User operation conversion method and system based on RFM model

Abstract

The invention belongs to the technical field of operation transformation. The invention provides a user operation conversion method and system based on an RFM model. The method comprises the following steps: receiving an input target ticket needing operation conversion, and determining a plurality of potential users according to the type attribute of the target ticket; acquiring and using the RFM model to process the consumption historical data of each potential user for the drama ticket business, calculating to obtain an R value, an F value and an M value, and scoring the R value, the F value and the M value according to set segments to obtain an R score, an F score and an M score; performing analysis according to the R score, the F score and the M score to obtain user classification of the potential users, and determining operation transformation intensity according to the user classification; and recommending target tickets to the potential users according to the operation conversion intensity. According to the method, the potential users are subjected to multi-dimensional analysis based on the RFM model, the appropriate operation conversion intensity is determined, the ticket service platform can obtain the optimal ticket service recommendation effect, and the operation conversion economy of the ticket service platform is improved.

Description

Technical Field

[0001] The present invention relates to the field of operation conversion technology, and in particular to a user operation conversion method and system based on an RFM model. Background Art

[0002] Analyzing users’ consumption habits can provide important references for the company’s operational transformation. For example, a ticketing platform can analyze users’ purchases of tickets for various plays, and then analyze the user’s interests in different plays, so as to perform operational transformation operations such as ticket push.

[0003] The existing consumption data analysis method considers the number of consumptions more, that is, the drama with the most consumptions is determined as the drama type that the user is interested in. However, the accuracy of the interest conclusion based on the single factor analysis is often insufficient, resulting in poor operation conversion effect, that is, the proportion of users who purchase tickets to all promoted users is low. The present invention aims to improve this technical problem, specifically, to provide a user operation conversion solution based on the RFM model. Summary of the invention

[0004] In this regard, the present invention provides a user operation conversion method, system, electronic device, computer storage medium and computer program product based on the RFM model to solve the above technical problems.

[0005] The present invention discloses a user operation conversion method based on an RFM model, and the method comprises the following steps: receiving an input target ticket that needs to be operated and converted, and determining a number of potential users according to the type attribute of the target ticket; obtaining consumption history data of each potential user for play ticketing, processing the consumption history data using an RFM model, calculating an R value, an F value, and an M value, and scoring the R value, the F value, and the M value according to set segments to obtain an R score, an F score, and an M score; analyzing and obtaining a user classification of the potential user according to the R score, the F score, and the M score, and determining an operation conversion intensity according to the user classification; and recommending a target ticket to each potential user according to the operation conversion intensity.

[0006] In some embodiments, the determining of a number of potential users based on the type attribute of the target ticket includes: inputting the received ticket introduction information of the target ticket into a semantic analysis model, the semantic analysis model semantically matching the ticket introduction information with each template ticket introduction information pre-stored in a database, and obtaining a number of matching template tickets and their corresponding matching degrees; wherein each template ticket corresponds one-to-one to the template ticket introduction information; determining a screening quantity based on the size of the matching degree, screening the first potential users of the screening quantity from all the first potential users corresponding to the template ticket in turn, and determining all the first potential users screened as the potential users corresponding to the target ticket.

[0007] In some embodiments, determining the number of screening according to the size of the matching degree includes: ; In the above formula, is the screening quantity, is the preset minimum number of screenings, is the matching degree, is the average matching degree of all matching template tickets, is the median value of the matching degree of all matching template tickets, It is the average value of the difference between the maximum and minimum matching degrees of all matching template tickets.

[0008] In some embodiments, the user classification of the potential user is obtained based on the analysis of the R score, the F score, and the M score, and the operational conversion intensity is determined based on the user classification, including: mapping the R score, the F score, and the M score to a preset three-dimensional coordinate system to determine a corresponding quadrant space in the three-dimensional coordinate system, and determining the user type associated with the corresponding quadrant space as the user classification of the potential user; retrieving the preset operational conversion intensity corresponding to the user classification, calculating the total number of all matching template tickets, putting the total number into a preset comparison table, and matching to obtain a first optimization value; using the first optimization value to optimize the preset operational conversion intensity to obtain a target operational conversion intensity.

[0009] In some embodiments, the use of the first optimization value to optimize the preset operational conversion intensity to obtain a target operational conversion intensity includes: using a semantic analysis model to perform semantic analysis on the ticket introduction information of the target ticket, evaluating the degree of innovation of the target ticket, and determining a second optimization value based on the degree of innovation; optimizing the preset operational conversion intensity based on the first optimization value and the second optimization value to obtain the target operational conversion intensity.

[0010] In some embodiments, the recommending of target tickets to each of the potential users based on the operational conversion intensity includes: parsing the number of promotions, the promotion frequency and the discount range from the target operational conversion intensity, and recommending the target ticket to the corresponding potential user based on the number of promotions, the promotion frequency and the discount range.

[0011] The present invention also discloses a user operation conversion system based on the RFM model, the system includes a processor and a memory, the processor runs the computer code stored in the memory to implement the following steps: receiving an input target ticket that needs to be operated and converted, and determining a number of potential users according to the type attributes of the target ticket; obtaining the consumption history data of each potential user for the play ticket, using the RFM model to process the consumption history data, calculating the R value, F value, and M value, and scoring the R value, F value, and M value according to the set segmentation to obtain the R score, F score, and M score; analyzing the user classification of the potential user according to the R score, the F score, and the M score, and determining the operation conversion intensity according to the user classification; and recommending the target ticket to each potential user according to the operation conversion intensity.

[0012] The present invention also discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method described in any of the preceding items.

[0013] The present invention also discloses a computer storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement any of the above methods.

[0014] The present invention also discloses a computer program product. When the computer program product is run on a terminal, the terminal implements any of the above methods when executing the computer program product.

[0015] The beneficial effect of the present invention is that the solution of the present invention performs a multi-dimensional analysis of potential users based on the RFM model, thereby determining the appropriate operational conversion intensity, which is beneficial for the ticketing platform to obtain the optimal ticket recommendation effect and improve the economic efficiency of its operational conversion. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 It is a flow chart of a user operation conversion method based on the RFM model disclosed in an embodiment of the present invention.

[0018] Figure 2 It is a structural diagram of a user operation conversion system based on the RFM model disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] The following is a description of the implementation of the present application by specific specific embodiments. People familiar with the technology can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0020] In addition, the technical features involved in the different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.

[0021] like Figure 1 As shown, an embodiment of the present invention discloses a user operation conversion method based on an RFM model, and the method includes the following steps: receiving an input target ticket that needs to be operated and converted, and determining a number of potential users according to the type attributes of the target ticket; obtaining consumption history data of each potential user for play tickets, using the RFM model to process the consumption history data, calculating the R value, F value, and M value, and scoring the R value, F value, and M value according to set segments to obtain the R score, F score, and M score; analyzing the user classification of the potential user according to the R score, the F score, and the M score, and determining the operation conversion intensity according to the user classification; and recommending target tickets to each potential user according to the operation conversion intensity.

[0022] The above scheme of the present invention adopts the RFM model, through which the RFM model can be used to analyze the R value, F value, and M value of potential users, thereby realizing the classification of users, and then determining the different operational conversion intensities for different potential users, and finally obtaining the optimal target ticket recommendation effect. Specifically: First, receive the target ticket that needs to be operationally converted, such as tickets for a basketball game, an e-sports game, a stage play, etc., input by relevant personnel. According to the type attributes of the target ticket, a number of potential users can be screened from the registered users, and these potential users are people who may be interested in the target ticket.

[0023] Then, the consumption history data of each potential user for play tickets is obtained, and the consumption history data is processed using the RFM model to obtain the R value, F value, and M value.

[0024] Among them, R (Recency): refers to the interval between the last consumption time and the deadline. Generally speaking, the shorter the interval between the last consumption time, the more likely the customer is to be interested in the product or service; F (Frequency): refers to the number of times a customer consumes within a certain period of time. Customers with higher consumption frequency are also more satisfied customers, with higher loyalty and greater customer value; M (Monetary): refers to the amount of money a customer spends within a certain period of time. The larger the amount of money a customer spends, the greater their spending power. The calculation methods of R value, F value, and M value are as follows: The calculation method of R indicator: first calculate the last purchase date of each user, and then subtract the last purchase date from the current date to get the time interval of the last consumption; the calculation method of F indicator: count the number of days with consumption; the calculation method of M indicator: count the total consumption amount.

[0025] According to the set segment (for example, -5-5 points), the R value, F value, and M value are scored respectively, and the corresponding R score, F score, and M score are obtained. According to the R score, F score, and M score obtained above, the potential users can be comprehensively classified to determine what type of user they belong to, and then the operational conversion intensity of the corresponding potential users is determined based on the user classification. The operational conversion intensity refers to the intensity of the ticketing platform when promoting the target ticket to the potential user. Among them, user classification includes but is not limited to important value users, important development users, important retention users, important retention users, general value users, general development users, general retention users, general retention users, etc.

[0026] Finally, according to the above determined conversion strengths of each operation, target tickets are recommended to the corresponding potential users, so that the ticketing platform can obtain the best ticket recommendation effect, that is, a higher proportion of users purchase the target ticket.

[0027] Therefore, the solution of the present invention analyzes potential users in more dimensions based on the RFM model, and determines the appropriate operational conversion intensity accordingly, which is beneficial for the ticketing platform to obtain the optimal ticket recommendation effect and improve the economic efficiency of its operational conversion.

[0028] In some embodiments, the determining of a number of potential users based on the type attribute of the target ticket includes: inputting the received ticket introduction information of the target ticket into a semantic analysis model, the semantic analysis model semantically matching the ticket introduction information with each template ticket introduction information pre-stored in a database, and obtaining a number of matching template tickets and their corresponding matching degrees; wherein each template ticket corresponds one-to-one to the template ticket introduction information; determining a screening quantity based on the size of the matching degree, screening the first potential users of the screening quantity from all the first potential users corresponding to the template ticket in turn, and determining all the first potential users screened as the potential users corresponding to the target ticket.

[0029] In an embodiment of the present invention, when relevant personnel need to promote a target ticket, they need to input the target ticket and its ticket introduction information. The semantic analysis model will semantically match the ticket introduction information with the template ticket introduction information pre-stored in the database to obtain a number of matching template tickets. Among them, a variety of template tickets are pre-stored in the database. These template tickets can be tickets that have been listed on the ticketing platform and other ticketing platforms. Each template ticket corresponds to a template ticket introduction information. The semantic analysis model will also output the matching degree corresponding to each successfully matched template ticket. The higher the matching degree, the higher the type similarity between the target ticket and the corresponding template ticket, and vice versa.

[0030] Next, each template ticket corresponds to a group of first potential users. These first potential users may also be users who have a high degree of interest in the template ticket based on the RFM model analysis. Of course, they may also be screened using other analysis methods, which are not specifically limited in the present invention. Then, the screening quantity is determined based on the corresponding matching degree. The screening quantity is used to determine the number that should be screened from the group of first potential users corresponding to the template ticket. The screening here can be performed in descending order according to the degree of interest. All the first potential users screened from the group of first potential users corresponding to each matching template ticket are determined as the potential users corresponding to the target ticket.

[0031] In some embodiments, determining the number of screening according to the size of the matching degree includes: ; In the above formula, is the screening quantity, is the preset minimum number of screenings, is the matching degree, is the average matching degree of all matching template tickets, is the median value of the matching degree of all matching template tickets, It is the average value of the difference between the maximum and minimum matching degrees of all matching template tickets.

[0032] In the embodiment of the present invention, when determining the number of screening of a certain template ticket that matches, the present invention calculates based on the matching degree of the template ticket; and the matching degrees of other template tickets are also considered in the calculation process. Specifically, the average value and median value of the matching degrees of all matching template tickets, and the average value of the difference between the maximum and minimum values ​​of the matching degrees of all matching template tickets are calculated respectively, that is, (maximum value - minimum value) / n-total, where n-total is the total number of all matching template tickets.

[0033] Since the mean of the sum of the two average values ​​and median values ​​is smaller than the matching degree The fluctuation range is smaller, so the screening quantity and the matching degree p are generally positively correlated. In other words, the higher the matching degree between the target ticket and the template ticket, that is, the more similar they are, the more first potential users corresponding to the template ticket will be screened.

[0034] In some embodiments, the user classification of the potential user is obtained based on the analysis of the R score, the F score, and the M score, and the operational conversion intensity is determined based on the user classification, including: mapping the R score, the F score, and the M score to a preset three-dimensional coordinate system to determine a corresponding quadrant space in the three-dimensional coordinate system, and determining the user type associated with the corresponding quadrant space as the user classification of the potential user; retrieving the preset operational conversion intensity corresponding to the user classification, calculating the total number of all matching template tickets, putting the total number into a preset comparison table, and matching to obtain a first optimization value; using the first optimization value to optimize the preset operational conversion intensity to obtain a target operational conversion intensity.

[0035] In the embodiment of the present invention, after obtaining the three values ​​of R, F, and M, they can be mapped to a three-dimensional coordinate system, where each quadrant space in the three-dimensional coordinate system corresponds to a user classification, for example, the first quadrant space is for important value users, the second quadrant space is for important development users, etc., which will not be described in detail. After mapping, the quadrant space where the potential user is located can be known, and then the user classification corresponding to the quadrant space can be determined.

[0036] Each user classification is preset with a corresponding preset operation conversion intensity, but the preset operation conversion intensity is obtained based on the fitting analysis of the historical operation conversion data of multiple tickets, lacking consideration of the actual situation of the target ticket, so further adjustment is required. Specifically, the present invention first calculates the total number of all template tickets matching the target ticket obtained above, and matches the corresponding first optimization value in the preset comparison table according to the total number. Among them, the more the total number, the higher the overall similarity between the target ticket and the existing ticket, that is, such tickets already exist in the existing ticket. At this time, it is necessary to focus on the preset operation conversion intensity obtained based on the fitting analysis of the historical operation conversion data of multiple existing tickets to promote the target ticket; and the less the total number, the lower the overall similarity between the target ticket and the existing ticket, that is, there is a lack of such tickets in the existing ticket, or there are only a few related tickets. At this time, it is necessary to adopt a higher intensity promotion based on the preset operation conversion intensity, that is, to increase the user's purchase probability by increasing the promotion of new ticket information. In addition, the first optimization value can be a value in the interval (1, 1.5). For example, when the total number is higher than 10, the first optimization value is set to 1, and no optimization adjustment is performed on the preset operation conversion intensity; when the total number is lower than 10, the first optimization value is set to a value in the interval (1, 1.5), and the smaller the total number, the larger the corresponding first optimization value.

[0037] In some embodiments, the use of the first optimization value to optimize the preset operational conversion intensity to obtain a target operational conversion intensity includes: using a semantic analysis model to perform semantic analysis on the ticket introduction information of the target ticket, evaluating the degree of innovation of the target ticket, and determining a second optimization value based on the degree of innovation; optimizing the preset operational conversion intensity based on the first optimization value and the second optimization value to obtain the target operational conversion intensity.

[0038] In an embodiment of the present invention, the ticket introduction information of the target ticket will also include the innovative description of the ticket information by relevant personnel, such as "This basketball event uses augmented reality technology for the first time in the world, which can bring you unparalleled visual enjoyment". The semantic analysis model is used to perform semantic analysis on the ticket introduction information to evaluate the degree of innovation of the target ticket, and then the corresponding second optimization value is matched according to the degree of innovation. Among them, the second optimization value is obviously positively correlated with the degree of innovation. However, in view of the fact that the innovation degree-related words in the ticket introduction information are usually very subjective, and some are even quite different from the actual situation, the present invention sets the second optimization value to be smaller than the first optimization value, for example, in the interval [1,1.2]. Finally, the first optimization value and the second optimization value are used simultaneously to optimize the preset operation conversion intensity to obtain the target operation conversion intensity.

[0039] In some embodiments, the recommending of target tickets to each of the potential users based on the operational conversion intensity includes: parsing the number of promotions, the promotion frequency and the discount range from the target operational conversion intensity, and recommending the target ticket to the corresponding potential user based on the number of promotions, the promotion frequency and the discount range.

[0040] In the embodiment of the present invention, the operational conversion intensity in the present invention includes three aspects: the number of promotions, the promotion frequency, and the discount range. The number of promotions refers to how many times the promotion information needs to be sent to a specific potential user before the target ticket stops selling. The promotion frequency refers to how many times the promotion information needs to be sent to a specific potential user in each time period before the target ticket stops selling. The discount range refers to the target ticket purchase discount range that needs to be given to the potential user. In summary, the above three aspects can achieve the best push of target tickets to potential users, thereby significantly improving the probability of potential users purchasing the target tickets.

[0041] Among them, the aforementioned optimization processing of the preset operation conversion intensity is also aimed at the above three aspects.

[0042] like Figure 2 As shown, an embodiment of the present invention further discloses a user operation conversion system based on an RFM model, the system comprising a processor and a memory, the processor running a computer code stored in the memory to implement the following steps: receiving an input target ticket that needs to be operated and converted, and determining a number of potential users according to the type attribute of the target ticket; obtaining consumption history data of each potential user for play tickets, processing the consumption history data using the RFM model, calculating an R value, an F value, and an M value, scoring the R value, the F value, and the M value according to set segments, and obtaining an R score, an F score, and an M score; analyzing the user classification of the potential user according to the R score, the F score, and the M score, and determining the operation conversion intensity according to the user classification; and recommending target tickets to each potential user according to the operation conversion intensity.

[0043] An embodiment of the present invention further discloses an electronic device, comprising: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, characterized in that: the processor executes the computer program to implement the method described in the above embodiment.

[0044] An embodiment of the present invention further discloses a computer storage medium, wherein the computer storage medium stores a computer program, and is characterized in that: the computer program is executed by a processor to implement the method described in the above embodiment.

[0045] The embodiment of the present invention further discloses a computer program product. When the computer program product is run on a terminal, the terminal implements the method described in the above embodiment.

[0046] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0047] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0048] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0049] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A user operation conversion method based on the RFM model, characterized in that The method includes the following steps: receiving an input target ticket that needs to be converted into an operation, and determining a number of potential users according to the type attributes of the target ticket; obtaining the consumption history data of each potential user for the play ticket, using the RFM model to process the consumption history data, and calculating the R value, F value, and M value, and scoring the R value, F value, and M value according to the set segmentation to obtain the R score, F score, and M score; analyzing the user classification of the potential user according to the R score, the F score, and the M score, and determining the operation conversion intensity according to the user classification; and recommending target tickets to each potential user according to the operation conversion intensity.

2. According to claim 1, a user operation conversion method based on the RFM model is characterized by: The determining of a number of potential users according to the type attribute of the target ticket comprises: inputting the received ticket introduction information of the target ticket into a semantic analysis model, wherein the semantic analysis model performs semantic matching on the ticket introduction information with each template ticket introduction information pre-stored in a database, and obtains a number of matching template tickets and their corresponding matching degrees; wherein each template ticket corresponds to the template ticket introduction information one by one; determining a screening quantity according to the size of the matching degree, sequentially screening the first potential users of the screening quantity from all the first potential users corresponding to the template tickets, and determining all the first potential users obtained by screening as the potential users corresponding to the target ticket.

3. A user operation conversion method based on the RFM model according to claim 2, characterized in that: Determining the number of screenings according to the matching degree includes: ; In the above formula, is the screening quantity, is the preset minimum number of screenings, is the matching degree, is the average matching degree of all matching template tickets, is the median value of the matching degree of all matching template tickets, It is the average value of the difference between the maximum and minimum matching degrees of all matching template tickets.

4. A user operation conversion method based on the RFM model according to claim 3, characterized in that: The method of obtaining a user classification of the potential user based on the analysis of the R score, the F score, and the M score, and determining an operation conversion intensity based on the user classification, includes: mapping the R score, the F score, and the M score to a preset three-dimensional coordinate system to determine a corresponding quadrant space in the three-dimensional coordinate system, and determining the user type associated with the corresponding quadrant space as the user classification of the potential user; retrieving a preset operation conversion intensity corresponding to the user classification, calculating the total number of all matching template tickets, putting the total number into a preset comparison table, and matching to obtain a first optimization value; and using the first optimization value to optimize the preset operation conversion intensity to obtain a target operation conversion intensity.

5. A user operation conversion method based on the RFM model according to claim 4, characterized in that: The using of the first optimization value to optimize the preset operational conversion intensity to obtain a target operational conversion intensity includes: using a semantic analysis model to perform semantic analysis on the ticket introduction information of the target ticket, evaluating the degree of innovation of the target ticket, and determining a second optimization value based on the degree of innovation; optimizing the preset operational conversion intensity based on the first optimization value and the second optimization value to obtain the target operational conversion intensity.

6. A user operation conversion method based on the RFM model according to claim 5, characterized in that: The recommending target tickets to each potential user according to the operational conversion intensity includes: parsing the number of promotions, the promotion frequency and the discount range from the target operational conversion intensity, and recommending the target ticket to the corresponding potential user based on the number of promotions, the promotion frequency and the discount range.

7. A user operation conversion system based on the RFM model, the system comprising a processor and a memory, characterized in that: The processor runs the computer code stored in the memory to implement the following steps: receiving an input target ticket that needs to be converted into an operation, and determining a number of potential users according to the type attributes of the target ticket; obtaining consumption history data of each potential user for play tickets, processing the consumption history data using the RFM model, calculating the R value, F value, and M value, and scoring the R value, F value, and M value according to the set segments to obtain the R score, F score, and M score; analyzing the user classification of the potential user according to the R score, the F score, and the M score, and determining the operation conversion intensity according to the user classification; and recommending target tickets to each potential user according to the operation conversion intensity.

8. An electronic device comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, wherein the processor executes the computer program to implement the method according to any one of claims 1 to 6.

9. A computer storage medium storing a computer program, characterized in that: The computer program is executed by a processor to implement the method according to any one of claims 1 to 6.

10. A computer program product comprising a computer program stored on a non-transitory computer readable medium, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images