CN110472154B - Resource pushing method and device, electronic equipment and readable storage medium - Google Patents
Resource pushing method and device, electronic equipment and readable storage medium Download PDFInfo
- Publication number
- CN110472154B CN110472154B CN201910787820.2A CN201910787820A CN110472154B CN 110472154 B CN110472154 B CN 110472154B CN 201910787820 A CN201910787820 A CN 201910787820A CN 110472154 B CN110472154 B CN 110472154B
- Authority
- CN
- China
- Prior art keywords
- user group
- target
- user
- resource
- pushing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
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
Abstract
The application provides a resource pushing method and device, electronic equipment and a readable storage medium, and relates to the technical field of resource pushing. In the embodiment of the application, by pushing the target resource to the obtained first user group matched with the attribute of the target resource, a pushing result for pushing to the first user group can be determined after pushing, and according to the pushing result of the first user group, a click user group actually interested in the target resource can be determined from the first user group, and then the target user group similar to the historical behavior of the click user group is determined from the users of the monitoring information base, namely, more people interested in the target resource are expanded through the click user group, and the target resource is pushed to the target user group, so that the popularization rate of pushing the target resource is improved, and meanwhile, the accuracy of pushing the target resource is improved.
Description
Technical Field
The present application relates to the field of resource pushing technologies, and in particular, to a resource pushing method and apparatus, an electronic device, and a readable storage medium.
Background
Currently, before pushing a resource, a target group matched with the resource is usually selected for pushing, so as to improve the accuracy of resource pushing.
In the prior art, generally, a user tag matched with a resource is determined first, and then a crowd with the user tag is determined as a target crowd, wherein the user tag is marked according to the condition that each user clicks each resource all the time. However, even for the same resource, the attractiveness of the same user may be different at different times and with different creatives, and therefore, if the target group for pushing the resource is determined simply by the user tag, a situation that users who are not actually interested in the resource exist in the target group may occur, so that the accuracy of resource pushing is not high.
Disclosure of Invention
In view of this, an object of the present application is to provide a resource pushing method, a resource pushing device, an electronic device, and a readable storage medium, which can improve the popularization rate of pushing a target resource and improve the accuracy of pushing the target resource.
The application mainly comprises the following aspects:
in a first aspect, an embodiment of the present application provides a resource pushing method, where the resource pushing method includes:
acquiring a first user group matched with the attribute of the target resource;
pushing the target resource to each user in the first user group, and determining a pushing result corresponding to each user in the first user group after pushing; the pushing result comprises a result of clicking or exposing the target resource;
determining a clicking user group for clicking the target resource from the first user group according to the pushing result;
determining a target user group similar to the click user group from the users of a monitoring information base based on the historical behaviors of all the users in the click user group; the historical behaviors comprise behaviors that each resource in the monitoring information base is clicked or exposed;
and pushing the target resource to each user in the target user group.
In a possible implementation, the obtaining a first user group matching the attribute of the target resource includes:
determining a screening condition for screening the first user group according to the attribute of the target resource;
and screening the first user group meeting the screening condition from the users of the monitoring information base.
In a possible implementation manner, the determining, from the users in the monitoring information base, a target user group similar to the click user group based on the historical behaviors of the respective users in the click user group includes:
acquiring a second user group with monitoring information in a preset time period from the users of the monitoring information base;
determining a target user group similar to the click user group from the second user group according to the historical behaviors of all users in the second user group, the historical behaviors of all users in the click user group and a target probability model; the target probability model is used for calculating the probability of any user clicking the target resource.
In one possible embodiment, the target probability model is generated according to the following steps:
determining an exposure user group for exposing the target resource from the first user group according to the pushing result;
taking the behavior feature vector of each user in the clicking user group as a positive sample, and taking the behavior feature vector of each user in the exposing user group as a negative sample;
and training an initial probability model according to the positive sample and the negative sample to generate the trained target probability model.
In a possible implementation manner, the determining, according to the historical behaviors of the users in the second user group, the historical behaviors of the users in the click user group, and a target probability model, a target user group similar to the click user group from the second user group includes:
inputting the behavior feature vector of each user in the second user group into the target probability model, and outputting the probability of each user in the second user group clicking the target resource;
and determining the users in the second user group with the probability greater than or equal to a preset threshold value as the users in the target user group.
In one possible implementation, for each user's behavior feature vector, each element in the behavior feature vector represents a behavior of each user clicking or exposing a respective resource in the monitoring information base; the dimensionality number of the behavior feature vector is equal to the total number of the resources contained in the monitoring information base.
In a second aspect, an embodiment of the present application further provides a resource pushing apparatus, where the resource pushing apparatus includes:
the acquisition module is used for acquiring a first user group matched with the attribute of the target resource;
the pushing module is used for pushing the target resource to each user in the first user group acquired by the acquiring module, and determining a pushing result corresponding to each user in the first user group after pushing; the pushing result comprises a result of clicking or exposing the target resource;
the first determining module is used for determining a clicking user group for clicking the target resource from the first user group according to the pushing result obtained by the pushing module;
a second determining module, configured to determine, based on the historical behaviors of the users in the clicked user group determined by the first determining module, a target user group similar to the clicked user group from among the users in the monitoring information base; the historical behaviors comprise behaviors that each resource in the monitoring information base is clicked or exposed;
the pushing module is further configured to push the target resource to each user in the target user group determined by the second determining module.
In a possible implementation manner, the obtaining module is configured to obtain the first user group according to the following steps:
determining a screening condition for screening the first user group according to the attribute of the target resource;
and screening the first user group meeting the screening condition from the users of the monitoring information base.
In one possible implementation, the second determining module includes:
the acquisition unit is used for acquiring a second user group with monitoring information in a preset time period from the users of the monitoring information base;
a determining unit, configured to determine, according to a historical behavior of each user in the second user group, a historical behavior of each user in the click user group, and a target probability model, a target user group similar to the click user group from the second user group; the target probability model is used for calculating the probability of any user clicking the target resource.
In a possible embodiment, the resource pushing apparatus further includes a generation module; the generating module is configured to generate the target probability model according to the following steps:
determining an exposure user group for exposing the target resource from the first user group according to the pushing result;
taking the behavior feature vector of each user in the clicking user group as a positive sample, and taking the behavior feature vector of each user in the exposing user group as a negative sample;
and training an initial probability model according to the positive sample and the negative sample to generate the trained target probability model.
In a possible implementation manner, the determining unit is configured to determine the target user group according to the following steps:
inputting the behavior feature vector of each user in the second user group into the target probability model, and outputting the probability of each user in the second user group clicking the target resource;
and determining the users in the second user group with the probability greater than or equal to a preset threshold value as the users in the target user group.
In one possible implementation, for each user's behavior feature vector, each element in the behavior feature vector represents a behavior of each user clicking or exposing a respective resource in the monitoring information base; the dimensionality number of the behavior feature vector is equal to the total number of the resources contained in the monitoring information base.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device runs, the processor and the memory communicate with each other through the bus, and when the processor runs, the machine-readable instructions perform the steps of the resource pushing method according to the first aspect or any one of the possible implementation manners of the first aspect.
In a fourth aspect, this application provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method performs the steps of the resource pushing method described in the first aspect or any possible implementation manner of the first aspect.
In the embodiment of the application, by pushing the target resource to the obtained first user group matched with the attribute of the target resource, a pushing result for pushing to the first user group can be determined after pushing, and according to the pushing result of the first user group, a click user group actually interested in the target resource can be determined from the first user group, and then the target user group similar to the historical behavior of the click user group is determined from the users of the monitoring information base, namely, more people interested in the target resource are expanded through the click user group, and the target resource is pushed to the target user group, so that the popularization rate of pushing the target resource is improved, and meanwhile, the accuracy of pushing the target resource is improved.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are required to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained from the drawings without inventive effort.
Fig. 1 shows a flowchart of a resource pushing method provided in an embodiment of the present application;
fig. 2 shows one of the functional block diagrams of a resource pushing apparatus provided in the second embodiment of the present application;
fig. 3 is a functional block diagram of a second determining module in the resource pushing apparatus according to the second embodiment of the present application;
fig. 4 shows a second functional block diagram of a resource pushing apparatus according to a second embodiment of the present application;
fig. 5 shows a schematic structural diagram of an electronic device provided in the third embodiment of the present application.
Detailed Description
To make the purpose, technical solutions and advantages of the embodiments of the present application clearer, 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 should be understood that the drawings in the present application are for illustrative and descriptive purposes only and are not used to limit the scope of protection of the present application. Additionally, it should be understood that the schematic drawings are not necessarily drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flow diagrams may be performed out of order, and that steps without logical context may be performed in reverse order or concurrently. One skilled in the art, under the guidance of this application, may add one or more other operations to, or remove one or more operations from, the flowchart.
In addition, the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. The components of the embodiments of the present application, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present application, presented in the accompanying drawings, is not intended to limit the scope of the claimed application, but is merely representative of selected embodiments of the application. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application.
To enable those skilled in the art to utilize the present disclosure, the following embodiments are presented in conjunction with a specific application scenario "push resources," and it will be apparent to those skilled in the art that the general principles defined herein may be applied to other embodiments and application scenarios without departing from the spirit and scope of the present disclosure.
The method, apparatus, electronic device or computer-readable storage medium described in the embodiments of the present application may be applied to any scenario that requires resource pushing, and the embodiments of the present application do not limit a specific application scenario, and any scheme that uses the method and apparatus for resource pushing provided by the embodiments of the present application is within the scope of protection of the present application.
It should be noted that the target resource may be a video resource, an audio resource, an advertisement resource, and so on.
It is to be noted that, before the present application is proposed, in the existing scheme, generally, a user tag matching with a resource is determined first, and then a group with the user tag is determined as a target group, where the user tag is marked according to a condition that each user clicks each resource all the time. However, even for the same resource, the attractiveness of the same user may be different at different times and with different creatives, and therefore, if the target group for pushing the resource is determined simply by the user tag, a situation that users who are not actually interested in the resource exist in the target group may occur, so that the accuracy of resource pushing is not high.
In order to solve the problems, according to the method and the device, the target resource is pushed to the obtained first user group matched with the attribute of the target resource, the pushing result pushed to the first user group can be determined after pushing, the clicking user group actually interested in the target resource can be determined from the first user group according to the pushing result of the first user group, and then the target user group similar to the historical behavior of the clicking user group is determined from the users of the monitoring information base, namely more people interested in the target resource are expanded through the clicking user group, the target resource is pushed to the target user group, and the accuracy of pushing the target resource can be improved while the promotion rate of pushing the target resource is improved.
For the convenience of understanding of the present application, the technical solutions provided in the present application will be described in detail below with reference to specific embodiments.
Example one
Fig. 1 is a flowchart of a resource pushing method according to an embodiment of the present application. As shown in fig. 1, a resource pushing method provided in an embodiment of the present application includes the following steps:
s101: a first user group matching the attributes of the target resource is obtained.
In a specific implementation, a first user group matching the attribute of the target resource may be obtained from the monitoring information base, that is, a user group that may be interested in the target resource is obtained preliminarily. Here, the users in the first user group may be users with tags matching the attributes of the target resources, or users satisfying the screening conditions formulated according to the attributes of the target resources, where the tags of the users are labeled according to the user's past clicks on each resource, and the tags may be, for example, mother and baby tags, cosmetic tags, age tags, or the like.
In one example, if the target resource is milk powder, the users with mother-infant labels may be users in the first group of users, and women between 20 and 35 years of age may be users in the first group of users.
It should be noted that historical monitoring information of each resource clicked or exposed by each user is stored in the monitoring information base, specifically, when any resource is clicked or exposed by any user once, a piece of monitoring information is correspondingly generated and stored in the monitoring information base, where the monitoring information includes an identifier of the clicked or exposed resource, a user identifier of the clicked or exposed resource, a click identifier, and an exposure identifier.
Further, the step S101 of acquiring the first user group matched with the attribute of the target resource includes the following steps:
step 1011: and determining a screening condition for screening the first user group according to the attribute of the target resource.
In a specific implementation, a screening condition for screening out the first user group from the monitoring information base may be formulated according to an attribute of the target resource, where the attribute of the target resource may be understood as a property, a type, and the like of the target resource.
Step 1012: and screening the first user group meeting the screening condition from the users of the monitoring information base.
In specific implementation, after the screening condition is determined, a first user group meeting the screening condition can be screened from the monitoring information base, that is, users who may be interested in the target resource are found preliminarily.
S102: pushing the target resource to each user in the first user group, and determining a pushing result corresponding to each user in the first user group after pushing; the push result comprises a result of clicking or exposing the target resource.
In specific implementation, the target resource may be pushed to a preliminarily screened first user group which may be interested in the target resource, and after the target resource is pushed, the behavior of the first user group is monitored, so as to determine a pushing result of clicking or exposing the target resource by the user in the first user group, where clicking means that the user clicks the target resource, exposing means that the user does not click the target resource, and only views a page for pushing the target resource.
S103: and determining a clicking user group for clicking the target resource from the first user group according to the pushing result.
In specific implementation, after a pushing result of clicking or exposing the target resource by the user in the first user group is determined, a user group clicking the target resource is determined from the users in the first user group, that is, users who are not interested in the target resource in the first user group are filtered out, users who are actually interested in the target resource in the first user group are further determined, and the users are determined as the users in the clicking user group.
It should be noted that, in the prior art, users in the first user group are not further screened, and target resources are directly pushed to the users in the first user group, and users that do not actually interest the target resources exist in the first user group, so that the accuracy of pushing the target resources is not high.
S104: determining a target user group similar to the click user group from the users of a monitoring information base based on the historical behaviors of all the users in the click user group; the historical behaviors include behaviors of clicking or exposing each resource in the monitoring information base.
In specific implementation, after a click user group which is actually interested in a target resource in a first user group is determined, the click user group can be used for acquiring the target user group similar to the click user group from a monitoring information base, that is, more groups interested in the target resource can be expanded through the click user group, and specifically, the target user group similar to the historical behavior of the click user group can be acquired in the monitoring information base according to the behavior of clicking or exposing each resource of each user in the click user group.
It should be noted that, the historical behavior of each user in the clicked user group may be obtained respectively, where the historical behavior includes behavior of each resource clicked or exposed by each user, where different resources have different resource identifiers, and for each user in the clicked user group, multiple pieces of monitoring information corresponding to each user may be obtained in the monitoring information base according to the user identifier of each user, and the resource identifier of each resource clicked or exposed by each user is obtained from the multiple pieces of monitoring information, so as to determine the historical behavior of each user.
Further, in step S104, determining a target user group similar to the click user group from the users in the monitoring information base based on the historical behaviors of the respective users in the click user group, may include the following steps:
step 1041: and acquiring a second user group with monitoring information in a preset time period from the users of the monitoring information base.
In a specific implementation, by actually using a clicking user group interested in a target resource, a target user group similar to the clicking user group can be determined to expand more people interested in the target resource, specifically, a second user group which is relatively active in a preset time period can be obtained from users of a monitoring information base, where the active users can be understood as any one or more resources clicked or exposed in the preset time period, and then monitoring information of the active users can exist in the monitoring information base. Here, in consideration of timeliness, the preset time period is preferably a time period closer to the push time of the current target resource.
The preset time period may be determined according to actual requirements of the target resource owner, for example, if the target resource owner wants to promote the target resource to as many users as possible, the preset time period is set to be longer, and if the target resource owner considers factors such as promotion cost and promotion rate, the preset time period may be set by integrating various factors.
Step 1042: determining a target user group similar to the click user group from the second user group according to the historical behaviors of all users in the second user group, the historical behaviors of all users in the click user group and a target probability model; the target probability model is used for calculating the probability of any user clicking the target resource.
In a specific implementation, after the second user group is obtained, a target user group similar to the clicked user group in the second user group may be determined according to similarity between the historical behavior of each user in the second user group and the historical behavior of each user in the clicked user group, so as to achieve a purpose of expanding more people interested in the target resource, and specifically, the target user group similar to the clicked user group may be calculated by using a target probability model.
Further, the target probability model is generated according to the following steps:
determining an exposure user group for exposing the target resource from the first user group according to the pushing result; taking the behavior feature vector of each user in the clicking user group as a positive sample, and taking the behavior feature vector of each user in the exposing user group as a negative sample; and training an initial probability model according to the positive sample and the negative sample to generate the trained target probability model.
In specific implementation, after a pushing result of clicking or exposing a target resource by a user in a first user group is determined, a crowd exposing the target resource is determined from the users in the first user group, that is, users who are not actually interested in the target resource are found from the first user group, and then a behavior feature vector of each user in the exposed user group is used as a negative sample, and a behavior feature vector of each user in the clicked user group is used as a positive sample, and then an initial probability model is trained through the positive sample and the negative sample, so as to generate a trained target probability model.
Here, for each user's behavior feature vector, each element in the behavior feature vector represents a behavior of each user clicking or exposing a respective resource in the monitoring information base; the dimensionality number of the behavior feature vector is equal to the total number of the resources contained in the monitoring information base.
Specifically, the historical click and exposure monitoring information of each user in the exposure user group and the historical click and exposure monitoring information of each user in the click user group can be obtained from the monitoring information base, the resource identifiers of each resource are extracted from the monitoring information, the total number of each resource identifier is counted, the total number is determined as the dimension number of the behavior characteristic vector, each element of the behavior characteristic vector is represented by the behavior of clicking or exposing each resource, then the behavior characteristic vectors of each user in the click user group and the exposure user group are respectively calculated, the user in the click user group and the user in the exposure user group are respectively marked by two different labels, and further, by clicking the behavior characteristic vector of each user in the user group, the behavior characteristic vector of each user in the exposure user group and the labels, and training the initial probability model to obtain a trained target probability model. The target probability model may be a neural network model.
In one example, the degree of dimension of the behavior feature vector is 5, 5 resources are respectively resource a, resource b, resource c, resource d, and resource e, the user a clicks on the resource a, resource b, and resource d, the user a exposes the resource c and resource e, the click is represented by 1, the exposure is represented by 0, and then the behavior feature vector of the user a is (11010).
Further, in step 1042, a target user group similar to the click user group is determined from the second user group according to the historical behaviors of the users in the second user group, the historical behaviors of the users in the click user group, and a target probability model; the target probability model is used for calculating the probability of any user clicking the target resource, and comprises the following steps:
inputting the behavior feature vector of each user in the second user group into the target probability model, and outputting the probability of each user in the second user group clicking the target resource; and determining the users in the second user group with the probability greater than or equal to a preset threshold value as the users in the target user group.
In specific implementation, after a target probability model is obtained according to training of an exposure user group and a click user group, for each user in a second user group, a behavior feature vector of each user is input into the target probability model, the probability of each user clicking a target resource is output, then the users in the second user group with the probability greater than or equal to a preset threshold are determined as the target user group, and more people interested in the target resource, namely the target user group, are expanded according to the click user group. Here, the preset threshold may be determined according to a probability obtained by inputting the positive sample into the target probability model, for example, the probability corresponding to the positive sample is 1, the probability corresponding to the negative sample is 0, and the preset threshold may be set to a value from 0.5 to 1, so as to ensure that the determined users in the target user group are more similar to the users in the click user group rather than similar to the users in the exposure user group according to the historical behavior, that is, it is ensured that the users in the target user group and the users in the click user group are the same and are interested in the target resource.
S105: and pushing the target resource to each user in the target user group.
In specific implementation, according to the confirmed click user group actually interested in the target resource, more people interested in the target resource, namely the target user group, can be expanded, and then the target resource can be pushed to the target user group, so that the accuracy of pushing the target resource can be improved while the promotion rate of pushing the target resource is improved, and due to the addition of the target resource pushing object, the effect of pushing the target resource can be further improved, such as the increase of the click rate, the increase of the purchase rate, the increase of the attention and the like.
It should be noted that, in general, target resources all have a push cycle, the cycle is short and several days, the cycle is long and several months, even if the same resource is used, the attractiveness to the same user may be different at different times and with different creatives, and therefore, like in the prior art, a target crowd who pushes the resource is determined simply by a user tag, a situation that a user who does not actually interest the resource exists in the target crowd may occur, so that the accuracy of resource push is not high. According to the method and the device, historical behaviors of the user are utilized, more target user groups interested in the target resource are expanded through the click user group, specifically, the click user group can be determined at the initial stage of pushing the target resource, the target user group is further determined according to the click user group, the target resource can be pushed to the target user group directly during subsequent pushing, the target user group can be updated every preset time period according to the click condition of the target user group, the updated target user group is obtained, and the target resource is pushed to the updated target user group, so that the accuracy of pushing the target resource can be further improved.
In the embodiment of the application, by pushing the target resource to the obtained first user group matched with the attribute of the target resource, a pushing result for pushing to the first user group can be determined after pushing, and according to the pushing result of the first user group, a click user group actually interested in the target resource can be determined from the first user group, so that the target user group similar to the historical behavior of the click user group is determined from the users of the monitoring information base, that is, more people interested in the target resource are expanded by the click user group, and the target resource is pushed to the target user group, so that the popularization rate for pushing the target resource is improved, and the accuracy for pushing the target resource is improved.
Example two
Based on the same application concept, a resource pushing device corresponding to the resource pushing method provided in the first embodiment is also provided in the second embodiment of the present application, and since the principle of solving the problem of the device in the embodiment of the present application is similar to that of the resource pushing method in the first embodiment of the present application, the implementation of the device may refer to the implementation of the method, and repeated details are not described herein.
Referring to fig. 2 to 4, fig. 2 shows one of functional block diagrams of a resource pushing apparatus provided in the second embodiment of the present application, fig. 3 shows a functional block diagram of a second determining module in the resource pushing apparatus provided in the second embodiment of the present application, and fig. 4 shows a second functional block diagram of a resource pushing apparatus provided in the second embodiment of the present application.
As shown in fig. 2 and fig. 4, the resource pushing apparatus 200 includes:
an obtaining module 210, configured to obtain a first user group matched with an attribute of a target resource;
a pushing module 220, configured to push the target resource to each user in the first user group acquired by the acquiring module 210, and determine a pushing result corresponding to each user in the first user group after pushing; the pushing result comprises a result of clicking or exposing the target resource;
a first determining module 230, configured to determine, according to the pushing result obtained by the pushing module 220, a click user group for clicking the target resource from the first user group;
a second determining module 240, configured to determine, based on the historical behaviors of the users in the clicked user group determined by the first determining module 230, a target user group similar to the clicked user group from among the users in the monitoring information base; the historical behaviors comprise behaviors that each resource in the monitoring information base is clicked or exposed;
the pushing module 220 is further configured to push the target resource to each user in the target user group determined by the second determining module 240.
In a possible implementation, as shown in fig. 2 and fig. 4, the obtaining module 210 is configured to obtain the first user group according to the following steps:
determining a screening condition for screening the first user group according to the attribute of the target resource;
and screening the first user group meeting the screening condition from the users of the monitoring information base.
In one possible implementation, as shown in fig. 3, the second determining module 240 includes:
an obtaining unit 242, configured to obtain, from the users in the monitoring information base, a second user group in which monitoring information exists within a preset time period;
a determining unit 244, configured to determine, according to the historical behaviors of the users in the second user group, the historical behaviors of the users in the click user group, and a target probability model, a target user group similar to the click user group from the second user group; the target probability model is used for calculating the probability of any user clicking the target resource.
In a possible embodiment, as shown in fig. 4, the resource pushing apparatus 200 further includes a generating module 250; the generating module 250 is configured to generate the target probability model according to the following steps:
determining an exposure user group for exposing the target resource from the first user group according to the pushing result;
taking the behavior feature vector of each user in the clicking user group as a positive sample, and taking the behavior feature vector of each user in the exposing user group as a negative sample;
and training an initial probability model according to the positive sample and the negative sample to generate the trained target probability model.
In a possible implementation, as shown in fig. 3, the determining unit 244 is configured to determine the target user group according to the following steps:
inputting the behavior feature vector of each user in the second user group into the target probability model, and outputting the probability of each user in the second user group clicking the target resource;
and determining the users in the second user group with the probability greater than or equal to a preset threshold value as the users in the target user group.
In one possible implementation, for each user's behavior feature vector, each element in the behavior feature vector represents a behavior of each user clicking or exposing a respective resource in the monitoring information base; the dimensionality number of the behavior feature vector is equal to the total number of the resources contained in the monitoring information base.
In the embodiment of the present application, by pushing the target resource to the first user group matching the attribute of the target resource acquired by the acquisition module 210, a push result of pushing to the first user group may be determined after pushing by the push module 220, and according to the push result of the first user group, a group of clicking users actually interested in the target resource may be determined from the first group of users by the first determining module 230, further, from the users of the monitoring information base, the target user group similar to the historical behavior of the clicking user group is determined by the second determination module 240, that is, more people interested in the target resource are expanded by clicking the user group, and the target resource is pushed to the target user group by the pushing module 220, the accuracy of pushing the target resource can be improved while the promotion rate of pushing the target resource is improved.
EXAMPLE III
Based on the same application concept, referring to fig. 5, a schematic structural diagram of an electronic device 500 provided in the third embodiment of the present application includes: a processor 510, a memory 520, and a bus 530, wherein the memory 520 stores machine-readable instructions executable by the processor 510, and when the electronic device 500 is running, the processor 510 and the memory 520 communicate via the bus 530, and the machine-readable instructions are executed by the processor 510 to perform the steps of the resource pushing method according to any one of the embodiments.
In particular, the machine readable instructions, when executed by the processor 510, may perform the following:
acquiring a first user group matched with the attribute of the target resource;
pushing the target resource to each user in the first user group, and determining a pushing result corresponding to each user in the first user group after pushing; the pushing result comprises a result of clicking or exposing the target resource;
determining a clicking user group for clicking the target resource from the first user group according to the pushing result;
determining a target user group similar to the click user group from the users of a monitoring information base based on the historical behaviors of all the users in the click user group; the historical behaviors comprise behaviors that each resource in the monitoring information base is clicked or exposed;
and pushing the target resource to each user in the target user group.
In the embodiment of the application, by pushing the target resource to the obtained first user group matched with the attribute of the target resource, a pushing result for pushing to the first user group can be determined after pushing, and according to the pushing result of the first user group, a click user group actually interested in the target resource can be determined from the first user group, and then the target user group similar to the historical behavior of the click user group is determined from the users of the monitoring information base, namely, more people interested in the target resource are expanded through the click user group, and the target resource is pushed to the target user group, so that the popularization rate of pushing the target resource is improved, and meanwhile, the accuracy of pushing the target resource is improved.
Example four
Based on the same application concept, a fourth embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the resource pushing method provided in the first embodiment are executed.
Specifically, the storage medium may be a general storage medium, such as a mobile disk, a hard disk, or the like, and when a computer program on the storage medium is executed, the resource pushing method may be executed, and by clicking a user group to expand more people interested in the target resource and push the target resource to the target user group, the popularization rate of pushing the target resource may be improved, and at the same time, the accuracy of pushing the target resource may be improved.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical 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 functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solutions of the present application may be embodied in the form of a software product, which is stored in a storage medium and includes 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 methods described in the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (5)
1. A resource pushing method is characterized by comprising the following steps:
determining a screening condition for screening the first user group according to the attribute of the target resource;
screening out the first user group meeting the screening condition from users in a monitoring information base;
pushing the target resource to each user in the first user group, and determining a pushing result corresponding to each user in the first user group after pushing; the pushing result comprises a result of clicking or exposing the target resource;
determining a clicking user group for clicking the target resource from the first user group according to the pushing result;
acquiring a second user group with monitoring information in a preset time period from the users of the monitoring information base;
determining a target user group similar to the click user group from the second user group according to the historical behaviors of all users in the second user group, the historical behaviors of all users in the click user group and a target probability model; the target probability model is used for calculating the probability of any user clicking the target resource; the historical behaviors comprise behaviors that each resource in the monitoring information base is clicked or exposed; the target probability model is generated by:
determining an exposure user group for exposing the target resource from the first user group according to the pushing result;
taking the behavior feature vector of each user in the clicking user group as a positive sample, and taking the behavior feature vector of each user in the exposing user group as a negative sample; for the behavior feature vector of each user, each element in the behavior feature vector represents the behavior of each user in clicking or exposing each resource in the monitoring information base; the dimensionality number of the behavior feature vector is equal to the total number of all resources contained in the monitoring information base;
training an initial probability model according to the positive sample and the negative sample to generate the trained target probability model;
and pushing the target resource to each user in the target user group.
2. The resource pushing method according to claim 1, wherein the determining, according to the historical behaviors of the users in the second user group, the historical behaviors of the users in the click user group, and a target probability model, a target user group similar to the click user group from the second user group comprises:
inputting the behavior feature vector of each user in the second user group into the target probability model, and outputting the probability of each user in the second user group clicking the target resource;
and determining the users in the second user group with the probability greater than or equal to a preset threshold value as the users in the target user group.
3. A resource pushing device, characterized in that the resource pushing device comprises:
the acquisition module is used for determining a screening condition for screening the first user group according to the attribute of the target resource; the first user group is also used for screening out the first user group meeting the screening condition from the users of the monitoring information base;
the pushing module is used for pushing the target resource to each user in the first user group acquired by the acquiring module, and determining a pushing result corresponding to each user in the first user group after pushing; the pushing result comprises a result of clicking or exposing the target resource;
the first determining module is used for determining a clicking user group for clicking the target resource from the first user group according to the pushing result obtained by the pushing module;
the second determining module is used for acquiring a second user group with monitoring information in a preset time period from the users of the monitoring information base; determining a target user group similar to the click user group from the second user group according to the historical behaviors of all users in the second user group, the historical behaviors of all users in the click user group and a target probability model; the target probability model is used for calculating the probability of any user clicking the target resource; the historical behaviors comprise behaviors that each resource in the monitoring information base is clicked or exposed; the target probability model is generated by: determining an exposure user group for exposing the target resource from the first user group according to the pushing result; taking the behavior feature vector of each user in the clicking user group as a positive sample, and taking the behavior feature vector of each user in the exposing user group as a negative sample; for the behavior feature vector of each user, each element in the behavior feature vector represents the behavior of each user in clicking or exposing each resource in the monitoring information base; the dimensionality number of the behavior feature vector is equal to the total number of all resources contained in the monitoring information base;
training an initial probability model according to the positive sample and the negative sample to generate the trained target probability model;
the pushing module is further configured to push the target resource to each user in the target user group determined by the second determining module.
4. An electronic device, comprising: processor, memory and bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the electronic device is running, the machine-readable instructions being executed by the processor to perform the steps of the resource pushing method according to any one of claims 1 to 2.
5. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, performs the steps of the resource pushing method according to any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910787820.2A CN110472154B (en) | 2019-08-26 | 2019-08-26 | Resource pushing method and device, electronic equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910787820.2A CN110472154B (en) | 2019-08-26 | 2019-08-26 | Resource pushing method and device, electronic equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110472154A CN110472154A (en) | 2019-11-19 |
| CN110472154B true CN110472154B (en) | 2022-03-29 |
Family
ID=68513760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910787820.2A Active CN110472154B (en) | 2019-08-26 | 2019-08-26 | Resource pushing method and device, electronic equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110472154B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110992089B (en) * | 2019-11-25 | 2023-08-29 | 秒针信息技术有限公司 | Traffic sharing method and device, electronic equipment and readable storage medium |
| CN110968802B (en) * | 2019-12-04 | 2023-05-05 | 上海风秩科技有限公司 | Analysis method and analysis device for user characteristics and readable storage medium |
| CN110929018B (en) * | 2019-12-04 | 2023-03-21 | Oppo（重庆）智能科技有限公司 | Text processing method and device, storage medium and electronic equipment |
| CN111127179B (en) * | 2019-12-12 | 2023-08-29 | 恩亿科(北京)数据科技有限公司 | Information pushing method, device, computer equipment and storage medium |
| CN111104597A (en) * | 2019-12-19 | 2020-05-05 | 秒针信息技术有限公司 | Screening method and screening device for resource delivery equipment and readable storage medium |
| CN111901411A (en) * | 2020-07-24 | 2020-11-06 | 北京字节跳动网络技术有限公司 | Method and device for pushing information |
| CN114666402A (en) * | 2020-12-23 | 2022-06-24 | 顺丰科技有限公司 | Resource information pushing method and device, computer equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106055657A (en) * | 2016-06-03 | 2016-10-26 | 北京网智天元科技股份有限公司 | Evaluation system for film viewing index of specific population |
| CN107784095A (en) * | 2017-10-18 | 2018-03-09 | 国网内蒙古东部电力有限公司 | A kind of education resource auto recommending method based on mobile learning |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8266226B2 (en) * | 2009-06-26 | 2012-09-11 | International Business Machines Corporation | System and method to enhance user presence management to enable the federation of rich media sessions |
| CN103019550B (en) * | 2012-12-07 | 2015-08-26 | 东软集团股份有限公司 | The real-time exhibiting method of content association and system |
| CN103902678A (en) * | 2014-03-21 | 2014-07-02 | 百度在线网络技术（北京）有限公司 | Search recommendation method and device |
| CN109325883A (en) * | 2017-07-31 | 2019-02-12 | 深圳市珍爱网信息技术有限公司 | A kind of recommended method and device of bi-directional matching |
| CN108171267B (en) * | 2017-12-28 | 2022-03-22 | 阿里巴巴（中国）有限公司 | User group division method and device and message pushing method and device |
| CN108491529B (en) * | 2018-03-28 | 2021-11-16 | 百度在线网络技术（北京）有限公司 | Information recommendation method and device |
-
2019
- 2019-08-26 CN CN201910787820.2A patent/CN110472154B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106055657A (en) * | 2016-06-03 | 2016-10-26 | 北京网智天元科技股份有限公司 | Evaluation system for film viewing index of specific population |
| CN107784095A (en) * | 2017-10-18 | 2018-03-09 | 国网内蒙古东部电力有限公司 | A kind of education resource auto recommending method based on mobile learning |
Non-Patent Citations (3)
| Title |
|---|
| Lightness: A Function-Virtualizable Software Defined Data Center Network With All-Optical Circuit/Packet Switching;George M. Saridis;《Journal of Lightwave Technology》;20151217;第1618-1627页 * |
| 互联网信息资源用户获取优化推送仿真研究;崔艳萍等;《计算机仿真》;20170715(第07期);第54-56页 * |
| 基于复杂网络社团结构的高校图书馆个性化推送服务;董娟;《中国优秀博硕士学位论文全文数据库(硕士)》;20121015;第Ⅰ143-53页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110472154A (en) | 2019-11-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110472154B (en) | Resource pushing method and device, electronic equipment and readable storage medium | |
| CN105427129B (en) | Information delivery method and system | |
| CN108733706B (en) | Method and device for generating heat information | |
| CN111190939A (en) | User portrait construction method and device | |
| CN108805598B (en) | Similarity information determination method, server and computer-readable storage medium | |
| CN108269122B (en) | Advertisement similarity processing method and device | |
| CN104951544A (en) | User data processing method and system and method and system for providing user data | |
| CN110543603B (en) | Collaborative filtering recommendation method, device, equipment and medium based on user behaviors | |
| CN111090807A (en) | Knowledge graph-based user identification method and device | |
| CN109598171B (en) | Data processing method, device and system based on two-dimensional code | |
| CN113379449B (en) | Multimedia resource recall method and device, electronic equipment and storage medium | |
| CN104951807A (en) | Stock market emotion determining method and device | |
| CN111104590A (en) | Information recommendation method, device, medium and electronic equipment | |
| CN111078742B (en) | User classification model training method, user classification method and device | |
| CN111160638B (en) | Conversion estimation method and device | |
| CN111242658A (en) | Information sharing reward method and device and computer readable storage medium | |
| CN111787042B (en) | Method and device for pushing information | |
| CN112785069A (en) | Prediction method and device for terminal equipment changing machine, storage medium and electronic equipment | |
| CN112561636A (en) | Recommendation method, recommendation device, terminal equipment and medium | |
| CN111667018A (en) | Object clustering method and device, computer readable medium and electronic equipment | |
| CN110210885B (en) | Method, device, equipment and readable storage medium for mining potential clients | |
| CN111768218A (en) | Method and device for processing user interaction information | |
| CN111582901A (en) | Method, device and system for quantizing display link effect and storage medium | |
| CN111382343B (en) | Label system generation method and device | |
| CN113807436A (en) | User mining method and device, computer equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |