CN111143608A

CN111143608A - Information pushing method and device, electronic equipment and storage medium

Info

Publication number: CN111143608A
Application number: CN201911185792.3A
Authority: CN
Inventors: 白明
Original assignee: Reach Best Technology Co Ltd
Current assignee: Reach Best Technology Co Ltd; Beijing Dajia Internet Information Technology Co Ltd
Priority date: 2019-11-27
Filing date: 2019-11-27
Publication date: 2020-05-12

Abstract

The disclosure relates to a method, a device, an electronic device and a storage medium for pushing information, wherein the method comprises the following steps: acquiring historical information of works issued by a first account, wherein at least time information of works issued by the first account in a historical manner is recorded in the historical information; predicting release information of the work released by the first account at least according to the time information of the work released by the first account in history, wherein the release information is used for indicating the release time of the first account for releasing the new work; and generating a notice carrying the release information, and sending the notice to a second account before the release time. According to the method and the device, the release time of the updated works is predicted according to the time information of the historical release works, and the release time is informed to the consumers who like the works in advance, namely before the authors update the works, the consumers can know the dynamic state of the updated works of the accounts concerned by the consumers in advance, so that the accuracy of learning the update information of the works by the users is improved, the requirements of different users are better met, and the satisfaction of each user is improved.

Description

Information pushing method and device, electronic equipment and storage medium

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to an information pushing method and apparatus, an electronic device, and a storage medium.

Background

In the related art, a video website platform or a video APP generally provides thousands of video contents for a user to watch, and a new video with huge data appears every day. In the face of such a huge amount of information, for some users (i.e., consumers), it is possible to enjoy the works distributed (or produced) by only a few authors (i.e., producers or video distributors), and to view the works distributed by the favorite authors in two ways:

one is that the user actively watches the favorite author's updated work on a regular basis, for example, the user finds that some authors update the work every friday morning, and the user can watch the author's work after the author fixes the update time; for the situation that the author is not known when the author updates, the user needs to go to the platform from time to check whether the favorite author has works to be updated or not;

alternatively, the user may subscribe to his favorite works through the subscription button, and if the author publishes a new work, the video platform sends a notification to the user, and after the user sees the notification, the user may enter the video platform to view the works updated by the author.

In both ways, the system pushes the message of the work update to the user after the author updates the work. That is, the user cannot accurately know when the author updates the work of interest before the author updates the work, thereby reducing the accuracy rate at which the user cannot know the update information of the work in advance.

Disclosure of Invention

The disclosure provides an information pushing method, an information pushing device, electronic equipment and a storage medium, so as to solve at least the technical problem that in the related art, a user can only know whether an author updates a work by checking or subscribing, and cannot know in advance when the author updates the work, so that the accuracy rate of obtaining update information of the work by the user is low. The technical scheme of the disclosure is as follows:

according to a first aspect of the embodiments of the present disclosure, there is provided an information pushing method, including:

acquiring historical information of works issued by a first account, wherein at least time information of works issued by the first account in a historical manner is recorded in the historical information;

predicting release information of the work released by the first account at least according to the time information of the work released by the first account in history, wherein the release information is used for indicating the release time of the first account for releasing the new work;

and generating a notice carrying the release information, and sending the notice to a second account before the release time.

The predicting the release information of the works released by the first account at least according to the time information of the works released by the first account in history comprises the following steps:

at least carrying out vector conversion on the time information of the works which are historically issued by the first account to obtain the characteristic information of different types of works issued by the first account;

and inputting the characteristic information of different types of works issued by the first account into a set model for learning, and predicting the issuing information of the works issued by the first account.

Optionally, the feature information of different types of works issued by the first account is input into a set model for learning, and predicting the issue information of the works issued by the first account includes:

carrying out classification calculation on the characteristic information of different kinds of works issued by the first account through a plurality of fully-connected calculation units in a convolutional neural network to obtain a classification calculation result;

mapping the classification calculation result to a sample mark space layer to obtain a plurality of corresponding scalars;

and inputting the scalars into a computing unit layer in the convolutional neural network for mapping to obtain the release information of the first account user release work.

Optionally, the release information includes at least one of:

a probability that the first account will release the work within a future time period;

the first account may be a probability of future release of each type of work.

Optionally, the history information further includes at least one of the following:

account information for the first account;

the association information of the first account includes account information of a third account having an association relationship with the first account and cross information of the first account and the third account, and the association relationship includes at least one of: the interaction relationship exists among the accounts, and the account attributes have commonality;

wherein the account information includes at least one of: the static information of the corresponding account, the historical behavior information of the corresponding account and the information of the corresponding account for releasing the historical works.

According to a second aspect of the embodiments of the present disclosure, there is provided an information pushing apparatus including:

the acquisition module is configured to execute acquisition of historical information of a work released by a first account, wherein at least time information of the work released by the first account in history is recorded in the historical information;

the prediction module is configured to predict the publishing information of the first account publishing works at least according to the time information of the first account publishing works historically, wherein the publishing information is used for indicating the publishing time of the first account publishing new works;

the generating module is configured to execute generation of the notification carrying the release information;

a sending module configured to execute sending the notification generated by the generating module to a second account before the release time.

Optionally, the prediction module includes:

the conversion module is configured to perform vector conversion on at least time information of the works which are historically issued by the first account, so as to obtain characteristic information of different kinds of works issued by the first account;

and the release information prediction module is configured to execute learning by inputting the time characteristic information into a set model, and predict release information of the first account release work.

Optionally, the release information prediction module includes:

the calculation module is configured to perform classification calculation on the feature information of different types of works issued by the first account through a plurality of fully-connected calculation units in a convolutional neural network to obtain a classification calculation result;

a first mapping module configured to perform mapping of the classification computation results to a sample label space layer, resulting in a corresponding plurality of scalars;

and the second mapping module is configured to execute the mapping processing of inputting the scalars into the computing unit layer in the convolutional neural network to obtain the release information of the first account user release work.

Optionally, the release information predicted by the release information prediction module includes at least one of:

the first account may be a probability of future release of each type of work.

Optionally, the history information acquired by the acquiring module at least includes one of the following:

account information for the first account;

the association information of the first account includes account information of a third account having an association relationship with the first account and cross information of the first account and the third account, and the association relationship includes at least one of the following: the interaction relationship exists among the accounts, and the account attributes have commonality;

According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the information pushing method as described above.

According to a fourth aspect of the embodiments of the present disclosure, there is provided a storage medium, wherein instructions of the storage medium, when executed by a processor of an electronic device, enable the electronic device to execute the method for pushing information as described above.

According to a fifth aspect of the embodiments of the present disclosure, there is provided a computer program product, wherein when the instructions in the computer program product are executed by a processor of an electronic device, the electronic device is caused to execute the method for pushing information as described above.

The technical scheme provided by the embodiment of the disclosure at least has the following beneficial effects: in the embodiment of the disclosure, historical information of works issued by a first account is obtained, wherein at least time information of works issued by the first account in history is recorded in the historical information; predicting release information of the work released by the first account at least according to the time information of the work released by the first account in history, wherein the release information is used for indicating the release time of the first account for releasing the new work; and generating a notice carrying the release information, and sending the notice to a second account before the release time. That is to say, in the embodiment of the present disclosure, the release time of the author's updated work is predicted according to the time information of the historically released work in the historical information that the author released before, and the consumer who likes the work is notified in advance by the release time of the updated work, that is, before the author updates the work, the consumer can know the dynamic state of the updated work of the account concerned by the consumer in advance, which not only improves the accuracy of knowing the updated work information by the user, but also better meets the requirements of different users, thereby improving the satisfaction of each user.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.

Fig. 1 is a flowchart illustrating a method for pushing information according to an exemplary embodiment.

Fig. 1A is a block diagram illustrating a prediction of a probability that a first account will update a different video, according to an example embodiment.

Fig. 2 is a block diagram illustrating an apparatus for pushing information according to an exemplary embodiment.

Fig. 3 is another block diagram illustrating an apparatus for pushing information according to an exemplary embodiment.

FIG. 3A is a block diagram illustrating a published information prediction module in accordance with an example embodiment.

FIG. 4 is a block diagram illustrating an electronic device in accordance with an example embodiment.

FIG. 5 is another block diagram illustrating an electronic device in accordance with an exemplary embodiment.

Detailed Description

In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.

Fig. 1 is a flowchart illustrating an information push method according to an exemplary embodiment, where the information push method is used in a mobile terminal, as shown in fig. 1, and includes the following steps:

in step 101, historical information of a work released by a first account is obtained, wherein at least time information of the work released by the first account in the historical information is recorded.

In step 102, predicting release information of the work released by the first account according to at least time information of the work released by the first account in history, wherein the release information is used for indicating the release time of the first account for releasing a new work;

in step 103, a notification carrying the release information is generated, and the notification is sent to a second account before the release time.

The information pushing method shown in the present exemplary embodiment may be applied to a mobile terminal, a server, a client, and the like, and is not limited herein, and the implementation device may be an electronic device such as a smart phone, a notebook computer, and a tablet computer, and is not limited herein.

For ease of description, in embodiments of the present disclosure, publication or update of a work (e.g., video, short video, micro-video, etc.) generally involves:

the first account, i.e. a unique account registered by a producer (user), or one of a plurality of accounts registered by the producer, i.e. an author who issues a work, or a user who issues or updates a work, there are many users who issue or update the work;

there are also a number of second accounts, i.e., consumers or consuming users, i.e., users who view or subscribe to the work (users), for which users who view or subscribe to the work;

a work (i.e., the content of the work), i.e., a medium such as a video or short video or article, etc.

The following describes in detail specific implementation steps of the information push method provided by the embodiment of the present disclosure with reference to fig. 1.

Firstly, executing step 101, obtaining historical information of works released by a first account, wherein at least time information of works released by the first account in history is recorded in the historical information;

in this step, at least time information of a work released by a first account in history is recorded in the history information, and of course, the history information may include at least one of the following: the account information of the first account may include, for example, user characteristics, historical behavior information, environmental factor information, geographic location information, work content characteristic information, and the like; the association information of the first account, wherein the association information may include: account information of a third account having an association with the first account (e.g., an account having a competitive relationship), and cross information of the first account and the third account, the association including at least one of: the interaction relationship exists among the accounts, and the account attributes have commonality; wherein the account information includes at least one of: the static information of the corresponding account, the historical behavior information of the corresponding account and the information of the corresponding account for releasing the historical works. For example, the status information of the user of the third account related to the first account publishing the work, the historical behavior of the author who has an association relationship (e.g., has a competition relationship) with the first account publishing the work, and the statistical information of the consumption of the author who has an association relationship with the first account publishing the work, etc.

That is, the history information may be influenced by factors such as festival, hot event, weather, natural law, emergency, personal physiological condition, etc. for any author (i.e. original User, referred to as the first account or the like in this disclosure), updating the work (e.g. video, i.e. User Generated Content) on the User Generated Content (UGC) platform. Accordingly, the present disclosure refers to such information that may affect the author's updated work collectively as historical information.

The user may have one account or a plurality of accounts, and the first account in the present disclosure may be the only account registered by the user or one of a plurality of accounts registered by the user. The user characteristics of the first account may include, but are not limited to: the ID of the first account, i.e. author ID (author ID), is a number used to identify different authors, age, gender, residential area, income ability, occupation, social data, set of APPs installed on the device, type of connected WIFI, device model and price, employment status, etc. Of course, the user characteristics of the first account may also be referred to as static characteristics of the first account.

The historical behavior information may include, but is not limited to: on different platforms, users (authors) publish historical behaviors of categories, time information and the like of works (such as videos, articles and the like), and the record forms of the historical behaviors can be as follows: list (list) or preset (set) form, etc. Wherein a user can produce (i.e., produce or generate) multiple types of video, such as landscape, gourmet, chapters, etc.

The environmental factor information may include, but is not limited to: hot spot events, emergency events, weather information, whether the event is a holiday, surrounding information, characteristics of a mobile phone used by a user and the like.

The content characteristic information of the work may include, but is not limited to: video subject, video content, match drawings, match words, match music, landscape, gourmet, paragraph, etc.

The status information of the user associated with the first account publishing the work may include, but is not limited to: the characteristics of the work released by the author who has an association relationship with the author (e.g., has a competition relationship, and the definition of competition is to seize time or fans of consumers), such as the release rule and the like; it may also be a feature that breaks historical behavior data: such as new functions published on the platform, etc. Historical work data and statistics of the first account may also be consumed.

In this step, the history information of all works issued by the first account may be obtained through the ID number of the first account, the user network name, or the pen name, and the specific obtaining process is well known and will not be described herein.

Then, step 102 is executed, and release information of the work released by the first account is predicted at least according to the time information of the work released by the first account in history, wherein the release information is used for indicating the release time of the first account for releasing the new work.

The method for predicting the release information of the work released by the first account comprises the following steps:

1) at least carrying out vector conversion on the time information of the works which are historically issued by the first account to obtain the characteristic information of different types of works issued by the first account;

in this step, the mobile device or the client may perform vector conversion on at least the history information to obtain feature information of different types of works issued by the first account, and the method specifically includes:

vector conversion is carried out on time information of the works which are historically issued by the first account within set time at least to obtain the rule that the first account issues different kinds of works; and then determining that the first account issues the characteristic information of different types of works according to the rule. Wherein the characteristic information at least comprises:

the static information characteristic of the first account, the historical behavior information characteristic of the first account, the static information characteristic of a third account clicking or subscribing (i.e. consuming) to the first account, the historical behavior information characteristic of a third account clicking or subscribing (i.e. consuming) to the first account, the cross characteristic, the environment information, the content characteristic and the like of the first account and the third account. The specific analysis process is well known and will not be described herein.

2) And inputting the characteristic information of different types of works issued by the first account into a set model for learning, and predicting the issuing information of the works issued by the first account.

In the step, the mobile equipment or the client firstly carries out classification calculation on the characteristic information of different types of works issued by the first account through a plurality of fully connected calculation units in the convolutional neural network to obtain a classification calculation result; then, mapping the classification calculation result to a sample mark space layer to obtain a plurality of corresponding scalars; and finally, inputting the scalars into a calculation unit layer in the convolutional neural network for mapping to obtain the release information of the first account user release work.

For ease of understanding, the use of a machine learning algorithm to predict the probability of a first account updating (or publishing) a different video is described below in a specific example. FIG. 1A, as shown in FIG. 1A, is a block diagram illustrating a method of predicting a probability that a first account will update different videos, according to an example embodiment; in the figure, a neural network model is taken as an example, a supervised learning mode is adopted for training the neural network model, and the adopted training data (i.e. samples) are taken as an example of a set of all feature data such as a work published by a first account in history and a work consumed by a second account of the first account. Each sample contains 2 sections for input and output. The definition of the inputs and outputs of the neural network model is described below;

wherein, taking 7 parts as an example, F1 represents the static information characteristic of a first account, F2 represents the historical behavior information characteristic of the first account, F3 represents the static information characteristic of a second account consuming the first account, F4 represents the historical behavior information characteristic of the second account consuming the first account, F5 represents the intersection characteristic of the first account and the second account, F6 represents the environment characteristic, and F7 represents the content characteristic.

The "output" of the neural network model refers to that there are different video types of K, video type 1, video type 2, and video type K …. Assuming that the video type of a certain sample is i, the corresponding output value is "video type i", namely, the one-hot vector of K dimension is represented as (0,0, …,1, …,0), wherein the ith dimension is 1, and the other dimensions are 0.

"FC" in the neural network model refers to full connection, i.e., a fully connected computational unit in a machine learning algorithm, and the mathematical formula is f (Wx + b), where the function f represents an activation function, w represents a model parameter, x represents a digitized representation of input data, and b represents a bias (also a model parameter). Each of the fully connected layers is composed of a number of neurons. The fully-connected layer plays a role of a classifier in the whole convolutional neural network, namely, the feature information of different types of works issued by the first account is input into a plurality of fully-connected computing units in the convolutional neural network model for classification computation to obtain a classification computation result, and the classification computation result is mapped to the sample mark space layer to obtain a plurality of corresponding scalars. That is, if we say that operations such as convolutional layers, pooling layers, and activation function layers map raw data to hidden layer feature space, the fully-connected layer serves to map the learned "distributed feature representation" to the sample label space.

And then, inputting the scalars into a computing unit layer in the convolutional neural network for mapping to obtain the release information of the first account user release work. That is to say, "Softmax layer" in the convolutional neural network model refers to a calculation unit layer in a machine learning algorithm, wherein a Softmax function maps a plurality of scalars (i.e. neurons) to a probability distribution, each value range of the output of the probability distribution is within a (0,1) interval, and the Softmax function is often used in the last layer of the neural network as an output layer for multi-classification. The specific procedures are well known in the art and will not be described herein.

Only the first layer FC and the last layer FC are shown in the figure, the type of the computing units used between the two layers is not limited, and only "m layer" is used to represent other m layer computing units in the neural network model structure.

The RNN in this figure refers to a current Neural Network, i.e., a Recurrent Neural Network. The recurrent neural network is an artificial neural network with nodes directionally connected into a ring. The internal state of such a network may exhibit dynamic timing behavior, unlike other neural networks, where the RNN may use its internal memory to process input sequences of arbitrary timing, which makes it easier to handle, e.g., unsegmented handwriting recognition, speech recognition, etc.

As shown in the figure, F2 and F7 are input to RNN1 for processing, and the resultant output is input to FC1, and FC1 inputs the processing result to the first layer FC for processing; and

inputting F4 and F7 into RNN2 for processing, inputting the obtained output into FC2, inputting F3 into FC2 for processing, and inputting the processing result into the first-layer FC for processing by FC 2; and

f1, F3, F5, F6 and F7 are also input into the first Layer FC for processing, the first Layer FC sequentially processes the processing result through M layers (Layer), finally, the processing result is input into the last Layer FC, the last Layer FC processes the received content, the processing result is input into a Softmax Layer of the neural network model, the Softmax Layer maps a plurality of scalars into a probability distribution, the probabilities of different video types are obtained, namely the probabilities of the video type 1, the video type 2, the video type … and the video type K are respectively obtained, and the issuing information of the account issuing different types of videos can be obtained according to the probabilities of the different video types.

The set model in the present disclosure may be, in addition to the neural network model described above, a model related to Logistic Regression (LR), a Maximum Likelihood Estimation (MLE) algorithm, a Maximum a posteriori probability estimation (MAPMaximum a likelihood estimation) algorithm, a probabilistic graph model basis-bayesian network parameter learning method, or the like, but is not limited thereto, and may be another model, and the present embodiment is not limited thereto.

The maximum likelihood estimation algorithm, the maximum posterior probability estimation algorithm, and the probability map model base-bayesian network parameter learning method are all commonly used generation estimation algorithms, which are well known to those skilled in the art and are not described herein again. While the name of Logistic Regression (LR) is a word "regression", its essence is a common classification model, which is usually used for binary problem, and it maps the feature space into a possibility, in LR, y is a qualitative variable {0,1}, and the LR method is mainly used to study the probability of some events.

That is, in the embodiment of the present disclosure, through the set model, a rule that the first account updates the work historically (for example, the first account publishes the video about the child 5 days a month, the first account also likes to publish the video about the hot event, and the like) is learned, and according to the rule, a probability of when the author publishes what kind of work can be predicted, for example, a probability of the author updating the video about the child on monday can be predicted; and then, the probability of issuing the different video types by the account can be used as the issuing information of the different types of videos issued by the account. Wherein the release information includes at least one of: a probability that the first account will release the work within a future time period; and the probability that the first account will release each type of work in the future.

In this disclosure, the probability that the first account issues different types of works in a time period may be understood as a probability that, for a group (group) of tags (tags), each Tag work is issued in a time period (e.g., 7 days) in the future (the sum of the issuance probabilities of k tags is 1), that is, the sum of the probabilities of issuing different types of works in a time period is 1. For example, the author updates three different types of works within 10 days, and when the probability of updating work 1 is 30%, the probability of updating work 2 is 50%, and the probability of updating work 3 is 20%.

Of course, in the embodiment of the present disclosure, it may also be predicted that the first account does not release the behavior data of the work according to the probability. That is, there are two results of determining the behavior data according to the probability, that is, the behavior data of the new work is issued by the first account within a set time period (for example, one day, one week, half a month, etc.), or the behavior data of the new work is not issued by the first account within a time period.

That is, the manner of predicting the release information of the first account for releasing the work is as follows: the neural network model may predict the probability of when the author publishes what type of work, e.g., the probability of the author updating videos about children on a monday, by learning the regularity that the first account historically updates the work (e.g., the author publishes videos about children on No. 5 a month, the author likes to publish videos of hot events, etc.). After training the neural network model, historical behavior information of the first account may be input into the neural network model, a future possible issuing behavior of the first account may be predicted through the neural network model, and a predicted result may be notified to the consumer (i.e., the second account).

It should be noted that the output of the neural network model can be divided into two categories: the first account will send video, or the first account will not send video.

Optionally, the structure output by the neural network model may also be: whether the first account will send video within a certain time period (e.g., one day, one week);

optionally, the structure output by the neural network model may also be: whether the first account will send a certain type of video for a certain period of time. For a group of Tag type, the probability of each Tag work being issued within a time period (e.g. 7 days) in the future (the sum of the issuing probabilities of k tags is 1).

And finally, executing step 103, generating a notification carrying the release information, and sending the notification to a second account before the release time.

In this step, when the release information of different types of works is predicted in step 102, the release information is packaged into a notification, and before the release time, the notification is sent to the second account, that is, the predicted release information of the first account is sent to the second account interested in each type of work (i.e., a subscriber, a user who has clicked the work, etc.) in a notification or active push manner, that is, the predicted release information of the different types of works may be sent to the second account interested in the work (i.e., other consumers, who may not pay attention to the work of the author or users who click the work of the author, etc.).

Specifically, the second account may be notified of the release information of the different types of works at one time in a list manner, or the second account may be notified of the release information of the different types of works one by one, so that the second account may predict the dynamics of the update work of the first account concerned by the second account in advance after receiving the notification.

In the embodiment of the disclosure, all historical information of a work published by a first account is obtained, at least time information of the work published by the first account is recorded in the historical information, and then the publishing information of the work published by the first account is predicted according to at least the time information of the work published by the first account, wherein the publishing information is used for indicating the publishing time of the first account for publishing a new work; and finally, generating a notice carrying the release information, and sending the notice to a second account before the release time. That is to say, in the embodiment of the present disclosure, the release time of the author's updated work is predicted according to the time information of the historically-released work in the historical information that the author released before, and the consumer who likes the work is notified in advance by the release time of the updated work, that is, before the author updates the work, so that the consumer can know the dynamic state of the updated work of the account concerned by the consumer in advance, which not only improves the accuracy of the user's learning of the update information of the work, but also better meets the requirements of different users, thereby improving the satisfaction of each user.

It should be noted that the account information and the user information related to the present application are collected by user or account authorization and then analyzed by subsequent processing.

It is noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the disclosed embodiments are not limited by the described order of acts, as some steps may occur in other orders or concurrently with other steps in accordance with the disclosed embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required of the disclosed embodiments.

Fig. 2 is a block diagram of an apparatus for pushing information according to an exemplary embodiment. Referring to fig. 2, the apparatus includes: an acquisition module 201, a prediction module 202, a generation module 203, and a transmission module 204, wherein,

the obtaining module 201 is configured to perform obtaining historical information of a work published by a first account, wherein at least time information of the work published by the first account in history is recorded in the historical information;

the prediction module 202 is configured to predict release information of a work released by a first account at least according to time information of the work released by the first account in history, wherein the release information is used for indicating the release time of a new work released by the first account;

the generating module 203 is configured to generate a notification carrying the release information;

the sending module 204 is configured to execute sending the notification generated by the generating module to a second account before the publication time. And sending a notice carrying the release information to a user who pays attention to the works of the first account or actively pushing the notice to other accounts which like the works of the corresponding types.

Optionally, in another embodiment, on the basis of the above embodiment, the prediction module 202 includes: the structure of the conversion module 301 and the release information prediction module 302 is schematically shown in fig. 3, wherein,

the conversion module 301 is configured to perform vector conversion on at least time information of the works which are released by the first account in history, so as to obtain characteristic information of different types of works which are released by the first account;

the release information prediction module 302 is configured to perform learning by inputting the time characteristic information into a set model, and predict release information of the first account for releasing the work.

Optionally, in another embodiment, on the basis of the foregoing embodiment, the published information prediction module 302 includes: a computing module 3021, a first mapping module 3022 and a second mapping module 3023, which are schematically illustrated in fig. 3A, wherein,

the probability prediction module 3021 is configured to perform learning by inputting the time characteristic information into a set model, and predict the probability of the first account issuing different works, where the sum of the probabilities of the first account updating different works of the same kind is 1;

the computing module 3021 is configured to perform a classification computation on the feature information of different types of works issued by the first account through a plurality of fully connected computing units in a convolutional neural network, so as to obtain a classification computation result

The first mapping module 3022 is configured to perform mapping of the classification calculation result to a sample label space layer, resulting in a plurality of scalars;

the second mapping module 3023 is configured to perform mapping processing on the calculation unit layer that inputs the scalars into the convolutional neural network, so as to obtain release information of a first account user release work.

Optionally, in another embodiment, on the basis of the foregoing embodiment, the release information predicted by the release information prediction module includes at least one of:

the first account may be a probability of future release of each type of work.

Optionally, in another embodiment, on the basis of the foregoing embodiment, the history information acquired by the acquiring module further includes at least one of the following:

account information for the first account;

the association information of the first account includes account information of a third account having an association relationship with the first account and cross information of the first account and the third account, and the association relationship includes at least one of the following: the interaction relationship exists among the accounts, the account attributes have commonality,

With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.

In the embodiment of the disclosure, according to the time information of the historically-published works in the historical information published by the author before, the publishing time of the author-updated works is predicted by adopting a machine learning method, and the publishing time of the updated works is notified to the consumers who like (for example, pay attention to or click) the works in advance, that is, before the author-updated works, the consumers can predict the dynamic state of the updated works of the concerned accounts in advance, so that the accuracy of learning the updating information of the works by the users is improved, the requirements of different users can be better met, and the satisfaction of each user is improved.

An embodiment of the present disclosure further provides an electronic device, including:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the information pushing method as described above, which is not described herein again.

The embodiment of the present disclosure also provides a storage medium, and when instructions in the storage medium are executed by a processor in an electronic device, the electronic device is enabled to execute the method for pushing information as described above.

Alternatively, the storage medium may be a non-transitory computer readable storage medium, which may be, for example, a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

Fig. 4 is a block diagram illustrating an electronic device 400 for information push according to an example embodiment. For example, the electronic device 400 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.

Referring to fig. 4, electronic device 400 may include one or more of the following components: a processing component 402, a memory 404, a power component 406, a multimedia component 408, an audio component 410, an interface for input/output (I/O) 412, a sensor component 414, and a communication component 416.

The processing component 402 generally controls overall operation of the electronic device 400, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing component 402 may include one or more processors 420 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 402 can include one or more modules that facilitate interaction between the processing component 402 and other components. For example, the processing component 402 can include a multimedia module to facilitate interaction between the multimedia component 408 and the processing component 402.

The memory 404 is configured to store various types of data to support operations at the electronic device 400. Examples of such data include instructions for any application or method operating on the electronic device 400, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 404 may be implemented by any type or combination of volatile or non-volatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.

The power supply component 406 provides power to the various components of the electronic device 400. Power components 406 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for electronic device 400.

The multimedia component 408 comprises a screen providing an output interface between the electronic device 400 and a user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 408 includes a front facing camera and/or a rear facing camera. The front-facing camera and/or the rear-facing camera may receive external multimedia data when the device 400 is in an operational mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

The audio component 410 is configured to output and/or input audio signals. For example, the audio component 410 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 400 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 404 or transmitted via the communication component 416. In some embodiments, audio component 410 also includes a speaker for outputting audio signals.

The I/O interface 412 provides an interface between the processing component 402 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.

The sensor component 414 includes one or more sensors for providing various aspects of status assessment for the electronic device 400. For example, the sensor component 414 can detect an open/closed state of the device 400, the relative positioning of components, such as a display and keypad of the electronic device 400, the sensor component 414 can also detect a change in the position of the electronic device 400 or a component of the electronic device 400, the presence or absence of user contact with the electronic device 400, orientation or acceleration/deceleration of the electronic device 400, and a change in the temperature of the electronic device 400. The sensor assembly 414 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 414 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 414 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 416 is configured to facilitate wired or wireless communication between the electronic device 400 and other devices. The electronic device 400 may access a wireless network based on a communication standard, such as WiFi, a carrier network (such as 2G, 3G, 4G, or 5G), or a combination thereof. In an exemplary embodiment, the communication component 416 receives broadcast signals or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 416 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 400 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the above-described method of pushing information shown in fig. 1.

In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions, such as the memory 404 including instructions, executable by the processor 420 of the electronic device 400 to perform the method for pushing information shown in fig. 1 described above is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

In an exemplary embodiment, a computer program product is also provided, and when the instructions in the computer program product are executed by the processor 420 of the electronic device 400, the electronic device 400 is caused to execute the information pushing method shown in fig. 1.

Fig. 5 is a block diagram illustrating an electronic device 500 for information push according to an exemplary embodiment. For example, the electronic device 500 may be provided as a server. Referring to fig. 3, electronic device 500 includes a processing component 522 that further includes one or more processors and memory resources, represented by memory 532, for storing instructions, such as applications, that are executable by processing component 522. The application programs stored in memory 532 may include one or more modules that each correspond to a set of instructions. Further, the processing component 522 is configured to execute the instructions to perform the above-described method of information pushing.

The electronic device 500 may also include a power component 526 configured to perform power management of the electronic device 500, a wired or wireless network interface 550 configured to connect the electronic device 500 to a network, and an input/output (I/O) interface 558. The electronic device 500 may operate based on an operating system stored in memory 532, such as Windows Server, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, or the like.

Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. An information pushing method, comprising:

2. The information pushing method according to claim 1, wherein the predicting of the release information of the work released by the first account according to at least the time information of the work released by the first account in history comprises:

3. The information pushing method according to claim 2, wherein the step of inputting the feature information of different types of works issued by the first account into a set model for learning, and the step of predicting the issue information of the works issued by the first account comprises the steps of:

4. The information pushing method according to claim 2 or 3, wherein the publishing information comprises at least one of:

the first account may be a probability of future release of each type of work.

5. The information pushing method according to any one of claims 1 to 4, wherein the history information further includes at least one of:

account information for the first account;

6. An information pushing apparatus, comprising:

7. The information push device according to claim 6, wherein the prediction module comprises:

8. The information pushing apparatus according to claim 7, wherein the published information prediction module comprises:

9. An electronic device, comprising:

a processor;

a memory for storing the processor-executable instructions;

wherein the processor is configured to execute the instructions to implement the method of information pushing according to any one of claims 1 to 5.

10. A storage medium, wherein instructions in the storage medium, when executed by a processor in an electronic device, enable the electronic device to perform the method of information pushing according to any one of claims 1 to 5.