CN108305013B - Method and device for determining effectiveness of operation project and computer equipment - Google Patents

Method and device for determining effectiveness of operation project and computer equipment Download PDF

Info

Publication number
CN108305013B
CN108305013B CN201810146258.0A CN201810146258A CN108305013B CN 108305013 B CN108305013 B CN 108305013B CN 201810146258 A CN201810146258 A CN 201810146258A CN 108305013 B CN108305013 B CN 108305013B
Authority
CN
China
Prior art keywords
sample data
index
sample
obtaining
preset
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810146258.0A
Other languages
Chinese (zh)
Other versions
CN108305013A (en
Inventor
卓晓慧
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN201810146258.0A priority Critical patent/CN108305013B/en
Publication of CN108305013A publication Critical patent/CN108305013A/en
Application granted granted Critical
Publication of CN108305013B publication Critical patent/CN108305013B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G06Q30/0202—Market predictions or forecasting for commercial activities

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Development Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Theoretical Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Data Mining & Analysis (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Educational Administration (AREA)
  • Complex Calculations (AREA)

Abstract

The application relates to a method, a device, a storage medium and computer equipment for determining effectiveness of an operation project, wherein the method comprises the following steps: acquiring feature sample data and index sample data corresponding to the feature sample data, wherein the feature sample data comprises sample data of a preset operation feature parameter corresponding to an operation item to be determined, and the index sample data comprises sample data of a preset operation index corresponding to the operation item; determining a relation model of a preset operation characteristic parameter and a preset operation index based on a regression model, characteristic sample data and index sample data of a preset type; performing statistical inspection based on the relation model, the characteristic sample data and the index sample data to obtain a correlation result between the preset operation characteristic parameter and the preset operation index; and obtaining a validity result corresponding to the operation item based on the relevance result. The embodiment of the application can improve the efficiency and accuracy.

Description

Method and device for determining effectiveness of operation project and computer equipment
Technical Field
The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for determining validity of an operation project, a computer-readable storage medium, and a computer device.
Background
For internet products, an operation project (an operation condition for a user to complete the operation project) is generally developed to achieve a predetermined operation target. Taking the network game product as an example, the operation condition may be lottery drawing in a game mall, and the predetermined operation target may be increasing the user activity, retention rate, payment rate, and the like. With the high-speed development of information technology, market competition is extremely intense, the development frequency of operation projects is higher and higher, and the forms are more and more diversified. In this case, determining the validity of the operation item (i.e., determining the validity of the operation condition to achieve the predetermined operation target) has an important meaning.
In a conventional determination method, relevant practitioners perform subjective analysis on predetermined operation index data related to a predetermined operation target by virtue of their own experience, thereby determining the validity of the operation project. However, the efficiency and accuracy of the conventional method are low due to manual participation in the analysis. And when the operation conditions of the operation project do not have intuitive and obvious relationship with the preset operation targets, the validity condition of the operation project is difficult to determine manually.
Disclosure of Invention
Therefore, it is necessary to provide a method, an apparatus, a computer-readable storage medium, and a computer device for determining the effectiveness of an operation project, aiming at the technical problem of relatively low efficiency and accuracy in the conventional method.
A method for determining the effectiveness of an operation project comprises the following steps:
acquiring feature sample data and index sample data corresponding to the feature sample data, wherein the feature sample data comprises sample data of a preset operation feature parameter corresponding to an operation item to be determined, and the index sample data comprises sample data of a preset operation index corresponding to the operation item;
determining a relation model of the preset operation characteristic parameter and the preset operation index based on a regression model of a preset type, the characteristic sample data and the index sample data;
performing statistical test based on the relationship model, the feature sample data and the index sample data to obtain a correlation result between the preset operation feature parameter and the preset operation index;
and obtaining a validity result corresponding to the operation item based on the relevance result.
An operational item validity determination apparatus, comprising:
the system comprises a sample data acquisition module, a parameter setting module and a parameter setting module, wherein the sample data acquisition module is used for acquiring characteristic sample data and index sample data corresponding to the characteristic sample data, the characteristic sample data comprises sample data of a preset operation characteristic parameter corresponding to an operation item to be determined, and the index sample data comprises sample data of a preset operation index corresponding to the operation item;
the relation model determining module is used for determining a relation model between the preset operation characteristic parameter and the preset operation index based on a regression model of a preset type, the characteristic sample data and the index sample data;
a correlation result obtaining module, configured to perform statistical inspection based on the relationship model, the feature sample data, and the index sample data, and obtain a correlation result between the predetermined operation feature parameter and the predetermined operation index;
and the validity result obtaining module is used for obtaining a validity result corresponding to the operation project based on the relevance result.
A computer-readable storage medium, storing a computer program which, when executed by a processor, implements the steps of the method of determining the effectiveness of an operational project as described above.
A computer device comprising a memory storing a computer program and a processor implementing the steps of the method of determining the validity of an operational project as described above when the computer program is executed.
The method and the device for determining the effectiveness of the operation project, the computer-readable storage medium and the computer equipment determine a relation model of the preset operation characteristic parameter and the preset operation index based on the relevant sample data of the operation project to be determined, perform statistical test based on the relation model and the sample data to obtain a correlation result between the preset operation characteristic parameter and the preset operation index, and further obtain the effectiveness result corresponding to the operation project based on the correlation result. On one hand, the incidence relation between the preset operation characteristic parameters and the preset operation indexes does not need to be analyzed manually, and the efficiency and the accuracy can be improved. On the other hand, statistical verification is carried out based on the related sample data and the relation model, then the validity result corresponding to the operation project is obtained based on the relevance result, and when the operation condition of the operation project does not have the intuitive and obvious relevance relation with the preset operation target, the validity condition of the operation project can be determined.
Drawings
FIG. 1 is a diagram of an application environment of a method for determining the effectiveness of an operational project in one embodiment;
FIG. 2 is a flowchart illustrating a method for determining the effectiveness of an operation project according to an embodiment;
FIG. 3 is a schematic flow chart diagram illustrating a method for determining a first statistical detection quantity in one embodiment;
FIG. 4 is a schematic flow chart diagram illustrating a method for determining a second statistically detected quantity in one embodiment;
FIG. 5 is a schematic flow chart diagram illustrating a method for determining a third statistically detected quantity in one embodiment;
FIG. 6 is a schematic flow chart diagram illustrating a method for determining a fourth statistical detection quantity in one embodiment;
FIG. 7 is a graph of average durations of participating and non-participating sample users in one embodiment;
FIG. 8 is a box plot of average durations of participating and non-participating sample users in one embodiment;
FIG. 9 is a schematic flow chart diagram illustrating a method for determining a fifth statistical detection quantity in one embodiment;
FIG. 10 is a graphical representation of the coordinates of sample user average durations before and after participation in a gaming session, in one embodiment;
FIG. 11 is a box diagram illustrating an example average user duration before and after participating in a game mission in one embodiment;
FIG. 12 is a flowchart illustrating a method for determining the effectiveness of an operation project according to another embodiment;
FIG. 13 is a block diagram showing the configuration of an operating item validity determination apparatus according to an embodiment;
FIG. 14 is a block diagram showing the construction of a computer device according to one embodiment;
fig. 15 is a block diagram showing a configuration of a computer device according to another embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The method for determining the effectiveness of the operation project provided by the embodiments of the present application can be applied to the application environment shown in fig. 1. The application environment involves a user terminal 110 and a server 120, the user terminal 110 and the server 120 communicating over a network. The server 120 obtains the feature sample data and the index sample data corresponding to the operation item to be determined, processes the feature sample data and the index sample data to obtain the validity result corresponding to the operation item, and further sends the validity result to the user terminal 110, and accordingly, the user terminal 110 displays the validity result for the user to check. The user terminal 110 may be a desktop terminal or a mobile terminal, the desktop terminal may include a desktop computer, and the mobile terminal may include at least one of a mobile phone, a tablet computer, a notebook computer, a personal digital assistant, a wearable device, and the like. The server 120 may be implemented as a stand-alone physical server or as a server cluster of multiple physical servers.
It is to be appreciated that in other application environments, the application environment relates to the user terminal 110 shown in FIG. 1. The user terminal 110 may also obtain feature sample data and index sample data corresponding to the operation item to be determined, then process the feature sample data and the index sample data to obtain a validity result corresponding to the operation item, and further display the validity result for the user to view.
In one embodiment, as shown in FIG. 2, a method for determining the effectiveness of an operational project is provided. The method is described by way of example as it would be applicable to the server 120 in fig. 1. The method may include the following steps S202 to S208.
S202, obtaining feature sample data and index sample data corresponding to the feature sample data, wherein the feature sample data comprises sample data of a preset operation feature parameter corresponding to an operation item to be determined, and the index sample data comprises sample data of a preset operation index corresponding to the operation item.
The predetermined operation characteristic parameter refers to a parameter that is preset and can be used for representing the operation condition of the operation item. In practical applications, the predetermined operation characteristic parameter may be set based on the operation condition of the operation item. In one embodiment, for an operation item of the activity class, the operation condition may be that the user completes the operation item, and accordingly, the predetermined operation characteristic parameter may include a characteristic parameter of the user completing the operation item, such as the number of times the user completes the operation item. Specifically, taking the network game application scenario as an example, the operation item may include a game task (e.g., a ranking game) of the network game, and accordingly, the predetermined operation characteristic parameter may include the number of times that the user completes the game task.
The predetermined operation index is an index that is preset to measure a predetermined operation target of the operation project. In practical applications, the predetermined operation target of the operation item may be set based on the actual requirement, and the predetermined operation index may be set based on the predetermined operation target. Taking the network game application scenario as an example, the predetermined operation target may include at least one of increasing user stickiness, increasing user activity, increasing user retention rate, increasing user payment rate, and the like. For the case that the predetermined operation target is to improve the user stickiness, the predetermined operation index may include the game duration of the user, that is, the improvement of the user stickiness may be measured by the game duration of the user.
In this embodiment, the feature sample data may include sample data of a predetermined operation feature parameter corresponding to the operation item to be determined. The index sample data may include sample data of a predetermined operation index corresponding to the operation item. Further, the feature sample data corresponds to the index sample data.
In one embodiment, the feature sample data may include sample data of a predetermined operation feature parameter corresponding to an operation item to be determined in a predetermined period of time, and accordingly, the index sample data may include sample data of a predetermined operation index corresponding to the operation item in the predetermined period of time. The predetermined period may be set based on actual demand, for example, within any 30 days after the launch date of the operation item, or within a specified 30 days after the launch date.
Taking the network game application scenario as an example, the operation item to be determined is a game task of the network game, and the feature sample data may include that a user finishes the game task in a predetermined sample within a predetermined time periodThe sub-value. The metric sample data may include a game age value of the predetermined sample user within the predetermined period of time. Table 1 shows the number of game tasks and the game duration value of a predetermined sample of user's completion within a given 30 days, where the number of game tasks is 11, and the task identifiers of the respective game tasks are T178、T179、T180、T181、T182、T183、T184、T185、T186、T187And T188And the task contents of the 11 game tasks are different from each other, such as T178Logging in mobile terminal, T, for user179Is a tournament, T180A one-to-one ranking match, etc. In addition, the number of the predetermined sample users is N, and the user identification of each sample user is U01，U02，U03，…，U0N(only U is shown in Table 101，U02And U03The sample data of (a).
The following description will be made with reference to table 1 for feature sample data and index sample data: the feature sample data comprises a sample user U01Sample user U02Sample user U03…, and sample user U0NRespectively completing each game task (T)178～T188) The decimal point of (c). The index sample data comprises a sample user U01Sample user U02Sample user U03…, and sample user U0NThe respective game age value. And, the sample user U01The number of times of completing each game task and the sample user U01The game duration values of (1) are corresponding to each other, sample user U02The number of times of completing each game task and the sample user U02The game duration values of (1) are corresponding to each other, sample user U03Sample user U04… sample user U0NAre similar and will not be described herein.
TABLE 1
Sample user ID U01 U02 U03 … U0N
User completes T178Value of (2) 2 3 5 … …
User completes T179Value of (2) 0 12 4 … …
User completes T180Value of (2) 2 11 4 … …
User completes T181Value of (2) 2 2 0 … …
User completes T182Value of (2) 3 0 0 … …
User completes T183Value of (2) 0 6 2 … …
User completes T184Value of (2) 4 4 2 … …
User completes T185Value of (2) 0 2 0 … …
User completes T186Value of (2) 0 3 0 … …
User completes T187Value of (2) 0 3 1 … …
User completes T188Value of (2) 0 0 0 … …
User's game duration value (minutes) 452672 483630 149784 … …
S204, determining a relation model of the preset operation characteristic parameter and the preset operation index based on the regression model of the preset type, the characteristic sample data and the index sample data.
The regression model is a mathematical model for quantitatively describing statistical relationships. In this embodiment, the type of the regression model may be determined based on the predetermined operation characteristic parameter, for example, when the predetermined operation characteristic parameter is a continuity value variable, the type of the regression model may be a linear regression modelOn the basis of the regression model, if the number of the predetermined operation characteristic parameters is more than two, the type of the regression model can be a multiple linear regression model, which can be expressed as: y ═ beta0+β1x1+β2x2+···+βmxn. Wherein y is a dependent variable, x1、x2…, and xnAre each a respective variable, beta0、β1…, and betamThe regression coefficients of the regression model are respectively.
In this embodiment, the relational model uses the predetermined operation index as a dependent variable and each predetermined operation characteristic parameter as a respective variable. It can be understood that the estimation values of the regression coefficients in the regression model can be determined based on the feature sample data and the index sample data corresponding to the feature sample data, and after the estimation values of the regression coefficients are determined, the relationship model between the predetermined operation feature parameter and the predetermined operation index is determined. In one embodiment, the estimated values of the regression coefficients may be determined based on various possible parameter estimation algorithms, such as the Least squares (OLS).
S206, carrying out statistical test based on the relation model, the characteristic sample data and the index sample data to obtain a correlation result between the preset operation characteristic parameter and the preset operation index.
In this embodiment, the statistical test may comprise a statistical hypothesis test. Statistical hypothesis testing refers to a testing method in which a population is inferred from a sample based on predetermined hypothesis conditions. In one embodiment, a corresponding statistical calibration value may be determined based on the relationship model, the feature sample data, and the index sample data, and then a correlation result between the predetermined operation feature parameter and the predetermined operation index may be obtained based on the corresponding statistical calibration value. Wherein the correlation result can be used to characterize the correlation between the predetermined operation characteristic parameter and the predetermined operation index (e.g. whether there is a corresponding correlation and/or a degree of correlation).
In one embodiment, the relevance result may include a relevance or non-relevance result, which may include a relevance result or a non-relevance result. The related result can be used for representing that the preset operation characteristic parameter and the preset operation index have corresponding related relation, namely, the preset operation characteristic parameter has influence on the change of the preset operation index; otherwise, the non-correlation result may be used to indicate that the predetermined operation characteristic parameter and the predetermined operation index do not have a corresponding correlation, that is, the predetermined operation characteristic parameter has no influence or a negligible influence on the change affecting the predetermined operation index.
In another embodiment, the correlation result may include a correlation result, and the correlation result may be used to characterize a correlation between the predetermined operation characteristic parameter and the predetermined operation index. It can be understood that the higher the degree of association, the greater the degree of influence of the predetermined operation characteristic parameter on the change of the predetermined operation index is; conversely, the lower the degree of association, the smaller the degree of influence of the predetermined operation characteristic parameter on the change of the predetermined operation index.
In another embodiment, the result of relevance may include both the result of relevance or not and the result of degree of relevance.
In addition, the number of the predetermined operation characteristic parameters may be only one, or may be two or more.
In one embodiment, when the number of the predetermined operation characteristic parameters is more than two, the association result may include an overall association result, and the overall association result may include an overall associated result or an overall non-associated result. The overall correlation result can be used for representing that the overall preset operation characteristic parameters and the preset operation indexes have corresponding correlation relations, namely, at least one preset operation characteristic parameter in each preset operation characteristic parameter and the preset operation indexes have corresponding correlation relations; otherwise, the overall non-correlation result may be used to represent that the predetermined operation characteristic parameter overall does not have a corresponding correlation with the predetermined operation index, that is, each predetermined operation characteristic parameter does not have a corresponding correlation with the predetermined operation index.
In one embodiment, when the number of the predetermined operation characteristic parameters is more than two, similarly, the correlation degree result may include an overall correlation degree result. The overall correlation degree result can be used for representing the correlation degree between the overall preset operation characteristic parameter and the preset operation index.
In another embodiment, when the number of the predetermined operation parameters is more than two, the association result may include independent association results respectively corresponding to the predetermined operation parameters (i.e., one-to-one correspondence). For any independent association or non-association result, the independent association or non-association result may include an independent associated result or an independent non-associated result. The independent related result can be used for representing that the corresponding preset operation characteristic parameter has a corresponding relation with the preset operation index, namely, the preset operation characteristic parameter has influence on the change of the preset operation index; otherwise, the independent non-correlation result may be used to characterize that the predetermined operation characteristic parameter corresponding to the independent non-correlation result does not have a corresponding correlation with the predetermined operation index, that is, the predetermined operation characteristic parameter has no influence or a negligible influence on the change of the predetermined operation index.
In another embodiment, when the number of the predetermined operation parameters is more than two, similarly, the association degree result may include each independent association degree result corresponding to each predetermined operation parameter. For any independent association degree result, the independent association degree result can be used for representing the association degree between the preset operation characteristic parameter corresponding to the independent association degree result and the preset operation index.
In another embodiment, the association result may include both the overall association result and each independent association result corresponding to each predetermined operation characteristic parameter. In addition, the association degree result may include both the overall association degree result and each independent association degree result corresponding to each predetermined operation characteristic parameter.
And S208, obtaining a validity result corresponding to the operation item to be determined based on the relevance result.
The operation item to be determined refers to an operation item for which an effective result is required to be obtained. Wherein the validity result can be used to characterize the validity of the operational item for achieving the predetermined operational goal.
In one embodiment, the validity result corresponding to the operation item may include a validity or non-validity result, and the validity or non-validity result includes a valid result or a non-valid result. Wherein the valid result can be used to characterize that the operation item is valid for achieving the predetermined operation target, that is, the operation item is a valid operation item; otherwise, the invalidation result can be used to characterize that the operation item is invalid for achieving the predetermined operation target, i.e., the operation item is an invalid operation item.
In another embodiment, the effectiveness result corresponding to the operation item may include an effectiveness degree result, and the effectiveness degree result may be used to characterize the effectiveness degree of the operation item for achieving the predetermined operation goal. It can be understood that the higher the effective degree is, the greater the contribution degree of the operation project to achieving the preset operation target is; conversely, the lower the validity degree, the smaller the contribution degree of the operation item to achieving the predetermined operation target.
In another embodiment, the validity result corresponding to the operation item may include both the validity result and the validity degree result.
In this embodiment, the validity result corresponding to the operation item may be obtained based on the relevance result. Specifically, when the result of association or not includes an associated result, the obtained validity result includes a valid result. Otherwise, when the association result or not includes the non-association result, the obtained validity result includes an invalid result. Further, a result of the degree of validity may also be obtained based on the result of the degree of correlation, for example, when the result of the degree of correlation is 0.86, a result of the degree of validity of 86% may be obtained.
It should be noted that, in one determination process, the operation items to be determined may include only one operation item, or may include more than two operation items.
In one embodiment, when the operation items to be determined include more than two operation items, and each operation item corresponds to each predetermined operation characteristic parameter, the association result may include an overall association result, and accordingly, the validity result may include an overall validity result. In particular, the overall association or non-association result comprises an overall associated result or an overall non-associated result, which may comprise an overall valid result or an overall invalid result, respectively. The overall effective result can be used to represent that the overall operation project to be determined is effective for achieving the predetermined operation target, that is, at least one operation project in the operation projects to be determined is effective for achieving the predetermined operation target. The overall invalidation result may be used to represent that the overall operation item to be determined is invalid for achieving the predetermined operation target, that is, each operation item in the operation item to be determined is invalid for achieving the predetermined operation target.
In one embodiment, when the operation item to be determined includes more than two operation items, and each operation item corresponds to each predetermined operation characteristic parameter, similarly, the association degree result may include an overall association degree result, and accordingly, the validity degree result may include an overall validity degree result. The overall effectiveness degree result can be used for representing the effectiveness degree of the overall operation project to be determined on achieving the preset operation target.
In another embodiment, when the operation item to be determined includes more than two operation items, and each operation item corresponds to each predetermined operation feature parameter, the association result may include each independent association result corresponding to each predetermined operation feature parameter, and correspondingly, the validity result may include each independent validity result corresponding to each operation item. Specifically, for any independent association result, the independent association result may include an independent associated result or an independent non-associated result, and the independent valid result or the independent invalid result corresponding to the independent association result may correspondingly include an independent valid result and an independent invalid result. Wherein, the independent effective result can be used for representing that the corresponding operation item is effective for realizing the preset operation target; otherwise, the independent invalidation result can be used for representing that the operation item corresponding to the independent invalidation result is invalid for realizing the preset operation target.
In another embodiment, when the operation item to be determined includes more than two operation items, and each operation item corresponds to each predetermined operation feature parameter, similarly, the association degree result may include each independent association degree result corresponding to each predetermined operation feature parameter, and correspondingly, the validity degree result may include each independent validity degree result corresponding to each operation item. The independent effectiveness level result can be used to characterize the effectiveness level of the corresponding operation item for achieving the predetermined operation goal.
In another embodiment, the validity or non-validity results may include both the above-described overall validity or non-validity result and each individual validity or non-validity result. Further, the effectiveness level results may include both the overall effectiveness level result and each of the individual effectiveness level results described above.
The method for determining the effectiveness of the operation project determines a relation model of the preset operation characteristic parameter and the preset operation index based on the relevant sample data of the operation project to be determined, then carries out statistical test based on the relation model and the sample data to obtain a correlation result between the preset operation characteristic parameter and the preset operation index, and further obtains the effectiveness result corresponding to the operation project based on the correlation result. On one hand, the incidence relation between the preset operation characteristic parameters and the preset operation indexes does not need to be analyzed manually, and the efficiency and the accuracy can be improved. On the other hand, statistical verification is carried out based on the related sample data and the relation model, then the validity result corresponding to the operation project is obtained based on the relevance result, and when the operation condition of the operation project does not have the intuitive and obvious relevance relation with the preset operation target, the validity condition of the operation project can be determined.
In one embodiment, the step S206 may include the following steps: and determining a first statistical detection quantity based on the relation model, the characteristic sample data and the index sample data. Then, the first statistical detection quantity is compared with a preset first critical value in magnitude, and a correlation result between the preset operation characteristic parameter and the preset operation index is obtained based on the comparison result. And the correlation result is used for representing whether the preset operation characteristic parameter and the preset operation index have a corresponding correlation relationship or not.
As shown in fig. 3, in the present embodiment, the first statistical detection amount determination method may include the following steps S302 to S308. S302, obtaining a regression square sum, a regression freedom, a residual square sum and a residual freedom based on the relation model, the characteristic sample data and the index sample data. S304, obtaining regression mean square error based on the regression sum of squares and the regression degree of freedom. And S306, obtaining the mean square error of the residual error based on the sum of squares of the residual error and the degree of freedom of the residual error. S308, determining the ratio of the regression mean square error to the residual mean square error as a first statistical detection quantity.
The first statistical detection quantity is used for obtaining the overall correlation result. For the determination of the first statistical detection quantity, the regression sum of squares may be obtained based on the following formula:
Figure BDA0001578898100000101
where k is the sample capacity of the feature sample data and the index sample data corresponding to the feature sample data (taking table 1 as an example, k is N),
Figure BDA0001578898100000102
as an index of the mean value of the sample data (taking table 1 as an example,
Figure BDA0001578898100000103
Figure BDA0001578898100000104
for the estimated value of the ith predetermined operation index (to be compared with
Figure BDA0001578898100000105
The corresponding characteristic sample data is substituted into the relation model for calculation to obtain
Figure BDA0001578898100000106
Taking Table 1 as an example, the estimated value of the 1 st predetermined operation index is
Figure BDA0001578898100000107
Figure BDA0001578898100000108
The sum of the squares of the residuals may be obtained based on the following equation:
Figure BDA0001578898100000109
wherein, yiIs the true value of the ith predetermined operation index (taking table 1 as an example, the true value of the 1 st predetermined operation index is 452672). Degree of regression freedom df1，df1M is the total number of independent variables in the relational model (see table 1 for example, d)f111), residual degree of freedom df2，df2K-m-1 (see table 1 for example, d)f2N-11-1). The regression mean square error is the regression sum of squares divided by the regression degree of freedom, the residual mean square error is the residual sum of squares divided by the residual degree of freedom, and the first statistical detection quantity is the regression sum of squares divided by the residual mean square error.
In the present embodiment, when performing hypothesis statistical tests, the following original and alternative hypotheses may be made. The original assumption is that: each preset operation characteristic parameter and each preset operation index do not have corresponding association relationship, namely H0: beta is a1＝β2＝…＝βm0. The alternative assumption is that: at least one of the predetermined operation characteristics has a corresponding relationship with the predetermined operation index, that is, H1: beta is a1、β2、…、βmAt least one of which is not equal to 0. And, a significance level value, which is the probability that the original hypothesis is actually correct but rejected, may be preset based on actual demand.
Further, comparing the first statistical detection quantity with a preset first critical value, and when the first statistical detection quantity is larger than the preset first critical value, rejecting the original hypothesis to obtain an overall associated result, wherein the overall associated result is used for representing that at least one preset operation characteristic parameter in each preset operation characteristic parameter has a corresponding association relationship with the preset operation index (but the preset operation characteristic parameter having the corresponding association relationship with the preset operation index cannot be specifically determined); otherwise, when the first statistical detection quantity is smaller than or equal to the preset first critical value, the original hypothesis is accepted, and an overall non-correlation result is obtained and used for representing that each preset operation characteristic parameter and each preset operation index do not have corresponding correlation. Wherein the predetermined first threshold is determined based on the regression degree of freedom, the residual degree of freedom, the predetermined significance level value, and the F-distribution threshold table.
In one embodiment, when the number of the predetermined operation characteristic parameters is more than two, the step S206 may include the following steps: and determining each second statistical detection quantity corresponding to each preset operation characteristic parameter respectively based on the relationship model, the characteristic sample data and the index sample data. Then, the absolute value of each second statistical detection quantity is compared with a preset second critical value, and the correlation result between each preset operation characteristic parameter and the preset operation index is obtained based on each comparison result. And the correlation result is used for representing whether the corresponding preset operation characteristic parameter and the preset operation index have a corresponding correlation relationship.
As shown in fig. 4, in the present embodiment, the manner of determining each second statistically detected amount corresponding to each predetermined operation characteristic parameter may include the following steps S402 to S406. S402, obtaining regression coefficients corresponding to the preset operation characteristic parameters respectively based on the relation model. S404, obtaining regression coefficient standard deviations corresponding to the preset operation characteristic parameters based on the relation model, the characteristic sample data and the index sample data. And S406, respectively determining the ratio of the regression coefficient corresponding to each preset operation characteristic parameter to the standard deviation of the regression coefficient as each second statistical detection quantity corresponding to each preset operation characteristic parameter.
A second statistical test quantity for obtaining the aforementioned independent correlation result. For the determination of the second statistical calibration quantity corresponding to the jth predetermined operating characteristic parameter, the regression coefficient standard deviation corresponding to the jth predetermined operating characteristic parameter may be obtained based on the following formula:
Figure BDA0001578898100000111
where j is less than the total number of independent variables, x, of the relational modeljiFor the ith sample of the jth predetermined operating characteristic parameterThis data (for example, Table 1, for the 1 st predetermined operating characteristic parameter-completion of the Game task T)178X is112, i.e. sample user U01Completing Game task T178Value of (a), x 123, i.e. sample user U02Completing Game task T178Value of (a), x 135, i.e. sample user U03Completing Game task T178The times value … …).
In this embodiment, when the number of the predetermined operation characteristic parameters is two or more, and the hypothesis statistical test is performed, the following original hypothesis and alternative hypothesis may be made for any one of the predetermined operation characteristic parameters. The original assumption is that: the predetermined operation characteristic parameter and the predetermined operation index do not have a corresponding relationship, i.e. H0: the true value of the regression coefficient corresponding to the predetermined operation characteristic parameter is equal to 0. The alternative assumption is that: the predetermined operation characteristic parameter and the predetermined operation index have corresponding correlation, that is, H1: the true value of the regression coefficient corresponding to the predetermined operation characteristic parameter is not equal to 0. And, the significance level value may be preset based on actual demand.
And comparing the absolute value of the second statistical detection quantity corresponding to the preset operation characteristic parameter with a preset second critical value. When the absolute value of the second statistical detection quantity is greater than or equal to a preset second critical value, rejecting the original hypothesis, and obtaining an independent associated result corresponding to the preset operation characteristic parameter, wherein the independent associated result is used for representing that the preset operation characteristic parameter and a preset operation index have a corresponding association relationship; otherwise, when the absolute value of the second statistical detection quantity is smaller than a preset second critical value, the original assumption is accepted, and an independent non-correlation result corresponding to the preset operation characteristic parameter is obtained, wherein the independent non-correlation result is used for representing that the preset operation characteristic parameter and the preset operation index do not have a corresponding correlation relationship. Wherein the predetermined second threshold is determined based on the total dispersion freedom, the predetermined significance level value, and the T-distribution threshold table. In addition, the total dispersion degree of freedom is (k-1), where k is the sample capacity of the feature sample data and the index sample data corresponding thereto.
In one embodiment, the step S206 may include the following steps: and determining a third statistical detection quantity based on the relation model, the characteristic sample data and the index sample data. Then, based on the third statistical detection quantity value, a correlation result between the preset operation characteristic parameter and the preset operation index is obtained. And the correlation result is used for representing the degree of correlation between the preset operation characteristic parameter and the preset operation index.
As shown in fig. 5, in the present embodiment, the manner of determining the third statistically detected amount may include the following steps S502 and S504. S502, obtaining a regression square sum and a total dispersion square sum based on the relation model, the feature sample data and the index sample data. And S504, determining the ratio of the regression sum of squares and the total deviation sum of squares as a third statistical detection quantity.
And a third statistically determined quantity for obtaining the overall correlation results as described above. For the determination of the third statistical assay, the regression sum of squares is determined in the same manner as described above, and will not be described herein. The sum of the squares of the total deviations can be obtained based on the following formula:
Figure BDA0001578898100000131
note that the total sum of squared deviations is the sum of the regression sum of squares and the sum of squared residuals. And, the third statistically detected amount is the regression sum of squares divided by the total sum of deviations sums of squares. Furthermore, the value of the third statistically detected amount may represent the degree of association between the whole of the predetermined operation characteristic parameter and the predetermined operation index, for example, the value of the third statistically detected amount is 0.86, and the degree of association between the whole of the predetermined operation characteristic parameter and the predetermined operation index is 86%.
It should be noted that, in the multiple linear regression equation, an increase in the number of independent variables causes a decrease in the sum of squared residuals, and in this case, the third statistically detected amount determined based on the manner shown in fig. 5 increases. That is, the third statistically detected amount determined based on the manner shown in fig. 5 is influenced by the number of independent variables in the relational model.
In order to eliminate the influence of the number of independent variables on the third statistical detection amount, in another embodiment, the method for determining the third statistical detection amount may include the following steps: and obtaining a residual square sum, residual freedom degree, total dispersion square sum and total dispersion freedom degree based on the relation model, the characteristic sample data and the index sample data. The sum of the squares of the residuals is divided by the degrees of freedom of the residuals to obtain a mean square error of the residuals, and the sum of the squares of the total deviations is divided by the degrees of freedom of the total deviations to obtain a mean square error of the total deviations. And dividing the residual mean square error by the total dispersion mean square error to obtain a quotient, subtracting the quotient from 1, and determining the obtained difference as a third statistical detection quantity. The total dispersion degree of freedom is (k-1), and k is the sample capacity of the feature sample data and the index sample data corresponding to the feature sample data.
In an embodiment, the method for determining the effectiveness of the operation item may further include the following steps: the method comprises the steps of obtaining first index sample data of a user who is scheduled to participate in a project and second index sample data of a user who is not scheduled to participate in the project in a preset time period, determining a fourth statistical detection quantity based on the first index sample data and the second index sample data, and obtaining an effectiveness result corresponding to an operation project based on the fourth statistical detection quantity.
As shown in fig. 6, in the present embodiment, the manner of determining the fourth statistical detection amount may include the following steps S602 to S614. S602, obtaining the average value difference of the first index sample data and the second index sample data. S604, the predetermined participation index standard value and the predetermined non-predetermined participation index standard value are subtracted to obtain a standard value difference. S606, the average value difference and the standard value difference are subjected to difference to obtain a first difference value. S608, obtaining a first sample variance and a first sample capacity based on the first index sample data. S610, obtaining a second sample variance and a second sample capacity based on the second index sample data. S612, obtaining a first sample mean standard deviation based on the first sample variance, the first sample capacity, the second sample variance and the second sample capacity. And S614, determining the ratio of the first difference value to the standard deviation of the first sample mean value as a fourth statistical detection quantity.
In one embodiment, first index sample data of a predetermined participating project user (hereinafter referred to as a participating sample user) and second index sample data of a predetermined non-participating project user (hereinafter referred to as a non-participating sample user) in a predetermined period of time may be obtained, and whether an operation project is effective for achieving a predetermined operation target may be determined by laterally comparing the first index sample data and the second index sample data. Taking the network game application scenario as an example, the average value of the daily game durations (game durations per day) of the predetermined sample users participating in the game task and the average value of the daily game durations of the predetermined sample users not participating in the game task within the specified 30 days can be obtained, and assuming that the obtained average value (average duration) of the game durations is as shown in fig. 7 and 8, it can be known that the average value of the game durations of the predetermined sample users participating in the game task is higher than the average value of the game durations of the predetermined sample users not participating in the game task by performing a horizontal comparison, and based on this, it can be determined that the game task is effective for achieving the predetermined operation target.
It is to be understood that the above lateral comparisons are only illustrative of how an operational project is effective in achieving a predetermined operational goal for participating and non-participating sample users. However, it cannot be stated that the operation project is effective for achieving the predetermined operation target for the overall user (all users on the operation platform).
Based on this, in the present embodiment, it is determined by a hypothesis statistical test whether the operation item is effective for achieving the predetermined operation target for the overall user. Taking the network game application scenario as an example, the following original assumptions and alternative assumptions can be made. The original assumption is that: the average value of the game duration of all the users participating in the game task is less than or equal to the average value of the game duration of all the users not participating in the game task. The alternative assumption is that: the average value of the game duration of all users participating in the game task is greater than the average value of the game duration of all users not participating in the game task. And, the significance level value may be preset based on actual demand.
Further, a fourth statistical detection amount is determined based on the first index sample data and the second index sample data. The absolute value of the fourth statistically detected quantity is then compared with a predetermined third threshold value. When the absolute value of the fourth statistical detection quantity is greater than or equal to a preset third critical value, rejecting the original hypothesis and obtaining an effective result, wherein the effective result is used for representing that the game task is effective for improving the game duration of the user; otherwise, when the absolute value of the fourth statistical detection quantity is smaller than the preset third critical value, the original hypothesis is accepted, and an invalid result is obtained and used for representing that the game task is invalid for improving the game duration of the user. Wherein the predetermined third threshold is determined based on the total dispersion freedom, the predetermined significance level value, and the T-distribution threshold table.
It should be noted that, in other alternative embodiments, the first testing probability corresponding to the predetermined third threshold value may also be obtained. And then, comparing the first detection probability with the significance level value, and rejecting the original hypothesis to obtain a valid result when the first detection probability is smaller than the significance level value. And conversely, when the first test probability is greater than or equal to the significance level value, the original hypothesis is accepted, and an invalid result is obtained. The first test probability is a probability of obtaining the same or more extreme result as the sample when the original hypothesis is assumed to be true, that is, the original hypothesis may be considered not to be true when the first test probability is smaller than the significance level value (which may be 0.05 in general).
In addition, for the determination of the fourth statistical detection value, the mean difference is a difference value between the mean value of the first index sample data and the mean value of the second index sample data. The predetermined participation index standard value refers to a standard value of a predetermined operation index of a user participating in the operation project, the predetermined non-predetermined participation index standard value refers to a standard value of a predetermined operation index of a user not participating in the operation project, and the predetermined participation index standard value and the predetermined non-predetermined participation index standard value can be set based on business experience. First sample variance (in)
Figure BDA0001578898100000151
Expression) can be obtained based on the following formula:
Figure BDA0001578898100000152
wherein k is1Is a first sample capacity of the first index sample data,
Figure BDA0001578898100000153
is the mean value of the first index sample data, y1iThe sample data is the ith sample data in the first index sample data. Second sample variance (in)
Figure BDA0001578898100000154
Expressed) can be obtained by the following formula:
Figure BDA0001578898100000155
wherein k is2Is a second sample capacity of the second index sample data,
Figure BDA0001578898100000157
is the mean value of the second index sample data, y2iIs the ith sample data in the second index sample data. The first sample mean standard deviation can be obtained based on the following equation:
Figure BDA0001578898100000156
the fourth statistically detected amount is the first difference divided by the standard deviation of the first sample mean.
In an embodiment, the method for determining the effectiveness of the operation item may further include the following steps: and obtaining third index sample data of a predetermined sample user in a predetermined non-project participating time period and fourth index sample data of the predetermined sample user in a predetermined project participating time period, determining a fifth statistical check quantity based on the third index sample data and the fourth index sample data, and further obtaining a validity result corresponding to the operation project based on the fifth statistical check quantity.
As shown in fig. 9, in the present embodiment, the method for determining the fifth statistical detection amount may include the following steps S902 to S910. And S902, correspondingly subtracting the third index sample data and the fourth index sample data to obtain variation sample data. And S904, subtracting the mean value of the variation sample data from the preset variation standard value to obtain a second difference value. And S906, obtaining a sample standard deviation and a third sample capacity based on the variation sample data. And S908, obtaining a second sample mean standard deviation based on the sample standard deviation and the third sample capacity. And S910, determining the ratio of the second difference to the standard deviation of the second sample mean value as a fifth statistical detection quantity.
In one embodiment, third index sample data of the same batch of predetermined sample users in a predetermined non-project-participating time period and fourth index sample data of the predetermined sample users in a predetermined project-participating time period can be obtained, and whether the operation project is effective for achieving the predetermined operation target is determined by longitudinally comparing the third index sample data and the fourth index sample data. Taking the network game application scenario as an example, the average value of the daily game time of the predetermined sample user in 30 days before participating in the game task and the average value of the daily game time of the predetermined sample user in 30 days after participating in the game task may be obtained, and assuming that the obtained average value (average time) of the game time is as shown in fig. 10 and 11, a vertical comparison may be performed, and the average value of the game time of the predetermined sample user after participating in the game task is higher than the average value of the game time of the predetermined sample user before participating in the game task, based on which it may be determined that the game task is effective for achieving the predetermined operation target.
It is to be understood that the above longitudinal comparison, again, can only illustrate that for a predetermined sample user, the operational project is effective for achieving the predetermined operational goal. However, it cannot be stated that the operation items are effective for achieving the predetermined operation targets for the overall user.
Based on this, in the present embodiment, it is determined by the hypothesis statistical test that the operation item is effective for achieving the predetermined operation target for the overall user. Taking the network game application scenario as an example, the following original assumptions and alternative assumptions can be made. The original assumption is that: the average value of the game time length of each user after participating in the game task is less than or equal to the average value of the game time length of each user before participating in the game task. The alternative assumption is that: the average value of the game time length of each user after participating in the game task is larger than the average value of the game time length of each user before participating in the game task. And, the significance level value may be preset based on actual demand.
Further, a fifth statistical detection amount is determined based on the third index sample data and the fourth index sample data. The absolute value of the fifth statistically detected quantity is then compared with a predetermined fourth threshold value. When the absolute value of the fifth statistical detection quantity is greater than or equal to a preset fourth critical value, rejecting the original hypothesis and obtaining an effective result, wherein the effective result is used for representing that the game task is effective for improving the game duration of the user; otherwise, when the absolute value of the fifth statistical detection quantity is smaller than the preset fourth critical value, the original hypothesis is accepted, and an invalid result is obtained, wherein the invalid result is used for representing that the game task is invalid for improving the game duration of the user. Wherein the predetermined fourth threshold is determined based on the total dispersion freedom, the predetermined significance level value, and the T-distribution threshold table.
It should be noted that, in other alternative embodiments, the second testing probability corresponding to the predetermined fourth threshold value may also be obtained. And then, comparing the second detection probability with the significance level value, and rejecting the original hypothesis to obtain a valid result when the second detection probability is smaller than the significance level value. And conversely, when the second testing probability is greater than or equal to the significance level value, the original hypothesis is accepted, and an invalid result is obtained. Similarly to the first test probability, the second test probability refers to the probability of obtaining the same or more extreme result as the sample when the original hypothesis is assumed to be true, that is, when the second test probability is smaller than the significance level value (which may be generally 0.05), the original hypothesis may be considered to be false.
The third index sample data includes a plurality of sample data, and the fourth index sample data includes a plurality of sample data corresponding to each sample data in the third index sample data. For example, the third index sample data includes a1、a2And a3The fourth index sample data includes b1、b2And b3Wherein a is1And b1Correspond to, a2And b2Correspond to, a3And b3Correspondingly, the variation sample data includes (a)1-b1)、(a2-b2) And (a)3-b3). Wherein, the variation sample data represents the variation of the mean value of the game duration before and after the participation of the game task.
For the determination of the fifth statistical evaluation value, the predetermined variation criterion value is referred to as participationAnd the standard value of the variation of the average value of the user game duration before and after the game task can be set based on business experience. Sample standard deviation (in s)dExpression) can be obtained based on the following formula:
Figure BDA0001578898100000171
wherein k is3For a third sample capacity of delta sample data,
Figure BDA0001578898100000172
is the mean of the sample data of the variation, y3iThe sample data is the ith sample data in the variation sample data. The second sample mean standard deviation can be obtained by the following formula:
Figure BDA0001578898100000173
the fifth statistically detected amount is the second difference divided by the second sample mean standard deviation.
In one embodiment, the operation item to be determined comprises a game task of the online game, the predetermined operation characteristic parameter comprises the number of times of completing the game task, and the predetermined operation index comprises the game duration of the user.
The method for determining the effectiveness of the operation item provided by the embodiments of the present application can be applied to a network game scenario, for example, for a game system in which a plurality of game tasks (for example, the game task T described above) are set178～T188) Then, based on the methods provided in the embodiments of the present application, the effectiveness (whether effective and the effective degree) of the game system for promoting the stickiness of the user can be determined, and the effectiveness of each game task in the game system for promoting the stickiness of the user can be separately determined. Specifically, the predetermined operation characteristic parameter includes the number of times each game task is completed (completion of game task T)178Number of times of completion of the game task T179…, and completion of task T188The number of times) the predetermined operation index includes a game duration of the user.
As shown in fig. 12, in one embodiment, a method for determining the effectiveness of an operation project is provided. The method may include the following steps S1201 to S1211.
And S1201, acquiring feature sample data and index sample data corresponding to the feature sample data, wherein the feature sample data comprises sample data of a preset operation feature parameter corresponding to the operation item to be determined, and the index sample data comprises sample data of a preset operation index corresponding to the operation item.
S1202, a relation model of the preset operation characteristic parameter and the preset operation index is determined based on the regression model, the characteristic sample data and the index sample data of the preset type.
S1203, determining a first statistical detection quantity based on the relation model, the characteristic sample data and the index sample data.
S1204, judge whether the first statistical detection quantity is greater than the predetermined first critical value; if so, obtaining a first relevance result, which includes an overall relevance result (not numbered), and jumping to step S1205, otherwise, obtaining a second relevance result, which includes an overall non-relevance result (not numbered), and ending the process.
And S1205, determining each second statistical detection quantity corresponding to each preset operation characteristic parameter respectively based on the relation model, the characteristic sample data and the index sample data.
And S1206, determining a second statistical detection quantity from the second statistical detection quantities which are not judged, wherein the second statistical detection quantity is used as the current second statistical detection quantity to be judged.
S1207, judging whether the absolute value of the current second statistical detection quantity to be judged is larger than or equal to a preset second critical value; if so, the process goes to step S1207a, and if not, the process goes to step S1207 b.
S1207a, obtaining a first correlation result, where the first correlation result further includes an independent correlation result corresponding to the current second statistical testing quantity to be determined.
S1207b, obtaining a first relevance result, where the first relevance result further includes an independent non-relevance result corresponding to the current second statistical testing amount to be determined.
S1208, judging whether the number of the second statistical detection quantity which is not judged is zero; if not, go to step S1206, and if yes, go to step S1209.
S1209, determining a third statistical detection quantity based on the relation model, the characteristic sample data and the index sample data.
S1210, obtaining a first correlation result based on the value of the third statistical detection quantity, wherein the first correlation result further comprises an overall correlation degree result.
S1211, obtaining a validity result corresponding to the operation item to be determined based on the first relevance result.
It should be noted that the technical features of each step in this embodiment may be the same as those of the corresponding step in the previous embodiments, and are not repeated herein.
It should be understood that although the various steps in the flowcharts of fig. 2-6, 9 and 12 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-6, 9 and 12 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performing the sub-steps or stages is not necessarily sequential, but may be performed alternately or alternatingly with other steps or at least some of the sub-steps or stages of other steps.
As shown in fig. 13, in one embodiment, a device 1300 for determining the effectiveness of an operational project is provided. The apparatus can include the following modules 1302-1308.
A sample data obtaining module 1302, configured to obtain feature sample data and index sample data corresponding to the feature sample data, where the feature sample data includes sample data of a predetermined operation feature parameter corresponding to an operation item to be determined, and the index sample data includes sample data of a predetermined operation index corresponding to the operation item;
a relation model determining module 1304, configured to determine a relation model between a predetermined operation characteristic parameter and a predetermined operation index based on a regression model of a predetermined type, the characteristic sample data, and the index sample data;
and the association result obtaining module 1306 is configured to perform statistical inspection based on the relationship model, the feature sample data, and the index sample data to obtain an association result between the predetermined operation feature parameter and the predetermined operation index.
A validity result obtaining module 1308, configured to obtain a validity result corresponding to the operation item to be determined based on the relevance result.
The apparatus 1300 for determining the validity of the operation project determines a relationship model between the predetermined operation characteristic parameter and the predetermined operation index based on the related sample data of the operation project to be determined, performs a statistical test based on the relationship model and the sample data, obtains a correlation result between the predetermined operation characteristic parameter and the predetermined operation index, and further obtains a validity result corresponding to the operation project based on the correlation result. On one hand, the incidence relation between the preset operation characteristic parameters and the preset operation indexes does not need to be analyzed manually, and the efficiency and the accuracy can be improved. On the other hand, statistical verification is carried out based on the related sample data and the relation model, then the validity result corresponding to the operation project is obtained based on the relevance result, and when the operation condition of the operation project does not have the intuitive and obvious relevance relation with the preset operation target, the validity condition of the operation project can be determined.
In one embodiment, the association result obtaining module 1306 may include the following units: and the first statistical determination unit is used for determining a first statistical detection quantity based on the relation model, the characteristic sample data and the index sample data. And the first size comparison unit is used for comparing the first statistical detection quantity with a preset first critical value in size, and obtaining a correlation result between the preset operation characteristic parameter and the preset operation index based on the comparison result, wherein the correlation result is used for representing whether the preset operation characteristic parameter and the preset operation index have a corresponding correlation relationship or not.
Wherein, the first statistical detection quantitative determination unit may include the following sub-units: and the first parameter determining subunit is used for obtaining a regression square sum, a regression degree of freedom, a residual square sum and a residual degree of freedom based on the relation model, the feature sample data and the index sample data. And the regression mean square error determining subunit is used for obtaining the regression mean square error based on the regression sum of squares and the regression degree of freedom. And the residual mean square error determining subunit is used for obtaining the residual mean square error based on the residual square sum and the residual freedom degree. And the first statistical detection quantitative determination subunit is used for determining the ratio of the regression mean square error to the residual mean square error as the first statistical detection quantitative.
In one embodiment, when the number of the predetermined operation characteristic parameters is more than two, the association result obtaining module 1306 may include the following units: and the second statistic acquisition unit is used for determining each second statistic detection quantity corresponding to each preset operation characteristic parameter respectively based on the relation model, the characteristic sample data and the index sample data. And the second size comparison unit is used for respectively comparing the absolute value of each second statistical detection quantity with a preset second critical value, and respectively obtaining a correlation result between each preset operation characteristic parameter and each preset operation index based on each comparison result, wherein the correlation result is used for representing whether the corresponding preset operation characteristic parameter and the corresponding preset operation index have a corresponding correlation relationship.
Wherein, the first statistic obtaining unit may include the following sub-units: and the regression coefficient obtaining subunit is used for respectively obtaining the regression coefficients corresponding to the preset operation characteristic parameters based on the relational model. And the coefficient standard deviation obtaining subunit is used for obtaining regression coefficient standard deviations corresponding to the preset operation characteristic parameters based on the relation model, the characteristic sample data and the index sample data. And the second statistic obtaining subunit is used for respectively determining the ratio of the regression coefficient corresponding to each preset operation characteristic parameter to the standard deviation of the regression coefficient as each second statistic detection quantity corresponding to each preset operation characteristic parameter.
In one embodiment, the association result obtaining module 1306 may include the following units: and the third statistic obtaining unit is used for determining a third statistic detection quantity based on the relation model, the feature sample data and the index sample data. And the correlation result obtaining unit is used for obtaining a correlation result between the preset operation characteristic parameter and the preset operation index based on the numerical value of the third statistical detection quantity, and the correlation result is used for representing the degree of correlation between the preset operation characteristic parameter and the preset operation index.
Wherein, the third statistic obtaining unit may include the following sub-units: and the square sum obtaining subunit is used for obtaining a regression square sum and a total dispersion square sum based on the relation model, the characteristic sample data and the index sample data. And a third statistic obtaining subunit, configured to determine a ratio of the regression sum of squares to the total sum of squared deviations as a third statistical detection amount.
In one embodiment, the apparatus 1300 may further include the following modules: the first index data acquisition module is used for acquiring first index sample data of a user who is scheduled to participate in the project and second index sample data of a user who is scheduled not to participate in the project in a preset time period. And the fourth statistic acquisition module is used for determining a fourth statistical detection quantity based on the first index sample data and the second index sample data. And the first validity determining module is used for obtaining a validity result corresponding to the operation project based on the fourth statistical detection quantity.
Wherein, the fourth statistic obtaining module may include the following units: and the average value difference obtaining unit is used for obtaining the average value difference of the first index sample data and the second index sample data. And a standard value difference obtaining unit for obtaining a standard value difference by subtracting the predetermined participation index standard value and the predetermined non-predetermined participation index standard value. And the first difference value obtaining unit is used for subtracting the average value difference from the standard value difference to obtain a first difference value. And the first sample parameter obtaining unit is used for obtaining a first sample variance and a first sample capacity based on the first index sample data. A second sample parameter obtaining unit, configured to obtain a second sample variance and a second sample capacity based on the second index sample data. And the first sample mean deviation obtaining unit is used for obtaining a first sample mean standard deviation based on the first sample variance, the first sample capacity, the second sample variance and the second sample capacity. And the fourth statistic obtaining unit is used for determining the ratio of the first difference value to the standard deviation of the first sample mean value as a fourth statistic detection quantity.
In one embodiment, the apparatus 1300 may further include the following modules: and the second index data acquisition module is used for acquiring third index sample data of a predetermined sample user in a predetermined non-project-participating time period and fourth index sample data of the predetermined sample user in a predetermined project-participating time period. And the fifth statistic obtaining module is used for determining a fifth statistical detection quantity based on the third index sample data and the fourth index sample data. And the second validity determining module is used for obtaining a validity result corresponding to the operation project based on the fifth statistical detection quantity.
Wherein, the fifth statistic obtaining module may include the following units: and the variable data obtaining unit is used for correspondingly subtracting the third index sample data and the fourth index sample data to obtain variable sample data. And the second difference obtaining unit is used for obtaining a second difference by subtracting the mean value of the variation sample data from the preset variation standard value. And the third sample parameter obtaining unit is used for obtaining the standard deviation of the sample and the capacity of the third sample based on the variable sample data. And the second sample mean deviation obtaining unit is used for obtaining a second sample mean deviation standard deviation based on the sample standard deviation and the third sample capacity. And the fifth statistic obtaining unit is used for determining the ratio of the second difference value to the standard deviation of the second sample mean value as a fifth statistical detection quantity.
In one embodiment, the operation item to be determined comprises a game task of the online game, the predetermined operation characteristic parameter comprises the number of times of completing the game task, and the predetermined operation index comprises the game duration of the user.
For specific limitations of the operation item validity determination device, reference may be made to the above limitations of the operation item validity determination method, and details are not repeated here. The modules in the device for determining the effectiveness of the operation items can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which includes a memory and a processor, where the memory stores a computer program, and the processor implements a validity determination method for an operation item provided in any embodiment of the present application when executing the computer program.
In one embodiment, the computer device may be the server 120 shown in FIG. 1, and its internal structure diagram may be as shown in FIG. 14. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor is configured to provide computational and control capabilities. The memory includes a nonvolatile storage medium and an internal memory, the nonvolatile storage medium stores an operating system and a computer program, the internal memory provides an environment for running the operating system and the computer program in the nonvolatile storage medium, and the computer program is executed by the processor to implement the validity determination method for the operation item provided in any embodiment of the present application. The network interface is used for communicating with an external terminal through a network connection.
In another embodiment, the computer device may be the user terminal 110 shown in fig. 1, and its internal structure diagram may be as shown in fig. 15. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected by a system bus. Wherein the processor is configured to provide computational and control capabilities. The memory includes a nonvolatile storage medium and an internal memory, the nonvolatile storage medium stores an operating system and a computer program, the internal memory provides an environment for running the operating system and the computer program in the nonvolatile storage medium, and the computer program is executed by the processor to implement the validity determination method for the operation item provided in any embodiment of the present application. The network interface is used for communicating with an external terminal through a network connection. The display may be a liquid crystal display or an electronic ink display. The input device of the computer equipment can be a touch layer covered on a display screen, a key, a track ball or a touch pad arranged on a shell of the computer equipment, an external keyboard, a touch pad or a mouse and the like.
It will be appreciated that the configurations shown in fig. 14 and 15 are block diagrams of only some of the configurations relevant to the present application, and do not constitute a limitation on the computing devices to which the present application may be applied, and that a particular computing device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, the apparatus for determining the effectiveness of an operation project provided by the present application may be implemented in the form of a computer program, and the computer program may be run on a computer device as shown in fig. 14 or 15. The memory of the computer device may store various program modules that make up the apparatus. For example, the sample data obtaining module 1302, the relationship model determining module 1304, the association result obtaining module 1306 and the validity result obtaining module 1308 shown in fig. 13. The computer program constituted by the respective program modules causes the processor to execute the steps in the determination method of the effectiveness of the operation item of the respective embodiments of the present application described in the present specification. For example, the computer device shown in fig. 14 or fig. 15 may perform step S202 by the sample data acquisition module 1302 in the apparatus shown in fig. 13, perform step S204 by the relationship model determination module 1304, perform step S206 by the association result acquisition module 1306, perform step S208 by the validity result acquisition module 1308, and so on.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, and the program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
Accordingly, in one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and the computer program, when executed by a processor, implements the method for determining the effectiveness of an operation project provided in any one of the embodiments of the present application.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (16)

1. A method for determining the effectiveness of an operation project is characterized by comprising the following steps:
acquiring characteristic sample data and index sample data corresponding to the characteristic sample data, wherein the characteristic sample data comprises sample data of a preset operation characteristic parameter corresponding to an operation project to be determined, the index sample data comprises sample data of a preset operation index corresponding to the operation project, the preset operation index is used for measuring a preset operation target of the operation project, and the preset operation target comprises at least one of improving user stickiness, improving user activity, improving user retention rate and improving user payment rate;
determining a relation model of the preset operation characteristic parameter and the preset operation index based on a regression model of a preset type, the characteristic sample data and the index sample data;
performing statistical test on the basis of the relationship model, the feature sample data and the index sample data to obtain a correlation result between the preset operation feature parameter and the preset operation index; the correlation result is used for representing the influence degree of the preset operation characteristic parameter on the preset operation index;
obtaining a validity result corresponding to the operation project based on the relevance result; and the effectiveness result is used for representing the effectiveness degree of the operation item on realizing the preset operation target.
2. The method according to claim 1, wherein said performing a statistical test based on said relationship model, said feature sample data and said index sample data to obtain a result of correlation between said predetermined operation feature parameter and said predetermined operation index comprises the steps of:
determining a first statistical detection quantity based on the relationship model, the feature sample data and the index sample data;
comparing the first statistical detection quantity with a preset first critical value, and obtaining a correlation result between the preset operation characteristic parameter and the preset operation index based on the comparison result, wherein the correlation result is used for representing whether the preset operation characteristic parameter and the preset operation index have a corresponding correlation relationship or not;
wherein determining the first statistical detection quantity comprises:
obtaining a regression sum of squares, a regression degree of freedom, a residual sum of squares, and a residual degree of freedom based on the relationship model, the feature sample data, and the index sample data;
obtaining a regression mean square error based on the regression sum of squares and the regression degree of freedom;
obtaining a residual mean square error based on the residual sum of squares and the residual degree of freedom;
and determining the ratio of the regression mean square error to the residual mean square error as the first statistical detection quantity.
3. The method of claim 1, wherein:
when the number of the predetermined operation characteristic parameters is more than two, the statistical test is performed based on the relationship model, the characteristic sample data and the index sample data to obtain the correlation result between the predetermined operation characteristic parameters and the predetermined operation index, and the method comprises the following steps:
determining each second statistical detection quantity corresponding to each preset operation characteristic parameter respectively based on the relationship model, the characteristic sample data and the index sample data;
comparing the absolute value of each second statistical detection quantity with a preset second critical value, and obtaining a correlation result between each preset operation characteristic parameter and the preset operation index based on each comparison result, wherein the correlation result is used for representing whether the corresponding preset operation characteristic parameter and the preset operation index have a corresponding correlation relationship;
wherein determining the manner of each second statistical detection quantity corresponding to each of the predetermined operation characteristic parameters, respectively, comprises the steps of:
obtaining regression coefficients corresponding to the preset operation characteristic parameters respectively based on the relation model;
obtaining a regression coefficient standard deviation corresponding to each preset operation characteristic parameter based on the relation model, the characteristic sample data and the index sample data;
and respectively determining the ratio of the regression coefficient corresponding to each preset operation characteristic parameter to the standard deviation of the regression coefficient as each second statistical detection quantity corresponding to each preset operation characteristic parameter.
4. The method according to claim 2, wherein said performing a statistical test based on said relationship model, said feature sample data and said index sample data to obtain a result of correlation between said predetermined operation feature parameter and said predetermined operation index comprises the steps of:
determining a third statistical detection quantity based on the relationship model, the feature sample data and the index sample data;
obtaining a correlation result between the predetermined operation characteristic parameter and the predetermined operation index based on the value of the third statistical detection quantity, wherein the correlation result is used for representing the correlation degree between the predetermined operation characteristic parameter and the predetermined operation index;
wherein determining the manner of the third statistical detection quantity comprises the steps of:
obtaining a regression sum of squares and a total dispersion sum of squares based on the relationship model, the feature sample data and the index sample data;
determining a ratio of the regression sum of squares to the total sum of squared deviations as the third statistical measure.
5. The method of claim 1, further comprising:
acquiring first index sample data of a user who is scheduled to participate in a project and second index sample data of a user who is scheduled not to participate in the project in a preset time period;
determining a fourth statistical detection quantity based on the first index sample data and the second index sample data;
obtaining a validity result corresponding to the operation project based on the fourth statistical detection quantity;
wherein determining the manner of the fourth statistical detection quantity comprises the steps of:
obtaining a mean difference between the first index sample data and the second index sample data;
subtracting the preset participation index standard value from the preset non-preset participation index standard value to obtain a standard value difference;
subtracting the average value difference from the standard value difference to obtain a first difference value;
obtaining a first sample variance and a first sample capacity based on the first index sample data;
obtaining a second sample variance and a second sample volume based on the second index sample data;
obtaining a first sample mean standard deviation based on the first sample variance, a first sample volume, the second sample variance, and the second sample volume;
and determining the ratio of the first difference to the standard deviation of the first sample mean as the fourth statistical detection quantity.
6. The method of claim 1, further comprising:
acquiring third index sample data of a predetermined sample user in a predetermined non-participation project time period and fourth index sample data of the predetermined sample user in a predetermined participation project time period;
determining a fifth statistical detection quantity based on the third index sample data and the fourth index sample data;
obtaining a validity result corresponding to the operation project based on the fifth statistical detection quantity;
wherein, determining the mode of the fifth statistical detection quantity comprises the following steps:
correspondingly subtracting the third index sample data from the fourth index sample data to obtain variation sample data;
the mean value of the variation sample data is subtracted from a preset variation standard value to obtain a second difference value;
obtaining a sample standard deviation and a third sample capacity based on the variation sample data;
obtaining a second sample mean standard deviation based on the sample standard deviation and a third sample capacity;
and determining the ratio of the second difference to the standard deviation of the second sample mean as the fifth statistical detection quantity.
7. The method according to any one of claims 1 to 6, wherein the operation item to be determined comprises a game task of a network game, the predetermined operation characteristic parameter comprises a number of times the game task is completed, and the predetermined operation index comprises a game duration of a user.
8. An apparatus for determining the effectiveness of an operational project, comprising:
the system comprises a sample data acquisition module, a parameter setting module and a parameter setting module, wherein the sample data acquisition module is used for acquiring characteristic sample data and index sample data corresponding to the characteristic sample data, the characteristic sample data comprises sample data of a preset operation characteristic parameter corresponding to an operation project to be determined, the index sample data comprises sample data of a preset operation index corresponding to the operation project, and the preset operation target comprises at least one of user stickiness improvement, user activity improvement, user retention rate improvement and user payment rate improvement;
the relation model determining module is used for determining a relation model between the preset operation characteristic parameter and the preset operation index based on a regression model of a preset type, the characteristic sample data and the index sample data;
a correlation result obtaining module, configured to perform statistical inspection based on the relationship model, the feature sample data, and the index sample data, and obtain a correlation result between the predetermined operation feature parameter and the predetermined operation index; the correlation result is used for representing the influence degree of the preset operation characteristic parameter on the preset operation index;
the validity result obtaining module is used for obtaining a validity result corresponding to the operation project based on the relevance result; and the effectiveness result is used for representing the effectiveness degree of the operation item on realizing the preset operation target.
9. The apparatus according to claim 8, wherein the correlation result obtaining module comprises a first statistic determining unit and a first size comparing unit;
the first statistical measurement determining unit is used for determining a first statistical detection quantity based on the relation model, the feature sample data and the index sample data;
the first size comparison unit is used for comparing the first statistical detection quantity with a preset first critical value, and obtaining a correlation result between the preset operation characteristic parameter and the preset operation index based on the comparison result, wherein the correlation result is used for representing whether the preset operation characteristic parameter and the preset operation index have a corresponding correlation relationship or not;
the first statistical detection quantitative determination unit comprises a first parameter determination subunit, a regression mean square error determination subunit, a residual mean square error determination subunit and a first statistical detection quantitative determination subunit;
the first parameter determining subunit is configured to obtain a regression square sum, a regression degree of freedom, a residual square sum, and a residual degree of freedom based on the relationship model, the feature sample data, and the index sample data;
the regression mean square error determining subunit is used for obtaining regression mean square error based on the regression sum of squares and the regression degree of freedom;
the residual mean square error determining subunit is used for obtaining a residual mean square error based on the residual square sum and the residual freedom degree;
and the first statistical detection quantity determining subunit is used for determining the ratio of the regression mean square error to the residual mean square error as the first statistical detection quantity.
10. The apparatus according to claim 8, wherein the correlation result obtaining module includes a second statistic obtaining unit and a second size comparing unit;
the second statistic obtaining unit is configured to determine, based on the relationship model, the feature sample data, and the index sample data, each second statistical detection amount corresponding to each predetermined operation feature parameter;
the second size comparison unit is configured to respectively compare an absolute value of each second statistical detection quantity with a predetermined second critical value, and respectively obtain a correlation result between each predetermined operation characteristic parameter and the predetermined operation index based on each comparison result, where the correlation result is used to represent whether a corresponding correlation relationship exists between the corresponding predetermined operation characteristic parameter and the predetermined operation index;
the second statistic obtaining unit comprises a regression coefficient obtaining subunit, a coefficient standard deviation obtaining subunit and a second statistic obtaining subunit;
the regression coefficient obtaining subunit is configured to obtain, based on the relationship model, regression coefficients corresponding to the predetermined operation characteristic parameters, respectively;
the coefficient standard deviation obtaining subunit is configured to obtain a regression coefficient standard deviation corresponding to each of the predetermined operation characteristic parameters based on the relationship model, the characteristic sample data, and the index sample data;
and the second statistic obtaining subunit is configured to determine, as each second statistic check amount corresponding to each predetermined operation feature parameter, a ratio between a regression coefficient corresponding to each predetermined operation feature parameter and a standard deviation of the regression coefficient.
11. The apparatus according to claim 9, wherein the correlation result obtaining module includes a third statistic obtaining unit and a correlation result obtaining unit;
the third statistic obtaining unit is configured to determine a third statistical detection amount based on the relationship model, the feature sample data, and the index sample data;
the correlation result obtaining unit is configured to obtain a correlation result between the predetermined operation characteristic parameter and the predetermined operation index based on the value of the third statistical detection quantity, where the correlation result is used to represent a degree of correlation between the predetermined operation characteristic parameter and the predetermined operation index;
wherein the third statistic obtaining unit includes a sum of squares obtaining subunit and a third statistic obtaining subunit;
the square sum obtaining subunit is configured to obtain a regression square sum and a total dispersion square sum based on the relationship model, the feature sample data, and the index sample data;
and the third statistic obtaining subunit is configured to determine a ratio of the regression sum of squares to the total sum of squared deviations as the third statistical determination amount.
12. The apparatus of claim 8, further comprising:
the first index data acquisition module is used for acquiring first index sample data of a user who is scheduled to participate in a project and second index sample data of a user who is scheduled not to participate in the project in a preset time period;
a fourth statistic obtaining module, configured to determine a fourth statistical detection amount based on the first index sample data and the second index sample data;
a first validity determination module, configured to obtain a validity result corresponding to the operation item based on the fourth statistical detection amount;
the fourth statistic obtaining module comprises a mean value difference obtaining unit, a standard value difference obtaining unit, a first sample parameter obtaining unit, a second sample parameter obtaining unit, a first sample mean value obtaining unit and a fourth statistic obtaining unit;
the mean difference obtaining unit is configured to obtain a mean difference between the first index sample data and the second index sample data;
the standard value difference obtaining unit is used for subtracting the preset participation index standard value and the preset non-preset participation index standard value to obtain a standard value difference;
the first difference obtaining unit is configured to obtain a first difference by subtracting the average value difference from the standard value difference;
the first sample parameter obtaining unit is configured to obtain a first sample variance and a first sample capacity based on the first index sample data;
the second sample parameter obtaining unit is configured to obtain a second sample variance and a second sample capacity based on the second index sample data;
the first sample mean deviation obtaining unit is used for obtaining a first sample mean standard deviation based on the first sample variance, the first sample capacity, the second sample variance and the second sample capacity;
the fourth statistic obtaining unit is configured to determine a ratio of the first difference to the standard deviation of the first sample mean as the fourth statistical detection amount.
13. The apparatus of claim 8, further comprising:
the second index data acquisition module is used for acquiring third index sample data of a predetermined sample user in a predetermined non-project-participating time period and fourth index sample data of the predetermined sample user in a predetermined project-participating time period;
a fifth statistic obtaining module, configured to determine a fifth statistical detection amount based on the third index sample data and the fourth index sample data;
a second validity determination module, configured to obtain a validity result corresponding to the operation item based on the fifth statistical detection amount;
the fifth statistic obtaining module comprises a variation data obtaining unit, a second difference obtaining unit, a third sample parameter obtaining unit, a second sample mean-square error obtaining unit and a fifth statistic obtaining unit;
the variable data obtaining unit is configured to subtract the third index sample data from the fourth index sample data to obtain variable sample data;
the second difference obtaining unit is configured to obtain a second difference by subtracting the average value of the variation sample data from a predetermined variation standard value;
the third sample parameter obtaining unit is configured to obtain a sample standard deviation and a third sample capacity based on the variation sample data;
the second sample mean deviation obtaining unit is used for obtaining a second sample mean deviation standard deviation based on the sample standard deviation and a third sample capacity;
the fifth statistic obtaining unit is configured to determine a ratio of the second difference to the second sample mean standard deviation as the fifth statistical determination amount.
14. The apparatus according to any one of claims 8 to 13, wherein the operation item to be determined comprises a game task of a network game, the predetermined operation characteristic parameter comprises a number of times the game task is completed, and the predetermined operation index comprises a game duration of a user.
15. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
16. A computer device comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 7 when executing the computer program.
CN201810146258.0A 2018-02-12 2018-02-12 Method and device for determining effectiveness of operation project and computer equipment Active CN108305013B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810146258.0A CN108305013B (en) 2018-02-12 2018-02-12 Method and device for determining effectiveness of operation project and computer equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810146258.0A CN108305013B (en) 2018-02-12 2018-02-12 Method and device for determining effectiveness of operation project and computer equipment

Publications (2)

Publication Number Publication Date
CN108305013A CN108305013A (en) 2018-07-20
CN108305013B true CN108305013B (en) 2022-02-18

Family

ID=62865484

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810146258.0A Active CN108305013B (en) 2018-02-12 2018-02-12 Method and device for determining effectiveness of operation project and computer equipment

Country Status (1)

Country Link
CN (1) CN108305013B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6717595B1 (en) * 2000-12-29 2004-04-06 Sun Microsystems, Inc. Computer-based list editor
CN103246958A (en) * 2013-05-17 2013-08-14 国家电网公司 Production concentrating operation system of provincial power metering center
CN104778173A (en) * 2014-01-10 2015-07-15 腾讯科技（深圳）有限公司 Determination method, device and equipment of objective user
CN106294182A (en) * 2016-08-24 2017-01-04 腾讯科技（深圳）有限公司 A kind of determine many survey the feedback method of effectiveness, test equipment and system

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6717595B1 (en) * 2000-12-29 2004-04-06 Sun Microsystems, Inc. Computer-based list editor
CN103246958A (en) * 2013-05-17 2013-08-14 国家电网公司 Production concentrating operation system of provincial power metering center
CN104778173A (en) * 2014-01-10 2015-07-15 腾讯科技（深圳）有限公司 Determination method, device and equipment of objective user
CN106294182A (en) * 2016-08-24 2017-01-04 腾讯科技（深圳）有限公司 A kind of determine many survey the feedback method of effectiveness, test equipment and system

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
预测方法的有效性分析;王明涛;《预测》;19941231(第6期);57-59 *

Also Published As

Publication number Publication date
CN108305013A (en) 2018-07-20

Similar Documents

Publication Publication Date Title
CN109840668B (en) Patent evaluation method using structural equation model and system for executing the method
White et al. Methodological tools
Wang et al. Adjusted logistic propensity weighting methods for population inference using nonprobability volunteer‐based epidemiologic cohorts
CN110941555A (en) Test case recommendation method and device, computer equipment and storage medium
CN115659177A (en) Method and device for generating data recommendation model and computer equipment
Ritter Offshoring and occupational specificity of human capital
Kamran et al. Estimating calibrated individualized survival curves with deep learning
Rosopa et al. Robustness of statistical inferences using linear models with meta-analytic correlation matrices
Schecter et al. The power, accuracy, and precision of the relational event model
US20220172085A1 (en) Methods and Systems to Account for Uncertainties from Missing Covariates in Generative Model Predictions
CN111091276A (en) Enterprise risk scoring method and device, computer equipment and storage medium
CN108304289B (en) Terminal fingerprint test method and device, computer equipment and storage medium
Beyhum et al. Instrumental variable quantile regression under random right censoring
CN108305013B (en) Method and device for determining effectiveness of operation project and computer equipment
Argyropoulos et al. Backtesting VaR and ES under the magnifying glass
Hu et al. Estimating incentive and selection effects in the medigap insurance market: An application with Dirichlet process mixture model
de Silva et al. Modeling and analysis of functional method comparison data
Popping Ag09: a computer program for interrater agreement for judgments
Waldorp et al. Network Inference with the Lasso
CN110858343A (en) Data asset value evaluation system and method
Ahmad et al. The Adoption of Enterprise Architecture by Public Sector Organizations: Research in Brief
KR20200086158A (en) The method and system for the resolution of bias arising from immeasurable time in the estimation of drug's effects
Lyu et al. Additive rates model for recurrent event data with intermittently observed time-dependent covariates
CN109816187B (en) Information processing method, information processing device, computer equipment and storage medium
Sinha et al. Semiparametric Bayesian analysis of censored linear regression with errors-in-covariates

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant