Information data processing method and device and electronic equipment

Abstract

The invention relates to the field of data processing, in particular to an information data processing method and device and electronic equipment. The method comprises the following steps: acquiring information data to be analyzed; identifying the hot topics in the information data in real time by adopting a hot topic detection model, and tracking the change trend of the hot topics in the social network dynamic graph to obtain an information analysis result of the hot topics; generating a real-time interaction strategy corresponding to the hot topic based on the information analysis result and the type of each social media platform; and executing a real-time interaction strategy through the real-time interaction model to simulate behavior characteristics of the user in each social media platform so as to obtain matched information to be published and / or a behavior operation instruction, and pushing the matched information to be published and / or the behavior operation instruction to the user to confirm whether to execute or not. According to the method, strategies can be flexibly adjusted according to different platform characteristics and dynamic information, the adaptability to complex information environments and emergencies is enhanced, intelligent information processing is achieved, the information processing flow is simplified, and the processing efficiency and quality are improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to an information data processing method, device, and electronic device. Background Art

[0002] In related technologies, the amount of data in information environments is vast and rapidly growing. Existing systems' hardware performance and software algorithms may not be able to meet the requirements for rapid processing and analysis of large amounts of data. For example, when faced with sudden information bursts, the amount of data can surge instantly. Insufficient system storage and computing power can lead to slow processing. Furthermore, existing information dissemination processes often employ standardized content and methods, failing to timely understand the feedback and evolving needs of different groups. This makes it difficult to optimize and adjust dissemination strategies based on actual results, and it fails to address the differences in information acceptance and preferences among different groups. For example, young people may prefer intuitive information formats like short videos and images, while older people may prefer detailed textual explanations. However, existing systems fail to adapt to these differences, resulting in poor information dissemination effectiveness.

[0003] Therefore, it is urgent to propose a new technical solution to solve at least one technical problem in the related technologies. Summary of the Invention

[0004] In response to the technical problems existing in the prior art, the present application provides an information data processing method, device, and electronic device to solve the technical problems of slow processing speed and poor information dissemination effect existing in the prior art.

[0005] In a first aspect, an embodiment of the present application provides an information data processing method, the method comprising:

[0006] Obtaining information data to be analyzed; the information data comes from different social media platforms;

[0007] A hot topic detection model is used to identify hot topics in the information data in real time and track the changing trends of hot topics in social network dynamic graphs to obtain information analysis results of hot topics; the information analysis results include at least: information change characteristics of hot topics on various social media platforms, information on the activities of opinion leaders, and the influence of social relationships; the hot topic detection model is obtained by combining graph neural networks and deep learning; information change characteristics include at least: information dissemination trends, public sentiment, and emotional tendencies;

[0008] Based on the information analysis results and the types of social media platforms, a real-time interaction strategy corresponding to the hot topics is generated; the real-time interaction strategy includes at least: an opinion leader interaction strategy adapted to the activity information and social relationship influence, and a topic information release strategy adapted to the characteristics of information changes;

[0009] The real-time interaction strategy is executed through a real-time interaction model to simulate the behavioral characteristics of users on various social media platforms to obtain matching information to be published and / or behavioral operation instructions, and push them to users to confirm whether to execute them, thereby achieving positive information guidance on hot topics.

[0010] In a second aspect, an embodiment of the present application provides an information data processing device, which includes at least the following units:

[0011] an acquisition unit configured to acquire information data to be analyzed; the information data comes from different social media platforms;

[0012] The identification unit is configured to use a hot topic detection model to identify hot topics in the information data in real time, and track the changing trends of hot topics in social network dynamic graphs to obtain information analysis results of the hot topics; the information analysis results include at least: information change characteristics of hot topics on various social media platforms, activity information of opinion leaders, and social relationship influence; the hot topic detection model is obtained by combining graph neural networks and deep learning; the information change characteristics include at least: information dissemination trends, public sentiment, and emotional tendencies;

[0013] A generating unit is configured to generate a real-time interaction strategy corresponding to a hot topic based on the information analysis results and the type of each social media platform; the real-time interaction strategy includes at least: an opinion leader interaction strategy adapted to the activity information and the influence of social relationships, and a topic information release strategy adapted to the characteristics of information changes;

[0014] The interaction unit is configured to execute the real-time interaction strategy through a real-time interaction model on each social media platform to achieve positive information guidance on hot topics; the real-time interaction model is used to simulate the behavioral characteristics of users on each social media platform to obtain information to be published or operational behavior instructions, and push them to the user to confirm whether to execute them.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, comprising:

[0016] At least one processor and a memory; wherein the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the information data processing method of the first aspect.

[0017] In a fourth aspect, a computer-readable storage medium is provided, which includes instructions. When the instructions are executed on a computer, the computer executes the information data processing method of the first aspect.

[0018] The present application provides an information data processing method, device, and electronic device. In this technical solution, first, information data to be analyzed is acquired. Then, a hot topic detection model is used to identify hot topics in the information data in real time, and the changing trends of hot topics in a social network dynamic graph are tracked to obtain information analysis results for the hot topics. The information analysis results include at least: information change characteristics of hot topics on various social media platforms, activity information of opinion leaders, and social relationship influence. The hot topic detection model is derived by combining graph neural networks and deep learning. Information change characteristics include at least: information dissemination trends, public sentiment, and emotional tendencies. Next, based on the information analysis results and the type of each social media platform, a real-time interaction strategy is generated for the hot topic. The real-time interaction strategy includes at least: an opinion leader interaction strategy adapted to activity information and social relationship influence, and a topic information release strategy adapted to information change characteristics. Finally, the real-time interaction model executes the real-time interaction strategy to simulate user behavior characteristics on various social media platforms to obtain matching information to be released and / or behavioral operation instructions, and pushes them to the user for confirmation, thereby achieving positive information guidance on hot topics. In summary, this solution rapidly senses and responds to information changes through distributed data collection, real-time analysis models, and automated policy generation. Leveraging multi-technical integration for in-depth analysis and targeted policy development, this solution accurately captures information and improves guidance effectiveness. It also flexibly adjusts policies based on the characteristics of different platforms and dynamic information, enhancing adaptability to complex information environments and emergencies. It achieves full automation and intelligent processing of information, streamlining the information processing process and improving both efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flowchart of an information data processing method according to an embodiment of the present application;

[0020] Figure 2 This is a structural diagram of an information data processing device according to an embodiment of the present application;

[0021] Figure 3 This is a schematic structural diagram of an electronic device according to an embodiment of the present application;

[0022] Figure 4 It is a structural diagram of a medium in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0024] To solve at least one technical problem in the related art, the embodiments of the present application provide an information data processing method, device, and electronic device.

[0025] In the technical solution of this application, information data to be analyzed is first acquired; this information data originates from various social media platforms. For example, a distributed crawler system is used to crawl data from multiple platforms and, after data cleaning and structuring, is stored in a distributed database. This distributed architecture improves data acquisition efficiency, enabling rapid acquisition of massive amounts of information data to meet real-time analysis requirements. Data cleaning and structuring provide high-quality, standardized data for subsequent analysis, reducing noise interference and analytical errors, ensuring that subsequent steps are based on reliable data. Furthermore, a hot topic detection model is employed to identify hot topics in the information data in real time and track their changing trends within social network dynamic graphs to obtain information analysis results for the hot topics. These information analysis results include at least: information change characteristics of hot topics across various social media platforms, information on opinion leader activities, and the influence of social relationships. The hot topic detection model is derived by combining graph neural networks and deep learning. Information change characteristics include at least: information dissemination trends, public sentiment, and emotional tendencies. Thus, using this hot topic detection model, which combines graph neural networks and deep learning, hot topics are identified in real time, their changes within social network dynamic graphs are tracked, and information change characteristics, opinion leader activities, and the influence of social relationships are analyzed. Graph neural networks excel at processing social network structure data and can accurately capture relationships between nodes (users, topics, content, etc.). Combined with the powerful feature extraction and pattern recognition capabilities of deep learning, they can quickly and accurately identify hot topics. By tracking dynamic social network graphs, we can comprehensively understand the dissemination paths, speed, and scope of hot topics. Analysis of the influence of opinion leaders and social relationships helps identify key nodes and forces in information guidance, providing a strong basis for subsequent strategy formulation. Next, based on the information analysis results and the type of social media platform, real-time interaction strategies are generated for hot topics. These real-time interaction strategies include at least: an opinion leader interaction strategy tailored to activity information and the influence of social relationships, and a topic information release strategy tailored to information fluctuations. Here, based on the information analysis results and the type of social media platform, a real-time interaction strategy, including both an opinion leader interaction strategy and a topic information release strategy, is generated. Consequently, strategies are formulated based on different platform characteristics (such as the social dissemination attributes of Weibo and the authoritativeness of news websites) and information fluctuations (such as dissemination trends and public sentiment), ensuring that information dissemination is more aligned with the habits and needs of platform users and improving dissemination effectiveness. Developing interactive strategies tailored to the activities and influence of opinion leaders can effectively leverage their power to guide information, enhancing its relevance and effectiveness, and avoiding the waste of resources and ineffectiveness of a one-size-fits-all approach. Finally, this strategy is implemented through a real-time interactive model, simulating user behavioral characteristics across various social media platforms to obtain matching information to be posted and / or behavioral instructions, which are then pushed to users for confirmation, thereby achieving positive information guidance on hot topics.Here, a real-time interactive model simulates user behavior, obtains information or action instructions to be published, and pushes them to the user for confirmation and execution. This model simulates real user behavior, generating information and instructions that better align with platform user behavior patterns, making information guidance more natural and easier to accept. The push confirmation mechanism empowers users with final decision-making power, ensuring the direction of guidance while increasing the flexibility and reliability of policy execution and reducing the risk of misdirection.

[0026] In summary, the embodiments of the present application utilize distributed data collection, real-time analysis models, and automated policy generation to rapidly perceive and respond to information changes. The embodiments of the present application can flexibly adjust policies based on different platform characteristics and dynamic information, enhancing adaptability to complex information environments and emergencies, achieving full automation and intelligent information processing, streamlining information processing processes, and improving processing efficiency and quality.

[0027] The technical solution of the present application and the information data processing solution provided in the embodiments of the present application can also be executed by an electronic device, which can be a server, a server cluster, or a cloud server. The electronic device can also be a terminal device such as a mobile phone, a computer, a tablet computer, a wearable device, or a dedicated device (such as a dedicated terminal device with an information data processing method system). These electronic devices can also be equipped with the chips or other hardware processing units introduced in the above embodiments. Alternatively, these electronic devices can also be installed with a service program for executing the information data processing solution.

[0028] Figure 1 A flowchart of an information data processing method provided in an embodiment of the present application is shown as follows: Figure 1 As shown, the method includes the following steps:

[0029] 101, obtaining information data to be analyzed;

[0030] 102. Using a hot topic detection model, identifying hot topics in the information data in real time, and tracking the changing trends of hot topics in a social network dynamic graph, to obtain information analysis results of the hot topics;

[0031] 103. Generate a real-time interaction strategy corresponding to the hot topic based on the information analysis results and the type of each social media platform;

[0032] 104. Execute the real-time interaction strategy through the real-time interaction model to simulate the user's behavioral characteristics on various social media platforms to obtain matching information to be published and / or behavioral operation instructions, and push them to the user to confirm whether to execute them, thereby achieving positive information guidance on hot topics.

[0033] In the embodiment of the present application, the information data comes from different social media platforms.

[0034] For example, social platforms enable rapid information dissemination, allowing users to quickly share information through short text, images, and videos, and through forwarding, information can be widely disseminated. They feature powerful topic and trending search features, reflecting social hot topics and information trends in real time, making them crucial platforms for the public to access news and participate in discussions. Short video platforms, primarily focused on short videos, offer general entertainment, encompassing a variety of lighthearted and enjoyable content, including music, dance, and humorous segments. They offer a wide variety of creative tools and special effects, making it easy for users to create creative videos. Furthermore, videos are relatively short, perfectly suited to the fast-paced lifestyles of modern people.

[0035] In an embodiment of the present application, the information analysis results include at least: information change characteristics of hot topics on various social media platforms, activity information of opinion leaders, and social relationship influence. Further optionally, the hot topic detection model is obtained by combining graph neural networks and deep learning.

[0036] The characteristics of information changes of hot topics on various social media platforms are that different social media platforms have different user groups, dissemination mechanisms and content characteristics, and the characteristics of information changes of hot topics on various platforms are also different.

[0037] Social platforms spread information quickly and widely. Their openness and immediacy allow topics to quickly gain traction, spreading like a virus. Users can quickly share information through short text, images, and videos. The forwarding function allows information to circulate rapidly among a vast user base, sparking widespread attention and discussion. After articles are published on official accounts on information platforms, they spread in a tiered manner. Based on user-focused relationships, articles first circulate within their followers' circles, sparking interaction and sharing among some users, which then spreads to other circles within their social networks. This method of dissemination results in a relatively steady rise in popularity, but with its in-depth content, it can have a lasting and profound impact on the target audience.

[0038] Short video platforms rely on algorithmic recommendation mechanisms, which can lead to explosive growth in topic popularity. Based on user browsing history, likes, and comments, the platforms accurately analyze user interests and preferences, pushing relevant content to potentially interested users. Once a topic resonates with a large number of users, it can quickly gain massive exposure, with a surge in views, likes, and comments, rapidly increasing its popularity.

[0039] On social platforms, public sentiment is expressed directly and diversely. Due to the relative freedom of expression, users often unthinkingly express their inner thoughts, leading to a flood of emotionally charged comments. Both positive and negative emotions can quickly converge, creating a powerful information wave. Emotions spread quickly and are easily contagious and amplified.

[0040] Users on knowledge-based platforms tend to be relatively rational. These users primarily seek knowledge and discuss issues. When approaching a topic, they tend to approach it from the perspectives of professional knowledge and logical analysis, presenting facts and reasoning to participate in discussions. Even when differing viewpoints clash, these discussions are often conducted within a rational framework, with fewer instances of extreme emotional expression.

[0041] Public sentiment on lifestyle-sharing platforms tends to be positive and upbeat. These platforms focus on daily life, product recommendations, and personal experiences, where users share beautiful moments and experiences with high-quality products, creating a warm and positive atmosphere. The content posted and interacted with often revolves around enjoyable things, conveying a love of life and a positive attitude.

[0042] Users on different platforms may have different sentiments towards the same hot topic. For example, when it comes to consumer topics, the sentiment in the comments section of e-commerce platforms is related to product evaluation, while on social platforms, the focus may be more on brand image and social influence.

[0043] Information on opinion leaders' activities includes the number of posts related to hot topics, their frequency, and interactions (such as likes, comments, and reposts). For example, if an opinion leader in the technology field frequently posts reviews of a new phone on Weibo and receives a high level of interaction, this indicates a high level of engagement with the hot topic.

[0044] The influence of opinion leaders' social connections can be analyzed through graph neural networks, such as their connections and positions within social networks. Highly influential opinion leaders may be connected to multiple different social groups, and their opinions can spread and influence others more widely.

[0045] Hot topic detection models treat users, topics, and content on social media platforms as nodes, and user attention and interaction relationships, as well as associations between topics and content, as edges, to construct a dynamic social network graph. Graph neural networks can learn feature representations for nodes and edges, mining the underlying structural information within social networks. For example, by analyzing node degree centrality and betweenness centrality, they can identify important user and topic nodes. As social network graphs evolve over time, graph neural networks can track these changes in real time and identify trends in hot topics. Deep learning models such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and their variants (such as LSTMs and GRUs) are used to extract features from text, images, videos, and other information. For example, CNNs can extract local features from text, while RNNs are suitable for processing sequential data and can capture contextual information within the text. Deep learning models can classify hot topics and determine their type and sentiment. They can also predict trends, such as rising or falling popularity and potential related topics.

[0046] In this way, the combination of graph neural networks and deep learning can fully leverage the advantages of both. Graph neural networks process social network structure information, while deep learning processes the content information of information data. This allows for more comprehensive and accurate identification of hot topics, tracking their changing trends, and improving the accuracy and reliability of information analysis.

[0047] Further optionally, the information change characteristics include at least: information dissemination trends, public sentiment, and emotional tendencies.

[0048] Information dissemination trends refer to the dynamic patterns and patterns exhibited by information during its dissemination process. These include aspects such as the speed, reach, and path of information dissemination, as well as its phased characteristics. For example, in certain hot events, information may spread rapidly through platforms such as social media within a short period of time, exhibiting exponential growth, and its reach may rapidly expand from a specific group to society as a whole. Over time, the popularity of information may gradually decline, exhibiting a decaying trend. By analyzing information dissemination trends, we can understand how information spreads across different groups and platforms, thereby grasping the pace and direction of information development and providing a basis for information response and guidance.

[0049] Public sentiment refers to the overall emotional state and affective response of the public to a specific event, phenomenon, or topic. Public sentiment is diverse and complex, with common emotions including anger, joy, sadness, anxiety, worry, dissatisfaction, and support. Public sentiment is often influenced by factors such as the nature and impact of the event itself, as well as the public's own interests and values. For example, in the face of a natural disaster, the public may express concern and sympathy; in response to social injustices, the public may express anger and dissatisfaction. Public sentiment can intuitively reflect the public's attitudes and feelings towards an event and plays a significant role in driving the development and evolution of information.

[0050] Emotional tendency primarily refers to the emotional color and value orientation inherent in the public's expression of their views and attitudes toward a particular thing. It is more in-depth and specific than public sentiment; it goes beyond simple emotional expression and involves the public's evaluation and judgment of things. Emotional tendencies can be categorized into three types: positive, negative, and neutral. Positive emotional tendencies manifest as recognition, support, and appreciation of things; negative emotional tendencies manifest as denial, opposition, and criticism of things; and neutral emotional tendencies indicate that the public holds an objective and rational attitude toward things, without a clear emotional bias. For example, for a newly launched product, consumers may express an emotional tendency of liking or disliking it based on their own usage experience and feelings. This emotional tendency can influence other consumers' views and purchasing decisions of the product, and can also have a significant impact on product-related information.

[0051] In the embodiment of the present application, the real-time interaction strategy includes at least: an opinion leader interaction strategy adapted to activity information and social relationship influence, and a topic information release strategy adapted to information change characteristics.

[0052] The influencer interaction strategy, centered on event attributes and influencer influence, achieves efficient allocation of information guidance resources through precise screening, tiered collaboration, and dynamic maintenance. During the screening phase, KOLs are matched based on event type and objectives. For example, for new product launches, technology review KOLs are invited to explain product technical highlights, while for beauty product promotions, mid-level KOLs in the beauty vertical are selected for precision marketing. To increase brand awareness, top KOLs are used to amplify communication. A tiered strategy is employed at the collaboration level: high-influence KOLs are deeply engaged, invited to participate in product development and co-create exclusive content; medium-influence KOLs engage their fans within their circle through topic challenges and interactive discussions; and low-influence KOLs are incentivized through coupons and traffic support to build a broad communication matrix. Furthermore, by real-time monitoring of KOL posting results, timely intervention is made in response to negative information, and KOL profiles are established to maintain long-term relationships, ensuring the sustainability of collaboration and the stability of information guidance.

[0053] The topic information release strategy dynamically adjusts the content and format of information releases based on information dissemination trends, public sentiment, and emotional tendencies. Regarding dissemination trends, during information outbreaks, high-frequency authoritative interpretations are released to seize information leadership. During diffusion periods, multi-platform collaboration is leveraged, such as generating topics on Weibo, in-depth analysis on WeChat Official Accounts, and videos on Douyin. During decay periods, achievements are reviewed to consolidate influence. Regarding public sentiment, positive sentiment is reinforced by promoting successful case studies to inspire emotional identification. Negative sentiment is addressed by releasing reassuring statements and solutions to resolve conflicts. Interactive forms such as voting and Q&A are used to stimulate participation in neutral sentiment. Regarding emotional tendencies, positive reviews are amplified through activities such as "Like and Retweet for a Prize." A FAQ page is established to provide targeted responses to negative viewpoints. Comprehensive and objective product reviews and other information are provided to neutral audiences to guide them in forming rational judgments, ultimately ensuring accurate and effective information guidance.

[0054] In 101, the information data to be analyzed is obtained. Specifically, on the one hand, data can be captured in parallel from multiple social media platforms (such as Weibo, WeChat, etc.), news websites, and various forums. During the crawling process, the crawler strategy needs to be flexibly adjusted according to the structural characteristics and anti-crawler mechanisms of different platforms. For example, a reasonable request frequency can be set, and real user behavior can be simulated to avoid being banned by the platform. At the same time, corresponding data parsing technologies are used for data formats of different platforms (such as JSON, HTML, etc.), such as using regular expressions, XPath or CSS selectors to extract the required information. In terms of data storage, the captured data can be stored in a distributed database, such as the Hadoop Distributed File System (HDFS) or a distributed key-value storage system (such as Redis), for subsequent large-scale data processing and analysis.

[0055] On the other hand, many social media platforms and news websites provide official APIs (Application Programming Interfaces). By calling these APIs, you can retrieve data in a manner specified by the platform. When using APIs to retrieve data, it's important to understand the platform's API documentation, including parameter requirements and return data formats. Also, be aware of API call frequency limits to avoid account restrictions due to excessive calls. To improve data acquisition efficiency, asynchronous programming techniques can be used to initiate multiple API requests simultaneously to reduce wait times.

[0056] Alternatively, raw data obtained from the internet often contains a large amount of noise and useless information, requiring cleaning and preprocessing. Data cleaning includes operations such as removing duplicate data and handling missing and outliers. For text data, preprocessing such as word segmentation, part-of-speech tagging, and named entity recognition is also required to facilitate subsequent semantic analysis. When processing image and video data, operations such as image recognition and video content analysis may be required to extract key information. To improve the efficiency of data cleaning and preprocessing, open source data processing tools and frameworks such as Apache Spark and Apache Flink can be used. These tools can handle large amounts of data and provide a rich set of data processing functions and algorithms.

[0057] To obtain more comprehensive information, data from different sources must be fused. This requires unified format conversion and standardization of different data types. For example, text, image, and video data must be converted into a unified feature representation for subsequent analysis and mining. During the fusion process, data consistency and conflicts must be resolved to ensure the accuracy and reliability of the fused data. To achieve multi-source data fusion, various data fusion algorithms and models can be used, such as feature-based and decision-based fusion algorithms.

[0058] Information data is time-sensitive. To stay informed of information trends, real-time data acquisition and monitoring are essential. Real-time stream processing technologies, such as Apache Flink and Apache Kafka, can be used to process and analyze real-time data. By setting real-time monitoring metrics, such as information popularity and sentiment, alerts can be issued when these metrics exceed certain thresholds. Furthermore, to ensure the accuracy and integrity of real-time data, real-time data verification and correction are required. During real-time data acquisition and monitoring, system performance and scalability must also be considered to ensure the system can handle large-scale real-time data.

[0059] Specifically, in 101, a distributed crawler system is constructed, which consists of multiple crawler nodes. These nodes can be distributed on different servers and crawl data from social media, news websites and other platforms in parallel. For social media platforms such as Weibo and WeChat, the crawler will simulate the browsing behavior of users, access the pages according to the set rules and frequency, and obtain the content, comments, likes and other information posted by users. When crawling data from news websites, the crawler will traverse each news column according to the page structure and link relationship of the website, and extract news headlines, text, release time, source and other data. In order to avoid putting too much pressure on the target platform and prevent being banned by the platform, the crawler will set a reasonable request interval and simulate the request header information of real users. For example, different User-Agents are set to disguise themselves as different browsers or devices to bypass the platform's anti-crawler mechanism.

[0060] Develop specialized data cleaning and preprocessing strategies based on the data characteristics of different platforms. For social media data, due to the relatively casual nature of user expression, there may be numerous typos, emoticons, and special characters, requiring text normalization, such as removing special characters and converting emoticons into text descriptions. Social media data may also contain duplicate content, requiring duplicate removal through duplication detection algorithms. Data from news websites may have inconsistent formats, such as date formats and author information formats, requiring format standardization. Furthermore, both social media and news website data may contain missing values. To address missing values, methods such as deletion and filling (e.g., using the mean, median, or mode) can be used depending on the specific situation. For example, if data records with missing important information cannot be completed through other means, consider deleting the record; for missing minor information, reasonable default values ​​can be used.

[0061] Then, the cleaned and pre-processed data is stored in a distributed database. Distributed databases have the advantages of high availability, scalability, and high performance, and can meet the storage and management needs of large amounts of information data. When choosing a distributed database, you can select an appropriate database type based on the characteristics of the data and the application scenario, such as a key-value storage database (such as Redis), a document database (such as MongoDB), or a relational database (such as the distributed version of MySQL). When storing data, a reasonable data table structure or data model will be designed based on the type and purpose of the data. For example, for social media data, corresponding data tables can be created for different entities such as users, posts, and comments, and appropriate indexes can be established to improve data query efficiency. For news website data, it can be stored according to dimensions such as news category and release time to facilitate subsequent analysis and retrieval.

[0062] Through the operation of the above data acquisition modules, rich information data can be obtained from multiple platforms, and these data can be effectively cleaned, preprocessed and stored, providing a high-quality data foundation for subsequent information analysis and processing.

[0063] As an optional embodiment, after obtaining the information data to be analyzed in 101, the user's task requirements for the positive information guidance process can also be obtained; based on the task requirements and the information data, a large prediction model is used to construct a guidance decision model that is adapted to the hot topics in the information data; the guidance decision model includes a behavior suggestion module and a long-term monitoring module; through the behavior suggestion module, the change trend of the task requirements and the information data is predicted to obtain monitoring behavior suggestions for hot topics; through the long-term monitoring module, the monitoring method of the task requirements, the information data and the monitoring behavior suggestions is matched to obtain a long-term monitoring strategy for hot topics; the long-term monitoring strategy is executed on each social media platform, and the changes in information data after the real-time interaction strategy is executed in each social media platform are monitored, and the information release strategy and behavior operation strategy in the real-time interaction strategy are dynamically adjusted.

[0064] Specifically, after obtaining the information data to be analyzed, further task requirements for the positive information guidance process are obtained from the user. For example, in the event of negative information about a brand's product quality, the user (brand) may propose specific task requirements such as increasing the proportion of positive product information to 60% within a week and maintaining a stable positive information ratio above 50% within a month, while also reducing the spread and influence of negative information.

[0065] Based on the acquired task requirements and information data, a large language model is then used to construct a decision-guidance model tailored to the hot topics within the information data. By learning from large amounts of text data, the large language model understands the semantic information within task requirements and information data and builds a model based on this information. For example, in the aforementioned incident involving negative brand product quality information, the large language model analyzed the hot topics surrounding product quality issues and user dissatisfaction, thereby constructing a targeted decision-guidance model. This model includes a behavioral recommendation module and a long-term monitoring module.

[0066] Next, the behavioral suggestion module conducts an in-depth analysis of the task requirements and information data, using a large language model to learn from historical data on similar information events and understand current data to predict changing trends. For example, the analysis found that over time, if effective measures are not taken, negative information may spread further, and the scope of influence will expand to more related fields and user groups. Based on this, the behavioral suggestion module generates monitoring behavior recommendations for hot topics. For example, it invites authoritative industry experts to publish objective analysis articles on product quality issues, emphasizing product improvement measures and quality improvement directions; arranges official brand customer service personnel to respond to users' negative comments on social media platforms in a timely and professional manner, explaining the causes of the problems and solutions, etc.

[0067] The long-term monitoring module then conducts a comprehensive analysis of task requirements, information data, and monitoring behavior recommendations, matching appropriate monitoring methods to develop a long-term monitoring strategy for hot topics. Different monitoring frequencies and indicators are developed for different social media platforms (such as Weibo, WeChat, and Douyin) based on their data characteristics and user behavior patterns. On Weibo, topics related to the brand's products are monitored hourly for popularity, number of comments, sentiment, and reach; on Douyin, relevant video playback volume, number of likes, comment content, and user interaction are monitored in real time. At the same time, the effectiveness of the measures proposed by the behavioral recommendation module is monitored, such as the number of expert article reads and reposts, and the impact on the sentiment of the information.

[0068] Finally, based on the long-term monitoring strategy, corresponding monitoring operations are performed on each social media platform. During the monitoring process, close attention is paid to changes in information data after the implementation of the real-time interaction strategy on each social media platform. If it is found that negative information is not effectively controlled after the implementation of the real-time interaction strategy, or even shows a trend of further deterioration, such as a continuous increase in the number of negative comments on Weibo and an increasingly negative sentiment trend, then the information release strategy and behavioral operation strategy within the real-time interaction strategy can be dynamically adjusted based on the monitored information data changes. For example, the information release strategy can be adjusted to increase the frequency and coverage of positive information, and publish more real-world examples of product quality improvements and positive user feedback; the behavioral operation strategy can be adjusted to strengthen the handling of negative comments, not only responding with explanations but also offering some compensation measures or promotions to appease user emotions and guide information development in a positive direction.

[0069] Through the above steps, starting from obtaining task requirements, to building a guidance decision model, to the operation of each module and the final strategy adjustment, a complete and intelligent positive information guidance process is formed to cope with the complex and changing information environment and achieve effective guidance and management of information.

[0070] Further optionally, in the above steps, executing the long-term monitoring strategy on each social media platform includes:

[0071] Based on the long-term monitoring strategy, a long-term information evaluation system matching hot topics is constructed; using the long-term information evaluation system, information change predictions are performed on the long-term information monitoring data collected from various social media platforms, as well as the information data changes after the real-time interaction strategy is executed, to obtain information change index data; a long-term social network dynamic graph is constructed based on the long-term information monitoring data, the information change index data, and the information data changes, and the degree centrality and betweenness centrality of the nodes in the social network dynamic graph are calculated to evaluate the social relationship influence of opinion leaders, so as to obtain dynamic information change data corresponding to the long-term social network; based on the information change index data and the dynamic information change data, a long-term information evaluation report for hot topics is generated.

[0072] Specifically, first, based on a long-term monitoring strategy and taking into account the characteristics and needs of hot topics, we utilize technologies such as natural language processing and machine learning to build a long-term information evaluation system. For example, for the hot topic "Application of Artificial Intelligence in the Medical Field," the system will focus on relevant professional terminology, industry trends, and public discussion points. By studying and analyzing large amounts of historical information data, we determine evaluation dimensions and indicators, such as the topic's popularity, sentiment, reach, and changing trends in public attention. This allows us to build a system that can accurately assess the information status of hot topics.

[0073] Furthermore, the established long-term information evaluation system is used to analyze the long-term information monitoring data collected from various social media platforms, as well as the changes in information data after implementing real-time interaction strategies. Using time series analysis and machine learning prediction algorithms, such as ARIMA models and neural networks, information data trends are modeled and predicted to generate information change indicators. These indicators may include the extent to which a topic's popularity will rise or fall over a period of time, the proportion of changes in positive or negative sentiment, and the expansion or contraction of its reach.

[0074] Next, by integrating long-term information monitoring data, information change indicator data, and information data change status, a long-term social network dynamic graph is constructed, using users, topics, and events on social media platforms as nodes, and interactive relationships between users (such as following, commenting, and forwarding) and the associations between topics as edges. For example, on the Weibo platform, using different user accounts as nodes, if user A frequently comments on and forwards user B's content related to "the application of artificial intelligence in the medical field," an edge will be established between A and B, indicating their interactive relationship on this topic.

[0075] The influence of opinion leaders' social connections is assessed by calculating the degree centrality and betweenness centrality of nodes in a dynamic graph. Degree centrality refers to the number of direct connections between a node and other nodes. Nodes with high degree centrality typically have broader social connections and are able to spread information quickly. Betweenness centrality measures the degree to which a node acts as an intermediary for the shortest path between other nodes in the network. Nodes with high betweenness centrality play a key role in information dissemination, exerting greater control over the flow and spread of information. These two metrics can be used to identify opinion leaders who have significant influence on the spread of hot topics.

[0076] Based on the assessment of the influence of opinion leaders' social relationships, combined with information monitoring data and change indicator data, we generate dynamic information change data corresponding to long-term social networks. This data can reflect the spread and evolution of information within social networks under the influence of opinion leaders. For example, a positive comment posted by an opinion leader may lead to a positive shift in the attitudes of their followers towards the topic, resulting in corresponding changes in information data.

[0077] Finally, based on information change indicator data and dynamic information change data, a long-term information evaluation report on the hot topic is generated according to a specific format and structure. The report may include an overall overview of the information, an analysis of information change trends, an assessment of the influence of opinion leaders, a forecast of future information developments, and corresponding recommendations and countermeasures. For example, a long-term information evaluation report on the hot topic "Application of Artificial Intelligence in Healthcare" would summarize the spread of the topic on social media platforms over a period of time, analyze whether information is trending in a positive or negative direction, identify key opinion leaders and their influence in guiding information, predict potential future information hotspots and trends, and provide relevant institutions or companies with advice on how to better guide information and enhance public awareness and acceptance of this technology. The report can use data visualization, such as charts and graphs, to present information data and analysis results, so that decision makers can intuitively understand the information status and development trends.

[0078] Further optionally, in the above steps, monitoring the changes in information data after the real-time interaction strategy is executed in each social media platform, and dynamically adjusting the information release strategy and behavioral operation strategy in the real-time interaction strategy, includes:

[0079] Extract information change data after the real-time interaction strategy is executed from each social media platform; determine the speed and scope of changes in information dissemination trends in each social media platform based on the information change data; and dynamically adjust the frequency and scope of information releases on hot topics based on the speed and scope of changes in information dissemination trends.

[0080] Exemplarily, on various social media platforms, data collection technologies (such as web crawlers, API calls, etc.) are used to extract data on relevant content after the implementation of real-time interaction strategies. Specifically, data such as posts, comments, likes, and reposts related to hot topics, as well as relevant user behavior information, are collected. For example, on social platforms, all blog posts with specific topic tags posted after the implementation of real-time interaction strategies are extracted, including the content of the blog posts, publishing time, publisher information, number of likes, number of comments, number of reposts, etc.; on short video platforms, data such as the number of views, number of likes, comment content, and user interactive behavior of related short videos are obtained. These data comprehensively reflect the information changes of hot topics on various platforms after the implementation of real-time interaction strategies.

[0081] Based on the extracted information change data, data analysis and mining techniques are then used to determine the speed and scope of information dissemination trends. The speed of change is determined by analyzing the growth or decline of data related to hot topics over a period of time (e.g., hourly or daily). For example, the change in discussion volume (the sum of the number of blog posts, comments, and reposts) for a related topic can be compared before and after the implementation of the real-time interaction strategy. If discussion volume increases rapidly after the strategy is implemented, it indicates that the speed of information dissemination has accelerated; conversely, it indicates that the speed of dissemination has slowed. To determine the scope of dissemination, multiple dimensions are considered, including the range of user groups involved (e.g., changes in the number of users by age, region, or occupation), the cross-platform spread of the topic (whether it has spread from one platform to others), and the relevance of related topics (whether it has triggered discussions on more related topics). For example, if a hot topic that was originally discussed only among users in the technology field gradually spreads to the general public after the strategy is implemented and sparks related discussions on multiple social media platforms, it indicates that its scope of dissemination has expanded.

[0082] Next, dynamically adjust the frequency and scope of information releases for hot topics based on the speed and scope of changes in identified information dissemination trends. When information dissemination accelerates and its reach expands, increase the frequency of information releases appropriately to maintain the topic's popularity and attention. For example, on Weibo, instead of releasing two official pieces of information per day on a hot topic, increase this to four or more, choosing more engaging content and formats (such as videos or images with detailed captions). At the same time, expand the scope of information releases, not only on existing channels and platforms, but also on other relevant platforms or channels to attract more user attention. For example, in addition to posting information, promote related short videos or livestreams on short video platforms or lifestyle sharing platforms. Conversely, when information dissemination slows and its reach shrinks, reduce the frequency of information releases to avoid user backlash caused by excessive dissemination. At the same time, optimize the content of information releases to make it more targeted and engaging to rekindle user interest. For example, filter and consolidate information, highlight key points and highlights, and release during periods of high user activity. Through such dynamic adjustments, the information release strategy in the real-time interaction strategy can be more in line with the actual changes in information, thereby improving the effect of information guidance.

[0083] Further optionally, in step 102, a hot topic detection model is used to identify hot topics in the information data in real time, and to track the changing trends of hot topics in the social network dynamic graph to obtain information analysis results of the hot topics, including:

[0084] A hot topic detection model is used to perform semantic analysis on the information data to extract event keywords, event themes and emotional tendencies in the information data; based on the extracted event keywords, event themes and emotional tendencies, user nodes, topic nodes and content nodes are constructed, and the nodes are connected to form the social network dynamic graph; event recognition is performed based on the social network dynamic graph to obtain the hot topics to be monitored; hot topics are determined based on the access popularity of event nodes, the number of associated edges and the density of related information in the social network dynamic graph; opinion leader activity analysis is performed based on user nodes in the social network dynamic graph to obtain key opinion leaders related to hot topics and their influence on them. The method comprises the following steps: collecting the corresponding activity information and the influence of social relationships; analyzing the degree centrality, betweenness centrality and PageRank value of each user node through the graph neural network (GNN) to identify the key opinion leaders; extracting the user nodes, topic nodes and content nodes related to the hot topics from the social network dynamic graph to form a local social network dynamic graph corresponding to the hot topics; selecting a topic analysis model matching the hot topics from the candidate data model library; performing adaptive topic analysis on the local social network dynamic graph using the topic analysis model to obtain the information analysis result; wherein, the topic analysis model is pre-obtained by training the historical information data of the historical hot topics matching the hot topics.

[0085] In the embodiment of the present application, a user node can be regarded as each user on the social platform. These users can be ordinary users, key opinion leaders (KOLs), event organizers, or other relevant organizations. Each user node has a unique identifier, such as user ID, username, etc., and can also contain other user attribute information, such as the number of fans, follow list, user activity, etc., to facilitate subsequent analysis of the user's influence and behavior patterns.

[0086] Topic nodes can be considered as nodes for each hot topic related to an activity identified in the information data. Topic nodes can be identified by key information about the topic, such as hashtags and subject content. Furthermore, adding attributes to topic nodes, such as the topic's popularity (calculated based on metrics such as the number of related posts and engagement) and the topic's sentiment (derived through sentiment analysis of related text), helps understand the characteristics and development trends of the topic.

[0087] Content nodes can also be used as nodes for every post, article, comment, and other content published on a social platform. A content node can be identified by its unique ID, and its attributes can include the time it was published, its length, its type (e.g., text, image, video), and the keywords it contains, allowing analysis of the impact of different content on the spread of hot topics.

[0088] Based on the three types of nodes described above, an edge between users can be established. For example, if one user follows another user, a directed edge is established between the two user nodes, from the follower to the followed. This edge represents the following relationship between users and reflects the potential path of information dissemination between users. Furthermore, if two users have interacted with each other, such as commenting, liking, or reposting, an edge can also be established between them. Edge weights can be set based on factors such as the frequency and intensity of interaction. For example, a repost might be given a higher weight than a like to reflect the different impacts of different interactions on information dissemination.

[0089] When a user posts content related to a hot topic, a directed edge is established between the user node and the corresponding topic node, with the direction pointing from the user to the topic. The weight of the edge is determined by the contribution of the user's content to the popularity of the topic. For example, if the content published has attracted a lot of discussion and forwarding, the weight of the edge will be relatively high, indicating that the user has played a significant role in the spread of the topic.

[0090] The edge between a user and content can be: When a user publishes content, a directed edge is established between the user node and the content node, pointing from the user to the content, representing the content's creator. When a user comments, likes, or forwards a piece of content, a corresponding directed edge is also established. The direction is determined by the specific behavior, such as a comment edge pointing from the user to the content, and a forwarding edge from the content to the forwarding user. This describes the interactive relationship between users and content.

[0091] For example, if a piece of content touches on a hot topic, a directed edge is established between the topic node and the content node, from the topic to the content, indicating that the content is about that topic. The edge weight can be set based on the relevance of the content to the topic. For example, if the content directly mentions the topic keyword and discusses the topic in detail, the edge weight will be higher; if the content only briefly mentions the topic, the edge weight will be lower. This edge construction allows for a clear view of the distribution and dissemination of relevant content under each hot topic.

[0092] Based on the above introduction, in 102, first, the large language model in the hot topic detection model is used to perform semantic analysis on the information data. The text data is split into individual words through word segmentation technology, the part of speech tagging determines the part of speech of each word, and the dependency syntax analysis clarifies the grammatical relationship between words, thereby extracting event keywords (such as "food additives", "exceeding standards", etc. in a certain food safety incident), event themes (such as "quality problems of a certain brand of food") and emotional tendencies (positive, negative or neutral). Based on the extracted information, user nodes (representing users participating in discussions in social networks), topic nodes (corresponding to different hot topics), and content nodes (such as published posts, articles, etc.) are constructed. Then, according to the association relationship between nodes, such as when a user publishes relevant content on a certain topic, the nodes are connected into a social network dynamic graph to intuitively display the connection between different elements in the social network.

[0093] Event identification is performed based on a constructed social network dynamic graph. Hot topics to monitor are determined by analyzing the characteristics of nodes and edges in the graph, such as node attributes (keywords, topics, etc.), edge connections, and weights. Specifically, hot topics are determined based on the visit popularity of the event node (e.g., the number of views and clicks on content related to a topic), the number of associated edges (the number of connections generated by user interactions and content dissemination related to the topic), and the density of related information in the social network dynamic graph (the richness of information contained in the topic). Topics with high visit popularity, a large number of associated edges, and high information density are more likely to become hot topics.

[0094] Opinion leader activity analysis begins with user nodes in social network dynamic graphs. By collecting user-related information, such as posted content and interaction data (likes, comments, and reposts), the graph neural network (GNN) is used to calculate each user node's degree centrality (a measure of the number of direct connections between nodes, reflecting the node's social activity), betweenness centrality (evaluating the degree to which a node acts as an intermediary for the shortest path between other nodes in the network, reflecting the node's control over information dissemination), and PageRank value (an algorithm used to rank web pages, which measures the importance of a node in a social network). Key opinion leaders are then identified. After identifying key opinion leaders, their activity related to hot topics (such as what content they have posted about hot topics and how often they post) and their social influence (the degree of influence they have on the opinions and behaviors of other users) are further analyzed.

[0095] User nodes, topic nodes, and content nodes related to hot topics are extracted from the social network dynamic graph. These nodes are then reassembled to construct a local social network dynamic graph corresponding to the hot topic, focusing on the network structure and information related to the hot topic. Next, topic analysis models matching the hot topic are selected from a library of candidate data models. These topic analysis models are pre-trained using historical information data from matching hot topics and have the ability to analyze specific types of hot topics. The selected topic analysis models are used to perform adaptive topic analysis on the local social network dynamic graph. Combining the structural information and node features in the graph, the model deeply explores the information changes of hot topics (such as information dissemination trends, public sentiment, emotional tendencies, etc.), the activities of opinion leaders, and the influence of social relationships. Ultimately, comprehensive and accurate information analysis results are obtained, providing strong support for subsequent information guidance and decision-making.

[0096] Further optionally, a hot topic detection model is used in 102 to identify hot topics in the information data in real time, and track the changing trends of hot topics in the social network dynamic graph. After obtaining the information analysis results of the hot topics, a hot topic indicator set can also be extracted from the information analysis results. In an embodiment of the present application, the hot topic indicator set includes at least: hot topic evolution records, related keywords, public sentiment analysis results, and opinion leader activity data; the public sentiment analysis results include at least: the proportion of each public sentiment category and the corresponding changing trends. Then, the hot topic indicator set is projected into the visualization space and converted into dynamic data graphs respectively, and the dynamic data graphs are bound to the visualization chart component; the dynamic data graphs include at least: hot topic evolution graph, public sentiment distribution graph, and opinion leader activity distribution graph. Finally, an information data analysis report for hot topics is generated based on the hot topic indicator set, and the information data analysis report and the visualization chart component are displayed to the user.

[0097] Specifically, after step 102, the hot topic detection model identifies hot topics in the information data in real time and tracks their changing trends in the social network dynamic graph. After obtaining the hot topic information analysis results, key information is extracted from these results to form a set of hot topic indicators. Specifically, the hot topic evolution record covers the change in topic popularity over time, clearly reflecting the entire process of a hot topic's emergence, development, and gradual decline. Associated keywords are important terms closely related to the hot topic, and these keywords can more accurately understand the core content of the hot topic. The public sentiment analysis results include the proportion of each public sentiment category (such as positive, negative, and neutral), as well as the changing trends of these proportions over time. This helps to understand the dynamic changes in public attitudes and emotional tendencies towards hot topics. Opinion leader activity data includes the number of opinion leaders' posts, interaction volume (such as the number of likes, comments, and reposts), and influence scores, reflecting the role of opinion leaders in the dissemination of hot topics and guiding information.

[0098] The extracted set of hot topic indicators is then projected into a visualization space and converted into dynamic data graphs. The evolution of hot topics is converted into a hot topic evolution graph, typically with time as the horizontal axis and topic popularity as the vertical axis. This graph displays the rise and fall of topic popularity via a line chart, allowing users to intuitively see the popularity of hot topics at different points in time and the changing trends. The public sentiment analysis results are converted into a public sentiment distribution graph, using bar charts or pie charts to display the proportion of each sentiment category. Heat maps are used to illustrate the distribution of public sentiment across regions, providing a clear overview of public sentiment. Opinion leader activity data is converted into an opinion leader activity distribution graph, comparing the number of posts and interactions of different opinion leaders via bar charts. Radar charts are then used to display the comprehensive performance of opinion leaders across various dimensions, such as influence, reach, and activity. These dynamic data graphs are then bound to a visualization chart component, enabling real-time updates of the data and charts, ensuring users have access to the latest information.

[0099] Then, based on the hot topic indicator set, an information data analysis report for the hot topic is generated. The report includes a detailed analysis of the hot topic, including its background, development process, and current status; an interpretation of public sentiment, including analysis of the reasons for changes in the proportion of sentiment categories and the impact of public sentiment on the hot topic; and an assessment of opinion leader activities, including the sources of their influence and the effectiveness of their statements and actions in guiding information. Furthermore, based on the conclusions generated by the information analysis module, the development trends of the hot topic are summarized and predicted, and corresponding information guidance strategies are proposed. Finally, the generated information data analysis report and visualization components are presented to the user. The visualization charts allow users to intuitively understand the various indicators and changes in the hot topic. The information data analysis report provides a deep understanding of the connotation and impact of the hot topic, providing strong support for user decision-making. The presentation also provides interactive features, such as online preview of the report content, confirmation of the report, and suggestion of revisions. After confirmation, the report file can be downloaded and stored in the system file library for easy access and tracing.

[0100] Further optionally, in step 103, based on the information analysis results and the types of the social media platforms, a real-time interaction strategy corresponding to the hot topics is generated, including:

[0101] A sentiment analysis model is used to identify the stance of a key opinion leader based on the activity information in the information analysis results, so as to obtain the stance type of the key opinion leader; the stance type is one of active support, neutral wait-and-see, and negative questioning; a multidimensional influence evaluation model is used to perform a multidimensional analysis based on the social relationship influence in the information analysis results, so as to obtain the leader influence level of the key opinion leader; based on the leader influence level and the stance type, an opinion leader interaction strategy corresponding to the key opinion leader is generated; a dynamic strategy adjustment frequency is set according to the event heat of the hot topic, and the leader influence level and the stance type are updated based on the dynamic strategy adjustment frequency; if the leader influence level and the stance type change, the opinion leader interaction strategy is switched through the rule engine bound to the social media platform; topic content prediction and topic construction method analysis are performed based on the characteristics of information changes to obtain the topic information release strategy; the opinion leader interaction strategy and the topic information release strategy are integrated to obtain the real-time interaction strategy.

[0102] Specifically, first, a sentiment analysis model is used to conduct an in-depth analysis of the activity information (such as the content posted by key opinion leaders and the discussions they participate in) in the information analysis results. Through techniques such as semantic understanding of text and emotional tendency judgment, the key opinion leaders' stance types on hot topics are identified. For example, if the content posted by a key opinion leader is full of affirmation, support, and positive evaluation of the hot topic, then their stance type can be determined to be active support; if their remarks are neither clearly supportive nor opposed, but more objectively stating facts or raising questions, then they are determined to be neutral and wait-and-see; if they express negative attitudes such as dissatisfaction, criticism, or questioning of the hot topic, then they are classified as passive and questioning.

[0103] Furthermore, a comprehensive, multidimensional analysis of the social influence of the information analysis results is conducted using a multi-dimensional influence assessment model. This model considers multiple factors, such as the number of followers of the KOL, follower activity (interaction volume, including likes, comments, and reposts), the breadth of connections within the social network (the number of connections with other important nodes), the scope and speed of information dissemination, and professional authority in specific fields. Through quantitative analysis and comprehensive evaluation of these dimensions, the KOL's level of influence is determined. Influence levels may be categorized as high, medium, or low, reflecting their actual ability to spread hot topics and guide information within social networks.

[0104] Develop corresponding interaction strategies for opinion leaders based on their determined influence levels and stance types. For KOLs who are actively supportive and highly influential, adopt a deep collaboration strategy, such as inviting them to participate in official events related to hot topics and jointly publishing content, further leveraging their influence to expand the reach of positive information. For KOLs who are neutral and wait-and-see and have moderate influence, provide detailed and accurate information to guide them in gaining a deeper understanding of hot topics and attempt to shift their neutral stance towards a positive one. For KOLs who are passive and questioning and have low influence, prioritize active communication and answering questions, using professional explanations and reasonable responses to alleviate their negative emotions and minimize negative impacts.

[0105] Set the frequency of dynamic strategy adjustments based on the heat of hot topics. When hot topics are hot and information changes quickly, increase the frequency of strategy adjustments, such as evaluating and adjusting every hour or half a day; when the heat is low and information is relatively stable, reduce the frequency of adjustments, such as once a day or once a week. Based on the dynamic strategy adjustment frequency, regularly update the leader influence level and position type of key opinion leaders. If changes are found in the leader influence level and position type during the update process, such as a originally neutral key opinion leader becoming an actively supportive type, or a leader with high influence declining for some reason, the corresponding opinion leader interaction strategy will be automatically switched through the rule engine bound to the social media platform to ensure the effectiveness and pertinence of the strategy.

[0106] Based on the characteristics of information changes (such as information dissemination trends, public sentiment, emotional tendencies, etc.), topic content prediction and topic construction methods are analyzed. By analyzing information dissemination trends, the possible future development direction and evolution trend of hot topics are predicted, so as to determine the appropriate topic content. For example, if it is predicted that a hot topic will develop in a certain direction, relevant topic content is prepared in advance to guide it. At the same time, according to public sentiment and emotional tendencies, appropriate topic construction methods are selected. When public sentiment is relatively positive, positive and inspiring content is released; when public sentiment is negative, soothing and problem-solving content is released. Combining these analysis results, a topic information release strategy is formulated, including the frequency of release, content format (such as text, pictures, videos, etc.), and the choice of release platform.

[0107] Finally, the generated opinion leader interaction strategy and topic information release strategy are integrated to ensure they coordinate and collaborate to form an integrated whole. For example, when interacting with key opinion leaders, the published topic content must align with the opinion leader's stance and influence to achieve optimal communication and information guidance. The resulting real-time interaction strategy can be flexibly applied across various social media platforms based on the actual situation and information changes of hot topics, effectively managing and guiding hot topics and improving the efficiency and quality of information response.

[0108] In one example, a large multinational corporation hosted a global technology innovation conference, attracting numerous international attendees, including technology companies, research institutions, industry experts, and technology enthusiasts from around the world. During the conference preparations and execution, the company adopted a multilingual avatar strategy to better communicate with international attendees and disseminate information about the conference.

[0109] The avatars are designed with a variety of styles and backgrounds to reflect diverse cultures. For example, there's a young tech entrepreneur from Asia, dressed in stylish business casual attire, projecting innovation and energy; a senior scientist from Europe, dressed in traditional formal attire, exuding a sense of professionalism and reliability; and a passionate and outgoing tech blogger from America, dressed in casual yet unique attire, creating an approachable and approachable look.

[0110] Each avatar is equipped with multiple language capabilities, covering major international languages ​​such as English, Chinese, French, Spanish, German, and Japanese. Depending on the character's setting and target audience, certain language skills are emphasized. For example, avatars targeting the European market will place greater emphasis on fluency in languages ​​like French and German; while avatars targeting the Asian market will excel in Chinese and Japanese.

[0111] During the conference's pre-launch phase, multilingual avatars posted pre-conference information on major international social media platforms (such as Twitter, Facebook, and LinkedIn). For example, they released the conference's theme, highlights, and keynote speakers in English to attract global audiences. They explained the conference's significance and potential opportunities for the local tech industries to European and Latin American audiences in French and Spanish. And they shared key events and attendee benefits with Asian audiences in Chinese and Japanese. Furthermore, the avatars also posted engaging short videos showcasing the conference preparations and venue layout, enhancing the appeal of the information.

[0112] During the conference, virtual characters will post real-time highlights of the conference, key points summaries of important speeches, and information about real-time interactive sessions. For example, when an internationally renowned scientist delivers a keynote speech, the virtual character will quickly summarize the core ideas and key data of the speech in multiple languages ​​and publish them on the corresponding platform. For interactive sessions, such as online voting and Q&A, the virtual characters will use multiple languages ​​to guide international participants to actively participate, ensuring that people from different language backgrounds can understand and participate. In addition, the virtual characters will adjust the way information is released and the content style according to the cultural characteristics of different regions. For example, on Japanese platforms, more polite and humble language will be used, and attention will be paid to detailed descriptions; on European and American platforms, more emphasis will be placed on direct and concise expressions to highlight key information.

[0113] After the conference, the language-specific avatars will present a summary and review of the conference, including its achievements, future plans, and a thank-you to the international participants. They will also share attendee feedback and comments, showcasing the conference's global impact and positive response in multiple languages. Furthermore, the avatars will guide international participants to follow the companies' subsequent activities and technological innovations, maintaining long-term connections.

[0114] By analyzing the dissemination data of information in different languages ​​(such as the number of readings, likes, comments, and reposts), the effectiveness of multilingual information dissemination can be evaluated. Languages ​​and content formats with better dissemination effects will be further optimized and promoted. For those with poor results, the reasons will be analyzed and adjustments will be made. For example, if a certain language version of information is found to have a low reading volume, it may be because the language expression is not accurate or vivid enough, or the release platform and time selection are inappropriate. Improvements will be made to these issues to improve the international dissemination of the information. Through the above methods, using multilingual virtual characters to release information can better meet the needs of international participants, ensure the effective dissemination of information on a global scale, and enhance the international influence and participation of the event.

[0115] Further optionally, in 101, after obtaining the information data to be analyzed, it also includes: constructing a real-time data stream processing pipeline, and using the real-time data stream processing pipeline to perform millisecond-level processing on the information data to extract dynamic analysis indicators corresponding to hot topics; the dynamic analysis indicators include at least: the discussion volume growth rate, sentiment value, keyword frequency, and negative sentiment concentration of hot topics within the time window; inputting the dynamic analysis indicators into the dynamic user portrait model of each social media platform to obtain the group behavior pattern corresponding to the hot topic; comparing the dynamic analysis indicators collected in real time with the dynamic threshold in the group behavior pattern to identify abnormal risk events corresponding to the hot topic; immediately launching an emergency response mechanism based on the abnormal risk event, generating and publishing soothing information that matches the group behavior pattern in each social media platform, so as to achieve auxiliary positive information guidance for hot topics.

[0116] In the above embodiment, a real-time data stream processing pipeline is constructed to process information data in milliseconds, enabling rapid capture of dynamic changes in hot topics. By extracting dynamic analysis indicators such as the discussion volume growth rate, sentiment value, keyword frequency, and negative sentiment concentration of hot topics within a time window, the development trends of hot topics can be accurately grasped. For example, sudden increases in topic popularity or shifts in public sentiment can be promptly detected, providing accurate data support for subsequent information guidance. Furthermore, dynamic analysis indicators are input into a dynamic user profiling model to obtain group behavior patterns corresponding to hot topics. This helps to gain a deeper understanding of the behavioral characteristics and preferences of different groups regarding hot topics, such as which groups are more likely to post negative comments or which groups are more sensitive to specific keywords. This makes information guidance measures more targeted and improves guidance effectiveness. Subsequently, the real-time collected dynamic analysis indicators are compared with the dynamic thresholds in the group behavior patterns to effectively identify abnormal risk events corresponding to hot topics. Once an indicator exceeds the threshold, it indicates the risk of a potential crisis or an outbreak of negative information, providing an early warning for timely response measures. Finally, by initiating emergency response mechanisms based on unusual risk events and generating and distributing reassuring information that aligns with group behavior patterns, we can promptly stabilize public sentiment during crises and guide information in a positive direction. Through targeted information release, we can enhance public understanding and trust in relevant events, reduce the spread of negative information, and maintain a positive information environment.

[0117] For example, suppose a well-known sports brand launches a new pair of sneakers, sparking widespread discussion on social media. After acquiring relevant data, a real-time data stream processing pipeline rapidly processes the data in milliseconds. Analysis reveals that the discussion volume for this hot topic has increased by 200% over the past hour (a measure of the growth rate of hot topic discussion within the time window), the sentiment value is 0.4 (assuming a sentiment value range of -1 to 1, with 0.4 indicating a slightly positive sentiment value), the keyword "new sneakers" appears 50 times per minute (a keyword frequency measure), and the negative sentiment concentration is 15% (a negative sentiment concentration measure). These dynamic analysis metrics are input into dynamic user profile models across various social media platforms. The analysis reveals that young sports enthusiasts are more concerned with product performance and design, preferring to use keywords related to sports technology in their discussions; whereas fashion enthusiasts prioritize the appearance and coordination of shoes, focusing more on the product's fashion elements. Furthermore, based on historical data and model analysis, the behavioral patterns and dynamic thresholds for different groups regarding similar hot topics are determined.

[0118] Continuing to monitor dynamic analysis indicators in real time, we discovered that two hours later, the concentration of negative sentiment suddenly spiked to 40%, exceeding the previously established dynamic threshold of 30%. Meanwhile, while the growth rate of discussion volume continued to rise, it slowed, potentially indicating a product issue leading to growing public dissatisfaction and thus identified as an abnormal risk event. Based on this abnormal risk event, the emergency response mechanism was immediately activated. The brand quickly generated and released reassuring messages that matched group behavior patterns across various social media platforms. For young sports enthusiasts, detailed product performance test reports and testimonials from professional athletes were released, highlighting the product's technological advantages. For fashion enthusiasts, stylish styling tips and trend analysis for the new sneakers were released. These targeted reassuring messages gradually stabilized public sentiment, negative sentiment began to decline, and information gradually shifted towards positivity, effectively providing additional positive information guidance on the hot topic.

[0119] In the technical solution of this application, distributed data collection, real-time analysis models and automated strategy generation are used to quickly perceive and respond to information changes. This application uses in-depth analysis and targeted strategy formulation based on the integration of multiple technologies to accurately grasp information and improve guidance efficiency. It also flexibly adjusts strategies based on the characteristics of different platforms and dynamic information, enhances the ability to adapt to complex information environments and emergencies, realizes the automation and intelligence of the entire information processing process, simplifies the information processing process, and improves processing efficiency and quality.

[0120] In another embodiment of the present application, an information data processing device is also provided. Figure 2 Said device comprises the following units:

[0121] an acquisition unit configured to acquire information data to be analyzed; the information data comes from different social media platforms;

[0122] The identification unit is configured to use a hot topic detection model to identify hot topics in the information data in real time, and track the changing trends of hot topics in social network dynamic graphs to obtain information analysis results of the hot topics; the information analysis results include at least: information change characteristics of hot topics on various social media platforms, activity information of opinion leaders, and social relationship influence; the hot topic detection model is obtained by combining graph neural networks and deep learning; the information change characteristics include at least: information dissemination trends, public sentiment, and emotional tendencies;

[0123] A generating unit is configured to generate a real-time interaction strategy corresponding to a hot topic based on the information analysis results and the type of each social media platform; the real-time interaction strategy includes at least: an opinion leader interaction strategy adapted to the activity information and the influence of social relationships, and a topic information release strategy adapted to the characteristics of information changes;

[0124] The interaction unit is configured to execute the real-time interaction strategy through a real-time interaction model on each social media platform to achieve positive information guidance on hot topics; the real-time interaction model is used to simulate the behavioral characteristics of users on each social media platform to obtain information to be published or operational behavior instructions, and push them to the user to confirm whether to execute them.

[0125] Further optionally, after acquiring the information data to be analyzed, the acquiring unit is further configured to:

[0126] Obtain the user's task requirements for the positive information guidance process; based on the task requirements and the information data, use a large prediction model to build a guidance decision model that is adapted to the hot topics in the information data; the guidance decision model includes a behavior suggestion module and a long-term monitoring module; through the behavior suggestion module, predict the change trend of the task requirements and the information data to obtain monitoring behavior suggestions for hot topics; through the long-term monitoring module, match the monitoring method of the task requirements, the information data and the monitoring behavior suggestions to obtain a long-term monitoring strategy for hot topics; execute the long-term monitoring strategy on each social media platform, and monitor the changes in information data after the real-time interaction strategy is executed on each social media platform, and dynamically adjust the information release strategy and behavior operation strategy in the real-time interaction strategy.

[0127] Further optionally, the acquisition unit executes the long-term monitoring strategy on each social media platform and is configured to:

[0128] Based on the long-term monitoring strategy, a long-term information evaluation system matching hot topics is constructed; using the long-term information evaluation system, information change predictions are performed on the long-term information monitoring data collected from various social media platforms, as well as the information data changes after the real-time interaction strategy is executed, to obtain information change index data; a long-term social network dynamic graph is constructed based on the long-term information monitoring data, the information change index data, and the information data changes, and the degree centrality and betweenness centrality of the nodes in the social network dynamic graph are calculated to evaluate the social relationship influence of opinion leaders, so as to obtain dynamic information change data corresponding to the long-term social network; based on the information change index data and the dynamic information change data, a long-term information evaluation report for hot topics is generated.

[0129] Further optionally, the monitoring unit monitors changes in information data after the real-time interaction strategy is executed on each social media platform, and dynamically adjusts the information release strategy and behavioral operation strategy in the real-time interaction strategy, and is configured to:

[0130] Extract information change data after the real-time interaction strategy is executed from each social media platform; determine the speed and scope of changes in information dissemination trends in each social media platform based on the information change data; and dynamically adjust the frequency and scope of information releases on hot topics based on the speed and scope of changes in information dissemination trends.

[0131] Further optionally, the identification unit adopts a hot topic detection model to identify hot topics in the information data in real time, and tracks the changing trend of hot topics in the social network dynamic graph to obtain information analysis results of the hot topics, and is configured to:

[0132] A hot topic detection model is used to perform semantic analysis on the information data to extract event keywords, event themes and emotional tendencies in the information data; based on the extracted event keywords, event themes and emotional tendencies, user nodes, topic nodes and content nodes are constructed, and the nodes are connected to form the social network dynamic graph; event recognition is performed based on the social network dynamic graph to obtain the hot topics to be monitored; hot topics are determined based on the access popularity of event nodes, the number of associated edges and the density of related information in the social network dynamic graph; opinion leader activity analysis is performed based on user nodes in the social network dynamic graph to obtain key opinion leaders related to hot topics and their influence on them. The method comprises the following steps: collecting the corresponding activity information and the influence of social relationships; analyzing the degree centrality, betweenness centrality and PageRank value of each user node through the graph neural network (GNN) to identify the key opinion leaders; extracting the user nodes, topic nodes and content nodes related to the hot topics from the social network dynamic graph to form a local social network dynamic graph corresponding to the hot topics; selecting a topic analysis model matching the hot topics from the candidate data model library; performing adaptive topic analysis on the local social network dynamic graph using the topic analysis model to obtain the information analysis result; wherein, the topic analysis model is pre-obtained by training the historical information data of the historical hot topics matching the hot topics.

[0133] Further optionally, it also includes a display unit, which is configured to: use a hot topic detection model in the identification unit to identify hot topics in the information data in real time, and track the changing trends of hot topics in the social network dynamic graph, and after obtaining the information analysis results of the hot topics, extract a hot topic indicator set from the information analysis results; the hot topic indicator set includes at least: hot topic evolution records, related keywords, public sentiment analysis results, opinion leader activity data; the public sentiment analysis results include at least: the proportion of each public sentiment category and the corresponding changing trends; project the hot topic indicator set into the visualization space and convert them into dynamic data graphs respectively, and bind the dynamic data graphs to the visualization chart component; the dynamic data graphs include at least: hot topic evolution graph, public sentiment distribution graph, opinion leader activity distribution graph; generate an information data analysis report for hot topics based on the hot topic indicator set, and display the information data analysis report and the visualization chart component to the user.

[0134] Further optionally, the generating unit generates a real-time interaction strategy corresponding to a hot topic based on the information analysis result and the type of each social media platform, and is configured to:

[0135] A sentiment analysis model is used to identify the stance of a key opinion leader based on the activity information in the information analysis results, so as to obtain the stance type of the key opinion leader; the stance type is one of active support, neutral wait-and-see, and negative questioning; a multidimensional influence evaluation model is used to perform a multidimensional analysis based on the social relationship influence in the information analysis results, so as to obtain the leader influence level of the key opinion leader; based on the leader influence level and the stance type, an opinion leader interaction strategy corresponding to the key opinion leader is generated; a dynamic strategy adjustment frequency is set according to the event heat of the hot topic, and the leader influence level and the stance type are updated based on the dynamic strategy adjustment frequency; if the leader influence level and the stance type change, the opinion leader interaction strategy is switched through the rule engine bound to the social media platform; topic content prediction and topic construction method analysis are performed based on the characteristics of information changes to obtain the topic information release strategy; the opinion leader interaction strategy and the topic information release strategy are integrated to obtain the real-time interaction strategy.

[0136] Further optionally, it also includes a construction unit, which is configured to: after the acquisition unit acquires the information data to be analyzed, construct a real-time data stream processing pipeline, and use the real-time data stream processing pipeline to perform millisecond-level processing on the information data to extract dynamic analysis indicators corresponding to hot topics; the dynamic analysis indicators include at least: the discussion volume growth rate, sentiment value, keyword frequency, and negative sentiment concentration of hot topics within the time window; input the dynamic analysis indicators into the dynamic user portrait model of each social media platform to obtain the group behavior pattern corresponding to the hot topic; compare the dynamic analysis indicators collected in real time with the dynamic threshold in the group behavior pattern to identify abnormal risk events corresponding to the hot topic; based on the abnormal risk event, immediately activate the emergency response mechanism, generate and publish soothing information that matches the group behavior pattern in each social media platform, so as to achieve auxiliary positive information guidance for hot topics.

[0137] The device can implement various steps in the above method embodiment, which will not be expanded here.

[0138] In the embodiment of the present application, an information data processing device is used, which can quickly perceive and respond to information changes, flexibly adjust strategies according to different platform characteristics and dynamic information, enhance the adaptability to complex information environments and emergencies, realize the automation and intelligence of the entire information processing process, simplify the information processing process, and improve processing efficiency and quality.

[0139] See also Figure 3 , Figure 3 This is a schematic diagram of an embodiment of an electronic device provided in an embodiment of the present application. Figure 3 As shown, an embodiment of the present application provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520. When the processor 520 executes the computer program 511, an information data processing method is implemented.

[0140] See also Figure 4 , Figure 4 This is a schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present application. Figure 4 As shown, this embodiment provides a computer-readable storage medium 600 on which a software program 611 is stored. When the software program 611 is executed by a processor, the information data processing method is implemented.

[0141] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0142] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0143] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application.

[0144] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if such changes and modifications of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such changes and modifications.

Claims

1. An information data processing method, characterized in that: The method comprises: Obtaining information data to be analyzed; the information data comes from different social media platforms; A hot topic detection model is used to identify hot topics in the information data in real time and track the changing trends of hot topics in social network dynamic graphs to obtain information analysis results of hot topics; the information analysis results include at least: information change characteristics of hot topics on various social media platforms, information on the activities of opinion leaders, and the influence of social relationships; the hot topic detection model is obtained by combining graph neural networks and deep learning; information change characteristics include at least: information dissemination trends, public sentiment, and emotional tendencies; Based on the information analysis results and the types of social media platforms, a real-time interaction strategy corresponding to the hot topics is generated; the real-time interaction strategy includes at least: an opinion leader interaction strategy adapted to the activity information and social relationship influence, and a topic information release strategy adapted to the characteristics of information changes; The real-time interaction strategy is executed through a real-time interaction model to simulate the behavioral characteristics of users on various social media platforms to obtain matching information to be published and / or behavioral operation instructions, and push them to users to confirm whether to execute them, thereby achieving positive information guidance on hot topics.

2. The information data processing method according to claim 1, characterized in that: After obtaining the information data to be analyzed, the method further includes: Obtaining users' task requirements for the positive information guidance process; Based on the task requirements and the information data, a large prediction model is used to construct a guidance decision model adapted to hot topics in the information data; the guidance decision model includes a behavior suggestion module and a long-term monitoring module; Through the behavior suggestion module, the change trend of the task requirements and the information data is predicted to obtain monitoring behavior suggestions for hot topics; By using the long-term monitoring module, the task requirements, the information data, and the monitoring behavior suggestions are matched with monitoring methods to obtain a long-term monitoring strategy for hot topics; The long-term monitoring strategy is executed on each social media platform, and the changes in information data after the real-time interaction strategy is executed in each social media platform are monitored, and the information release strategy and behavioral operation strategy in the real-time interaction strategy are dynamically adjusted.

3. The information data processing method according to claim 2, characterized in that: The implementation of the long-term monitoring strategy for each social media platform includes: Based on the long-term monitoring strategy, a long-term information evaluation system matching hot topics is constructed; Using the long-term information evaluation system, the long-term information monitoring data collected from each social media platform and the information data changes after the real-time interaction strategy is implemented are used to predict information changes, thereby obtaining information change index data; Constructing a long-term social network dynamic graph based on the long-term information monitoring data, the information change indicator data, and the information data change situation, and calculating the degree centrality and betweenness centrality of the nodes in the social network dynamic graph to evaluate the social relationship influence of the opinion leader, so as to obtain dynamic information change data corresponding to the long-term social network; Based on the information change index data and the dynamic information change data, a long-term information evaluation report of the hot topic is generated.

4. The information data processing method according to claim 2, characterized in that: The monitoring of information data changes after the real-time interaction strategy is executed on each social media platform, and the dynamic adjustment of the information release strategy and the behavior operation strategy in the real-time interaction strategy, include: Extracting information change data after the real-time interaction strategy is executed from various social media platforms; Based on the information change data, determine the speed and scope of changes in information dissemination trends on various social media platforms; Dynamically adjust the frequency and scope of information releases on hot topics based on the speed and scope of changes in information dissemination trends.

5. The information data processing method according to claim 1, characterized in that: The hot topic detection model is used to identify hot topics in the information data in real time, and to track the changing trends of hot topics in the social network dynamic graph to obtain information analysis results of hot topics, including: Using a hot topic detection model to perform semantic analysis on the information data to extract event keywords, event themes, and emotional tendencies in the information data; Based on the extracted event keywords, event themes, and sentiment tendencies, user nodes, topic nodes, and content nodes are constructed, and the nodes are connected to form the social network dynamic graph; Perform event recognition based on the social network dynamic graph to obtain hot topics to be monitored; determine hot topics based on the access popularity of event nodes, the number of associated edges, and the density of related information in the social network dynamic graph; Conduct opinion leader activity analysis based on user nodes in the social network dynamic graph to obtain key opinion leaders related to hot topics, their corresponding activity information, and their social relationship influence; analyze the degree centrality, betweenness centrality, and PageRank value of each user node through a graph neural network (GNN) to identify the key opinion leaders; Extracting user nodes, topic nodes, and content nodes related to hot topics from the social network dynamic graph to form a local social network dynamic graph corresponding to the hot topics; Select a topic analysis model that matches the hot topic from the candidate data model library; Using the topic analysis model to perform adaptive topic analysis on the local social network dynamic graph to obtain the information analysis result; The topic analysis model is pre-obtained by training historical information data of historical hot topics that match the hot topics.

6. The information data processing method according to claim 1, characterized in that: The method further includes: using a hot topic detection model to identify hot topics in the information data in real time, tracking the changing trends of hot topics in the social network dynamic graph, and obtaining the information analysis results of the hot topics; Extracting a hot topic indicator set from the information analysis results; the hot topic indicator set includes at least: hot topic evolution records, related keywords, public sentiment analysis results, and opinion leader activity data; the public sentiment analysis results include at least: the proportion of each public sentiment category and the corresponding change trend; Projecting the hot topic indicator set into a visualization space and converting them into dynamic data graphs, and binding the dynamic data graphs to a visualization chart component; the dynamic data graphs at least include: a hot topic evolution graph, a public sentiment distribution graph, and an opinion leader activity distribution graph; An information data analysis report of a hot topic is generated based on the hot topic indicator set, and the information data analysis report and the visual chart component are presented to a user.

7. The information data processing method according to claim 1, characterized in that: Generating a real-time interaction strategy corresponding to a hot topic based on the information analysis results and the type of each social media platform includes: Using a sentiment analysis model, leader stance identification is performed based on activity information in the information analysis results to obtain the stance type of the key opinion leader; the stance type is one of active support, neutral wait-and-see, and passive questioning; Through a multi-dimensional influence evaluation model, a multi-dimensional analysis is performed based on the social relationship influence in the information analysis results to obtain the leadership influence level of the key opinion leaders; Based on the leader influence level and the position type, generating an opinion leader interaction strategy corresponding to the key opinion leader; Setting a dynamic strategy adjustment frequency according to the event popularity of hot topics, and updating the leader influence level and the position type based on the dynamic strategy adjustment frequency; if the leader influence level and the position type change, switching the opinion leader interaction strategy through the rule engine bound to the social media platform; Predict topic content and analyze topic construction methods based on information change characteristics to obtain the topic information release strategy; The opinion leader interaction strategy and the topic information release strategy are integrated to obtain the real-time interaction strategy.

8. The information data processing method according to claim 1, characterized in that: After obtaining the information data to be analyzed, the method further includes: Construct a real-time data stream processing pipeline, and use the real-time data stream processing pipeline to perform millisecond-level processing on the information data to extract dynamic analysis indicators corresponding to hot topics; the dynamic analysis indicators include at least: the growth rate of discussion volume of hot topics within the time window, sentiment value, keyword frequency, and negative sentiment concentration; Input the dynamic analysis indicators into the dynamic user portrait models of various social media platforms to obtain group behavior patterns corresponding to hot topics; Comparing the dynamic analysis indicators collected in real time with the dynamic thresholds in the group behavior pattern to identify abnormal risk events corresponding to hot topics; Based on the abnormal risk event, the emergency response mechanism is immediately activated to generate and release soothing information that matches the group behavior patterns on various social media platforms to achieve auxiliary positive information guidance on hot topics.

9. An information data processing device, characterized in that: The device comprises the following units, wherein: an acquisition unit configured to acquire information data to be analyzed; the information data comes from different social media platforms; The identification unit is configured to use a hot topic detection model to identify hot topics in the information data in real time, and track the changing trends of hot topics in social network dynamic graphs to obtain information analysis results of the hot topics; the information analysis results include at least: information change characteristics of hot topics on various social media platforms, activity information of opinion leaders, and social relationship influence; the hot topic detection model is obtained by combining graph neural networks and deep learning; the information change characteristics include at least: information dissemination trends, public sentiment, and emotional tendencies; A generating unit is configured to generate a real-time interaction strategy corresponding to a hot topic based on the information analysis results and the type of each social media platform; the real-time interaction strategy includes at least: an opinion leader interaction strategy adapted to the activity information and the influence of social relationships, and a topic information release strategy adapted to the characteristics of information changes; The interaction unit is configured to execute the real-time interaction strategy through a real-time interaction model on each social media platform to achieve positive information guidance on hot topics; the real-time interaction model is used to simulate the behavioral characteristics of users on each social media platform to obtain information to be published or operational behavior instructions, and push them to the user to confirm whether to execute them.

10. An electronic device, characterized in that: including a memory for storing a computer software program; A processor is used to read and execute the computer software program, thereby implementing the information data processing method according to any one of claims 1 to 8.

Images