WO2023050931A1

WO2023050931A1 - Event analysis method and device, and storage medium

Info

Publication number: WO2023050931A1
Application number: PCT/CN2022/101530
Authority: WO
Inventors: 安安; 陈朝亮
Original assignee: 深圳前海微众银行股份有限公司
Priority date: 2021-09-28
Filing date: 2022-06-27
Publication date: 2023-04-06
Also published as: CN113868308A

Abstract

Disclosed in the present application is an event analysis method. The method comprises: determining that a target service comprises a conversion path set of conversion paths for implementing a conversion target; counting the operation instances, within a preset time period, of a target operation corresponding to each reference burying-point event in the conversion path set, so as to obtain a burying-point event set; and determining a target contribution coefficient of the target burying-point event on the basis of the conversion path set and the burying-point event set, so as to determine an event analysis result according to the target contribution coefficient, wherein the target contribution coefficient is used for representing the contribution of the target burying-point event in the target service during the process of being converted into the conversion target. Further disclosed in the present application are an event analysis device and a storage medium.

Description

An event analysis method, device and storage medium

Cross References to Related Applications

This application is based on a Chinese patent application with application number 202111142788.6 and a filing date of September 28, 2021, and claims the priority of this Chinese patent application. The entire content of this Chinese patent application is hereby incorporated by reference into this application.

technical field

The present application relates to the technical field of statistical analysis, in particular to an event analysis method, device and storage medium.

Background technique

With the rapid development of computer technology, more and more technologies are applied in the financial field, and the traditional financial industry is gradually transforming into financial technology (Fintech). However, due to the security and real-time requirements of the financial industry, more and more technical requirements high demands. With the rapid development of Internet technology, the Internet has had a major impact on people's life, study, entertainment and other aspects. At present, the marketing activities of various types of products are usually implemented through the Internet, that is, merchants usually implement marketing promotion activities by setting embedded events on different pages, and users can realize access to marketing products by triggering embedded events. Even buy merchandise. In order to improve the efficiency of marketing and the effectiveness of embedded events, merchants usually conduct attribution analysis on the conversion of user behavior embedded events to the final target event, and determine the contribution value of each embedded event. At present, there are at least three ways to determine the contribution value of each buried point event when performing attribution analysis: the first method is to use the linear trigger method, that is, all buried point events distribute the contribution value equally; the second method is the location The trigger method is to set the contribution value of the first buried point event and the last buried point event to 40% respectively, and the remaining events are equally distributed to 20%; the third method is the time decay method, that is, the distance between each buried point event and the target buried point The closer the event time is, the higher the contribution value is, that is, the event contribution value is allocated incrementally according to the time difference.

However, in the current attribution method for determining the contribution value of each buried point event, since the contribution value of each buried point event in the marketing activity is predetermined, in the attribution analysis process, it may occur that each buried point The contribution of events can be subject to human intervention, or even cheating, resulting in a single method for determining the contribution value of each buried event, making the contribution value of each buried event inconsistent with the actual situation.

Contents of the invention

In order to solve the above technical problems, the embodiment of the present application expects to provide an event analysis method, device and storage medium, which solves the problem that the method for determining the contribution value of each buried point event is relatively simple, and realizes a dynamic determination of each buried point The method of the contribution value of the event enriches the determination method of the contribution value of each buried point event, so that the determined contribution value of each buried point event is consistent with the actual situation.

The technical scheme of the present application is realized like this:

In a first aspect, an event analysis method, the method comprising:

Determining a set of conversion paths in the target business including conversion paths that achieve the conversion goal;

Counting the number of operations of the target operation corresponding to each reference buried point event in the conversion path set within a preset time period to obtain a buried point event set;

Based on the set of conversion paths and the set of buried point events, determine the target contribution coefficient of the target buried point event, so as to determine the analysis result of the event according to the target contribution coefficient; wherein, the target contribution coefficient is used to represent the target The contribution of the buried point event in the process of converting the target business to the conversion target.

In a second aspect, an event analysis device, the device comprising: a memory, a processor, and a communication bus; wherein:

The memory is used to store executable instructions;

The communication bus is used to realize the communication connection between the processor and the memory;

The processor is configured to execute the event analysis program stored in the memory to implement the steps of the event analysis method described in any one of the above.

In a third aspect, a storage medium stores an event analysis program on the storage medium, and when the event analysis program is executed by a processor, the steps of the event analysis method described in any one of the foregoing are implemented.

In the embodiment of the present application, after determining the conversion path set including the conversion path that achieves the conversion goal in the target business, counting the number of operations of the target operation corresponding to each reference buried point event in the conversion path set within the preset time period, Obtain the buried point event set, and determine the target contribution coefficient of the target buried point event based on the conversion path set and the buried point event set. In this way, by analyzing the conversion path set included in the target business and the buried point event set including the number of operations of the target operation corresponding to each reference buried point event in the conversion path set, it is determined that the target buried point event is in the target business The target contribution coefficient in the process of converting to the conversion target solves the problem that the current method for determining the contribution value of each buried point event is relatively simple, and realizes a method for dynamically determining the contribution value of each buried point event, which enriches each buried point. The method for determining the contribution value of the event makes the determined contribution value of each buried point event consistent with the actual situation.

Description of drawings

FIG. 1 is a schematic flow diagram of an event analysis method provided in an embodiment of the present application;

FIG. 2 is a schematic flow diagram of another event analysis method provided in the embodiment of the present application;

FIG. 3 is a schematic flowchart of another event analysis method provided in the embodiment of the present application;

FIG. 4 is a schematic diagram of an application scenario provided by an embodiment of the present application;

FIG. 5 is a schematic structural diagram of an event analysis device provided in an embodiment of the present application.

Detailed ways

In order to make the purpose, technical solutions and advantages of the application clearer, the application will be further described in detail below in conjunction with the accompanying drawings. All other embodiments obtained under the premise of creative labor belong to the scope of protection of this application.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application, and are not intended to limit the present application.

The embodiment of the application provides a kind of event analysis method, with reference to shown in Fig. 1, method is applied to event analysis equipment, and this method comprises the following steps:

Step 101 , determining a conversion path set in the target business that includes a conversion path that realizes the conversion goal.

In this embodiment of the present application, the event analysis device is an electronic device with computing capabilities, such as a computing device, a server device, and the like. The target service may be a service with buried events, and the target service may be a service provided by a web page or a service provided by an application program. The conversion goal can refer to a buried point event in the conversion path, or it can refer to the conversion success of the conversion path. Buried events, which can be referred to as events for short, usually set user behavior capture as an event, such as clicking on a banner (banner), browsing a page, clicking on payment, etc., as buried events. At least one conversion path included in the conversion path set is a conversion path of the target business during an actual conversion process.

Step 102: Count the number of operations of the target operation corresponding to each reference buried point event in the conversion path set within a preset time period to obtain a buried point event set.

In the embodiment of the present application, the preset time period may be a time experience value obtained from a large number of experiments, it may be an analysis period for time analysis, or it may be a time experience value set by analysts according to actual analysis requirements. Each conversion path in the conversion path set is composed of a series of reference buried point events, and some reference buried point events may be the same in different conversion paths, or may not have the same reference buried point events. The target operation can refer to the user's operation on the reference buried point event, for example, it can be an access operation, and the corresponding number of operations is the user's visit number. to obtain statistics. In the buried point event set, the number of operations of the target operation corresponding to each reference buried point event can be expressed according to the conversion path in the conversion path set. Exemplarily, the buried point event set can be recorded as (the reference included in path 1 The number of operations of the target operation corresponding to the buried event, and the number of operations of the target operation corresponding to the reference buried event included in path 2).

Step 103, based on the conversion path set and the buried point event set, determine the target contribution coefficient of the target buried point event.

Among them, based on the conversion path set and buried point event set, the target contribution coefficient of the target buried point event is determined to determine the analysis result of the event according to the target contribution coefficient. The target contribution coefficient is used to indicate that the target buried point event is converted to conversion in the target business Contribution to the goal process.

In the embodiment of the present application, the event analysis device analyzes the conversion path set and the buried point event set, and obtains the degree of influence of all buried point events in the buried point event set on the conversion to conversion goal in the target business, and from Determine the target influence degree corresponding to the target buried point event from the influence degree corresponding to all buried point events, and then determine the target contribution coefficient according to the target influence degree and the influence degree corresponding to all buried point events. The analysis result of the event is the reference buried point event that can be abandoned in the marketing process or the reference buried point event that focuses on strengthening the marketing ratio. That is to say, after determining the target contribution coefficients of all buried events, compare and analyze the target contribution coefficients of all reference buried events, give up marketing considerations for reference buried events with the smallest target contribution coefficient, and/or enhance Target the marketing behavior of the reference buried event with a large target contribution coefficient to increase the conversion rate of the target business.

Based on the foregoing embodiments, the embodiments of the present application provide an event analysis method, as shown in FIG. 2 , the method is applied to an event analysis device, and the method includes the following steps:

Step 201 , determining a conversion path set in the target business that includes a conversion path that realizes the conversion goal.

In the embodiment of the present application, the conversion path set may be obtained by the event analysis device analyzing and determining the actual conversion process between buried events.

Exemplarily, it is assumed that the event analysis device analyzes the successfully converted conversion paths in the target business, and determines that the obtained conversion path set is: {start->E1->end, start->E1->E2->end, start- >E1->E2->E3->end}. Among them, the conversion path "Start->E1->End" indicates that the conversion can be completed after one reference event of E1, and "Start->E1->E2->End" indicates that two reference events of E1 and E2 are required To complete the conversion, "Start->E1->E2->E3->End" indicates that the conversion needs to go through three reference buried point events of E1, E2 and E3 to complete the conversion.

Step 202: Count the number of operations of the target operation corresponding to each reference buried point event in the conversion path set within a preset time period to obtain a buried point event set.

In the embodiment of the present application, the number of operations of the target operation is taken as the number of triggering users of the event as an example, and the set of buried point events obtained by statistics can be expressed as {(M, M1, N1), (M, M1, M2, N12), (M, M1, M2, M3, N123)}, where M represents the total number of users at the beginning, M1 represents the number of users entering the reference event E1, and M2 represents the number of users entering the reference event E2 , M3 represents the number of users who entered the reference event E3, N1 represents the number of users who successfully converted after the reference event E1, N12 represents the number of users who successfully converted after the reference event E1 and E2, N123 represents the number of users who passed the reference event The number of users who successfully converted after point events E1, E2, and E3.

Step 203, based on the set of conversion paths and the set of embedded events, determine the comprehensive conversion coefficient.

Wherein, the comprehensive conversion coefficient is used to represent the conversion rate of all the conversion paths included in the conversion path set to the realization of the conversion goal in the target business.

In the embodiment of the present application, the conversion path set and buried point event set are analyzed to determine the conversion rate of all conversion paths successfully converted, and obtain the comprehensive conversion coefficient. The comprehensive conversion coefficient may be obtained by analyzing the path conversion rates of all conversion paths.

Step 204: Based on the set of conversion paths, the set of buried point events and the comprehensive conversion coefficient, determine the degree of influence corresponding to each reference buried point event, and obtain the degree of influence corresponding to m reference buried point events.

Wherein, m is the number of buried point events included in the buried point event set.

In the embodiment of the present application, statistical analysis is performed on the conversion path set, buried point event set, and comprehensive conversion coefficient to determine the influence degree corresponding to each reference buried point event, thereby obtaining the influence degree corresponding to m reference buried point events.

Step 205: Determine the target contribution coefficient based on the influence degrees corresponding to the m reference buried point events and the target buried point event.

Wherein, the target contribution coefficient is used to represent the contribution of the target embedded event in the process of converting the target business into the conversion target.

In the embodiment of the present application, the influence degree corresponding to the target buried point event is determined from the influence degrees corresponding to the m reference buried point events, and the influence degree corresponding to the target buried point event and the influence degree corresponding to the m reference buried point events are determined. Analyze and determine the target contribution coefficient corresponding to the target buried point event. The target buried point event may be any one of the m reference buried point events.

In this way, by analyzing the conversion path set and buried point event set of the target business, the comprehensive conversion coefficient is determined, and the influence degree corresponding to each reference buried point event is further determined, so as to achieve the goal of each reference buried point event in the target The impact of the conversion process in the business is quantified using a unified standard, so that effective comparison and analysis can be carried out, which effectively reduces the probability of human intervention or even cheating in the analysis process, and improves the reliability of the target contribution coefficient of the target buried point event.

Based on the foregoing embodiments, in other embodiments of the present application, step 203 may be implemented by steps 203a-203b:

Step 203a, based on the buried point event set, determine the path conversion rate of each conversion path in the conversion path set, and obtain n path conversion rates.

Wherein, n is the number of conversion paths included in the conversion path set.

In the embodiment of this application, the conversion rate of each buried point event in each conversion path is determined from the set of buried point events, and each conversion path is determined according to the conversion rate of the buried point events included in each conversion path The conversion rate of the path, so as to obtain the conversion rate of n paths.

Step 203b, based on the conversion rates of the n paths, determine the comprehensive conversion coefficient.

In the embodiment of the present application, the event analysis device analyzes the determined conversion rates of the n paths to determine a comprehensive conversion coefficient. The comprehensive conversion coefficient can be obtained by simple summation of the conversion rates of the determined n paths, or by weighted summation of the conversion rates of the n paths.

Exemplarily, the comprehensive conversion coefficient can be recorded as N1/M+N12/M+N123/M=(N1+N12+N123)/M.

In this way, when determining the target contribution coefficient, the path conversion rate of all conversion paths in the conversion path set is also fully considered, and the comprehensive conversion coefficient is determined according to the path conversion rate of all conversion paths, so as to determine the impact according to the comprehensive conversion coefficient. degree, and finally realize the determination of the target contribution coefficient, which effectively guarantees the reliability of the target contribution coefficient.

Based on the foregoing embodiments, in other embodiments of the present application, step 203a may be implemented by steps a11-a12:

Step a11, from the set of buried point events, determine the first number of operations corresponding to the starting point of each conversion path in the conversion path set and the corresponding second number of operations corresponding to the end point of each conversion path.

In this embodiment of the application, for the conversion path "start->E1->end", the corresponding first number of operations is M, and the corresponding second number of operations is N1; for the conversion path "start->E1->E2- >End", the corresponding number of first operations is M, and the corresponding number of second operations is N12; for the conversion path "Start->E1->E2->E3->End", the corresponding number of first operations is M, The corresponding second number of operations is N123.

Step a12, based on each second number of operations and the corresponding first number of operations, n path conversion rates are obtained.

In the embodiment of the present application, for the conversion path "Start->E1->End", analyze the first number of operations M and the second number of operations N1, and determine the conversion path "Start->E1->End" Conversion rate, the path conversion rate of the conversion path "Start->E1->End" can specifically be the ratio of the second number of operations N1 to the first number of operations M; for the conversion path "Start->E1->E2->End" , analyze the first number of operations M and the second number of operations N12, and determine the path conversion rate of the conversion path "Start->E1->E2->End", and the conversion path "Start->E1->E2-> The path conversion rate of "End" can specifically be the ratio of the second number of operations N12 to the first number of operations M; for the conversion path "Start->E1->E2->E3->End", the first number of operations is M and The second number of operations N123 is analyzed to determine the path conversion rate of the conversion path "start->E1->E2->E3->end", which may be the ratio of the second number of operations N123 to the first number of operations M.

In this way, the path conversion rate of each conversion path is determined by the final target number of successful conversions and the initial target number, which can be consistent with the actual situation and ensure the accuracy of the path conversion rate of each conversion path.

Based on the foregoing embodiments, in other embodiments of the present application, step 204 may be implemented by steps 204a-204d:

Step 204a, based on the buried point event set, determine the path conversion rate of each conversion path in the conversion path set, and obtain n path conversion rates.

Step 204b, from the set of conversion paths, determine p target conversion paths that do not include each reference buried point event.

Wherein, p is a positive integer greater than or equal to 0.

In the embodiment of this application, from the conversion path set {start->E1->end, start->E1->E2->end, start->E1->E2->E3->end}, it is determined not to include The target conversion path of the reference buried point event E1 is 0; the target conversion path excluding the reference buried point event E2 is start->E1->end, p=1; the target conversion path excluding the reference buried point event E3 is Start->E1->End and Start->E1->E2->End, p=2.

Step 204c, from the n path conversion rates, determine the path conversion rates corresponding to the p target conversion paths, and obtain the p target conversion rates corresponding to each reference buried point event.

In the embodiment of this application, for the reference buried point event E1, the corresponding target conversion path is 0, therefore, the target conversion rate corresponding to the reference buried point event E1 is 0; for the reference buried point event E2, the corresponding target conversion rate is 0 The conversion rate is the path conversion rate of the start->E1->end of the target conversion path; for the reference buried point event E3, the corresponding two target conversion rates are the conversion rate of the start->E1->end path and the start->E1- >E2->End Path Conversion Rate.

Step 204d, based on the preset coefficients, p target conversion rates and comprehensive conversion coefficients, determine the influence degree of each corresponding reference buried point event, and obtain the influence degree corresponding to m reference buried point events.

In the embodiment of this application, the cumulative sum of the P target conversion rates corresponding to each reference buried point event is calculated to obtain the target sum value; the ratio of the target sum value to the comprehensive conversion coefficient is calculated to obtain the target coefficient; for the preset coefficient and The target coefficient is analyzed and calculated to obtain the influence degree of each corresponding reference buried point event, thereby obtaining the influence degree corresponding to m reference buried point events. In this way, by calculating the path conversion rate of all target conversion paths that do not include the reference buried point event in the conversion path set, the influence degree of the reference buried point event can be determined, and the impact of the reference buried point event on the target business conversion can be fully and fully considered. The influence of other influences on the influence degree of the reference buried point event is excluded, which ensures the reliability of the determined influence degree of the reference buried point event.

Based on the foregoing embodiments, in other embodiments of the present application, step 204d may be implemented by steps b11-b12:

Step b11, based on the p target conversion rates and comprehensive conversion coefficients, determine the corresponding target coefficient for each reference buried point event.

Wherein, the target coefficient is used to represent the conversion rate of the target business to the conversion target process by the buried point events except for each corresponding reference buried point event.

In the embodiment of the present application, the cumulative sum of p target conversion rates is calculated to obtain the target sum, and the ratio of the target sum to the comprehensive conversion coefficient is calculated to obtain the corresponding target coefficient for each reference buried point event.

Step b12, based on the preset coefficient and the target coefficient, determine the degree of influence of each corresponding reference buried point event, and obtain the degree of influence corresponding to the m reference buried point events.

In the embodiment of the present application, the difference between the preset coefficient and the target coefficient is calculated to obtain the influence degree of the corresponding reference buried point event. That is, the degree of influence corresponding to each reference buried point event=preset coefficient-target coefficient=preset coefficient-target sum value/comprehensive conversion coefficient. Normally, the value of the preset coefficient is 1. However, in some application scenarios, the target coefficient can also be directly determined as the influence degree of each reference buried point event, that is, the default coefficient is 0. At this time, the greater the target contribution coefficient of the corresponding final calculated target reference tracking event, the smaller the impact of the target reference tracking event on the conversion of the target business.

Exemplarily, the influence degree of the reference buried point event E1 can be recorded as 1-0/((N1+N12+N123)/M)=1; the influence degree of the reference buried point event E2 can be recorded as 1-(N1/M )/((N1+N12+N123)/M)=1-N1/(N1+N12+N123); refer to 1-((N1/M)/((N1+N12+N123)/ M)+(N12/M)/((N1+N12+N123)/M))＝1-(N1+N12)/(N1+N12+N123), in this way, 3 reference buried points corresponding to reference events degree of influence.

In this way, by analyzing the corresponding conversion rate when the reference buried point event is not included, the influence degree of the reference buried point event on the conversion process is determined, and other factors in the determination process of the influence degree corresponding to the reference buried point event are excluded. The influence of factors realizes the digital measurement of the influence of each reference buried point event on the transformation process, reduces the possibility of human intervention, and ensures the accuracy of the determined influence degree of each reference buried point event.

Based on the foregoing embodiments, in other embodiments of the present application, step 205 may be implemented by steps 205a-205b:

Step 205a, from the influence degrees corresponding to the m reference buried point events, determine the target influence degree corresponding to the target buried point event.

Step 205b: Determine the target contribution coefficient based on the target influence degree and the influence degrees corresponding to the m reference buried point events.

In the embodiment of this application, the cumulative sum of influence degrees corresponding to m reference buried point events is calculated, and then the cumulative sum of influence degrees corresponding to the target influence degree and m reference buried point events is analyzed to determine the target contribution coefficient.

Based on the foregoing embodiments, in other embodiments of the present application, step 205b may be implemented by steps c11-c12:

Step c11, based on the influence degrees corresponding to the m reference buried point events, determine the collective influence degree of the m reference buried point events.

In the embodiment of the present application, the collective influence degree of the m reference buried point events can be obtained by summing the influence degrees corresponding to the m reference buried point events. The sum processing method can be a simple accumulation and analysis method, or a weighted accumulation and analysis method.

Step c12. Determine the ratio between the target influence degree and the collective influence degree to obtain the target contribution coefficient.

In the embodiment of the present application, the ratio of the target influence degree to the cumulative sum of the influence degrees corresponding to m reference buried point events is calculated to obtain the target contribution coefficient corresponding to the target buried point event.

Exemplarily, when the target buried point event is E1, the target contribution coefficient corresponding to E1 is 1/(1+(1-N1/(N1+N12+N123))+(1-(N1+N12)/(N1+ N12+N123)))=1/{3-(2N1+N12)/(N1+N12+N123)}. In this way, by calculating the ratio between the target influence degree of the target buried point event and the collective influence degree as the target contribution coefficient of the target buried point event, the target influence degree of each reference buried point event is uniformly standardized, which is convenient The comparative analysis between the reference buried point events improves the comparative analysis efficiency.

Based on the foregoing embodiments, in other embodiments of the present application, referring to FIG. 3 , after the event analysis device executes step 205, it is also used to execute steps 206-207:

Step 206: If it is determined that the target contribution coefficient of each reference buried point event in the conversion path set is obtained, compare and analyze the target contribution coefficients of the reference buried point events included in the conversion path set, and determine that the buried point event can be discarded.

In the embodiment of the present application, through the method of steps 201-205, the target contribution coefficient of each reference buried point event is determined, and then the size of the target contribution coefficients included in the conversion path set to remove all reference buried point events is compared and analyzed, Determining a reference tracking point event with a smaller target contribution coefficient as an abandonable tracking point event, or determining a reference tracking point event with a target contribution coefficient smaller than a preset threshold as a abandonable tracking point event.

Step 207: Generate prompt information based on the event that can be discarded.

Wherein, the prompt information is used to prompt that the buried event can be ignored or discarded in the target business.

In the embodiment of the present application, the event analysis device generates prompt information for prompting that the buried event can be ignored or discarded, and displays it at the target display area corresponding to the event analysis device. The target display area corresponding to the event analysis device may be a time analysis The display screen of the device may also be an electronic device with a display function that has a communication connection with the event analysis device.

In this way, through the prompt information indicating that the tracking event can be abandoned, the merchant can make corresponding adjustments to the target business, such as no longer setting the tracking event that can be abandoned, which helps to invest resources in the most important tracking events corresponding to channels to maximize resource efficiency.

Based on the foregoing embodiments, this embodiment of the present application provides an event analysis method, in which the corresponding buried point event set can be recorded as (A, B, C, D), and the corresponding event transformation path can be referred to in Figure 4 , where the conversion path includes a start and an end, and it is a successful conversion path. In this way, it can be determined from Figure 4 that the obtained conversion path set is (A→B, A→C, A→B→C), correspondingly, the value on each path in Figure 4 represents the triggering of each buried point event number of customers. Specifically, it can be expressed as: M=1000, for conversion path A→B: M(A)=1000, M(B)=375, N(A,B)=125; for conversion path A→C: M(A) =1000, M(A,C)=425, N(A,C)=400; for conversion path A→B→C: M(A)=1000, M(A,B)=375, M(A, B,C)=125, N(A,B,C)=100.

In this way, after calculating the conversion rate of each buried point event in each path, the conversion rate of each buried point event can be obtained by multiplying the conversion rate of each buried point event. Correspondingly, the path conversion rate of the conversion path Start→A→B→End can be recorded as: P(A,B)=M(A)/M*M(B)/M(A)*N(A,B) /M(B)＝N(A,B)/M＝1000/1000*375/125*125/375＝0.125; the path conversion rate of conversion path Start→A→C→End can be recorded as: P(A, C)＝M(A)/M*M(C)/M(A)*N(A,C)/M(C)＝N(A,C)/M＝1000/1000*425/1000*400 /425＝0.4; the path conversion rate of the conversion path Start→A→B→C→End can be recorded as: P(A,B,C)＝M(A)/M*M(B)/M(A)* M(C)/M(B)N(A,B,C)/M(C)＝N(A,B,C)/M＝1000/1000*375/1000*125/375*100/125＝ 0.1. In this way, based on P(A,B), P(A,C) and P(A,B,C), it can be determined that the comprehensive conversion coefficient P=P(A,B)+P(A,C)+P( A, B, C)=N(A,B)/M+N(A,C)/M+N(A,B,C)/M=0.125+0.4+0.1=0.625.

For buried event A, it can be seen that there is no successful conversion path after removing buried event A. Therefore, the target conversion rate corresponding to buried event A is 0, and the influence degree of buried event A is Q(A)=1– 0/0.625=1. For buried event B, after removing buried event B, it corresponds to a target conversion path P(A,C). Therefore, the target conversion rate corresponding to buried event B is P(A,C)=0.4, then buried event B The degree of influence Q(B)=1-0.4/0.625=0.36. For the buried event C, after removing the buried event C, it corresponds to a target conversion path P(A,B). Therefore, the target conversion rate corresponding to the buried event C is P(A,B)=0.125, then the buried event C The degree of influence Q(C)=1-0.125/0.626=0.8.

Therefore, it can be determined that the target contribution coefficient of buried point event A=Q(A)/(Q(A)+Q(B)+Q(C))=1/(1+0.36+0.8)=(1-0/ 0.625)/(1-0/0.625)+(1-0.4/0.625)+(1-0.125/0.626)＝0.463, similarly, the target contribution coefficient of event B＝0.36/(1+0.36+0.8) =0.277, and the target contribution coefficient of event C of buried point=0.8/(1+0.36+0.8)=0.37.

From this, it can be concluded that each buried event is important in the entire business operation. Under the condition of limited resources, the target contribution coefficient of buried event B is the smallest, and the target contribution coefficient of buried event A and buried event C Relatively large, it has a great effect on the overall transformation of the business. In this way, in the actual business process, the channel corresponding to event B can be abandoned, and resources can be invested in the most important channel to maximize resource efficiency.

In this way, this solution combines the conversion rate of the specific buried event conversion path to accurately quantify the target contribution coefficient of each buried event, providing marketing conversion reference for operation analysts, and avoiding linear trigger methods, location trigger methods, and time decay methods, etc. The selective bias brought about by the method allows limited resources to be invested in more effective buried events or channels to achieve a more accurate increase in business conversion rate.

It should be noted that, for descriptions of the same steps and content in this embodiment as in other embodiments, reference may be made to the descriptions in other embodiments, and details are not repeated here.

Based on the foregoing embodiments, an embodiment of the present application provides an event analysis device. Referring to FIG. 5 , the event analysis device 3 may include: a processor 31, a memory 32, and a communication bus 33, wherein:

Memory 32, used to store executable instructions;

A communication bus 33 is used to realize the communication connection between the processor 31 and the memory 32;

The processor 31 is used to execute the event analysis program stored in the memory 32, so as to realize the following steps:

Count the operation times of the target operation corresponding to each reference buried point event in the conversion path set within the preset time period, and obtain the buried point event set;

Determine the target contribution coefficient of the target buried point event based on the conversion path set and the buried point event set, so as to determine the analysis result of the event according to the target contribution coefficient; where the target contribution coefficient is used to indicate that the target buried point event is converted to conversion in the target business Contribution to the goal process.

In other embodiments of the present application, when the processor 31 executes the step of determining the target contribution coefficient of the target buried point event based on the conversion path set and the buried point event set, the following steps can be implemented:

Determine the comprehensive conversion coefficient based on the conversion path set and the embedded point event set; wherein, the comprehensive conversion coefficient is used to represent the conversion rate of all the conversion paths included in the conversion path set to the target business to achieve the conversion goal;

Based on the conversion path set, buried point event set and comprehensive conversion coefficient, the influence degree corresponding to each reference buried point event is determined, and the influence degree corresponding to m reference buried point events is obtained; where m is the buried point included in the buried point event set the number of point events;

Determine the target contribution coefficient based on the influence degrees corresponding to the m reference buried point events and the target buried point event.

In other embodiments of the present application, when the processor 31 executes the step of determining the comprehensive conversion coefficient based on the conversion path set and the buried point event set, the following steps can be implemented:

Based on the buried point event set, determine the path conversion rate of each conversion path in the conversion path set, and obtain n path conversion rates; wherein, n is the number of conversion paths included in the conversion path set;

Based on the conversion rates of the n paths, the comprehensive conversion coefficient is determined.

In other embodiments of the present application, the processor 31 performs steps to determine the path conversion rate of each conversion path in the conversion path set based on the set of buried point events, and obtain the conversion rates of n paths, which can be achieved by the following steps:

From the buried point event set, determine the first number of operations corresponding to the starting point of each conversion path in the conversion path set and the corresponding second number of operations corresponding to the end point of each conversion path;

Based on each second number of operations and the corresponding first number of operations, n path conversion rates are obtained.

In other embodiments of the present application, the processor 31 performs steps to determine the influence degree corresponding to each reference buried point event based on the conversion path set, buried point event set and comprehensive conversion coefficient, and obtain the influence degree corresponding to m reference buried point events , it can be achieved through the following steps:

From the set of conversion paths, determine p target conversion paths excluding each reference buried point event; wherein, p is a positive integer greater than or equal to 0;

From the n path conversion rates, determine the path conversion rates corresponding to the p target conversion paths, and obtain the p target conversion rates corresponding to each corresponding reference buried point event;

Based on the preset coefficients, p target conversion rates and comprehensive conversion coefficients, determine the degree of influence of each corresponding reference buried point event, and obtain the degree of influence corresponding to the m reference buried point events.

In other embodiments of the present application, the processor 31 performs steps to determine the influence degree of each corresponding reference buried point event based on preset coefficients, p target conversion rates and comprehensive conversion coefficients, and obtain the corresponding Influence can be achieved through the following steps:

Based on p target conversion rates and comprehensive conversion coefficients, determine the corresponding target coefficient for each reference buried point event; wherein, the target coefficient is used to indicate that the buried point events other than each corresponding reference buried point event have an impact on the target business. the conversion rate of the conversion goal process;

Based on the preset coefficient and the target coefficient, the degree of influence of each corresponding reference buried point event is determined, and the degree of influence corresponding to the m reference buried point events is obtained.

In other embodiments of the present application, when the processor 31 executes the step of determining the target contribution coefficient based on the influence degree corresponding to the m reference buried point events and the target buried point event, the following steps may be implemented:

From the influence degrees corresponding to the m reference buried point events, determine the target influence degree corresponding to the target buried point event;

Determine the target contribution coefficient based on the target influence degree and the influence degrees corresponding to the m reference buried point events.

In other embodiments of the present application, when the processor 31 executes the step of determining the target contribution coefficient based on the target influence degree and the influence degrees corresponding to the m reference buried point events, the following steps can be implemented:

Based on the influence degrees corresponding to the m reference buried point events, determine the collective influence degree of the m reference buried point events;

Determine the ratio between the target influence degree and the collective influence degree to obtain the target contribution coefficient.

In other embodiments of the present application, after the processor 31 executes the step of determining the target contribution coefficient of the target buried point event based on the conversion path set and the buried point event set, it is also used to perform the following steps:

If it is determined that the target contribution coefficient of each reference buried point event in the conversion path set is obtained, compare and analyze the target contribution coefficients of the reference buried point events included in the conversion path set, and determine that the buried point event can be discarded;

Prompt information is generated based on the burying event that can be abandoned; wherein, the prompt information is used to prompt that the burying event that can be ignored in the target business can be ignored.

It should be noted that one or more programs in the embodiment of the present application can be explained by the steps of one or more processors, and the implementation process of the method provided by the embodiment corresponding to Figures 1 to 3 can be referred to, and will not be repeated here. .

Based on the foregoing embodiments, the embodiments of the present application provide a computer-readable storage medium, referred to as a storage medium for short, where one or more programs are stored in the computer-readable storage medium, and the one or more programs can be used by one or more The processor executes to implement the implementation process of the event analysis method provided in the embodiments corresponding to FIGS. 1 to 3 , which will not be repeated here.

The above are only examples of the present application, and are not intended to limit the scope of protection of the present application. All modifications, equivalent replacements and improvements made within the spirit and scope of this application are included within the protection scope of this application.

Industrial Applicability

An embodiment of the present application provides an event analysis method, device, and storage medium, including: determining a conversion path set in the target business that includes a conversion path that achieves the conversion goal; Refer to the operation times of the target operation corresponding to the buried point event to obtain the buried point event set; based on the conversion path set and the buried point event set, determine the target contribution coefficient of the target buried point event, so as to determine according to the target contribution coefficient The analysis result of the event; wherein, the target contribution coefficient is used to represent the contribution of the target buried point event in the process of converting the target business to the conversion target, which solves the current problem of determining the contribution value of each buried point event For the problem that the method is relatively simple, a method for dynamically determining the contribution value of each buried point event is implemented, which enriches the method for determining the contribution value of each buried point event, so that the determined contribution value of each buried point event is in line with the actual situation.

Claims

A method for event analysis, the method comprising:

Determining a set of conversion paths in the target business including conversion paths that achieve the conversion goal;

Counting the number of operations of the target operation corresponding to each reference buried point event in the conversion path set within a preset time period to obtain a buried point event set;

Based on the set of conversion paths and the set of buried point events, determine the target contribution coefficient of the target buried point event, so as to determine the analysis result of the event according to the target contribution coefficient; wherein, the target contribution coefficient is used to represent the target The contribution of the buried point event in the process of converting the target business to the conversion target.
The method according to claim 1, wherein said determining the target contribution coefficient of the target buried point event based on the set of conversion paths and the set of buried point events includes:

Based on the set of conversion paths and the set of embedded events, determine a comprehensive conversion coefficient; wherein, the comprehensive conversion coefficient is used to indicate that all conversion paths included in the conversion path set are effective in achieving the conversion goal in the target business conversion rate;

Based on the set of conversion paths, the set of buried point events and the comprehensive conversion coefficient, determine the degree of influence corresponding to each of the reference buried point events, and obtain the degree of influence corresponding to m reference buried point events; where m is The number of buried point events included in the set of buried point events;

The target contribution coefficient is determined based on the influence degrees corresponding to the m reference buried point events and the target buried point event.
The method according to claim 2, wherein said determining a comprehensive conversion coefficient based on said conversion path set and said buried point event set includes:

Based on the buried event set, determine the path conversion rate of each conversion path in the conversion path set, and obtain n path conversion rates; wherein, n is the number of conversion paths included in the conversion path set;

Based on the conversion ratios of the n paths, determine and obtain the comprehensive conversion coefficient.
The method according to claim 3, wherein, based on the buried point event set, determining the path conversion rate of each conversion path in the conversion path set to obtain n path conversion rates includes:

From the buried point event set, determine the first number of operations corresponding to the starting point of each conversion path in the conversion path set and the corresponding second number of operations corresponding to the end point of each conversion path ;

Based on each of the second number of operations and the corresponding first number of operations, n path conversion rates are obtained.
The method according to claim 2, wherein, based on the set of conversion paths, the set of buried point events and the comprehensive conversion coefficient, determine the degree of influence corresponding to each of the reference buried point events, and obtain m Refer to the influence degree corresponding to the buried point event, including:

Based on the buried event set, determine the path conversion rate of each conversion path in the conversion path set, and obtain n path conversion rates; wherein, n is the number of conversion paths included in the conversion path set;

From the set of conversion paths, determine p target conversion paths that do not include each of the reference buried point events; wherein, p is a positive integer greater than or equal to 0;

From the n path conversion rates, determine the path conversion rates corresponding to the p target conversion paths, and obtain the p target conversion rates corresponding to each of the corresponding reference buried point events;

Based on the preset coefficient, the p target conversion rates and the comprehensive conversion coefficient, determine the degree of influence of each of the corresponding reference buried point events, and obtain the degree of influence corresponding to the m reference buried point events.
The method according to claim 5, wherein, based on the preset coefficient, the p target conversion rate and the comprehensive conversion coefficient, the degree of influence of each of the corresponding reference buried point events is determined to obtain m The degree of influence corresponding to the reference buried point event includes:

Based on the p target conversion rates and the comprehensive conversion coefficients, determine the corresponding target coefficient of each of the reference buried point events; wherein, the target coefficient is used to represent the division of each of the corresponding reference buried point events The conversion rate of the conversion of the target business to the conversion target process by the external buried point event;

Based on the preset coefficient and the target coefficient, the degree of influence corresponding to each of the reference buried point events is determined, and the degree of influence corresponding to the m reference buried point events is obtained.
The method according to any one of claims 2 to 6, wherein the determination of the target contribution coefficient based on the influence degrees corresponding to the m reference buried point events and the target buried point event includes:

From the influence degrees corresponding to the m reference buried point events, determine the target influence degree corresponding to the target buried point event;

The target contribution coefficient is determined based on the target influence degree and the influence degrees corresponding to the m reference buried point events.
The method according to claim 7, wherein the determination of the target contribution coefficient based on the target influence degree and the influence degrees corresponding to the m reference buried point events includes:

Based on the influence degrees corresponding to the m reference buried point events, determine the collective influence degree of the m reference buried point events;

Determine the ratio between the target influence degree and the collective influence degree to obtain the target contribution coefficient.
The method according to claim 1, wherein, after determining the target contribution coefficient of the target buried point event based on the conversion path set and the buried point event set, the method further includes:

If it is determined that the target contribution coefficient of each of the reference buried point events in the conversion path set is obtained, compare and analyze the target contribution coefficients of the reference buried point events included in the conversion path set, and determine that the buried point can be discarded event;

Prompt information is generated based on the abandonable tracking event; wherein, the prompt information is used to prompt that the abandonable tracking event can be ignored in the target service.
An event analysis device, the device comprising: a memory, a processor, and a communication bus; wherein:

The memory is used to store executable instructions;

The communication bus is used to realize the communication connection between the processor and the memory;

The processor is configured to execute the event analysis program stored in the memory to realize the steps of the event analysis method according to any one of claims 1-9.
A storage medium, an event analysis program is stored on the storage medium, and when the event analysis program is executed by a processor, the steps of the event analysis method according to any one of claims 1 to 9 are realized.