A cinema surrounding product layout method and system based on ticket purchase information atlas assistance

Abstract

The application belongs to the field of cinema systems and provides a cinema surrounding product layout method and system based on ticket purchase information graph assistance, which comprises constructing a graph based on ticket purchase information; constructing a commodity node to represent a cinema surrounding product; when a shopping behavior occurs, the corresponding path weight is increased by 1; after a user orders a movie ticket, real-time ticket purchase information is acquired, a corresponding commodity list is acquired according to the path, the commodities are sorted according to the path weight when the maximum path weight is not less than a preset value, and the sorted commodity recommendation list is displayed to the user; if the maximum path weight is less than the preset value, the movie type is acquired according to the movie name, the latest released same-type movie is acquired according to the movie type, the commodities are sorted according to the path weight of the same-type movie, and the sorted commodity recommendation list is displayed to the user; after the movie is released, the corresponding movie name node and the associated path are deleted in the graph.

Description

Technical Field

[0001] This invention belongs to the field of cinema systems, and specifically relates to a method and system for the layout of cinema peripheral products based on ticket purchase information maps. Background Technology

[0002] With the rapid development of the cinema industry, audiences' demand for peripheral products (such as food, beverages, and movie merchandise) during movie viewings is increasing. How to accurately recommend cinema-related products, enhance the audience's consumption experience, and simultaneously improve cinema sales conversion rates has become a crucial issue of concern for the industry.

[0003] Traditional personalized recommendation systems typically require collecting information such as a user's gender, age, movie preferences, and past spending history to build a user profile and generate personalized recommendations. However, during the movie ticket purchase process, users are not required to provide their real names, making it difficult for the system to directly obtain basic user attribute data. Furthermore, the same device or account may be shared by different users, making it difficult to guarantee the accuracy of account-based user profiles. This information gap significantly limits the application of existing recommendation methods in movie theater scenarios.

[0004] Furthermore, existing technologies commonly employ machine learning or deep learning models for product recommendation, such as collaborative filtering, matrix factorization, deep neural networks (DNNs), and graph neural networks (GNNs). These methods typically require large amounts of training data and complex model training and parameter optimization processes to achieve high recommendation accuracy. However, in practical applications of cinema-related product recommendations, the amount of data is relatively limited, especially in the early stages of a single cinema or a particular film's release, where data sparsity is a serious problem. Moreover, training and deploying machine learning models often requires significant computing resources, increasing the difficulty of system implementation and operational costs, making it difficult for some cinemas to promote and apply these methods in their actual operations.

[0005] Furthermore, the release cycle of a film is typically short, making its popularity highly uncertain. The vast majority of films are released for only 30 to 60 days, with some even reaching their peak box office period within a few weeks, followed by a rapid decline in screenings. Because a film's market performance is influenced by various factors, such as word-of-mouth, cast, marketing strategies, and competing films, its popularity is difficult to predict accurately. Even with pre-release predictions using historical data or box office forecasting models, it's challenging to accurately grasp the market performance of an individual film. Traditional prediction methods, such as time series analysis and regression models, usually require extensive data accumulation, which is insufficient for short-term films. Some films may experience a box office reversal after release due to positive word-of-mouth, while others may suffer a rapid decline due to market competition or negative reviews. This unpredictability makes recommendation systems based on historical box office data or fixed models ill-suited to adapt to market changes. Summary of the Invention

[0006] To address the problems in the existing technology, this invention provides a method for the layout of cinema peripheral products based on ticket purchase information maps, comprising the following steps:

[0007] A graph is constructed based on ticket purchase information. The nodes of the graph include: movie name node, time period node, number of people node, ticket price node, and seat area node. The connection relationships between the nodes are as follows: movie name node is connected to time period node, time period node is connected to number of people node, number of people node is connected to ticket price node, and ticket price node is connected to seat area node.

[0008] Construct product nodes to represent cinema-related products. When a shopping behavior occurs, establish connections between movie name nodes, time slot nodes, number of people nodes, ticket price nodes, seat area nodes and product nodes. Each time a shopping behavior occurs, the corresponding path weight increases by 1.

[0009] When a user places an order for movie tickets, the system obtains the movie name, time slot, number of people, ticket price, and seat area information in real time. Based on the path of movie name-time slot-number of people-ticket price-seat area, the system obtains the corresponding product list. When the maximum path weight is not less than a preset value, the products are sorted according to the path weight, and the sorted product recommendation list is displayed to the user.

[0010] If the maximum path weight is less than the preset value, the movie type is obtained based on the movie name, and the most recently released movies of the same type are obtained based on the movie type. The products are sorted according to the path weight of the movies of the same type, and the sorted product recommendation list is displayed to the user.

[0011] After a movie's theatrical run ends, the corresponding movie name node and its associated paths are deleted from the graph.

[0012] This invention also provides a cinema peripheral product layout system based on ticket purchase information map assistance, including the following modules:

[0013] The first construction module is used to construct a graph based on ticket purchase information. The nodes of the graph include: movie name node, time period node, number of people node, ticket price node, and seat area node. The connection relationships between the nodes are as follows: movie name node is connected to time period node, time period node is connected to number of people node, number of people node is connected to ticket price node, and ticket price node is connected to seat area node.

[0014] The second construction module is used to construct product nodes, representing products around the cinema. When a shopping behavior occurs, a connection is established between the movie name node, time period node, number of people node, ticket price node, seat area node and product node. Each time a shopping behavior occurs, the corresponding path weight increases by 1.

[0015] The recommendation module is used to obtain movie name, time slot, number of people, ticket price, and seat area information in real time after a user places an order for movie tickets. Based on the path of movie name-time slot-number of people-ticket price-seat area, it obtains the corresponding product list. When the maximum path weight is not less than a preset value, the products are sorted according to the path weight and the sorted product recommendation list is displayed to the user. If the maximum path weight is less than the preset value, the movie type is obtained based on the movie name, and the most recently released movies of the same type are obtained based on the movie type. The products are then sorted according to the path weight of the movies of the same type and the sorted product recommendation list is displayed to the user.

[0016] The cleanup module is used to delete the corresponding movie name node and its associated paths from the graph after the movie's theatrical run ends.

[0017] Furthermore, if no corresponding shopping behavior occurs within a set time period, the path weight is exponentially decayed to prevent outdated data from affecting product recommendations.

[0018]

[0019] in This represents the weight at time t+1. This represents the weight at time t.

[0020] Furthermore, the generated ticket purchase information map is visualized;

[0021] The ticket purchase information graph is displayed using a node-edge structure, where:

[0022] Movie title nodes use different colors or icons to distinguish different types of movies;

[0023] Time periods are presented in a timeline format;

[0024] The number of people, ticket price, and seating area are displayed in a hierarchical layout.

[0025] Product nodes are labeled with size or color based on purchase frequency and correlation strength to highlight high-demand products;

[0026] Based on the path weights of ticket purchase and shopping behaviors, adjust the thickness, transparency, or color of the edges in the graph to reflect different association strengths.

[0027] Furthermore, if the maximum weight of the current movie is less than the preset weight, the product recommendation weight of the current movie will be adjusted according to the following rules:

[0028] Set an inheritance weight coefficient α to control the weight inheritance ratio and calculate the inheritance path weight:

[0029] W i, ′ j =αW similar,i,j +(1-α)W current,i,j

[0030] Among them, W i, ′ j These are the weights ultimately used for recommendation ranking;

[0031] W similar,i,j The product path weight for recently released movies of the same type;

[0032] W current,i,j This represents the weight of the original product path for the current movie.

[0033] Furthermore, after a movie's theatrical run ends, the corresponding movie name node and its associated paths are deleted from the graph. Based on the movie's purchase records, high-frequency products associated with that movie are extracted and stored in the historical recommendation database.

[0034] This invention provides a method and system for the layout of cinema-related products based on ticket purchase information maps, overcoming the following shortcomings of existing technologies in cinema scenarios, and having the following beneficial effects:

[0035] This method constructs a graph based on ticket purchase information, using only ticket purchase behavior data such as movie name, time period, number of people, ticket price, and seat area, without needing to obtain sensitive information such as users' gender, age, and historical movie viewing records, and can achieve accurate recommendations in non-real-name ticket purchase environments.

[0036] It is applicable to all moviegoers, whether they are first-time ticket buyers or regular moviegoers, and can generate effective product recommendations based on the current ticket purchase behavior.

[0037] This method utilizes the path weighting mechanism of the ticket purchase information graph to make recommendations based on existing ticket purchase-shopping relationships, even with limited data. It is applicable to single cinemas or newly released movies, and even with limited data, it can infer highly relevant peripheral products based on the graph structure, avoiding the ineffective recommendation problem of traditional recommendation methods in data-sparse situations.

[0038] This invention updates product recommendation results in real time based on path weights, enabling the recommendation system to adapt to the influence of factors such as different movies, time periods, and seating areas on consumer behavior. After purchasing tickets, the system can instantly calculate the weight of the current ticket purchase information path and recommend the most relevant products, significantly improving the accuracy of recommendations and user acceptance.

[0039] This method employs a graph-based dynamic weight adjustment strategy, eliminating the need to predict movie popularity in advance. Even with newly released or less popular movies, it can still make recommendations based on historical consumption data of similar films.

[0040] When the ticket purchase-shopping path of the current movie has a low weight, the consumption pattern of the recently released movies of the same type can be automatically inherited to avoid recommendation failure due to insufficient data and improve the generalization ability of the system.

[0041] In summary, this method solves the problems of missing user information, data sparsity, and difficulty in film market prediction caused by non-real-name ticket purchases in existing technologies by constructing a ticket purchase information graph, updating path weights, adjusting dynamic recommendations, and inheriting data from similar films. It can accurately recommend products around cinemas under limited data conditions, thereby improving the operating efficiency of cinemas and the consumption experience of audiences. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0044] The invention will now be described in preferred form with reference to the accompanying drawings and specific embodiments.

[0045] This embodiment solves the above problems through the following steps:

[0046] In one embodiment, reference Figure 1This invention provides a method for the layout of cinema-related products based on ticket purchase information maps. It combines moviegoers' ticket purchase behavior, consumption preferences and cinema sales data to intelligently optimize the display and layout of cinema-related products.

[0047] Specifically, this method includes the following steps:

[0048] A graph is constructed based on ticket purchase information. The nodes of the graph include: movie name node, time period node, number of people node, ticket price node, and seating area node. The connection relationships between the nodes are as follows: the movie name node is connected to the time period node.

[0049] The time period node is connected to the number of people node, the number of people node is connected to the ticket price node, and the ticket price node is connected to the seating area node.

[0050] A graph is constructed based on ticket purchase information, and the nodes of the graph include:

[0051] Movie Name Node: Represents the movie name involved in the ticket purchase. Each movie is an independent node, reflecting the audience's ticket purchase and consumption behavior for different movies.

[0052] Time period nodes: These indicate the time interval for purchasing tickets or watching movies, such as "weekday daytime", "weekday evening", "weekend afternoon", "weekend evening", etc., to distinguish the impact of different time periods on users' ticket purchasing and consumption habits.

[0053] The time period when audiences purchase tickets directly affects their consumption patterns, for example:

[0054] Early morning events may attract students and the elderly, whose consumption preferences tend to favor low-priced foods.

[0055] Evening sessions are likely to be frequented by office workers and couples, who tend to purchase premium packages or related products.

[0056] Time-based analysis can help determine the impact of different time periods on the sales of products related to cinemas, and optimize product recommendation strategies for different screenings.

[0057] Number of people node: Indicates the number of people watching the movie corresponding to each ticket purchase order, such as single person watching the movie, two people watching the movie, or multiple people watching the movie (such as family watching the movie).

[0058] The number of ticket buyers determines users' consumption preferences, for example:

[0059] People going to the movies alone may be more inclined to buy a light meal, such as a cup of coffee or a small bucket of popcorn.

[0060] Couples watching a movie may purchase a couples' package or two drinks.

[0061] Groups or families tend to buy family packages or even movie merchandise (such as children's toys) when watching movies together.

[0062] Audience metrics can be used to analyze the characteristics of audience groups at different times, in order to develop targeted product recommendation strategies.

[0063] Ticket price nodes: These indicate the price category of the tickets purchased by users, such as "low price (discounted ticket)", "medium price (regular 2D ticket)" and "high price (IMAX / 4DX ticket)", to measure the relationship between ticket prices and users' spending power.

[0064] Ticket prices reflect users' spending power, and the number of people buying tickets also influences ticket price choices.

[0065] Students or price-sensitive users are more likely to choose lower-priced tickets (such as group discount tickets).

[0066] Couples and moviegoers may choose regular tickets or premium seats (such as IMAX tickets).

[0067] Families may opt for mid-priced movie packages or family theaters.

[0068] Ticket price nodes help analyze the differences in consumption of surrounding products between high-ticket users and low-ticket users, and optimize product layout.

[0069] Seating area node: Indicates the seating area selected by the user when purchasing tickets, such as "front row", "middle row", "back row" or "VIP seat", to reflect the user's movie-watching habits and consumption behavior.

[0070] Seat selection reflects a user's movie-watching preferences and may also influence their spending power.

[0071] Users who choose VIP seats are usually willing to pay extra for premium food or movie merchandise.

[0072] Users who choose the front row may be more inclined to opt for lower ticket prices and are more price-sensitive.

[0073] Viewers who choose the middle row may place more emphasis on the viewing experience and be more willing to purchase package deals.

[0074] Seating area nodes can optimize the layout of merchandise inside the cinema, for example, prioritizing the placement of high-end food and limited-edition movie merchandise near IMAX theaters or VIP areas.

[0075] Construct product nodes to represent cinema-related products. When a purchase occurs, establish connections between the movie name node, time slot node, number of people node, ticket price node, seat area node, and product node. Each time a purchase occurs, the corresponding path weight increases by 1.

[0076] When a ticket purchase occurs, obtain information such as movie name, time period, number of people, ticket price, and seat area, and establish corresponding movie name node, time period node, number of people node, ticket price node, and seat area node in the ticket purchase information graph.

[0077] When a shopping behavior occurs, a connection relationship is established between movie name node, time period node, number of people node, ticket price node, seat area node and product node in the ticket purchase information graph, so that the shopping behavior can be reflected in the graph as the association between product node and ticket-related nodes.

[0078] In the ticket purchase information graph, a path weight parameter W is defined. i,j This is used to characterize the strength of the purchase association between ticket information nodes and product nodes.

[0079] Whenever a viewer makes a purchase after buying a ticket, the weight of the corresponding path in the ticket purchase information graph is adjusted, increasing the path weight by 1.

[0080] W i,j =W i,j +1

[0081] Optionally, if no corresponding shopping behavior occurs within a set time period, the path weight is exponentially decayed to prevent outdated data from affecting product recommendations.

[0082]

[0083] in This represents the weight at time t+1. This represents the weight at time t.

[0084] The accumulation of path weights can be used to calculate the popularity of different products, optimize product layout and recommendation strategies.

[0085] Using the methods described above, cinemas can achieve intelligent product recommendations and layout optimization based on ticket purchase behavior, thereby improving the audience's consumption experience and increasing the sales conversion rate of cinema-related products.

[0086] Furthermore, the generated ticket information graph is visualized to intuitively display the relationship between movie name, time period, number of people, ticket price, seat area and product, and provides dynamic interactive functions to support data analysis and optimization decision-making.

[0087] The ticketing information graph is displayed intuitively using a node-edge structure, where:

[0088] Movie title nodes use different colors or icons to distinguish different types of movies;

[0089] Time periods are presented in a timeline format to allow for observation of ticket purchase and consumption trends at different times;

[0090] The number of attendees, ticket prices, and seating areas are presented in a hierarchical layout to reveal the impact of audience characteristics on shopping behavior.

[0091] Product nodes are labeled with size or color based on purchase frequency and correlation strength to highlight high-demand products.

[0092] The atlas can be arranged in a force-oriented layout, a hierarchical layout, or a circular layout to optimize the visualization effect.

[0093] Based on the path weights of ticket purchase and shopping behaviors, adjust the thickness, transparency, or color of the edges in the graph to reflect different levels of association strength:

[0094] Paths with higher weights can be displayed with thicker, darker edges to highlight strong correlations;

[0095] Paths with lower weights can be displayed as thinner, semi-transparent, or dashed lines to reduce visual clutter;

[0096] Dynamically adjust path colors or animation effects to demonstrate the real-time impact of ticket purchasing behavior on product recommendations.

[0097] Through the visualization methods described above, cinema managers can intuitively understand the relationship between ticket purchases and the consumption of peripheral products, improve data analysis efficiency, and thus optimize the recommendation strategy and layout plan for cinema peripheral products.

[0098] When a user places an order for movie tickets, the system obtains the movie name, time slot, number of attendees, ticket price, and seating area information in real time. Based on the path of movie name-time slot-number of attendees-ticket price-seating area, the system retrieves the corresponding product list. When the maximum path weight is not less than a preset value, the products are sorted according to the path weight, and the sorted product recommendation list is displayed to the user.

[0099] After a user places an order for movie tickets, the purchase information is obtained in real time, and key information from the user's purchase is collected, including:

[0100] Movie title, time slot, number of attendees, ticket price, and seating area are obtained through the cinema's ticketing system, online ticketing platform, or cinema self-service terminal, and stored in real time in the ticketing information graph database.

[0101] In the ticket purchase information map, based on the movie name-time period-number of people-price-seat area path, all product lists associated with the ticket purchase information are retrieved. The product list includes food products, movie merchandise and souvenirs.

[0102] In the ticket purchase information graph, each product node is connected to a ticket purchase information node, and their relevance is represented by path weight.

[0103] Calculate the path weight of all product nodes in the ticket purchase information graph. The larger the path weight, the higher the frequency of purchase of the product under the same ticket purchase information.

[0104] Determine if the maximum path weight is greater than a preset threshold T:

[0105] If the maximum path weight is greater than or equal to T, the products are sorted in descending order according to the path weight, and the sorted product recommendation list is displayed to the user.

[0106] If the maximum path weight is less than T, a recommendation strategy based on movies of the same type is executed to improve the rationality and accuracy of the recommendations.

[0107] The sorted product recommendation list can be displayed on the following channels:

[0108] Online ticketing platform: After the user completes the ticket purchase, a product recommendation page pops up, displaying sorted products;

[0109] Cinema self-service ticket machines: During the ticket collection process, personalized product recommendations are displayed based on the ticket purchase information;

[0110] Cinema App / Mini Program: Push personalized product recommendations to users after they purchase tickets;

[0111] Theater entrance screen: Based on screening information, popular products are dynamically displayed in the theater entrance area.

[0112] If a user chooses to purchase a recommended product, the path weight corresponding to the product node in the ticket purchase information graph will increase by 1.

[0113] If a user does not purchase the recommended product, the path weight remains unchanged, but the recommendation strategy can be adjusted in subsequent analysis to optimize the product recommendation effect.

[0114] If the maximum path weight is less than the preset value, the movie type is obtained based on the movie name, and the most recently released movies of the same type are obtained based on the movie type. The products are then sorted according to the path weight of the movies of the same type, and the sorted product recommendation list is displayed to the user.

[0115] If the maximum path weight is less than the preset value, it means that the movie's release time is too short and there is not enough data to support it. In this case, further optimization of product recommendations will be carried out based on the movie type.

[0116] Based on the movie title purchased by the current user, search the movie database or ticket information map to obtain the movie genre (such as science fiction, action, comedy, animation, etc.);

[0117] In the ticketing information map, the most recently released movies under this type are retrieved. The most recently released movies can be determined according to the following rules:

[0118] Filter by release date and select the movie closest to the current time;

[0119] Filter by box office or audience ratings, and select the most popular movies in the same genre;

[0120] Based on ticket purchase data, select movies with a high number of purchase records in the ticket purchase information graph.

[0121] Based on the recently released similar films, retrieve their product recommendation paths in the ticketing information graph and obtain the corresponding path weights.

[0122] Alternatively, the following rules may be used to adjust the product recommendation weight of the current movie:

[0123] Set an inheritance weight coefficient α to control the weight inheritance ratio and calculate the inheritance path weight:

[0124] W i, ′ j =αW similar,i,j +(1-α)W current,i,j

[0125] Among them, W i, ′ j These are the weights ultimately used for recommendation ranking;

[0126] W similar,i,j The product path weight for recently released movies of the same type;

[0127] W current,i,j This represents the weight of the original product path for the current movie.

[0128] The inheritance coefficient α can be dynamically adjusted based on historical data.

[0129] Based on the adjusted path weights, the product list is sorted in descending order, and a recommended product list is displayed to the user.

[0130] In this step, given the limited current movie shopping activity, supplementary recommendation information is provided based on historical purchase data of popular movies of the same genre, thereby improving the reliability and accuracy of the recommendations.

[0131] By inheriting the product recommendation weights from similar movies, the recommended products are more aligned with user preferences, thus optimizing the shopping experience.

[0132] By using the path weights of recently released movies, the recommendation system can adapt to market trends in real time, avoiding the drawbacks of fixed recommendation strategies.

[0133] After a movie's theatrical run ends, the corresponding movie name node and its associated paths are deleted from the graph.

[0134] Monitor the screening status of movies to determine whether they have reached their end date or have been removed from the cinema schedule; mark movies that have finished screening based on information from the cinema management system or movie database.

[0135] In the ticketing information graph, locate the movie title node for movies that have finished showing;

[0136] Remove all paths associated with the movie name node in sequence, including:

[0137] The connection between the movie title node and the time segment node;

[0138] The connection between the movie name node and the number of people node;

[0139] The connection between the movie title node and the ticket price node;

[0140] The connection between the movie name node and the seat area node;

[0141] The connection between movie title nodes and product nodes;

[0142] Completely delete the movie name node to free up storage resources and improve graph query efficiency.

[0143] At the same time, based on the purchase records of movies that have finished their theatrical run, high-frequency products associated with those movies are extracted and stored in the historical recommendation database; when similar movies are released in the future, the product recommendation weight of the movies that have finished their theatrical run will be inherited first, so as to optimize the product recommendation list of newly released movies.

[0144] On the other hand, the present invention also provides a cinema peripheral product layout system based on ticket purchase information map assistance, including:

[0145] The first construction module is used to construct a graph based on ticket purchase information. The nodes of the graph include: movie name node, time period node, number of people node, ticket price node, and seat area node. The connection relationship between each node is as follows: movie name node is connected to time period node, time period node is connected to number of people node, number of people node is connected to ticket price node, and ticket price node is connected to seat area node.

[0146] The second construction module is used to construct product nodes, representing products around the cinema. When a shopping behavior occurs, a connection is established between the movie name node, time period node, number of people node, ticket price node, seat area node and product node. Each time a shopping behavior occurs, the corresponding path weight increases by 1.

[0147] The recommendation module is used to obtain movie name, time slot, number of people, ticket price, and seat area information in real time after a user places an order for movie tickets. Based on the path of movie name-time slot-number of people-ticket price-seat area, it obtains the corresponding product list. When the maximum path weight is not less than a preset value, the products are sorted according to the path weight and the sorted product recommendation list is displayed to the user. If the maximum path weight is less than the preset value, the movie type is obtained based on the movie name, and the most recently released movies of the same type are obtained based on the movie type. The products are then sorted according to the path weight of the movies of the same type and the sorted product recommendation list is displayed to the user.

[0148] The cleanup module is used to delete the corresponding movie name node and its associated paths from the graph after the movie's theatrical run ends.

[0149] For any module structures not specifically defined in this invention, the existing technical descriptions shall prevail. The prior art mentioned in the foregoing background and specific embodiments sections can be considered part of this invention and used to understand the meaning of certain technical features or parameters.

Claims

1. A method for the layout of cinema peripheral products based on ticket purchase information maps, characterized in that, The method includes the following steps: A graph is constructed based on ticket purchase information. The nodes of the graph include: movie name node, time period node, number of people node, ticket price node, and seat area node. The connection relationships between the nodes are as follows: movie name node is connected to time period node, time period node is connected to number of people node, number of people node is connected to ticket price node, and ticket price node is connected to seat area node. Construct product nodes to represent cinema-related products. When a shopping behavior occurs, establish connections between movie name nodes, time slot nodes, number of people nodes, ticket price nodes, seat area nodes and product nodes. Each time a shopping behavior occurs, the corresponding path weight increases by 1. When a user places an order for movie tickets, the system obtains the movie name, time slot, number of people, ticket price, and seat area information in real time. Based on the path of movie name-time slot-number of people-ticket price-seat area, the system obtains the corresponding product list. When the maximum path weight is not less than a preset value, the products are sorted according to the path weight, and the sorted product recommendation list is displayed to the user. If the maximum path weight is less than the preset value, the movie type is obtained based on the movie name, and the most recently released movies of the same type are obtained based on the movie type. The products are sorted according to the path weight of the movies of the same type, and the sorted product recommendation list is displayed to the user. After a movie's theatrical run ends, the corresponding movie name node and its associated paths are deleted from the graph. If no corresponding shopping behavior occurs within a set time period, the path weight is exponentially decayed to prevent outdated data from affecting product recommendations. Visualize the generated ticket purchase information map; The ticket purchase information graph is displayed using a node-edge structure, where: Movie title nodes use different colors or icons to distinguish different types of movies; Time periods are presented in a timeline format; The number of people, ticket price, and seating area are displayed in a hierarchical layout. Product nodes are labeled with size or color based on purchase frequency and correlation strength to highlight high-demand products; Based on the path weights of ticket purchase and shopping behaviors, adjust the thickness, transparency, or color of the edges in the graph to reflect different association strengths; If the maximum weight of the current movie is less than the preset weight, the product recommendation weight of the current movie will be adjusted according to the following rules: Set an inheritance weight coefficient α to control the weight inheritance ratio and calculate the inheritance path weight: ， Among them, W i ,′ j The weights used for final recommendation ranking; W similar ,i ,j The product path weight for recently released movies of the same genre; W current ,i ,j The weight of the original product path for the current movie; the inheritance coefficient α can be dynamically adjusted based on historical data.

2. The method for cinema peripheral product layout based on ticket purchase information map assistance according to claim 1, characterized in that, After a movie's theatrical run ends, the corresponding movie name node and its associated paths are deleted from the graph. Then, based on the purchase records of the movie after its theatrical run, high-frequency products associated with that movie are extracted and stored in the historical recommendation database.

3. A cinema peripheral product layout system based on ticket purchase information map assistance, characterized in that, The system includes the following modules: The first construction module is used to construct a graph based on ticket purchase information. The nodes of the graph include: movie name node, time period node, number of people node, ticket price node, and seat area node. The connection relationship between each node is as follows: movie name node is connected to time period node, time period node is connected to number of people node, number of people node is connected to ticket price node, and ticket price node is connected to seat area node. The second construction module is used to construct product nodes, representing products around the cinema. When a shopping behavior occurs, a connection is established between the movie name node, time period node, number of people node, ticket price node, seat area node and product node. Each time a shopping behavior occurs, the corresponding path weight increases by 1. The recommendation module is used to obtain movie name, time slot, number of people, ticket price, and seat area information in real time after a user places an order for movie tickets. Based on the path of movie name-time slot-number of people-ticket price-seat area, it obtains the corresponding product list. When the maximum path weight is not less than a preset value, the products are sorted according to the path weight and the sorted product recommendation list is displayed to the user. If the maximum path weight is less than the preset value, the movie type is obtained based on the movie name, and the most recently released movies of the same type are obtained based on the movie type. The products are then sorted according to the path weight of the movies of the same type and the sorted product recommendation list is displayed to the user. The cleanup module is used to delete the corresponding movie name node and its associated paths from the graph after the movie's theatrical run ends. If no corresponding shopping behavior occurs within a set time period, the path weight is exponentially decayed to prevent outdated data from affecting product recommendations. Visualize the generated ticket purchase information map; The ticket purchase information graph is displayed using a node-edge structure, where: Movie title nodes use different colors or icons to distinguish different types of movies; Time periods are presented in a timeline format; The number of people, ticket price, and seating area are displayed in a hierarchical layout. Product nodes are labeled with size or color based on purchase frequency and correlation strength to highlight high-demand products; Based on the path weights of ticket purchase and shopping behaviors, adjust the thickness, transparency, or color of the edges in the graph to reflect different association strengths; If the maximum weight of the current movie is less than the preset weight, the product recommendation weight of the current movie will be adjusted according to the following rules: Set the inheritance weight coefficient α to control the weight inheritance ratio and calculate the inheritance path weight; ， Among them, W i ,′ j The weights used for final recommendation ranking; W similar ,i ,j The product path weight for recently released movies of the same genre; W current ,i ,j The weight of the original product path for the current movie; the inheritance coefficient α can be dynamically adjusted based on historical data.

4. The cinema peripheral product layout system based on ticket purchase information map assistance according to claim 3, characterized in that, After a movie's theatrical run ends, the corresponding movie name node and its associated paths are deleted from the graph. Then, based on the purchase records of the movie after its theatrical run, high-frequency products associated with that movie are extracted and stored in the historical recommendation database.

Images