CN112907264A

CN112907264A - Ticket data processing method and device

Info

Publication number: CN112907264A
Application number: CN201911133405.1A
Authority: CN
Inventors: 沈开明; 韩啸天
Original assignee: Shanghai Taopiaoer Information Technology Co ltd
Current assignee: Shanghai Taopiaoer Information Technology Co ltd
Priority date: 2019-11-19
Filing date: 2019-11-19
Publication date: 2021-06-04

Abstract

The application relates to a ticket data processing method and device. The method comprises the following steps: ticket data of a plurality of cinemas are obtained; ticket data of the plurality of cinemas are respectively input to ticket prediction model components matched with the cinemas, and parameter values of ticket target parameters corresponding to the cinemas are output through the ticket prediction model components; wherein the ticket prediction model component is configured to be trained using a correspondence between historical ticket data and reference ticket data of the theater. Through the mode described in each embodiment of the application, on one hand, the accuracy of minimum granularity prediction data can be realized by following the difference of each cinema behavior, and on the other hand, the future behavior of each cinema can be predicted by using the historical behavior of each cinema, the stability of each cinema behavior is followed, and the prediction accuracy is improved.

Description

Ticket data processing method and device

Technical Field

The present application relates to the field of big data processing technologies, and in particular, to a ticket data processing method and apparatus.

Background

The prediction of the movie box office becomes an important reference item for investment of the international movie industry, and has a strong guiding function on pricing of movie products, development of derivative products and the like. 10/2/2015, the movie box office in the special capital office is on line on a real-time data platform, the special capital office belongs to the national radio and television bureau and is responsible for counting the movie box offices in the whole country, and the cinema lines in the whole country are almost covered. For a long time, thousands of cinemas in the country report the data of film box rooms, people times, field times and the like to a receiving platform of proprietary filing in real time, so that the authoritative data of the film box rooms in China are obtained through arrangement, and therefore, the data of the proprietary filing is the only and accurate data source of the film box rooms in China at present.

However, data provided by the funded movie box office real-time data platform is often updated once a day, and for a user who wants to know box office data in real time, the update period is long, and the real-time requirement is difficult to meet. In addition, the movie box office real-time data platform provides historical data, and cannot provide box office prediction data.

Therefore, there is a need in the art for a way to provide real-time box-office data and predictive box-office data quickly and accurately.

Disclosure of Invention

In order to overcome the problems in the related art, the application provides a ticket data processing method and device.

The ticket data processing method and device provided by the embodiment of the application are specifically realized as follows:

a method of ticketing data processing, the method comprising:

ticket data of a plurality of cinemas are obtained;

ticket data of the plurality of cinemas are respectively input to ticket prediction model components matched with the cinemas, and parameter values of ticket target parameters corresponding to the cinemas are output through the ticket prediction model components;

wherein the ticket prediction model component is configured to be trained using a correspondence between historical ticket data and reference ticket data of the theater.

A ticketing data processing apparatus comprising a processor and a memory for storing processor-executable instructions that when executed by the processor implement:

ticket data of a plurality of cinemas are obtained;

A non-transitory computer readable storage medium, wherein instructions of the storage medium, when executed by a processor, enable the processor to perform the ticket data processing method.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application.

According to the ticket data processing method and device, the parameter value of the ticket target parameter of each cinema can be predicted firstly, and then the box office data of each film can be obtained through statistics according to the parameter value of the ticket target parameter, so that fine-grained statistics from bottom to top can be realized, and the accuracy of a prediction result can be improved. In addition, in the process of predicting the parameter values of the ticket business target parameters of each cinema, model components matched with each cinema can be used for prediction, and the model components are obtained by training through historical ticket business data of the cinemas. On one hand, the accuracy of minimum granularity prediction data can be realized by following the difference of each cinema behavior, on the other hand, the future behavior of each cinema can be predicted by using the historical behavior of each cinema, the stability of each cinema behavior is followed, and the prediction accuracy is improved. Finally, the box office data of each film can be accurately counted and obtained through the parameter values of the ticket business target parameters obtained according to the embodiments of the application, and a strong guiding effect is generated for investment and financing of the film industry, pricing of film products, development of derivative products and the like.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.

FIG. 1 is a schematic diagram illustrating an application scenario in accordance with an exemplary embodiment.

Fig. 2 is a flow diagram illustrating a method of ticket data processing according to an example embodiment.

Fig. 3 is a block diagram illustrating a ticket data processing apparatus according to an exemplary embodiment.

Detailed Description

Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

In order to facilitate those skilled in the art to understand the technical solutions provided in the embodiments of the present application, the following non-limiting application scenarios of movie ticket management will describe a technical environment for implementing the technical solutions.

At present, there are many movie ticket distribution channels in the market, typically cat eyes, panning tickets, sticky rice movies, micro tickets, etc., and these distribution channels can be directly connected to most of the cinemas in the country, so as to sell movie tickets of each cinema to users. Theoretically, each distribution channel provider has a direct connection relationship with most of cinemas throughout the country, so that each distribution channel provider can realize statistics of parameters such as the field number, the ticket price, the number of people and the like of each cinema. However, in practice, the data collected by each distribution channel has a large error with the data reported to the professional sponsorship by the cinema. For example, when a movie theater packages a certain session of a movie to a certain company, the number of persons in the session is full (assuming that the number of persons is 100) from the statistical data of distribution channel provider, and the ticket price is 50 yuan per actual bid, then the box office of the session is 5000. However, since the package yard has a large uncertainty, for example, although the company is in the cinema package yard, the number of persons actually present at the end is only 60, i.e., the number of actual persons in the yard is 60. And, because of the package, the user may enjoy the fare privilege, such as to fold the fare by 7, that is, the actually collected single fare is 35 yuan, and the package price is 3500 yuan. Thus, the data reported by the distribution channel to the funding office is: the number of seats is 60, and the box office is 3500.

Of course, the above example is only one aspect of the error between the distribution channel provider and the professional funding data reported from the cinema, and of course, there are errors caused by a plurality of aspects such as service fee difference and member discount. Thus, predicting real-time data reported to the funding at each theater has been a difficult problem.

In one embodiment, the real-time data reported to the funding professional in the cinema can be predicted by using a mode based on a stability coefficient, and the mode mainly comprises the following five steps:

step 1: selecting some credible cinemas with small errors of schedule capturing data and proprietary fund data from the direct-connected cinemas;

step 2: capturing data according to the historical schedule of the credible cinema, and counting to obtain the credible cinema box office X₁Trusted theatre session Y₁And according to the historical schedule capturing data of the direct-connected cinema, counting to obtain the scene Y of the direct-connected cinema₂Large disc ticket house X for historical special capital₂；

And step 3: calculate historically daily X₁、Y₁、X₂、Y₂A stability factor μ constructed for predicting future daily μ values, the stability factor μ being calculated by the formula:

μ＝(X₂/Y₂)/(X₁/Y₁)

and 4, step 4: in the real-time prediction process, the real-time credible cinema box office X can be obtained₁', real-time credible cinema session Y₁', real-time direct-connected cinema field Y₂', calculating to obtain the real-time large-disk box office predicted value X₂' is:

X₂’＝μ(X₁’/Y₁’)Y₂’

and 5: calculating the ratio of each film box office in a trusted cinema (direct-connected cinema), and multiplying the ratio by the real-time large-disc box office predicted value X₂' the box office predicted value of each film can be obtained.

However, the above embodiment has at least the following technical problems such as:

(1) the predicted mu values on different dates have large fluctuation, so that the stability of the prediction result is not high;

(2) the ratio fluctuation of the trusted cinema in the direct-connected cinema is large, so that the prediction error of the box office predicted value of the final film is large;

(3) the low-latitude box office data (cinema, city and region) is directly summarized direct cinema value, which is greatly different from national dimension and is not proper.

Based on the above technical requirements, the ticket data processing method provided by each embodiment of the application can respectively predict future behaviors of the directly connected cinema by using the historical behaviors, so that prediction from a time dimension can be realized, and the accuracy of box office prediction is greatly improved.

The following describes a ticket data processing method provided in various embodiments of the present application through a specific application scenario.

The prediction of the film box-office has very important significance in each stage, before the film is shown, a investor prepares to release a film, the prediction of the film box-office can estimate the return on investment in advance, and effective risk control can be realized. And in the film release period, advertising and marketing are carried out on the film, and effective cost control can be realized if different marketing schemes can be made according to the predicted film box-office scale. During the showing period of the film, intelligent film arrangement can be performed according to the estimation result of the box office, and the goal of benefit maximization is approached. Therefore, the real-time and accurate prediction of the movie box office plays an important role for relevant users.

Fig. 1 is a flowchart of a ticket data processing method according to an embodiment of the present application. As shown in fig. 1, ticket prediction model components corresponding to each theater can be trained, and the model components are hereinafter referred to as modules. The ticket prediction module is set to be obtained by training according to the corresponding relation between the historical ticket data and the reference ticket data of each cinema, and in China, data which is specially funded and disclosed on a movie box office real-time data platform can be used as the reference ticket data. In addition, the ticket business prediction module can also comprise a person number prediction module, a ticket price prediction module, a service fee prediction module and other sub-modules, parameters such as the person number, the ticket price, the service fee and the like can be obtained through smaller granularity prediction, and the complexity and the training difficulty of the ticket business prediction module can be reduced.

Before the ticket business prediction module is used for acquiring data of people number, ticket price, service fee and the like of the cinema, the data related to the people number, the ticket price and the service fee and the like of each cinema can be acquired. Then, the data of the number of people, the ticket price, the service fee and the like can be predicted according to the field. In addition, the prediction dimension can include real-time prediction and future prediction, wherein the implementation prediction can utilize the result predicted by the data of the showing session on the day during the showing period, and the future prediction can utilize the result predicted by the pre-sale data, namely the data of the showing session, such as the number of people, the ticket price, the service fee and the like on the second day at 21 o' clock before.

As shown in fig. 1, after acquiring data of each theater, statistical data corresponding to each movie can be obtained through statistics. For example, after prediction results such as the number of persons, the price of tickets, and the service fee of the movie a of day 7 and 3 in 2019 at each theater are obtained, data such as the total box office, the total number of persons, and the total service fee of the movie a of day 7 and 3 in 2019 can be obtained statistically.

However, the box office data of the above movie a is based only on the prediction results obtained by the direct cinema of the ticketing distributor, and not on the prediction results of all theaters nationwide. For example, a ticket vendor has 9000 direct theaters, but the total number of theaters in the country is 10000, so that 1000 additional boxes are predicted to determine the large disc outcome of movie a. Based on this, the final large-disc result of the film a can be obtained by using the total ticket house prediction module.

The following describes the ticket data processing method in detail with reference to the accompanying drawings. Fig. 2 is a schematic method flow diagram of an embodiment of a ticket data processing method provided in the present application. Although the present application provides method steps as shown in the following examples or figures, more or fewer steps may be included in the method based on conventional or non-inventive efforts. In the case of steps where no necessary causal relationship exists logically, the order of execution of the steps is not limited to that provided by the embodiments of the present application. The method can be executed sequentially or in parallel (for example, in the context of a parallel processor or a multi-thread process) according to the method shown in the embodiment or the figures when the ticket data processing process or the device is executed in practice.

Specifically, an embodiment of a ticket data processing method provided in the present application is shown in fig. 2, where the method may include:

s201: ticket data for a plurality of theaters is obtained.

S203: ticket data of the plurality of cinemas are respectively input to ticket prediction model components matched with the cinemas, and parameter values of ticket target parameters corresponding to the cinemas are output through the ticket prediction model components;

In the embodiment of the present application, ticket data of a plurality of cinemas may be acquired, wherein the plurality of cinemas may include cinemas to which movie ticket distribution channels can be directly connected, which will be referred to as direct-connected cinemas hereinafter. Since the distribution channel can have a relationship directly connected to the plurality of theaters, ticket data of the plurality of theaters can be acquired. The ticketing data may include people data, ticket price data, service fee data, sales data, etc. for various theatres. Then, the ticket data may be input to a ticket prediction model component, and parameter values of ticket objective parameters corresponding to the theater may be output via the ticket prediction model component, wherein the ticket prediction model component is matched with the theater. As described above, there may be a large difference between the data displayed by the cinema on the platform of the distribution channel provider and the data reported to the exclusive office, so that the various embodiments of the present application may at least predict the data reported by the cinema to the exclusive office, and the corresponding ticket objective parameter may include at least one of the number of people, the ticket price, and the service fee.

In an actual application environment, the data displayed on the platform of the distribution channel by different cinemas is different from the data reported to the proprietor, some of the data displayed on the platform by different cinemas may have no difference from the data reported to the proprietor, and others may have a larger difference, so that the ticketing prediction model components of the plurality of cinemas can be set respectively. Wherein the ticket prediction model component may be configured to be trained using a correspondence between historical ticket data and reference ticket data of the theater. The benchmark ticketing data may include data reported to the national specialization office at a cinema, i.e., the specialization office discloses data on the movie box office real-time data platform. Of course, the benchmark ticketing data is not limited to data disclosed by proprietary sponsorship, and may include data disclosed by any platform with benchmark reference value, and the application is not limited thereto.

In the course of training the ticket prediction model component, historical ticket data for the theater as well as baseline ticket data may be obtained. From the perspective of distribution channel, the historical ticketing data can be directly obtained from the ticketing platform, and the benchmark ticketing data can be obtained from a platform with reference value such as a proprietary office. After the historical ticket data of the cinema and the reference ticket data are acquired, the historical ticket data can be input into the built ticket prediction model component to generate a prediction result. Then, based on the difference between the prediction result and the reference ticket data, the training parameters may be iteratively adjusted until the difference meets a preset requirement. In one example, ticket data of each session of JY cinema of 12 months and 25 days in 2018 is captured by a certain ticketing platform TP, table 1 is a comparison table of historical ticket data and reference ticket data, as shown in table 1, the historical ticket data may include the number of sold tickets, the number of reserved tickets, the number of unavailable tickets, a ticket price, a service fee and the like of each session, where the number of sold tickets is the number of sold tickets, the number of reserved tickets is the number of sold tickets in a predetermined manner, often a package field or a large number of tickets, the number of persons actually arriving at the field may be less than the number of reserved tickets, the ticket price is the price calibrated for a movie of the session, and the service fee is the calibrated service fee for a movie of the session. The baseline ticketing data can include the number of people, ticket prices, service fees, etc. that the theater actually reports to a reference platform (e.g., a funding office).

As shown in Table 1, the total ticket rooms statistically obtained according to the historical ticket data and the reference ticket data are different in the JY cinema in three times from 12:55 to 13: 10. For example, in a 12:55 session, the predetermined number of persons is 80, which may be the case of a package, the number of persons actually arriving is 65, so the number of persons reported to the reference platform is also 65, and in addition, the cinema is online and can give a discount to the user 7, so the calculated box office is 80, 50, 0.7, 2800, the average fare is 2800/65, 43.1, the total service fee is 80, 3, 0.7, 168, the average service fee is 168/65, 2.58, which is different from the number of persons, fare and service fee obtained by the platform. In the 13:00 session, the predetermined number of people is 10, but the actual number of people is 7, and the theater may offer a 9-fold benefit, such that the actual number of people is 42, the box office is 35 + 45+10 + 45 0.9-1980 dollar, the average fare is 1980/42-47.1 dollars, the total service fee is 35 + 3-0.9-132 dollars, and the average service fee is 132/42-3.1 dollars. In the 13:10 session, although there is no predetermined ticket, some users have members of the theater, so the actual payment can also be discounted, therefore, the box room reported to the reference platform by the theater is 2268 yuan, the average fare is 59.7 yuan, and the data captured by the ticketing platform TP is also different.

TABLE 1 History ticketing data and reference ticketing data comparison Table

It should be noted that the ticket prediction model component may include a model component trained by using a machine learning manner. The machine learning mode can also comprise a K nearest neighbor algorithm, a perception machine algorithm, a decision tree, a support vector machine, a logistic background regression, a maximum entropy and the like, and correspondingly, the generated model components such as naive Bayes, hidden Markov and the like. Of course, in other embodiments, the machine learning manner may further include a deep learning manner, a reinforcement learning manner, and the like, and the generated model component may include a Convolutional Neural Network model Component (CNN), a Recurrent Neural Network model component (RNN), LeNet, ResNet, a Long-Short Term Memory Network model component (LSTM), a bidirectional Long-Short Term Memory Network model component (Bi-LSTM), and the like, which is not limited herein.

In the example shown in table 1, the historical ticket data mainly relates to the number of people (including the number of sold, reserved and unsold tickets), the ticket price, the service fee and the like in each session, and correspondingly, the reference ticket data mainly comprises the number of people, the ticket price and the service fee. Thus, in various embodiments of the present application, the ticketing prediction model component can be divided into a people prediction model subcomponent, a fare prediction model subcomponent, a service fee prediction model subcomponent, and the like. The person number prediction model subcomponent is used for determining the person number of the single-scene movie, the fare prediction model subcomponent is used for determining the fare of the single-scene movie, and the service fee prediction model subcomponent is used for determining the service fee of the single-scene movie. In the embodiment of the application, the ticket prediction model component is divided into a plurality of sub-components for processing, so that the complexity of the model can be reduced, and the processing efficiency of the model can be improved.

The training of these sub-components is described below by taking the human prediction model sub-components as an example. Firstly, sample data is obtained, and the people data of a single-session movie can be respectively extracted from the historical ticket data and the reference ticket data. The historical ticket data may include data related to the number of persons in the table 1, such as sold, reserved, or unsold, and the corresponding reference ticket data is the number of persons in the same session. As in Table 1, the training objective for the human data (0,80, 0) in the 12:55 session is 65, the training objective for the human data (35,10,2) in the 13:00 session is 42, and the training objective for the human data (0,0,60) in the 13:10 session is 38. After the sample data is obtained, the people data in the historical ticketing data can be input into the constructed people prediction model sub-assembly, and a prediction result is generated. Then, iterative adjustment can be performed on training parameters in the people prediction model sub-component based on the difference between the prediction result and the people data in the reference ticketing data until the difference meets the preset requirement. It should be noted that the scale of the input data may be set according to the computing power of the people prediction model subcomponent, and in one example, people data of different times of each day in 30 days of a certain cinema may be used as the input of the people prediction model subcomponent, and the corresponding training targets are people data disclosed by a reference platform of the same time. Of course, the input data may be data of any number of days, such as 7 days, 15 days, etc., and the application is not limited herein.

The training modes of the fare prediction model sub-component and the service fee prediction model sub-component are the same as the training mode of the people prediction model sub-component, and are not repeated here. In the process of extracting the fare data of a single session of movie from the reference data, as shown in table 1, the data of the room of the ticket may be divided by the data of the number of people, and the training target of 12:55 sessions is that the average fare is 2800/65 ═ 43.1 yuan. Similarly, in the process of training the service charge prediction model subcomponent, the training target is the total service charge divided by the number of people data, and the training target for the 12:55 session is the average service charge 168/65-2.58 yuan.

In the embodiment of the application, after the ticket prediction model component (including the people prediction model subcomponent, the ticket price prediction model subcomponent and the service fee prediction model subcomponent) is obtained through training, the parameter value of the ticket target parameter can be obtained by using the ticket prediction model component. In the embodiment of the application, the predicted dimension may include historical data prediction and future data prediction. The historical data prediction may include a result predicted by using the historical data, for example, a result of the current day may be predicted by using data of a field that has been shown on the current day. The future data forecast may include results from utilizing future data forecasts, which may include data in an unmapped pre-sale state, and the like.

It should be noted that, in the prediction method based on the stability factor described in the first embodiment of the present application, a set of stability factors (i.e., μ values) needs to be set for the historical data prediction and the future data prediction, respectively, and the operation and maintenance cost is high. However, in the embodiment of the application, the trained ticket prediction model component can be suitable for historical data prediction and future data prediction, and is low in operation and maintenance cost and high in adaptability.

In the embodiment of the application, after the parameter values of the ticketing object parameters of each cinema are obtained, at least one statistical data of the target film can be obtained according to the parameter values of the ticketing object parameters. And the table 2 is a data table of the predicted number of people, the predicted fare and the predicted service charge of each movie in each cinema, which is obtained by summarizing the field data of each cinema captured in the time period of 0-24 days from 7 months and 3 days in 2019. The predicted values of the number of persons, the price of ticket, and the service fee for each session are predicted individually, for example, the result of the predicted number of persons, price of ticket, and service fee for the session of movie a in theater 1 is (74,45.3,4.1), where the number of persons 74 is the result of inputting the number of persons (sold, reserved, or not sold) as (60,20,1) to the number of persons prediction model subcomponent, the price of ticket 45.3 is the result of inputting the price of ticket 45 for movie a in theater 1 to the number of persons prediction model subcomponent, and the service fee 4.1 is the result of inputting the price of service fee 4 for movie a in theater 1 to the service fee prediction model subcomponent. Of course, the field data in cinema 1 for each film is more than one field, and table 2 is only an exemplary representation.

TABLE 2 prediction times, prediction prices, prediction service charge data sheet of movie in cinema

In an embodiment of the present application, the statistical data of the target movie may include at least one of the following: total box office, total number of people, total service fee. For movie a in table 2, the total box house of 3 days 7 months in 2019 was (74 × 45.3+65 × 45.1+50 × 46.7+62 × 44.4) ═ 11371.5, the total number of persons was 74+65+50+62 ═ 251, and the total service fee was (74 × 4.1+65 × 4+50 + 3.8+62 ═ 4.1) ═ 1007.6. Therefore, the box office prediction of the target film can be achieved. Of course, the average fare (total fare/total number of persons), the average service charge (total service charge/total number of persons), and other data of the target film can be determined based on statistical data such as the total fare, the total number of persons, and the total service charge.

In practical application scenarios, there may be few theaters that can be connected to all theaters nationwide, and the above statistics for movie tickets a are only based on the statistics of theater 1, theater 2, theater 3, and theater 4, and cannot represent that theater a is based on nationwide statistics. Assuming that the nationwide corresponds to the target theater set including theater 1, theater 2, theater 3, and theater 4, in the embodiment of the present application, it is further necessary to determine the statistical data of movie a based on the target theater set according to the statistical data of theater 1, theater 2, theater 3, and theater 4.

In one embodiment of the present application, the target movie based on the target theater set statistics may be determined by a general box office prediction model component. The total box office prediction model component can be obtained by utilizing the corresponding relation between the statistical sample data of a plurality of film samples based on the plurality of cinemas and the statistical sample data of the target cinema set. Table 3 is a comparison table of historical ticketing data and reference ticketing data used for training the total ticketing house prediction model component, and of course, the total ticketing house prediction model may include linear models of the respective ticketing houses, the number of people, the service fees, and the like, that is, the relationship between the ticketing houses, the number of people, and the service fees of the movies in the historical ticketing house data and the reference ticketing house data is expressed by straight lines. Of course, the training may also be performed by machine learning, and the present application is not limited thereto.

TABLE 3 History ticketing data and reference ticketing data look-up table

According to the ticket data processing method, the parameter value of the ticket target parameter of each cinema can be predicted firstly, and then the box office data of each film can be obtained through statistics according to the parameter value of the ticket target parameter, so that fine-grained statistics from bottom to top can be realized, and the accuracy of a prediction result can be improved. In addition, in the process of predicting the parameter values of the ticket business target parameters of each cinema, model components matched with each cinema can be used for prediction, and the model components are obtained by training through historical ticket business data of the cinemas. On one hand, the accuracy of minimum granularity prediction data can be realized by following the difference of each cinema behavior, on the other hand, the future behavior of each cinema can be predicted by using the historical behavior of each cinema, the stability of each cinema behavior is followed, and the prediction accuracy is improved.

Corresponding to the above ticket data processing method, as shown in fig. 3, the present application further provides a ticket data processing apparatus, including a processor and a memory for storing processor executable instructions, where the processor executes the instructions to implement:

ticket data of a plurality of cinemas are obtained;

Optionally, in an embodiment of the present application, the ticket prediction model component is configured to be trained as follows:

acquiring historical ticket data and reference ticket data of the cinema;

constructing a ticket prediction model component, wherein training parameters are set in the ticket prediction model component;

respectively inputting the historical ticket data into the ticket prediction model component to generate a prediction result;

and iteratively adjusting the training parameters based on the difference between the prediction result and the reference ticketing data until the difference meets the preset requirement.

Optionally, in an embodiment of the present application, the ticket prediction model component includes at least one of a people prediction model subcomponent for determining people of a single-scene movie, a fare prediction model subcomponent for determining fares of a single-scene movie, and a service fare prediction model subcomponent for determining service fares of a single-scene movie.

Optionally, in an embodiment of the present application, the human prediction model subcomponent is configured to be trained as follows:

extracting the personal data of a single scene of the movie from the historical ticket data and the reference ticket data respectively;

constructing a human number prediction model subassembly, wherein training parameters are set in the human number prediction model subassembly;

respectively inputting the times of people data of a single session of film in the historical ticketing data into the times of people prediction model sub-component to generate a prediction result;

and iteratively adjusting the training parameters based on the difference between the prediction result and the corresponding times of people data of the same field in the reference ticketing data until the difference meets the preset requirement.

Optionally, in an embodiment of the present application, the fare prediction model subcomponent is arranged to be trained in the following manner:

extracting ticket price data of a single-session movie from the historical ticket data and the reference ticket data respectively;

constructing a fare prediction model sub-component, wherein training parameters are set in the fare prediction model sub-component;

respectively inputting the fare data of a single movie in the historical fare data into the fare prediction model sub-component to generate a prediction result;

and iteratively adjusting the training parameters based on the difference between the prediction result and the corresponding fare data of the same time in the reference ticketing data until the difference meets the preset requirement.

Optionally, in an embodiment of the present application, the service charge prediction model subcomponent is configured to be trained in the following manner:

extracting service fee data of a single movie from the historical ticket data and the reference ticket data respectively;

constructing a service charge prediction model subcomponent, wherein training parameters are set in the service charge prediction model subcomponent;

respectively inputting service fee data of a single movie in the historical ticket data into the service fee prediction model sub-component to generate a prediction result;

and iteratively adjusting the training parameters based on the difference between the prediction result and the service charge data of the same time in the corresponding reference ticket business data until the difference meets the preset requirement.

Optionally, in an embodiment of the present application, the processor further implements the following steps:

counting parameter values of ticket business target parameters of the plurality of cinemas, and determining a target movie based on at least one statistical data of the plurality of cinemas;

determining at least one statistical data of the target movie based on the target cinema set according to the at least one statistical data based on the plurality of cinemas.

Optionally, in an embodiment of the present application, the statistical data includes at least one of: total box office, total number of people, total service fee.

Optionally, in an embodiment of the application, the processor, when implementing the step of determining the target movie based on at least one statistical data of the target cinema set according to the at least one statistical data based on the plurality of cinemas, includes:

inputting the target film into a general ticket house prediction model component based on at least one statistical data of the plurality of cinemas, and outputting at least one statistical data of the target film based on a target cinema set through the general ticket house prediction model component;

the total box office prediction model component is obtained by training through the corresponding relation between the statistical sample data of a plurality of film samples based on the plurality of cinemas and the statistical sample data of the target cinema set.

Optionally, in an embodiment of the present application, the ticket data includes historical ticket data or ticket data in a pre-sale state.

In another aspect, the present application further provides a computer-readable storage medium, on which computer instructions are stored, and the instructions, when executed, implement the steps of the method according to any of the above embodiments.

The computer readable storage medium may include physical means for storing information, typically by digitizing the information for storage on a medium using electrical, magnetic or optical means. The computer-readable storage medium according to this embodiment may include: devices that store information using electrical energy, such as various types of memory, e.g., RAM, ROM, etc.; devices that store information using magnetic energy, such as hard disks, floppy disks, tapes, core memories, bubble memories, and usb disks; devices that store information optically, such as CDs or DVDs. Of course, there are other ways of storing media that can be read, such as quantum memory, graphene memory, and so forth.

In the 90 s of the 20 th century, improvements in a technology could clearly distinguish between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, an Application Specific Integrated Circuit (ASIC), a programmable logic controller, and an embedded microcontroller, examples of which include, but are not limited to, the following microcontrollers: the ARC625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic for the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller as pure computer readable program code, the same functionality can be implemented by logically programming method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers and the like. Such a controller may thus be considered a hardware component, and the means included therein for performing the various functions may also be considered as a structure within the hardware component. Or even means for performing the functions may be regarded as being both a software module for performing the method and a structure within a hardware component.

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.

Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method of ticket data processing, the method comprising:

ticket data of a plurality of cinemas are obtained;

2. The method of claim 1, wherein the ticket prediction model component is configured to be trained in the following manner:

acquiring historical ticket data and reference ticket data of the cinema;

3. The method of claim 1, wherein the ticketing prediction model component comprises at least one of a people prediction model subcomponent for determining people of a single-shot movie, a fare prediction model subcomponent for determining fares of a single-shot movie, and a service fee prediction model subcomponent for determining service fees of a single-shot movie.

4. The method of claim 3, wherein the people prediction model subcomponent is arranged to be trained in the following manner:

5. A method according to claim 3, wherein the fare prediction model subcomponent is arranged to be trained in the following manner:

6. The method of claim 3, wherein the service fee prediction model subcomponent is arranged to be trained in the following manner:

7. The method of claim 1, wherein after the ticket data of the plurality of theaters are respectively input to a ticket prediction model component matched with the theaters and parameter values of ticket objective parameters corresponding to the theaters are output through the ticket prediction model component, the method further comprises:

8. The method of claim 7, wherein the statistical data comprises at least one of: total box office, total number of people, total service fee.

9. The method of claim 8, wherein determining the target movie based on at least one statistical data of a target theater set based on the at least one statistical data of the plurality of theaters comprises:

10. The method of claim 1, wherein the ticketing data includes historical ticketing data or ticketing data in a pre-sold state.

11. A ticketing data processing apparatus comprising a processor and a memory for storing processor-executable instructions that when executed by the processor implement:

ticket data of a plurality of cinemas are obtained;

12. The apparatus of claim 11, wherein the ticket prediction model component is configured to be trained in the following manner:

acquiring historical ticket data and reference ticket data of the cinema;

13. The apparatus of claim 11, wherein the ticketing prediction model component comprises at least one of a people prediction model subcomponent for determining people of a single-shot movie, a fare prediction model subcomponent for determining fares of a single-shot movie, and a service fee prediction model subcomponent for determining service fees of a single-shot movie.

14. The apparatus of claim 13, wherein the people prediction model subcomponent is arranged to be trained in the following manner:

15. The apparatus of claim 13, wherein the fare prediction model subcomponent is arranged to be trained in the following manner:

16. The apparatus of claim 13, wherein the service fee prediction model subcomponent is arranged to be trained in the following manner:

17. The apparatus of claim 11, wherein the processor further implements the steps of:

18. The apparatus of claim 17, wherein the statistical data comprises at least one of: total box office, total number of people, total service fee.

19. The apparatus of claim 18, wherein the processor, when implementing the step of determining the target movie based on at least one statistical data of a target theater set based on the at least one statistical data of the plurality of theaters, comprises:

20. The apparatus of claim 11, wherein the ticketing data includes historical ticketing data or ticketing data in a pre-sold state.

21. A non-transitory computer-readable storage medium, wherein instructions in the storage medium, when executed by a processor, enable the processor to perform the ticketing data processing method of any one of claims 1-10.