CN113129080A - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN113129080A CN113129080A CN202110524322.6A CN202110524322A CN113129080A CN 113129080 A CN113129080 A CN 113129080A CN 202110524322 A CN202110524322 A CN 202110524322A CN 113129080 A CN113129080 A CN 113129080A
- Authority
- CN
- China
- Prior art keywords
- user
- target user
- determining
- probability
- information
- 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.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title abstract description 9
- 238000006243 chemical reaction Methods 0.000 claims abstract description 76
- 238000000034 method Methods 0.000 claims abstract description 45
- 238000004590 computer program Methods 0.000 claims description 12
- 230000004044 response Effects 0.000 claims description 8
- 230000007704 transition Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 5
- 239000000047 product Substances 0.000 description 30
- 230000008569 process Effects 0.000 description 15
- 230000009466 transformation Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 3
- 102100035932 Cocaine- and amphetamine-regulated transcript protein Human genes 0.000 description 2
- 101000715592 Homo sapiens Cocaine- and amphetamine-regulated transcript protein Proteins 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000006227 byproduct Substances 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000004936 stimulating effect Effects 0.000 description 1
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- General Engineering & Computer Science (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a data processing method and device. After the characteristic information of the target user is obtained, the forwarding probability of the target user is determined based on the forwarding probability prediction model according to the characteristic information of the target user, the conversion probability of the target user is determined based on the conversion probability prediction model, the coordinate information of the target user is determined according to the forwarding probability and the conversion probability, the level information of the target user is determined according to the coordinate information, the incentive information sent to the target user is determined according to the level information, the incentive information can be sent in a targeted mode through the method, and the effect generated after the incentive information is sent is improved.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a data processing method and apparatus.
Background
The forwarding probability and the conversion probability of the user are important factors influencing the product popularization.
In the prior art, the forwarding probability is usually improved by sending incentive information to users, but in the prior art, only the incentive information is sent indiscriminately, and the effect generated after the incentive information is sent is very poor.
Disclosure of Invention
In view of this, embodiments of the present invention provide a data processing method and apparatus, which can purposefully send incentive information to improve the effect after sending the incentive information.
In a first aspect, an embodiment of the present invention provides a data processing method, where the method includes:
acquiring characteristic information of a target user;
determining the forwarding probability of the target user based on a forwarding probability prediction model according to the characteristic information of the target user, and determining the conversion probability of the target user based on a conversion probability prediction model;
determining coordinate information of the target user according to the forwarding probability and the conversion probability;
determining the level information of the target user according to the coordinate information;
determining incentive information sent to the target user according to the level information;
the forwarding probability is used for representing the probability that the target user performs forwarding operation after receiving the incentive information, and the conversion probability is used for representing the probability that the target user brings a new user after performing the forwarding operation.
Further, the determining the coordinate information of the target user according to the forwarding probability and the conversion probability includes:
determining the abscissa of the coordinate information according to the forwarding probability of the target user;
and determining the ordinate of the coordinate information according to the conversion probability of the target user.
Further, the determining the abscissa of the coordinate information according to the forwarding probability of the target user includes:
taking the difference between the forwarding probability of the target user and the forwarding probability threshold value as the abscissa of the coordinate information;
the determining the ordinate of the coordinate information according to the conversion probability of the target user includes:
and taking the difference between the conversion probability of the target user and the conversion probability threshold value as the ordinate of the coordinate information.
Further, the determining the level information of the target user according to the coordinate information includes:
determining the level of the target user as a second level in response to the abscissa of the coordinate information being positive and the ordinate of the coordinate information being positive;
determining the level of the target user as a first level in response to the abscissa of the coordinate information being negative and the ordinate of the coordinate information being positive;
determining the level of the target user as a fourth level in response to the abscissa of the coordinate information being negative and the ordinate of the coordinate information being negative; and
and determining the level of the target user as a third level in response to the abscissa of the coordinate information being positive and the ordinate of the coordinate information being negative.
Further, the forwarding probability prediction model is obtained by training as follows:
determining a first user set, wherein the first user set comprises at least one user receiving overdriving information within a preset time period;
determining a first training sample set according to the first user set;
and training the forwarding probability prediction model according to the first training sample set.
Further, the determining a first set of training samples from the first set of users comprises:
determining users which have undergone forwarding operation after receiving the incentive information in the first user set as first positive sample users;
determining users which do not perform forwarding operation after receiving the incentive information in the first user set as first negative sample users;
user characteristics of the first positive sample user and the first negative sample user before receiving incentive information are obtained to determine the first training sample set.
Further, the conversion probability prediction model is obtained by training as follows:
determining a first positive sample user set, wherein the first positive sample user set comprises at least one first positive sample user;
determining a second training sample set according to the first positive sample user set;
and training the conversion probability prediction model according to the second training sample set.
Further, the determining a second set of training samples from the first set of positive sample users comprises:
determining a first positive sample user bringing a new user after forwarding operation in the first positive sample user set as a second positive sample user;
determining a first positive sample user which does not bring a new user after forwarding operation in the first positive sample user set as a second negative sample user;
user characteristics of the second positive sample user and the second negative sample user before receiving incentive information are obtained to determine a second training sample set.
In a second aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, the memory being configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to the first aspect.
In a third aspect, an embodiment of the present invention provides a computer-readable storage medium for storing computer program instructions, which when executed by a processor implement the method according to the first aspect.
After the method of the embodiment of the invention obtains the characteristic information of the target user, the forwarding probability of the target user is determined based on the forwarding probability prediction model according to the characteristic information of the target user, the conversion probability of the target user is determined based on the conversion probability prediction model, the coordinate information of the target user is determined according to the forwarding probability and the conversion probability, the level information of the target user is determined according to the coordinate information, the incentive information sent to the target user is determined according to the level information, and the incentive information can be sent in a targeted manner through the method, so that the effect generated after the incentive information is sent is improved.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent from the following description of the embodiments of the present invention with reference to the accompanying drawings, in which:
FIG. 1 is a flow chart of a data processing method according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart illustrating a process of determining coordinate information of a target user according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a process of determining target user level information according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a coordinate system according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart of a method for training a forward probability prediction model according to an embodiment of the present invention;
FIG. 6 is a schematic flow chart of training a transition probability prediction model according to an embodiment of the present invention;
fig. 7 is a schematic diagram of an electronic device of an embodiment of the invention.
Detailed Description
The present invention will be described below based on examples, but the present invention is not limited to only these examples. In the following detailed description of the present invention, certain specific details are set forth. It will be apparent to one skilled in the art that the present invention may be practiced without these specific details. Well-known methods, procedures, components and circuits have not been described in detail so as not to obscure the present invention.
Further, those of ordinary skill in the art will appreciate that the drawings provided herein are for illustrative purposes and are not necessarily drawn to scale.
Unless the context clearly requires otherwise, throughout the description, the words "comprise", "comprising", and the like are to be construed in an inclusive sense as opposed to an exclusive or exhaustive sense; that is, what is meant is "including, but not limited to".
In the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified.
In the embodiments of the present invention, the obtained user information is performed on the premise that the user allows the user to protect the privacy right of the user, and the user information is only applied to the method in the embodiments of the present invention.
In the process of popularizing a product, users are often required to be motivated to forward corresponding product popularization information to attract more new users.
In the prior art, in order to improve the promotion efficiency, incentive information is usually sent to users, and the incentive information includes rewards given to the users and text contents for motivating the users to perform forwarding operation so as to prompt the users to forward corresponding product promotion information.
Fig. 1 is a flowchart of a data processing method according to an embodiment of the present invention. As shown in fig. 1, the data processing method of the present embodiment includes the following steps.
S11: and acquiring the characteristic information of the target user.
Wherein the characteristic information comprises the age of the target user, the historical forwarding times and the type of the purchased product.
Optionally, the feature information may be set according to actual needs, for example: the characteristic information may also include the number of times the target user purchased the product, the time of purchasing the product, the account registration time, the average forwarding frequency, etc., and it should be understood that the characteristic information may also be combined in any manner, such as acquiring only the age of the user, the time of purchasing the product, and the account registration time.
S12: and determining the forwarding probability of the target user based on a forwarding probability prediction model according to the characteristic information of the target user, and determining the conversion probability of the target user based on a conversion probability prediction model.
The forwarding probability prediction model and the conversion probability prediction model are pre-trained two-classification models, the forwarding probability is used for representing the probability of forwarding the product information after the target user receives the incentive information, and the conversion probability is used for representing the probability of bringing a new user after the target user forwards the product information.
Specifically, the feature information of the target user is respectively input into a pre-trained forwarding probability prediction model and a pre-trained conversion probability prediction model, and the forwarding probability and the conversion probability of the target user are predicted through the prediction models.
Optionally, the forwarding probability prediction model and the conversion probability prediction model may both adopt an Xgboost model, and the forwarding probability and the conversion probability of the target user may be predicted based on the Xgboost model.
Specifically, the Xgboost model is composed of a plurality of CART (Classification and regression on Trees), each CART corresponds to different feature information, and a value corresponding to a leaf node of the CA RT is an actual score.
In this embodiment, after receiving a training sample, the Xgboost model may find out user features that affect the forwarding probability and the transformation probability from the training sample, then establish corresponding CART according to the found user features, and respectively assign corresponding scores to leaf nodes of each CART, and may obtain a forwarding probability prediction model and a transformation probability prediction model through training. The trained forwarding probability prediction model and the trained conversion probability prediction model can be classified and scores are accumulated through the CARTs in the models according to input user characteristics, and finally the scores obtained by the CARTs are added to obtain the forwarding probability and the conversion probability.
Optionally, fig. 5 is a schematic flowchart of a process of training a forwarding probability prediction model according to an embodiment of the present invention, and the process shown in fig. 5 may be used to train the forwarding probability prediction model, which specifically includes the following steps.
S21: a first set of users is determined.
The first user set comprises at least one user receiving the overdriving information within a preset time period.
Specifically, at least one user who receives overdriving information within a preset time is determined as a first user set, wherein the number of the users in the first user set can be set according to actual needs, the overdriving information includes rewards given to the users, such as shopping coupons, and text content for stimulating the users to forward promotion information of products purchased by the users, the promotion information may be recommendation information for recommending the products after the users use the products, and the promotion information may also include purchase links of the recommended products.
For example: and the users A and B receive the incentive information sent by the product customer service within half a year, and then the users A and B are determined as the users in the first user set.
Alternatively, the users in the first set of users may be users who received and read the incentive information within a preset time, and users who received the incentive information but did not read the incentive information may not be determined to be within the first set of users.
For example: and users C and D both receive the incentive information sent by the product customer service within half a year, wherein the user C reads the incentive information after receiving the incentive information, the user D cannot read the incentive information for some reasons, and only the user C receiving and reading the incentive information is determined as the user in the first user set.
S22: and determining a first training sample set according to the first user set.
Alternatively, the first set of training samples may be determined by the following steps.
S221: and determining the user which is subjected to forwarding operation after receiving the incentive information in the first user set as a first positive sample user.
For example: after receiving incentive information sent by product customer service, a user A in the first user set forwards promotion information of a product purchased by the user A to a social platform or shares the promotion information with friends of the user A through the social platform, and then the user A is determined as a first positive sample user.
S222: and determining users which do not perform forwarding operation after receiving the incentive information in the first user set as first negative sample users.
For example: after receiving the incentive information sent by the product customer service, the user B in the first user set does not forward or share the promotion information, and then the user B is determined as a first negative sample user.
S223: user characteristics of the first positive sample user and the first negative sample user before receiving incentive information are obtained to determine the first training sample set.
Specifically, after the users in the first user set are determined as the first positive sample user and the first negative sample user one by one, user characteristics of the first positive sample user and the first negative sample user before receiving the incentive information are obtained to determine the first training sample set.
Wherein the user characteristics include at least an age of the user, a historical number of forwards, and a category of the product purchased.
Optionally, the user characteristic may also be set as any characteristic that may affect the user forwarding probability, such as: the number of times a product was purchased, the time a product was purchased, the average frequency of forwarding, the last forwarding time, etc.
S23: and training the forwarding probability prediction model according to the first training sample set.
Specifically, after a first training sample set is obtained, the first training sample set is input into an Xgboost model, the Xgboost model is trained based on the first training sample set, user features which may affect the forwarding probability in the first training sample set are found, a plurality of cards are established according to the found user features, and corresponding scores are given to different leaf nodes of each card. The trained Xgboost model can be used as a forwarding probability prediction model for predicting the forwarding probability of the target user.
Optionally, fig. 6 is a schematic flowchart of a process of training a transformation probability prediction model according to an embodiment of the present invention, and the process of training the transformation probability prediction model according to fig. 6 specifically includes the following steps.
S31: a first set of positive sample users is determined.
The first positive sample user set includes at least one first positive sample user, where the first positive sample user is a first positive sample user in the process shown in fig. 5, and specifically is a user that has performed forwarding operation after receiving the incentive information within a preset time.
Optionally, the number of first positive sample users in the first positive sample user set may be set according to actual needs, for example, all the first positive sample users may be determined as the first positive sample user set, or a part of the first positive sample users may be determined as the first positive sample user set.
S32: and determining a second training sample set according to the first positive sample user set.
Alternatively, the second set of training samples may be determined by the following steps.
S321: and determining a first positive sample user bringing a new user after forwarding operation in the first positive sample user set as a second positive sample user.
S322: and determining a first positive sample user which does not bring a new user after forwarding operation in the first positive sample user set as a second negative sample user.
For example: the users A and E are both first positive sample users, the user A brings new users after forwarding the promotion information of the products purchased by the user A to the social platform, at the moment, the user A is determined to be a second positive sample user, the user E fails to bring new users after forwarding the product information, and the user E is determined to be a second negative sample user.
S323: user characteristics of the second positive sample user and the second negative sample user before receiving incentive information are obtained to determine a second training sample set.
The user characteristics acquired in S323 are different from the user characteristics acquired in S223 in that the user characteristics acquired in S323 are characteristics that may affect the user conversion probability.
Alternatively, the user characteristics acquired in S323 and the user characteristics acquired in S223 may partially overlap, or may be set separately.
For example, the user characteristics acquired in S323 may include the age of the user, the kind of purchased product, the number of historical conversions, the average frequency of conversions, the account registration time, the last conversion time, and the like. Wherein the user' S age and the kind of the purchased product overlap with the user characteristics acquired at S223, and the number of historical conversions, the average frequency of conversions, the account registration time, and the last conversion time are individually set at S323.
S33: and training the conversion probability prediction model according to the second training sample set.
Specifically, after a second training sample set is obtained, the second training sample set is input into an Xgboost model, the Xgboost model is trained based on the second training sample set, user features that may affect the transformation probability in the second training sample set are found, a plurality of cards are established according to the found user features, and corresponding scores are given to different leaf nodes of each card. The trained Xgboost model can be used as a conversion probability prediction model for predicting the conversion probability of the target user.
S13: and determining the coordinate information of the target user according to the forwarding probability and the conversion probability.
Optionally, fig. 2 is a schematic flowchart of a process of determining coordinate information of a target user according to an embodiment of the present invention, and the process may be implemented by determining the coordinate information of the target user according to the process shown in fig. 2, which specifically includes the following steps.
S131: and determining the abscissa of the coordinate information according to the forwarding probability of the target user.
Specifically, the difference between the forwarding probability of the target user and the forwarding probability threshold is taken as the abscissa of the coordinate information. Wherein, the forwarding probability threshold can be set according to actual needs.
S132: and determining the ordinate of the coordinate information according to the conversion probability of the target user.
Specifically, the difference between the conversion probability of the target user and the conversion probability threshold is taken as the ordinate of the coordinate information. Wherein, the conversion probability threshold value can be set according to actual needs.
For example: after the feature information of the target user 1 is respectively input into the forwarding probability prediction model and the transformation probability prediction model, the forwarding probability and the transformation probability of the target user 1 are respectively 90% and 80%, and the set forwarding probability threshold and the set transformation probability threshold are respectively 80% and 70%, at this time, (10, 10) can be used as the coordinate information of the target user 1.
Another example is: after the feature information of the target user 2 is respectively input into the forwarding probability prediction model and the transformation probability prediction model, the forwarding probability and the transformation probability of the target user 2 are respectively 70% and 60%, and the set forwarding probability threshold and the transformation probability threshold are respectively 80% and 70%, at this time, the (-10 ) can be used as the coordinate information of the target user 2.
S14: and determining the level information of the target user according to the coordinate information.
Optionally, fig. 3 is a schematic flowchart of a process of determining target user level information according to an embodiment of the present invention, where the process may be used to determine the target user level information according to the process shown in fig. 3, and the process specifically includes the following steps.
S141: and judging whether the abscissa in the coordinate information is positive, if so, executing S142, and otherwise, executing S145.
Alternatively, if the abscissa in the coordinate information is 0, S142 is also performed.
S142: and judging whether the ordinate in the coordinate information is positive, if so, executing S143, otherwise, executing S144.
Alternatively, if the ordinate in the coordinate information is 0, S143 is also performed.
S143: determining the level of the target user as a second level.
Specifically, if the abscissa and the ordinate of the coordinate information of the target user are both positive, the forwarding probability representing the target user is greater than or equal to the forwarding probability threshold, and the conversion probability is greater than or equal to the conversion probability threshold, that is, after the incentive information is sent to the target user, the target user has a high probability of forwarding the promotion information of the purchased product, and meanwhile, the target user has a high possibility of bringing a new user after forwarding the promotion information, wherein the larger the abscissa value in the coordinate information is, the higher the probability representing the target user for forwarding is, the larger the ordinate value is, and the higher the probability representing the target user for bringing a new user after forwarding the promotion information is.
S144: determining the level of the target user as a third level.
Specifically, if the abscissa of the coordinate information of the target user is positive and the ordinate is negative, the forwarding probability representing the target user is greater than or equal to the forwarding probability threshold, and the conversion probability is smaller than the conversion probability threshold, that is, after the incentive information is sent to the target user, the target user has a high probability of forwarding the promotion information of the purchased product, but the target user has only a small possibility of bringing new users after forwarding the promotion information, wherein the larger the abscissa value in the coordinate information is, the higher the probability representing the target user for forwarding is, the smaller the ordinate value is, and the lower the probability representing the target user for bringing new users after forwarding the promotion information is.
S145: and judging whether the ordinate in the coordinate information is positive, if so, executing S146, otherwise, executing S147.
Alternatively, if the ordinate in the coordinate information is 0, S146 is also performed.
S146: determining the level of the target user as a first level.
Specifically, if the abscissa of the coordinate information of the target user is negative and the ordinate is positive, the forwarding probability representing the target user is smaller than the forwarding probability threshold, and the conversion probability is greater than or equal to the conversion probability threshold, that is, after the incentive information is sent to the target user, the target user has only a small possibility of forwarding the promotion information of the purchased product, but the target user has a high probability of bringing a new user after forwarding the promotion information, wherein the smaller the abscissa value in the coordinate information is, the lower the probability representing the target user for forwarding is, the larger the ordinate value is, and the higher the probability representing the target user for bringing a new user after forwarding the promotion information is.
S147: determining the level of the target user as a fourth level.
Specifically, if the abscissa and the ordinate of the coordinate information of the target user are negative, the forwarding probability representing the target user is smaller than the forwarding probability threshold, and the conversion probability is smaller than the conversion probability threshold, that is, after the incentive information is sent to the target user, the target user has only a small possibility of forwarding promotion information of a product purchased by the target user, and meanwhile, the target user has only a small possibility of bringing a new user after forwarding the promotion information, wherein the smaller the abscissa value in the coordinate information is, the lower the probability representing the target user for forwarding is, the smaller the ordinate value is, and the lower the probability representing the target user for bringing a new user after forwarding the promotion information is.
In an optional implementation manner, the level information of the target user may also be determined based on four quadrant regions of the coordinate system according to the forwarding probability threshold, the conversion probability threshold, and the forwarding probability and the conversion probability of the target user. Specifically, the level information of the target user may be determined by the following steps.
S41: and establishing a coordinate system according to the forwarding probability threshold and the conversion probability threshold.
Specifically, fig. 4 is a schematic diagram of a coordinate system according to an embodiment of the present invention, and as shown in fig. 4, the coordinate system is composed of an abscissa axis, an ordinate axis, and a center point O.
The abscissa axis is a forwarding probability, the ordinate axis is a conversion probability, the abscissa of the central point O is a forwarding probability threshold, the ordinate is a conversion probability threshold, and specific values of the forwarding probability threshold and the conversion probability threshold can be set according to actual needs.
For example: when the forwarding probability threshold is set to 80% and the transformation probability threshold is set to 80%, the coordinate information of the center point O of the coordinate system is (80, 80).
S42: and converting the target user into a corresponding coordinate point in the coordinate system according to the forwarding probability and the conversion probability of the target user.
Specifically, the forwarding probability may be used as an abscissa, and the conversion probability may be used as an ordinate, so as to convert the target user into a coordinate point in a coordinate system.
For example: if the forwarding probability of the target user 1 is 90% and the conversion probability is 88%, the coordinate point corresponding to the target user 1 in the coordinate system is (90, 88), the forwarding probability of the target user 2 is 86%, and the conversion probability is 76%, the coordinate point corresponding to the target user 2 in the coordinate system is (86, 76), the forwarding probability of the target user 3 is 76%, and the conversion probability is 84%, the coordinate point corresponding to the target user 3 in the coordinate system is (76, 84), the forwarding probability of the target user 4 is 70%, and the conversion probability is 74%, and the coordinate point corresponding to the target user 4 in the coordinate system is (70, 74).
S43: and determining the level information of the target user based on four quadrant areas of the coordinate system according to the corresponding coordinate point of the target user in the coordinate system.
Specifically, as shown in fig. 4, the level of the target user 1 in the first quadrant area is determined as the second level, the level of the target user 2 in the fourth quadrant area is determined as the third level, the level of the target user 3 in the second quadrant area is determined as the first level, and the level of the target user 4 in the third quadrant area is determined as the fourth level.
Alternatively, the level information of the user on the boundary line of the first quadrant region and the second quadrant region is determined as a second level, the level information of the user on the boundary line of the first quadrant region and the fourth quadrant region is determined as a second level, the level information of the user on the boundary line of the second quadrant region and the third quadrant region is determined as a first level, and the level information of the user on the boundary line of the third quadrant region and the fourth quadrant region is determined as a third level.
Compared with the method shown in fig. 3, through steps S41-S43, when the levels of a large number of target users are processed, the coordinate information of the target users does not need to be calculated one by one, and then the judgment is performed according to the abscissa and the ordinate in the target information, but the target users are converted into corresponding coordinate points in a coordinate system by establishing the coordinate system, and then the target users in different quadrant areas are obtained, so that the level information of the target users can be determined, and the memory usage of the system is reduced.
S15: and determining incentive information sent to the target user according to the level information.
The users at the first level forward the promotion information with a low probability, but the users at the second level forward the promotion information with a high probability to bring new users, the users at the third level forward the promotion information with a low probability to bring new users, and the users at the fourth level forward the promotion information with a high probability to bring new users with a low probability to bring new users.
Specifically, the incentive information to be transmitted is determined according to the level information of the target user.
For example: if the level of the target user 3 is the first level, incentive information may be sent to the target user 3 to incentive the user to perform forwarding operation, if the level of the target user 1 is the second level, the incentive information may not be sent to the target user 1, and the current situation is maintained, if the levels of the target users 2 and 4 are the third level and the fourth level, respectively, the incentive information may be sent to the target users 2 or 4, and corresponding preferential denominations may be given at the same time, for example, when a new user purchases a product through a purchase link in promotion information sent by the target users 2 or 4, the new user may enjoy a certain discount, so as to increase the probability that the third level and fourth level users bring the new user.
After the method of the embodiment of the invention obtains the characteristic information of the target user, the forwarding probability of the target user is determined based on the forwarding probability prediction model according to the characteristic information of the target user, the conversion probability of the target user is determined based on the conversion probability prediction model, the coordinate information of the target user is determined according to the forwarding probability and the conversion probability, the level information of the target user is determined according to the coordinate information, the incentive information sent to the target user is determined according to the level information, and the incentive information can be sent in a targeted manner through the method, so that the effect generated after the incentive information is sent is improved.
Fig. 7 is a schematic diagram of an electronic device of an embodiment of the invention. As shown in fig. 7, the electronic device is a general-purpose data processing apparatus comprising a general-purpose computer hardware structure including at least a processor 51 and a memory 52. The processor 51 and the memory 52 are connected by a bus 53. The memory 52 is adapted to store instructions or programs executable by the processor 51. The processor 51 may be a stand-alone microprocessor or a collection of one or more microprocessors. Thus, the processor 51 implements the processing of data and the control of other devices by executing instructions stored by the memory 52 to perform the method flows of embodiments of the present invention as described above. The bus 53 connects the above components together, and also connects the above components to a display controller 54 and a display device and an input/output (I/O) device 55. Input/output (I/O) devices 55 may be a mouse, keyboard, modem, network interface, touch input device, motion sensing input device, printer, and other devices known in the art. Typically, the input/output device 55 is connected to the system through an input/output (I/O) controller 56.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, apparatus (device) or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may employ a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations of methods, apparatus (devices) and computer program products according to embodiments of the application. It will be understood that each flow in the flow diagrams can be implemented by computer program instructions.
These computer program instructions may be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows.
These computer program instructions may also be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows.
Another embodiment of the invention is directed to a non-transitory storage medium storing a computer-readable program for causing a computer to perform some or all of the above-described method embodiments.
That is, as can be understood by those skilled in the art, all or part of the steps in the method for implementing the embodiments described above may be accomplished by specifying the relevant hardware through a program, where the program is stored in a storage medium and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of data processing, the method comprising:
acquiring characteristic information of a target user;
determining the forwarding probability of the target user based on a forwarding probability prediction model according to the characteristic information of the target user, and determining the conversion probability of the target user based on a conversion probability prediction model;
determining coordinate information of the target user according to the forwarding probability and the conversion probability;
determining the level information of the target user according to the coordinate information;
determining incentive information sent to the target user according to the level information;
the forwarding probability is used for representing the probability that the target user performs forwarding operation after receiving the incentive information, and the conversion probability is used for representing the probability that the target user brings a new user after performing the forwarding operation.
2. The method of claim 1, wherein the determining the coordinate information of the target user according to the forwarding probability and the conversion probability comprises:
determining the abscissa of the coordinate information according to the forwarding probability of the target user;
and determining the ordinate of the coordinate information according to the conversion probability of the target user.
3. The method of claim 2, wherein the determining the abscissa of the coordinate information according to the forwarding probability of the target user comprises:
taking the difference between the forwarding probability of the target user and the forwarding probability threshold value as the abscissa of the coordinate information;
the determining the ordinate of the coordinate information according to the conversion probability of the target user includes:
and taking the difference between the conversion probability of the target user and the conversion probability threshold value as the ordinate of the coordinate information.
4. The method of claim 3, wherein determining the level information of the target user according to the coordinate information comprises:
determining the level of the target user as a second level in response to the abscissa of the coordinate information being positive and the ordinate of the coordinate information being positive;
determining the level of the target user as a first level in response to the abscissa of the coordinate information being negative and the ordinate of the coordinate information being positive;
determining the level of the target user as a fourth level in response to the abscissa of the coordinate information being negative and the ordinate of the coordinate information being negative; and
and determining the level of the target user as a third level in response to the abscissa of the coordinate information being positive and the ordinate of the coordinate information being negative.
5. The method of claim 1, wherein the forward probability prediction model is obtained by training:
determining a first user set, wherein the first user set comprises at least one user receiving overdriving information within a preset time period;
determining a first training sample set according to the first user set;
and training the forwarding probability prediction model according to the first training sample set.
6. The method of claim 5, wherein determining a first set of training samples from the first set of users comprises:
determining users which have undergone forwarding operation after receiving the incentive information in the first user set as first positive sample users;
determining users which do not perform forwarding operation after receiving the incentive information in the first user set as first negative sample users;
user characteristics of the first positive sample user and the first negative sample user before receiving incentive information are obtained to determine the first training sample set.
7. The method of claim 6, wherein the transition probability prediction model is obtained by training as follows:
determining a first positive sample user set, wherein the first positive sample user set comprises at least one first positive sample user;
determining a second training sample set according to the first positive sample user set;
and training the conversion probability prediction model according to the second training sample set.
8. The method of claim 7, wherein determining a second set of training samples from the first set of positive sample users comprises:
determining a first positive sample user bringing a new user after forwarding operation in the first positive sample user set as a second positive sample user;
determining a first positive sample user which does not bring a new user after forwarding operation in the first positive sample user set as a second negative sample user;
user characteristics of the second positive sample user and the second negative sample user before receiving incentive information are obtained to determine a second training sample set.
9. An electronic device comprising a memory and a processor, wherein the memory is configured to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method of any of claims 1-8.
10. A computer readable storage medium storing computer program instructions, which when executed by a processor implement the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110524322.6A CN113129080A (en) | 2021-05-13 | 2021-05-13 | Data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110524322.6A CN113129080A (en) | 2021-05-13 | 2021-05-13 | Data processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113129080A true CN113129080A (en) | 2021-07-16 |
Family
ID=76781984
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110524322.6A Pending CN113129080A (en) | 2021-05-13 | 2021-05-13 | Data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113129080A (en) |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130124272A1 (en) * | 2011-11-11 | 2013-05-16 | Rovio Entertainment Ltd. | Method and server system for enhanced management of event-based user rewards |
| CN106022508A (en) * | 2016-05-06 | 2016-10-12 | 陈丛威 | Method and apparatus for predicting user friend invitation behaviors of online financing platform |
| US20170185908A1 (en) * | 2014-09-18 | 2017-06-29 | Huawei Technologies Co.,Ltd. | Method and device for predicting information propagation in social network |
| CN107093084A (en) * | 2016-08-01 | 2017-08-25 | 北京小度信息科技有限公司 | Potential user predicts method for transformation and device |
| CN107369052A (en) * | 2017-08-29 | 2017-11-21 | 北京小度信息科技有限公司 | User's registration behavior prediction method, apparatus and electronic equipment |
| CN107679920A (en) * | 2017-10-20 | 2018-02-09 | 北京奇艺世纪科技有限公司 | The put-on method and device of a kind of advertisement |
| CN108133390A (en) * | 2017-12-22 | 2018-06-08 | 北京三快在线科技有限公司 | For predicting the method and apparatus of user behavior and computing device |
| CN109460513A (en) * | 2018-10-31 | 2019-03-12 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating clicking rate prediction model |
| JP2019046173A (en) * | 2017-09-01 | 2019-03-22 | ヤフー株式会社 | Information analysis apparatus, information analysis method, and program |
| CN110490658A (en) * | 2019-08-21 | 2019-11-22 | 北京字节跳动网络技术有限公司 | User's motivational techniques, device, electronic equipment and the readable medium of application program |
| CN111275470A (en) * | 2018-12-04 | 2020-06-12 | 北京嘀嘀无限科技发展有限公司 | Service initiation probability prediction method and training method and device of model thereof |
| CN111724184A (en) * | 2019-03-20 | 2020-09-29 | 北京嘀嘀无限科技发展有限公司 | Transformation probability prediction method and device |
| CN111798273A (en) * | 2020-07-01 | 2020-10-20 | 中国建设银行股份有限公司 | Training method of purchase probability prediction model of product and purchase probability prediction method |
| CN112380449A (en) * | 2020-12-03 | 2021-02-19 | 腾讯科技（深圳）有限公司 | Information recommendation method, model training method and related device |
-
2021
- 2021-05-13 CN CN202110524322.6A patent/CN113129080A/en active Pending
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130124272A1 (en) * | 2011-11-11 | 2013-05-16 | Rovio Entertainment Ltd. | Method and server system for enhanced management of event-based user rewards |
| US20170185908A1 (en) * | 2014-09-18 | 2017-06-29 | Huawei Technologies Co.,Ltd. | Method and device for predicting information propagation in social network |
| CN106022508A (en) * | 2016-05-06 | 2016-10-12 | 陈丛威 | Method and apparatus for predicting user friend invitation behaviors of online financing platform |
| CN107093084A (en) * | 2016-08-01 | 2017-08-25 | 北京小度信息科技有限公司 | Potential user predicts method for transformation and device |
| CN107369052A (en) * | 2017-08-29 | 2017-11-21 | 北京小度信息科技有限公司 | User's registration behavior prediction method, apparatus and electronic equipment |
| JP2019046173A (en) * | 2017-09-01 | 2019-03-22 | ヤフー株式会社 | Information analysis apparatus, information analysis method, and program |
| CN107679920A (en) * | 2017-10-20 | 2018-02-09 | 北京奇艺世纪科技有限公司 | The put-on method and device of a kind of advertisement |
| CN108133390A (en) * | 2017-12-22 | 2018-06-08 | 北京三快在线科技有限公司 | For predicting the method and apparatus of user behavior and computing device |
| CN109460513A (en) * | 2018-10-31 | 2019-03-12 | 北京字节跳动网络技术有限公司 | Method and apparatus for generating clicking rate prediction model |
| CN111275470A (en) * | 2018-12-04 | 2020-06-12 | 北京嘀嘀无限科技发展有限公司 | Service initiation probability prediction method and training method and device of model thereof |
| CN111724184A (en) * | 2019-03-20 | 2020-09-29 | 北京嘀嘀无限科技发展有限公司 | Transformation probability prediction method and device |
| CN110490658A (en) * | 2019-08-21 | 2019-11-22 | 北京字节跳动网络技术有限公司 | User's motivational techniques, device, electronic equipment and the readable medium of application program |
| CN111798273A (en) * | 2020-07-01 | 2020-10-20 | 中国建设银行股份有限公司 | Training method of purchase probability prediction model of product and purchase probability prediction method |
| CN112380449A (en) * | 2020-12-03 | 2021-02-19 | 腾讯科技（深圳）有限公司 | Information recommendation method, model training method and related device |
Non-Patent Citations (2)
| Title |
|---|
| 犀利姐: "APP拉新进阶：5招激发老用户带来大量新用户", pages 1 - 5, Retrieved from the Internet <URL:https://zhuanlan.zhihu.com/p/23911294> * |
| 王向君: "撇开虚荣指标，如何策划一场成功的拉新活动？", pages 1 - 7, Retrieved from the Internet <URL:https://zhuanlan.zhihu.com/p/97655961> * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104967587B (en) | A kind of recognition methods of malice account and device | |
| CN107016587B (en) | Personalized page pushing method and device | |
| US20200098031A1 (en) | Product recommending apparatus and non-transitory computer readable medium | |
| CN108509458B (en) | Business object identification method and device | |
| CN108305181B (en) | Social influence determination method and device, information delivery method and device, equipment and storage medium | |
| CN110827086A (en) | Product marketing prediction method and device, computer equipment and readable storage medium | |
| CN104111938A (en) | Information recommendation method and device | |
| JP2019075094A (en) | Information processing device, information processing method, program, and marketing information processing device for calculating prediction data on use of application program by one user | |
| CN107203883B (en) | Risk control method and equipment | |
| CN112348549A (en) | Advertisement operation method, intelligent terminal and storage device | |
| CN110751493B (en) | Risk prevention and control method and device based on historical reservation orders | |
| CN110633919A (en) | Method and device for evaluating business entity | |
| CN111967970B (en) | Bank product recommendation method and device based on spark platform | |
| CN110992095B (en) | Consumer portrait generation method and device | |
| CN112330373A (en) | User behavior analysis method and device and computer readable storage medium | |
| CN111787042B (en) | Method and device for pushing information | |
| CN113129080A (en) | Data processing method and device | |
| CN111831630A (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
| CN107622408A (en) | Purchase the predictor method and estimating device of fare rope transaction conversion | |
| CN113191821A (en) | Data processing method and device | |
| CN108960904A (en) | Promotion method and system, equipment and storage medium | |
| CN115063178A (en) | Method and device for determining sensitivity degree of target group to service scene | |
| CN115167965A (en) | Transaction progress bar processing method and device | |
| CN110503467B (en) | Cross-platform consumer group acquisition method and device | |
| CN109191192B (en) | Data estimation method, apparatus and computer-readable storage medium |
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 |