CN111833141A - Information push processing method, device, equipment and storage medium - Google Patents
Information push processing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN111833141A CN111833141A CN202010480037.4A CN202010480037A CN111833141A CN 111833141 A CN111833141 A CN 111833141A CN 202010480037 A CN202010480037 A CN 202010480037A CN 111833141 A CN111833141 A CN 111833141A
- Authority
- CN
- China
- Prior art keywords
- user
- price
- item
- data
- data set
- 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.)
- Withdrawn
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
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
- G06Q30/0203—Market surveys; Market polls
Abstract
The application provides an information push processing method, an information push processing device, information push processing equipment and a storage medium, wherein a characteristic data set of a user is obtained, the characteristic data set comprises at least one characteristic data, and the characteristic data comprises state characteristic data and behavior characteristic data; determining a price sensitivity of the user for at least one item price data from the feature data set; and pushing the item information according to the price sensitivity of the user aiming at least one item price data. The method and the device realize the pushing of the item information matched with the price sensitivity of the user, are favorable for improving the transaction rate of the item and ensuring the effectiveness of pushing the item information on the one hand, and are favorable for realizing the maximization of the user value and have obvious item resource allocation effect on the other hand.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to an information push processing method, an information push processing apparatus, an information push processing device, and a storage medium.
Background
With the rapid development of the internet technology, the influence and the penetration of the internet economy on the life of people are deeper and deeper, and the fine operation is a key factor for improving the competitiveness of the internet economy, wherein the accurate pushing of the article information to the user is important content of the fine operation.
In the related art, when the resource of the article is allocated, the article information is pushed to all potential users, and the users decide whether to purchase the article according to the requirements.
However, different users have different price sensitivities to the price of the article, and push undifferentiated article information to all users, so that on one hand, the effectiveness of pushing the article information cannot be effectively ensured, on the other hand, the maximization of the user value is not facilitated, and the article resource allocation effect is not good.
Disclosure of Invention
In order to solve the above problem, the present application provides an information push processing method, apparatus, device and storage medium.
In a first aspect, the present application provides an information push processing method, including:
acquiring a characteristic data set of a user, wherein the characteristic data set comprises at least one characteristic data, and the characteristic data comprises state characteristic data and behavior characteristic data;
determining a price sensitivity of the user for at least one item price data from the feature data set;
and pushing the item information according to the price sensitivity of the user aiming at least one item price data.
Further, the at least one item price data constitutes an item price data set, and the determining a price sensitivity of the user for the at least one item price data from the feature data set comprises:
determining transaction probability data corresponding to each item price data according to the characteristic data set of the user by using an evaluation model obtained by pre-training to obtain a transaction probability data set of the user;
determining a price sensitivity of the user for at least one item price data from the item price dataset and the user's transaction probability dataset.
Further, said determining a price sensitivity of said user for at least one item price data from said item price dataset and said user's transaction probability dataset comprises:
determining an association of the item price dataset and the user's transaction probability dataset;
and determining the price sensitivity of the user aiming at least one item price data according to the incidence relation.
Further, the determining the association relationship between the item price dataset and the user's transaction probability dataset comprises:
fitting to generate a correlation curve according to the item price data set and the transaction probability data set of the user;
the determining the price sensitivity of the user for at least one item price data according to the incidence relation comprises:
and determining the slope of the association curve corresponding to each item price data to obtain the price sensitivity of the user for at least one item price data.
Further, the determining the association relationship between the item price dataset and the user's transaction probability dataset comprises:
fitting to generate a correlation curve according to the item price data set and the transaction probability data set of the user;
the determining the price sensitivity of the user for at least one item price data according to the incidence relation comprises:
determining a normalized slope of the correlation curve, the normalized slope constituting a price sensitivity of the user for at least one item price data.
Further, the evaluation model is obtained by training through the following method:
establishing a model of feature data about a user, wherein the behavior feature data in the feature data comprises historical transaction data and historical travel data;
acquiring a characteristic data set of a user as a training sample, wherein the characteristic data set comprises at least one characteristic data;
and carrying out model training according to the training samples to obtain the evaluation model.
Further, the pushing of item information according to the price sensitivity of the user for at least one item price data includes:
when resource allocation of an item with a certain item price is carried out, determining a user with the price sensitivity exceeding a preset threshold value as a target user according to the price sensitivity of the user for the item price;
and pushing the item information to the target user.
Further, the pushing of item information according to the price sensitivity of the user for at least one item price data includes:
determining a user profile characteristic according to the price sensitivity of the user to at least one item price data, wherein the user profile characteristic comprises an average transaction probability and a user maximum value;
and pushing the item information according to the user image characteristics and the price sensitivity of the user aiming at least one item price data.
In a second aspect, the present application provides an information push processing apparatus, including:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a feature data set of a user, the feature data set comprises at least one feature data, and the feature data comprises state feature data and behavior feature data;
a first processing unit for determining a price sensitivity of a user for at least one item price data from the feature data set;
and the second processing unit is used for pushing the item information according to the price sensitivity of the user aiming at the price data of at least one item.
Further, the at least one item price data constitutes an item price data set, the first processing unit comprising:
the first processing subunit is used for determining transaction probability data corresponding to each item price data according to the characteristic data set of the user by using an evaluation model obtained through pre-training to obtain a transaction probability data set of the user;
a second processing subunit for determining a price sensitivity of the user for at least one item price data set from the item price data set and the user's transaction probability data set.
Further, the second processing subunit includes:
a first processing module for determining an association of the item price dataset and the user's transaction probability dataset;
and the second processing module is used for determining the price sensitivity of the user aiming at the price data of at least one item according to the incidence relation.
Further, the first processing module includes:
the first processing submodule is used for fitting and generating a correlation curve according to the item price data set and the transaction probability data set of the user;
the second processing module comprises:
and the second processing submodule is used for determining the slope of the association curve corresponding to each item price data to obtain the price sensitivity of the user for at least one item price data.
Further, the first processing module includes:
the third processing submodule is used for fitting and generating a correlation curve according to the item price data set and the transaction probability data set of the user;
the second processing module comprises:
a fourth processing submodule for determining a normalized slope of the association curve, the normalized slope constituting a price sensitivity of the user for at least one item price data.
Further, the evaluation model is obtained by training through the following method:
establishing a model of feature data about a user, wherein the behavior feature data in the feature data comprises historical transaction data and historical travel data;
acquiring a characteristic data set of a user as a training sample, wherein the characteristic data set comprises at least one characteristic data;
and carrying out model training according to the training samples to obtain the evaluation model.
Further, the second processing unit includes:
the third processing subunit is configured to, when resource allocation is performed on an item with a certain item price, determine, according to a price sensitivity of the user to the item price, that the user whose price sensitivity exceeds a preset threshold is a target user;
and the fourth processing subunit is used for pushing the article information to the target user.
Further, the second processing unit includes:
a fifth processing subunit, configured to determine a user profile feature according to a price sensitivity of the user for at least one item price data, wherein the user profile feature includes an average transaction probability and a user maximum value;
and the sixth processing subunit is used for pushing the item information according to the user portrait characteristics and the price sensitivity of the user aiming at least one item price data.
In a third aspect, the present application provides an information push processing apparatus, including: a processor, a memory, and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any of the first aspect.
In a fourth aspect, the present application provides a computer readable storage medium having stored thereon a computer program for execution by a processor to perform the method of any of the first aspects.
The application provides an information push processing method, an information push processing device, information push processing equipment and a storage medium, wherein a characteristic data set of a user is obtained, the characteristic data set comprises at least one characteristic data, and the characteristic data comprises state characteristic data and behavior characteristic data; determining a price sensitivity of the user for at least one item price data from the feature data set; and pushing the item information according to the price sensitivity of the user aiming at least one item price data. According to the characteristic data set of the user, the price sensitivity of the user for at least one item price data is determined, and the item information is pushed according to the price sensitivity of the user for at least one item price data, so that different item information pushing strategies are formulated for different users, and the item information matched with the price sensitivity is pushed for different users.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and together with the description, serve to explain the principles of the application.
Fig. 1 is a schematic flowchart of an information push processing method according to an embodiment of the present application;
fig. 2 is a schematic flowchart of another information push processing method according to an embodiment of the present application;
FIG. 2a is a graph of correlation between purchase rate and monthly card price of six users according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an information push processing apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of another information push processing apparatus according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an information push processing device according to an embodiment of the present application.
With the above figures, there are shown specific embodiments of the present application, which will be described in more detail below. These drawings and written description are not intended to limit the scope of the inventive concepts in any manner, but rather to illustrate the inventive concepts to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The application has the specific application scenarios that: with the rapid development of the internet technology, the influence and penetration of the internet economy on the life of people are deeper and deeper, and the fine operation is a key factor for improving the competitiveness of the internet economy, wherein the accurate pushing of the article information to the user group is important content of the fine operation. For example, coupon marketing is an effective transaction stimulation method, and in the coupon marketing process, how to accurately push coupon information to a user is achieved, so that subsidy cost is effectively controlled, and the user is stimulated to improve the transaction rate; for another example, the package card is an intelligent marketing means in the shared bicycle service, how to accurately push package card information to the user is realized, the package card purchase rate is effectively improved, the user stickiness degree is improved, the package card subsidy cost is controlled, and the user value maximization is realized.
In the related art, when the resource of the article is allocated, the article information is pushed to all potential users, and the users decide whether to purchase the article according to the requirements. However, different users have different price sensitivities to the price of the article, and push undifferentiated article information to all users, so that on one hand, the effectiveness of pushing the article information cannot be effectively ensured, on the other hand, the maximization of the user value is not facilitated, and the article resource allocation effect is not good.
The application provides an information push processing method, an information push processing device, information push processing equipment and a storage medium, and aims to solve the technical problems in the prior art.
Fig. 1 is a schematic flow diagram of an information push processing method according to an embodiment of the present application, and as shown in fig. 1, the method includes:
In this embodiment, specifically, the execution main body of this embodiment is a terminal device, a server arranged on the terminal device, a controller, or other devices or devices that can execute this embodiment, and this embodiment is described by taking the execution main body as the server arranged on the terminal device as an example.
The method is mainly used for pushing the item information in the internet economy, and aims to push the item information matched with the user price sensitivity for different users so as to improve the item transaction rate of the users, ensure the effectiveness of pushing the item information and simultaneously realize the maximization of the user value, for example, push different coupon information or package card information to different users. The resources in this embodiment include preferential resources, such as a secondary card, a week card, a month card, a year card, a coupon, discount strength, and the like in a virtual article. The month card in the shared bicycle service will be described as an example in this embodiment.
The characteristic data includes state characteristic data and behavior characteristic data. The state feature data refers to a type of data used for characterizing the attribute features of the user, such as the gender, age, residential address, work address, distance between the residential address and the work address, the registration state of the user in the server, and the like. The behavior characteristic data refers to a type of data for representing the use condition of the resource by the user, such as the riding times, riding amount, last riding time, whether the monthly card is purchased, purchasing amount of the monthly card and the like of the user in the shared bicycle service.
The method for obtaining the characteristic data of the user may be conventional in the art, and for example, a crawler technology may be used to crawl a user log and registration information of the user in the server, and then the behavior characteristic data of the user is determined according to the user log, and the state characteristic data of the user is determined according to the registration information.
In this embodiment, specifically, there may be a plurality of item price data, for example, for a month card in the shared bicycle service, different prices may be set for the month card according to different preferential strengths, and for example, the price of the month card may be set to 8 yuan, 10 yuan, 12 yuan, 14 yuan, 16 yuan, 18 yuan, or the like. The price sensitivity of the user to the item price data is characterized in that after the item price data is changed, the change situation of the user to the corresponding item purchase rate is represented, for example, for a monthly card in a shared bicycle business, the price sensitivity of the user to the monthly card price data refers to the absolute value of the reduction (or increase) of the monthly card purchase rate of the user after the monthly card price increases (or decreases) each unit quantity.
The characteristic data set comprises state characteristic data and behavior characteristic data, so that the price sensitivity of the user determined according to the characteristic data set can reflect the influence of the attribute characteristics of the user and the historical behavior characteristics of the user on the resource use condition on the purchase rate of the goods.
The method for determining the price sensitivity of the user for at least one item price data according to the feature data set may be conventional in the art, for example, the XGboost algorithm may be used to calculate the item purchase rate of the user for each item price data according to the feature data set of the user, and then determine the price sensitivity of the user for each item price data according to the item purchase rate.
And 103, pushing the item information according to the price sensitivity of the user aiming at the price data of at least one item.
In this embodiment, specifically, according to the price sensitivity of the user for at least one item price data, resources are preferentially allocated to the user with high price sensitivity, that is, item information is preferentially pushed to the user with high price sensitivity. For the same item, the item transaction rate corresponding to the user with high price sensitivity is higher, the item information is preferentially pushed to the user with the price sensitivity higher than the preset threshold value, the transaction rate of the item is favorably improved, the effectiveness of pushing the item information is ensured, and the maximization of the user value is favorably realized.
In this embodiment, a feature data set of a user is obtained, where the feature data set includes at least one feature data, and the feature data includes state feature data and behavior feature data; determining a price sensitivity of the user for at least one item price data from the feature data set; and pushing the item information according to the price sensitivity of the user aiming at least one item price data. According to the characteristic data set of the user, the price sensitivity of the user for at least one item price data is determined, then the item information is pushed according to the price sensitivity of the user for at least one item price data, different item information pushing strategies are formulated for different users, and the item information matched with the price sensitivity is pushed for different users, so that the trading rate of the items is improved, the effectiveness of item information pushing is guaranteed, the maximization of the user value is facilitated, and the item resource distribution effect is obvious.
Fig. 2 is a schematic flowchart of another information push processing method according to an embodiment of the present application, and based on the embodiment shown in fig. 1, as shown in fig. 2,
The method and principle of step 201 are similar to or the same as those of step 101, see the related description of step 101, and this embodiment is not described herein again.
In this embodiment, the transaction probability data is used to represent the probability that the user purchases the corresponding item at a certain item price. For the monthly card in the shared bicycle service, the frequency period of the monthly card purchased by the user is longer, usually more than one month, so that the times of purchasing the monthly card by the user are generally less, and therefore, the purchase probability calculated by dividing the purchase times by the total browsing times in the related technology is not accurate enough; moreover, when the user purchases the monthly card for a plurality of times, the price of each transaction is generally the same, which is not beneficial to directly calculating the purchase probability of the user aiming at the price of each item. Therefore, in the present embodiment, the evaluation model obtained by training in advance is used to determine the transaction probability data corresponding to the price data of each item according to the feature data set of the user. The pre-trained evaluation model is used for representing the relevance between the characteristic data of the user and the transaction probability data corresponding to the price data of each article.
Optionally, the evaluation model for the user is obtained by training as follows: establishing a model of characteristic data of a user, wherein behavior characteristic data in the characteristic data comprise historical transaction data and historical trip data; acquiring a characteristic data set of a user as a training sample, wherein the characteristic data set comprises at least one characteristic data; and carrying out model training according to the training samples to obtain an evaluation model. The method and principle for establishing and training the related model by using the XGBoost algorithm are conventional in the field, for example, a first evaluation model may be established and trained according to the feature data set of the user and the price data of the first item, and the first evaluation model is used for evaluating the correlation between the feature data of the user and the transaction probability data corresponding to the price data of the first item; on the basis of the first evaluation model, a second evaluation model is established and trained according to the feature data set of the user and the price data of the second item, and the second evaluation model is used for evaluating the relevance between the feature data of the user and the transaction probability data corresponding to the price data of the second item; and repeating the training of a new evaluation model on the basis of the trained evaluation model until all the item price data are traversed to obtain the evaluation model for evaluating the relevance between the characteristic data of the user and the transaction probability data corresponding to all the item price data. And when determining the transaction probability data corresponding to each item price data according to the feature data set of the user by using the evaluation model obtained by training, determining the transaction probability data corresponding to each item price data respectively, and adding all the transaction probability data to obtain the transaction probability data of the user.
In the present embodiment, in particular, the at least one item price data constitutes an item price data set. The price data of the articles can be determined through experiments or research, and can also be determined manually according to market needs. For example, for the shared bicycle service, the initial price of the monthly card is 20 yuan, and after the initial price is discounted by 4-9, the price of the monthly card can be 8 yuan, 10 yuan, 12 yuan, 14 yuan, 16 yuan or 18 yuan.
Optionally, in this embodiment, determining a price sensitivity of the user for at least one item price data according to the item price data set and the transaction probability data set of the user includes: determining an association relationship between an item price dataset and a transaction probability dataset of a user; and determining the price sensitivity of the user aiming at the price data of at least one item according to the association relation.
As a preferable solution in this embodiment, determining the association relationship between the item price data set and the transaction probability data set of the user includes: and fitting to generate a correlation curve according to the item price data set and the transaction probability data set of the user. Determining a price sensitivity of the user for the price data of the at least one item according to the association relationship, comprising: and determining the slope of the association curve corresponding to each item price data to obtain the price sensitivity of the user aiming at least one item price data.
Specifically, the fitting generation of the association curve according to the item price data set and the transaction probability data set of the user comprises the following steps: and establishing a user transaction probability-item price association curve chart by taking the single item price data in the item price data set as an abscissa and the single user transaction probability data in the user transaction probability data set as an ordinate. Determining the slope of the association curve corresponding to each item price data, and obtaining the price sensitivity of the user for at least one item price data, wherein the method comprises the following steps: determining the corresponding point of each item price data on the association curve; determining the slope of a straight line between a point corresponding to the current item price data and a point corresponding to the next item price data, namely determining the slope of an association curve corresponding to the current item price data; and taking the inverse of the slope of the association curve corresponding to the current item price data as the price sensitivity of the user for the current item price data.
As another preferable solution in this embodiment, determining the association relationship between the item price data set and the transaction probability data set of the user includes: fitting to generate a correlation curve according to the item price data set and the transaction probability data set of the user; determining a price sensitivity of the user for the price data of the at least one item according to the association relationship, comprising: a normalized slope of the correlation curve is determined, the normalized slope constituting a price sensitivity of the user for the at least one item price data.
Specifically, the fitting generation of the association curve according to the item price data set and the transaction probability data set of the user comprises the following steps: and establishing a user transaction probability-item price association curve chart by taking the single item price data in the item price data set as an abscissa and the single user transaction probability data in the user transaction probability data set as an ordinate. Determining a normalized slope of the correlation curve, the normalized slope constituting a price sensitivity of the user for the at least one item price data, comprising: determining the corresponding points of each item price data on the association curve, and performing linear fitting on the points to obtain a normalized straight line of the association curve, wherein the slope of the normalized straight line is the normalized slope of the association curve; and taking the inverse of the normalized slope as the price sensitivity of the user for the price data of the at least one item.
For example, for a month card in the shared bicycle service, the item price data may be a month card price after discount offer, or may be a month card price after using a coupon, and the user transaction probability data may be a card purchase rate. Fig. 2a is a graph of correlation between purchase card rate and monthly card price of six users provided in this embodiment, and as shown in fig. 2a, a broken line in the graph is a user purchase card rate-monthly card price correlation curve, which is equivalent to the user transaction probability-item price correlation curve in this embodiment; the straight line in the graph is a normalized straight line of the user purchase card rate-monthly card price association curve, and is equivalent to a normalized straight line of the user transaction probability-item price association curve in the embodiment. As can be seen from fig. 2a, the higher the transaction probability of the user, the higher the price sensitivity of the user to the price data of at least one item.
And 204, pushing the item information according to the price sensitivity of the user aiming at the price data of at least one item.
Optionally, in this embodiment, pushing the item information according to the price sensitivity of the user for at least one item price data includes: when resource allocation of an item with a certain item price is carried out, determining a user with the price sensitivity exceeding a preset threshold value as a target user according to the price sensitivity of the user for the item price; and pushing the article information to the target user. The size of the preset threshold value can be set according to actual needs, when the price sensitivity of the user to the item price exceeds the preset threshold value, the price sensitivity of the user to the item price is higher, so that the transaction probability of the user is higher, the item information is pushed to the target user with higher transaction probability, and the purchase rate of the user to the item can be improved.
Optionally, in this embodiment, pushing the item information according to the price sensitivity of the user for at least one item price data includes: determining a user profile characteristic according to a price sensitivity of a user to at least one item price data, wherein the user profile characteristic comprises an average transaction probability and a user maximum value; and pushing the item information according to the user portrait characteristics and the price sensitivity of the user aiming at the price data of at least one item. The average transaction probability represents the demand intensity of the user on the corresponding article, and the higher the average transaction probability is, the higher the demand intensity of the user on the corresponding article is; according to the foregoing content of this embodiment, the user corresponds to each item price data with a corresponding transaction probability, a product of the item price data and the corresponding transaction probability is used as an expected price of the user for the corresponding item, a maximum value in the expected price is used as a user maximum value, and the larger the user maximum value is, the larger the contribution value of the user to the marketing income is. Therefore, the item information is pushed according to the user portrait characteristics and the price sensitivity of the user aiming at least one item price data, the resources are preferentially distributed to the users with high average transaction probability, high user maximum value and high price sensitivity, the resource utilization rate can be further improved, and the marketing income is favorably improved.
In this embodiment, a feature data set of a user is obtained, where the feature data set includes at least one feature data, and the feature data includes state feature data and behavior feature data; determining transaction probability data corresponding to price data of each item according to a characteristic data set of the user by using an evaluation model obtained by pre-training to obtain a transaction probability data set of the user; determining a price sensitivity of the user for the at least one item price data from the item price dataset and the transaction probability dataset of the user; and pushing the item information according to the price sensitivity of the user aiming at the price data of at least one item. The method comprises the steps of determining a transaction probability data set of a user aiming at least one item price data according to a feature data set of the user by utilizing an evaluation model obtained by pre-training, and determining the price sensitivity of the user according to the transaction probability data set and the item price data set of the user, so that the problem of inaccurate price sensitivity calculation caused by low transaction frequency of the user can be effectively solved, and the price sensitivity of the user can be evaluated according to a plurality of item price data, therefore, the price sensitivity of the user can be evaluated more accurately; meanwhile, in the embodiment, the item information matched with the price sensitivity of the user is pushed to the user according to the price sensitivity of the user, so that the problems that the user with high price sensitivity obtains too many preferential resources and the user with low price sensitivity cannot obtain enough preferential resources are solved, the effectiveness of pushing the item information is effectively improved, the utilization rate of the resources is effectively improved, the transaction rate of the user is effectively stimulated, and the maximization of the user value is facilitated.
Fig. 3 is a schematic structural diagram of a resource allocation apparatus according to an embodiment of the present application, and as shown in fig. 3, the apparatus includes:
the device comprises an acquisition unit 1, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a feature data set of a user, the feature data set comprises at least one feature data, and the feature data comprises state feature data and behavior feature data;
a first processing unit 2 for determining a price sensitivity of the user for at least one item price data from the feature data set;
and the second processing unit 3 is used for pushing the item information according to the price sensitivity of the user aiming at the price data of at least one item.
In this embodiment, a feature data set of a user is obtained, where the feature data set includes at least one feature data, and the feature data includes state feature data and behavior feature data; determining a price sensitivity of the user for at least one item price data from the feature data set; and pushing the item information according to the price sensitivity of the user aiming at least one item price data. According to the characteristic data set of the user, the price sensitivity of the user for at least one item price data is determined, then the item information is pushed according to the price sensitivity of the user for at least one item price data, different item information pushing strategies are formulated for different users, and the item information matched with the price sensitivity is pushed for different users, so that the trading rate of the items is improved, the effectiveness of item information pushing is guaranteed, the maximization of the user value is facilitated, and the item resource distribution effect is obvious.
Fig. 4 is a schematic structural diagram of another resource allocation apparatus according to an embodiment of the present application, and based on the embodiment shown in fig. 3, as shown in fig. 4,
at least one item price data constituting an item price data set, the first processing unit 2 comprising:
the first processing subunit 21 is configured to determine, according to the feature data set of the user, transaction probability data corresponding to price data of each item by using an evaluation model obtained through pre-training, so as to obtain a transaction probability data set of the user;
a second processing subunit 22 for determining a price sensitivity of the user for the at least one item price data based on the item price data set and the transaction probability data set of the user.
A second processing subunit 22 comprising:
a first processing module 221, configured to determine an association relationship between an item price data set and a transaction probability data set of a user;
and a second processing module 222, configured to determine, according to the association relationship, a price sensitivity of the user for the price data of the at least one item.
A first processing module 221, comprising:
the first processing sub-module 2211 is configured to generate a correlation curve by fitting according to the item price data set and the transaction probability data set of the user;
a second processing module 222, comprising:
the second processing sub-module 2221 is configured to determine a slope of the association curve corresponding to each item price data, so as to obtain a price sensitivity of the user for at least one item price data.
A first processing module 221, comprising:
the third processing sub-module 2212 is configured to generate a correlation curve by fitting according to the item price data set and the transaction probability data set of the user;
a second processing module 222, comprising:
a fourth processing sub-module 2222 for determining a normalized slope of the association curve, the normalized slope constituting a price sensitivity of the user for the at least one item price data.
The evaluation model for the user is obtained by training through the following method: establishing a model of characteristic data of a user, wherein behavior characteristic data in the characteristic data comprise historical transaction data and historical trip data; acquiring a characteristic data set of a user as a training sample, wherein the characteristic data set comprises at least one characteristic data; and carrying out model training according to the training samples to obtain an evaluation model.
A second processing unit 3 comprising:
a third processing subunit 31, configured to, when resource allocation is performed on an item with a certain item price, determine, according to a price sensitivity of a user for the item price, that the user whose price sensitivity exceeds a preset threshold is a target user;
and the fourth processing subunit 32 is configured to push the item information to the target user.
A second processing unit 3 comprising:
a fifth processing subunit 33, configured to determine a user profile feature according to a price sensitivity of the user for the at least one item price data, wherein the user profile feature comprises an average transaction probability and a user maximum value;
and a sixth processing subunit 34, configured to perform item information pushing according to the user portrait characteristics and the price sensitivity of the user for the at least one item price data.
In this embodiment, a feature data set of a user is obtained, where the feature data set includes at least one feature data, and the feature data includes state feature data and behavior feature data; determining transaction probability data corresponding to price data of each item according to a characteristic data set of the user by using an evaluation model obtained by pre-training to obtain a transaction probability data set of the user; determining a price sensitivity of the user for the at least one item price data from the item price dataset and the transaction probability dataset of the user; and pushing the item information according to the price sensitivity of the user aiming at the price data of at least one item. The method comprises the steps of determining a transaction probability data set of a user aiming at least one item price data according to a feature data set of the user by utilizing an evaluation model obtained by pre-training, and determining the price sensitivity of the user according to the transaction probability data set and the item price data set of the user, so that the problem of inaccurate price sensitivity calculation caused by low transaction frequency of the user can be effectively solved, and the price sensitivity of the user can be evaluated according to a plurality of item price data, therefore, the price sensitivity of the user can be evaluated more accurately; meanwhile, in the embodiment, the item information matched with the price sensitivity of the user is pushed to the user according to the price sensitivity of the user, so that the problems that the user with high price sensitivity obtains too many preferential resources and the user with low price sensitivity cannot obtain enough preferential resources are solved, the effectiveness of pushing the item information is effectively improved, the utilization rate of the resources is effectively improved, the transaction rate of the user is effectively stimulated, and the maximization of the user value is facilitated.
Fig. 5 is a schematic structural diagram of an information push processing device according to an embodiment of the present application, and as shown in fig. 5, an embodiment of the present application provides an information push processing device, which may be used to execute actions or steps of the information push processing device in the embodiments shown in fig. 1 to fig. 2, and specifically includes: a processor 501, a memory 502 and a communication interface 503.
A memory 502 for storing a computer program.
The processor 501 is configured to execute the computer program stored in the memory 502 to implement the actions of the information pushing processing device in the embodiments shown in fig. 1-2, which are not described again.
Optionally, the information push processing device may further include a bus 504. The processor 501, the memory 502 and the communication interface 503 may be connected to each other through a bus 504; the bus 504 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus 504 may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 5, but this is not intended to represent only one bus or type of bus.
In the embodiments of the present application, the above embodiments may be referred to and referred to by each other, and the same or similar steps and terms are not repeated.
Alternatively, part or all of the above modules may be implemented by being embedded in a chip of the information push processing device in the form of an integrated circuit. And they may be implemented separately or integrated together. That is, the above modules may be configured as one or more integrated circuits implementing the above methods, for example: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs)
A computer-readable storage medium on which a computer program is stored, the computer program being executed by a processor to implement the processing method described above.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions according to the embodiments of the present application are all or partially generated when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions may be transmitted from one website, computer, information push processing device, or data center to another website, computer, information push processing device, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. Computer-readable storage media can be any available media that can be accessed by a computer or data storage device, including one or more available media integrated information push processing devices, data centers, and the like. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), among others.
Those skilled in the art will recognize that, in one or more of the examples described above, the functions described in the embodiments of the present application may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It will be understood that the present application 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 application is limited only by the appended claims.
Claims (11)
1. An information push processing method, comprising:
acquiring a characteristic data set of a user, wherein the characteristic data set comprises at least one characteristic data, and the characteristic data comprises state characteristic data and behavior characteristic data;
determining a price sensitivity of the user for at least one item price data from the feature data set;
and pushing the item information according to the price sensitivity of the user aiming at least one item price data.
2. The method of claim 1, wherein the at least one item price data constitutes an item price data set, and wherein determining a price sensitivity of the user for the at least one item price data from the characteristic data set comprises:
determining transaction probability data corresponding to each item price data according to the characteristic data set of the user by using an evaluation model obtained by pre-training to obtain a transaction probability data set of the user;
determining a price sensitivity of the user for at least one item price data from the item price dataset and the user's transaction probability dataset.
3. The method of claim 2, wherein determining a price sensitivity of the user for at least one item price data from the item price dataset and the user's transaction probability dataset comprises:
determining an association of the item price dataset and the user's transaction probability dataset;
and determining the price sensitivity of the user aiming at least one item price data according to the incidence relation.
4. The method of claim 3, wherein said determining an association of said item price dataset and said user's transaction probability dataset comprises:
fitting to generate a correlation curve according to the item price data set and the transaction probability data set of the user;
the determining the price sensitivity of the user for at least one item price data according to the incidence relation comprises:
and determining the slope of the association curve corresponding to each item price data to obtain the price sensitivity of the user for at least one item price data.
5. The method of claim 3, wherein said determining an association of said item price dataset and said user's transaction probability dataset comprises:
fitting to generate a correlation curve according to the item price data set and the transaction probability data set of the user;
the determining the price sensitivity of the user for at least one item price data according to the incidence relation comprises:
determining a normalized slope of the correlation curve, the normalized slope constituting a price sensitivity of the user for at least one item price data.
6. The method of claim 2, wherein the evaluation model is trained by:
establishing a model of feature data about a user, wherein the behavior feature data in the feature data comprises historical transaction data and historical travel data;
acquiring a characteristic data set of a user as a training sample, wherein the characteristic data set comprises at least one characteristic data;
and carrying out model training according to the training samples to obtain the evaluation model.
7. The method according to any one of claims 1-6, wherein said pushing item information according to the price sensitivity of said user for at least one of said item price data comprises:
when resource allocation of an item with a certain item price is carried out, determining a user with the price sensitivity exceeding a preset threshold value as a target user according to the price sensitivity of the user for the item price;
and pushing the item information to the target user.
8. The method according to any one of claims 1-6, wherein said pushing item information according to a price sensitivity of said user for at least one of said item price data, further comprises:
determining a user profile characteristic according to the price sensitivity of the user to at least one item price data, wherein the user profile characteristic comprises an average transaction probability and a user maximum value;
and pushing the item information according to the user image characteristics and the price sensitivity of the user aiming at least one item price data.
9. An information push processing device, comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring a feature data set of a user, the feature data set comprises at least one feature data, and the feature data comprises state feature data and behavior feature data;
a first processing unit for determining a price sensitivity of a user for at least one item price data from the feature data set;
and the second processing unit is used for pushing the item information according to the price sensitivity of the user aiming at the price data of at least one item.
10. An information push processing device, comprising:
a processor, a memory, and a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any of claims 1-8.
11. A computer-readable storage medium having stored thereon a computer program for execution by a processor to perform the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010480037.4A CN111833141A (en) | 2020-05-29 | 2020-05-29 | Information push processing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010480037.4A CN111833141A (en) | 2020-05-29 | 2020-05-29 | Information push processing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111833141A true CN111833141A (en) | 2020-10-27 |
Family
ID=72913927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010480037.4A Withdrawn CN111833141A (en) | 2020-05-29 | 2020-05-29 | Information push processing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111833141A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112800329A (en) * | 2021-01-29 | 2021-05-14 | 深圳维创乐科技有限公司 | Information pushing method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107622413A (en) * | 2017-08-08 | 2018-01-23 | 阿里巴巴集团控股有限公司 | A kind of price sensitivity computational methods, device and its equipment |
| CN108985809A (en) * | 2017-06-02 | 2018-12-11 | 北京京东尚科信息技术有限公司 | Motivate method, apparatus, electronic equipment and the storage medium of push |
| CN110084648A (en) * | 2019-04-28 | 2019-08-02 | 广东技术师范大学 | Calculation method, device and the computer readable storage medium of price sensitivity |
| CN110363652A (en) * | 2019-06-27 | 2019-10-22 | 上海淇毓信息科技有限公司 | A kind of financial product pricing method, device and electronic equipment based on Price Sensitive model |
-
2020
- 2020-05-29 CN CN202010480037.4A patent/CN111833141A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108985809A (en) * | 2017-06-02 | 2018-12-11 | 北京京东尚科信息技术有限公司 | Motivate method, apparatus, electronic equipment and the storage medium of push |
| CN107622413A (en) * | 2017-08-08 | 2018-01-23 | 阿里巴巴集团控股有限公司 | A kind of price sensitivity computational methods, device and its equipment |
| CN110084648A (en) * | 2019-04-28 | 2019-08-02 | 广东技术师范大学 | Calculation method, device and the computer readable storage medium of price sensitivity |
| CN110363652A (en) * | 2019-06-27 | 2019-10-22 | 上海淇毓信息科技有限公司 | A kind of financial product pricing method, device and electronic equipment based on Price Sensitive model |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112800329A (en) * | 2021-01-29 | 2021-05-14 | 深圳维创乐科技有限公司 | Information pushing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109389431B (en) | Method and device for distributing coupons, electronic equipment and readable storage medium | |
| WO2019196579A1 (en) | Method and apparatus for issuing smart voucher, and method and apparatus for verification and cancellation by using smart voucher | |
| TW201939379A (en) | Information conversion rate prediction method and apparatus, and information recommendation method and apparatus | |
| WO2019184583A1 (en) | Activity content push method based on electronic book, and electronic device | |
| CN110070399A (en) | A kind of discount coupon method for pushing and device | |
| CN106487715B (en) | Method and device for allocating resources to users | |
| CN106897905B (en) | Method and device for pushing information and electronic equipment | |
| CN104965844A (en) | Information processing method and apparatus | |
| CN108112038B (en) | Method and device for controlling access flow | |
| WO2019179030A1 (en) | Product purchasing prediction method, server and storage medium | |
| CN109543940B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| TW201939402A (en) | Resource recommendation method and apparatus, marketing recommendation method and apparatus, and electronic device | |
| CN110033120A (en) | For providing the method and device that risk profile energizes service for trade company | |
| TW201417008A (en) | Method and apparatus for processing resource returns | |
| CN111311294A (en) | Data processing method, device, medium and electronic equipment | |
| CN106415637A (en) | Commission allocation method and system | |
| CN115375177A (en) | User value evaluation method and device, electronic equipment and storage medium | |
| CN111756837A (en) | Information pushing method, device, equipment and computer readable storage medium | |
| CN111626767A (en) | Resource data distribution method, device and equipment | |
| CN111833141A (en) | Information push processing method, device, equipment and storage medium | |
| CN111598632B (en) | Method and device for determining equity shares and equity share sequence | |
| CN112819552A (en) | Advertisement pushing method and device and computer readable storage medium | |
| CN112085332A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN109300055B (en) | Continuous insurance profit and loss query method, device, equipment and readable storage medium | |
| CN111833142A (en) | Information push processing method, device, equipment and 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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201027 |
|
| WW01 | Invention patent application withdrawn after publication |