CN113256353A - Business data processing method and construction method of business data processing system - Google Patents
Business data processing method and construction method of business data processing system Download PDFInfo
- Publication number
- CN113256353A CN113256353A CN202110759304.6A CN202110759304A CN113256353A CN 113256353 A CN113256353 A CN 113256353A CN 202110759304 A CN202110759304 A CN 202110759304A CN 113256353 A CN113256353 A CN 113256353A
- Authority
- CN
- China
- Prior art keywords
- data
- dependent variable
- variable data
- current
- historical
- 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.)
- Granted
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
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present disclosure relates to a method for processing service data and a method for constructing a service data processing system, the method including: acquiring user portrait data and user behavior data of a target service; determining current independent variable data and current dependent variable data indicating a current time point and historical dependent variable data indicating a historical time point from the user behavior data aiming at the analysis object of the target service; constructing a panel data model based on the user representation data, the current independent variable data, the current dependent variable data, and the historical dependent variable data; and determining the influence degree value of the historical dependent variable data on the current dependent variable data by using the panel data model. The method and the device can improve the accuracy of analyzing the analysis object, and further improve the accuracy of the provided service guide information. The constructed service data processing system can improve the analysis efficiency of large data volume and even mass user data.
Description
Technical Field
The present disclosure relates to computer technologies, and in particular, to a method for processing service data and a method for constructing a service data processing system.
Background
With the development of internet technology, more and more internet products are emerging, which provide users with rich product use experiences, such as the experience of watching short videos, the experience of participating in live broadcasts as a main broadcast/audience, and the like. In order to better analyze the situation that users use internet products, in the related art, a large amount of data is often collected, and then the related data is regressed based on an analysis object to obtain the relationship between a dependent variable and an independent variable. For example, a large amount of user behavior data of a certain internet product is collected, and then research is performed based on a regression model of an analysis model, for example, a relationship between a duration (dependent variable) when a user uses the certain internet product and comment area behavior data (independent variable) of the user. However, some independent variables are often highly self-correlated in a short time, and therefore, the influence degree of such independent variables on dependent variables is overestimated, and regression results are biased, thereby providing inaccurate service guide information for optimizing current internet products or developing new internet products. Therefore, the above-mentioned related art solutions have problems that the analysis object cannot be accurately and effectively analyzed and accurate and effective service guide information cannot be provided.
Disclosure of Invention
The present disclosure provides a method for processing service data and a method for constructing a service data processing system, so as to solve at least the problems of the related art that an analysis object cannot be accurately and effectively analyzed and accurate and effective service guide information cannot be provided. The technical scheme of the disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, a method for processing service data is provided, where the method includes:
acquiring user portrait data and user behavior data of a target service;
determining current independent variable data and current dependent variable data indicating a current time point and historical dependent variable data indicating a historical time point from the user behavior data aiming at the analysis object of the target service;
constructing a panel data model based on the user representation data, the current independent variable data, the current dependent variable data, and the historical dependent variable data;
and determining the influence degree value of the historical dependent variable data on the current dependent variable data by using the panel data model.
In an exemplary embodiment, the building a panel data model based on the user representation data, the current independent variable data, the current dependent variable data, and the historical dependent variable data includes:
determining a fixed effect value corresponding to the user representation data;
determining an error term indicative of the current point in time;
constructing the panel data model based on the fixed effect value, the error term, the current independent variable data, the current dependent variable data, and the historical dependent variable data.
In an exemplary embodiment, the determining, by using the panel data model, a degree of influence value of the historical dependent variable data on the current dependent variable data includes:
performing first-order difference processing on the panel data model in a time dimension;
determining tool variables with preset correlation degrees with the historical dependent variable data based on a first-order difference processing result;
and performing regression processing on the panel data model by using the tool variables to obtain the degree of influence of the historical dependent variable data on the current dependent variable data.
In an exemplary embodiment, the performing regression processing on the panel data model by using the tool variable to obtain the degree of influence of the historical dependent variable data on the current dependent variable data includes:
when the number of the tool variables is larger than the preset number, constructing a moment condition corresponding to the first-order difference processing result by using the tool variables based on a generalized moment estimation method; the preset number is determined by the pre-estimated parameters corresponding to the panel data model;
determining a degree of influence value of the historical dependent variable data on the current dependent variable data based on the moment condition.
In an exemplary embodiment, the performing regression processing on the panel data model by using the tool variable to obtain an influence degree value of the historical dependent variable data on the current dependent variable data further includes:
and when the number of the tool variables is less than or equal to the preset number, performing least square regression on the first-order difference processing result by using the tool variables to obtain the degree of influence of the historical dependent variable data on the current dependent variable data.
In an exemplary embodiment, the performing regression processing on the panel data model by using the tool variable to obtain the degree of influence of the historical dependent variable data on the current dependent variable data includes:
acquiring a preset function;
and processing the first-order difference processing result by using the preset function and the tool variable to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
According to a second aspect of the embodiments of the present disclosure, there is provided a method for constructing a business data processing system, the method including:
acquiring a preset basic frame;
acquiring a first service code; the first service code indicates to acquire user portrait data and user behavior data of a target service, and determines current independent variable data and current dependent variable data indicating a current time point and historical dependent variable data indicating a historical time point from the user behavior data aiming at an analysis object of the target service;
acquiring a second service code; wherein the second business code indicates that the panel data model is constructed based on the user portrait data, the current independent variable data, the current dependent variable data, and the historical dependent variable data, and that the panel data model is utilized to determine a degree of influence value of the historical dependent variable data on the current dependent variable data;
and fusing the preset basic framework, the first service code and the second service code to construct a service data processing system.
According to a third aspect of the embodiments of the present disclosure, there is provided a service data processing apparatus, including:
a data acquisition unit configured to perform acquisition of user portrait data and user behavior data of a target service;
a variable data determination unit configured to execute an analysis object for the target service, determine current independent variable data and current dependent variable data indicating a current time point, and historical dependent variable data indicating a historical time point from the user behavior data;
a model construction unit configured to perform construction of a panel data model based on the user portrait data, the current independent variable data, the current dependent variable data, and the historical dependent variable data;
a degree value determination unit configured to perform determining an influence degree value of the historical dependent variable data on the current dependent variable data using the panel data model.
In an exemplary embodiment, the model building unit includes:
a fixed effect value determination unit configured to perform determining a fixed effect value to which the user portrait data corresponds;
an error term determination unit configured to perform determining an error term indicating the current time point;
a model building subunit configured to perform building the panel data model based on the fixed effect value, the error term, the current independent variable data, the current dependent variable data, and the historical dependent variable data.
In an exemplary embodiment, the degree value determining unit includes:
a difference processing unit configured to perform first-order difference processing of a time dimension on the panel data model;
a tool variable determination unit configured to perform determination of a tool variable having a preset degree of correlation with the history dependent variable data based on a first order difference processing result;
and the regression unit is configured to perform regression processing on the panel data model by using the tool variable to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
In an exemplary embodiment, the regression unit includes:
a moment condition construction unit configured to perform construction of a moment condition corresponding to the first-order difference processing result by using the tool variables based on a generalized moment estimation device when the number of the tool variables is greater than a preset number; the preset number is determined by the pre-estimated parameters corresponding to the panel data model;
a first degree value determining subunit configured to perform determining a degree of influence value of the historical dependent variable data on the current dependent variable data based on the moment condition.
In an exemplary embodiment, the regression unit further includes:
and the second degree value determining subunit is configured to perform least square regression on the first-order difference processing result by using the tool variables when the number of the tool variables is less than or equal to a preset number, so as to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
In an exemplary embodiment, the regression unit includes:
a function acquisition unit configured to perform acquisition of a preset function;
and the third degree value determining subunit is configured to execute processing of the first-order difference processing result by using the preset function and the tool variable to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
According to a fourth aspect of the embodiments of the present disclosure, there is provided a construction apparatus of a business data processing system, the apparatus including:
a frame acquisition unit configured to perform acquisition of a preset base frame;
a first service code acquisition unit configured to perform acquisition of a first service code; the first service code indicates to acquire user portrait data and user behavior data of a target service, and determines current independent variable data and current dependent variable data indicating a current time point and historical dependent variable data indicating a historical time point from the user behavior data aiming at an analysis object of the target service;
a second service code acquiring unit configured to perform acquisition of a second service code; wherein the second business code indicates to construct a panel data model based on the user representation data, the current independent variable data, the current dependent variable data, and the historical dependent variable data, and to determine a degree of influence value of the historical dependent variable data on the current dependent variable data using the panel data model;
and the fusion unit is configured to perform fusion of the preset basic framework, the first service code and the second service code to construct a service data processing system.
According to a fifth aspect of embodiments of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing the processor-executable instructions; wherein the processor is configured to execute the instructions to implement the business data processing method according to the first aspect or the construction method of the business data processing system according to the second aspect.
According to a sixth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein instructions of the computer-readable storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the business data processing method according to the first aspect or the construction method of the business data processing system according to the second aspect.
According to a seventh aspect of embodiments of the present disclosure, there is provided a computer program product comprising computer programs/instructions, wherein the computer programs/instructions, when executed by a processor, implement the business data processing method of the first aspect or the construction method of the business data processing system of the second aspect.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
user portrait data and user behavior data of a target service are obtained; then, aiming at an analysis object of the target service, current independent variable data and current dependent variable data which indicate a current time point and historical dependent variable data which indicate a historical time point are determined from the user behavior data; then, a panel data model is constructed based on the user portrait data, the current independent variable data, the current dependent variable data and the historical dependent variable data; and determining the influence degree value of the historical dependent variable data on the current dependent variable data by using the panel data model. According to the technical scheme, the accuracy of analyzing the analysis object can be improved, and the accuracy of the provided service guide information is further improved. The information of the user behavior data on the time dimension is considered, the time dimension information is not ignored when the analysis object is analyzed, and the influence of the independent variable with self-correlation on the analysis accuracy in a short time is avoided. The introduction of the historical dependent variable data and the application of the panel data model can correct the problem that the variable is omitted in the causal analysis of the scheme of the related technology, and can avoid the problem of estimation parameter error caused by neglecting the influence of the historical dependent variable on the current dependent variable. Meanwhile, a preset basic framework and relevant business codes are fused to construct a business data processing system for determining the degree of influence value of historical dependent variable data on the current dependent variable data. The analysis efficiency of the user data with large data volume and even mass can be improved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
Fig. 1 is a flowchart illustrating a business data processing method according to an exemplary embodiment.
FIG. 2 is a flow diagram illustrating building a panel data model according to an exemplary embodiment.
FIG. 3 is a flow diagram illustrating the determination of a degree of influence value of historical dependent variable data on current dependent variable data using a panel data model in accordance with an exemplary embodiment.
FIG. 4 is a flowchart illustrating the use of a tool variable regression panel data model to derive a degree of influence value of historical dependent variable data on current dependent variable data according to an exemplary embodiment.
FIG. 5 is a flowchart illustrating a method of building a business data processing system in accordance with an exemplary embodiment.
FIG. 6 is a schematic diagram illustrating a matrix of tool variables, according to an exemplary embodiment.
Fig. 7 is a flowchart also illustrating a business data processing method according to an example embodiment.
Fig. 8 is a block diagram illustrating a traffic data processing apparatus according to an example embodiment.
FIG. 9 is a block diagram illustrating a construction apparatus of a business data processing system in accordance with an exemplary embodiment.
FIG. 10 is a block diagram illustrating an electronic device in accordance with an example embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The service data processing method provided by the disclosure can be applied to a terminal or a server provided with a service data processing system, and the terminal and the server can be connected through a wired network or a wireless network. The terminal may specifically be a smart phone, a desktop computer, a tablet computer, a notebook computer, an Augmented Reality (AR)/Virtual Reality (VR) device, a digital assistant, a smart speaker, a smart wearable device, or the like. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud computing services.
Fig. 1 and 7 are flowcharts illustrating a service data processing method according to an exemplary embodiment, where the service data processing method, as shown in fig. 1, includes the following steps.
In step S101, user portrait data and user behavior data of the target service are acquired.
In this embodiment of the present specification, the target service may be some internet product, such as a short video application and a live application. The target service may also be at least one functional module of an internet product, such as a live e-commerce module of a short video application a, a live game module of a live application B, and a live show module. The target service can also be some kind of internet products, such as video internet products a-c, navigation internet products d and e.
User representation data is user characteristic information describing a plurality of dimensions of a user. User representation data of a user includes user characteristic information of multiple dimensions of the user, such as user identification, age, gender, geographic characteristic information (e.g., place of birth, location), academic calendar, occupation, hobbies, income, and the like. The subscriber characteristic information may be extracted from its subscriber information base by the network service provider of the target service. The user characteristic information can be from registration data filled by the user, collection of user behaviors by a network service provider and the like.
The user behavior data reflects the interaction operation information of the user. The user behavior data of a user includes interactive operation information of how many times the user clicks a certain page based on a client, interactive operation information of how long the user stays in a certain video for watching, interactive operation information of how many times a certain account is concerned, interactive operation information of how many times the user last interacts with the video, interactive operation information of interactive feedback (for example, comments, praise, share, forward, report, and the like) on media content (for example, short video, long video, live video, animation, image and text, and the like) provided by a target service, interactive operation information of how long the user uses the target service, and the like.
The user portrait data and user behavior data of the target service acquired here may be user portrait data and user behavior data of a plurality of users under the target service. The user profile data and the user behavior data of each user can refer to the above description, and are not described again. In practical applications, the "plurality of users" may be a vast number of users. In addition, user screening may be performed according to an analysis target of the target service, and corresponding user portrait data and user behavior data may be acquired based on "a plurality of users" after the screening. Time screening can also be performed according to an analysis object of the target service, and user portrait data and user behavior data of 'multiple users' are further acquired based on the screened time.
In step S102, for the analysis object of the target service, current independent variable data and current dependent variable data indicating a current time point and historical dependent variable data indicating a historical time point are determined from the user behavior data.
In the embodiments of the present specification, the analysis object of the target service indicates a target object that needs to be subjected to causal analysis. For example, if the analysis object is a use duration, the dependent variable is a use duration, and the independent variable is a factor or a condition causing a change of the dependent variable, and accordingly, the independent variable may select interactive operation information of the user, such as page click times, video viewing duration, and the like. Of course, the analysis object may be the use duration of the user in the age range of 30 to 40 years, and then the user profile data and the user behavior data indicating the user in the age range of 30 to 40 years may be acquired in step S201. In step S201, user portrait data and user behavior data of a plurality of users may be directly obtained without user filtering, and data filtering may be performed according to the age group of 30 to 40 years.
The acquired user behavior data may be user behavior data within a preset time period. The preset time period may be a period of time starting from a historical time point and ending at a current time point. Dependent variable data indicating the analysis object may be determined in the user behavior data according to the analysis object (such as the usage time length), and the user behavior data excluding the dependent variable data may be used as candidate data of the independent variable data. When the independent variable data is selected from the user behavior data excluding the dependent variable data, the independent variable data can be selected according to historical feedback for causal analysis, and all or part of the independent variable data can be selected. It should be noted that the user behavior data may be user behavior data indicating at least two discrete time points within a preset time period. The at least two discrete time points are a current time point and at least one historical time point.
Considering that some independent variables are often highly self-correlated in a short time, the influence degree of such independent variables on dependent variables is overestimated on the basis of the above, so that time dimension information, namely historical dependent variables,
thereby determining current dependent variable data indicating a current time point, historical dependent variable data indicating a historical time point, and current independent variable data indicating the current time point. Data indicating a current time point among the above-described dependent variable data may be taken as the current dependent variable data, and data indicating a historical time point may be taken as the historical dependent variable data. The independent variable item may be determined from the user behavior data from which the dependent variable data is removed, and then the independent variable item data indicating the current time point in the user behavior data from which the dependent variable data is removed may be used as the current independent variable data.
In step S103, a panel data model is constructed based on the user portrait data, the current independent variable data, the current dependent variable data, and the historical dependent variable data.
In the embodiment of the present specification, in order to determine the influence degree value of newly introduced historical dependent variable data on the current dependent variable, even to determine the influence degree value of the original current independent variable data on the current dependent variable, a regression model is often used to study the causal relationship. Compared with a static panel model with an inherent problem, the panel data model is constructed by utilizing user portrait data, current independent variable data, current dependent variable data and historical dependent variable data so as to better solve biased and inconsistent causal analysis results caused by the inherent problem. Wherein, 1) variables are omitted; 2) missing variables that are related to other variables in the model or interpretive and interpretive variables can be responsible for the occurrence of endogenous problems.
See equation 1 below for the constructed panel data model:
Wherein the content of the first and second substances,
and indicating the current dependent variable data to reflect the dependent variable of the user i at the time point t.
And indicating historical dependent variable data and reflecting the dependent variable of the user i at the time point t-1. And indicating the current independent variable data to reflect the independent variable of the user i at the time point t.
In order to be a random error-perturbing term,
can be divided into two parts: 1)
which is a time-independent effect term that may indicate user portrait data of user i；2）
It is an error term, user i is the error term at time point t. Gamma and beta are estimated parameters, wherein gamma is used for representing the causal relationship between historical dependent variable data and current dependent variable data, and beta is used for representing the causal relationship between current independent variable data and current dependent variable data. Then equation 1 may be further expressed as equation 2:
In an exemplary embodiment, as shown in FIG. 2, the building a panel data model based on the user representation data, the current independent variable data, the current dependent variable data, and the historical dependent variable data includes the following steps.
In step S201, a fixed effect value corresponding to the user portrait data is determined.
In step S202, an error term indicating the current time point is determined.
In step S203, the panel data model is constructed based on the fixed effect value, the error term, the current independent variable data, the current dependent variable data, and the historical dependent variable data.
User representation data for a user may be considered relatively constant, unchanging for a predetermined period of time. User portrait data may be utilized to derive time-independent effect terms. User portrait data may be input into the fixed effect model to obtain corresponding fixed effect values as effect terms
. The fixation effect here may be an individual fixation effect. User representation data is considered for a plurality of users, even a large number of users, which are often related to the individual user and not to the time. For different time series, the intercept term of the model in the individual solid effect model changes with the individual, and the coefficients of the explanatory variables changeNo change has occurred. Thus, individual fixed effect models are selected to determine the effect term
. The error term for the current point in time may be randomly generated. And determining the fixed effect value and the error term to determine the variable composition of the panel data model, wherein the current dependent variable is used as an explained variable, and the historical dependent variable and the current independent variable are used as explained variables.
The number of users involved in building the panel data model is often huge, and here, taking user a, user B and user C as examples, the fixed effect values corresponding to the user portrait data of user a can be respectively determined
Fixed effect value corresponding to user portrait data of user B
And fixed effect values corresponding to user portrait data of user C
. Then respectively generating error terms indicating the current time points corresponding to the users A
Error term corresponding to user B and indicating current time point
An error item corresponding to the error item of the current time point corresponding to the user C and indicating the current time point
. Further based on the current independent variable data, current dependent variable data, historical dependent variable data and
、
constructing a panel data model; user B-based current independent variable data, current dependent variable data, historical dependent variable data and
、
constructing a panel data model; user C based current independent variable data, current dependent variable data, historical dependent variable data and
、
a panel data model is constructed. Accordingly, a panel data model relating to a plurality of users, even a large number of users, can be regarded as one panel data model group.
In step S104, determining an influence degree value of the historical dependent variable data on the current dependent variable data by using the panel data model.
In the embodiment of the present specification, although there is an endogenous problem in the panel data model due to the lag of the interpreted variables (such as the historical dependent variables), a generalized moment estimation method may be adopted to determine the values of the estimated parameters (such as γ and β).
In an exemplary embodiment, as shown in fig. 3, the determining the degree of influence of the historical dependent variable data on the current dependent variable data by using the panel data model includes the following steps.
In step S301, first order difference processing in the time dimension is performed on the panel data model.
In step S302, a tool variable having a preset degree of correlation with the history dependent variable data is determined based on the first order difference processing result.
In step S303, regression processing is performed on the panel data model by using the tool variable, so as to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
And performing first-order difference processing on the panel data model in a time dimension, namely subtracting the variable at the corresponding previous time point from the variable at the next time point. E.g. by subtracting the variable at the corresponding recent historical point in time from the variable at the current point in time, i.e.
：
Wherein, t-1 can be regarded as the latest historical time point from the current time point t, t-2 is the next latest historical time point, and t-3, t-4, t-5.
Reflects the dependent variable of the user i at the time point t-2,
reflects the argument of user i at point in time t-1,
at time t-1 for user i is an error term. Equation 3 also shows the first order difference processing result.
The panel data model relating to a plurality of users, even a large number of users, can be regarded as a panel data model set, and then performing a difference operation on all variable data can obtain an equation set, wherein the equation set comprises a difference result item corresponding to each user:
and
. After the first order difference processing is carried out on the original model, the effect items which can cause the endogenous problem can be eliminated, however, the effect items can be eliminated
And error term
It is the case that it is a related,
it is an endogenous variable that causes endogenous problems. To solve the endogenous problem, tool variables having a preset degree of correlation with the history dependent variable data may be determined based on the first order difference processing result. The tool variable needs to be highly correlated with the endogenous variable, but with the error term
The correlation is low or even irrelevant. The tool variable may be
、
......
And the like. In practical applications, a tool variable matrix map as shown in fig. 6 may be generated. And performing regression processing on the panel data model by means of the tool variables to further obtain the influence degree value gamma of the historical dependent variable data on the current dependent variable data and the influence degree value beta of the current independent variable data on the current dependent variable data. The tool variables that are used are highly correlated with the lagged interpreted variables (e.g., historical dependent variables) after differentiation, and with the error terms after differentiation
The method is irrelevant, can be used for eliminating the endogenous problem related to the determination of the estimated parameters by the dynamic model, and further can improve the factorAccuracy of fruit analysis.
Two cases of regression processing of the panel data model using tool variables will be described below:
1) when the number of the tool variables is larger than the preset number, constructing a moment condition corresponding to the first-order difference processing result by using the tool variables based on a generalized moment estimation method; the preset number is determined by the pre-estimated parameters corresponding to the panel data model; determining a degree of influence value of the historical dependent variable data on the current dependent variable data based on the moment condition.
It was mentioned above that a panel data model involving a plurality of even a large number of users can be regarded as one panel data model set, and then performing a differential operation on all variable data can result in one equation set. When the regression processing is performed on the panel data model by means of the tool variables, the tool variables can be substituted into the equation set to obtain corresponding equations. In general, the number of unknowns to be solved in the equation (such as the estimated parameters γ, β) needs to be equal to the number of equations, and when the number of tool variables is too large, a situation occurs in which the number of unknowns to be solved in the equation is smaller than the number of equations, resulting in over-recognition. Therefore, when the number of the tool variables is too large or the tool variable matrix is too large (see fig. 6), a moment condition corresponding to the first-order difference processing result is constructed by using the tool variables based on a Generalized moment estimation (GMM) method, and then the degree of influence γ of the historical dependent variable data on the current dependent variable data and the degree of influence β of the current independent variable data on the current dependent variable data are determined based on the moment condition. The number of the moment conditions is matched with the number of the estimated parameters. The generalized moment estimation method can utilize more tool variables to carry out parameter estimation as much as possible under the condition of over-identification, meanwhile, the generalized moment estimation method is strong in adaptability, and suitable moment estimation can be flexibly determined to improve the effectiveness of parameter estimation.
2) And when the number of the tool variables is less than or equal to the preset number, performing least square regression on the first-order difference processing result by using the tool variables to obtain the degree of influence of the historical dependent variable data on the current dependent variable data.
Compared with the case that the number of the tool variables is too large or the tool variable matrix is too large, when the number of the tool variables is less than or equal to the preset number, the tool variables or the tool variable matrix can be used for performing least square regression on the first-order difference processing result to obtain the influence degree value gamma of the historical dependent variable data on the current dependent variable data and the influence degree value beta of the current independent variable data on the current dependent variable data. The Least Squares method used may be a Two-Stage Least Squares method (2SLS or TSLS), or an Ordinary Least Squares method (OLS). This allows for efficiency and accuracy in parameter estimation with appropriate tool variables.
In an exemplary embodiment, as shown in fig. 4, the performing a regression process on the panel data model by using the tool variable to obtain an influence degree value of the historical dependent variable data on the current dependent variable data includes the following steps.
In step S401, a preset function is acquired.
In step S402, the first-order difference processing result is processed by using the preset function and the tool variable, so as to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
The preset function may be a function provided by the GMM estimation model: and obtaining the function, and then processing the first-order difference processing result by using the function and the tool variable to obtain an influence degree value gamma of the historical dependent variable data on the current dependent variable data and an influence degree value beta of the current independent variable data on the current dependent variable data. The process of processing the first-order difference processing result by using the function and the tool variable may refer to the above description of the generalized moment estimation method and the least square method, and will not be described herein again. The function can realize the number and the preset number of the judgment tool variables and the application logic of parameter solving by adopting a generalized moment estimation method or a least square method. In practical application, the use setting of the GMM estimation model often requires that the input data is not less than 3 time points and the number of users tends to be infinite user data. The first-order difference processing result may be input to the GMM estimation model, and the equation set corresponding to the first-order difference processing result includes independent variable data, dependent variable data, effect terms, error terms, variables of the time dimension, and variables of the user dimension. The values of the estimated parameters, the estimation standard errors of the values, the overall remarkable evaluation of the related panel data model and the like can be output through the GMM estimation model. The preset function participates in parameter estimation, so that timeliness of parameter estimation can be improved, and the obtained result can be used as service guide information in time to guide optimization of the current internet product or development of a new internet product.
The service data processing method provided in the above embodiment can improve the accuracy of analyzing the analysis object, thereby improving the accuracy of the provided service guide information. The information of the user behavior data on the time dimension is considered, the time dimension information is not ignored when the analysis object is analyzed, and the influence of the independent variable with self-correlation on the analysis accuracy in a short time is avoided. The introduction of the historical dependent variable data and the application of the panel data model can correct the problem that the variable is omitted in the causal analysis of the scheme of the related technology, and can avoid the problem of estimation parameter error caused by neglecting the influence of the historical dependent variable on the current dependent variable.
FIG. 5 is a flowchart illustrating a method of building a business data processing system, as shown in FIG. 5, in accordance with an exemplary embodiment, which includes the following steps.
In step S501, a preset base frame is acquired.
In step S502, a first service code is acquired; the first service code indicates to acquire user portrait data and user behavior data of a target service, and determines current independent variable data and current dependent variable data indicating a current time point and historical dependent variable data indicating a historical time point from the user behavior data for an analysis object of the target service.
In step S503, a second service code is acquired; wherein the second business code indicates that a panel data model is constructed based on the user portrait data, the current independent variable data, the current dependent variable data, and the historical dependent variable data, and an influence degree value of the historical dependent variable data on the current dependent variable data is determined using the panel data model.
In step S504, the preset basic frame, the first service code, and the second service code are fused to construct a service data processing system.
The pre-set base framework may be a base development framework indicating a Python (a computer programming language) platform. Here, the execution logic of the first service code and the second service code may refer to the related contents of the foregoing steps S101-S104, and will not be described in detail. The business data processing system constructed by fusing the preset basic framework, the first business code and the second business code can determine the degree of influence of historical dependent variable data on the current dependent variable data and the degree of influence of the current independent variable data on the current dependent variable data.
The business data processing system can be a cause and effect analysis package based on a Python platform, and can be functionally aligned with PROC PANEL instructions (instruction PANEL data model program) in standard SAS software (a statistical analysis software). By using the causal analysis package, the solving speed of the model under a large amount of data, even mass data, can be improved, the accuracy of analyzing an analysis object can be improved, and the accuracy of the provided service guide information can be improved. Because the information of the user behavior data on the time dimension is considered, the time dimension information is not ignored when the analysis object is analyzed, and the influence of the independent variable having self-correlation on the analysis accuracy in a short time is avoided. The introduction of the historical dependent variable data and the application of the panel data model can correct the problem that the variable is omitted in the causal analysis of the scheme of the related technology, and can avoid the problem of estimation parameter error caused by neglecting the influence of the historical dependent variable on the current dependent variable.
The method for constructing the service data processing system provided in the above embodiment divides the service code into the first service code for acquiring the user data and the second service code for constructing and applying the panel data model, and then fuses the preset basic framework and the related service codes to construct the service data processing system, so that the development and maintenance efficiency of developers can be greatly improved. The constructed service data processing system can improve the analysis efficiency of large data volume and even mass user data.
Fig. 8 is a block diagram illustrating a business data processing apparatus 800 according to an example embodiment. Referring to fig. 8, the apparatus includes a data acquisition unit 801, a variable data determination unit 802, a model construction unit 803, and a degree value determination unit 804.
The data acquisition unit 801 is configured to perform acquisition of user portrait data and user behavior data of a target service;
the variable data determination unit 802 is configured to perform an analysis object for the target service, determine current independent variable data and current dependent variable data indicating a current time point, and historical dependent variable data indicating a historical time point from the user behavior data;
the model building unit 803 is configured to perform building a panel data model based on the user portrait data, the current independent variable data, the current dependent variable data and the historical dependent variable data;
the degree value determination unit 804 is configured to perform determining an influence degree value of the historical dependent variable data on the current dependent variable data using the panel data model.
In an exemplary embodiment, the model building unit includes:
a fixed effect value determination unit configured to perform determining a fixed effect value to which the user portrait data corresponds;
an error term determination unit configured to perform determining an error term indicating the current time point;
a model building subunit configured to perform building the panel data model based on the fixed effect value, the error term, the current independent variable data, the current dependent variable data, and the historical dependent variable data.
In an exemplary embodiment, the degree value determining unit includes:
a difference processing unit configured to perform first-order difference processing of a time dimension on the panel data model;
a tool variable determination unit configured to perform determination of a tool variable having a preset degree of correlation with the history dependent variable data based on a first order difference processing result;
and the regression unit is configured to perform regression processing on the panel data model by using the tool variable to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
In an exemplary embodiment, the regression unit includes:
a moment condition construction unit configured to perform construction of a moment condition corresponding to the first-order difference processing result by using the tool variables based on a generalized moment estimation device when the number of the tool variables is greater than a preset number; the preset number is determined by the pre-estimated parameters corresponding to the panel data model;
a first degree value determining subunit configured to perform determining a degree of influence value of the historical dependent variable data on the current dependent variable data based on the moment condition.
In an exemplary embodiment, the regression unit further includes:
and the second degree value determining subunit is configured to perform least square regression on the first-order difference processing result by using the tool variables when the number of the tool variables is less than or equal to a preset number, so as to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
In an exemplary embodiment, the regression unit includes:
a function acquisition unit configured to perform acquisition of a preset function;
and the third degree value determining subunit is configured to execute processing of the first-order difference processing result by using the preset function and the tool variable to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
FIG. 9 is a block diagram illustrating a construction apparatus 900 of a business data processing system in accordance with an exemplary embodiment. Referring to fig. 9, the apparatus includes a framework acquisition unit 901, a first service code acquisition unit 902, a second service code acquisition unit 903, and a fusion unit 904.
The frame acquiring unit 901 is configured to perform acquiring a preset base frame;
the first service code acquiring unit 902 is configured to perform acquiring a first service code; the first service code indicates to acquire user portrait data and user behavior data of a target service, and determines current independent variable data and current dependent variable data indicating a current time point and historical dependent variable data indicating a historical time point from the user behavior data aiming at an analysis object of the target service;
the second service code obtaining unit 903 is configured to perform obtaining a second service code; wherein the second business code indicates that the panel data model is to be built based on the user representation data, the current independent variable data, the current dependent variable data, and the historical dependent variable data;
the fusion unit 904 is configured to perform fusion of the preset basic framework, the first service code and the second service code to construct a service data processing system for determining an influence degree value of the historical dependent variable data on the current dependent variable data.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
In an exemplary embodiment, there is also provided an electronic device, comprising a processor; a memory for storing processor-executable instructions; when the processor is configured to execute the instructions stored in the memory, the steps of any one of the service data processing methods or the construction method of the service data processing system in the foregoing embodiments are implemented.
The electronic device may be a terminal, a server, or a similar computing device, taking the electronic device as a server as an example, fig. 10 is a block diagram of an electronic device for implementing a business data Processing method or a construction method of a business data Processing system according to an exemplary embodiment, where the electronic device 1000 may generate a relatively large difference due to different configurations or performances, and may include one or more Central Processing Units (CPUs) 1010 (the processor 1010 may include but is not limited to a presentation device such as a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 1030 for storing data, and one or more storage media 1020 (e.g., one or more mass storage devices) for storing an application 1023 or data 1022. Memory 1030 and storage media 1020 may be, among other things, transient or persistent storage. The program stored in the storage medium 1020 may include one or more modules, each of which may include a sequence of instructions operating on an electronic device. Still further, the central processor 1010 may be configured to communicate with the storage medium 1020 to execute a series of instruction operations in the storage medium 1020 on the electronic device 1000. The electronic device 1000 may also include one or more power supplies 1060, one or more wired or wireless network interfaces 1050, one or more input-output interfaces 1040, and/or one or more operating systems 1021, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, and so forth.
Input-output interface 1040 may be used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the electronic device 1000. In one example, i/o Interface 1040 includes a Network adapter (NIC) that may be coupled to other Network devices via a base station to communicate with the internet. In an exemplary embodiment, the input/output interface 100 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
It will be understood by those skilled in the art that the structure shown in fig. 10 is merely an illustration and is not intended to limit the structure of the electronic device. For example, the electronic device 1000 may also include more or fewer components than shown in FIG. 10, or have a different configuration than shown in FIG. 10.
In an exemplary embodiment, a computer-readable storage medium including instructions, such as a memory including instructions, which are executable by the processor 1010 of the electronic device 1000 to perform the business data processing method or the construction method of the business data processing system is also provided. Alternatively, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, a computer program product is also provided, the computer program product comprising computer instructions, the computer program/instructions being stored in a computer readable storage medium. The processor of the electronic device reads the computer program/instruction from the computer-readable storage medium, and executes the computer program/instruction, so that the electronic device executes the business data processing method or the business data processing system construction method provided in any of the above embodiments.
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 instructions of a computer program, which 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).
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (16)
1. A method for processing service data, the method comprising:
acquiring user portrait data and user behavior data of a target service;
determining current independent variable data and current dependent variable data indicating a current time point and historical dependent variable data indicating a historical time point from the user behavior data aiming at the analysis object of the target service;
constructing a panel data model based on the user representation data, the current independent variable data, the current dependent variable data, and the historical dependent variable data;
and determining the influence degree value of the historical dependent variable data on the current dependent variable data by using the panel data model.
2. The method of claim 1, wherein constructing a panel data model based on the user representation data, the current independent variable data, the current dependent variable data, and the historical dependent variable data comprises:
determining a fixed effect value corresponding to the user representation data;
determining an error term indicative of the current point in time;
constructing the panel data model based on the fixed effect value, the error term, the current independent variable data, the current dependent variable data, and the historical dependent variable data.
3. The method according to any one of claims 1 or 2, wherein the determining the degree of influence value of the historical dependent variable data on the current dependent variable data by using the panel data model comprises:
performing first-order difference processing on the panel data model in a time dimension;
determining tool variables with preset correlation degrees with the historical dependent variable data based on a first-order difference processing result;
and performing regression processing on the panel data model by using the tool variables to obtain the degree of influence of the historical dependent variable data on the current dependent variable data.
4. The method of claim 3, wherein the performing regression processing on the panel data model using the tool variables to obtain the degree of influence value of the historical dependent variable data on the current dependent variable data comprises:
when the number of the tool variables is larger than the preset number, constructing a moment condition corresponding to the first-order difference processing result by using the tool variables based on a generalized moment estimation method; the preset number is determined by the pre-estimated parameters corresponding to the panel data model;
determining a degree of influence value of the historical dependent variable data on the current dependent variable data based on the moment condition.
5. The method of claim 4, wherein the performing a regression process on the panel data model using the tool variables to obtain a degree of influence of the historical dependent variable data on the current dependent variable data further comprises:
and when the number of the tool variables is less than or equal to the preset number, performing least square regression on the first-order difference processing result by using the tool variables to obtain the degree of influence of the historical dependent variable data on the current dependent variable data.
6. The method of claim 3, wherein the performing regression processing on the panel data model using the tool variables to obtain the degree of influence value of the historical dependent variable data on the current dependent variable data comprises:
acquiring a preset function;
and processing the first-order difference processing result by using the preset function and the tool variable to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
7. A method for constructing a business data processing system, the method comprising:
acquiring a preset basic frame;
acquiring a first service code; the first service code indicates to acquire user portrait data and user behavior data of a target service, and determines current independent variable data and current dependent variable data indicating a current time point and historical dependent variable data indicating a historical time point from the user behavior data aiming at an analysis object of the target service;
acquiring a second service code; wherein the second business code indicates to construct a panel data model based on the user representation data, the current independent variable data, the current dependent variable data, and the historical dependent variable data, and to determine a degree of influence value of the historical dependent variable data on the current dependent variable data using the panel data model;
and fusing the preset basic framework, the first service code and the second service code to construct a service data processing system.
8. A service data processing apparatus, characterized in that the apparatus comprises:
a data acquisition unit configured to perform acquisition of user portrait data and user behavior data of a target service;
a variable data determination unit configured to execute an analysis object for the target service, determine current independent variable data and current dependent variable data indicating a current time point, and historical dependent variable data indicating a historical time point from the user behavior data;
a model construction unit configured to perform construction of a panel data model based on the user portrait data, the current independent variable data, the current dependent variable data, and the historical dependent variable data;
a degree value determination unit configured to perform determining an influence degree value of the historical dependent variable data on the current dependent variable data using the panel data model.
9. The apparatus of claim 8, wherein the model building unit comprises:
a fixed effect value determination unit configured to perform determining a fixed effect value to which the user portrait data corresponds;
an error term determination unit configured to perform determining an error term indicating the current time point;
a model building subunit configured to perform building the panel data model based on the fixed effect value, the error term, the current independent variable data, the current dependent variable data, and the historical dependent variable data.
10. The apparatus according to any one of claims 8 or 9, wherein the degree value determination unit includes:
a difference processing unit configured to perform first-order difference processing of a time dimension on the panel data model;
a tool variable determination unit configured to perform determination of a tool variable having a preset degree of correlation with the history dependent variable data based on a first order difference processing result;
and the regression unit is configured to perform regression processing on the panel data model by using the tool variable to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
11. The apparatus of claim 10, wherein the regression unit comprises:
a moment condition construction unit configured to perform construction of a moment condition corresponding to the first-order difference processing result by using the tool variables based on a generalized moment estimation device when the number of the tool variables is greater than a preset number; the preset number is determined by the pre-estimated parameters corresponding to the panel data model;
a first degree value determining subunit configured to perform determining a degree of influence value of the historical dependent variable data on the current dependent variable data based on the moment condition.
12. The apparatus of claim 11, wherein the regression unit further comprises:
and the second degree value determining subunit is configured to perform least square regression on the first-order difference processing result by using the tool variables when the number of the tool variables is less than or equal to a preset number, so as to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
13. The apparatus of claim 10, wherein the regression unit comprises:
a function acquisition unit configured to perform acquisition of a preset function;
and the third degree value determining subunit is configured to execute processing of the first-order difference processing result by using the preset function and the tool variable to obtain an influence degree value of the historical dependent variable data on the current dependent variable data.
14. An apparatus for building a business data processing system, the apparatus comprising:
a frame acquisition unit configured to perform acquisition of a preset base frame;
a first service code acquisition unit configured to perform acquisition of a first service code; the first service code indicates to acquire user portrait data and user behavior data of a target service, and determines current independent variable data and current dependent variable data indicating a current time point and historical dependent variable data indicating a historical time point from the user behavior data aiming at an analysis object of the target service;
a second service code acquiring unit configured to perform acquisition of a second service code; wherein the second business code indicates to construct a panel data model based on the user representation data, the current independent variable data, the current dependent variable data, and the historical dependent variable data, and to determine a degree of influence value of the historical dependent variable data on the current dependent variable data using the panel data model;
and the fusion unit is configured to perform fusion of the preset basic framework, the first service code and the second service code to construct a service data processing system.
15. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the business data processing method of any one of claims 1 to 6 or the construction method of the business data processing system of claim 7.
16. A non-transitory computer-readable storage medium, instructions in which, when executed by a processor of an electronic device, enable the electronic device to perform the business data processing method of any one of claims 1 to 6 or the construction method of the business data processing system of claim 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110759304.6A CN113256353B (en) | 2021-07-05 | 2021-07-05 | Business data processing method and construction method of business data processing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110759304.6A CN113256353B (en) | 2021-07-05 | 2021-07-05 | Business data processing method and construction method of business data processing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113256353A true CN113256353A (en) | 2021-08-13 |
| CN113256353B CN113256353B (en) | 2022-04-22 |
Family
ID=77190740
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110759304.6A Active CN113256353B (en) | 2021-07-05 | 2021-07-05 | Business data processing method and construction method of business data processing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113256353B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114168565A (en) * | 2021-12-10 | 2022-03-11 | 北京宇信科技集团股份有限公司 | Backtracking test method, device and system of business rule model and decision engine |
| CN114186096A (en) * | 2021-12-10 | 2022-03-15 | 北京达佳互联信息技术有限公司 | Information processing method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10719578B1 (en) * | 2014-10-27 | 2020-07-21 | University Of South Florida | Local lagged adapted generalized method of moments dynamic process |
| CN112380273A (en) * | 2020-11-11 | 2021-02-19 | 北京达佳互联信息技术有限公司 | Data estimation method and device |
-
2021
- 2021-07-05 CN CN202110759304.6A patent/CN113256353B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10719578B1 (en) * | 2014-10-27 | 2020-07-21 | University Of South Florida | Local lagged adapted generalized method of moments dynamic process |
| CN112380273A (en) * | 2020-11-11 | 2021-02-19 | 北京达佳互联信息技术有限公司 | Data estimation method and device |
Non-Patent Citations (4)
| Title |
|---|
| MZDG: "《关于内生性和工具变量》", 《经管之家-HTTPS://BBS.PINGGU.ORG/THREAD-4673021-1-1.HTML?TDSOURCETAG=S_PCQQ_AIOMSG》 * |
| 周海涛: "《政府R&D资助与企业技术创新 基于决策 行为 绩效视角》", 31 December 2021 * |
| 百度用户: "《广义矩估计》", 《百度文库-HTTPS://WENKU.BAIDU.COM/VIEW/C0FDCA33EEFDC8D376EE32DB.HTML?REC_FLAG=DEFAULT&FR=RECOMMEND_RELATIVERECOMMEND-60306,60273,60321,40251,60308,40308,40307-VIEWREC_PCVIEW_REC-B22358EBB8F67C1CFAD6B8CE》 * |
| 陈丰龙等: "《高铁发展与城乡居民收入差距:来自中国城市的证据》", 《经济评论》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114168565A (en) * | 2021-12-10 | 2022-03-11 | 北京宇信科技集团股份有限公司 | Backtracking test method, device and system of business rule model and decision engine |
| CN114186096A (en) * | 2021-12-10 | 2022-03-15 | 北京达佳互联信息技术有限公司 | Information processing method and device |
| CN114168565B (en) * | 2021-12-10 | 2022-07-08 | 北京宇信科技集团股份有限公司 | Backtracking test method, device and system of business rule model and decision engine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113256353B (en) | 2022-04-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11122333B2 (en) | User feature generation method and apparatus, device, and computer-readable storage medium | |
| US20210326729A1 (en) | Recommendation Model Training Method and Related Apparatus | |
| CN113256353B (en) | Business data processing method and construction method of business data processing system | |
| WO2019114423A1 (en) | Method and apparatus for merging model prediction values, and device | |
| CN110688598B (en) | Service parameter acquisition method and device, computer equipment and storage medium | |
| CN114461871B (en) | Recommendation model training method, object recommendation device and storage medium | |
| CN111522724B (en) | Method and device for determining abnormal account number, server and storage medium | |
| CN107623862A (en) | multimedia information push control method, device and server | |
| CN113919923B (en) | Live broadcast recommendation model training method, live broadcast recommendation method and related equipment | |
| CN114595016B (en) | Comment information display method, comment information generation method, comment information display device, comment information generation device and electronic equipment | |
| CN113918738A (en) | Multimedia resource recommendation method and device, electronic equipment and storage medium | |
| CN113343024A (en) | Object recommendation method and device, electronic equipment and storage medium | |
| CN106817296B (en) | Information recommendation test method and device and electronic equipment | |
| CN113139082A (en) | Multimedia content processing method, apparatus, device and medium | |
| CN111026912B (en) | IPTV-based collaborative recommendation method, device, computer equipment and storage medium | |
| CN114491093B (en) | Multimedia resource recommendation and object representation network generation method and device | |
| CN110634031A (en) | Method, device, equipment and medium for tracking and analyzing published content | |
| JP2019526129A (en) | Apparatus and method for digital media measurement including a user panel | |
| CN112291625B (en) | Information quality processing method, information quality processing device, electronic equipment and storage medium | |
| CN115186173A (en) | Multimedia resource pushing and intelligent agent network generating method and device | |
| CN114510627A (en) | Object pushing method and device, electronic equipment and storage medium | |
| JP2011227720A (en) | Recommendation system, recommendation method and recommendation program | |
| CN112565904A (en) | Video clip pushing method, device, server and storage medium | |
| CN114048392B (en) | Multimedia resource pushing method and device, electronic equipment and storage medium | |
| US20240054527A1 (en) | Ad Frequency Management in Disjoint Identity Space |
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 |