Ticket sales warning method, device, storage medium and server
Through the ticket trajectory retention technology based on slice technology and historical database to calculate the best occupancy rate, the problem of insensitive abnormal trend identification in railway passenger ticketing organizations is solved, real-time identification and early warning of abnormal trends is achieved, and the sensitivity of the ticketing process is improved. Sex and accuracy.
Patent Information
- Application Number
- CN202210039243.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-01-13
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2042-01-13
AI Technical Summary
There are problems in the railway passenger ticketing organization that are insensitive to abnormal trend recognition, weak real-time sensitivity, and strong artificial dependence, resulting in insufficient real-time and accuracy of abnormal trend recognition during ticketing.
Real-time sales data slices and remaining ticket slices are obtained through ticket trajectory retention technology based on slicing technology, and the best occupancy rate is calculated based on the historical ticket sales database, and whether the deviation between the actual occupancy rate and the best occupancy rate is within the error range. If not, abnormal warning prompts will be issued to improve the sensitivity and real-time sensitivity of abnormal trend recognition.
It has achieved an improvement in the sensitivity to abnormal trend identification of railway passenger ticket sales organizations, improved real-time sensitivity, reduced dependence on manual monitoring, and improved the accuracy and efficiency of the ticket sales process.
Smart Images

Figure CN114529027B_ABST
Abstract
Description
[Technical field]
[0001] The present invention relates to the field of railway passenger tickets, and in particular to a ticket sales early warning method, device, storage medium and server. [Background technology]
[0002] At present, the ticket sales strategy adopted in the process of railway passenger ticket sales is mainly based on the pre-ticket allocation plan, supplemented by manual monitoring and adjustment during the ticket sales process. Although this ticket sales strategy is in line with the development history and actual production status of the railway, with the continuous increase in railway operating mileage and the number of trains, the passenger flow has increased sharply, and this ticket sales strategy has gradually failed to meet the needs of the development of railway ticket sales organizations in actual production applications. Because, on the one hand, the current ticket allocation plan is highly dependent on passenger flow forecasting, but because passenger demand is affected by various factors such as competing transportation modes, weather changes, and emergencies, passenger flow forecasting is uncertain, and the degree of restoration of the actual passenger flow by the passenger flow forecasting method has a certain deviation, resulting in inevitable differences between the pre-ticket allocation plan formulated before the pre-sale period and the actual passenger flow demand during the pre-sale period; on the other hand, the ticket sales process mainly relies on manual monitoring to detect anomalies and make adjustments, which not only has weak real-time and low sensitivity in identifying abnormal ticket sales trends, but is also time-consuming and labor-intensive, with huge human costs. At the same time, there is a lack of clear standard definitions for the "abnormal" judgment in ticket sales, resulting in the need to improve the accuracy of manual monitoring, and manual monitoring methods are difficult to quantify and efficiently and strictly manage a large number of train trips.
[0003] In summary, the current railway passenger ticketing organization has problems such as insensitivity to abnormal trend identification, weak real-time sensitivity, and strong dependence on manual labor. [Summary of the invention]
[0004] In view of this, the embodiments of the present invention provide a ticket warning method, device, storage medium and server, so that railway passenger ticket sales organizations are sensitive to abnormal trend identification, improve real-time sensitivity and do not rely on manual labor.
[0005] In a first aspect, an embodiment of the present invention provides a ticket sales warning method, the method comprising:
[0006] The real-time sales data slice and the real-time remaining ticket slice of the current train are obtained by using the ticketing track retention technology based on the slicing technology to obtain the actual passenger occupancy rate of the current train;
[0007] According to the historical ticketing database, the best passenger load factor corresponding to the date of the current train is obtained;
[0008] When the deviation between the actual passenger load factor and the optimal passenger load factor is not within the error interval, an abnormal warning prompt is issued.
[0009] Optionally, obtaining the best passenger load factor on the date corresponding to the current train number according to the historical ticket database includes:
[0010] Cleaning the historical ticket sales data in the historical ticket sales database;
[0011] According to the error interval and the cleaned historical ticket sales data, a first set including a set of passenger load factor values is obtained;
[0012] Calculate the first set by using the ticket selling rule optimal value algorithm based on the error interval to obtain the optimal value interval;
[0013] According to the optimal value interval, the optimal passenger occupancy rate of the train within a unit time is obtained;
[0014] According to the optimal passenger occupancy rate of the train number within a unit time, a knowledge base of train ticket health rules based on date segmentation is constructed;
[0015] The optimal passenger occupancy rate on the date corresponding to the current train number is obtained from the train ticket sales health law knowledge base.
[0016] Optionally, the calculating the first set by using an optimal value algorithm of the ticket selling rule based on the error interval to obtain an optimal value interval includes:
[0017] Initialize and set the first parameter, the second parameter and the intersection set;
[0018] Selecting the passenger load factor value set corresponding to the first parameter from the first set, and updating the intersection of the intersection set and the passenger load factor value set as the intersection set;
[0019] Taking the sum of the first parameter and the first value as the second parameter;
[0020] Determine whether the second parameter is greater than the number of the occupancy rate value sets in the first set;
[0021] If it is determined that the second parameter is greater than the number of the passenger load factor value sets in the first set, taking the sum of the first parameter and the first value as the first parameter;
[0022] Determining whether the first parameter is greater than or equal to the number of the occupancy rate value sets in the first set;
[0023] If it is determined that the first parameter is greater than or equal to the number of the occupancy rate value sets in the first set, the intersection set is used as the optimal value interval.
[0024] Optionally, after determining whether the second parameter is greater than the number of the passenger load factor value sets in the first set, the method further includes:
[0025] If it is determined that the second parameter is less than or equal to the number of the passenger load factor value sets in the first set, extracting a subset from the first set according to the second parameter;
[0026] Selecting a passenger load factor value set corresponding to the second parameter from the subset, and updating the intersection of the intersection set and the passenger load factor value set corresponding to the second parameter as the intersection set;
[0027] The sum of the second parameter and the first value is taken as the second parameter, and the step of determining whether the second parameter is greater than the number of the occupancy rate value sets in the first set is continued.
[0028] Optionally, after determining whether the first parameter is greater than or equal to the number of the occupancy rate value sets in the first set, the method further includes:
[0029] If it is determined that the first parameter is less than the number of occupancy rate value sets in the first set, continue to execute the step of selecting the occupancy rate value set corresponding to the first parameter from the first set, and update the intersection of the intersection set and the occupancy rate value set to the intersection set.
[0030] Optionally, when the deviation between the actual passenger load factor and the optimal passenger load factor is not within an error interval, before issuing an abnormal warning prompt, the method includes:
[0031] Determining whether a deviation between the actual passenger load factor and the optimal passenger load factor is within the error interval;
[0032] If it is determined that the deviation between the actual occupancy rate and the optimal occupancy rate is within the error interval, a normal mode reminder is performed.
[0033] Optionally, after the normal mode reminder is performed, the following steps are included:
[0034] Determine whether the ticket sale is finished;
[0035] If it is determined that the ticket sale has not ended, continue to execute the step of obtaining the real-time sales data slice and real-time remaining ticket slice of the current train through the ticket track retention technology based on slicing technology to obtain the actual occupancy rate of the current train.
[0036] On the other hand, an embodiment of the present invention provides a ticket sales warning device, the device comprising:
[0037] An acquisition module is used to obtain a real-time sales data slice and a real-time remaining ticket slice of the current train through a ticketing track retention technology based on a slicing technology, and obtain an actual passenger occupancy rate of the current train;
[0038] A processing module, used for obtaining the best passenger load factor for the date corresponding to the current train according to the historical ticket database;
[0039] The early warning module is used to issue an abnormal early warning prompt when the deviation between the actual passenger load factor and the optimal passenger load factor is not within the error interval.
[0040] On the other hand, an embodiment of the present invention provides a storage medium, which includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the above-mentioned ticket sales warning method.
[0041] On the other hand, an embodiment of the present invention provides a server, including a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, and is characterized in that the program instructions implement the steps of the above-mentioned ticket sales warning method when loaded and executed by the processor.
[0042] In the technical solutions of the ticket warning method, device, storage medium and server provided by the embodiments of the present invention, real-time sales data slices and real-time remaining ticket slices of the current train are obtained through the ticket track retention technology based on slicing technology to obtain the actual occupancy rate of the current train; the best occupancy rate on the date corresponding to the current train is obtained according to the historical ticket database; when the deviation between the actual occupancy rate and the best occupancy rate is not within the error range, an abnormal warning prompt is issued, so that the railway passenger ticket sales organization is sensitive to abnormal trend recognition, improves real-time sensitivity and does not rely on manual labor.
Brief Description of the Drawings
[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0044] Figure 1 A flowchart of a ticket sales warning method provided by an embodiment of the present invention;
[0045] Figure 2 A flowchart of a ticket sales warning method provided by another embodiment of the present invention;
[0046] Figure 3 This is a schematic diagram of the remaining ticket calculation platform;
[0047] Figure 4 for Figure 2 According to the historical ticket database, a flowchart of the best passenger load factor corresponding to the current train number is obtained;
[0048] Figure 5 It is a schematic diagram of the optimal value interval based on the error interval;
[0049] Figure 6 for Figure 4 The first set is calculated by the optimal value algorithm of ticket selling rules based on error interval, and a flow chart of the optimal value interval is obtained;
[0050] Figure 7 This is a schematic diagram of the optimal passenger load factor range curve.
[0051] Figure 8 A schematic diagram of the structure of a ticket sales warning device provided by an embodiment of the present invention;
[0052] Fig. 9 for Figure 8 The structural diagram of the processing module;
[0053] Fig.10 for Fig. 9 A schematic diagram of the structure of the second processing submodule;
[0054] Fig.11 A schematic diagram of a server provided in an embodiment of the present invention. [Specific implementation method]
[0055] In order to better understand the technical solution of the present invention, the embodiments of the present invention are described in detail below with reference to the accompanying drawings.
[0056] It should be clear that the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0057] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments, and are not intended to limit the present invention. The singular forms "a", "said" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.
[0058] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.
[0059] Figure 1 A flowchart of a ticket sales warning method provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the method includes:
[0060] Step 101: Obtain the real-time sales data slice and real-time remaining ticket slice of the current train through the ticket track retention technology based on slicing technology to obtain the actual passenger occupancy rate of the current train.
[0061] Step 102: According to the historical ticketing database, the best passenger load factor for the date corresponding to the current train number is obtained.
[0062] Step 103: When the deviation between the actual passenger load factor and the optimal passenger load factor is not within the error range, an abnormal warning prompt is issued.
[0063] In a technical solution of a ticket sales warning method provided by an embodiment of the present invention, a real-time sales data slice and a real-time remaining ticket slice of the current train are obtained through a ticket sales track retention technology based on slicing technology to obtain the actual occupancy rate of the current train; based on a historical ticket sales database, the best occupancy rate on the date corresponding to the current train is obtained; when the deviation between the actual occupancy rate and the best occupancy rate is not within an error range, an abnormal warning prompt is issued, so that the railway passenger ticket sales organization is sensitive to abnormal trend recognition, improves real-time sensitivity and does not rely on manual labor.
[0064] Figure 2 A flowchart of a ticket sales warning method provided by another embodiment of the present invention is as follows: Figure 2 As shown, the method includes:
[0065] Step 201: Obtain the real-time sales data slice and real-time remaining ticket slice of the current train through the ticket track retention technology based on the slicing technology to obtain the actual passenger occupancy rate of the current train.
[0066] In the embodiment of the present invention, before step 201, after the start of ticket sales is detected, a monitoring period is entered.
[0067] In order to obtain the ticket sales status of the train, the ticket sales track retention technology based on the slicing technology of the present invention obtains the real-time sales data slice and the real-time remaining ticket slice of the current train, and obtains the actual passenger occupancy rate of the train. At present, in the passenger ticket system, the passenger ticket sales process of the train is mainly reflected by two types of data tables, namely the remaining ticket table and the ticket stub table. The remaining ticket table reflects the train's sale capacity, and the ticket stub table reflects the number of tickets that have been sold. At present, the passenger ticket system updates the remaining ticket data and stub data from the marketing system to the database at 18:00 or 24:00 every day. Since the remaining ticket data and stub data during the pre-sale period change continuously with the sales process, the ticket sales monitoring and early warning link is a process that continues with the ticket sales during the pre-sale period. Therefore, it is necessary to record the remaining ticket data and stub data at a specific time point to obtain the ticket sales status and trend. At present, the recording granularity of the remaining ticket data and stub data is relatively coarse, and the number of tickets sold and the remaining ticket situation of the train at a specific time point cannot be obtained, and the requirements of the ticket sales monitoring and early warning for the precision of the remaining tickets cannot be met.
[0068] The ticketing track retention technology based on slicing technology refers to automatically obtaining the current train's remaining ticket data and sales data (i.e., real-time sales data slices and real-time remaining ticket slices) by calling the remaining ticket cluster interface at a specific time point, and completely retaining and storing them. As of the current train departure time, the complete ticketing status of the current train during the pre-sale period can be obtained, and the real-time sales data slices and real-time remaining ticket slices of the current train obtained are used as historical training samples for monitoring the current train's ticket sales anomalies and the train ticket sales health law knowledge base at a specific time. As the date goes by, the ticketing track retention technology based on slicing technology can accumulate a large amount of multi-dimensional train ticket sales historical data, providing sufficient samples and analysis basis for the subsequent training of the train ticket sales health law knowledge base.
[0069] In the embodiment of the present invention, according to the historical rules of different trains, different slice time granularities are used at different time nodes during the pre-sale period, namely hourly granularity and natural day granularity. For all trains during the pre-sale period, slices of different time granularities are collected to obtain the law of remaining ticket changes, which is helpful for ticket sales organization strategy monitoring and early warning. For example, within three days before the departure date, one slice time granularity is taken per hour, and for other dates during the pre-sale period, one slice time granularity is taken per natural day. This strategy can not only reduce the amount of unnecessary redundant data, but also reduce the pressure on the server and better serve production.
[0070] It should be noted that the actual passenger occupancy rate of the current train is used as the basis for ticket sales warning on the one hand, and as sample data for optimizing the knowledge base of healthy rules of train ticket sales in the future on the other hand.
[0071] In order to obtain the remaining ticket data, the embodiment of the present invention designs and constructs a remaining ticket calculation platform. The remaining ticket calculation platform is used to calculate, extract and load the remaining ticket information of the train in real time. Figure 3 As shown in the figure, the remaining ticket computing platform includes: ticket system database, OTX synchronization system, distributed memory computing platform, data collection and loading middleware and marketing analysis data warehouse. The distributed memory computing platform includes the distributed memory computing cluster of the bureau and the distributed memory computing cluster of the Internet.
[0072] The process of remaining ticket calculation is slightly different depending on the source of remaining ticket data. For the remaining ticket data of the data center of this railway bureau (hereinafter referred to as "this bureau"), first, according to the monitoring time range, after the generation of this bureau's passenger ticket database and before entering the pre-sale period, the entire database of this bureau's passenger ticket database is automatically copied from the passenger ticket system to the remaining ticket cluster server at the set time point to obtain the remaining seat ticket data; then, the heterogeneous data synchronization software OTX is used as a data transfer station to send data changes in the form of SQL statements and store the received messages in memory; the message receiving end captures the message, and performs operation judgment and data analysis on the SQL statements in the message. According to the different operation types, different operations are performed on the data in the memory database and input into the distributed memory computing cluster of this bureau; in order to realize the persistence of remaining ticket data, according to the remaining ticket query business, the memory is divided into several data areas and data units, and a unified rule is established to store the data in the memory of multiple devices in a dispersed manner. The distributed memory computing platform calculates the remaining ticket situation according to the ticket sales organization strategy; the remaining ticket calculation algorithm is provided, the number of remaining tickets is calculated according to different interface parameters, and the data in the agreed format is provided to the requesting client. For the remaining ticket data of external bureau data centers (including other railway bureaus and centralized storage data centers), mainly non-originating through trains related to this bureau, the existing Internet computing resources can be used to obtain the remaining ticket calculation results. All data are collected and loaded into the marketing analysis data warehouse through data collection and loading middleware. According to the needs of remaining ticket query, the remaining ticket calculation platform can provide remaining ticket interface service and remaining ticket query service. As the date increases, the remaining ticket calculation platform will gradually obtain more comprehensive historical train remaining ticket slice data, providing sufficient data support for the analysis and update of train ticket sales rules.
[0073] The embodiment of the present invention can save the remaining ticket data in fine granularity during the pre-sale period. As time passes during the pre-sale period, the amount of sliced data continues to increase. The embodiment of the present invention can continuously enhance the flexibility, scalability, and manageability of the remaining ticket information data during the ticketing process, and provide a large amount of business data that supports ticketing strategy decisions and behavior analysis, making a major breakthrough in the collection of remaining ticket data in terms of space efficiency, data granularity, storage support, and user experience.
[0074] Step 202: According to the historical ticketing database, the best passenger load factor for the date corresponding to the current train number is obtained.
[0075] In the embodiment of the present invention, Figure 4As shown, step 202 specifically includes:
[0076] Step 2021: clean the historical ticket sales data in the historical ticket sales database.
[0077] Since the train occupancy rate can most directly reflect the train operation efficiency, the occupancy rate data is used as the main indicator for ticket sales warning. The historical ticket sales data is the train occupancy rate of each train on different dates during the pre-sale period under different segmented operation dates.
[0078] For example, cleaning the historical ticket sales data in the historical ticket sales database includes removing singular values in the historical ticket sales data.
[0079] Step 2022: Obtain a first set including a set of passenger load factor values based on the error interval and the cleaned historical ticket sales data.
[0080] The key problem to be solved by the embodiment of the present invention is to calculate the optimal passenger occupancy rate of each train in each unit time according to the error tolerance. In order to meet the personalized needs in different application scenarios, the range of the error interval is set according to the actual situation.
[0081] In addition, the determination of abnormal warning standards is also the primary problem to be solved in ticket warning. In the embodiment of the present invention, the abnormal warning standard in the pre-sale period is defined as the deviation between the actual passenger load factor of the current train and the optimal passenger load factor of the corresponding train on the corresponding date in the train ticket health law knowledge base at the corresponding time point exceeds the error interval. Therefore, the train pre-sale health model in the embodiment of the present invention can provide a calculation method for the optimal passenger load factor of each train under different subdivided dates, and determine the abnormal warning standard in combination with the given error interval.
[0082] For each train number, given the error interval [b, a], the selection of the optimal passenger load factor directly determines the accuracy of the ticket warning. Assuming that for the current train number i, the departure date type d is known in the historical ticket sales data, in the k days before departure, the corresponding N historical actual passenger load factors y j,k , that is, [y 1,k ,y 2, …y j,k …y N,k ]. The specific classification of the historical actual passenger load factor depends on the accuracy requirement of the passenger load factor. For example, when the accuracy is required to be determined to one decimal place, 92.3%, 92.5% and 92.8% are all considered different train passenger load factors. According to the given error interval [b, a], each passenger load factor has a corresponding passenger load factor value x j,k , so that the historical actual passenger load factor y j,k Satisfy the requirements of the error interval [b, a], that is:
[0083]
[0084] Then for the current train number i, each passenger load factor value under a departure date k satisfies the passenger load factor value set A j,k :
[0085] A j,k ={x j,k |x j,k ∈[b*y j,k +y j,k , a*y j,k +y j,k ]}
[0086] Passenger load factor value set A j,k It can be defined as the absolute error range of the jth passenger load factor value of the current train number i including the k days before departure, A j,k Each passenger load factor value in is the value that makes the actual historical passenger load factor y j,k The passenger load factor value x that meets the error interval [b, a] requirements j,k The first set A = {A 1,k , A 2,k …A j,k …A N,k}. If the occupancy rate value set A in the first set A j,k There is an intersection, which means that in this intersection, the passenger load factor value x j,k The corresponding historical actual passenger load factor y j,k All of them can meet the requirements of the error interval [b, a]. Therefore, the values in the intersection can cover all the sample data corresponding to several sets, and it can be considered that the optimal passenger load factor exists in the intersection on the departure date of a train.
[0087] If the first set A does not have an intersection within the error interval [b, a], the mean of the occupancy rate on that date is taken as the optimal occupancy rate. When there is one and only one intersection, the optimal occupancy rate can be directly taken as the value in the intersection; when there are two or more intersections, the median of the interval with the largest coverage sample density is taken as the optimal occupancy rate; if the sample density of each intersection is the same, the median of the median interval is taken as the optimal occupancy rate.
[0088] like Figure 5 As shown in the figure, the train occupancy rate of a certain train and a certain seat type under a certain segment date and pre-sale period number k is expanded to the two-dimensional coordinate axis. The actual historical occupancy rate after removing the singular value is y 1,k ,y 2,k ,y 3,k ,y 4,k ,y 5,k , under the given error interval [b, a], the set of passenger load factor values that meet the error interval requirements are A 1,k , A2,k , A 3,k , A 4,k , A 5,k The embodiment of the present invention assumes that the pre-sale rules of the same train and the same seat class are the same on the same segment date. Therefore, it is obviously biased to use any value to represent the best pre-sale status of the group of trains. However, the intersection of all sample error intervals (shaded part) can meet the optimal error requirements of all train samples, that is, it represents the best pre-sale status of the train. Therefore, the intersection of all sample error intervals (shaded part) can meet the optimal error requirements of all train samples, that is, it represents the best pre-sale status of the train. Figure 5 The interval in the shaded part is taken as the optimal value interval.
[0089] Step 2023: Calculate the first set using the ticket selling rule optimal value algorithm based on the error interval to obtain the optimal value interval.
[0090] In the embodiment of the present invention, Figure 6 As shown, step 2023 specifically includes:
[0091] Step a: Initialize and set the first parameter, the second parameter and the intersection set.
[0092] In this step, the first parameter j, the second parameter i and the intersection set Initialize the first parameter, the second parameter and the intersection set, specifically including: setting the first parameter j and the second parameter i to 1, setting the intersection set to A 1,k .
[0093] Step b: Select a passenger occupancy rate value set corresponding to the first parameter from the first set, and update the intersection of the intersection set and the passenger occupancy rate value set into the intersection set.
[0094] In this step, the first set A={A 1,k , A 2,k …A j,k …A N,k}, the set of passenger load factor values corresponding to the first parameter j is A j,k , update the intersection set
[0095] Step c: taking the sum of the first parameter and the first value as the second parameter.
[0096] In this step, the first value is 1, and the second parameter i=j+1.
[0097] Step d, determine whether the second parameter is greater than the number of occupancy rate value sets in the first set. If so, execute step e; if not, execute step h.
[0098] In this step, it is determined whether the second parameter i is greater than the number N of passenger load factor value sets in the first set.
[0099] Step e: taking the sum of the first parameter and the first value as the first parameter.
[0100] In this step, if it is determined that i is greater than N, the first parameter j=j+1.
[0101] Step f, determine whether the first parameter is greater than or equal to the number of occupancy rate value sets in the first set. If so, execute step g; if not, continue to execute step b.
[0102] In this step, it is determined whether the first parameter j is greater than or equal to the number N of passenger load factor value sets in the first set.
[0103] Step g: take the intersection set as the optimal value interval and continue to execute step 2024.
[0104] In this step, if it is determined that j is greater than or equal to N, the intersection set as the optimal value interval.
[0105] Step h: extract a subset from the first set according to the second parameter.
[0106] In this step, if it is determined that i is less than or equal to N, a subset {A i,k , A i+1,k …A N,k}.
[0107] Step i: Select a set of passenger occupancy rate values corresponding to the second parameter from the subset, and update the intersection of the intersection set and the set of passenger occupancy rate values corresponding to the second parameter into the intersection set.
[0108] In this step, from the subset {A i,k , A i+1,k …A N,k} select the passenger load factor value set A corresponding to the second parameter i i,k , and update the intersection set
[0109] Step j: take the sum of the second parameter and the first value as the second parameter, and continue to execute step d.
[0110] In this step, let the second parameter i=i+1, and continue to execute step d.
[0111] The time complexity of the algorithm executed in the above steps a to j is o((n-1)!), and the intersection of all sample error intervals can be found, which contains all samples.
[0112] Step 2024: According to the optimal value interval, the optimal passenger occupancy rate of the train within a unit time is obtained.
[0113] In the embodiment of the present invention, the mean of the optimal value interval is set as the optimal passenger load factor y * j,k In practice, different error intervals [b, a] will produce different optimal value intervals. The algorithm given above is applicable to the case where there is a common intersection. When all sample error intervals have no intersection, the mean of all data is taken as the optimal occupancy rate y * j,k When there are two or more intersections, the error range set that can cover more samples is calculated as the optimal value interval.
[0114] The optimal passenger load factor prediction method based on the intersection of error intervals can be used to calculate the optimal passenger load factor y on the kth day before departure. * j,k . According to the error interval [b, a], calculate the optimal passenger load factor y * j,k The upper limit of the error range is a+y * j,k As the upper threshold, the lower limit of the error range b+y * j,k As the lower threshold. Figure 7 As shown, the middle curve is the best occupancy rate curve in the pre-sale period, the bottom curve is the lower threshold curve in the pre-sale period, and the top curve is the upper threshold curve in the pre-sale period. When the lower threshold is less than 0%, 0% is taken as the lower threshold.
[0115] Step 2025: According to the optimal passenger occupancy rate of the train number within a unit time, a knowledge base of train ticket health rules based on date segmentation is constructed.
[0116] Step 2026: Obtain the best passenger occupancy rate for the date corresponding to the current train from the train ticket sales health law knowledge base.
[0117] Step 203, determine whether the deviation between the actual passenger load factor and the optimal passenger load factor is within the error interval. If so, execute step 204; if not, execute step 206.
[0118] In this step, judging whether the deviation between the actual passenger load factor and the optimal passenger load factor is within the error range is actually judging whether the actual passenger load factor is within the optimal value interval [b+y * j,k , a+y * j,k ]Inside.
[0119] Step 204: Perform normal mode reminder.
[0120] In the embodiment of the present invention, if it is determined that the deviation between the actual passenger load factor and the optimal passenger load factor is within the error interval, a normal mode reminder is performed.
[0121] Step 205, determine whether the ticket sale is completed, if so, the process ends; if not, continue to execute step 201.
[0122] In the embodiment of the present invention, if the ticket sale is completed, the process ends; if the ticket sale is not completed, step 201 is continued.
[0123] Step 206: Provide an abnormal warning prompt. The process ends.
[0124] In the embodiment of the present invention, if it is determined that the deviation between the actual passenger load factor and the optimal passenger load factor is not within the error interval, an abnormal warning prompt is issued. The process ends.
[0125] In a technical solution of a ticket sales warning method provided by an embodiment of the present invention, a real-time sales data slice and a real-time remaining ticket slice of the current train are obtained through a ticket sales track retention technology based on slicing technology to obtain the actual occupancy rate of the current train; based on a historical ticket sales database, the best occupancy rate on the date corresponding to the current train is obtained; when the deviation between the actual occupancy rate and the best occupancy rate is not within an error range, an abnormal warning prompt is issued, so that the railway passenger ticket sales organization is sensitive to abnormal trend recognition, improves real-time sensitivity and does not rely on manual labor.
[0126] Figure 8 A schematic diagram of a ticket sales warning device provided by an embodiment of the present invention is shown in FIG. Figure 8 As shown, the device includes: an acquisition module 31, a processing module 32, a first judgment module 33, a reminder module 34, a second judgment module 35 and an early warning module 36.
[0127] The acquisition module 31 is used to obtain the real-time sales data slice and real-time remaining ticket slice of the current train through the ticket track retention technology based on the slicing technology, and obtain the actual passenger occupancy rate of the current train.
[0128] The processing module 32 is used to obtain the best passenger occupancy rate on the date corresponding to the current train number based on the historical ticket sales database.
[0129] In the embodiment of the present invention, Fig. 9 As shown, the processing module 32 includes: a cleaning submodule 321 , a first processing submodule 322 , a second processing submodule 323 , a third processing submodule 324 , a construction submodule 325 and an acquisition submodule 326 .
[0130] The cleaning submodule 321 is used to clean the historical ticket sales data in the historical ticket sales database.
[0131] The first processing submodule 322 is used to obtain a first set including a set of passenger load factor values according to the error interval and the cleaned historical ticket sales data.
[0132] The second processing submodule 323 is used to calculate the first set through the ticket selling rule optimal value algorithm based on the error interval to obtain the optimal value interval.
[0133] In the embodiment of the present invention, Fig.10 As shown, the second processing submodule 323 includes: an initialization subunit 3a, a first update subunit 3b, a first processing subunit 3c, a first judgment subunit 3d, a second processing subunit 3e, a second judgment subunit 3f, a third processing subunit 3g, an interception subunit 3h, a second update subunit 3i and a fourth processing subunit 3j.
[0134] Initialization subunit 3a, used for initializing and setting the first parameter, the second parameter and the intersection set;
[0135] A first updating subunit 3b is used to select a passenger load factor value set corresponding to the first parameter from the first set, and update the intersection of the intersection set and the passenger load factor value set into the intersection set;
[0136] A first processing subunit 3c, configured to use the sum of the first parameter and the first value as a second parameter;
[0137] The first judging subunit 3d is used to judge whether the second parameter is greater than the number of passenger load factor value sets in the first set;
[0138] The second processing subunit 3e is configured to use the sum of the first parameter and the first value as the first parameter if the first judging subunit 3d judges that the second parameter is greater than the number of passenger load factor value sets in the first set;
[0139] The second judging subunit 3f is used to judge whether the first parameter is greater than or equal to the number of passenger load factor value sets in the first set;
[0140] The third processing subunit 3g is used to use the intersection set as the optimal value interval if the second judgment subunit 3f judges that the first parameter is greater than or equal to the number of passenger load factor value sets in the first set.
[0141] The interception subunit 3h is used to intercept a subset from the first set according to the second parameter if the first determination subunit 3d determines that the second parameter is less than or equal to the number of passenger load factor value sets in the first set;
[0142] The second updating subunit 3i is used to select a passenger load factor value set corresponding to the second parameter from the subset, and update the intersection of the intersection set and the passenger load factor value set corresponding to the second parameter into the intersection set;
[0143] The fourth processing subunit 3j is used to take the sum of the second parameter and the first value as the second parameter, and trigger the first judgment subunit 3d to continue to execute the step of judging whether the second parameter is greater than the number of passenger load factor value sets in the first set.
[0144] The second judgment subunit 3f is also used to trigger the first updating subunit 3b if the second judgment subunit 3f determines that the first parameter is less than the number of occupancy rate value sets in the first set, and continue to execute the step of selecting the occupancy rate value set corresponding to the first parameter from the first set, and updating the intersection set with the occupancy rate value set to the intersection set.
[0145] The third processing submodule 324 is used to obtain the optimal passenger occupancy rate of the train within a unit time according to the optimal value interval.
[0146] The construction submodule 325 is used to construct a knowledge base of train ticket health rules based on date segmentation according to the optimal passenger occupancy rate of the train number within a unit time.
[0147] The acquisition submodule 326 is used to obtain the best passenger occupancy rate on the date corresponding to the current train number from the train ticket health law knowledge base.
[0148] The first judgment module 33 is used to judge whether the deviation between the actual passenger load factor and the optimal passenger load factor is within an error interval.
[0149] The reminder module 34 is used to perform a normal mode reminder and trigger the second judgment module 35 if the first judgment module 33 determines that the deviation between the actual passenger occupancy rate and the optimal passenger occupancy rate is within the error interval.
[0150] The second judging module 35 is used to judge whether the ticket selling is finished.
[0151] The second judging module 35 is further configured to terminate the process if the second judging module 35 determines that the ticket selling is finished.
[0152] The second judgment module 35 is also used to trigger the acquisition module 31 if the second judgment module 35 determines that the ticket sale is not completed, and continue to execute the operation of obtaining the real-time sales data slice and real-time remaining ticket slice of the current train through the ticket track retention technology based on slicing technology to obtain the actual occupancy rate of the current train.
[0153] The early warning module 36 is used to issue an abnormal early warning prompt if the first judgment module 33 determines that the deviation between the actual passenger occupancy rate and the optimal passenger occupancy rate is not within the error interval.
[0154] The ticket sales warning device provided by the embodiment of the present invention can be used to achieve the above Figures 1 to 7For the ticket sales warning method, the specific description can be found in the above-mentioned embodiment of the ticket sales warning method, which will not be repeated here.
[0155] In a technical solution of a ticket warning device provided by an embodiment of the present invention, real-time sales data slices and real-time remaining ticket slices of the current train are obtained through a ticket track retention technology based on slicing technology to obtain the actual occupancy rate of the current train; based on the historical ticket database, the best occupancy rate on the date corresponding to the current train is obtained; when the deviation between the actual occupancy rate and the best occupancy rate is not within an error range, an abnormal warning prompt is issued, so that the railway passenger ticket sales organization is sensitive to abnormal trend recognition, improves real-time sensitivity and does not rely on manual labor.
[0156] Fig.11 This is a schematic diagram of the structure of an embodiment of the server of this specification, such as Fig.11 As shown, the server may include at least one processor; and at least one memory in communication with the processor, wherein: the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the instructions of this specification. Figure 1 to Figure 7 The illustrated embodiment provides a ticket sales warning method.
[0157] Fig.11 A block diagram of an exemplary server suitable for implementing the embodiments of the present specification is shown. Fig.11 The server shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of this specification.
[0158] like Fig.11 As shown, the server is in the form of a general-purpose computing device. The components of the server may include, but are not limited to: one or more processors 21, memory 23, and a communication bus 24 connecting different system components (including memory 23 and processing unit 21).
[0159] The communication bus 24 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnection (PCI) bus.
[0160] The server typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the server, including volatile and non-volatile media, removable and non-removable media.
[0161] The memory 23 may include a computer system readable medium in the form of a volatile memory, such as a random access memory (RAM) and / or a cache memory. The server may further include other removable / non-removable, volatile / non-volatile computer system storage media. The memory 23 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of each embodiment of the present specification.
[0162] A program / utility having a set (at least one) of program modules may be stored in the memory 23, such program modules including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules generally perform the functions and / or methods of the embodiments described in this specification.
[0163] The processor 21 executes various functional applications and data processing by running the programs stored in the memory 23, such as implementing the Figure 1 to Figure 7 The illustrated embodiment provides a ticket sales warning method.
[0164] The embodiment of the present specification provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions enable the computer to execute the present specification. Figure 1 to Figure 7The illustrated embodiment provides a ticket sales warning method.
[0165] The above-mentioned non-transitory computer-readable storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (Read Only Memory; hereinafter referred to as: ROM), an erasable programmable read-only memory (Erasable Programmable Read Only Memory; hereinafter referred to as: EPROM) or flash memory, optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.
[0166] Computer-readable signal media may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0167] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0168] Computer program code for performing the operations of this specification may be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0169] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0170] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of this specification. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.
[0171] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this specification, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.
[0172] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of this specification includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of this specification belong.
[0173] The word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrases "if it is determined" or "if (stated condition or event) is detected" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)", depending on the context.
[0174] It should be noted that the terminals involved in the embodiments of this specification may include but are not limited to personal computers (Personal Computer; hereinafter referred to as: PC), personal digital assistants (Personal Digital Assistant; hereinafter referred to as: PDA), wireless handheld devices, tablet computers (Tablet Computer), mobile phones, MP3 players, MP4 players, etc.
[0175] In the several embodiments provided in this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0176] In addition, each functional unit in each embodiment of this specification may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0177] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor (Processor) to perform some steps of the method described in each embodiment of this specification. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), disk or optical disk and other media that can store program codes.
[0178] The above description is only a preferred embodiment of this specification and is not intended to limit this specification. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of this specification should be included in the scope of protection of this specification.
Claims
1. A ticket sales early warning method, characterized in that: The method comprises: The real-time sales data slice and the real-time remaining ticket slice of the current train are obtained by using the ticketing track retention technology based on the slicing technology to obtain the actual passenger occupancy rate of the current train; According to the historical ticketing database, the best passenger load factor corresponding to the date of the current train is obtained; When the deviation between the actual passenger load factor and the optimal passenger load factor is not within the error range, an abnormal warning prompt is issued; The method of obtaining the best passenger load factor for the date corresponding to the current train according to the historical ticket database includes: Cleaning the historical ticket sales data in the historical ticket sales database; According to the error interval and the cleaned historical ticket sales data, a first set including a set of passenger load factor values is obtained; Calculate the first set by using the ticket selling rule optimal value algorithm based on the error interval to obtain the optimal value interval; According to the optimal value interval, the optimal passenger occupancy rate of the train within a unit time is obtained; According to the optimal passenger occupancy rate of the train number within a unit time, a knowledge base of train ticket health rules based on date segmentation is constructed; The optimal passenger occupancy rate on the date corresponding to the current train number is obtained from the train ticket sales health law knowledge base.
2. A ticket sales early warning method according to claim 1, characterized in that: The step of calculating the first set by using the ticket selling rule optimal value algorithm based on the error interval to obtain the optimal value interval includes: Initialize and set the first parameter, the second parameter and the intersection set; Selecting the passenger load factor value set corresponding to the first parameter from the first set, and updating the intersection of the intersection set and the passenger load factor value set as the intersection set; Taking the sum of the first parameter and the first value as the second parameter; Determine whether the second parameter is greater than the number of the occupancy rate value sets in the first set; If it is determined that the second parameter is greater than the number of the passenger load factor value sets in the first set, taking the sum of the first parameter and the first value as the first parameter; Determining whether the first parameter is greater than or equal to the number of the occupancy rate value sets in the first set; If it is determined that the first parameter is greater than or equal to the number of the occupancy rate value sets in the first set, the intersection set is used as the optimal value interval.
3. A ticket sales early warning method according to claim 2, characterized in that: After determining whether the second parameter is greater than the number of the passenger load factor value sets in the first set, the method further includes: If it is determined that the second parameter is less than or equal to the number of the passenger load factor value sets in the first set, extracting a subset from the first set according to the second parameter; Selecting a passenger load factor value set corresponding to the second parameter from the subset, and updating the intersection of the intersection set and the passenger load factor value set corresponding to the second parameter as the intersection set; The sum of the second parameter and the first value is taken as the second parameter, and the step of determining whether the second parameter is greater than the number of the occupancy rate value sets in the first set is continued.
4. A ticket sales early warning method according to claim 2, characterized in that: After determining whether the first parameter is greater than or equal to the number of the passenger load factor value sets in the first set, the method further includes: If it is determined that the first parameter is less than the number of occupancy rate value sets in the first set, continue to execute the step of selecting the occupancy rate value set corresponding to the first parameter from the first set, and update the intersection of the intersection set and the occupancy rate value set to the intersection set.
5. A ticket sales early warning method according to claim 1, characterized in that: When the deviation between the actual passenger load factor and the optimal passenger load factor is not within the error range, before the abnormal warning prompt is issued, the method includes: Determining whether a deviation between the actual passenger load factor and the optimal passenger load factor is within the error interval; If it is determined that the deviation between the actual occupancy rate and the optimal occupancy rate is within the error interval, a normal mode reminder is performed.
6. A ticket sales early warning method according to claim 5, characterized in that: After the normal mode reminder is performed, the following steps are included: Determine whether the ticket sale is finished; If it is determined that the ticket sale has not ended, continue to execute the step of obtaining the real-time sales data slice and real-time remaining ticket slice of the current train through the ticket track retention technology based on slicing technology to obtain the actual occupancy rate of the current train.
7. A ticket sales warning device, characterized in that: The device comprises: An acquisition module is used to obtain a real-time sales data slice and a real-time remaining ticket slice of the current train through a ticketing track retention technology based on a slicing technology, and obtain an actual passenger occupancy rate of the current train; A processing module, used for obtaining the best passenger load factor for the date corresponding to the current train according to the historical ticket database; An early warning module is used to issue an abnormal early warning prompt when the deviation between the actual passenger load factor and the optimal passenger load factor is not within an error interval; The processing module includes a cleaning submodule, a first processing submodule, a second processing submodule, a third processing submodule, a construction submodule and an acquisition submodule; The cleaning submodule is used to clean the historical ticket sales data in the historical ticket sales database; The first processing submodule is used to obtain a first set including a set of passenger load factor values according to the error interval and the cleaned historical ticket sales data; The second processing submodule is used to calculate the first set by using the ticket selling rule optimal value algorithm based on the error interval to obtain the optimal value interval; The third processing submodule is used to obtain the optimal passenger occupancy rate of the train within a unit time according to the optimal value interval; The construction submodule is used to construct a knowledge base of train ticket health rules based on date segmentation according to the optimal passenger occupancy rate of the train number within a unit time; The acquisition submodule is used to obtain the optimal passenger occupancy rate on the date corresponding to the current train number from the train ticket health law knowledge base.
8. A storage medium, characterized in that: The storage medium includes a stored program, wherein when the program is running, the device where the storage medium is located is controlled to execute the ticket sales warning method according to any one of claims 1 to 6.
9. A server comprising a memory and a processor, wherein the memory is used to store information including program instructions, and the processor is used to control the execution of the program instructions, characterized in that: When the program instructions are loaded and executed by the processor, the steps of the ticket sales warning method according to any one of claims 1 to 6 are implemented.
