Film box office prediction system based on machine learning and big data

Abstract

The invention relates to the technical field of movie box office prediction, in particular to a movie box office prediction system based on machine learning and big data, which comprises a data collection module, a data processing and feature engineering module, a social propagation path prediction module, a box office prediction module, a model verification and optimization module and a result display module, the data collection module collects market data related to a movie box office; the data processing and feature engineering module cleans the market data; the social contact propagation path prediction module simulates an information propagation path and speed on social contact media; the box office prediction module predicts a movie box office; the model verification and optimization module adjusts model parameters; and the result display module displays the predicted movie box office result to the user. According to the invention, the prediction result is more accurate and timely, and a movie issuer and a marketing team are assisted to make market decisions.

Description

Technical Field

[0001] The present invention relates to the technical field of movie box office prediction, and in particular to a movie box office prediction system based on machine learning and big data. Background Art

[0002] With the rapid development of the film industry, movie box office forecasts play a vital role in film distribution and marketing strategies. Box office forecasts not only affect the choice of film release time, but also have important guiding significance for decisions such as advertising and resource allocation. Especially in the context of the rapid development of social media, audience feedback, word-of-mouth communication and marketing activities have an increasingly obvious impact on movie box office. Therefore, how to accurately and timely predict movie box office has become the focus of attention in the film industry.

[0003] At present, traditional movie box office prediction models mostly rely on historical box office data and basic market analysis. This method seems to be powerless when dealing with market changes and dynamic social media influences. Existing technologies are often unable to fully integrate multi-source data, especially key features such as dynamic information propagation paths and node influence in social media. This leads to poor performance of prediction models in complex and changing market environments, making it difficult to accurately capture the audience's emotional fluctuations and the real-time impact of information diffusion, which in turn affects the accuracy of movie box office predictions and the timeliness of decision-making.

[0004] The present invention aims to solve the above-mentioned deficiencies in the prior art and proposes a movie box office prediction system based on machine learning and big data, which can provide accurate market insights and decision support for film distributors, optimize marketing strategies, and maximize movie box office. Summary of the invention

[0005] Based on the above objectives, the present invention provides a movie box office prediction system based on machine learning and big data.

[0006] A movie box office prediction system based on machine learning and big data, including a data collection module, a data processing and feature engineering module, a social communication path prediction module, a box office prediction module, a model verification and optimization module, and a result display module, wherein;

[0007] The data collection module collects market data related to movie box office from multiple data sources, including historical box office data, social media feedback data, marketing activity data, and information on competing movies in the same period;

[0008] The data processing and feature engineering module cleans and integrates the collected market data, and constructs a feature set based on factors that affect the movie box office, including movie type, director and actor influence, release time, budget size, and audience sentiment data;

[0009] The social communication path prediction module simulates the information communication path and speed on social media and quantifies the influential nodes in the information communication process, specifically including:

[0010] Social network construction: Construct a social network graph of movie-related topics, model users and information on social media platforms as nodes and edges, and form a dynamic social network structure;

[0011] Propagation path tracking: Using the dynamic graph neural network (D-GNN) model, the propagation path of information in social networks is tracked in real time to identify the starting point of information propagation, influential nodes and its propagation direction;

[0012] Propagation speed analysis: Calculate the speed at which information spreads in the social network structure, analyze the time required for information to spread from one node to another, and evaluate the propagation efficiency in combination with the breadth of the propagation path;

[0013] Quantification of node influence: Based on the influential nodes in the information propagation path, the influence of each node in the information diffusion process is quantified. Combined with the node's connectivity and propagation ability, a node influence score is generated as the input feature for box office prediction;

[0014] The box office prediction module combines the simulated information propagation path and speed to predict the movie box office through the movie box office prediction model;

[0015] The model verification and optimization module verifies and optimizes the movie box office prediction model through cross-validation and adjusts the model parameters;

[0016] The result display module presents the predicted movie box office results to the user in the form of charts or reports, and provides box office growth predictions based on social communication paths.

[0017] Optionally, the data collection module includes:

[0018] Historical box office data interface: Through API connection with the movie box office database, historical box office data for each time period can be automatically obtained, including release time, total box office, and number of moviegoers;

[0019] Social media data crawler: Use the public API of social media platforms to crawl social media feedback data related to movies in real time, including user comments, likes, reposts, and sentiment analysis results;

[0020] Marketing activity data collection: Through the data interface connection with major advertising platforms and marketing channels, we can obtain the investment and effect data of movie marketing activities, including advertising click-through rate, exposure and interaction rate;

[0021] Information collection tool for competing movies in the same period: Automatically collect relevant data of movies released at the same time as the target movie, including the box office performance, marketing strategies and audience evaluation of competing movies.

[0022] Optionally, the data processing and feature engineering module includes:

[0023] Data cleaning: Use the Z-Score algorithm to clean the collected market data, identify and process abnormal data, missing data, and duplicate data;

[0024] Data integration: Through multi-dimensional data alignment technology, market data from different sources are aligned and integrated in time and space;

[0025] Feature construction: Based on the factors that affect the movie box office, a feature set is constructed, including:

[0026] Movie genre features: One-hot encoding is used to convert the movie genre into multiple binary features to capture the impact of different movie genres on the box office;

[0027] Director and actor influence characteristics: Based on historical box office data, the director or actor influence index I is calculated, expressed as:

[0028]

[0029] Among them, R i represents the box office revenue of the i-th movie, B i represents the budget of the i-th film, and n is the total number of films in which the director or actor has participated;

[0030] Release time features: Convert release dates into holiday, weekend or weekday features, and identify the impact of release time on box office through time series analysis;

[0031] Budget size feature: Through normalization, the budget size of the movie is converted into a comparative feature value, which is used to analyze the box office performance of movies with different budget sizes;

[0032] Audience sentiment characteristics: The sentiment analysis of social media feedback data is performed using natural language processing (NLP) technology to extract sentiment tendency scores (such as positive, negative, and neutral) as sentiment characteristics, and the audience sentiment index E is calculated by combining the sentiment intensity weights, expressed as:

[0033]

[0034] Among them, S j is the sentiment score of the jth feedback, W j is the sentiment intensity weight, and m is the total number of feedbacks.

[0035] Optionally, the social network construction includes:

[0036] Node definition and identification: Users and movie-related content (such as posts, comments, reposts, etc.) on social media platforms are regarded as nodes, where user nodes represent social media users and information nodes represent movie-related content;

[0037] Definition and generation of edges: Based on the interactive relationships between users (such as likes, comments, and reposts) and the associations between users and information nodes (such as posting, commenting, and sharing), edges are generated between nodes to form a preliminary social network graph. The weight of the edge is w uv It is expressed as:

[0038] w uv =α·F uv +β·I ui +γ·S ii′ ;

[0039] Among them, F uv represents the interaction frequency between user u and user v, I ui represents the association strength between user u and information node i, S ii′ represents the similarity between information node i and information node i′, α, β, γ are the corresponding weight coefficients;

[0040] Dynamic social network update: Through the dynamic social network evolution model, the social network graph is updated in real time to capture the changes in the interactive relationships between users over time, and the weights of nodes and edges are dynamically adjusted to reflect the real-time social communication status, which is expressed as:

[0041] A t+1 =A t +ΔA t ;

[0042] Among them, A t represents the adjacency matrix at time t, ΔA t Represents the changes in the network structure from time t to t+1 (added or deleted edges);

[0043]

[0044] in, represents the probability of generating an edge between nodes u and v at time t+1, σ is the sigmoid function, is the feature vector of node u at time t, represents the feature vector of node v at time t, A t [u,v] is the element of the adjacency matrix at time t;

[0045] Network structure optimization: When constructing a dynamic social network graph, the Louvain algorithm is used to optimize the social network graph, identify the community structure in the network, and improve the resolution and stability of the social network graph by optimizing the distribution of nodes and edges, which is expressed as:

[0046]

[0047] Where Q represents modularity, m is the number of edges in the network, and k u and k v are the degrees of nodes u and v respectively, A[u,v] is the value in the adjacency matrix, δ(c u ,c v ) is the indicator function.

[0048] Optionally, the propagation path tracking includes:

[0049] Model construction: Build a dynamic graph neural network model to model the information propagation path that changes over time in social networks. Nodes represent users and information, and edges represent interactions between users or associations between users and information, expressed as:

[0050]

[0051] in, represents the hidden state of node u at time t+1, is the hidden state of node u at time t, is the set of neighbor nodes of node u, A t [u,v] is the element in the adjacency matrix at time t, W1, W2 and W3 are weight matrices, and σ is the activation function;

[0052] Information propagation path tracking: By dynamically updating the hidden state of the node, the dynamic graph neural network model tracks the propagation path of information in the social network in real time, which can be expressed as:

[0053]

[0054] Among them, Active(u) represents the activation state of node u, and θ is the threshold;

[0055]

[0056] in, represents the propagation path at time t;

[0057] Identification of the starting point of information dissemination and influential nodes: The dynamic graph neural network model identifies the starting point of information dissemination by analyzing the hidden state of the initial node (information publisher). At the same time, through the change amplitude of the node hidden state and the cumulative impact in the propagation path, it quantifies and identifies the influential nodes that contribute to the diffusion of information during the dissemination process, expressed as:

[0058]

[0059] Among them, u0 is the initial node, t u is the activation time of node u, is the set of all nodes;

[0060] I u =∑ v∈v A t [u,v]·Active(v);

[0061] Among them, I u represents the cumulative influence of node u, A t [u,v] represents the connection status between node u and node v, and Active(v) represents the activation status of node v;

[0062] Propagation direction identification: By analyzing the changing trend of hidden states between nodes, the dynamic graph neural network model is used to infer the propagation direction of information in the social network, which is expressed as:

[0063]

[0064] Among them, D uv Indicates the direction of information propagation from node u to node v, sign is the sign function;

[0065]

[0066] in, represents the overall propagation direction at time t, and ε is the set of edges.

[0067] Optionally, the propagation speed analysis includes:

[0068] Propagation time calculation: by recording the time Δt required for information to propagate from node u to node v uv , and combined with the activation time of the node, calculate the propagation speed v of information from one node to the next node in the social network uv , expressed as:

[0069]

[0070] Among them, d uv is the graph distance between node u and node v;

[0071] Breadth analysis of the propagation path: Analyze the breadth B(t) of the information propagation path in the network, expressed as:

[0072]

[0073] Among them, Active(v) is the activation state of node v at time t;

[0074] Propagation efficiency evaluation: Combine the propagation speed and breadth to evaluate the propagation efficiency of information in the entire social network, expressed as:

[0075]

[0076] in, represents the propagation path at time t, Represents a set of propagation paths The number of node pairs in v uv is the propagation speed of each pair of nodes in the path, and B(t) is the breadth of the propagation path.

[0077] Optionally, the node influence quantification includes:

[0078] Node connectivity calculation: connectivity k of node u u It represents the number of connections between node u and other nodes in the social network, expressed as:

[0079]

[0080] Among them, A[u,v] is the element in the adjacency matrix, is the set of all nodes;

[0081] Node propagation capacity calculation: propagation capacity C of node u u The position and influence of the node in the propagation path are quantified and expressed as:

[0082]

[0083] Among them, Active(v) represents the activation state of node v;

[0084] Node influence score calculation: influence score G of node u u It is quantified by combining its connectivity and propagation capabilities, expressed as:

[0085] G u =α·k u +β·C u ;

[0086] Among them, α and β are weight coefficients;

[0087] Application of node influence in box office prediction: The generated node influence score G u As features of social communication paths, they serve as input for box office prediction.

[0088] Optionally, the movie box office prediction model adopts a Bayesian optimization neural network, and the Bayesian optimization neural network includes:

[0089] Feature preprocessing and fusion: Normalize the social communication path, speed, and node influence features, and fuse them to generate the feature vector of the neural network input, expressed as:

[0090] x fused =α·x path +β·x speed +γ·x influence ;

[0091] Among them, x fused is the feature vector of the fused neural network input, x path 、x speed 、x influence They are social communication path characteristics, communication speed characteristics, and node influence characteristics, and α, β, and γ are fusion weights;

[0092] Network structure design: Introduce a processing mechanism for social network characteristics into the neural network structure, expressed as:

[0093] Input layer: h (0) =x fused ;

[0094] Branching hidden layer:

[0095]

[0096] Among them, h (0) is the fused feature vector of the input layer, are the weight matrices of social communication path characteristics, communication speed characteristics, and node influence characteristics, respectively. They are the bias items of social communication path characteristics, communication speed characteristics, and node influence characteristics. are the outputs of social communication path characteristics, communication speed characteristics, and node influence characteristics, σ is the activation function, is the processed fusion feature vector;

[0097] Box office prediction output: The fused features are input into the output layer to generate the final movie box office prediction results, expressed as:

[0098]

[0099] in, is the predicted movie box office value, and are the weight matrix and bias term of the output layer respectively;

[0100] Feature importance analysis and feedback mechanism: Feature importance analysis and feedback mechanism are introduced to enhance the interpretability of the model and make feedback adjustments based on the prediction error, expressed as:

[0101]

[0102] Among them, I i Indicates the influence of the i-th fusion feature on the prediction result, is the i-th fusion feature, Δw i is the adjustment amount of the i-th feature weight, is the loss function, y is the real box office value, and η is the learning rate.

[0103] Optionally, the model verification and optimization module includes:

[0104] Cross-validation process: The model validation and optimization module validates the movie box office prediction model through k-fold cross-validation, which is expressed as:

[0105]

[0106] Among them, CV k is the average error of k-fold cross validation, is the prediction error in the kth fold, is the predicted value on the k-fold validation set, y (i) is the true value of the k-th fold;

[0107] Model parameter optimization: After completing cross-validation, minimize the average cross-validation error CV k To adjust the model parameters (such as learning rate, number of hidden layers, number of neurons, etc.), the model parameter optimization adopts the Bayesian optimization algorithm, which is expressed as:

[0108] min θ CV k (θ)+λ·R(θ);

[0109] Among them, θ represents the hyperparameter set of the model, CV k (θ) is the cross-validation mean error under the corresponding parameters, R(θ) is the regularization term of the hyperparameter, and λ is the regularization coefficient;

[0110] Adaptive adjustment: During the model parameter optimization process, the model parameters are adjusted based on the gradient descent algorithm, which is expressed as:

[0111]

[0112] Among them, θ t+1 represents the model parameters after the next iteration, η is the learning rate, is the current parameter θ t The gradient of the cross validation error under .

[0113] Optionally, the result display module includes:

[0114] Chart generation: The movie box office results predicted by the movie box office prediction model are presented to users in the form of charts, including line charts, bar charts, and pie charts;

[0115] Report generation: Automatically generate a comprehensive report based on the output data of the movie box office prediction model, including the predicted movie box office results, model performance indicators (such as mean square error, R 2 value) and related analysis description;

[0116] Box office growth prediction based on social communication paths: Combine social communication paths to predict the dynamic changes in movie box office and provide box office growth trends within a predetermined period of time in the future, expressed as:

[0117]

[0118] in, represents the box office growth based on social communication path analysis, is the predicted box office value at the current time t, and GrowthPrediction(t) is the predicted box office growth value after considering the social communication path.

[0119] Beneficial effects of the present invention:

[0120] The present invention, through the data collection module, efficiently and automatically integrates market data from multiple data sources, including historical box office data, social media feedback, marketing activity data and information on competing films in the same period. Through the data processing and feature engineering module, the collected data is comprehensively cleaned, integrated and feature constructed, ensuring the high quality and multi-dimensionality of the input data, providing a reliable foundation for subsequent box office predictions. This modular processing method significantly improves the system's perception of market changes and prediction accuracy, allowing film distributors to obtain more comprehensive market insights.

[0121] The present invention constructs a dynamic social network graph and uses a dynamic graph neural network model to accurately simulate the information propagation path, speed and node influence on social media, and comprehensively evaluates the information propagation efficiency by quantifying key nodes and path breadth. Combined with these dynamic characteristics, the box office prediction module can more accurately reflect the real-time impact of social media on movie box office, provide in-depth propagation path analysis and box office growth prediction, make the prediction results more accurate and timely, and help movie distributors and marketing teams make accurate market decisions.

[0122] The present invention, through the model verification and optimization module, adopts cross-validation combined with Bayesian optimization and gradient descent method to dynamically adjust the model parameters to minimize the prediction error, thereby enhancing the generalization ability and robustness of the model. The result display module generates intuitive charts and comprehensive reports to clearly present the movie box office prediction results and growth prediction based on social communication paths to users, providing comprehensive data support and decision-making basis, so that film distributors can better grasp market trends and optimize marketing strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0123] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0124] Figure 1 A schematic diagram of system function modules according to an embodiment of the present invention;

[0125] Figure 2 Schematic diagram of a social communication path prediction module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0126] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0127] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0128] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0129] like Figure 1-Figure 2 As shown, a movie box office prediction system based on machine learning and big data includes a data collection module, a data processing and feature engineering module, a social communication path prediction module, a box office prediction module, a model verification and optimization module, and a result display module, wherein;

[0130] The data collection module collects market data related to movie box office from multiple data sources, including historical box office data, social media feedback data, marketing activity data, and information about competing movies in the same period;

[0131] The data processing and feature engineering module cleans and integrates the collected market data, and constructs a feature set based on factors that affect movie box office, including movie type, director and actor influence, release time, budget size, and audience sentiment data;

[0132] The social communication path prediction module simulates the information communication path and speed on social media and quantifies the influential nodes in the information communication process, including:

[0133] Social network construction: Construct a social network graph of movie-related topics, model users and information on social media platforms as nodes and edges, and form a dynamic social network structure;

[0134] Propagation path tracking: Using the dynamic graph neural network (D-GNN) model, the propagation path of information in social networks is tracked in real time to identify the starting point of information propagation, influential nodes and its propagation direction;

[0135] Propagation speed analysis: Calculate the speed at which information spreads in the social network structure, analyze the time required for information to spread from one node to another, and evaluate the propagation efficiency in combination with the breadth of the propagation path;

[0136] Quantification of node influence: Based on the influential nodes in the information propagation path, the influence of each node in the information diffusion process is quantified. Combined with the node's connectivity and propagation ability, a node influence score is generated as the input feature for box office prediction;

[0137] The box office prediction module combines the simulated information propagation path and speed, and uses the movie box office prediction model to predict the movie box office;

[0138] The model verification and optimization module verifies and optimizes the movie box office prediction model through cross-validation and adjusts the model parameters to improve the accuracy and robustness of the prediction;

[0139] The result display module presents the predicted movie box office results to users in the form of charts or reports, and provides box office growth forecasts based on social communication paths to facilitate decision-making support for film distributors and marketing teams;

[0140] Through the above content, not only can the dynamic impact of social media information dissemination be analyzed in real time, but also the accuracy and adaptability of box office forecasts can be significantly improved through multi-dimensional data integration and machine learning algorithms, providing more accurate decision-making support for film distributors and marketing teams.

[0141] The data collection modules include:

[0142] Historical box office data interface: Through API connection with the movie box office database, historical box office data for each time period can be automatically obtained, including release time, total box office, and number of moviegoers;

[0143] Social media data crawler: Use the public API of social media platforms to crawl social media feedback data related to movies in real time, including user comments, likes, reposts, and sentiment analysis results;

[0144] Marketing activity data collection: Through the data interface connection with major advertising platforms and marketing channels, we can obtain the investment and effect data of movie marketing activities, including advertising click-through rate, exposure and interaction rate;

[0145] Information collection tool for competing movies in the same period: automatically collects relevant data of movies released at the same time as the target movie, including the box office performance, marketing strategies and audience evaluation of competing movies;

[0146] Through the above content, multi-source data can be collected efficiently and automatically, providing accurate and multi-dimensional input for subsequent box office forecasts, significantly improving the system's ability to perceive market changes and prediction accuracy, and providing a solid data foundation for decision support.

[0147] Data processing and feature engineering modules include:

[0148] Data cleaning: Use the Z-Score algorithm to clean the collected market data, identify and process abnormal data, missing data, and duplicate data to ensure data quality and consistency;

[0149] Data integration: Through multi-dimensional data alignment technology, market data from different sources are aligned and integrated in time and space to ensure the consistency and integrity of the data set;

[0150] Feature construction: Based on the factors that affect the movie box office, a feature set is constructed, including:

[0151] Movie genre features: One-hot encoding is used to convert the movie genre into multiple binary features to capture the impact of different movie genres on the box office;

[0152] Director and actor influence characteristics: Based on historical box office data, the director or actor influence index I is calculated, expressed as:

[0153]

[0154] Among them, R i represents the box office revenue of the i-th movie, B i represents the budget of the i-th film, and n is the total number of films in which the director or actor participated;

[0155] Release time feature: The release date is converted into holiday, weekend or weekday features, and the impact trend of release time on box office is identified through time series analysis, which is expressed as:

[0156]

[0157] Among them, X t is the box office data at time t, c is a constant, and θ j are the autoregressive and moving average coefficients, ∈ t is the error term, p and q are the orders of autoregression and moving average respectively;

[0158] Budget size feature: Through normalization, the budget size of the movie is converted into a comparative feature value, which is used to analyze the box office performance of movies with different budget sizes;

[0159] Audience sentiment characteristics: The sentiment analysis of social media feedback data is performed using natural language processing (NLP) technology to extract sentiment tendency scores (such as positive, negative, and neutral) as sentiment characteristics, and the audience sentiment index E is calculated by combining the sentiment intensity weights, expressed as:

[0160]

[0161] Among them, S j is the sentiment score of the jth feedback, W j is the sentiment intensity weight, m ​​is the total number of feedbacks;

[0162] Through the above content, the high quality and consistency of the data are ensured, and the key factors affecting the box office are captured, such as the influence of directors and actors, the seasonal effect of release time, and the emotional response of the audience. The finely processed features provide rich and efficient input for the box office prediction model, greatly enhancing the model's predictive ability and adaptability.

[0163] Social network building includes:

[0164] Node definition and identification: Users and movie-related content (such as posts, comments, reposts, etc.) on social media platforms are regarded as nodes, where user nodes represent social media users and information nodes represent movie-related content;

[0165] Definition and generation of edges: Based on the interactive relationships between users (such as likes, comments, and reposts) and the associations between users and information nodes (such as posting, commenting, and sharing), edges are generated between nodes to form a preliminary social network graph. The weight of the edge is w uv It is expressed as:

[0166] w uv =α·F uv +β·I ui +γ·S ii′ ;

[0167] Among them, F uv represents the interaction frequency between user u and user v, I ui represents the association strength between user u and information node i, S ii′ represents the similarity between information node i and information node i′, α, β, γ are the corresponding weight coefficients;

[0168] Dynamic social network update: Through the dynamic social network evolution model, the social network graph is updated in real time to capture the changes in the interactive relationships between users over time, and the weights of nodes and edges are dynamically adjusted to reflect the real-time social communication status, which is expressed as:

[0169] A t+1 =A t+ΔA t ;

[0170] Among them, A t represents the adjacency matrix at time t, ΔA t Represents the changes in the network structure from time t to t+1 (added or deleted edges);

[0171]

[0172] in, represents the probability of generating an edge between nodes u and v at time t+1, σ is the sigmoid function, is the feature vector of node u at time t, represents the feature vector of node v at time t, A t [u,v] is the element of the adjacency matrix at time t, indicating whether nodes u and v are directly connected at time t;

[0173] Network structure optimization: When constructing a dynamic social network graph, the Louvain algorithm is used to optimize the social network graph, identify the community structure in the network, and improve the resolution and stability of the social network graph by optimizing the distribution of nodes and edges, which is expressed as:

[0174]

[0175] Where Q represents modularity, m is the number of edges in the network, and k u and k v are the degrees of nodes u and v respectively, A[u,v] is the value in the adjacency matrix, δ(c u ,c v ) is an indicator function, which takes the value 1 when u and v belong to the same community and 0 otherwise;

[0176] Through the above content, not only the accuracy and adaptability of the network structure are improved, but also a solid data foundation is provided for subsequent propagation path analysis and box office prediction, ensuring the accuracy of the prediction model in a dynamic environment.

[0177] Propagation path tracking includes:

[0178] Model construction: Build a dynamic graph neural network model to model the information propagation path that changes over time in social networks. Nodes represent users and information, and edges represent interactions between users or associations between users and information, expressed as:

[0179]

[0180] in, represents the hidden state of node u at time t+1, is the hidden state of node u at time t, is the set of neighbor nodes of node u, A t [u,v] is the element in the adjacency matrix at time t, W1, W2 and W3 are weight matrices, and σ is the activation function;

[0181] Information propagation path tracking: By dynamically updating the hidden state of the node, the dynamic graph neural network model tracks the propagation path of information in the social network in real time. The propagation path is characterized by the activation state of the node. When the hidden state of the node exceeds the threshold, it means that the information has reached the node and is recorded as part of the propagation path, which is expressed as:

[0182]

[0183] Among them, Active(u) represents the activation state of node u. When its value is 1, it means that the information has been propagated to node u, and θ is the threshold;

[0184]

[0185] in, represents the propagation path at time t, which is composed of all nodes whose activation state is 1;

[0186] Identification of the starting point of information dissemination and influential nodes: The dynamic graph neural network model identifies the starting point of information dissemination by analyzing the hidden state of the initial node (information publisher). At the same time, through the change amplitude of the node hidden state and the cumulative impact in the propagation path, it quantifies and identifies the influential nodes that contribute to the diffusion of information during the dissemination process. These nodes play a key role in the propagation path and have an important impact on the subsequent direction and breadth of dissemination, which can be expressed as:

[0187]

[0188] Among them, u0 is the initial node, t u is the activation time of node u, is the set of all nodes;

[0189]

[0190] Among them, I u represents the cumulative influence of node u, A t [u,v] represents the connection status between node u and node v, and Active(v) represents the activation status of node v;

[0191] Propagation direction identification: By analyzing the changing trend of hidden states between nodes, the dynamic graph neural network model is used to infer the propagation direction of information in the social network. Information propagates from nodes with higher activation states to nodes with lower activation states. The model determines the main direction of information propagation based on the connection weights and hidden state changes between nodes, which can be expressed as:

[0192]

[0193] Among them, D uv Indicates the direction of information propagation from node u to node v. sign is a sign function. When x>0, it takes 1, indicating that the information propagates from u to v. When x<0, it takes -1, indicating that the information propagates from v to u.

[0194]

[0195] in, represents the overall propagation direction at time t, and ε is the set of edges;

[0196] Through the above content, it is possible to accurately track the diffusion process of information in social networks in real time, identify the starting point, key influence nodes and propagation direction of information dissemination, provide real-time propagation path data for the box office prediction model, and improve the accuracy and timeliness of the prediction.

[0197] The setting of the threshold θ specifically includes:

[0198] Initial setting: The initial value of θ can be based on the node hidden state The historical distribution setting is usually set to the mean of the hidden state plus a multiple of a certain standard deviation, expressed as:

[0199] θ0=μ h +k·σ h ;

[0200] Among them, μ h Is a hidden state The mean value, σ h Is a hidden state The standard deviation of , k is a constant coefficient used to adjust the sensitivity of the initial threshold;

[0201] Adaptive adjustment: As time goes by, the system dynamically adjusts the threshold θ based on the activation of the nodes. It makes adjustments when it observes too many or too few activated nodes, expressed as:

[0202] θ t+1 =θ t ±Δθ;

[0203] Wherein, Δθ is the adjustment amount, which is determined based on the ratio of activated nodes. When the activation ratio is higher than the preset range, Δθ increases, and when the activation ratio is lower than the preset range, Δθ decreases;

[0204] Stable convergence: Through iterative adjustment, θ will eventually converge to a stable value, so that the number of node activations remains within a reasonable range, ensuring effective identification of information propagation paths.

[0205] Propagation velocity analysis includes:

[0206] Propagation time calculation: by recording the time Δt required for information to propagate from node u to node v uv , and combined with the activation time of the node, calculate the propagation speed v of information from one node to the next node in the social network uv , expressed as:

[0207]

[0208] Among them, d uv is the graph distance between node u and node v;

[0209] Breadth analysis of propagation paths: Analyze the breadth B(t) of the information propagation path in the network. Breadth is defined as the number of nodes to which information can be propagated within a given time t, expressed as:

[0210]

[0211] Among them, Active(v) is the activation state of node v at time t;

[0212] Propagation efficiency evaluation: Combine the propagation speed and breadth to evaluate the propagation efficiency of information in the entire social network, expressed as:

[0213]

[0214] in, represents the propagation path at time t, Represents a set of propagation paths The number of node pairs in v uv is the propagation speed of each pair of nodes in the path, and B(t) is the breadth of the propagation path;

[0215] Through the above content, we can accurately calculate the speed of information propagation in social networks, combine the breadth of the propagation path, and comprehensively evaluate the efficiency of information propagation, providing more in-depth dynamic propagation characteristics for box office prediction, so that the prediction model can more accurately reflect the impact of social media on movie box office.

[0216] Node influence quantification includes:

[0217] Node connectivity calculation: connectivity k of node u u It represents the number of connections between node u and other nodes in the social network, expressed as:

[0218]

[0219] Among them, A[u,v] is an element in the adjacency matrix, which represents the connection status between node u and node v. is the set of all nodes;

[0220] Node propagation capacity calculation: propagation capacity C of node u u The position and influence of the node in the propagation path are quantified and expressed as:

[0221]

[0222] Among them, Active(v) represents the activation state of node v;

[0223] Node influence score calculation: influence score G of node u u It is quantified by combining its connectivity and propagation capabilities, expressed as:

[0224] G u =α·k u +β·C u ;

[0225] Among them, α and β are weight coefficients, which are used to balance the contribution of node connectivity and communication ability in the influence score;

[0226] Application of node influence in box office prediction: The generated node influence score G u As features of social communication paths, they are used as inputs for box office predictions to enhance the model’s understanding of information diffusion dynamics, thereby improving the accuracy of box office predictions;

[0227] Through the above content, we can effectively quantify the influence of each node in the social network in the process of information diffusion, and use this dynamic feature as an important input of the box office prediction model, combining the structural properties (connectivity) and behavioral properties (propagation ability) of the nodes, thereby providing more comprehensive social network data support for box office prediction.

[0228] The movie box office prediction model uses a Bayesian optimization neural network, which includes:

[0229] Feature preprocessing and fusion: Normalize the social communication path, speed, and node influence features, and fuse them to generate the feature vector of the neural network input, expressed as:

[0230]

[0231] Among them, x i is the i-th feature, min(x) and max(x) are the minimum and maximum values ​​of the feature respectively;

[0232] x fused =α·x path +β·x speed +γ·x influence ;

[0233] Among them, x fused is the feature vector of the fused neural network input, x path 、x speed 、x influence They are social communication path characteristics, communication speed characteristics, and node influence characteristics, and α, β, and γ are fusion weights;

[0234] Network structure design: Introduce a processing mechanism for social network characteristics into the neural network structure to better capture the impact of complex social dynamics on box office, expressed as:

[0235] Input layer: h (0) =x fused ;

[0236] Branching hidden layer:

[0237]

[0238] Among them, h (0) is the fused feature vector of the input layer, are the weight matrices of social communication path characteristics, communication speed characteristics, and node influence characteristics, respectively. They are the bias items of social communication path characteristics, communication speed characteristics, and node influence characteristics. are the outputs of social communication path characteristics, communication speed characteristics, and node influence characteristics, σ is the activation function, is the processed fusion feature vector;

[0239] Box office prediction output: The fused features are input into the output layer to generate the final movie box office prediction results, expressed as:

[0240]

[0241] in, is the predicted movie box office value, and are the weight matrix and bias term of the output layer respectively;

[0242] Feature importance analysis and feedback mechanism: Feature importance analysis and feedback mechanism are introduced to enhance the interpretability of the model and make feedback adjustments based on the prediction error, expressed as:

[0243]

[0244] Among them, I i Indicates the influence of the i-th fusion feature on the prediction result, is the i-th fusion feature, Δw i is the adjustment amount of the i-th feature weight, is the loss function, y is the real box office value, and η is the learning rate;

[0245] Through the above content, the automatic tuning of model parameters is ensured, the generalization ability and robustness of the overall model are improved, and the model performs well when facing multi-dimensional features and dynamic data, providing strong support for the accurate prediction of movie box office.

[0246] Model validation and optimization modules include:

[0247] Cross-validation process: The model validation and optimization module validates the movie box office prediction model through k-fold cross-validation. In the cross-validation process, the data set is divided into k equal subsets, the model is trained on k-1 subsets, and validated on the remaining subset, alternating k times, each time using a different subset as the validation set, expressed as:

[0248]

[0249] Among them, CV k is the average error of k-fold cross validation, is the prediction error in the kth fold, is the predicted value on the k-fold validation set, y (i) is the true value of the k-th fold;

[0250] Model parameter optimization: After completing cross-validation, minimize the average cross-validation error CV k To adjust the model parameters (such as learning rate, number of hidden layers, number of neurons, etc.), the model parameter optimization adopts the Bayesian optimization algorithm, which is expressed as:

[0251] min θ CV k (θ)+λ·R(θ);

[0252] Among them, θ represents the hyperparameter set of the model, CV k (θ) is the cross-validation mean error under the corresponding parameters, R(θ) is the regularization term of the hyperparameter, and λ is the regularization coefficient;

[0253] Adaptive adjustment: In the process of model parameter optimization, the model parameters are adjusted based on the gradient descent algorithm to minimize the cross-validation error so that the finally selected parameters can obtain the best prediction performance on different data sets, which is expressed as:

[0254]

[0255] Among them, θ t+1 represents the model parameters after the next iteration, η is the learning rate, is the current parameter θ t The gradient of the cross-validation error under ;

[0256] Through the above content, the generalization ability of the movie box office prediction model can be effectively evaluated, and the model parameters can be automatically adjusted through Bayesian optimization combined with the gradient descent method, so as to maintain high-precision prediction results in different data scenarios.

[0257] The result display module includes:

[0258] Chart generation: The movie box office results predicted by the movie box office prediction model are presented to users in the form of charts, including line charts, bar charts, and pie charts;

[0259] Report generation: Automatically generate a comprehensive report based on the output data of the movie box office prediction model, including the predicted movie box office results, model performance indicators (such as mean square error, R 2 value) and related analysis description;

[0260] Box office growth prediction based on social communication paths: Combine social communication paths to predict the dynamic changes in movie box office and provide box office growth trends within a predetermined period of time in the future, expressed as:

[0261]

[0262] in, represents the box office growth based on social communication path analysis, is the predicted box office value at the current time t, and GrowthPrediction(t) is the predicted box office growth value after considering the social communication path;

[0263] Through the above content, the movie box office forecast results can be presented to users in the form of intuitive charts or detailed reports, and box office growth forecasts based on social communication paths can be provided, so that film distributors and marketing teams can have a more comprehensive understanding of the film’s market performance and future trends, providing data support for decision-making.

[0264] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0265] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A movie box office prediction system based on machine learning and big data, characterized in that: It includes data collection module, data processing and feature engineering module, social communication path prediction module, box office prediction module, model verification and optimization module and result display module, among which; The data collection module collects market data related to movie box office from multiple data sources, including historical box office data, social media feedback data, marketing activity data, and information on competing movies in the same period; The data processing and feature engineering module cleans and integrates the collected market data, and constructs a feature set based on factors that affect the movie box office, including movie type, director and actor influence, release time, budget size, and audience sentiment data; The social communication path prediction module simulates the information communication path and speed on social media and quantifies the influential nodes in the information communication process, specifically including: Social network construction: Construct a social network graph of movie-related topics, model users and information on social media platforms as nodes and edges, and form a dynamic social network structure; Propagation path tracking: Using dynamic graph neural network models, the propagation path of information in social networks is tracked in real time to identify the starting point of information propagation, influential nodes and its propagation direction; Propagation speed analysis: Calculate the speed at which information spreads in the social network structure, analyze the time required for information to spread from one node to another, and evaluate the propagation efficiency in combination with the breadth of the propagation path; Quantification of node influence: Based on the influential nodes in the information propagation path, the influence of each node in the information diffusion process is quantified. Combined with the node's connectivity and propagation ability, a node influence score is generated as the input feature for box office prediction; The box office prediction module combines the simulated information propagation path and speed to predict the movie box office through the movie box office prediction model; The model verification and optimization module verifies and optimizes the movie box office prediction model through cross-validation and adjusts the model parameters; The result display module presents the predicted movie box office results to the user in the form of charts or reports, and provides box office growth predictions based on social communication paths.

2. The movie box office prediction system based on machine learning and big data according to claim 1, characterized in that: The data collection module includes: Historical box office data interface: Through API connection with the movie box office database, historical box office data for each time period can be automatically obtained, including release time, total box office, and number of moviegoers; Social media data crawler: Use the public API of social media platforms to crawl social media feedback data related to movies in real time, including user comments, likes, reposts, and sentiment analysis results; Marketing activity data collection: Through the data interface connection with major advertising platforms and marketing channels, we can obtain the investment and effect data of movie marketing activities, including advertising click-through rate, exposure and interaction rate; Information collection tool for competing movies in the same period: Automatically collect relevant data of movies released at the same time as the target movie, including the box office performance, marketing strategies and audience evaluation of competing movies.

3. The movie box office prediction system based on machine learning and big data according to claim 1, characterized in that: The data processing and feature engineering module includes: Data cleaning: Use the Z-Score algorithm to clean the collected market data, identify and process abnormal data, missing data, and duplicate data; Data integration: Through multi-dimensional data alignment technology, market data from different sources are aligned and integrated in time and space; Feature construction: Based on the factors that affect the movie box office, a feature set is constructed, including: Movie genre features: One-hot encoding is used to convert the movie genre into multiple binary features to capture the impact of different movie genres on the box office; Director and actor influence characteristics: Based on historical box office data, the director or actor influence index I is calculated, expressed as: Among them, R i represents the box office revenue of the i-th movie, B i represents the budget of the i-th film, and n is the total number of films in which the director or actor has participated; Release time features: Convert release dates into holiday, weekend or weekday features, and identify the impact of release time on box office through time series analysis; Budget size feature: Through normalization, the budget size of the movie is converted into a comparative feature value, which is used to analyze the box office performance of movies with different budget sizes; Audience emotional characteristics: The sentiment analysis of social media feedback data is performed through natural language processing technology, and the sentiment tendency score is extracted as the sentiment feature. The audience sentiment index E is calculated by combining the sentiment intensity weighting, which is expressed as: Among them, S j is the sentiment score of the jth feedback, W j is the sentiment intensity weight, and m is the total number of feedbacks.

4. The movie box office prediction system based on machine learning and big data according to claim 1, characterized in that: The social network construction includes: Node definition and identification: Users on social media platforms and movie-related content are taken as nodes, where user nodes represent social media users and information nodes represent movie-related content; Definition and generation of edges: Based on the interactive relationship between users and the association between users and information nodes, edges are generated between nodes to form a preliminary social network graph. The weight of the edge is w uv It is expressed as: w uv =α·F uv +β·I ui +γ·S ii′ ; Among them, F uv represents the interaction frequency between user u and user v, I ui represents the association strength between user u and information node i, S ii′ represents the similarity between information node i and information node i′, α, β, γ are the corresponding weight coefficients; Dynamic social network update: Through the dynamic social network evolution model, the social network graph is updated in real time to capture the changes in the interactive relationships between users over time, and the weights of nodes and edges are dynamically adjusted to reflect the real-time social communication status, which is expressed as: IN t+1 = Yes t +ΔA t ; Among them, A t represents the adjacency matrix at time t, ΔA t Represents the change of network structure from time t to t+1; in, represents the probability of generating an edge between nodes u and v at time t+1, σ is the sigmoid function, is the feature vector of node u at time t, represents the feature vector of node v at time t, A t [u,v] is the element of the adjacency matrix at time t; Network structure optimization: When constructing a dynamic social network graph, the Louvain algorithm is used to optimize the social network graph, identify the community structure in the network, and improve the resolution and stability of the social network graph by optimizing the distribution of nodes and edges, which is expressed as: Where Q represents modularity, m is the number of edges in the network, and k u and k v are the degrees of nodes u and v respectively, A[u,v] is the value in the adjacency matrix, δ(c u ,c v ) is the indicator function.

5. The movie box office prediction system based on machine learning and big data according to claim 4, characterized in that: The propagation path tracking includes: Model construction: Build a dynamic graph neural network model to model the information propagation path that changes over time in social networks. Nodes represent users and information, and edges represent interactions between users or associations between users and information, expressed as: in, represents the hidden state of node u at time t+1, is the hidden state of node u at time t, is the set of neighbor nodes of node u, A t [u,v] is the element in the adjacency matrix at time t, W1, W2 and W3 are weight matrices, and σ is the activation function; Information propagation path tracking: By dynamically updating the hidden state of the node, the dynamic graph neural network model tracks the propagation path of information in the social network in real time, which can be expressed as: Among them, Active(u) represents the activation state of node u, and θ is the threshold; in, represents the propagation path at time t; Identification of the starting point of information dissemination and influential nodes: The dynamic graph neural network model identifies the starting point of information dissemination by analyzing the hidden state of the initial node. At the same time, the influential nodes that contribute to the diffusion of information during the dissemination process are quantified and identified through the change amplitude of the node hidden state and the cumulative impact in the propagation path, which is expressed as: u0=argmin u∈v {t u |Active(u)=1}; Among them, u0 is the initial node, t u is the activation time of node u, v is the set of all nodes; I u =∑ v∈v A t [u,v]·Active(v); Among them, I u represents the cumulative influence of node u, A t [u,v] represents the connection status between node u and node v, and Active(v) represents the activation status of node v; Propagation direction identification: By analyzing the changing trend of hidden states between nodes, the dynamic graph neural network model is used to infer the propagation direction of information in the social network, which is expressed as: Among them, D uv Indicates the direction of information propagation from node u to node v, sign is the sign function; in, represents the overall propagation direction at time t, and ε is the set of edges.

6. The movie box office prediction system based on machine learning and big data according to claim 5, characterized in that: The propagation velocity analysis includes: Propagation time calculation: by recording the time Δt required for information to propagate from node u to node v uv , and combined with the activation time of the node, calculate the propagation speed v of information from one node to the next node in the social network uv , expressed as: Among them, d uv is the graph distance between node u and node v; Breadth analysis of the propagation path: Analyze the breadth B(t) of the information propagation path in the network, expressed as: B(t)=∑ v∈v Active(v)·d uv ; Among them, Active(v) is the activation state of node v at time t; Propagation efficiency evaluation: Combine the propagation speed and breadth to evaluate the propagation efficiency of information in the entire social network, expressed as: in, represents the propagation path at time t, Represents a set of propagation paths The number of node pairs in v uv is the propagation speed of each pair of nodes in the path, and B(t) is the breadth of the propagation path.

7. The movie box office prediction system based on machine learning and big data according to claim 6, characterized in that: The node influence quantification includes: Node connectivity calculation: connectivity k of node u u It represents the number of connections between node u and other nodes in the social network, expressed as: k u =∑ v∈v A[u,v]; Among them, A[u,v] is the element in the adjacency matrix, and v is the set of all nodes; Node propagation capacity calculation: propagation capacity C of node u u The position and influence of the node in the propagation path are quantified and expressed as: Among them, Active(v) represents the activation state of node v; Node influence score calculation: influence score G of node u u It is quantified by combining its connectivity and propagation capabilities, expressed as: G u =α·k u +β·C u ; Among them, α and β are weight coefficients; Application of node influence in box office prediction: The generated node influence score G u As features of social communication paths, they serve as input for box office prediction.

8. The movie box office prediction system based on machine learning and big data according to claim 1, characterized in that: The movie box office prediction model adopts a Bayesian optimization neural network, which includes: Feature preprocessing and fusion: Normalize the social communication path, speed, and node influence features, and fuse them to generate the feature vector of the neural network input, expressed as: x fused =α·x path +β·x speed +γ·x influence ; Among them, x fused is the feature vector of the fused neural network input, x path 、x speed 、x influence They are social communication path characteristics, communication speed characteristics, and node influence characteristics, and α, β, and γ are fusion weights; Network structure design: Introduce a processing mechanism for social network characteristics into the neural network structure, expressed as: Input layer: h (0) =x fused ; Branched Hidden Layers: Among them, h (0) is the fused feature vector of the input layer, are the weight matrices of social communication path characteristics, communication speed characteristics, and node influence characteristics, respectively. They are the bias items of social communication path characteristics, communication speed characteristics, and node influence characteristics. are the outputs of social communication path characteristics, communication speed characteristics, and node influence characteristics, σ is the activation function, is the processed fusion feature vector; Box office prediction output: The fused features are input into the output layer to generate the final movie box office prediction results, expressed as: in, is the predicted movie box office value, and are the weight matrix and bias term of the output layer respectively; Feature importance analysis and feedback mechanism: Feature importance analysis and feedback mechanism are introduced to enhance the interpretability of the model and make feedback adjustments based on the prediction error, expressed as: Among them, I i Indicates the influence of the i-th fusion feature on the prediction result, is the i-th fusion feature, Δw i is the adjustment amount of the i-th feature weight, is the loss function, y is the real box office value, and η is the learning rate.

9. The movie box office prediction system based on machine learning and big data according to claim 8, characterized in that: The model verification and optimization module includes: Cross-validation process: The model validation and optimization module validates the movie box office prediction model through k-fold cross-validation, which is expressed as: Among them, CV k is the average error of k-fold cross validation, is the prediction error in the kth fold, is the predicted value on the k-fold validation set, y (i) is the true value of the k-th fold; Model parameter optimization: After completing cross-validation, minimize the average error CV of cross-validation k To adjust the model parameters, the model parameter optimization adopts the Bayesian optimization algorithm, which is expressed as: minutes θ CV k (θ)+λ·R(θ); Among them, θ represents the hyperparameter set of the model, CV k (θ) is the cross-validation mean error under the corresponding parameters, R(θ) is the regularization term of the hyperparameter, and λ is the regularization coefficient; Adaptive adjustment: During the model parameter optimization process, the model parameters are adjusted based on the gradient descent algorithm, which is expressed as: Among them, θ t+1 represents the model parameters after the next iteration, η is the learning rate, is the current parameter Δ t The gradient of the cross validation error under .

10. The movie box office prediction system based on machine learning and big data according to claim 1, characterized in that: The result display module includes: Chart generation: The movie box office results predicted by the movie box office prediction model are presented to users in the form of charts, including line charts, bar charts, and pie charts; Report generation: Automatically generate a comprehensive report based on the output data of the movie box office prediction model, including the predicted movie box office results, the model's performance indicators, and related analysis instructions; Box office growth prediction based on social communication paths: Combine social communication paths to predict the dynamic changes in movie box office and provide box office growth trends within a predetermined period of time in the future, expressed as: in, represents the box office growth based on social communication path analysis, is the predicted box office value at the current time t, and GrowthPrediction(t) is the predicted box office growth value after considering the social communication path.

Images