Video Content Creation Method and Device Based on New Media Data Analysis

Abstract

The present application discloses a video content creation method and device based on new media data analysis. The server-side method includes: receiving a video content creation request sent by a client, where the video content creation request carries content keywords; through a preset BI system, retrieving new media accounts related to the content keywords and the comment area content corresponding to each video published by each new media account as new media data, and retrieving e-commerce platform data corresponding to products related to the content keywords; generating user preference information and market trend information corresponding to the content keywords based on the new media data and the e-commerce platform data; generating a target video based on the user preference information and the market trend information, and sending it to the client for playback. Therefore, by adopting the embodiments of the present application, the limitations of traditional manual creation and single automatic editing technologies are overcome, thereby realizing the automation, personalization, and high-quality output of video content creation.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular, to a video content creation method and device based on new media data analysis. Background Art

[0002] In the new media era, short video platforms have become the main channels for the public to obtain information and entertainment. Enterprises and individual creators are faced with the challenge of attracting audiences, increasing brand exposure, and user engagement through video content. Therefore, efficiently and accurately creating video content that meets the preferences of the target audience has become a key task in the field of new media marketing.

[0003] In related technologies, the creation of video content mainly relies on manual editing and the creativity of creators. This process usually involves market research and the collection of audience feedback to determine the theme and style of the video. In addition, existing automatic editing technologies can perform some single functions, such as adding special effects. The process of manually creating video content is time-consuming and laborious. The automatic editing technologies have single functions and cannot comprehensively analyze user preferences, which limits the ability to create high-quality video content. Summary of the Invention

[0004] Embodiments of this application provide a video content creation method and device based on new media data analysis. To provide a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. This summary part is not a general review, nor is it intended to identify key / important constituent elements or delineate the protection scope of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0005] In a first aspect, embodiments of this application provide a video content creation method based on new media data analysis, which is applied to a server. The method includes:

[0006] Receiving a video content creation request sent by a client, where the video content creation request carries a content keyword;

[0007] Through a preset BI system, retrieving new media accounts related to the content keyword and the comment area content corresponding to each video published by each new media account as new media data, and retrieving e-commerce platform data corresponding to products related to the content keyword;

[0008] Generate user preference information and market trend information corresponding to content keywords based on new media data and e-commerce platform data; the user preference information is generated through a pre-trained sentiment recognition model, the vocabulary sequence and phrase sequence corresponding to the content of each comment area, and the pre-trained sentiment recognition model is obtained by training with positive sentiment data, negative sentiment data, and neutral sentiment data. The positive sentiment data, negative sentiment data, and neutral sentiment data are obtained by performing sentiment label annotation on social media comments and product evaluations covering different sentiment tendencies. The market trend information is generated based on the product sales information and product sale evaluations included in the e-commerce platform data;

[0009] Generate a target video based on the user preference information and market trend information, and send it to the client for playback.

[0010] In a second aspect, an embodiment of the present application provides a video content creation device based on new media data analysis. The device includes:

[0011] A request receiving module, configured to receive a video content creation request sent by the client, where the video content creation request carries a content keyword;

[0012] A data retrieval module, configured to retrieve, through a preset BI system, new media accounts related to the content keyword and the comment area content corresponding to each video published by each new media account as new media data, and retrieve e-commerce platform data corresponding to products related to the content keyword;

[0013] An information generation module, configured to generate user preference information and market trend information corresponding to content keywords based on new media data and e-commerce platform data; the user preference information is generated through a pre-trained sentiment recognition model, the vocabulary sequence and phrase sequence corresponding to the content of each comment area, and the pre-trained sentiment recognition model is obtained by training with positive sentiment data, negative sentiment data, and neutral sentiment data. The positive sentiment data, negative sentiment data, and neutral sentiment data are obtained by performing sentiment label annotation on social media comments and product evaluations covering different sentiment tendencies. The market trend information is generated based on the product sales information and product sale evaluations included in the e-commerce platform data;

[0014] A video generation module, configured to generate a target video based on the user preference information and market trend information, and send it to the client for playback.

[0015] The technical solution provided by the embodiment of the present application may include the following beneficial effects:

[0016] In the embodiments of the present application, on the one hand, through the preset BI system and the content keywords carried in the video content creation request, relevant new media accounts, comment area content, and e-commerce platform data can be automatically retrieved. The automatically retrieved data can provide a data basis for video creation, thus overcoming the time-consuming and laborious problems of manual video creation. On the other hand, through a pre-trained sentiment tendency recognition model, the system can comprehensively analyze user preferences. This model is trained with positive sentiment data, negative sentiment data, and neutral sentiment data, which are from social media comments and product evaluations with different sentiment tendencies. Therefore, by analyzing the sentiment tendency in user comments, the system can identify the preferences of different user groups, so as to customize personalized video content for different users. At the same time, the system combines user preferences and market trend information to generate target videos, which can not only meet user needs but also adapt to market changes, improving the attractiveness and competitiveness of the videos.

[0017] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application and used together with the specification to explain the principles of the present application.

[0019] Figure 1 is a schematic flowchart of a method for creating video content based on new media data analysis provided by an embodiment of the present application;

[0020] Figure 2 is a user interface diagram displayed on a client provided by an embodiment of the present application;

[0021] Figure 3 is an interaction schematic diagram between a server and a client provided by an embodiment of the present application;

[0022] Figure 4 is a schematic flowchart of a method for training a sentiment tendency recognition model provided by an embodiment of the present application;

[0023] Figure 5 is a schematic diagram of the model architecture of a sentiment tendency recognition model provided by an embodiment of the present application;

[0024] Figure 6 is a schematic diagram of the structure of a video content creation device based on new media data analysis provided by an embodiment of the present application;

[0025] Figure 7 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] The following description and the accompanying drawings fully disclose specific embodiments of the present application, enabling those skilled in the art to practice them.

[0027] It should be clear that the described embodiments are only a part of the embodiments of the present application, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0028] When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0029] In the description of the present application, it should be understood that terms such as "first", "second", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances. In addition, in the description of the present application, unless otherwise specified, "a plurality of" means two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0030] Currently, the creation of video content mainly relies on manual editing and the creativity of creators. This process usually involves market research and the collection of audience feedback to determine the theme and style of the video. In addition, existing automatic editing technologies can perform some single functions, such as adding special effects.

[0031] The inventors have realized that the process of manually creating video content is time-consuming and laborious. The automatic editing technology has a single function and cannot comprehensively analyze user preferences, which limits the ability to create high-quality video content.

[0032] To solve the above problems, the present application provides a video content creation method and device based on new media data analysis to solve the problems existing in the above related technical problems. In an embodiment of the present application, on the one hand, through a preset BI system and content keywords carried in the video content creation request, relevant new media accounts, comment area content, and e-commerce platform data can be automatically retrieved. The automatically retrieved data can provide a data basis for video creation, thus overcoming the problem of time-consuming and laborious manual video creation. On the other hand, through a pre-trained sentiment tendency recognition model, the system can comprehensively analyze user preferences. This model is trained with positive sentiment data, negative sentiment data, and neutral sentiment data, which come from social media comments and product evaluations with different sentiment tendencies. Therefore, by analyzing the sentiment tendency in user comments, the system can identify the preferences of different user groups, so as to customize personalized video content for different users. At the same time, the system combines user preferences and market trend information to generate target videos. These videos can not only meet user needs but also adapt to market changes, improving the attractiveness and competitiveness of the videos. The following uses exemplary embodiments for detailed description.

[0033] The following will combine the attached Figure 1 - attached Figure 5 drawings to introduce in detail the video content creation method based on new media data analysis provided by the embodiments of the present application. This method can be implemented depending on a computer program and can run on a video content creation device based on the von Neumann architecture and based on new media data analysis. This computer program can be integrated in an application or run as an independent tool-like application.

[0034] Please refer to Figure 1 FIG. [X], which is a schematic flowchart of a video content creation method based on new media data analysis provided by an embodiment of the present application and is applied to a server. As Figure 1 shown, the method of the embodiment of the present application may include the following steps:

[0035] S101, receive a video content creation request sent by a client, where the video content creation request carries content keywords;

[0036] Among them, the client refers to the device or software used by the user, such as a mobile application, a web browser, or a professional video editing software. The user interacts with the server through these devices or software. The video content creation request refers to a request sent by the client to the server, asking the server to help create video content. The content keywords refer to the words related to the video content, which are used to describe the theme, style, or other important features of the video.

[0037] In some embodiments of the present application, a user uses a video creation application on a mobile phone and inputs the theme or keywords of the video they want to create. For example, keywords such as "healthy diet", "exercise", "natural food", etc. are input, and these keywords will be used to guide the creation of video content. The application encapsulates the keywords into a video content creation request and sends it to the server. Among them, the user interface for the user to input keywords is, for example Figure 2 as shown.

[0038] S102, through a preset BI system, retrieve new media accounts related to the content keywords and the content of the comment areas corresponding to each video published by each new media account as new media data, and retrieve e-commerce platform data corresponding to the products related to the content keywords;

[0039] Among them, the preset BI system is a tool for analyzing and storing new media platform data and e-commerce platform data. A new media account refers to an individual or enterprise account on a new media platform, such as Weibo, Douyin, Instagram, etc., which is used to publish content and interact with audiences. The content of the comment area refers to the comments of users under the videos published by new media accounts, and these comments reflect the feedback and emotions of the audience on the video content. E-commerce platform data refers to the data collected from e-commerce platforms, including product information, sales data, user evaluations, etc.

[0040] In some embodiments of the present application, the BI system first collects data from new media platforms and e-commerce platforms. These data include account information, video content, content of the comment area, as well as product sales information and evaluations. The collected data is stored in the database of the BI system. These databases may adopt distributed database technologies such as Hadoop, HBase or Cassandra to ensure the reliability, scalability and high performance of the data. For new media data, the BI system may extract text features such as keywords, themes or sentiment tendencies. For e-commerce platform data, the system may extract product features such as categories, prices or user evaluations.

[0041] For example, if the content keyword is "eco-friendly fashion", the BI system will calculate the similarity between this keyword and the new media accounts and video content stored in the database, as well as the similarity with the relevant products on the e-commerce platform. According to the similarity scores, the BI system retrieves the most relevant new media accounts and videos, as well as the relevant products on the e-commerce platform. The content of the comment area corresponding to each video is used as new media data, and the product features are used as e-commerce platform data.

[0042] In some embodiments of the present application, the specific process of generating data in the preset BI system is as follows: Obtain each registered new media account from the new media platform; Store each new media account and the content of the comment area corresponding to each video published by it; Obtain the product description information of each product from the e-commerce platform; Store the product description information of each product and its e-commerce platform data, and use the database storing the above content as the preset BI system.

[0043] S103. Generate user preference information and market trend information corresponding to the content keywords according to the new media data and the e-commerce platform data; The user preference information is generated through a pre-trained sentiment tendency recognition model, the vocabulary sequence and the phrase sequence corresponding to each comment area content. The pre-trained sentiment tendency recognition model is trained by positive sentiment data, negative sentiment data and neutral sentiment data. The positive sentiment data, negative sentiment data and neutral sentiment data are obtained by performing sentiment label annotation on the social media comments and product evaluations covering different sentiment tendencies collected. The market trend information is generated according to the product sales information and product sale evaluations included in the e-commerce platform data;

[0044] Among them, the new media data includes multiple comment area contents, and the e-commerce platform data includes product sales information and product sale evaluations.

[0045] In some embodiments of the present application, the specific process of generating user preference information and market trend information corresponding to the content keywords according to the new media data and the e-commerce platform data includes: Perform data cleaning and data word segmentation processing on each comment area content to obtain the vocabulary sequence and the phrase sequence corresponding to each comment area content; Generate user preference information corresponding to the content keywords according to the vocabulary sequence and the phrase sequence corresponding to each comment area content; Count the product sales volume related to the content keywords from the product sales information included in the e-commerce platform data; Analyze the change trend of the product sales volume over time in a time series; Use the time series analysis method to analyze the change trend to predict the product sales volume trend within a preset period of time in the future. The time series analysis method is the ARIMA model; Predict the user demand information for the product according to the product sale evaluations included in the e-commerce platform data; Use the change trend of the product sales volume over time and the user demand information for the product as the market trend information corresponding to the content keywords.

[0046] Among them, data cleaning refers to removing or correcting errors, duplicates, or incomplete information in the content of each comment area. Data tokenization is the process of splitting the content of each comment area into individual words or phrases. The sequence of words and the sequence of phrases refer to a series of words or phrases divided from the content of each comment area. Product sales information includes data such as the sales volume and sales amount of products, which is used to analyze the market performance of products. Time series analysis is a statistical technique used to analyze data points arranged in chronological order to identify trends, seasonality, and periodicity. The ARIMA (AutoRegressive Integrated Moving Average) model is a statistical model used for time series forecasting. Product sale evaluation refers to the evaluation of the purchased products by users, and these evaluations can provide additional information about product satisfaction and demand.

[0047] In the embodiments of the present application, user preference information is extracted from the content of the comment area of the new media platform, and at the same time, the product sales trend is statistically analyzed and predicted from the product sales information of the e-commerce platform. Combining the time series analysis of the ARIMA model, the system can accurately predict the product sales trend in a future period of time. In addition, by analyzing the product sale evaluation, the system can predict the demand information of users for products. These comprehensive information provide in-depth market trend insights for the content keywords, enabling video content creators to produce video content that better meets the market demand and user preferences, thereby improving the attractiveness and market competitiveness of the video.

[0048] In some embodiments of the present application, the specific process of generating user preference information corresponding to content keywords according to the sequence of words and the sequence of phrases corresponding to the content of each comment area includes: inputting the sequence of words and the sequence of phrases corresponding to the content of each comment area into a pre-trained sentiment tendency recognition model, and outputting multiple sentiment words corresponding to the content of each comment area and the intensity of each sentiment word; calculating the sentiment intensity value of the content of each comment area according to the intensity of each sentiment word and the number of sentiment words; performing topic analysis on the sequence of words and the sequence of phrases corresponding to the content of each comment area, and extracting the tendency topics involved in the content of each comment area; identifying the user preferences for different topics according to the sentiment intensity value of the content of each comment area and the tendency topics involved in the content of each comment area, as the user preference information corresponding to the content keywords.

[0049] Among them, the sentiment tendency recognition model is a machine learning model used to analyze text data and identify the sentiment tendency expressed therein, such as positive, negative, or neutral. Sentiment words refer to words with emotional colors, and the intensity represents the emotional degree or strength of these sentiment words.

[0050] For example, the content in the comment area is input into the sentiment tendency recognition model. The model outputs the sentiment words in each comment, such as "satisfied" and "disappointed", and their respective intensities. For each comment, according to the intensity and quantity of the sentiment words, a sentiment intensity value is calculated. For example, the positive sentiment intensity is 0.8 and the negative sentiment intensity is 0.2. Thematic analysis is performed on the vocabulary sequence and phrase sequence of the comment to extract the tendency themes, such as "sustainable development" and "product effect". Combining the sentiment intensity value and the tendency theme, it is identified that the user has a relatively strong positive preference for the "sustainable development" theme, while there are more negative feedbacks on the "product effect". These analysis results are integrated to form user preference information about the "environmental protection product" video, which can be used to guide the creation and optimization of video content to better meet the needs and expectations of users.

[0051] S104, Generate a target video based on the user preference information and market trend information, and send it to the client for playback.

[0052] In some embodiments of the present application, the specific process of generating a target video based on the user preference information and market trend information includes: extracting target audience characteristics related to the content keyword from the user preference information, where the target audience characteristics include age characteristics, gender characteristics, and interest characteristics; extracting product characteristics related to the content keyword from the market trend information, where the product characteristics include product name, feature information, and advantage information; integrating the target audience characteristics and the product characteristics into a semantically coherent descriptive text to obtain a text prompt for prompting a preset large language model, and the text prompt is used to guide the preset large language model to generate a product introduction text corresponding to the content keyword; inputting the text prompt into the preset large language model to output the product introduction text; the preset large language model is ChatGPT; retrieving video materials matching the content keyword from the preset video material library, where the video materials include pictures, special effects, and music; using video editing software to integrate the pictures, special effects, music, and the product introduction text to obtain the target video.

[0053] Among them, the target audience characteristics refer to the specific attributes of the target audience, such as age, gender, and interest. The product characteristics refer to the specific attributes of the product, such as name, feature, and advantage, which help to distinguish the product and attract potential consumers. The semantically coherent descriptive text refers to the text that is semantically related and logically clear. ChatGPT is a large language model developed by OpenAI that can conduct conversations and generate text. The video material library is a database storing the materials required for video production, including pictures, special effects, and music. The target video is video content customized according to specific target audiences and market trends.

[0054] For example, extract target audience characteristics from user preference information, such as "young adults", "health-conscious", and "interested in technology products". Extract product characteristics from market trend information, such as "fitness tracker", "real-time heart rate monitoring", and "long battery life". Integrate the target audience characteristics with the product characteristics into a descriptive text, such as "Introduce a fitness tracker with real-time heart rate monitoring and long battery life to young and health-conscious technology enthusiasts". Use the descriptive text as a text prompt to guide ChatGPT to generate product introduction text. Input the text prompt into ChatGPT to output the product introduction text. Retrieve pictures, special effects, and music that match "fitness tracker" from the video material library. Use video editing software to integrate the retrieved pictures, special effects, music, and product introduction text to produce the target video. Finally, obtain an introduction video for a fitness tracker targeted at young and health-conscious technology enthusiasts, which combines attractive visual materials and appealing product introduction text generated by ChatGPT.

[0055] For example Figure 3 As shown, the server 110 can be a server, which can specifically be an independent server or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, Content Delivery Network (CDN), and big data and artificial intelligence platforms. For example, it can be a server device running a preset BI system. When video content creation based on new media data analysis is required, the server 110 receives a video content creation request sent by the client 120, and the video content creation request carries a content keyword. The server 110 retrieves, through the preset BI system, new media accounts related to the content keyword and the comment area content corresponding to each video published by each new media account as new media data, and retrieves e-commerce platform data corresponding to products related to the content keyword. The server 110 generates user preference information and market trend information corresponding to the content keyword based on the new media data and the e-commerce platform data. The server 110 generates a target video based on the user preference information and the market trend information and sends it to the client 120 for playback.

[0056] It should be noted that the client 120 can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The server 110 and the client 120 can be connected through Bluetooth, USB (Universal Serial Bus), or other communication connection methods, and the present invention does not make any restrictions here.

[0057] In the embodiments of the present application, on the one hand, through the preset BI system and the content keywords carried in the video content creation request, relevant new media accounts, comment area content, and e-commerce platform data can be automatically retrieved. The automatically retrieved data can provide a data basis for video creation, thus overcoming the time-consuming and laborious problems of manual video creation. On the other hand, through a pre-trained sentiment tendency recognition model, the system can comprehensively analyze user preferences. This model is trained with positive sentiment data, negative sentiment data, and neutral sentiment data, which come from social media comments and product evaluations with different sentiment tendencies. Therefore, by analyzing the sentiment tendency in user comments, the system can identify the preferences of different user groups, so as to customize personalized video content for different users. At the same time, the system combines user preferences and market trend information to generate target videos. These videos can not only meet user needs but also adapt to market changes, improving the attractiveness and competitiveness of the videos.

[0058] Please refer to Figure 4 , which provides a schematic flowchart of a method for training a sentiment tendency recognition model according to an embodiment of the present application. As Figure 4 shown, the method of the embodiment of the present application may include the following steps:

[0059] S201, collect social media comments and product evaluations covering different fields and sentiment tendencies to obtain text data;

[0060] Among them, comments or feedbacks made by users on specific content (such as posts, videos, pictures, etc.) on social media platforms. Feedbacks provided by consumers on purchased products or services on e-commerce platforms or review websites, usually including ratings and text comments. Sentiment tendency is the emotional direction expressed in the text, usually divided into positive, negative, and neutral.

[0061] In some embodiments of the present application, comments and evaluations are obtained from multiple social media platforms and e-commerce platforms. Data from different fields can be collected, including but not limited to technology products, health foods, fashion clothing, and online education services.

[0062] S202, perform sentiment annotation on the collected text data to divide the text data into positive sentiment data, negative sentiment data, and neutral sentiment data; positive sentiment data is data marked to represent users' optimistic emotions, negative sentiment data is data marked to represent users' negative emotions, and neutral sentiment data is data marked to represent users' lack of emotions;

[0063] In some embodiments, identify and mark the sentiment tendency of each comment. Positive sentiment may be represented by "1", negative sentiment by "-1", and neutral sentiment by "0" to obtain positive sentiment data, negative sentiment data, and neutral sentiment data.

[0064] S203, create a sentiment recognition model;

[0065] For example Figure 5 As shown, the sentiment recognition model includes a word embedding network, a sequence embedding layer, a position embedding layer, a self-attention layer, a feature fusion module, and a loss function.

[0066] S204, input positive sentiment data, negative sentiment data, and neutral sentiment data into the sentiment recognition model, and output the loss value of the model;

[0067] In some embodiments of the present application, the specific process of inputting positive sentiment data, negative sentiment data, and neutral sentiment data into the sentiment recognition model and outputting the loss value of the model includes: cleaning and text tokenization of the positive sentiment data, negative sentiment data, and neutral sentiment data to obtain tokenized text data; inputting the tokenized text data into the word embedding network to capture the semantic relationship and context information between words for word conversion, and obtaining word vectors in the text sequence; inputting the word vectors in the text sequence into the sequence embedding layer to capture the sequential information and context relationship in the text sequence, and obtaining sequence vectors; obtaining the position information of the tokenized text data, and inputting the obtained position information of the text data into the position embedding layer to capture the position information of the words in the text, and obtaining position vectors; inputting the sequence vectors and position vectors into the self-attention layer to capture the mutual relationship between different words, and obtaining global features; inputting the word vectors, sequence vectors, position vectors, and global features into the feature fusion module to integrate feature information at different levels, and obtaining a comprehensive feature vector; according to the comprehensive feature vector and the loss function, outputting the loss value of the model.

[0068] Specifically, the specific process of outputting the loss value of the model according to the comprehensive feature vector and the loss function includes: performing a linear transformation on the comprehensive feature vector to obtain a score vector for each sentiment category; where the calculation formula for the score vector is:

[0069] where is the score vector, is the weight matrix, is the comprehensive feature vector, is the bias vector; converting the score vector for each sentiment category into a probability distribution to obtain the predicted sentiment category probability distribution; where the calculation formula for the probability distribution is:

[0070]

[0071] where is the probability distribution of the th sentiment category, is the The score vector of each emotion category, is the total number of emotion categories, is the sum of the score vectors of all emotion categories; the predicted emotion category probability distribution and the labeled emotion label corresponding to the predicted emotion category probability distribution are input into the loss function to output the loss value of the model.

[0072] Specifically, the loss function is:

[0073]

[0074] Among them, is the forward propagation result of the emotion tendency recognition model at time step , is the model update parameter, the optimization objective is to maximize the loss value of the parameter set , is the predicted emotion category probability distribution, is the labeled emotion label corresponding to the predicted emotion category probability distribution, is the probability distribution of all predicted emotion categories, represents the quantization value of the labeled emotion label , is the logarithmic probability, is the original parameter of the model, is the model parameter after update, is the time step label.

[0075] S205, when the loss value reaches the minimum, generate a pre-trained emotion tendency recognition model; or, when the loss value does not reach the minimum, forward propagate the model loss value to update the model update parameter of the emotion tendency recognition model, and continue to execute the step of inputting positive emotion data, negative emotion data, and neutral emotion data into the emotion tendency recognition model until the loss value reaches the minimum.

[0076] In the embodiments of the present application, on the one hand, through the preset BI system and the content keywords carried in the video content creation request, relevant new media accounts, comment area content, and e-commerce platform data can be automatically retrieved. The automatically retrieved data can provide a data basis for video creation, thus overcoming the problem of time-consuming and laborious manual video creation. On the other hand, through a pre-trained sentiment tendency recognition model, the system can comprehensively analyze user preferences. This model is trained with positive sentiment data, negative sentiment data, and neutral sentiment data, which come from social media comments and product evaluations with different sentiment tendencies. Therefore, by analyzing the sentiment tendency in user comments, the system can identify the preferences of different user groups, so as to customize personalized video content for different users. At the same time, the system combines user preferences and market trend information to generate target videos. These videos can not only meet user needs but also adapt to market changes, improving the attractiveness and competitiveness of the videos.

[0077] The following is an embodiment of the device of the present application, which can be used to execute the method embodiment of the present application. For the details not disclosed in the embodiment of the device of the present application, please refer to the method embodiment of the present application.

[0078] Please refer to Figure 6 , which shows a schematic structural diagram of a video content creation device based on new media data analysis provided by an exemplary embodiment of the present application. The video content creation device based on new media data analysis can be implemented as all or part of an electronic device through software, hardware, or a combination of both. The device 1 includes a request receiving module 10, a data retrieval module 20, an information generation module 30, and a video generation module 40.

[0079] The request receiving module 10 is configured to receive a video content creation request sent by a client, and the video content creation request carries content keywords;

[0080] The data retrieval module 20 is configured to retrieve, through the preset BI system, new media accounts related to the content keywords and the comment area content corresponding to each video published by each new media account as new media data, and retrieve e-commerce platform data corresponding to products related to the content keywords;

[0081] An information generation module 30, configured to generate user preference information and market trend information corresponding to content keywords according to new media data and e-commerce platform data; the user preference information is generated by a pre-trained sentiment recognition model, a vocabulary sequence and a phrase sequence corresponding to the content of each comment area, and the pre-trained sentiment recognition model is trained by positive sentiment data, negative sentiment data and neutral sentiment data, and the positive sentiment data, negative sentiment data and neutral sentiment data are obtained by performing sentiment label annotation on social media comments and product evaluations covering different sentiment tendencies collected, and the market trend information is generated according to the product sales information and product sale evaluations included in the e-commerce platform data;

[0082] A video generation module 40, configured to generate a target video based on the user preference information and the market trend information, and send it to a client for playing.

[0083] It should be noted that when the video content creation device based on new media data analysis provided in the above embodiments executes the video content creation method based on new media data analysis, only the above-mentioned division of each functional module is used for illustration. In practical applications, the above functions can be assigned to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the video content creation device based on new media data analysis provided in the above embodiments and the embodiments of the video content creation method based on new media data analysis belong to the same concept, and the implementation process thereof is detailed in the method embodiments, which will not be elaborated here.

[0084] The serial numbers of the embodiments of the present application above are only for description and do not represent the advantages and disadvantages of the embodiments.

[0085] In the embodiments of the present application, on the one hand, through the preset BI system and the content keywords carried in the video content creation request, relevant new media accounts, comment area content, and e-commerce platform data can be automatically retrieved, and the automatically retrieved data can provide a data basis for video creation, thus overcoming the problem of time-consuming and laborious manual video creation. On the other hand, through the pre-trained sentiment recognition model, the system can comprehensively analyze user preferences. This model is trained by positive sentiment data, negative sentiment data and neutral sentiment data, and these data come from social media comments and product evaluations with different sentiment tendencies. Therefore, by analyzing the sentiment tendency in user comments, the system can identify the preferences of different user groups, so as to customize personalized video content for different users. At the same time, the system combines user preferences and market trend information to generate target videos, which can not only meet user needs, but also adapt to market changes, improving the attractiveness and competitiveness of the videos.

[0086] The present application also provides a computer-readable medium, on which program instructions are stored. When the program instructions are executed by a processor, the video content creation method based on new media data analysis provided by each of the above method embodiments is implemented.

[0087] The present application also provides a computer program product containing instructions. When it runs on a computer, it enables the computer to execute the video content creation method based on new media data analysis of each of the above method embodiments.

[0088] Please refer to Figure 7 , which is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 7 shown, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0089] Among them, the communication bus 1002 is used to realize the connection and communication between these components.

[0090] Among them, the user interface 1003 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 1003 may further include a standard wired interface and a wireless interface.

[0091] Among them, the network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0092] Among them, the processor 1001 may include one or more processing cores. The processor 1001 connects various parts within the entire electronic device 1000 through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling the data stored in the memory 1005, it performs various functions of the electronic device 1000 and processes data. Optionally, the processor 1001 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 1001 may integrate one or a combination of several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 1001 and may be implemented separately by a single chip.

[0093] Among them, the memory 1005 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 1005 includes a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 1005 may also be at least one storage system located far from the aforementioned processor 1001. As Figure 7 shown, the memory 1005, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a video content creation application program based on new media data analysis.

[0094] In Figure 7In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an interface for the user to input and obtain the data input by the user; while the processor 1001 can be used to call the video content creation application program stored in the memory 1005 based on new media data analysis, and specifically perform the following operations:

[0095] Receive a video content creation request sent by the client, and the video content creation request carries a content keyword;

[0096] Through a preset BI system, retrieve new media accounts related to the content keyword and the comment area content corresponding to each video published by each new media account as new media data, and retrieve e-commerce platform data corresponding to products related to the content keyword;

[0097] Generate user preference information and market trend information corresponding to the content keyword according to the new media data and e-commerce platform data; the user preference information is generated through a pre-trained sentiment tendency recognition model, the vocabulary sequence and phrase sequence corresponding to each comment area content, the pre-trained sentiment tendency recognition model is trained through positive sentiment data, negative sentiment data and neutral sentiment data, and the positive sentiment data, negative sentiment data and neutral sentiment data are obtained by performing sentiment label annotation on social media comments and product evaluations covering different sentiment tendencies, and the market trend information is generated according to the product sales information and product sale evaluations included in the e-commerce platform data;

[0098] Generate a target video based on the user preference information and market trend information, and send it to the client for playback.

[0099] In one embodiment, when the processor 1001 executes to generate user preference information and market trend information corresponding to the content keyword according to the new media data and e-commerce platform data, it specifically performs the following operations:

[0100] Perform data cleaning and data word segmentation processing on each comment area content to obtain the vocabulary sequence and phrase sequence corresponding to each comment area content;

[0101] Generate user preference information corresponding to the content keyword according to the vocabulary sequence and phrase sequence corresponding to each comment area content;

[0102] Count the product sales volume related to the content keyword from the product sales information included in the e-commerce platform data;

[0103] Analyze the change trend of the product sales volume over time according to the time series;

[0104] Adopt a time series analysis method to analyze the change trend to predict the product sales volume trend within a preset period of time in the future, and the time series analysis method is the ARIMA model;

[0105] Predict the demand information of users for products based on the product sale evaluations included in the e-commerce platform data;

[0106] Use the changing trend of product sales over time and the demand information of users for products as the market trend information corresponding to the content keywords.

[0107] In one embodiment, when the processor 1001 executes to generate the user preference information corresponding to the content keywords according to the vocabulary sequence and phrase sequence corresponding to the content of each comment area, the following operations are specifically performed:

[0108] Input the vocabulary sequence and phrase sequence corresponding to the content of each comment area into a pre-trained sentiment tendency recognition model, and output multiple sentiment words corresponding to the content of each comment area and the intensity of each sentiment word;

[0109] Calculate the sentiment intensity value of the content of each comment area according to the intensity of each sentiment word and the number of sentiment words;

[0110] Perform topic analysis on the vocabulary sequence and phrase sequence corresponding to the content of each comment area, and extract the tendency topics involved in the content of each comment area;

[0111] Identify the preferences of users for different topics according to the sentiment intensity value of the content of each comment area and the tendency topics involved in the content of each comment area, as the user preference information corresponding to the content keywords.

[0112] In one embodiment, when the processor 1001 executes to generate a pre-trained sentiment tendency recognition model, the following operations are specifically performed:

[0113] Collect social media comments and product evaluations covering different fields and sentiment tendencies to obtain text data;

[0114] Perform sentiment annotation on the collected text data to classify the text data into positive sentiment data, negative sentiment data, and neutral sentiment data; positive sentiment data is the data annotated to represent the optimistic mood of users, negative sentiment data is the data annotated to represent the negative mood of users, and neutral sentiment data is the data annotated to represent the absence of mood of users;

[0115] Create a sentiment tendency recognition model;

[0116] Input the positive sentiment data, negative sentiment data, and neutral sentiment data into the sentiment tendency recognition model, and output the loss value of the model;

[0117] When the loss value reaches the minimum, a pre-trained sentiment recognition model is generated; or, when the loss value does not reach the minimum, the model loss value is propagated forward to update the model update parameters of the sentiment recognition model, and the steps of inputting positive sentiment data, negative sentiment data, and neutral sentiment data into the sentiment recognition model are continued until the loss value reaches the minimum.

[0118] In one embodiment, when the processor 1001 outputs the loss value of the model by inputting positive sentiment data, negative sentiment data, and neutral sentiment data into the sentiment recognition model, the following operations are specifically performed:

[0119] Perform data cleaning and text tokenization on the positive sentiment data, negative sentiment data, and neutral sentiment data to obtain the tokenized text data;

[0120] Input the tokenized text data into a word embedding network to capture the semantic relationships and context information between words for vocabulary transformation, and obtain word vectors in the text sequence;

[0121] Input the word vectors in the text sequence into a sequence embedding layer to capture the sequential information and context relationships in the text sequence, and obtain sequence vectors;

[0122] Obtain the position information of the tokenized text data, and input the obtained position information of the text data into a position embedding layer to capture the position information of the words in the text, and obtain position vectors;

[0123] Input the sequence vectors and position vectors into a self-attention layer to capture the mutual relationships between different words, and obtain global features;

[0124] Input the word vectors, sequence vectors, position vectors, and global features into a feature fusion module to integrate feature information at different levels, and obtain comprehensive feature vectors;

[0125] Output the loss value of the model according to the comprehensive feature vectors and the loss function.

[0126] In one embodiment, when the processor 1001 generates a target video based on user preference information and market trend information, the following operations are specifically performed:

[0127] Extract target audience characteristics related to content keywords from the user preference information, where the target audience characteristics include age characteristics, gender characteristics, and interest characteristics;

[0128] Extract product characteristics related to content keywords from the market trend information, where the product characteristics include product names, feature information, and advantage information;

[0129] Integrate the target audience characteristics and product characteristics into semantically coherent descriptive text to obtain a text prompt for prompting a preset large language model, and the text prompt is used to guide the preset large language model to generate product introduction text corresponding to the content keywords;

[0130] Input the text prompt into the preset large language model to output the product introduction text;

[0131] Retrieve video materials matching the content keywords from the preset video material library, and the video materials include pictures, special effects, and music;

[0132] Use video editing software to integrate the pictures, special effects, music, and product introduction text to obtain the target video.

[0133] In the embodiments of the present application, on the one hand, through the content keywords carried by the preset BI system and the video content creation request, relevant new media accounts, comment area content, and e-commerce platform data can be automatically retrieved, and the automatically retrieved data can provide a data basis for video creation, thus overcoming the time-consuming and laborious problems of manual video creation. On the other hand, through the pre-trained sentiment tendency recognition model, the system can comprehensively analyze user preferences. This model is trained with positive sentiment data, negative sentiment data, and neutral sentiment data, which come from social media comments and product evaluations with different sentiment tendencies. Therefore, by analyzing the sentiment tendency in user comments, the system can identify the preferences of different user groups, so as to customize personalized video content for different users. At the same time, the system combines user preferences and market trend information to generate target videos, which can not only meet user needs but also adapt to market changes, improving the attractiveness and competitiveness of the videos.

[0134] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program for video content creation based on new media data analysis can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium of the program for video content creation based on new media data analysis can be a magnetic disk, an optical disk, a read-only memory, or a random access memory, etc.

[0135] The above-disclosed are only the preferred embodiments of the present application. Of course, the scope of the rights of the present application cannot be limited thereby. Therefore, equivalent changes made according to the claims of the present application still fall within the scope covered by the present application.

Claims

1. A video content creation method based on new media data analysis, characterized in that: Applied to the server, the method includes: Receive a video content creation request sent by a client, wherein the video content creation request carries a content keyword; Through the preset BI system, new media accounts related to the content keywords and the content of the comment area corresponding to each video published by each new media account are retrieved as new media data, and e-commerce platform data corresponding to the products related to the content keywords are retrieved; Generate user preference information and market trend information corresponding to the content keywords based on the new media data and the e-commerce platform data; the user preference information is generated by a pre-trained sentiment tendency recognition model, a vocabulary sequence and a phrase sequence corresponding to the content of each comment area, the pre-trained sentiment tendency recognition model is obtained by training positive sentiment data, negative sentiment data and neutral sentiment data, the positive sentiment data, negative sentiment data and neutral sentiment data are obtained by collecting social media comments and product reviews covering different sentiment tendencies and annotating them with sentiment tags, and the market trend information is generated based on product sales information and product sales evaluations contained in the e-commerce platform data; Based on the user preference information and market trend information, a target video is generated and sent to the client for playback; including: extracting target audience features related to content keywords from the user preference information, extracting product features related to content keywords from the market trend information, integrating the target audience features and product features into semantically coherent description text to obtain text prompts, inputting the text prompts into a preset large language model, and outputting product introduction text; retrieving video materials matching the content keywords from a preset video material library, using video editing software to integrate pictures, special effects, music and product introduction text to obtain the target video.

2. The method according to claim 1, characterized in that The new media data includes the contents of multiple comment areas, and the e-commerce platform data includes product sales information and product sales evaluations; The generating of user preference information and market trend information corresponding to the content keywords according to the new media data and the e-commerce platform data includes: Performing data cleaning and data segmentation processing on the content of each comment area to obtain a vocabulary sequence and a phrase sequence corresponding to the content of each comment area; Generating user preference information corresponding to the content keywords according to the vocabulary sequence and phrase sequence corresponding to the content of each comment area; Counting the sales volume of products related to the content keywords from the product sales information included in the e-commerce platform data; Analyze the sales trend of the product over time by time series; A time series analysis method is used to analyze the change trend to predict the product sales trend within a preset period of time in the future. The time series analysis method is an ARIMA model. Predicting user demand information for products based on product sales reviews contained in the e-commerce platform data; The change trend of the product sales volume over time and the user's demand information for the product are used as the market trend information corresponding to the content keyword.

3. The method according to claim 2, characterized in that Generating user preference information corresponding to the content keywords according to the vocabulary sequence and phrase sequence corresponding to the content of each comment area includes: Inputting the vocabulary sequence and phrase sequence corresponding to each comment area content into a pre-trained sentiment tendency recognition model, and outputting a plurality of sentiment words corresponding to each comment area content and the strength of each sentiment word; Calculate the sentiment intensity value of each comment area content according to the intensity of each sentiment word and the number of sentiment words; Performing topic analysis on the word sequence and phrase sequence corresponding to the content of each comment area, and extracting the tendency theme involved in the content of each comment area; According to the sentiment intensity value of the content in each comment area and the tendency topics involved in the content in each comment area, the user's preference for different topics is identified as the user preference information corresponding to the content keyword.

4. The method according to claim 3, characterized in that Follow these steps to generate a pre-trained sentiment recognition model, including: Collect social media comments and product reviews covering different fields and sentiment tendencies to obtain text data; Performing sentiment annotation on the collected text data to divide the text data into positive sentiment data, negative sentiment data and neutral sentiment data; the positive sentiment data is data annotated to represent the user's optimistic sentiment, the negative sentiment data is data annotated to represent the user's negative sentiment, and the neutral sentiment data is data annotated to represent the user's lack of sentiment; Create a sentiment tendency recognition model; Inputting the positive emotion data, negative emotion data and neutral emotion data into the emotion tendency recognition model, and outputting the loss value of the model; When the loss value reaches the minimum, a pre-trained emotion tendency recognition model is generated; or, when the loss value does not reach the minimum, the model loss value is forward propagated to update the model update parameters of the emotion tendency recognition model, and the step of inputting the positive emotion data, negative emotion data and neutral emotion data into the emotion tendency recognition model is continued until the loss value reaches the minimum.

5. The method according to claim 4, characterized in that The sentiment tendency recognition model includes a word embedding network, a sequence embedding layer, a position embedding layer, a self-attention layer, a feature fusion module and a loss function; The step of inputting the positive emotion data, the negative emotion data and the neutral emotion data into the emotion tendency recognition model and outputting the loss value of the model comprises: Performing data cleaning and text segmentation on the positive sentiment data, the negative sentiment data, and the neutral sentiment data to obtain text data after segmentation; Inputting the segmented text data into the word embedding network to capture the semantic relationship and context information between words for word conversion, and obtaining word vectors in the text sequence; Inputting the word vectors in the text sequence into the sequence embedding layer to capture the order information and contextual relationship in the text sequence to obtain a sequence vector; Acquire the position information of the text data after word segmentation, and input the acquired position information of the text data into the position embedding layer to capture the position information of the vocabulary in the text and obtain the position vector; Inputting the sequence vector and the position vector into the self-attention layer to capture the relationship between different words and obtain a global feature; Inputting the word vector, sequence vector, position vector and global feature into the feature fusion module to integrate feature information at different levels to obtain a comprehensive feature vector; According to the comprehensive feature vector and the loss function, the loss value of the model is output.

6. The method according to claim 5, characterized in that Outputting the loss value of the model according to the comprehensive feature vector and the loss function includes: Performing a linear transformation on the comprehensive feature vector to obtain a score vector for each emotion category; Convert the score vector of each emotion category into a probability distribution to obtain a predicted emotion category probability distribution; The predicted emotion category probability distribution and the annotated emotion label corresponding to the predicted emotion category probability distribution are input into the loss function, and the loss value of the model is output.

7. The method according to claim 1, characterized in that The target audience characteristics include age characteristics, gender characteristics and interest characteristics; The product features include product name, feature information, and advantage information; The video material includes pictures, special effects, and music.

8. The method according to claim 1, characterized in that Before receiving the video content creation request sent by the client, the method further includes: Get each registered new media account from the new media platform; Store the comment area content corresponding to each new media account and each video it publishes; Get product description information of each product from the e-commerce platform; Storing product description information and e-commerce platform data of each product; The database storing the above contents is used as the preset BI system.

9. A video content creation device based on new media data analysis, characterized in that: The device comprises: A request receiving module, used to receive a video content creation request sent by a client, wherein the video content creation request carries a content keyword; A data retrieval module is used to retrieve new media accounts related to the content keywords and the comment area content corresponding to each video published by each new media account as new media data through a preset BI system, and to retrieve e-commerce platform data corresponding to products related to the content keywords; An information generation module is used to generate user preference information and market trend information corresponding to the content keywords based on the new media data and the e-commerce platform data; the user preference information is generated by a pre-trained sentiment tendency recognition model, a vocabulary sequence and a phrase sequence corresponding to the content of each comment area, the pre-trained sentiment tendency recognition model is obtained by training positive sentiment data, negative sentiment data and neutral sentiment data, the positive sentiment data, negative sentiment data and neutral sentiment data are obtained by collecting social media comments and product reviews covering different sentiment tendencies and annotating them with sentiment tags, and the market trend information is generated based on product sales information and product sales evaluations contained in the e-commerce platform data; The video generation module is used to generate a target video based on the user preference information and market trend information, and send it to the client for playback; including: extracting target audience characteristics related to content keywords from the user preference information, extracting product characteristics related to content keywords from the market trend information, integrating the target audience characteristics and product characteristics into a semantically coherent description text to obtain a text prompt, inputting the text prompt into a preset large language model, and outputting a product introduction text; retrieving video materials matching the content keywords from a preset video material library, and using video editing software to integrate pictures, special effects, music and product introduction text to obtain a target video.

Images