the selling point characteristics or selling point features of the product; According to a predetermined strategy, the static materials are arranged and combined according to the categories of the acquired static materials; the predetermined strategy at least includes adopting different arrangement and combination orders for different target customer objects; The arranged and combined static materials are formed into a whole to generate the dynamic video cover; Obtain the target dynamic video cover that matches the target customer group; The target dynamic video cover is adjusted to obtain multiple fine-tuned target dynamic video covers; the adjustment refers to adjusting the expression form of the content features of the target dynamic video cover, presenting the content features that the target group is concerned about through different expression forms, and the expression form includes at least one of situation drama, commentary, vlog diary, talk show, and the same type; A fine-tuned dynamic video cover matching the target customer group is obtained.

2. The method according to claim 1, characterized in that The method also includes: according to different predetermined strategies, the acquired static materials related to the video body can generate multiple versions of dynamic video covers; for the same predetermined strategy, due to different selections of the static materials, multiple different versions of dynamic video covers can also be generated.

3. According to the method of claim 1, the step of forming a whole from the arranged and combined static materials to generate the dynamic video cover comprises: Before generating the dynamic video cover, the expression method of the static material related to the video body is deformed.

4. The method according to claim 3, characterized in that The deforming processing of the expression method of the static material related to the video body includes: beautifying the acquired static material by selecting a template using a design style.

5. The method according to claim 1, characterized in that: In the method, the number of dynamic video covers is at least a first number, and obtaining a target dynamic video cover that matches a target customer group includes: Obtain the first number of dynamic video covers; For the first number of dynamic video covers, a number of sample customers are selected from the target customer group to perform a first estimation test; Based on the test feedback data and predetermined evaluation criteria, a target dynamic video cover matching the target customer group is obtained.

6. The method according to claim 5, characterized in that The step of obtaining a fine-tuned dynamic video cover that matches the target customer group includes: For the multiple fine-tuned target dynamic video covers, a number of sample customers are selected from the target customer group to perform a second estimation test; Based on the test feedback data, a fine-tuned dynamic video cover matching the target customer group is obtained.

7. The method according to claim 1, characterized in that The target customer group is a customer group with target attributes obtained after classifying customer groups.

8. The method according to claim 7, characterized in that The classifying of customer groups includes: classifying customers with the same demand characteristic labels into the same type of customer group.

9. The method according to claim 7, characterized in that: The target attribute is an attribute marked according to the customer's demand feature label.

10. The method according to claim 5 or 6, characterized in that: The number of dynamic video covers is a second number greater than the first number, and the method further includes: for a customer group with specific target attributes, before conducting a first estimation test, according to the specific target attributes, in a predetermined method, selecting the first number of dynamic video covers for testing from a second number of dynamic video covers greater than the first number.

11. A device for generating a dynamic video cover, characterized in that: include: A material acquisition unit is configured to acquire static materials related to a video subject, wherein the video subject refers to various commodities, and the static materials are materials used to display characteristics or information of the commodities; A material processing unit is configured to classify the acquired static material related to the video subject into a corresponding static material category according to the nature of the content, wherein the static material category is used to express the selling point characteristics or selling point features of the product; The material transformation unit is configured to arrange and combine the static materials according to a predetermined strategy and the categories of the acquired static materials; the predetermined strategy at least includes adopting different arrangement and combination orders for different target customer objects; A video generation unit is configured to form a whole by arranging and combining the static materials to generate the dynamic video cover; The video generation unit is also configured to obtain a target dynamic video cover that matches the target customer group; adjust the target dynamic video cover to obtain multiple fine-tuned target dynamic video covers; the adjustment refers to adjusting the expression form of the content features of the target dynamic video cover, and presenting the content features that the target group is concerned about through different expression forms, and the expression form includes at least one of situation drama, commentary, vlog diary, talk show, and the same type; obtain a fine-tuned dynamic video cover that matches the target customer group.

12. An electronic device for generating dynamic video cover, characterized in that: include: Memory and processor; The memory is used to store program instructions; The processor is configured to call the program instructions in the memory to execute the method according to any one of claims 1 to 10.

13. A storage medium for generating a dynamic video cover, characterized in that: Used to store a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 10 is implemented.

Images