CN114358852A

CN114358852A - Online donation behavior pattern analysis method and related equipment

Info

Publication number: CN114358852A
Application number: CN202210018550.0A
Authority: CN
Inventors: 吕欣; 蔡梦思; 王梦宁; 郭淑慧; 谭跃进
Original assignee: National University of Defense Technology
Current assignee: National University of Defense Technology
Priority date: 2022-01-07
Filing date: 2022-01-07
Publication date: 2022-04-15

Abstract

The application provides an online donation behavior pattern analysis method and related equipment. The method comprises the following steps: acquiring a user set and a contribution record set corresponding to the user set, wherein the number of contributions of the user set is greater than a preset number of contributions in an online contribution platform, the contribution record set comprises a contribution record corresponding to each user in the user set, and each contribution record comprises a plurality of contribution amount data; sequencing all donation amount data in the donation records of any user according to the donation time to obtain initial donation amount sequence data; taking a predetermined amount of the donation amount data therefrom as the donation amount sequence data; determining a behavioral characteristic indicator of the user based on the data; reconstructing the data to obtain feature description data, and obtaining a behavior feature set based on the data; and clustering the behavior feature set to obtain different donation behavior pattern categories. The complexity analysis of the online donation behavior is realized, and meanwhile, a reference is provided for the improvement of the success rate of the crowd funding project.

Description

Online donation behavior pattern analysis method and related equipment

Technical Field

The application relates to the technical field of information analysis, in particular to an online donation behavior pattern analysis method and related equipment.

Background

The rapid development of the online crowd funding platform changes the traditional funding and contribution modes, summarizes the online contribution behavior characteristics and behavior modes of the users, is favorable for revealing the online crowd funding behavior rules of the users, and provides reference suggestions for improving the success rate of crowd funding projects.

Based on the situation, in the prior art, the analysis of success rate influence factors of the online crowd funding project and the ethical and moral problems of the online crowd funding project are mainly concerned, the complexity analysis of the online contribution behavior of the user is rarely concerned, and reference cannot be provided for revealing the online crowd funding behavior rule of the user and improving the success rate of the crowd funding project.

Disclosure of Invention

In view of the above, an objective of the present application is to provide an online donation behavior pattern analysis method and related devices, so as to solve the above technical problems.

Based on the above objectives, a first aspect of the present application provides an online donation behavior pattern analysis method, including:

acquiring a user set with the donation times larger than the preset times in an online donation platform and a donation record set corresponding to the user set, wherein the donation record set comprises donation records corresponding to each user in the user set, and each donation record comprises a plurality of donation amount data;

sequencing all the donation amount data in the donation record of any user according to donation time to obtain initial donation amount sequence data;

taking a predetermined amount of the contribution amount data from the initial contribution amount sequence data as the contribution amount sequence data of the any user;

determining a behavioral characteristic indicator for the any user based on the contribution amount sequence data;

reconstructing the behavior characteristic index of any user to obtain characteristic description data of any user, and taking all the characteristic description data corresponding to all the users in the user set as a behavior characteristic set;

and clustering the behavior feature set to obtain different donation behavior pattern categories.

A second aspect of the application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of the first aspect when executing the program.

As can be seen from the above, according to the online contribution behavior pattern analysis method and the related device provided by the application, the corresponding contribution amount sequence data of each user acquired from the online contribution platform is processed to obtain the corresponding behavior characteristic index, the complexity analysis of the online contribution behavior is realized by using the behavior characteristic index, the contribution behavior characteristics of the users are described, and different user contribution behavior pattern categories are obtained through clustering, so that the online crowd funding behavior rules of the users are revealed, and a reference is provided for improving the success rate of crowd funding projects.

Drawings

In order to more clearly illustrate the technical solutions in the present application or the related art, the drawings needed to be used in the description of the embodiments or the related art will be briefly introduced below, and it is obvious that the drawings in the following description are only embodiments of the present application, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without creative efforts.

FIG. 1 is a flowchart of an online donation behavior pattern analysis method according to an embodiment of the present disclosure;

fig. 2 is a diagram illustrating a clustering result of user contribution behaviors according to an embodiment of the present application;

FIG. 3-a is a diagram illustrating a distribution of user contributions diversity index for different clusters, according to an embodiment of the present disclosure;

FIG. 3-b is a diagram illustrating an uncertainty indicator distribution of user contributions under different cluster clusters, according to an embodiment of the present disclosure;

FIG. 3-c is a graph illustrating a distribution of centralized indicators of user contributions under different clusters, according to an embodiment of the present disclosure;

FIG. 3-d is a graph illustrating a distribution of consistency indicators of user contributions for different clusters, according to an embodiment of the present disclosure;

FIG. 4-a is a display diagram of a random pattern in a user donation behavior pattern according to one embodiment of the present application;

4-b is a diagram illustrating a stable pattern in a user contribution behavior pattern according to an embodiment of the present application;

FIG. 5 is a schematic structural diagram of an online donation behavior pattern analysis device according to an embodiment of the present disclosure;

fig. 6 is a schematic diagram of an electronic device according to an embodiment of the present application.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is further described in detail below with reference to the accompanying drawings in combination with specific embodiments.

It should be noted that technical terms or scientific terms used in the embodiments of the present application should have a general meaning as understood by those having ordinary skill in the art to which the present application belongs, unless otherwise defined. The use of "first," "second," and similar terms in the embodiments of the present application do not denote any order, quantity, or importance, but rather the terms are used to distinguish one element from another. The word "comprising" or "comprises", and the like, means that the element or item listed before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "upper", "lower", "left", "right", and the like are used merely to indicate relative positional relationships, and when the absolute position of the object being described is changed, the relative positional relationships may also be changed accordingly.

In the related technology, the complexity analysis of the online contribution behavior of the user is rarely concerned, and the reference cannot be provided for improving the success rate of the crowd funding project.

The embodiment of the application provides an online donation behavior pattern analysis method, donation amount time sequence data of each user in an online donation platform are obtained, then diversity indexes, uncertainty indexes, concentration indexes and consistency indexes of the donation amounts of the users are calculated to describe characteristics of user donation behaviors, the donation amount time sequence data are converted into characteristic sets, the characteristic sets are clustered into different donation behavior pattern categories, characteristics corresponding to the different donation behavior pattern categories are summarized, and reference is provided for improvement of the success rate of crowd funding projects.

As shown in fig. 1, the method of the present embodiment includes:

step 101, acquiring a user set with donation times greater than a preset number in an online donation platform and a donation record set corresponding to the user set, wherein the donation record set comprises donation records corresponding to each user in the user set, and each donation record comprises a plurality of donation amount data.

In the step, the user sets with the donation times larger than the preset times are obtained from the online donation platform, and the donation record sets corresponding to the user sets are exported, so that the donation record sets corresponding to the obtained large number of user sets are prepared as analyzed data, and the accuracy of analysis is further guaranteed.

And 102, sequencing all the donation amount data in the donation record of any user according to donation time to obtain initial donation amount sequence data.

In this step, the initial contribution amount sequence data is a set of data in which all the contribution amount data in the contribution record of any user are arranged in the order of contribution time.

Step 103, taking a predetermined amount of the donation amount data from the initial donation amount sequence data as the donation amount sequence data of any one user.

In this step, the donation amount sequence data is a set of data consisting of a predetermined number of donation amount data selected from the initial donation sequence data obtained by arranging in order of donation time.

And 104, determining a behavior characteristic index of any user based on the contribution amount sequence data.

In the step, the behavior characteristic index of any user is determined according to the donation amount sequence data of the user, complexity analysis of online donation behaviors is carried out by utilizing the behavior characteristic index, the donation amount selection rule condition of the user is analyzed, the donation behavior characteristics of the user are described according to the rule condition, different users have different preferences in donation amount selection, and understanding of complexity and regularity of the donation behaviors of the online users is promoted.

And 105, reconstructing the behavior characteristic index of any user to obtain characteristic description data of any user, and taking all the characteristic description data corresponding to all the users in the user set as a behavior characteristic set.

In the step, the user behavior characteristic index is reconstructed to obtain the characteristic description data of the user, so that the contribution amount sequence data is converted into the characteristic description data of the user contribution behavior, all the characteristic description data is used as a characteristic set, the characteristic of the contribution behavior of each user is analyzed more comprehensively, and further the subsequent analysis is more accurate.

And 106, clustering the behavior feature set to obtain different contribution behavior pattern categories.

In the step, clustering processing is carried out on the behavior feature set through a K-means clustering algorithm (K-means clustering algorithm), different contribution behavior pattern categories are obtained, and reference is provided for improving the success rate of crowd funding projects.

The donation behavior pattern class square error divided by the K-means clustering algorithm is minimum, and meanwhile, a large amount of dense feature sets can be efficiently processed, so that a better classification effect is obtained.

In the scheme, the donation amount sequence data corresponding to each user is acquired from the online donation platform, so that the acquired mass data are prepared as analyzed data, and the accuracy of analysis is further guaranteed. And processing the donation amount sequence data to obtain a corresponding behavior characteristic index, performing complexity analysis on online donation behaviors by using the behavior characteristic index, analyzing the donation amount selection rule condition of the user, describing the donation behavior characteristics of the user according to the rule condition, promoting the understanding of the complexity and regularity of the donation behaviors of the online user, obtaining different user donation behavior pattern categories through clustering, and providing reference for improvement of the success rate of the funding project.

In some embodiments, step 104 specifically includes:

determining a sequence set of amounts comprising different values of donation amounts from the donation amount data in the donation amount sequence data of any one of the users;

and obtaining the behavior characteristic indexes of any user based on the money sequence set, wherein the behavior characteristic indexes comprise diversity indexes, uncertainty indexes, concentration indexes and consistency indexes.

In this step, the amount sequence set is a set of data composed of different values of the donation amount in the donation amount sequence data of any user, and the behavior characteristic index of the user is obtained through the amount sequence set, and the behavior characteristic index includes a diversity index, an uncertainty index, a concentration index and a consistency index, so as to characterize the donation behavior of the user.

In some embodiments, the contribution amount data for any of the users is obtained from the collection of users, and a first amount of the contribution amount data in the contribution amount data is obtained;

determining the sequence set of amounts based on the donation amount sequence data and obtaining a second amount of the donation amount data in the sequence set of amounts;

obtaining the diversity index through the first number and the second number, wherein the diversity index is specifically:

wherein k is represented as the first number; | S' | represents the second number; dy is expressed as the diversity index.

In this step, the user may select a different contribution amount in each contribution, and the difference of the contribution amount data in the user contribution amount sequence data is measured by the diversity index.

For example, if a user has 5 donation records, and its sequence data S is ═ 10, 20, 10, 20, 30], then its sequence set is S '═ 10, 20, 30], then the diversity index of the user' S donation data is equal to 3/5.

In some embodiments, a third amount of any of said contribution amount data in said contribution amount sequence data is obtained;

obtaining probability information of the donation amount data based on the third amount;

obtaining the uncertainty index based on the probability information, wherein the uncertainty index specifically comprises:

wherein p is_iRepresenting probability information of selecting any donation amount data from the donation amount sequence data for any user to donate, and the calculation formula is

c_iRepresenting as said third amount the number of times that said contribution amount data is selected by said any user to contribute; i is expressed as the ith said donation amount data in said sequence set of amounts; uy is expressed as the uncertainty indicator.

In the step, in order to further analyze the rule of the user selecting the donation amount, the uncertainty index of the user selected donation amount data is quantified through entropy. The essence of entropy is a system "inherent degree of confusion," which in user contribution behavior describes the degree of confusion of the amount of the contribution selected in the user contribution record.

In some embodiments, the concentration indicator is obtained based on the third amount, and the concentration indicator specifically is:

wherein, max (c)_i) Representing the number of donations corresponding to the donation amount data most frequently used by said any user; cn is expressed as the centrality indicator.

In this step, in order to describe whether the user tends to select fixed donation amount data for donation in each donation, the proportion of the number of donation amount data with differences in all amount sequence sets of the donation amount frequently used by the user is measured through the concentration index, and the probability that the most frequently used donation amount data is selected when the user selects the donation is reflected.

In some embodiments, two of the donation amount data that are adjacent in donation time are obtained based on the donation amount sequence data to form a donation pair;

acquiring all the donation amount data of the donation pairs;

obtaining the consistency index based on all the donation amount data, wherein the consistency index specifically comprises:

wherein s is_iSaid contribution amount data represented as an ith contribution; cy represents the consistency index; (s)_i，s_i+1) Representing said donation pair, s, consisting of two said donation amount data adjacent in donation time_i＝s_i+1，

s_i≠s_i+1，

In the step, the consistency of the donation amount data in every two consecutive donations of the user is measured through a consistency index, and the stability of the donation amount selection in time is reflected. The index reflects the probability that the user chooses the amount data equal to the previous donation amount when selecting the donation.

Wherein a greater consistency indicator indicates that the user is more stable in the selection of the donation amount data.

In some embodiments, step 106 specifically includes:

selecting the feature description data of any user in the user set from the behavior feature set as an initial cluster center for clustering;

acquiring distance information between the behavior feature description data of all the users and the initial cluster center of any user;

assigning the respective user to a nearest cluster based on the distance information;

in response to determining that all the users complete the allocation, updating a cluster center, reacquiring the distance information about the cluster center, and performing the user allocation according to the distance information;

different donation behavior pattern categories are derived in response to determining that a preset condition is reached.

In the step, the distance between the user and the cluster center is defined through the Euclidean distance by the K-means clustering algorithm, the category of the object is judged according to the distance, the feature description data in the user contribution behavior feature set is clustered into different user contribution behavior pattern categories, so that the square error of the different user contribution behavior pattern categories is minimum, meanwhile, a large amount of intensive feature sets are efficiently processed, a better classification effect is obtained, and a reference is provided for improving the success rate of crowd-funded projects.

The preset condition is an iteration termination condition of the K-means clustering algorithm, and the iteration termination condition of the K-means clustering algorithm is a certain limit that the feature description data of the user is not redistributed or the cluster center is not changed or the change distance of the iterated cluster center is smaller than the initial cluster center.

In some embodiments, the cluster center is specifically:

wherein, c_kDenoted as kth cluster, k representing the number of different donation behavior pattern categories; m is_kIs represented as a cluster c_kThe cluster center of (a); l c_kI is represented as a cluster c_kThe total number of said users in (a); x'_iThe profile data represented as the user i.

In the step, the feature description data of the users are divided based on the cluster center, and the feature description data of all the users are divided into different donation behavior model categories by iteratively updating the cluster center.

In some embodiments, the distance information is specifically:

wherein p represents the total amount of characteristic index information contained in the characteristic description data; a is expressed as the a-th feature index information in the feature description data.

In the step, the donation behavior model of the user is classified according to the distance information between the characteristic description data of the user and the cluster center.

In some embodiments, 16494 (specifically, may be specifically set according to actual conditions, and is not specifically defined herein) online users (user set) are obtained from an online contribution platform for more than 50 times (may be 60 times, 70 times, 80 times, and n times, and may be specifically set according to actual conditions, and is not specifically defined herein), and the previous 50 times (specifically, may be specifically set according to actual conditions, and is not specifically defined herein) of these users are selected (contribution record set) for analysis.

Based on the previous 50 donation amount data of 16494 users, the user donation record set D ═ X can be obtained₁，X₂，...，X₁₆₄₉₄In which any X is_iThe donation amount sequence data areX_i＝[x_i，1，x_x，2，...，x_x，50]Wherein x is_i，jRepresenting the donation amount data of the user i in the j donation, and the donation amount data have a chronological sequence, namely x_i，jOccurs earlier than x_i，j+1。

Then, an amount sequence set including different values of the donation amount is determined according to the donation amount data in the donation amount sequence data of each user.

And obtaining diversity indexes, uncertainty indexes, concentration indexes and consistency indexes of all users based on all money sequence sets.

And then according to the diversity index, the uncertainty index, the concentration index and the consistency index of each user, obtaining a behavior feature set D of the user donation^T＝{X′₁，X′₂，...，X′₁₆₄₉₄Wherein X'_i＝[Dy_i，Uy_i，Cn_i，Cy_i](feature description data). The behavior characteristic index statistics of the contribution behavior of 16494 users are shown in table 1,

TABLE 1 behavioral characteristic index statistics of user contribution behavior

	Diversity	Uncertainty	Concentration property	Consistency
					Mean value	0.115	1.418	0.645	0.539
Standard deviation of	0.080	0.933	0.241	0.265
					Minimum value	0.020	0.000	0.060	0.000
Quantile 25%	0.060	0.667	0.440	0.320
					50% quantile	0.100	1.383	0.640	0.500
75% quantile	0.140	2.036	0.880	0.780
					Maximum value	0.780	5.174	1.000	0.980

Behavior feature set D for user contribution behavior by utilizing K-means clustering algorithm^TClustering is performed, the number K of the clusters is set to 3 (which may be specifically set according to actual conditions, and is not specifically limited here), a Principal Component Analysis algorithm (Principal Component Analysis) is used to reduce the 4-dimensional features to 2-dimensional features, and then the visual display of each cluster is obtained as shown in fig. 2, the contour coefficient after the K-means clustering algorithm clustering is 0.734, the contour coefficient is larger and close to 1, which indicates that the clustering effect is better. The distribution of the user number and the user contribution behavior characteristic value under each cluster is shown in fig. 3 and table 2, so that three user contribution mode categories can be summarized:

mode 1: (irregular pattern, corresponding to category 1 in table 2) users often choose multiple donation amount data to donate, and the user donation amount data has high diversity, high uncertainty, low concentration and low consistency.

Mode 2: (intermediate type, corresponding to category 2 in table 2) users may select some different contribution amount data for contribution, the diversity and uncertainty of the user contribution amount data are at a medium level, and the concentration and consistency are also at a medium level.

Mode 3: (stable form, correspond to category 3 in table 2) the user often chooses fixed contribution amount data to contribute, and user contribution amount data has low variety, low uncertainty, high collection neutral, high uniformity.

The thermodynamic diagram of the first 50 donations of 50 users randomly selected from the irregular-style and stable-style users is shown in fig. 4, each row represents one user, the 50 columns represent the first 50 donations of the user, the color in the square box represents the user donation amount data, it is obvious that the donation amount data of the stable-style user (fig. 4-b) is very fixed (the color of each row is consistent), and the donation amount data of the irregular-style user (fig. 4-a) is very diverse (the color of each row is more). Therefore, different user contribution behavior patterns can be well identified based on the clustering of the behavior characteristic indexes of the user contributions.

TABLE 2 distribution of user number and user donation behavior characteristics under different clusters

Clustering clusters	Class	1	Class 2	Class 3
					Behavioral pattern name	Atactic form	Type of Zhongyong	Stable form
Number of users	3597	7262	5635
				Diversity	0.228(0.1-0.78)	0.106(0.04-0.28)	0.053(0.02-0.14)
Uncertainty	2.741(2.094-5.174)	1.534(0.904-2.169)	0.413(0-1.059)
				Concentration property	0.338(0.06-0.62)	0.584(0.28-0.84)	0.920(0.66-1)
Consistency	0.230(0-0.74)	0.450(0.06-0.94)	0.850(0.46-0.98)
				Amount of unique donation	11.414(5-39)	5.302(2-14)	2.669(1-7)

It should be noted that the method of the embodiment of the present application may be executed by a single device, such as a computer or a server. The method of the embodiment can also be applied to a distributed scene and completed by the mutual cooperation of a plurality of devices. In such a distributed scenario, one of the multiple devices may only perform one or more steps of the method of the embodiment, and the multiple devices interact with each other to complete the method.

It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments described above and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

Based on the same inventive concept, corresponding to the method of any embodiment, the application also provides an online donation behavior pattern analysis device.

Referring to fig. 5, the online donation behavior pattern analysis apparatus includes:

an obtaining module 501, configured to obtain a user set and a contribution record set corresponding to the user set, where the number of contributions in an online contribution platform is greater than a predetermined number of times, where the contribution record set includes a contribution record corresponding to each user in the user set;

a first processing module 502, configured to sort all the donation amount data in the donation record of any user according to donation time, so as to obtain initial donation amount sequence data;

a second processing module 503 configured to take a predetermined amount of the donation amount data from the initial donation amount sequence data as the donation amount sequence data of the any one user;

a third processing module 504 configured to determine behavioral characteristic indicators for the any user based on the contribution amount sequence data;

a fourth processing module 505, configured to reconstruct the behavior feature index of any user to obtain feature description data of the user, and use all the feature description data corresponding to all users in the user set as a behavior feature set;

a fifth processing module 506, configured to perform clustering processing on the behavior feature set to obtain different types of contribution behavior patterns.

In some embodiments, the first processing module 502 is specifically configured to:

determining a sequence set of amounts comprising different donation amount values according to the donation amount data in the donation amount sequence data of any user;

c_iRepresenting as said third amount the number of times that said contribution amount data is selected by said any user to contribute; i is expressed as the ith said donation amount data in said sequence set of amounts; uy tableShown as the uncertainty indicator.

acquiring all the donation amount data of the donation pairs;

s_i≠s_i+1，

In some embodiments, the fifth processing module 506 is specifically configured to:

In some embodiments, the cluster center is specifically:

In some embodiments, the distance information is specifically:

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

The device of the above embodiment is used for implementing the corresponding online donation behavior pattern analysis method in any one of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.

Based on the same inventive concept, corresponding to the method of any embodiment described above, the present application further provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the method for analyzing the online donation behavior pattern according to any embodiment described above is implemented.

Fig. 6 is a schematic diagram illustrating a more specific hardware structure of an electronic device according to this embodiment, where the electronic device may include: processor 6010, memory 6020, input/output interface 6030, communication interface 6040, and bus 6050. Wherein processor 6010, memory 6020, input/output interface 6030, and communication interface 6040 enable communication connections within the device to each other over bus 6050.

The processor 6010 may be implemented by a general purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits, and is configured to execute related programs to implement the technical solutions provided in the embodiments of the present specification.

The Memory 6020 may be implemented in the form of a Read Only Memory (ROM), a Random Access Memory (RAM), a static storage device, a dynamic storage device, or the like. The memory 6020 may store an operating system and other application programs, and when the technical solution provided in the embodiments of the present specification is implemented by software or firmware, the relevant program codes are stored in the memory 6020 and called to be executed by the processor 6010.

The input/output interface 6030 is used for connecting an input/output module to realize information input and output. The i/o module may be configured as a component in a device (not shown) or may be external to the device to provide a corresponding function. The input devices may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output devices may include a display, a speaker, a vibrator, an indicator light, etc.

The communication interface 6040 is used to connect a communication module (not shown in the figure) to implement communication interaction between the present apparatus and other apparatuses. The communication module can realize communication in a wired mode (such as USB, network cable and the like) and also can realize communication in a wireless mode (such as mobile network, WIFI, Bluetooth and the like).

Bus 6050 includes a path that transfers information between various components of the device, such as processor 6010, memory 6020, input/output interface 6030, and communication interface 6040.

It should be noted that although the above-mentioned apparatus only shows processor 6010, memory 6020, input/output interface 6030, communication interface 6040 and bus 6050, in a specific implementation, the apparatus may also include other components necessary for normal operation. In addition, those skilled in the art will appreciate that the above-described apparatus may also include only those components necessary to implement the embodiments of the present description, and not necessarily all of the components shown in the figures.

The electronic device of the above embodiment is used for implementing the corresponding online donation behavior pattern analysis method in any one of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiment, which are not described herein again.

Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application further provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to perform the online donation behavior pattern analysis method according to any of the above-mentioned embodiments.

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

The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the online donation behavior pattern analysis method according to any one of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which are not described herein again.

Those of ordinary skill in the art will understand that: the discussion of any embodiment above is meant to be exemplary only, and is not intended to intimate that the scope of the disclosure, including the claims, is limited to these examples; within the context of the present application, features from the above embodiments or from different embodiments may also be combined, steps may be implemented in any order, and there are many other variations of the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of brevity.

In addition, well-known power/ground connections to Integrated Circuit (IC) chips and other components may or may not be shown in the provided figures for simplicity of illustration and discussion, and so as not to obscure the embodiments of the application. Furthermore, devices may be shown in block diagram form in order to avoid obscuring embodiments of the application, and this also takes into account the fact that specifics with respect to implementation of such block diagram devices are highly dependent upon the platform within which the embodiments of the application are to be implemented (i.e., specifics should be well within purview of one skilled in the art). Where specific details (e.g., circuits) are set forth in order to describe example embodiments of the application, it should be apparent to one skilled in the art that the embodiments of the application can be practiced without, or with variation of, these specific details. Accordingly, the description is to be regarded as illustrative instead of restrictive.

While the present application has been described in conjunction with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art in light of the foregoing description. For example, other memory architectures (e.g., dynamic ram (dram)) may use the discussed embodiments.

The present embodiments are intended to embrace all such alternatives, modifications and variances which fall within the broad scope of the appended claims. Therefore, any omissions, modifications, substitutions, improvements, and the like that may be made without departing from the spirit and principles of the embodiments of the present application are intended to be included within the scope of the present application.

Claims

1. An online donation behavior pattern analysis method is characterized by comprising the following steps:

2. The method according to claim 1, wherein the determining a behavioral characteristic indicator of any one of the users based on the contribution amount sequence data specifically comprises:

3. The method of claim 2,

obtaining the contribution amount sequence data of any user from the user set, and obtaining a first amount of the contribution amount data in the contribution amount sequence data;

4. The method of claim 3,

obtaining a third amount of any one of the donation amount data in the donation amount sequence data;

5. The method of claim 4,

obtaining the concentration index based on the third quantity, wherein the concentration index specifically comprises:

6. The method of claim 2,

obtaining two donation amount data adjacent to a donation time to form a donation pair based on the donation amount sequence data;

acquiring all the donation amount data of the donation pairs;

s_i≠s_i+1，

7. The method according to claim 1, wherein the clustering the behavior feature set to obtain different contribution behavior pattern categories specifically comprises:

8. The method according to claim 7, characterized in that the cluster center is in particular:

9. The method according to claim 7, wherein the distance information is specifically:

10. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 9 when executing the program.