A big data-based intelligent operation management system for movie ticket sales

Abstract

The application relates to the technical field of movie ticket management, in particular to a movie ticket intelligent operation management system based on big data, which comprises a conversion capacity characterization quantity acquisition module, a reverse intensity index acquisition module, an order behavior fluctuation characteristic index acquisition module and a conversion rate acquisition module. The conversion capacity characterization quantity acquisition module is used for analyzing and acquiring conversion capacity characterization quantities of paid orders and locked seat orders in a current time window of a target session. The reverse intensity index acquisition module is used for recording orders with ticket refund and order change in the paid orders as reverse orders, and analyzing and acquiring reverse intensity indexes of the reverse orders in the current time window. The order behavior fluctuation characteristic index acquisition module is used for analyzing and acquiring order behavior fluctuation characteristic indexes of the paid orders and the reverse orders in the current time window. The conversion rate acquisition module is used for acquiring conversion risk factors of the current time window, and acquiring conversion rates of the current time window according to the conversion capacity characterization quantities and the conversion risk factors of the current time window. The application can improve the robustness of movie ticket management.

Description

Technical Field

[0001] This invention relates to the field of movie ticketing management technology, specifically to a big data-based intelligent operation and management system for movie ticketing. Background Technology

[0002] Existing movie ticketing operation and management systems are typically built on internet ticketing platforms. Their main functions include displaying movie information, managing showtimes, online seat selection, order generation, and payment processing. They also assist in the management of the movie screening process through statistical analysis of ticketing data. Structurally, these systems generally include a data acquisition module, an order processing module, and a statistical analysis module. The data acquisition module collects user action data during the ticket purchase process, including seat selection, seat reservation, and payment information. The order processing module handles order generation, payment confirmation, and order status updates. The statistical analysis module summarizes and statistically analyzes ticket sales for each showtime based on the generated order data, such as the number of tickets sold, the number of reserved seats, and the occupancy rate.

[0003] The system typically evaluates ticket sales for different films and screenings based on historical data or cumulative data at the current moment, providing data support for subsequent screening arrangements, seat management, and ticketing strategies. Specifically, the system often estimates potential demand by statistically analyzing the number of reserved seats and paid orders, combined with historical conversion rates, thereby forming a judgment on the demand situation for the current screening.

[0004] Traditionally, conversion rates are calculated by tracking and statistically analyzing seat-locking behavior within a preset statistical period, determining the percentage of seat-locking orders that ultimately result in payment. This percentage, representing the proportion of seat-locking orders that convert to payment orders, forms the "conversion rate," which is then used as a parameter to adjust demand for seat-locking behavior at the current moment. However, this approach has limitations in the current scenario. First, the conversion rate is derived from historical statistics, primarily reflecting the average level of past seat-locking behavior converted to payment. Directly applying this historical conversion rate to current seat-locking behavior for demand calculation can easily lead to discrepancies between the obtained effective demand and actual ticket purchase demand. Second, user ticketing behavior in the movie ticketing scenario is highly dynamic and time-varying. The conversion relationship between seat-locking behavior and payment varies significantly across different time periods, film popularity, and user behavior patterns. In this context, the conversion rate obtained through traditional methods fails to reflect the real-time changes in the current order behavior process and structure, making it difficult to accurately represent the actual ticket sales situation in the ticketing system, thus impacting the operation and management of movie ticketing. Summary of the Invention

[0005] To address the aforementioned technical problems, the present invention aims to provide a big data-based intelligent operation and management system for movie ticketing, the specific technical solution of which is as follows: One embodiment of the present invention provides a big data-based intelligent operation and management system for movie ticketing, the system comprising: The conversion capability representation module is used to set a time window and slide it with the length of the time window as the sliding step; a movie screening is recorded as the target screening; the conversion capability representation of the current time window is obtained by using the number of paid orders and the number of locked seats in the current time window of the target screening, as well as the time interval between the seat locking time and the payment time of the paid orders. The reversal strength index acquisition module is used to record paid orders that have been refunded or rescheduled as reversal orders; and to obtain the reversal strength index of the current time window by using the time interval between the refund or rescheduling time and the payment time of each reversal order within the current time window. The Order Behavior Fluctuation Characteristic Index Acquisition Module is used to obtain the order behavior fluctuation characteristic index for the current time window based on the ratio of the number of paid orders to the number of reverse orders within the current time window, as well as the standard deviation of the time interval between the refund or rescheduling time of each reverse order and the payment time. The conversion rate acquisition module is used to obtain the conversion risk factor of the current time window based on the reversal strength index and order behavior volatility characteristic index of the current time window; and to obtain the conversion rate of the current time window based on the conversion capability characterization quantity and conversion risk factor of the current time window.

[0006] Preferably, the conversion capacity of the current time window is obtained by utilizing the number of paid orders and locked seats within the current time window of the target session, as well as the time interval between the seat locking time and the payment time of paid orders, including: The instant conversion increment is obtained by dividing the number of paid orders in the current time window of the target session by the sum of the number of locked seats and the hyperparameter; the first mapping value is obtained by negatively mapping the mean of the time interval between the seat locking time and the payment time of each paid order using an exponential function with the natural constant as the base; the instant conversion increment and the first mapping value are added together to obtain the conversion capacity characterization of the current time window.

[0007] Preferably, the reversal strength index for the current time window is obtained by utilizing the time interval between the cancellation or rescheduling time and the payment time of each reversal order within the current time window, including: The median of the time interval between the lock-in time and the payment time for each order that has been paid within the current time window is obtained as the typical time interval. The time interval between the refund or rescheduling time and the payment time for a reversal order within the current time window is recorded as the reversal time interval of the reversal order. The second mapping value corresponding to the reversal order is obtained by negatively mapping the ratio of the reversal time interval to the sum of the typical time interval and the hyperparameters using an exponential function with the natural constant as the base. The mean value of the second mapping values ​​corresponding to each reversal order within the current time window is calculated to obtain the reversal intensity index of the current time window.

[0008] Preferably, the order behavior fluctuation characteristic index for the current time window is obtained based on the ratio of paid orders to rescheduled orders within the current time window and the standard deviation of the time interval between the refund or rescheduling time of each rescheduled order and the payment time, including: The reversal ratio is obtained by dividing the number of reversal orders in the current time window by the sum of the number of paid orders in the current time window and the hyperparameter; the order behavior fluctuation characteristic index of the current time window is obtained by adding the normalized value of the standard deviation of the time interval between the time of refund or rescheduling and the time of payment for each reversal order in the current time window.

[0009] Preferably, the conversion risk factor for the current time window is obtained based on the reversal strength index and the order behavior volatility characteristic index of the current time window, including: The transformation risk factor for the current time window is obtained by taking the mean of the normalized values ​​of the reversal strength index and the order behavior volatility characteristic index for the current time window.

[0010] Preferably, the conversion rate for the current time window is obtained based on the conversion capability representation and conversion risk factor of the current time window, including: The conversion rate of the current time window is obtained by multiplying the conversion capability representation of the current time window by the difference between the first preset value and the conversion risk factor.

[0011] The embodiments of this invention have at least the following beneficial effects: This application sets a time window and slides it with the length of the time window as the sliding step. By setting a time window, it realizes the dynamic characterization and correction of users' ticket purchase demand. Compared with the traditional fixed conversion rate model based on historical statistics or single time section data, it has higher timeliness and accuracy. Then, it uses the number of paid orders and the number of locked seats in the current time window of the target session, as well as the time interval between the seat locking time and the payment time of paid orders, to obtain the conversion capacity characterization quantity of the current time window. Then, it analyzes the order situation of users in the window to obtain the reversal strength index and order behavior fluctuation characteristic index of the current time window, and then obtains the conversion risk factor of the current time window. Finally, it obtains the conversion rate of the current time window based on the conversion capacity characterization quantity and the conversion risk factor of the current time window. This avoids the problem of demand misjudgment caused by ignoring the time evolution process in the traditional static statistical method. Moreover, the system can respond in real time to the behavioral changes (order situation changes) at different time stages in the ticket sales process, improve the system's perception ability and processing timeliness of order situation changes, and avoid the information lag problem caused by the traditional one-time statistical method. It effectively reduces the impact of data deviations caused by abnormal behavior, repetitive operations, or short-term fluctuations on the system's analysis results, enhances the system's robustness to changes in complex order situations, and thus improves the robustness of movie ticketing management. Attached Figure Description

[0012] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art 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.

[0013] Figure 1 This is a system block diagram of a big data-based intelligent operation and management system for movie ticketing, provided as an embodiment of the present invention. Detailed Implementation

[0014] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a big data-based intelligent operation and management system for movie ticketing proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0015] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0016] The following description, in conjunction with the accompanying drawings, details a specific solution for a big data-based intelligent operation and management system for movie ticketing provided by this invention.

[0017] In this embodiment, the main application scenario of the present invention is: this application is mainly used for the management of movie ticket sales.

[0018] Please see Figure 1 The diagram illustrates a system block diagram of a big data-based intelligent operation and management system for movie ticketing provided by an embodiment of the present invention. The system includes the following modules: The conversion capability representation module is used to set a time window and slide it with the length of the time window as the sliding step; a movie screening is recorded as the target screening; the conversion capability representation of the current time window is obtained by using the number of paid orders and the number of locked seats in the current time window of the target screening, as well as the time interval between the seat locking time and the payment time of the paid orders.

[0019] First, ticket sales data for each movie screening needs to be collected. This can be done by obtaining order flow data from the ticketing system database (such as the order table and status change log table) or business interfaces. This data includes, but is not limited to: order identification information (order ID); screening / movie identification information; order creation time (seat locking time); order status (seat locked, paid, refunded, rescheduled); and status change time (payment time, refund time, rescheduled time, etc.). For the data obtained above, orders lacking crucial time information should be deleted, obviously abnormal time records should be removed (such as payment time earlier than seat locking time), and duplicate records should be eliminated. Since order statuses may differ across systems, a unified mapping is needed. For example, different types of "seat locked status" should be unified as "seat locked," different payment methods should be unified as "paid," and refunds and cancellations should be unified as "reversal behavior," etc.

[0020] Let any given screening be designated as the target screening. For each order since ticket sales for the target screening began, the order information needs to be organized, its behavioral paths analyzed, and an order behavior sequence constructed chronologically. This sequence is then initially categorized according to screening information. For example, for a movie screening in the target screening, the time-series behavior of each order is obtained, including the time-series behavior of order i. ,in, Indicates the type of order action (seat lock / payment / refund / rescheduling, etc.). Indicates the time when the action occurs, and satisfies A represents the session information, thus providing sufficient data for subsequent analysis.

[0021] Furthermore, a time window needs to be set. The length of the time window can be set according to different needs. Considering that movie ticketing behavior has obvious short-term clustering characteristics, that is, seat locking, payment and reversal behavior usually occur in a short period of time, the preset time window is preferably set to one hour. Then, the time window length is used as the sliding step to slide on the time axis, and then the order situation within the time period corresponding to the time window is analyzed.

[0022] First, by obtaining a quantitative measure of the conversion rate from seat-locking to payment behavior for the target session within the current time window, this measure is used to characterize the activity and trend of this conversion, thereby reflecting the conversion momentum of potential ticket purchase demand—that is, characterizing the "capacity" of conversion from seat-locking to payment behavior within the current time window. The purpose of this section is to quantify the activity and development trend of the conversion from seat-locking to payment behavior in the target session, starting from the order behavior process, providing a basis for determining the subsequent conversion rate.

[0023] Therefore, the conversion capacity of the current time window is represented by the number of paid orders and the number of locked seats in the target session within the current time window, as well as the time interval between the seat locking time and the payment time of paid orders.

[0024] Specifically, the instant conversion increment is obtained by dividing the number of paid orders in the current time window of the target session by the sum of the number of locked-in orders and the hyperparameter; the first mapping value is obtained by negatively mapping the mean of the time interval between the locked-in time and the payment time of each paid order using an exponential function with the natural constant as the base; the instant conversion increment and the first mapping value are added together to obtain the conversion capacity characterization of the current time window.

[0025] The specific calculation model for the conversion capacity characterization is as follows: , in, This represents the conversion capability of the target session at time t within the time window (the current time window), where time t is the last moment of the time window and is used as the identifier of the time window. This function is used to reflect the activity level and conversion momentum of seat-locking behavior into payment behavior within the current time window for a target session, representing the ability of potential demand to be converted into actual transactions in the current order behavior. exp is an exponential function with the natural constant as its base, and exp(-) represents an inverse proportional normalization function, which restricts the target output result to [0,1]. This ensures that the larger the final output result, the more active and rapid the conversion of seat-locking behavior into payment behavior, indicating that the ticket purchase demand for the current session has a strong conversion momentum. and These are the number of paid orders (orders that have completed payment) and the number of locked seats within the current time window, respectively. The number of locked seats refers to the number of orders that have completed payment and the number of orders that have completed seat locking within the current time window (the number of locked seats includes all orders with "seat locking" behavior, including those that have completed payment). The number of paid orders is the number of orders that have completed payment. This represents the instantaneous conversion increment within the current time window. By calculating the ratio between the growth of payment behavior and the growth of lock-up behavior within the current time window, it reflects the degree of conversion of new lock-up behavior into payment behavior. When the growth of payment and the growth of lock-up behavior maintain a high matching relationship, it indicates that the new lock-up behavior can be effectively converted into payment behavior, indicating an enhanced conversion trend. Conversely, it indicates that there are many unconverted parts in the new lock-up behavior, and the conversion trend is weakened. ε represents the hyperparameter, which is an infinitesimal value to prevent the denominator from being 0. This indicates the payment time of order i that has been paid within the current time window. This indicates the lock-in time for order i that has been paid within the current time window. This represents the average time interval from order locking to payment within the current time window, where P represents the set of orders that have completed payment within the current time window. The first mapping value is the average time interval. The shorter the average time interval, the larger the first mapping value, which means that users can complete the payment faster after locking in their seats. This indicates that users have a clearer intention to buy tickets and have a stronger interest in the movie or show. In this case, the seat-locking behavior is closer to the actual ticket purchase demand than a tentative seat-holding or short-term observation behavior.

[0026] The reversal strength index acquisition module is used to record paid orders that have been refunded or rescheduled as reversal orders; and to obtain the reversal strength index of the current time window by using the time interval between the refund or rescheduling time and the payment time of each reversal order within the current time window.

[0027] The above-mentioned method of characterizing the conversion ability of seat-locking behavior to payment behavior in the target session by obtaining conversion capability representation can only reflect the activity level and development trend of the conversion process within the current time window. However, the result mainly focuses on the occurrence process of conversion behavior. Since payment behavior may still be subject to subsequent reversal behaviors such as ticket refunds or rescheduling in actual business, some completed conversions are not stable.

[0028] Therefore, it is also necessary to identify and quantify the stability and effectiveness of payment behavior from the subsequent evolution of order behavior, thereby correcting the deviation caused by focusing solely on the conversion process and providing constraints and correction basis for determining the final conversion rate. Thus, it is necessary to identify behaviors of rescheduling or refunding after payment within the current time window. This application records paid orders that have undergone refunds or rescheduling as reverse orders, and obtains reverse orders within the current time window.

[0029] Next, the reversal strength index of the current time window is obtained by using the time interval between the time of ticket refund or rescheduling and the time of payment for each reversal order within the current time window.

[0030] Specifically, the median of the time interval between the lock-in time and the payment time of each order that has been paid within the current time window is obtained as the typical time interval; the time interval between the refund or rescheduling time and the payment time of a reversal order within the current time window is recorded as the reversal time interval of the reversal order; the second mapping value corresponding to the reversal order is obtained by negatively mapping the ratio of the reversal time interval to the sum of the typical time interval and the hyperparameters using an exponential function with the natural constant as the base; the mean value of the second mapping values ​​corresponding to each reversal order within the current time window is calculated to obtain the reversal intensity index of the current time window.

[0031] The specific calculation model for the reversal strength index is as follows: , in, The reversal intensity index for the target session at time t (the current time window) characterizes the overall intensity of reversal behavior among completed payment orders for the target session within the current time window. Its calculation incorporates an exponentially decaying weight based on the time interval between payment and reversal, ensuring that earlier reversals have a greater impact on the overall index. This effectively distinguishes the differences in the impact of different reversals on the stability of conversion results. A higher output value indicates more reversals among completed payment orders within the current time window, with a significant portion occurring shortly after payment, suggesting higher instability in conversion results and a risk of overestimating actual demand. Conversely, a lower output value indicates fewer reversals or those occurring more frequently after payment, indicating higher stability in conversion results and a more accurate reflection of the actual ticket demand level for the current session (reversal behavior: refunds or changes after payment). This refers to the time when the i-th reversal order within the current time window is refunded or rescheduled, which is also the time when the reversal occurs. Let i be the payment time for the i-th reverse order. The time interval between the time of cancellation or rescheduling of the reversed order and the time of payment is also known as the reversal time interval. The typical time interval represents the median time interval between the lock time and the payment time for all orders that have been paid within the current time window, reflecting the typical time interval from "locking the seat" to "paying". This value is used to characterize the degree of time deviation of the reversal behavior of the reversal order relative to the normal ticket purchase decision cycle. The smaller the value, the faster the reversal behavior occurs compared to the normal ticket purchase decision cycle, indicating that the stability of the conversion behavior is poor. This value is also used as the weight index of the order in the global calculation. The contribution unit of each reversal event is the same (i.e., 1), so it is not reflected in the formula. P represents the set of orders that have been paid within the current time window, R represents the number of reversal orders within the current time window, and ε represents the hyperparameter, which is an infinitesimal value to prevent the denominator from being 0.

[0032] The Order Behavior Fluctuation Characteristic Index Acquisition Module is used to obtain the order behavior fluctuation characteristic index for the current time window based on the ratio of the number of paid orders to the number of reversal orders within the current time window, as well as the standard deviation of the time interval between the refund or rescheduling time of each reversal order and the payment time.

[0033] The above has obtained the reversal situation of orders that have completed payment within the current time window. Further analysis is needed on the situation when orders that have completed payment are reversed.

[0034] Therefore, the order behavior fluctuation characteristic index for the current time window is obtained based on the ratio of paid orders to rescheduled orders within the current time window and the standard deviation of the time interval between the refund or rescheduling time of each rescheduled order and the payment time.

[0035] Specifically, the reversal ratio is obtained by dividing the number of reversal orders in the current time window by the sum of the number of paid orders in the current time window and the hyperparameter; the order behavior fluctuation characteristic index of the current time window is obtained by adding the normalized value of the standard deviation of the time interval between the time of refund or rescheduling of each reversal order in the current time window and the time of payment.

[0036] The specific calculation model for the order behavior fluctuation characteristic index is as follows: , in, The order behavior fluctuation characteristic index for the target session at time t (the current time window) is used to characterize the fluctuation of paid orders for the target session in subsequent behavior within the current time window; Norm() represents the normalization function, which restricts the target output result to [0,1]. The larger the final output result, the higher the proportion of reversed behavior among paid orders within the current time window, indicating that the payment result is more likely to be canceled or adjusted; on the other hand, the larger the fluctuation of the time interval between order payment and order rescheduling or refund among reversed orders, the higher the fluctuation of the time spent on the behavior adjustment process after payment for a single order, indicating that the user's ticket purchase decision lacks stability, the order conversion result has high uncertainty, the conversion result of the target session has poor stability and strong uncertainty, and the actual effective ticket purchase demand may be overestimated; R represents the number of paid orders within the current time window, and R represents the number of reverse orders within the current time window. The inversion ratio is represented by ε, which is a hyperparameter and an infinitesimal value to prevent the denominator from being zero. The larger the inversion ratio, the larger the proportion of orders that fail to maintain their original transaction status after payment is completed. This indicates that the "final certainty" of the payment behavior is weaker and the stability of the actual transaction is worse. This is the standard deviation of the time interval between the time of refund or rescheduling and the time of payment for each reversal order within the current time window. In other words, it is the standard deviation of the reversal time interval for each reversal order. When the reversal time interval fluctuates greatly, it indicates that the reversal behavior is more dispersed in the time dimension, and the time of reversal for different orders varies greatly. This indicates that the conversion behavior within this time window is highly unstable, reflecting that the user decision-making process has strong volatility and uncertainty, user behavior has strong differences, and the consistency of the conversion process is low.

[0037] The conversion rate acquisition module is used to obtain the conversion risk factor of the current time window based on the reversal strength index and order behavior volatility characteristic index of the current time window; and to obtain the conversion rate of the current time window based on the conversion capability characterization quantity and conversion risk factor of the current time window.

[0038] The above obtained the reversal strength index and order behavior volatility characteristic index for the current time window. Furthermore, the two are fused to obtain the conversion risk factor for the current time window.

[0039] Specifically, the transformation risk factor for the current time window is obtained by taking the mean of the normalized values ​​of the reversal strength index and the order behavior volatility characteristic index for the current time window.

[0040] The specific calculation model for the conversion risk factor is as follows: , in, The conversion risk factor for the target session within the current time window; This is an index representing the volatility characteristics of order behavior within the time window (current time window) of the target session at time t. This is to normalize it, thereby ensuring The value range is from 0 to 1; The reversal intensity index is the time window (current time window) of the target event at time t. The reversal strength index primarily characterizes the overall intensity of reversal behavior among completed payment orders within the current time window, focusing on reflecting the "scale and timeliness" of reversal behavior. The order behavior volatility index, on the other hand, characterizes the volatility of reversed orders in subsequent behavior, focusing on reflecting the "complexity and frequency of change" of the behavior process at the individual order level. In the movie ticketing scenario, the instability of conversion results depends not only on the quantity of reversal behavior but also on the volatility characteristics within the reversal behavior itself. This means it may manifest as a small number of orders with repeated changes, or a large number of orders with a single change. Therefore, a single indicator cannot comprehensively reflect conversion risk. Thus, conversion instability is comprehensively characterized from two dimensions: "group occurrence intensity" and "individual behavior complexity."

[0041] The conversion risk factor is used to comprehensively characterize the degree of instability risk of paid orders in the target session during subsequent behavior. The larger the output of this factor, the higher the proportion of reversal behavior among the paid orders in the target session, and the earlier the reversal behavior occurs and the greater the volatility of the duration of the process, thus indicating that the payment conversion results still exhibit strong instability and volatility after they are formed.

[0042] This indicates that some payment transactions were cancelled or adjusted within a short period of time, reflecting a lack of sustainability in the conversion results; on the other hand, the high degree of fluctuation in the duration of the order reversal process reflects the instability of the user's decision-making process.

[0043] Finally, the conversion rate for the current time window is obtained based on the conversion capability representation and the conversion risk factor. Specifically, the conversion rate for the current time window is obtained by multiplying the conversion capability representation by the difference between a first preset value and the conversion risk factor, where the first preset value is 1.

[0044] The specific model for calculating conversion rate is as follows: , In the formula, The conversion rate of the target session in the current time window is also the conversion rate at the last moment t of the current time window.

[0045] in, As a metric for conversion capability, this indicator primarily reflects the activity level of converting seat-locking behavior into payment behavior within the current time window. However, it only characterizes the conversion from the perspective of "whether the conversion has occurred," failing to distinguish which of the converted behaviors are stable and effective demands, and which may be withdrawn or adjusted later. Therefore, a conversion risk factor is introduced. It is used to characterize the degree of reversal and behavioral fluctuation in subsequent stages of completed payment orders, and introduces "conversion reliability weight" to modulate conversion capability.

[0046] pass The final conversion rate model is constructed in the form of [the model]. It can be considered a stability coefficient of conversion results, used to represent the proportion of conversion behaviors in the target session that can be considered effective and reliable. When the conversion risk factor increases, the corresponding stability coefficient decreases, thus weakening the conversion ability; when the conversion risk factor is small, the impact on the conversion ability is small, making the final result closer to the actual ticket purchase demand level.

[0047] In summary, after obtaining the final conversion rate of the target screening within the current time window through the above operations, this rate is used as a core parameter representing the intensity of actual ticket purchase demand and input into the movie ticketing operation management module. Regarding screening management, based on the final conversion rate of different screenings, theater screening resources are dynamically allocated, ensuring that screenings with higher conversion rates receive more screenings, while screenings with lower conversion rates or significant instability are optimized or have their screenings reduced, thereby improving the utilization efficiency of theater resources. Regarding ticket price management, ticket prices are dynamically adjusted based on the final conversion rate. Regarding seat resource management, by analyzing the relationship between the final conversion rate and seat-locking behavior, seat-locking duration and seat-occupancy strategies are optimized to reduce the occupation of seat resources by ineffective seat locks and improve seat turnover efficiency.

[0048] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this specification. Additionally, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0049] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0050] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart operation and management system for movie ticketing based on big data, characterized in that, The system includes: The conversion capability representation module is used to set a time window and slide it with the length of the time window as the sliding step; a movie screening is recorded as the target screening; the conversion capability representation of the current time window is obtained by using the number of paid orders and the number of locked seats in the current time window of the target screening, as well as the time interval between the seat locking time and the payment time of the paid orders. The reversal strength index acquisition module is used to record paid orders that have been refunded or rescheduled as reversal orders; and to obtain the reversal strength index of the current time window by using the time interval between the refund or rescheduling time and the payment time of each reversal order within the current time window. The Order Behavior Fluctuation Characteristic Index Acquisition Module is used to obtain the order behavior fluctuation characteristic index for the current time window based on the ratio of the number of paid orders to the number of reverse orders within the current time window, as well as the standard deviation of the time interval between the refund or rescheduling time of each reverse order and the payment time. The conversion rate acquisition module is used to obtain the conversion risk factor of the current time window based on the reversal strength index and order behavior volatility characteristic index of the current time window; and to obtain the conversion rate of the current time window based on the conversion capability characterization quantity and conversion risk factor of the current time window.

2. The intelligent operation and management system for movie ticketing based on big data according to claim 1, characterized in that, The method of obtaining the conversion capacity characteristic of the current time window by utilizing the number of paid orders and locked seats within the current time window of the target session, as well as the time interval between the seat locking time and the payment time of paid orders, includes: The instant conversion increment is obtained by dividing the number of paid orders in the current time window of the target session by the sum of the number of locked seats and the hyperparameter; the first mapping value is obtained by negatively mapping the mean of the time interval between the seat locking time and the payment time of each paid order using an exponential function with the natural constant as the base; the instant conversion increment and the first mapping value are added together to obtain the conversion capacity characterization of the current time window.

3. The intelligent operation and management system for movie ticketing based on big data according to claim 1, characterized in that, The method of obtaining the reversal strength index of the current time window by utilizing the time interval between the refund or rescheduling time and the payment time of each reversal order within the current time window includes: The median of the time interval between the lock-in time and the payment time for each order that has been paid within the current time window is obtained as the typical time interval. The time interval between the refund or rescheduling time and the payment time for a reversal order within the current time window is recorded as the reversal time interval of the reversal order. The second mapping value corresponding to the reversal order is obtained by negatively mapping the ratio of the reversal time interval to the sum of the typical time interval and the hyperparameters using an exponential function with the natural constant as the base. The mean value of the second mapping values ​​corresponding to each reversal order within the current time window is calculated to obtain the reversal intensity index of the current time window.

4. The intelligent operation and management system for movie ticketing based on big data according to claim 1, characterized in that, The method of obtaining the order behavior fluctuation characteristic index for the current time window based on the ratio of paid orders to rescheduled orders within the current time window and the standard deviation of the time interval between the refund or rescheduling time of each rescheduled order and the payment time includes: The reversal ratio is obtained by dividing the number of reversal orders in the current time window by the sum of the number of paid orders in the current time window and the hyperparameter; the order behavior fluctuation characteristic index of the current time window is obtained by adding the normalized value of the standard deviation of the time interval between the time of refund or rescheduling and the time of payment for each reversal order in the current time window.

5. The intelligent operation and management system for movie ticketing based on big data according to claim 1, characterized in that, The conversion risk factors for the current time window are obtained based on the reversal strength index and order behavior volatility characteristic index, including: The transformation risk factor for the current time window is obtained by taking the mean of the normalized values ​​of the reversal strength index and the order behavior volatility characteristic index for the current time window.

6. The intelligent operation and management system for movie ticketing based on big data according to claim 1, characterized in that, The process of obtaining the conversion rate for the current time window based on the conversion capability representation and conversion risk factor of the current time window includes: The conversion rate of the current time window is obtained by multiplying the conversion capability representation of the current time window by the difference between the first preset value and the conversion risk factor.

Images