CN112800329A - Information pushing method and device, electronic equipment and storage medium - Google Patents

Information pushing method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN112800329A
CN112800329A CN202110133992.5A CN202110133992A CN112800329A CN 112800329 A CN112800329 A CN 112800329A CN 202110133992 A CN202110133992 A CN 202110133992A CN 112800329 A CN112800329 A CN 112800329A
Authority
CN
China
Prior art keywords
user
analyzed
node
target
article
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
Application number
CN202110133992.5A
Other languages
Chinese (zh)
Inventor
梁春阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Weichuangle Technology Co ltd
Original Assignee
Shenzhen Weichuangle Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Weichuangle Technology Co ltd filed Critical Shenzhen Weichuangle Technology Co ltd
Priority to CN202110133992.5A priority Critical patent/CN112800329A/en
Publication of CN112800329A publication Critical patent/CN112800329A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/95—Retrieval from the web
    • G06F16/953—Querying, e.g. by the use of web search engines
    • G06F16/9535—Search customisation based on user profiles and personalisation
    • 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
    • G06Q30/0206—Price or cost determination based on market factors
    • 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]
    • G06Q30/0623—Item investigation
    • G06Q30/0625—Directed, with specific intent or strategy
    • 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

Abstract

The embodiment of the application discloses an information pushing method, an information pushing device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring historical data of an article to be analyzed; according to the historical data of the object to be analyzed, predicting the expected price of the object to be analyzed at the current moment; acquiring the behavior data of any user, and determining the matching degree between any user and the to-be-analyzed object according to the behavior data of any user and the expected price of the to-be-analyzed object at the current moment; determining a target user corresponding to the article to be analyzed according to the matching degree between any user and the article to be analyzed; sending the detailed information of the object to be analyzed to the terminal equipment of the target user so as to display the detailed information of the object to be analyzed on a visual interface of the terminal equipment of the target user. The method and the device are beneficial to improving the screening precision of the target user.

Description

Information pushing method and device, electronic equipment and storage medium
Technical Field
The present application relates to the field of information processing technologies, and in particular, to an information pushing method and apparatus, an electronic device, and a storage medium.
Background
With the development of internet technology, users using intelligent terminals are increasing. More and more platforms push information such as advertisements and articles to the intelligent terminal of the user through a pushing system so as to achieve the purposes of increasing click rate, promoting profit and the like.
At present, when an article is on-line, a target user needs to be screened out firstly, and then detailed information of the article is pushed to the target user so as to achieve the purpose of popularizing the article. However, when a target user is screened at present, the purchasing ability of the user is generally determined through historical consumption data of the user, and the target user is screened through the purchasing ability, so that the method for screening the target user is single, and the precision of the screened target user is low.
Disclosure of Invention
The embodiment of the application provides an information pushing method and device, electronic equipment and a storage medium, so as to improve the accuracy of a screened target user.
In a first aspect, an embodiment of the present application provides an information pushing method, including:
acquiring historical data of an article to be analyzed;
according to the historical data of the object to be analyzed, predicting the expected price of the object to be analyzed at the current moment;
acquiring the behavior data of any user, wherein the behavior data of any user comprises the consumption amount, consumption frequency, payment rate and buyback rate on a target object of the any user in a preset time period, and the target object is the same kind of object of the object to be analyzed;
coding the consumption amount of any user to obtain a first feature vector;
encoding the consumption frequency of any user to obtain a second feature vector;
coding the payment rate of any user to obtain a third feature vector;
coding the expected price of the object to be analyzed to obtain a fourth feature vector;
splicing the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain a target feature vector of any one user;
determining the matching probability between any user and the object to be analyzed according to the target feature vector of any user, and taking the matching probability as the matching degree between any user and the object to be analyzed;
determining a target user corresponding to the article to be analyzed according to the matching degree between any user and the article to be analyzed;
sending the detailed information of the object to be analyzed to the terminal equipment of the target user so as to display the detailed information of the object to be analyzed on a visual interface of the terminal equipment of the target user.
In a second aspect, an embodiment of the present application provides an information pushing apparatus, including:
the acquisition unit is used for acquiring historical data of an article to be analyzed;
the processing unit is used for predicting the expected price of the object to be analyzed at the current moment according to the historical data of the object to be analyzed;
acquiring the behavior data of any user, wherein the behavior data of any user comprises the consumption amount, consumption frequency, payment rate and buyback rate on a target object of the any user in a preset time period, and the target object is the same kind of object of the object to be analyzed;
coding the consumption amount of any user to obtain a first feature vector;
encoding the consumption frequency of any user to obtain a second feature vector;
coding the payment rate of any user to obtain a third feature vector;
coding the expected price of the object to be analyzed to obtain a fourth feature vector;
splicing the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain a target feature vector of any one user;
determining the matching probability between any user and the object to be analyzed according to the target feature vector of any user, and taking the matching probability as the matching degree between any user and the object to be analyzed;
determining a target user corresponding to the article to be analyzed according to the matching degree between any user and the article to be analyzed;
and the sending unit is used for sending the detailed information of the article to be analyzed to the terminal equipment of the target user so as to display the detailed information of the article to be analyzed on a visual interface of the terminal equipment of the target user.
In a third aspect, an embodiment of the present application provides an electronic device, including: a processor coupled to a memory, the memory configured to store a computer program, the processor configured to execute the computer program stored in the memory to cause the electronic device to perform the method of the first aspect.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, which stores a computer program, where the computer program makes a computer execute the method according to the first aspect.
In a fifth aspect, embodiments of the present application provide a computer program product comprising a non-transitory computer-readable storage medium storing a computer program, the computer being operable to cause a computer to perform the method according to the first aspect.
The embodiment of the application has the following beneficial effects:
it can be seen that, in the embodiment of the present application, the expected price of the object to be analyzed at the current time (i.e. the pricing at the current time) is predicted according to the historical data of the object to be analyzed; and then, screening out the target users matched with the to-be-analyzed object according to the expected price and the behavior data of the users. Therefore, the target user is screened out by integrating the characteristics of the object to be analyzed and the characteristics of the user, and the screening precision of the target user is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic structural diagram of an information push system according to an embodiment of the present disclosure;
fig. 2 is a schematic flowchart of an information pushing method according to an embodiment of the present application;
fig. 3 is a schematic diagram of a social topological graph according to an embodiment of the present disclosure;
FIG. 4 is a schematic flow chart illustrating a method for determining a desired price according to an embodiment of the present application;
fig. 5 is a block diagram illustrating functional units of an information pushing apparatus according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The terms "first," "second," "third," and "fourth," etc. in the description and claims of this application and in the accompanying drawings are used for distinguishing between different objects and not for describing a particular order. Furthermore, the terms "include" and "have," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements listed, but may alternatively include other steps or elements not listed, or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, result, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It is explicitly and implicitly understood by one skilled in the art that the embodiments described herein can be combined with other embodiments.
First, an application scenario of the present application is explained, and the embodiment of the present application may be applied to information pushing scenarios of various articles, for example, clothing (jacket, short sleeve, sweater, and the like), home appliances, furniture, electronic products (e.g., mobile phone, tablet, computer, and the like), decoration materials (wallpaper, ceiling, and the like), living goods, and the like. The article to be analyzed is exemplified as a garment in the present application.
Referring to fig. 1, fig. 1 is an architecture diagram of an information push system according to an embodiment of the present disclosure. The information push system comprises an information push device 10 and a terminal device 20.
Based on the information pushing system shown in fig. 1, the information pushing device 10 acquires historical data of an article to be analyzed; according to the historical data of the object to be analyzed, predicting the expected price of the object to be analyzed at the current moment; acquiring the behavior data of any user, and determining the matching degree between any user and the to-be-analyzed object according to the behavior data of any user and the expected price of the to-be-analyzed object at the current moment; determining a target user corresponding to the article to be analyzed according to the matching degree between any user and the article to be analyzed; the information pushing device 10 sends the detailed information of the article to be analyzed to the terminal device 20, so as to display the detailed information of the article to be analyzed on a visual interface of the terminal device 20, so as to display the detailed information of the article to be analyzed to the user.
It can be seen that, in the embodiment of the present application, the information pushing device 10 predicts the expected price of the object to be analyzed at the current time (i.e. pricing at the current time) according to the historical data of the object to be analyzed; and then, screening out the target users matched with the to-be-analyzed object according to the expected price and the behavior data of the users. Therefore, the target user is screened out by integrating the characteristics of the object to be analyzed and the characteristics of the user, and the screening precision of the target user is improved; due to the fact that the accuracy of the screened target users is high, when the target users are popularized to be analyzed, pertinence is achieved, and popularization effects are improved.
Referring to fig. 2, fig. 2 is a schematic flowchart of an information pushing method according to an embodiment of the present disclosure. The method is applied to the information pushing device. The method comprises the following steps:
201: the information pushing device acquires historical data of the object to be analyzed.
The historical data of the analyte item comprises historical data under a plurality of historical moments, the historical data under each historical moment comprises sales data and comment data of the analyte item under each historical moment, the sales data under each historical moment comprises price, sales quantity (the sales quantity is the sales quantity between the last historical moment and the historical moment), advertisement investment and cost of the analyte item under each historical moment, and the comment data comprises the score of the analyte item and the number of comments related to the analyte item.
202: and the information pushing device predicts the expected price of the object to be analyzed at the current moment according to the historical data of the object to be analyzed.
For example, the manner of predicting the expected price can be seen in fig. 3, and will not be described herein too much.
203: the information pushing device obtains the behavior data of any user, and the matching degree between any user and the object to be analyzed is determined according to the behavior data of any user and the expected price of the object to be analyzed at the current moment.
Illustratively, the behavior data of the user includes a consumption amount, a consumption frequency, a payment rate and a buyback rate on a target item of the user within a preset time period, wherein the target item is a kind of the object to be analyzed, for example, the object to be analyzed is a jacket in clothing, and the target item is a jacket. The consumption amount is an average consumption amount of the user in the preset time period, for example, if 5 items are bought in the preset time period and the total price is 600 yuan, the consumption amount of the user in the preset time period is 120 yuan. The consumption frequency is the ratio of the consumption times in the preset time period to the preset time period (namely the duration of the preset time period), the payment rate is the ratio of the times of successfully purchasing the goods in the preset time period to the quantity of the goods added into the shopping cart, and the ratio of the times of repeatedly purchasing the target goods by the user on the same kind of goods in the preset time period to the preset time period (namely the duration of the preset time period).
Wherein, the preset time period can be the first 3 days, the first 5 days, the first month or other values.
Illustratively, the consumption amount of the user is encoded to obtain a first feature vector; encoding the consumption frequency of the user to obtain a second feature vector; coding the payment rate of the user to obtain a third feature vector; coding the expected price of the object to be analyzed to obtain a fourth feature vector; coding the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain a target feature vector of the user; then, determining the matching probability between the user and the article to be analyzed according to the target feature vector of the user, and taking the matching probability as the matching degree between the user and the article to be analyzed, wherein the mode of determining the matching probability according to the target feature vector of the user is similar to the existing mode of classifying by using a neural network, namely, performing secondary classification according to the target feature vector of the user to obtain the probability of falling into two categories (matching and unmatching), and taking the probability of falling into the category of matching as the matching probability between the user and the article to be analyzed.
The process of encoding the amount of consumption will be described below by taking the amount of consumption as an example.
Illustratively, a plurality of preset price intervals are obtained, wherein interval intervals of any two price intervals can be the same or different, and the interval intervals are not limited in the application; then, determining a price interval in which the consumption amount of the user falls; and assigning values according to the order from small to large of the price intervals to obtain the first feature vector, wherein the dimension of the first feature vector is the same as the quantity of the price intervals, the dimension value corresponding to the price interval in which the consumption amount of the user falls is 1, the dimension values corresponding to the remaining price intervals are all 0, and the remaining price intervals are price intervals except the price interval in which the consumption amount falls in the price intervals.
For example, if the price ranges include [0,10], [10,20], [20,30], …, and [990,1000], the first feature vector is a 100-dimensional vector, and if the consumption amount of the user is 35 dollars, the first feature vector is [0,0,0,1, … …, 0] (dimension is 100).
Therefore, the consumption frequency, the payment rate and the expected price can be coded respectively based on a similar method for coding the consumption amount, so as to obtain the second feature vector, the third feature vector and the fourth feature vector.
204: and the information pushing device determines a target user corresponding to the to-be-analyzed object according to the matching degree between any user and the to-be-analyzed object.
For example, in a case that the matching degree between the arbitrary user and the article to be analyzed is greater than a first threshold, the arbitrary user is taken as a target user corresponding to the article to be analyzed.
It can be seen that, in the embodiment of the present application, the expected price of the object to be analyzed at the current time (i.e. the pricing at the current time) is predicted according to the historical data of the object to be analyzed; and then, screening out the target users matched with the to-be-analyzed object according to the expected price and the behavior data of the users. Therefore, the target user is screened out by integrating the characteristics of the object to be analyzed and the characteristics of the user, and the screening precision of the target user is improved.
In an embodiment of the application, after the target user corresponding to the article to be analyzed is determined, the detailed information of the article to be analyzed may be further sent to the terminal device of the target user, so that the detailed information of the article to be analyzed is displayed on a visualization interface of the terminal device. Illustratively, the detailed information of the item to be analyzed includes a price, an attribute, a picture, a purchase link, comment details, and the like of the item to be analyzed.
In an embodiment of the present application, when the matching degree between the user and the article to be analyzed is greater than the first threshold, social information of the user may also be obtained, where the social information includes a contact owned by the user and a contact owned by the user, and of course, the social information may also be extended downward, and only two metrics are used as an example in the present application. Therefore, as shown in fig. 3, a social topological graph corresponding to the user may be established according to the social information of the user, where the social topological graph includes a target node and a plurality of first nodes, the target node is a node of the arbitrary user in the social topological graph, the plurality of first nodes are nodes of a plurality of users having social connections with the arbitrary user in the social topological graph, the plurality of users correspond to the plurality of first nodes one to one, and the plurality of users may be understood as contacts owned by the arbitrary user or contacts (which may also be referred to as indirect contacts) of the contacts owned by the arbitrary user, so that the social connections include direct social connections or indirect social connections. Then, according to a target feature vector of any one node in the social topological graph and an affinity between any two nodes in the social topological graph, determining an information exchange probability between the target node and each of the plurality of first nodes, wherein the target feature vector of any one node is determined by behavior data of a user corresponding to the any one node, and the manner of determining the target feature vector of any one node is similar to that of determining the target feature vector, which is not described again, the affinity between any two nodes is determined by the exchange frequency of the user corresponding to any two nodes within the preset time period, that is, the exchange frequency of the user corresponding to any two nodes within the preset time period is determined, the exchange frequency is used as the affinity between the two nodes, for example, the preset time period is 8 days, in 8 days, two users corresponding to the two nodes have information communication for 4 days, and the communication frequency between the two users is 0.5, that is, the intimacy between the two users is 0.5.
Specifically, a first similarity between a target feature vector of a first node i and a target feature vector of a target node is determined, wherein the first node i is any one of the plurality of first nodes; in the case that the first node i is directly connected to the target node, such as the first node B, the first node C, and the first node D shown in fig. 3, the product of the affinity between the first node i and the target node and the first similarity is used to establish an information exchange probability between the first node i and the target node; in the case that the first node i is indirectly connected to the target node, such as the first node a and the first node E shown in fig. 3, the node a is taken as an example for explanation; taking the product of the intimacy degree between the first node j (namely, the first node B) and the first node i (namely, the first node A) and the intimacy degree between the first node j and the target node as the intimacy degree between the first node i and the target node; and then, taking the product of the intimacy between the first node i and the target node and the first similarity between the first node i and the target node as the information exchange probability between the first node i and the target node, wherein the first node j is directly connected with the first node i, and the first node j is directly connected with the target node.
It should be understood that, in the present application, in the case that the first node is indirectly connected to the target node, only one node is illustrated as being separated between two nodes, in practical applications, more nodes may be separated between the two nodes, and the manner of separating more nodes is similar to the manner of separating one node, and will not be described again.
It should be understood that, by determining the first similarity between the target feature vector of the target node and the target feature vector of each first node, the user corresponding to the target node and the user corresponding to each first node can be characterized, and the matching degree between the user corresponding to the target node and the object to be analyzed can be simultaneously determined, which indicates how likely the user will send the detailed information of the object to be analyzed to the user corresponding to each first node. However, since the target node and the first node are not directly connected or do not communicate with each other frequently, the communication probability is multiplied on the basis of the first similarity, and the obtained information communication probability can be used to represent the probability that the information sent to the user in any month is transmitted from any user to the user corresponding to each first node. That is, in the case where the detailed information of the analysis item is transmitted to the arbitrary user, there is a high probability that the detailed information of the analysis item is transmitted from the user to the user corresponding to each first node.
Further, the number of the first nodes with the information exchange probability larger than a second threshold value is obtained; and determining that the number of the first nodes with the information exchange probability larger than the second threshold is larger than the third threshold. For example, when the information exchange probability is greater than the second threshold, it is considered that information can be transmitted from the user to a user corresponding to the first node with a certain degree of confidence, and when the number is greater than the third threshold, it is determined that the user can transmit information to many users, so that the influence of the user is large, and the user can be used as a target user.
In one embodiment of the application, after sending detailed information of an article to be analyzed to the terminal device of the target user, feedback information is also received from the terminal device of the target user; and determining the target income of the object to be analyzed according to the feedback information. Illustratively, the feedback information includes an operation of the target user for detailed information of the object to be analyzed, specifically, if the target user clicks on the detailed information and purchases the object to be analyzed or adds the object to be analyzed to a shopping cart, the target user is taken as a first valid target user; if the target user clicks on the detailed information and browses the to-be-analyzed object, taking the target user as a second effective target user; if the target user does not process the detailed information, the target user is taken as an invalid target user; then, determining the target benefit of the analyte item according to the number of the first effective target users, the number of the second target users and the price of the analyte item at the current moment, for example, the number of the second target users may be multiplied by a preset coefficient to obtain a final number of the second target users, taking the sum of the final number of the second target users and the number of the first target users as a target number, and taking the product of the target number and the profit (i.e., the difference between the price and the cost of the analyte item at the current moment) of each analyte item as the target benefit of the analyte item; then, according to the target income of the object to be analyzed, whether to continue pushing the detailed information of the object to be analyzed is determined, for example, if the difference between the target income and the cost for pushing the detailed information of the object to be analyzed is greater than a threshold value, the detailed information of the object to be analyzed is continuously pushed, otherwise, the detailed information of the object to be analyzed is not pushed any more.
It can be seen that, in this embodiment, through treating the popularization effect of analysis article and analyzing, avoid always blindly propelling movement, improve the pertinence of propelling movement.
First, it should be noted that the product parameters to be analyzed in the embodiments of the present application include historical data of the items to be analyzed and data at the current time, and the product parameters of each item of the same kind also include historical data of each item of the same kind and data at the current time, and the product parameters are described later according to the description herein and will not be further described.
Furthermore, the historical data of the article to be analyzed comprises historical data at a plurality of historical moments, the historical data at each historical moment comprises sales data and comment data of the article to be analyzed at the historical moment, wherein the sales data at each historical moment comprises price, sales quantity (the sales quantity is the sales quantity between the last historical moment and the historical moment), advertisement investment and cost of the article to be analyzed at the historical moment, and the comment data at each historical moment comprises score of the article to be analyzed at the historical moment and number of comments related to the article to be analyzed at the historical moment. Similarly, the historical data of each similar item comprises historical data at a plurality of historical moments, and the historical data at each historical moment comprises sales data and comment data of the similar item at the historical moment, wherein the sales data at each historical moment also comprises the price, the sales quantity (the sales quantity is the sales quantity between the last historical moment and the historical moment) and the advertisement investment of the similar item at the historical moment, and the comment data at each historical moment comprises the rating of the similar item at each historical moment and the quantity of comments related to the similar item at the historical moment.
Therefore, the data of the article to be analyzed at the current moment comprises the advertising investment, the cost and the comment data of the article to be analyzed at the current moment, wherein the comment data at the current moment comprises the score of the article to be analyzed at the current moment and the number of comments related to the article to be analyzed at the current moment. Similarly, the data of each similar object at the current moment comprises the advertisement investment, the cost and the comment data of the to-be-analyzed object at the current moment, wherein the comment data at the current moment comprises the score of each similar object at the current moment and the number of comments related to each similar object at the current moment.
It can be seen that compared with the historical moment, the price and the sales volume of the object to be analyzed and each similar object at the current moment are unknown, namely, a non-linear relation between the sales volume and the price is established, and then the market potential value of the object to be analyzed at the current moment is predicted based on the non-linear relation.
Referring to fig. 4, fig. 4 is a flowchart illustrating a method for determining a desired price according to an embodiment of the present application. The method is applied to the information pushing device. The method comprises the following steps:
401: and determining a nonlinear relation between the sales volume of the article to be analyzed and the expected price at the current moment according to the historical data of the article to be analyzed.
Illustratively, the property of the article to be analyzed is acquired, for example, when the article to be analyzed is clothing, the property of the article to be analyzed is men's sweater; then, according to the article attribute of the article to be analyzed, the similar articles (men's sweaters) corresponding to the article to be analyzed are determined, and historical data of each similar article in the similar articles are obtained.
Then, according to the historical data of the object to be analyzed and the historical data of each similar object, determining a nonlinear relation between a first parameter and a second parameter of the object to be analyzed at the current moment, wherein the first parameter is the sales volume of the object to be analyzed, the second parameter is the expected price of the object to be analyzed, and it is understood that in the historical data, the expected price is the actual price of the object to be analyzed at each historical moment; and finally, predicting the expected price of the article to be analyzed at the current moment according to the nonlinear relation between the first parameter and the second parameter of the article to be analyzed.
Specifically, a preset parameter set is obtained, wherein the second parameter is one of the parameter set. Illustratively, the set of parameters includes, but is not limited to, price, cost of advertising, number of reviews, and rating. It is then assumed in this application that the influence of each parameter in the set of parameters on the sales of the items to be analyzed is independent of each other and can be superimposed. Therefore, for the parameter a, a sub-nonlinear relationship between the first parameter and the parameter a is determined according to the historical data of the object to be analyzed and the historical data of each of the similar objects, wherein the parameter a is any one of the parameters in the parameter set.
Specifically, according to the historical data of the object to be analyzed, determining a plurality of first values of a parameter a at the plurality of historical moments, wherein each historical moment corresponds to one first value, that is, determining the values of the parameter a in the object to be analyzed at the plurality of historical moments, for example, the parameter a is a price, and the values of the object to be analyzed at the plurality of historical moments are respectively 50 yuan, 55 yuan, 60 yuan and 50 yuan, so that the plurality of first values are respectively 50 yuan, 55 yuan, 60 yuan and 50 yuan; similarly, according to the historical data of each similar article, a plurality of second values of the parameter a corresponding to each similar article at a plurality of historical moments are determined, wherein each historical moment corresponds to one second value, that is, the value of the parameter a in each similar article at the plurality of historical moments is determined.
Then, at each historical moment, according to the first value of the parameter A in the object to be analyzed and the second value of the parameter A in each similar object, the ranking of the first value of the parameter A in the object to be analyzed at each historical moment is determined. For example, if the first value of the parameter a in the analyte is 50 and the second values in the similar items are 40,55,60,70, and 85 respectively at the historical time T1, the ranking of the first value of the parameter a in the analyte is 3 at the historical time T1; then, according to the ranking of the first value of the parameter A in the object to be analyzed at each historical moment, determining a standardized value corresponding to the first value of the parameter A in the object to be analyzed at each historical moment, namely, obtaining a standardized value corresponding to the ranking of the first value of the parameter A in the object to be analyzed at each historical moment through cross section standardization processing. Illustratively, the normalized value can be expressed by equation (1):
Figure BDA0002925041510000111
wherein the content of the first and second substances,
Figure BDA0002925041510000112
is the corresponding standardized value of the parameter A, rank (A) is the ranking of the first value of the parameter A in the object to be analyzed at each historical moment, NThe number of the same kind of articles.
For example, as described above, if the first value of the parameter a in the object to be analyzed at the historical time T1 is ranked 3, and the number of the same kind of object is 5, the normalized value corresponding to the parameter a is 0.5.
Based on the formula (1), it can be known that one standardized value can be obtained at each historical time, and the parameter a corresponds to a plurality of standardized values at a plurality of historical times.
It should be noted that, each parameter is standardized, mainly the dimensions of the parameters in the preset parameter set are not consistent, and in order to enable the subsequent sub-nonlinear relationship to be fused, values of all the parameters need to be standardized to dimensionless dimensions (i.e., uniform dimensions), so as to facilitate the subsequent nonlinear relationship stacking.
Further, according to the standardized value of the parameter A at each historical moment, the sub-nonlinear relation between the first parameter and the parameter A is determined.
Illustratively, the sub-nonlinear relationship between the first parameter and the parameter a can be represented by equation (2):
Figure BDA0002925041510000121
Figure BDA0002925041510000122
for the normalized value of the first parameter, α0，α1，…，αnIs the coefficient of the sub-nonlinear relationship (unknown),
Figure BDA0002925041510000123
for the normalized value of the parameter a, n (unknown) is the highest power of the sub-nonlinear relationship.
Thus, solving for the sub-nonlinear relationship between the first parameter and the parameter A is essentially solving for α0，α1，…，αnAnd the value of n.
The following provides a method for calculating a partial derivative by basing the assumptionsSolving for alpha0，α1，…，αnAnd n.
Firstly, setting the plurality of historical moments as m historical moments, wherein m is greater than 1, and the parameter A correspondingly has m standardized values; then, assuming that n is 1, randomly selecting one standardized value from m standardized values corresponding to the parameter a at m historical times as the standardized value
Figure BDA0002925041510000124
And taking the standard value
Figure BDA0002925041510000125
Substituting equation (2) results in the equation shown in equation (3):
Figure BDA0002925041510000126
Figure BDA0002925041510000127
the normalized value of the predicted first parameter is obtained when the first parameter is predicted by using the sub-nonlinear relation when n is 1. It should be understood that the sub-nonlinear relation prediction when n is 1 needs to be optimized
Figure BDA0002925041510000128
And
Figure BDA0002925041510000129
the smallest absolute difference between them, may be equated with the smallest squared difference, where,
Figure BDA00029250415100001210
is prepared by reacting with
Figure BDA00029250415100001211
The corresponding normalized value of the first parameter (i.e., the actual normalized value).
Illustratively, the square of the difference can be expressed by equation (4):
Figure BDA00029250415100001212
further, in the case of minimizing ε, a can be solved0And a1Value of (a is obtained as described in detail later)0And a1The value of (a) is not described herein too much), that is, when n is equal to 1, the sub-nonlinear relationship between the first parameter and the parameter a is obtained.
Then, assuming that n is 2, randomly selecting two normalized values from the m normalized values, and building an equation as shown in equation (2), a sub-nonlinear relationship between the first parameter and the parameter a can be obtained when n is 2.
By analogy, assuming that n is equal to m, all m normalized values are substituted into the equation of equation (2), and an equation set as shown in equation (5) can be constructed:
Figure BDA0002925041510000131
wherein the content of the first and second substances,
Figure BDA0002925041510000132
is a function of the m standardized values,
Figure BDA0002925041510000133
are respectively and
Figure BDA0002925041510000134
and correspondingly predicting the standardized value of the first parameter.
Further, suppose
Figure BDA0002925041510000135
Wherein the content of the first and second substances,
Figure BDA0002925041510000136
are respectively and
Figure BDA0002925041510000137
Figure BDA0002925041510000138
and marking the value of the corresponding actual first parameter. Therefore, equation (5) can be simplified to equation (6):
Figure BDA0002925041510000139
likewise, when n is equal to m, the square of the difference between the predicted normalized value of the first parameter and the actual normalized value of the first parameter can be expressed by equation (7):
Figure BDA00029250415100001310
then, let ε be respectively coupled to a1,a2，…，amPartial derivatives are calculated and each calculated partial derivative is made equal to 0, which can be reduced to obtain the equation set shown in equation (8):
Figure BDA00029250415100001311
solving the system of equations in equation (8) can obtain a1,a2，…，amAnd obtaining a sub-nonlinear relationship between the first parameter and the parameter A when n is equal to m.
Then, obtaining an absolute difference between the predicted normalized value of the first parameter and the actual normalized value of the first parameter when n is 1,2,3, … …, m, respectively; then, fitting a curve equation between the absolute difference value and n in the xoy coordinate system by taking n as a variable and the absolute difference value as an independent variable; finally, determining the minimum value of the absolute difference value according to the curve equation, determining the value of n corresponding to the minimum value, and if the value is an integer, taking the sub-nonlinear relation corresponding to the value as the nonlinear relation between the parameter A and the first parameter; if the value is not an integer, the sub-nonlinear relationship corresponding to the integer closest to the difference is taken as the nonlinear relationship between the parameter A and the first parameter.
Further, after the nonlinear relationship between each parameter and the first parameter is determined, the nonlinear relationships between all the parameters in the parameter set and the first parameter are superposed to obtain the nonlinear relationships between the first parameter and all the parameters. Then, determining a standardized value of any one of the remaining parameters in the object to be analyzed at the current moment, and inputting the value into the nonlinear relationship between the first parameter and all the parameters to obtain the nonlinear relationship between the first parameter and the second parameter of the object to be analyzed at the current moment, wherein the remaining parameters are parameters of all the parameters except the second parameter.
It should be understood that, the standardized value of the value of any one of the remaining parameters in the object to be analyzed at the current time is similar to the standardized value of the above-mentioned determined parameter a, and will not be described again.
402: and according to the nonlinear relation between the sales volume of the object to be analyzed and the expected price at the current moment and the cost of the object to be analyzed at the current moment, the expected price of the object to be analyzed at the current moment.
Illustratively, obtaining a difference value between the second parameter and a preset parameter, wherein the preset parameter can be understood as the cost of the object to be analyzed at the current moment; then, according to the nonlinear relationship between the first parameter and the second parameter and the difference, the nonlinear relationship between a target parameter and the second parameter is determined, wherein the target parameter is the expected profit of the object to be analyzed. Illustratively, the nonlinear relationship between the target parameter and the second parameter can be represented by equation (9):
P＝(x-y)*(a0+a1*x+…+az*xz+ B formula (9)
Where P is the target expectation, x is the second parameter, y is the preset parameter, a0+a1*x+…+az*xzIs a secondAnd B is a value obtained by substituting the labeled parameters of the rest parameters into the nonlinear relations between the first parameters and all the parameters and summing the labeled parameters.
Therefore, according to the formula (9), the maximum value of the target parameter is determined, and the value of x corresponding to the maximum value is determined, wherein the value of x is the expected price of the object to be analyzed at the current moment when the expected income is maximum. Therefore, the most appropriate expected price can be worked out through the formula (9), the expected benefit is maximized, and the profitability of a merchant is improved.
Referring to fig. 5, fig. 5 is a block diagram illustrating functional units of an information pushing apparatus according to an embodiment of the present disclosure. The information pushing device 500 includes: an obtaining unit 501, a processing unit 502 and a sending unit 503, wherein:
the acquiring unit 501 is used for acquiring historical data of an article to be analyzed;
the processing unit 502 is configured to predict an expected price of the object to be analyzed at the current time according to the historical data of the object to be analyzed;
acquiring the behavior data of any user, wherein the behavior data of any user comprises the consumption amount, consumption frequency, payment rate and buyback rate on a target object of the any user in a preset time period, and the target object is the same kind of object of the object to be analyzed;
coding the consumption amount of any user to obtain a first feature vector;
encoding the consumption frequency of any user to obtain a second feature vector;
coding the payment rate of any user to obtain a third feature vector;
coding the expected price of the object to be analyzed to obtain a fourth feature vector;
splicing the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain a target feature vector of any one user;
determining the matching probability between any user and the object to be analyzed according to the target feature vector of any user, and taking the matching probability as the matching degree between any user and the object to be analyzed;
determining a target user corresponding to the article to be analyzed according to the matching degree between any user and the article to be analyzed;
the sending unit 503 is configured to send the detailed information of the object to be analyzed to the terminal device of the target user, so that the detailed information of the object to be analyzed is displayed on a visual interface of the terminal device of the target user.
In some possible embodiments, in predicting the expected price of the analyte item at the current time according to the historical data of the analyte item, the processing unit 502 is specifically configured to:
determining a nonlinear relation between the sales volume of the article to be analyzed and the expected price at the current moment according to the historical data of the article to be analyzed;
and according to the nonlinear relation between the sales volume of the article to be analyzed and the expected price at the current moment, the cost of the article to be analyzed at the current moment and the expected price of the article to be analyzed at the current moment.
In some possible embodiments, in encoding the consumption amount of the arbitrary user to obtain the first feature vector, the processing unit 502 is specifically configured to:
acquiring a plurality of preset price intervals;
determining a price interval in which the consumption amount of any one user falls;
assigning values according to the sequence from small to large among the price intervals to obtain the first characteristic vector, wherein the dimensionality of the first characteristic vector is equal to the quantity of the price intervals, the dimensionality value corresponding to the price interval in which the consumption amount of any user falls is 1, the dimensionality value corresponding to the residual price interval is all 0, and the residual price interval is a price interval except the price interval in which the consumption amount of any user falls in the price intervals.
In some possible embodiments, in terms of determining, according to the matching degree between the any user and the article to be analyzed, a target user corresponding to the article to be analyzed, the processing unit 502 is specifically configured to:
and when the matching degree between any user and the article to be analyzed is larger than a first threshold value, taking the any user as a target user corresponding to the article to be analyzed.
In some possible embodiments, before the arbitrary user is taken as the target user corresponding to the article to be analyzed, the obtaining unit 501 is further configured to obtain social information of the arbitrary user; the processing unit 502 is further configured to establish a social topology graph corresponding to the arbitrary user according to social information of the arbitrary user, where the social topology graph includes a target node and a plurality of first nodes, any one of the plurality of first nodes is directly or indirectly connected to the target node, the target node is a node of the arbitrary user in the social topology graph, the plurality of first nodes are nodes of a plurality of users having social connections with the arbitrary user in the social topology graph, the social connections include direct social connections or indirect social connections, and the plurality of users correspond to the plurality of first nodes one to one;
determining an information exchange probability between the target node and each first node in the plurality of first nodes according to a target feature vector of any one node in the social topological graph and an affinity between any two nodes in the social topological graph, wherein the target feature vector of any one node is determined by behavior data of a user corresponding to any one node, the affinity between any two nodes is determined by an exchange frequency of the user corresponding to any two nodes in the preset time period, and the information exchange probability between the target node and each first node in the plurality of first nodes is used for representing a probability that information sent to any one user is transmitted from any one user to the user corresponding to each first node;
acquiring the number of first nodes with the information exchange probability larger than a second threshold;
and determining that the number of the first nodes with the information exchange probability larger than a second threshold is larger than a third threshold.
In some possible embodiments, in terms of determining the probability of information exchange between the target node and each of the plurality of first nodes according to the target feature vector of any one node in the social topological graph and the affinity between any two nodes in the social topological graph, the processing unit 502 is specifically configured to:
determining a first similarity between a target feature vector of a first node i and a target feature vector of the target node, wherein the first node i is any one of the plurality of first nodes;
taking the product of the affinity between the first node i and the target node and the first similarity as the information exchange probability between the first node i and the target node under the condition that the first node i is directly connected with the target node;
under the condition that the first node i is indirectly connected with the target node, taking the product of the intimacy degree between the first node j and the first node i and the intimacy degree between the first node j and the target node as the intimacy degree between the first node i and the target node, and taking the product of the intimacy degree between the first node i and the target node and the first similarity degree between the first node i and the target node as the information exchange probability between the first node i and the target node, wherein the first node j is directly connected with the first node i, and the first node j is directly connected with the target node.
Referring to fig. 6, fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. As shown in fig. 6, the electronic device 600 includes a transceiver 601, a processor 602, and a memory 603. Connected to each other by a bus 604. The memory 603 is used to store computer programs and data, and can transfer data stored in the memory 603 to the processor 602.
The processor 602 is configured to read the computer program in the memory 603 to perform the following operations:
acquiring historical data of an article to be analyzed;
according to the historical data of the object to be analyzed, predicting the expected price of the object to be analyzed at the current moment;
acquiring the behavior data of any user, and determining the matching degree between any user and the to-be-analyzed object according to the behavior data of any user and the expected price of the to-be-analyzed object at the current moment;
and determining a target user corresponding to the article to be analyzed according to the matching degree between any user and the article to be analyzed.
In some possible embodiments, in predicting the expected price of the analyte item at the current time according to the historical data of the analyte item, the processor 602 is specifically configured to:
determining a nonlinear relation between the sales volume of the article to be analyzed and the expected price at the current moment according to the historical data of the article to be analyzed;
and according to the nonlinear relation between the sales volume of the article to be analyzed and the expected price at the current moment, the cost of the article to be analyzed at the current moment and the expected price of the article to be analyzed at the current moment.
In some possible embodiments, the behavior data of any one user includes a consumption amount, a consumption frequency, a payment rate and a buyback rate on a target item within a preset time period, wherein the target item is a homogeneous item of the to-be-analyzed item; in terms of determining the matching degree between any one user and the article to be analyzed according to the behavior data of any one user and the expected price of the article to be analyzed at the current time, the processor 602 is specifically configured to perform the following operations:
coding the consumption amount of any user to obtain a first feature vector;
encoding the consumption frequency of any user to obtain a second feature vector;
coding the payment rate of any user to obtain a third feature vector;
coding the expected price of the object to be analyzed to obtain a fourth feature vector;
splicing the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain a target feature vector of any one user;
and determining the matching probability between the any user and the article to be analyzed according to the target feature vector of the any user, and taking the matching probability as the matching degree between the any user and the article to be analyzed.
In some possible embodiments, in encoding the consumption amount of the arbitrary user to obtain the first feature vector, the processor 602 is specifically configured to perform the following operations:
acquiring a plurality of preset price intervals;
determining a price interval in which the consumption amount of any one user falls;
assigning values according to the sequence from small to large among the price intervals to obtain the first characteristic vector, wherein the dimensionality of the first characteristic vector is equal to the quantity of the price intervals, the dimensionality value corresponding to the price interval in which the consumption amount of any user falls is 1, the dimensionality value corresponding to the residual price interval is all 0, and the residual price interval is a price interval except the price interval in which the consumption amount of any user falls in the price intervals.
In some possible embodiments, in terms of determining a target user corresponding to the article to be analyzed according to the matching degree between the arbitrary user and the article to be analyzed, the processor 602 is specifically configured to:
and when the matching degree between any user and the article to be analyzed is larger than a first threshold value, taking the any user as a target user corresponding to the article to be analyzed.
In some possible embodiments, before the any user is taken as the target user corresponding to the article to be analyzed, the processor 602 is further configured to:
acquiring social information of any user; establishing a social topological graph corresponding to any user according to social information of the any user, wherein the social topological graph comprises a target node and a plurality of first nodes, any one of the first nodes is directly or indirectly connected with the target node, the target node is a node of the any user in the social topological graph, the first nodes are nodes of a plurality of users having social connection with the any user in the social topological graph, the social connection comprises direct social contact or indirect social contact, and the users are in one-to-one correspondence with the first nodes;
determining an information exchange probability between the target node and each first node in the plurality of first nodes according to a target feature vector of any one node in the social topological graph and an affinity between any two nodes in the social topological graph, wherein the target feature vector of any one node is determined by behavior data of a user corresponding to any one node, the affinity between any two nodes is determined by an exchange frequency of the user corresponding to any two nodes in the preset time period, and the information exchange probability between the target node and each first node in the plurality of first nodes is used for representing a probability that information sent to any one user is transmitted from any one user to the user corresponding to each first node;
acquiring the number of first nodes with the information exchange probability larger than a second threshold;
and determining that the number of the first nodes with the information exchange probability larger than a second threshold is larger than a third threshold.
In some possible embodiments, in terms of determining the probability of information exchange between the target node and each of the plurality of first nodes according to the target feature vector of any one node in the social topological graph and the affinity between any two nodes in the social topological graph, the processor 602 is specifically configured to:
determining a first similarity between a target feature vector of a first node i and a target feature vector of the target node, wherein the first node i is any one of the plurality of first nodes;
taking the product of the affinity between the first node i and the target node and the first similarity as the information exchange probability between the first node i and the target node under the condition that the first node i is directly connected with the target node;
under the condition that the first node i is indirectly connected with the target node, taking the product of the intimacy degree between the first node j and the first node i and the intimacy degree between the first node j and the target node as the intimacy degree between the first node i and the target node, and taking the product of the intimacy degree between the first node i and the target node and the first similarity degree between the first node i and the target node as the information exchange probability between the first node i and the target node, wherein the first node j is directly connected with the first node i, and the first node j is directly connected with the target node.
It should be understood that the electronic device in the present application may include a smart Phone (e.g., an Android Phone, an iOS Phone, a Windows Phone, etc.), a tablet computer, a palm computer, a notebook computer, a Mobile Internet device MID (MID), a wearable device, or the like. The above mentioned electronic devices are only examples, not exhaustive, and include but not limited to the above mentioned electronic devices. In practical applications, the electronic device may further include: intelligent vehicle-mounted terminal, computer equipment and the like.
The embodiments of the present application also provide a computer-readable storage medium, which stores a computer program, where the computer program is executed by a processor to implement part or all of the steps of any one of the information pushing methods described in the above method embodiments.
Embodiments of the present application also provide a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any one of the information push methods described in the above method embodiments.
It should be noted that, for simplicity of description, the above-mentioned method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present application is not limited by the order of acts described, as some steps may occur in other orders or concurrently depending on the application. Further, those skilled in the art should also appreciate that the embodiments described in the specification are exemplary embodiments and that the acts and modules referred to are not necessarily required in this application.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one type of division of logical functions, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of some interfaces, devices or units, and may be an electric or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may be implemented in the form of a software program module.
The integrated units, if implemented in the form of software program modules and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be substantially implemented or a part of or all or part of the technical solution contributing to the prior art may be embodied in the form of a software product stored in a memory, and including several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method described in the embodiments of the present application. And the aforementioned memory comprises: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable memory, which may include: flash Memory disks, Read-Only memories (ROMs), Random Access Memories (RAMs), magnetic or optical disks, and the like.
The foregoing detailed description of the embodiments of the present application has been presented to illustrate the principles and implementations of the present application, and the above description of the embodiments is only provided to help understand the method and the core concept of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.

Claims (10)

1. An information pushing method, comprising:
acquiring historical data of an article to be analyzed;
according to the historical data of the object to be analyzed, predicting the expected price of the object to be analyzed at the current moment;
acquiring the behavior data of any user, wherein the behavior data of any user comprises the consumption amount, consumption frequency, payment rate and buyback rate on a target object of the any user in a preset time period, and the target object is the same kind of object of the object to be analyzed;
coding the consumption amount of any user to obtain a first feature vector;
encoding the consumption frequency of any user to obtain a second feature vector;
coding the payment rate of any user to obtain a third feature vector;
coding the expected price of the object to be analyzed to obtain a fourth feature vector;
splicing the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain a target feature vector of any one user;
determining the matching probability between any user and the object to be analyzed according to the target feature vector of any user, and taking the matching probability as the matching degree between any user and the object to be analyzed;
determining a target user corresponding to the article to be analyzed according to the matching degree between any user and the article to be analyzed;
sending the detailed information of the object to be analyzed to the terminal equipment of the target user so as to display the detailed information of the object to be analyzed on a visual interface of the terminal equipment of the target user.
2. The method of claim 1, wherein predicting the expected price of the item to be analyzed at the current time based on the historical data of the item to be analyzed comprises:
determining a nonlinear relation between the sales volume of the article to be analyzed and the expected price at the current moment according to the historical data of the article to be analyzed;
and according to the nonlinear relation between the sales volume of the article to be analyzed and the expected price at the current moment, the cost of the article to be analyzed at the current moment and the expected price of the article to be analyzed at the current moment.
3. The method according to claim 1 or 2, wherein said encoding the amount of consumption of said any one user to obtain a first feature vector comprises:
acquiring a plurality of preset price intervals;
determining a price interval in which the consumption amount of any one user falls;
assigning values according to the sequence from small to large among the price intervals to obtain the first characteristic vector, wherein the dimensionality of the first characteristic vector is equal to the quantity of the price intervals, the dimensionality value corresponding to the price interval in which the consumption amount of any user falls is 1, the dimensionality value corresponding to the residual price interval is all 0, and the residual price interval is a price interval except the price interval in which the consumption amount of any user falls in the price intervals.
4. The method according to any one of claims 1 to 3, wherein the determining a target user corresponding to the article to be analyzed according to the matching degree between the any one user and the article to be analyzed comprises:
and when the matching degree between any user and the article to be analyzed is larger than a first threshold value, taking the any user as a target user corresponding to the article to be analyzed.
5. The method of claim 4, wherein prior to identifying the arbitrary user as a target user corresponding to the item to be analyzed, the method further comprises:
acquiring social information of any user;
establishing a social topological graph corresponding to any user according to social information of the any user, wherein the social topological graph comprises a target node and a plurality of first nodes, any one of the first nodes is directly or indirectly connected with the target node, the target node is a node of the any user in the social topological graph, the first nodes are nodes of a plurality of users having social connection with the any user in the social topological graph, the social connection comprises direct social contact or indirect social contact, and the users are in one-to-one correspondence with the first nodes;
determining an information exchange probability between the target node and each first node in the plurality of first nodes according to a target feature vector of any one node in the social topological graph and an affinity between any two nodes in the social topological graph, wherein the target feature vector of any one node is determined by behavior data of a user corresponding to any one node, the affinity between any two nodes is determined by an exchange frequency of the user corresponding to any two nodes in the preset time period, and the information exchange probability between the target node and each first node in the plurality of first nodes is used for representing a probability that information sent to any one user is transmitted from any one user to the user corresponding to each first node;
acquiring the number of first nodes with the information exchange probability larger than a second threshold;
and determining that the number of the first nodes with the information exchange probability larger than a second threshold is larger than a third threshold.
6. The method of claim 5, wherein determining the probability of information exchange between the target node and each of the plurality of first nodes according to the target feature vector of any one node in the social topological graph and the affinity between any two nodes in the social topological graph comprises:
determining a first similarity between a target feature vector of a first node i and a target feature vector of the target node, wherein the first node i is any one of the plurality of first nodes;
taking the product of the affinity between the first node i and the target node and the first similarity as the information exchange probability between the first node i and the target node under the condition that the first node i is directly connected with the target node;
under the condition that the first node i is indirectly connected with the target node, taking the product of the intimacy degree between the first node j and the first node i and the intimacy degree between the first node j and the target node as the intimacy degree between the first node i and the target node, and taking the product of the intimacy degree between the first node i and the target node and the first similarity degree between the first node i and the target node as the information exchange probability between the first node i and the target node, wherein the first node j is directly connected with the first node i, and the first node j is directly connected with the target node.
7. An information pushing apparatus, comprising:
the acquisition unit is used for acquiring historical data of an article to be analyzed;
the processing unit is used for predicting the expected price of the object to be analyzed at the current moment according to the historical data of the object to be analyzed;
acquiring the behavior data of any user, wherein the behavior data of any user comprises the consumption amount, consumption frequency, payment rate and buyback rate on a target object of the any user in a preset time period, and the target object is the same kind of object of the object to be analyzed;
coding the consumption amount of any user to obtain a first feature vector;
encoding the consumption frequency of any user to obtain a second feature vector;
coding the payment rate of any user to obtain a third feature vector;
coding the expected price of the object to be analyzed to obtain a fourth feature vector;
splicing the first feature vector, the second feature vector, the third feature vector and the fourth feature vector to obtain a target feature vector of any one user;
determining the matching probability between any user and the object to be analyzed according to the target feature vector of any user, and taking the matching probability as the matching degree between any user and the object to be analyzed;
determining a target user corresponding to the article to be analyzed according to the matching degree between any user and the article to be analyzed;
and the sending unit is used for sending the detailed information of the article to be analyzed to the terminal equipment of the target user so as to display the detailed information of the article to be analyzed on a visual interface of the terminal equipment of the target user.
8. The apparatus according to claim 7, characterized in that, in predicting the expected price of the item to be analyzed at the current moment from the historical data of the item to be analyzed, the processing unit is specifically configured to:
determining a nonlinear relation between the sales volume of the article to be analyzed and the expected price at the current moment according to the historical data of the article to be analyzed;
and according to the nonlinear relation between the sales volume of the article to be analyzed and the expected price at the current moment, the cost of the article to be analyzed at the current moment and the expected price of the article to be analyzed at the current moment.
9. An electronic device, comprising: a processor coupled to the memory, and a memory for storing a computer program, the processor for executing the computer program stored in the memory to cause the electronic device to perform the method of any of claims 1-6.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which is executed by a processor to implement the method according to any one of claims 1-6.
CN202110133992.5A 2021-01-29 2021-01-29 Information pushing method and device, electronic equipment and storage medium Pending CN112800329A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110133992.5A CN112800329A (en) 2021-01-29 2021-01-29 Information pushing method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110133992.5A CN112800329A (en) 2021-01-29 2021-01-29 Information pushing method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN112800329A true CN112800329A (en) 2021-05-14

Family

ID=75813241

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110133992.5A Pending CN112800329A (en) 2021-01-29 2021-01-29 Information pushing method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN112800329A (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106022869A (en) * 2016-05-12 2016-10-12 北京邮电大学 Consumption object recommending method and consumption object recommending device
CN107203901A (en) * 2017-05-11 2017-09-26 中国联合网络通信集团有限公司 The method and device of product information is pushed to user
CN109034957A (en) * 2018-07-06 2018-12-18 北京摩拜科技有限公司 A kind of Products Show method, server and system for sharing articles
CN109685540A (en) * 2018-08-31 2019-04-26 深圳壹账通智能科技有限公司 Electric business platform and its commercial promotions control method, equipment, readable storage medium storing program for executing
CN110163661A (en) * 2019-04-23 2019-08-23 上海淇玥信息技术有限公司 Marketing message promotion method, device, electronic equipment and computer-readable medium
CN110992097A (en) * 2019-12-03 2020-04-10 上海钧正网络科技有限公司 Processing method and device for revenue product price, computer equipment and storage medium
CN111833141A (en) * 2020-05-29 2020-10-27 摩拜(北京)信息技术有限公司 Information push processing method, device, equipment and storage medium

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106022869A (en) * 2016-05-12 2016-10-12 北京邮电大学 Consumption object recommending method and consumption object recommending device
CN107203901A (en) * 2017-05-11 2017-09-26 中国联合网络通信集团有限公司 The method and device of product information is pushed to user
CN109034957A (en) * 2018-07-06 2018-12-18 北京摩拜科技有限公司 A kind of Products Show method, server and system for sharing articles
CN109685540A (en) * 2018-08-31 2019-04-26 深圳壹账通智能科技有限公司 Electric business platform and its commercial promotions control method, equipment, readable storage medium storing program for executing
CN110163661A (en) * 2019-04-23 2019-08-23 上海淇玥信息技术有限公司 Marketing message promotion method, device, electronic equipment and computer-readable medium
CN110992097A (en) * 2019-12-03 2020-04-10 上海钧正网络科技有限公司 Processing method and device for revenue product price, computer equipment and storage medium
CN111833141A (en) * 2020-05-29 2020-10-27 摩拜(北京)信息技术有限公司 Information push processing method, device, equipment and storage medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张雅云等: "基于价格与销量非线性关系的季节性商品促销定价模型", 《产业与科技论坛》, vol. 14, no. 14, 31 July 2015 (2015-07-31), pages 60 - 61 *

Similar Documents

Publication Publication Date Title
CN108230057A (en) A kind of intelligent recommendation method and system
CN107730389A (en) Electronic installation, insurance products recommend method and computer-readable recording medium
CN108960992A (en) A kind of information recommendation method and relevant device
CN106779940B (en) Method and device for confirming display commodity
CN110008397B (en) Recommendation model training method and device
CN111652648A (en) Method for intelligently generating personalized combined promotion scheme and system with same
CN111695960A (en) Object recommendation system, method, electronic device and storage medium
CN113643103A (en) Product recommendation method, device, equipment and storage medium based on user similarity
CN110020124A (en) The method and device excavated for Related product
WO2014110950A1 (en) Method and device for pushing information
CN115392947A (en) Demand prediction method and device
CN111461827A (en) Product evaluation information pushing method and device
CN109767302B (en) Method and device for constructing big data accurate model
CN107274247A (en) Wisdom based on cloud computing perceives recommendation method
KR102425758B1 (en) System for recommending company based machine learning
CN116911953B (en) Article recommendation method, apparatus, electronic device and computer readable storage medium
CN112800329A (en) Information pushing method and device, electronic equipment and storage medium
CN107357847B (en) Data processing method and device
CN110298730A (en) Commodity method for pushing and equipment based on machine learning algorithm under new retail mode
CN112036988B (en) Label generation method and device, storage medium and electronic equipment
CN112819533A (en) Information pushing method and device, electronic equipment and storage medium
CN114418012A (en) Object association relation determining method, device and equipment and computer storage medium
CN104050174B (en) A kind of personal page generation method and device
CN116911913B (en) Method and device for predicting interaction result
CN110766478A (en) Method and device for improving user connectivity

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