CN115883503A - Message pushing method and device, computer equipment and storage medium - Google Patents

Abstract

The application relates to a message pushing method, a message pushing device, a computer device, a storage medium and a computer program product. The method comprises the following steps: acquiring a message pushing task; extracting candidate pushing object portrait labels corresponding to the message pushing task, the priority of the messages to be pushed, a preset pushing frequency, historical pushing data and the messages to be pushed; determining a push object blacklist of the rejection message according to historical push data; performing portrait label control on candidate push objects based on portrait labels, performing frequency control based on priorities of required push messages and preset push frequencies, and performing real-time control based on push object blacklists to generate push overall policy data; and pushing the message to be pushed based on the pushing overall strategy data. By adopting the method, the accurate pushing of the message can be realized.

Description

Message pushing method and device, computer equipment and storage medium

Technical Field

The present application relates to the field of internet technologies, and in particular, to a message pushing method, an apparatus, a computer device, a storage medium, and a computer program product.

Background

With the development of internet technology, pushing users by using the internet also becomes a popular hot technology, which can discover or discover user requirements, and enable users to know the pushed products and purchase the products.

In the conventional technology, a common message push technology is to push a message to be pushed indiscriminately to a user in an advertisement, a short message, or an APP screen-open mode. However, this push technology cannot accurately implement pushing, for example, when indiscriminate pushing is performed on a user, the user may feel that pushing is too much for the user who does not want to receive pushing, which causes waste of pushing resources and may cause the user to feel the objection to pushing; and for the users with the push receiving requirements, the push effect may be deteriorated by only performing indiscriminate push for a few times.

Disclosure of Invention

In view of the foregoing, it is necessary to provide a message pushing method, an apparatus, a computer device, a computer readable storage medium, and a computer program product, which can implement accurate message pushing in view of the above technical problems.

In a first aspect, the present application provides a message pushing method. The method comprises the following steps:

acquiring a message pushing task;

extracting candidate pushing object portrait labels corresponding to the message pushing task, the priority of the messages to be pushed, preset pushing frequency, historical pushing data and the messages to be pushed;

determining a push object blacklist of the rejection message according to the historical push data;

performing portrait label control on candidate push objects based on the portrait labels, performing frequency control based on the priority of the required push message and a preset push frequency, and performing real-time control based on a push object blacklist to generate push overall policy data;

and pushing the message to be pushed based on the pushed overall strategy data.

In one embodiment, before the extracting of the candidate push object portrait tags corresponding to the message push task, the priority of the required push message, the preset push frequency, the historical push data, and the message to be pushed, the method further includes:

acquiring the type of the message pushing task;

based on the type of the message pushing task, primarily screening a message pushing object set to obtain a primarily screened pushing object set;

and dividing candidate push objects from the primarily screened push object set.

In one embodiment, the dividing the candidate push object from the initially screened set of push objects includes:

and carrying out proportional subdivision on the primarily screened push object set to obtain candidate push objects.

In one embodiment, the method further comprises:

carrying out proportional subdivision on the primarily screened push object set to obtain candidate push objects and a candidate push object comparison group;

pushing the message to be pushed to the candidate pushing object comparison group, and collecting first message pushing feedback data fed back by the candidate pushing object comparison group;

when the pushing of the message to be pushed is completed based on the pushing overall strategy data, acquiring second feedback message pushing feedback data fed back;

and obtaining pushed overall strategy data evaluation data by contrasting the first message pushing feedback data and the second message pushing feedback data.

In one embodiment, the portrait tag management and control on candidate push objects based on the portrait tag, the frequency management and control on the priority of the required push message and a preset push frequency, and the real-time management and control on the push object blacklist include:

performing portrait label control on the candidate pushing object based on the portrait label to obtain pushing strategy data after portrait label control;

after the push strategy data after the portrait label is controlled is obtained, performing frequency control based on the priority of the required push message and a preset push frequency to obtain push strategy data after the frequency control;

after the push strategy data which are controlled frequently are obtained, real-time control is carried out on the basis of the push object blacklist, and push strategy data which are controlled in real time are obtained;

generating pushing overall strategy data based on the pushing strategy data after the portrait label is controlled, the pushing strategy data after the portrait label is controlled frequently and the pushing strategy data after the portrait label is controlled in real time.

In one embodiment, the method further comprises:

acquiring an exemptable object list;

when the candidate pushing object is in the exemptable object list, performing real-time control on the candidate pushing object in the exemptable object list based on the pushing object blacklist to generate first pushing strategy data;

when the candidate pushing object is not in the exemptable object list, performing portrait label control on the candidate pushing object based on the portrait label, performing frequency control based on the priority of the required pushing message and a preset pushing frequency, and performing real-time control based on a pushing object blacklist to generate second pushing strategy data;

and aggregating the first pushing strategy data and the second pushing strategy data to generate pushing overall strategy data.

In a second aspect, the application further provides a message pushing device. The device comprises:

the task acquisition module is used for acquiring a message pushing task;

the data extraction module is used for extracting candidate pushed object portrait labels corresponding to the message pushing task, the priority of messages to be pushed, preset pushing frequency, historical pushing data and messages to be pushed;

the blacklist determining module is used for determining a pushed object blacklist of the rejection message according to the historical pushed data;

the third-level control module is used for controlling portrait labels of candidate push objects based on the portrait labels, controlling frequency based on the priority of the required push information and a preset push frequency, controlling in real time based on a push object blacklist and generating push overall policy data;

and the message pushing module is used for pushing the message to be pushed based on the pushing overall strategy data.

In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:

acquiring a message pushing task;

extracting candidate pushing object portrait labels corresponding to the message pushing task, the priority of the messages to be pushed, a preset pushing frequency, historical pushing data and the messages to be pushed;

determining a push object blacklist of the rejection message according to the historical push data;

performing portrait label control on candidate push objects based on the portrait labels, performing frequency control based on the priority of the required push message and a preset push frequency, and performing real-time control based on a push object blacklist to generate push overall policy data;

and pushing the message to be pushed based on the pushed overall strategy data.

In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:

acquiring a message pushing task;

extracting candidate pushing object portrait labels corresponding to the message pushing task, the priority of the messages to be pushed, a preset pushing frequency, historical pushing data and the messages to be pushed;

determining a push object blacklist of a rejection message according to the historical push data;

performing portrait label control on candidate push objects based on the portrait labels, performing frequency control based on the priority of the required push message and a preset push frequency, and performing real-time control based on a push object blacklist to generate push overall policy data;

and pushing the message to be pushed based on the pushed overall strategy data.

In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:

acquiring a message pushing task;

extracting candidate pushing object portrait labels corresponding to the message pushing task, the priority of the messages to be pushed, preset pushing frequency, historical pushing data and the messages to be pushed;

determining a push object blacklist of the rejection message according to the historical push data;

performing portrait label control on candidate push objects based on the portrait labels, performing frequency control based on the priority of the required push message and a preset push frequency, and performing real-time control based on a push object blacklist to generate push overall policy data;

and pushing the message to be pushed based on the pushed overall strategy data.

According to the message pushing method, the message pushing device, the computer equipment, the storage medium and the computer program product, firstly, a message pushing task is obtained; extracting candidate pushing object portrait labels corresponding to the message pushing task, the priority of the messages to be pushed, a preset pushing frequency, historical pushing data and the messages to be pushed; determining a push object blacklist of the rejection message according to historical push data; performing portrait label control on candidate push objects based on portrait labels, performing frequency control based on the priority of required push messages and a preset push frequency, and performing real-time control based on a push object blacklist to generate push overall policy data; and pushing the message to be pushed based on the pushing overall strategy data. In the application, based on the overall pushing strategy data generated after portrait label management and control, frequency management and control and real-time management and control, accurate pushing of the message to be pushed can be achieved by relying on the overall pushing strategy data.

Drawings

FIG. 1 is a diagram of an application environment of a message push method in one embodiment;

FIG. 2 is a flowchart illustrating a message push method according to an embodiment;

FIG. 3 is a flowchart illustrating steps of a message pushing method according to another embodiment;

FIG. 4 is a logic diagram illustrating the implementation of priority frequency management in another embodiment;

FIG. 5 is a flowchart of message pushing executed by a scheduler for job scheduling in a specific application example;

FIG. 6 is a block diagram illustrating an exemplary message pushing apparatus;

FIG. 7 is a diagram of the internal structure of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of and not restrictive on the broad application.

The message pushing method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104 or may be placed on the cloud or other network server. Firstly, a terminal 102 sends a message pushing task request to a server 104, wherein the message pushing request comprises a candidate pushing object portrait label corresponding to the message pushing task, a priority of a message to be pushed, a preset pushing frequency, historical pushing data and a message to be pushed; determining a push object blacklist of the rejection message according to historical push data; performing portrait label control on candidate push objects based on portrait labels, performing frequency control based on the priority of required push messages and preset push frequency, and performing real-time control based on push object blacklists to generate push overall policy data; pushing a message to be pushed based on the pushing overall strategy data; further, the server 104 can also feed back the pushed overall policy data to the terminal 102. The terminal 102 may be, but is not limited to, various personal computers, notebook computers, smart phones, and tablet computers. The server 104 may be implemented as a stand-alone server or as a server cluster comprised of multiple servers.

In one embodiment, as shown in fig. 2, a message pushing method is provided, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:

and S100, acquiring a message pushing task.

S200, extracting candidate pushing object portrait labels corresponding to the message pushing task, the priority of the messages to be pushed, preset pushing frequency, historical pushing data and the messages to be pushed.

The portrait label refers to a fact label, a behavior label, a credit-granting related label, a risk related label, an AI (Artificial Intelligence) model related label and other labels aiming at the candidate push object; fact tags may include gender, birthday, age, etc. tags; behavior tags may include tags such as tolerance to message pushing; the priority of the message to be pushed refers to the importance degree of the message to be pushed, and in the application, the priority of the message to be pushed can be manually adjusted; the preset push frequency refers to a preset push frequency, for example, only one message can be pushed to a specific user in one day; the historical push data refers to data related to message pushing generated in a message pushing process before the current message pushing task is acquired, and may be push time, a push object, whether the push object rejects a message, and the like.

Specifically, the terminal sends a message pushing task request to the server, the message pushing request contains candidate pushing object portrait tags corresponding to the message pushing task, the priority of messages to be pushed, a preset pushing frequency, historical pushing data and messages to be pushed, and the server receives the message pushing task request sent by the terminal and extracts the candidate pushing object portrait tags corresponding to the message pushing task, the priority of the messages to be pushed, the preset pushing frequency, the historical pushing data and the messages to be pushed from the message pushing task request.

S300, determining a push object blacklist of the rejection message according to the historical push data.

Specifically, after the server extracts the historical push data, it may determine which push objects reject the message pushed by the server according to the historical push data, where the message pushed by the rejection server may be a logout account number, a message pushed before complaint, and the like, that is, a push object blacklist of the rejection message may be determined according to the historical push data.

S400, portrait label management and control are carried out on candidate push objects based on portrait labels, frequency management and control are carried out based on the priority of the required push information and the preset push frequency, real-time management and control are carried out based on push object blacklists, and push overall strategy data are generated.

In the application, portrait label management and control refers to a management and control rule for filtering and screening portrait according to a candidate pushing object; the frequency control refers to the control rule that the same push message range of the same push object is limited by the number of marketing times in the same day, and the message with high priority occupies the number of users first; the real-time management and control refers to that for the real-time conditions of the current day, such as logout, complaints and the like, the part of users need to be pulled into a push object blacklist, and the part of management and control rules are filtered before the message is pushed; the push overall policy data is data related to message push, including push object, push frequency, and the like.

Specifically, after extracting a candidate pushed object portrait label corresponding to the message pushing task, the priority of the message to be pushed, the preset pushing frequency, historical pushing data and the message to be pushed, and determining a pushed object blacklist of rejected messages according to the historical pushing data, the server can perform portrait label control on the candidate pushed object based on the portrait label of the candidate pushed object; after the preset push frequency of the same push message of the same push object is limited, the priority of the message to be pushed is judged, the pushed message can be subjected to frequency control according to the priority, the message with high priority can be pushed to candidate push objects in advance, and the message with low priority can be pushed less; real-time management and control are carried out based on the pushed object blacklist; after portrait tagging, frequency control, and real-time control are performed on the candidate push objects, data related to message push, that is, push general policy data, including actual push objects, the number of times to push messages to be pushed on the same day, and the like, is generated.

And S500, pushing the message to be pushed based on the pushing overall strategy data.

Specifically, after acquiring the push overall policy data, the server generates a message push file according to the push overall policy data, and pushes the message to be pushed to the actual push object through the message push file.

In the message pushing method, a message pushing task is firstly obtained; extracting candidate pushing object portrait labels corresponding to the message pushing task, the priority of the messages to be pushed, preset pushing frequency, historical pushing data and the messages to be pushed; determining a push object blacklist of the rejection message according to historical push data; performing portrait label control on candidate push objects based on portrait labels, performing frequency control based on the priority of required push messages and a preset push frequency, and performing real-time control based on a push object blacklist to generate push overall policy data; and pushing the message to be pushed based on the pushing overall strategy data. In the application, based on the general push strategy data generated after portrait label management and control, frequency management and control and real-time management and control, accurate push of the message to be pushed can be achieved by relying on the general push strategy data.

In one embodiment, before extracting a candidate push object portrait label corresponding to a message push task, a priority of a message to be pushed, a preset push frequency, historical push data, and a message to be pushed, the method further includes:

acquiring the type of a message pushing task; based on the type of the message pushing task, primarily screening a message pushing object set to obtain a primarily screened pushing object set; and dividing candidate push objects from the primarily screened push object set.

Exemplarily, an application a, an application b, an application c and a message pushing task X exist, each application has a corresponding pushing object group, the pushing object groups of all the applications are regarded as a message pushing object set, the application to which the message pushing task is pushed can be obtained by acquiring the type of the message pushing task, the message pushing object set is primarily screened, and the pushing object set of the corresponding application after primary screening can be obtained; and candidate push objects can be divided into a set of preliminarily screened push objects according to a proportion.

In this embodiment, by obtaining the type of the message pushing task, the message pushing object set can be preliminarily screened, so that the message pushing object can be found more accurately.

In one embodiment, the dividing the candidate push object from the preliminarily screened set of push objects comprises:

and carrying out proportional subdivision on the primarily screened push object set to obtain candidate push objects.

Specifically, after the primarily screened pushing object set is obtained, the method for dividing the candidate pushing objects from the primarily screened pushing object set is to subdivide the primarily screened pushing object set in proportion.

Further, the proportional subdivision mode can be an AB-test equal proportional division mode.

In this embodiment, by performing proportional subdivision on the primarily screened push object set, a more accurate message push object can be obtained.

In one embodiment, the method further comprises: and carrying out proportional subdivision on the primarily screened push object set to obtain candidate push objects and a candidate push object comparison group.

The control group is a randomly selected subset of subjects, the individuals of which have no particular treatment.

Specifically, the preliminarily screened push object set is subjected to proportional subdivision, so that not only can a candidate push object be obtained, but also another part of the proportionally subdivided push object set can be used as a candidate push object comparison group.

And pushing the message to be pushed to the candidate pushing object comparison group, and acquiring first message pushing feedback data fed back by the candidate pushing object comparison group.

In the present application, the first message push feedback data refers to a behavior response made by a push object in the candidate push object comparison group to a message to be pushed after receiving the message to be pushed.

Specifically, the candidate push object comparison group is a comparison group of the candidate push object and is used for judging the superiority of the push total policy data, so that the push total policy data is used as a variable to be controlled, the push total policy data does not need to be generated at this time, the message to be pushed is directly pushed to the candidate push object comparison group, after the push is completed, the push object in the push object comparison group can make a corresponding behavior reaction according to the message to be pushed, and the behavior reaction is collected and used as first message push feedback data to be fed back to the server.

Still further, the behavioral responses may include click through to message browsing, click disinterest in messages, close messages, and complaint messages.

And when pushing the message to be pushed based on the pushing total strategy data is completed, acquiring the fed back second message pushing feedback data.

In this application, the second message push feedback data refers to a behavior response made by a push object in the candidate push objects to the message to be pushed after receiving the message to be pushed.

Specifically, after the process of pushing the message to be pushed based on the pushed total policy data is completed, the actual pushing object in the candidate pushing object may make a corresponding behavior reaction according to the message to be pushed, and at this time, the behavior reaction is collected and used as second message pushing feedback data to be fed back to the server.

And obtaining pushed total strategy data evaluation data by contrasting the first message pushed feedback data and the second message pushed feedback data.

In the present application, the policy data evaluation data refers to data for evaluating the quality of the pushed total policy data.

Specifically, the first message push feedback data is feedback data obtained by pushing a message to be pushed to a candidate push object based on the pushed overall strategy data, and the second message push feedback data is feedback data obtained by directly pushing the message to be pushed to the candidate push object without generating the pushed overall strategy data; by comparing the obtained first message push feedback data and the second message push feedback data, the advantages and disadvantages of the unique variable push overall policy data in the generation process of the two kinds of push feedback data can be evaluated to obtain push overall policy data evaluation data.

In this embodiment, by obtaining the candidate push object comparison group, the comparison group does not generate push overall policy data, and based on comparison between the candidate push object comparison group and the candidate push object, push feedback data after pushing is performed, push overall policy data evaluation data can be obtained, so as to determine advantages of push overall policy data.

In one embodiment, as shown in fig. 3, S400 includes:

s420, portrait label control is conducted on the candidate pushing objects based on the portrait labels, and pushing strategy data after portrait label control is obtained.

Specifically, portrait tags such as fact tags, behavior tags, trust-related tags, risk-related tags, and AI model-related tags of the candidate pushed objects are subjected to portrait tag management and control.

Taking sex in the fact tag to perform portrait tag management and control as an example, an acquired message pushing task is suitable for being pushed to a woman, portrait tag management and control needs to be performed on candidate pushing objects based on the sex represented by the portrait tag of the candidate pushing objects, the candidate pushing objects which are women in the candidate pushing objects are selected as the objects to be pushed, and the obtained pushing policy data based on portrait tag management and control at this time includes selection of the sex in the candidate pushing objects as women.

And S440, after the push strategy data of the portrait label after being controlled is obtained, performing frequency control based on the priority of the required push message and the preset push frequency to obtain the push strategy data after the frequency control.

Specifically, after a pushed object subjected to portrait label management and control is obtained, frequency management and control can be performed based on the obtained priority of the required pushed message and the preset pushing frequency, and pushed policy data subjected to frequency management and control is obtained, that is, the pushed policy data subjected to frequency management and control includes that the pushed object pushed by the message to be pushed and the number of times of pushing the pushed object in the same day are judged according to the preset pushing frequency and the priority of the required pushed message.

Exemplarily, two messages, namely a message a and a message B, are to be pushed out, candidate push objects to be pushed by the message a and the message B are overlapped, an overlapped user 1 is arranged in the overlapped object, the overlapped user 1 only receives the message a and the message B, at this time, a preset push frequency for the overlapped user 1 is once a day, at this time, frequency control needs to be performed on pushing of the message before the message is pushed to the overlapped user 1, it is determined which message between the message a and the message B has a higher priority for the overlapped user 1, if the priority of the message a is higher than that of the message B, the preset push frequency for the overlapped user 1 is sent to the message a, and the message a is pushed to the overlapped user 1; if the overlapping user 1 only receives the messages of the messages a and B, but the preset push frequency of the overlapping user 1 is three times a day, it is determined which message priority of the messages a and B is higher for the overlapping user 1, the push times of the messages a and B can be determined according to the priority, but the push times of the messages with high priority are greater than the push times of the messages with low priority, that is, when the preset push frequency is three times a day and the push times of the message a account for two thirds of the preset push frequency, the push times of the message B account for the remaining one third, and the message a and the message B at the moment need to be all pushed out, and the message a and the message B cannot be pushed out only.

Further, if the priority levels are at the same level, the priority levels between the same level are judged according to the time predicted to be pushed to the overlapping users 1; in addition, as shown in the logic diagram of fig. 4, the implementation logic of the priority frequency management may be: in fig. 4, the right diagram is a result output table, the left diagram is a candidate push object table, the pushed push object is written into the result output table, and the candidate push object and the result output table are compared:

1. screening out candidate push object ids which are not in a result output table, namely usr-ids;

2. grouping the screened candidate push object ids, sequencing the messages to be pushed of the candidate push objects in the same group according to the priority order, pushing the candidate push objects by taking the messages with higher priority, and screening the push objects to be pushed by the messages to be pushed;

3. rewriting the pushed object pushed by the screened message to be pushed into a result output table;

4. and generating push strategy data after frequency management and control according to the result output table.

And S460, after the frequently controlled pushing strategy data is obtained, performing real-time control based on the pushing object blacklist to obtain the real-time controlled pushing strategy data.

Specifically, after the frequently controlled push objects are obtained, if the frequently controlled push objects enter a push object blacklist on the same day to be pushed, that is, when the candidate push objects are sales users or complaint users, the frequently controlled push objects are controlled in real time based on the push object blacklist, the push objects in the push object blacklist are filtered, no message is pushed to the push objects in the push object blacklist, and push policy data after real-time control is obtained, that is, the push policy data after real-time control includes filtering out objects which cannot be pushed in the candidate push objects in real time according to the push object blacklist.

And S480, generating pushing total strategy data based on the pushing strategy data after portrait label control, the pushing strategy data after frequent control and the pushing strategy data after real-time control.

Specifically, the pushed overall policy data may be generated based on the pushed policy data after portrait tag management, the pushed policy data after frequency management, and the pushed policy data after real-time management, where the pushed overall policy data includes portrait tag management and control of candidate pushed objects based on portrait tags, frequency management and control based on priorities of required pushed messages and preset push frequencies, and real-time management and control based on a pushed object blacklist.

In this embodiment, through portrait label management and control, frequency management and control and real-time management and control to candidate propelling movement object, accomplish accurate propelling movement under the condition of not excessively disturbing propelling movement object.

In one embodiment, the method further comprises:

acquiring a list of exemptable objects; and when the candidate push object is in the exemptable object list, performing real-time control on the candidate push object in the exemptable object list based on a push object blacklist, and generating first push strategy data.

The exemptable object refers to an object which can avoid limitation on rules, in the application, the exemptable object refers to an object which avoids portrait label control and frequency control, and portrait label control and frequency control are not needed for the exemptable object.

Specifically, a list of exemptable objects is obtained, the list of exemptable objects is compared with a candidate pushed object, when the candidate pushed object is in the list of exemptable objects, no portrait label control and frequency control are performed on the candidate pushed object in the list of exemptable objects, at this time, if the candidate pushed object enters a pushed object blacklist on the same day, namely, when the candidate pushed object is a customer or a customer, real-time control is performed on the candidate pushed object based on the pushed object blacklist, the candidate pushed object in the pushed object blacklist is filtered, no message is pushed to the candidate pushed object in the pushed object blacklist, first pushing policy data is obtained, and the first pushing policy data comprises filtering out objects which cannot be pushed in the candidate pushed object in the pushed object blacklist in real time according to the pushed object blacklist.

And when the candidate pushing object is not in the exemptable object list, performing portrait label control on the candidate pushing object based on portrait labels, performing frequency control based on the priority of the required pushing information and a preset pushing frequency, and performing real-time control based on a pushing object blacklist to generate second pushing strategy data.

Specifically, when the candidate push object is not in the list of exemptable objects, that is, the candidate push object is not limited by the list of exemptable objects, portrait label management and control may be performed on the candidate push object based on the portrait label, frequency management and control may be performed based on the priority of the required push message and the preset push frequency, and real-time management and control may be performed based on the push object blacklist, so as to generate second push policy data, where the second push policy data includes push overall policy data including portrait label management and control on the candidate push object based on the portrait label, frequency management and control may be performed based on the priority of the required push message and the preset push frequency, and real-time management and control may be performed based on the push object blacklist.

And collecting the first pushing strategy data and the second pushing strategy data to generate pushing total strategy data.

The aggregation refers to inducing and aggregating the first push strategy data and the second push strategy data.

Specifically, by summarizing and concentrating the first push policy data and the second push policy data, push overall policy data may be generated.

In this application, but through acquireing exemption user's list, can portrait label management and control and the exemption of frequency management and control to being in the candidate propelling movement object in the exemption object list, realize accurate propelling movement to the object that needs the propelling movement.

In one embodiment, as shown in FIG. 5, message pushing may be performed by employing a scheduler for job scheduling.

The job scheduling refers to examining whether the system can meet the resource requirements of user jobs according to information in the job control block, selecting some jobs from a backup queue of an external memory according to a certain algorithm, calling the jobs into the internal memory, creating processes for the jobs and allocating necessary resources for the jobs; and then the newly created process is inserted into the ready queue to be executed.

Specifically, the message pushing may be divided into five jobs, including a prescreening job, a fine-dividing job, a three-level management and control job, a file generation job, and a message pushing job, where each job is executed by scheduling, and the execution time of each job is started immediately from the job of the same day.

It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.

Based on the same inventive concept, the embodiment of the present application further provides a message pushing apparatus for implementing the above-mentioned message pushing method. The implementation scheme for solving the problem provided by the apparatus is similar to the implementation scheme described in the above method, so the specific limitations in one or more message pushing apparatus embodiments provided below may refer to the limitations on the message pushing method in the foregoing, and are not described herein again.

In one embodiment, as shown in fig. 6, there is provided a message pushing apparatus, including: the system comprises a task obtaining module 100, a data extracting module 200, a blacklist determining module 300, a three-level management and control module 400 and a message pushing module 500, wherein:

the task obtaining module 100 is configured to obtain a message push task.

The data extraction module 200 is configured to extract a candidate pushed object portrait label corresponding to the message pushing task, a priority of a message to be pushed, a preset pushing frequency, historical pushing data, and a message to be pushed.

A blacklist determining module 300, configured to determine a blacklist of push objects of the rejection message according to the historical push data.

A third level management and control module 400, configured to perform portrait label management and control on candidate push objects based on portrait labels, perform frequency management and control based on priorities of required push messages and preset push frequencies, and perform real-time management and control based on push object blacklists, so as to generate push total policy data.

A message pushing module 500, configured to push a message to be pushed based on the pushed overall policy data.

In one embodiment, the system further comprises an initial screening module, wherein the initial screening module is used for acquiring the type of the message pushing task; based on the type of the message pushing task, primarily screening a message pushing object set to obtain a primarily screened pushing object set; and dividing candidate push objects from the primarily screened push object set.

In an embodiment, the preliminary screening module is further configured to perform proportional subdivision on the preliminarily screened push object set to obtain candidate push objects.

In one embodiment, the system further comprises a comparison pushing module, wherein the comparison pushing module is used for performing proportional subdivision on the primarily screened pushing object set to obtain candidate pushing objects and a candidate pushing object comparison group; pushing a message to be pushed to a candidate pushing object comparison group, and acquiring first message pushing feedback data fed back by the candidate pushing object comparison group; when pushing of the message to be pushed is completed based on the pushing of the overall strategy data, acquiring second feedback message pushing feedback data fed back; and obtaining pushed overall strategy data evaluation data by contrasting the first message pushing feedback data and the second message pushing feedback data.

In one embodiment, the tertiary control module 400 is further configured to perform portrait label control on the candidate pushing object based on the portrait label, so as to obtain pushing policy data after the portrait label control; after the push strategy data after the portrait label is controlled is obtained, performing frequency control based on the priority of the required push message and the preset push frequency to obtain the push strategy data after the frequency control; after the push strategy data which are controlled frequently are obtained, real-time control is carried out on the basis of a push object blacklist, and push strategy data which are controlled in real time are obtained; and generating pushing overall strategy data based on the pushing strategy data after portrait label control, the pushing strategy data after frequent control and the pushing strategy data after real-time control.

In one embodiment, the system further comprises a push exemption module, wherein the push exemption module is used for acquiring a list of exemptable objects; when the candidate push object is in the exemptable object list, updating the push total strategy data; and pushing the message to be pushed based on the updated pushing overall strategy data.

The modules in the message pushing device may be implemented wholly or partially by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent of a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, an Input/Output interface (I/O for short), and a communication interface. The processor, the memory and the input/output interface are connected through a system bus, and the communication interface is connected to the system bus through the input/output interface. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operating system and the computer program to run on the non-volatile storage medium. The database of the computer device is used for storing the push overall strategy data. The input/output interface of the computer device is used for exchanging information between the processor and an external device. The communication interface of the computer device is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement a message push method.

It will be appreciated by those skilled in the art that the configuration shown in fig. 7 is a block diagram of only a portion of the configuration associated with the present application, and is not intended to limit the computing device to which the present application may be applied, and that a particular computing device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In an embodiment, a computer device is further provided, which includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method embodiments when executing the computer program.

In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored which, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.

In an embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, carries out the steps in the method embodiments described above.

It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) referred to in the present application are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the relevant laws and regulations and standards of the relevant countries and regions.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by hardware instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. Any reference to memory, databases, or other media used in the embodiments provided herein can include at least one of non-volatile and volatile memory. The nonvolatile Memory may include a Read-Only Memory (ROM), a magnetic tape, a floppy disk, a flash Memory, an optical Memory, a high-density embedded nonvolatile Memory, a resistive Random Access Memory (ReRAM), a Magnetic Random Access Memory (MRAM), a Ferroelectric Random Access Memory (FRAM), a Phase Change Memory (PCM), a graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the various embodiments provided herein may be, without limitation, general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, or the like.

All possible combinations of the technical features in the above embodiments may not be described for the sake of brevity, but should be considered as being within the scope of the present disclosure as long as there is no contradiction between the combinations of the technical features.

The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims (10)

1. A message pushing method, the method comprising:

acquiring a message pushing task;

extracting candidate pushing object portrait labels corresponding to the message pushing task, the priority of the messages to be pushed, preset pushing frequency, historical pushing data and the messages to be pushed;

determining a push object blacklist of a rejection message according to the historical push data;

performing portrait label control on candidate push objects based on the portrait labels, performing frequency control based on the priority of the required push message and a preset push frequency, and performing real-time control based on a push object blacklist to generate push overall policy data;

and pushing the message to be pushed based on the pushed overall strategy data.

2. The method of claim 1, wherein before extracting the candidate push object portrait tags corresponding to the message push task, the priority of the required push message, the preset push frequency, the historical push data, and the message to be pushed, the method further comprises:

acquiring the type of the message pushing task;

based on the type of the message pushing task, primarily screening a message pushing object set to obtain a primarily screened pushing object set;

and dividing candidate push objects from the primarily screened push object set.

3. The method of claim 2, wherein partitioning candidate push objects from the initially filtered set of push objects comprises:

and carrying out proportional subdivision on the primarily screened push object set to obtain candidate push objects.

4. The method of claim 3, further comprising:

carrying out proportional subdivision on the primarily screened push object set to obtain candidate push objects and a candidate push object comparison group;

pushing the message to be pushed to the candidate pushing object comparison group, and collecting first message pushing feedback data fed back by the candidate pushing object comparison group;

when the pushing of the message to be pushed is completed based on the pushing overall strategy data, acquiring second feedback message pushing feedback data fed back;

and obtaining pushed total strategy data evaluation data by contrasting the first message pushed feedback data and the second message pushed feedback data.

5. The method of claim 1, wherein the portrait tagging candidate push objects based on the portrait tags, frequency management based on the priority of the desired push message and a preset push frequency, and real-time management based on the push object blacklist, generating push global policy data comprises:

performing portrait label control on the candidate pushing object based on the portrait label to obtain pushing strategy data after portrait label control;

after the push strategy data after the portrait label control is obtained, performing frequency control based on the priority of the required push message and a preset push frequency to obtain push strategy data after the frequency control;

after the push strategy data which are controlled frequently are obtained, real-time control is carried out on the basis of the push object blacklist, and push strategy data which are controlled in real time are obtained;

and generating pushing total strategy data based on the pushing strategy data after the portrait label is controlled, the pushing strategy data after the portrait label is controlled frequently and the pushing strategy data after the portrait label is controlled in real time.

6. The method of claim 1, further comprising:

acquiring a list of exemptable objects;

when the candidate pushing object is in the exemptable object list, performing real-time control on the candidate pushing object in the exemptable object list based on the pushing object blacklist to generate first pushing strategy data;

when the candidate pushing object is not in the exemptable object list, performing portrait label control on the candidate pushing object based on the portrait label, performing frequency control based on the priority of the required pushing message and a preset pushing frequency, and performing real-time control based on a pushing object blacklist to generate second pushing strategy data;

and aggregating the first pushing strategy data and the second pushing strategy data to generate pushing overall strategy data.

7. A message push apparatus, the apparatus comprising:

the task acquisition module is used for acquiring a message pushing task;

the data extraction module is used for extracting candidate pushing object portrait labels corresponding to the message pushing tasks, the priority of the messages to be pushed, preset pushing frequency, historical pushing data and the messages to be pushed;

the blacklist determining module is used for determining a pushed object blacklist of the rejection message according to the historical pushed data;

the third-level control module is used for controlling portrait labels of candidate push objects based on the portrait labels, controlling frequency based on the priority of the required push information and a preset push frequency, controlling in real time based on a push object blacklist and generating push overall policy data;

and the message pushing module is used for pushing the message to be pushed based on the pushed total strategy data.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.

9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.

Images