CN114244897A - Message pushing method and device - Google Patents

Message pushing method and device Download PDF

Info

Publication number
CN114244897A
CN114244897A CN202210165324.5A CN202210165324A CN114244897A CN 114244897 A CN114244897 A CN 114244897A CN 202210165324 A CN202210165324 A CN 202210165324A CN 114244897 A CN114244897 A CN 114244897A
Authority
CN
China
Prior art keywords
user
push
target
pushing
strategy
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202210165324.5A
Other languages
Chinese (zh)
Other versions
CN114244897B (en
Inventor
杜培锋
冯鲁汉
陈光金
张海军
沈珑斌
张疏桐
曾启洋
邱灿清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Zhejiang Koubei Network Technology Co Ltd
Original Assignee
Zhejiang Koubei Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zhejiang Koubei Network Technology Co Ltd filed Critical Zhejiang Koubei Network Technology Co Ltd
Priority to CN202210165324.5A priority Critical patent/CN114244897B/en
Publication of CN114244897A publication Critical patent/CN114244897A/en
Application granted granted Critical
Publication of CN114244897B publication Critical patent/CN114244897B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/386—Payment protocols; Details thereof using messaging services or messaging apps
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0631—Item recommendations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G06Q30/0639—Item locations

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • General Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Computer Security & Cryptography (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The application discloses a message pushing method and device, and relates to the technical field of communication. The method comprises the following steps: acquiring a target end event triggered by a user at a client; sequencing a plurality of pushing strategies corresponding to the target end event based on the attribute characteristics corresponding to the user, wherein each pushing strategy at least comprises two intervention actions; determining an executable target push strategy from the multiple push strategies according to the sequencing results of the multiple push strategies; and based on the target pushing strategy, sequentially pushing corresponding notification messages to the user. The message touch reaching rate can be improved, and the message touch reaching effect is improved.

Description

Message pushing method and device
Technical Field
The present application relates to the field of communications technologies, and in particular, to a method and an apparatus for pushing a message.
Background
With the development of internet technology, more and more internet-technology-based network service platforms are provided, which provide online transaction channels for merchants and users, the merchants distribute products or services provided by the merchants to the network service platforms, and the users browse and purchase products or services required by the merchants on the network service platforms. To facilitate ordering by the user, the web services platform pushes a notification message to the user.
At present, after a user triggers an event at a client, a network service platform usually pushes a notification message to the user in time, and performs an action intervention on the user. However, the user may not be interested in the content of the file in the notification message at present, or may not see the notification message at all, thereby resulting in a low message reach rate and failure to achieve the desired message reach effect.
Disclosure of Invention
In view of this, the present application provides a message pushing method and device, and mainly aims to improve a message reach rate and improve a message reach effect.
According to an aspect of the present application, there is provided a message pushing method, including:
acquiring a target end event triggered by a user at a client;
sequencing a plurality of pushing strategies corresponding to the target end event based on the attribute characteristics corresponding to the user, wherein each pushing strategy at least comprises two intervention actions;
determining an executable target push strategy from the multiple push strategies according to the sequencing results of the multiple push strategies;
and based on the target pushing strategy, sequentially pushing corresponding notification messages to the user.
Optionally, the sorting, based on the attribute characteristics corresponding to the user, the multiple push policies corresponding to the target end event includes:
analyzing attribute characteristics corresponding to the user based on a plurality of decision factors related to the target end event to obtain analysis results corresponding to the decision factors respectively;
sequencing the multiple push strategies corresponding to the target end event according to the analysis result to obtain a sequencing result of the multiple push strategies corresponding to the target end event;
wherein the method further comprises:
and determining variable values corresponding to the target variables respectively related to the multiple push strategies according to the analysis result.
Optionally, the analyzing the attribute characteristics corresponding to the user based on multiple decision factors related to the target end event to obtain analysis results corresponding to the multiple decision factors respectively includes:
analyzing attribute characteristics corresponding to the user respectively based on a preference factor, a position factor and a rights factor related to the target end event to obtain stores and categories preferred by the user, a predicted position of the user and virtual resources currently owned by the user;
the sorting the multiple push strategies corresponding to the target end event according to the analysis result to obtain a sorting result of the multiple push strategies corresponding to the target end event includes:
and sequencing the multiple pushing strategies corresponding to the target end event according to the shop and the category preferred by the user, the predicted position and the virtual resource currently owned by the user to obtain the sequencing result.
Optionally, analyzing attribute features corresponding to the user respectively based on the location factor and the right factor related to the target end event to obtain a predicted location of the user and a virtual resource currently owned by the user, including:
analyzing the user historical behavior characteristics in the attribute characteristics based on the position factor related to the target end event and the current position information of the user to obtain the predicted position of the user;
analyzing attribute characteristics corresponding to the user based on the rights and interests factor to obtain virtual resources currently owned by the user and the interest degree of the user for different types of virtual resources;
the sorting the multiple push strategies corresponding to the target end event according to the shop and the category preferred by the user, the predicted position and the virtual resource currently owned by the user to obtain the sorting result comprises the following steps:
and sequencing the multiple pushing strategies corresponding to the target end event according to the shop and the category preferred by the user, the predicted position, the virtual resource currently owned by the user and the interestingness to obtain the sequencing result.
Optionally, the determining, according to the sorting result of the multiple push policies, an executable target push policy from the multiple push policies includes:
and sequentially carrying out feasibility verification on the multiple push strategies according to the sequencing results of the multiple push strategies, and determining the target push strategy from the multiple push strategies according to the feasibility verification result.
Optionally, the sequentially performing feasibility verification on the multiple push strategies according to the sorting result of the multiple push strategies, and determining the target push strategy from the multiple push strategies according to the feasibility verification result includes:
carrying out feasibility verification on the first sorted pushing strategy;
if the first-ranked push strategy passes the feasibility verification, determining the first-ranked push strategy as the target push strategy;
and if the first-ranked push strategy does not pass the feasibility verification, continuing to perform the feasibility verification on the second-ranked push strategy until the target push strategy is determined.
Optionally, the performing feasibility verification on the first ranked push policy includes:
collecting user real-time characteristics corresponding to the first sorted pushing strategy;
and carrying out feasibility verification on the first sorted pushing strategy based on the real-time characteristics of the user.
Optionally, the sequentially pushing, based on the target pushing policy, corresponding notification messages to the user includes:
generating notification messages corresponding to the at least two intervention actions according to the variable value and the notification message templates corresponding to the at least two intervention actions in the target pushing strategy;
and sequentially pushing notification messages corresponding to the at least two intervention actions to the user according to the message channels corresponding to the at least two intervention actions in the target pushing strategy.
Optionally, if a virtual resource issuing action exists in at least two intervention actions of the target push policy, generating, according to the variable value and a notification message template corresponding to each of the at least two intervention actions in the target push policy, a notification message corresponding to each of the at least two intervention actions, including:
based on the variable value, issuing corresponding virtual resources to the user;
generating a notification message issued by the virtual resource according to the notification message template corresponding to the virtual resource issuing action and the variable value;
the sequentially pushing notification messages corresponding to the at least two intervention actions to the user according to the message channels corresponding to the at least two intervention actions in the target pushing strategy comprises:
and pushing the notification message issued by the virtual resource to the user according to the message channel corresponding to the virtual resource issuing action.
Optionally, before the sorting the multiple push policies corresponding to the target end event based on the attribute characteristics corresponding to the user, the method further includes:
determining a plurality of push strategies corresponding to different types of end events related to the target crowd from a preset push strategy library according to the target crowd to which the user belongs;
determining a plurality of push strategies corresponding to the target end event according to the plurality of push strategies corresponding to the end events of different types;
before the obtaining of the target-side event triggered by the user at the client, the method further includes:
configuring a plurality of pushing strategies corresponding to different types of end events aiming at the target crowd, wherein each pushing strategy comprises at least two intervention actions, and a notification message template and a message channel corresponding to each intervention action;
and storing a plurality of push strategies corresponding to different types of end events related to the target crowd into the preset push strategy library.
According to another aspect of the present application, there is provided a message pushing apparatus, including:
the acquisition unit is used for acquiring a target end event triggered by a user at a client;
the ordering unit is used for ordering a plurality of pushing strategies corresponding to the target end event based on the attribute characteristics corresponding to the user, wherein each pushing strategy at least comprises two intervention actions;
a determining unit, configured to determine, according to a sorting result of the multiple push policies, an executable target push policy from the multiple push policies;
and the pushing unit is used for sequentially pushing corresponding notification messages to the user based on the target pushing strategy.
Optionally, the sorting unit includes: an analysis module and a sequencing module, wherein the analysis module is used for analyzing the data of the data to be analyzed,
the analysis module is used for analyzing the attribute characteristics corresponding to the user based on a plurality of decision factors related to the target end event to obtain analysis results corresponding to the decision factors respectively;
and the sequencing module is used for sequencing the multiple push strategies corresponding to the target end event according to the analysis result to obtain a sequencing result of the multiple push strategies corresponding to the target end event.
Optionally, the sorting unit further comprises a first determining module 323,
and the first determining module is used for determining variable values corresponding to the target variables respectively related to the multiple push strategies according to the analysis result.
Optionally, the analysis module is specifically configured to analyze attribute features corresponding to the user based on a preference factor, a location factor, and a right factor related to the target-end event, so as to obtain a store and a category preferred by the user, a predicted location of the user, and a virtual resource currently owned by the user;
the sorting module is specifically configured to sort the multiple push strategies corresponding to the target-side event according to the stores and categories preferred by the user, the predicted position, and the virtual resources currently owned by the user, so as to obtain the sorting result.
Optionally, the analysis module is further specifically configured to analyze the user historical behavior feature in the attribute feature based on the location factor related to the target end event and the current location information of the user, so as to obtain a predicted location of the user; analyzing attribute characteristics corresponding to the user based on the rights and interests factor to obtain virtual resources currently owned by the user and the interest degree of the user for different types of virtual resources;
the sorting module is further specifically configured to sort, according to the store and the category preferred by the user, the predicted position, the virtual resource currently owned by the user, and the interest level, the multiple push strategies corresponding to the target event to obtain the sorting result.
Optionally, the determining unit is specifically configured to sequentially perform feasibility verification on the multiple push policies according to the sorting results of the multiple push policies, and determine the target push policy from the multiple push policies according to the feasibility verification result.
Optionally, the determining unit includes: a verification module and a second determination module,
the verification module is used for verifying the feasibility of the first sorted push strategy;
the second determining module is configured to determine the first ranked push policy as the target push policy if the first ranked push policy passes feasibility verification;
the verification module is further configured to continue to perform feasibility verification on the second ranked push policy until the target push policy is determined if the first ranked push policy fails in feasibility verification.
Optionally, the verification module is specifically configured to collect real-time characteristics of the user corresponding to the first sorted push policy; and carrying out feasibility verification on the first sorted pushing strategy based on the real-time characteristics of the user.
Optionally, the pushing unit includes: a generation module and a push module, wherein the push module is used for pushing the data,
the generating module is configured to generate notification messages corresponding to the at least two intervention actions according to the variable value and the notification message templates corresponding to the at least two intervention actions in the target push policy;
and the pushing module is used for sequentially pushing the notification messages corresponding to the at least two intervention actions to the user according to the message channels corresponding to the at least two intervention actions in the target pushing strategy.
Optionally, the generating module is specifically configured to issue, based on the variable value, a corresponding virtual resource to the user; generating a notification message issued by the virtual resource according to the notification message template corresponding to the virtual resource issuing action and the variable value;
the pushing module is specifically configured to push a notification message issued by the virtual resource to the user according to a message channel corresponding to the virtual resource issuing action.
Optionally, the determining unit is further configured to determine, according to a target group to which the user belongs, multiple push policies corresponding to different types of end events related to the target group from a preset push policy library; and determining a plurality of push strategies corresponding to the target end event according to the plurality of push strategies corresponding to the end events of different types.
Optionally, the apparatus further comprises: a configuration unit and a storage unit, wherein,
the configuration unit is used for configuring multiple push strategies corresponding to different types of end events aiming at the target crowd, wherein each push strategy comprises at least two intervention actions, and a notification message template and a message channel corresponding to each intervention action.
The storage unit is configured to store multiple push policies corresponding to different types of end events related to the target group into the preset push policy library.
According to yet another aspect of the present application, there is provided a storage medium having stored thereon a computer program which, when executed by a processor, implements the above message push method.
According to yet another aspect of the present application, there is provided a computer device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, the processor implementing the message pushing method when executing the computer program.
By means of the technical scheme, compared with the mode that the network service platform pushes the notification message to the user in time after the current user triggers the event at the client side and the user is subjected to one-time action intervention, the message pushing method and the message pushing device can obtain the target-side event triggered by the user at the client side; sequencing a plurality of pushing strategies corresponding to the target end event based on the attribute characteristics corresponding to the user, wherein each pushing strategy at least comprises two intervention actions; meanwhile, determining an executable target push strategy from the multiple push strategies according to the sequencing results of the multiple push strategies; and finally, based on the target pushing strategy, sequentially pushing corresponding notification messages to the user. Therefore, a target pushing strategy is screened from multiple pushing strategies, corresponding notification messages are sequentially sent based on at least two intervention actions in the target pushing strategy, a series of interventions are conducted on a user, the message reaching effect can be improved, meanwhile, the message reaching rate can be comprehensively improved through application of the intervention actions in the pushing strategy, in addition, the pushing messages can be prevented from being limited by a single expression form through measurement of multiple pushing strategies, and therefore result deviation is caused, and the message reaching effect is influenced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 shows a flowchart of a message pushing method provided in an embodiment of the present application;
fig. 2 is a schematic flowchart illustrating another message pushing method provided in an embodiment of the present application;
fig. 3 is a schematic structural diagram illustrating a message pushing apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of another message pushing apparatus provided in an embodiment of the present application;
fig. 5 shows a physical structure diagram of a computer device according to an embodiment of the present invention.
Detailed Description
The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
In order to solve the problems that the push message in the prior art cannot achieve the expected message reach effect and the message reach rate is low, as shown in fig. 1, the method includes:
step 101, acquiring a target end event triggered by a user at a client.
The client in the embodiment of the invention has functions of selecting and ordering by a user, the target event is an event triggered by the user at the client, and specifically can be an end-quitting event, an end-entering event, a search event, a store page event, a list-lifting event and the like, the end-quitting event is an operation event that the user quits the client, such as the user directly quits the client or presses the client at the background, the end-entering event is an operation event that the user enters the client, the search event is an operation event that the user searches a certain product at the client, such as the user searches products such as fried chicken strings, hot pot and the like at the client, the page event is an operation event that the user browses the store at the client, and the list-lifting operation event is an operation event that the user orders at the client and enters the list-lifting page.
The embodiment of the invention is mainly applied to a scene of pushing the notification message to the user by utilizing the pushing strategy. The execution main body of the embodiment of the invention is a device or equipment which can push the notification message to the user according to the push strategy, and can be specifically arranged at one side of the server.
In order to improve the touch effect of the notification message, the embodiment of the invention configures a plurality of push strategies aiming at different crowds in advance, wherein the push strategies specifically can be store push, category push, virtual resource distribution and the like, each push strategy at least comprises two intervention actions, for example, aiming at the store push strategies, the first intervention action is waiting for two hours, the second intervention action is used as a store with user preference pushed to the user by using a message channel A after two hours, the third intervention action is used as a store with user preference pushed to the user by using a message channel B if the user is unread or uninteresting, and 11 points push the store with user preference to the user by using a message channel B. For another example, for a push policy for virtual resource distribution, a first intervention action is to issue a virtual resource to a user, and a message channel C is used to send a corresponding notification message to the user, a second intervention action is to wait for two hours, and a third intervention action is to send a corresponding notification message to the user through a message channel D if the user is unread after two hours.
In addition, as the embodiment of the invention configures a plurality of push strategies aiming at different crowds, the content and the form of each push strategy are different, the notification message can be prevented from being limited by a single expression form and content, and the message reach effect is further influenced.
Based on this, before step 101, the method further comprises: configuring a plurality of pushing strategies corresponding to different types of end events aiming at the target crowd, wherein each pushing strategy comprises at least two intervention actions, and a notification message template and a message channel corresponding to each intervention action; and storing a plurality of push strategies corresponding to different types of end events related to the target crowd into the preset push strategy library. The notification message templates corresponding to the intervention actions in different push strategies are different, for example, the message template corresponding to the notification message of the push shop in the shop push strategy is different from the message template corresponding to the notification message of the push item in the item push strategy. In addition, the message channel may specifically include channels such as a message push notification, a short message notification, an applet notification, a public number message notification, a client station internal message and the like of a mobile phone manufacturer, the target group may be a group having a certain common characteristic, and the different types of end events specifically include an end-quitting event, an end-entering event, a search event, a shop page event, a bill-picking event and the like.
For example, users in Beijing area are set as target groups, a plurality of push strategies corresponding to different types of end events are configured for the users in Beijing area, for example, push strategies such as store push, category push, virtual resource distribution and the like are respectively set aiming at the back end event of the user, wherein, each pushing strategy at least sets two intervention actions, and configures a message template and a message channel corresponding to each intervention action, if aiming at the push strategy of virtual resource distribution, setting a first intervention action as the virtual resource distribution to the user, and sends corresponding notice message to the user by short message, further, sets the second intervention action as waiting for two hours, and the third intervention action is taken as that if the user is unread after two hours, the corresponding notification message is sent to the user by adopting the client station internal signal, and meanwhile, the corresponding virtual resource is configured to issue a notification message template.
It should be noted that, for the same type of intervention action (for example, all the intervention actions are sending notification messages for issuing virtual resources), different message channels may correspond to the same message template, or may correspond to different message templates, for example, a notification message template for issuing virtual resources to a user by using a short message is "respected user, good, and has issued 2 coupons with 6 elements for you", and a notification message template for issuing virtual resources to a user by using a client-side in-station information is "parent," and has issued 2 coupons with 6 elements for you, and it is required to use as soon as possible ".
In addition to the above configuration of the document content of the message template, in order to improve the message reach rate and enhance the user experience, a corresponding picture may be configured, for example, when a notification message pushed by a store is sent to a user through a public number, a picture corresponding to the store may be added to the notification message. Further, after configuring the plurality of push strategies corresponding to the different types of end events of the target group, the configured plurality of push strategies may be stored in a preset push strategy library of the recall engine.
For the embodiment of the invention, when a user operates at the client, the client reports a target end event triggered by the user to the server, so that the server determines multiple push strategies corresponding to the target end event from preset push strategies according to the type corresponding to the target end event.
And 102, sequencing a plurality of push strategies corresponding to the target end event based on the attribute characteristics corresponding to the user.
Each pushing strategy at least comprises two intervention actions, and the attribute characteristics of the user comprise the browsing times of the user to the shop, the purchasing times of the user to a certain class, virtual resources (universal coupons, takeaway delivery coupons, new retail commodity coupons, supermarket coupons and the like) currently owned by the user, the current position of the user, the occupation of the user and the like.
For the embodiment of the present invention, after the client reports the target end event triggered by the user to the server, if the server determines that the target end event satisfies the corresponding trigger condition, the server may obtain multiple push policies corresponding to the target end event from a preset push policy library, and regarding a process of determining the multiple push policies corresponding to the target end event, as an optional implementation manner, the method includes: determining a plurality of push strategies corresponding to different types of end events related to the target crowd from a preset push strategy library according to the target crowd to which the user belongs; and determining a plurality of push strategies corresponding to the target end event according to the plurality of push strategies corresponding to the end events of different types. When reporting the target end event to the server, the client sends the attribute characteristics of the user to the server, and the server can determine the target population to which the user belongs according to the attribute characteristics of the user, such as occupation, the region and the like.
Further, after determining the plurality of push strategies corresponding to the target end event, the plurality of push strategies corresponding to the target end event may be sorted by analyzing the attribute characteristics of the user. Specifically, the attribute characteristics of the user may be analyzed in multiple dimensions, and then multiple push strategies may be ranked, for example, according to the browsing amount of the user to some stores or the order placement amount of some categories in the stores, it is determined whether the user has a more preferred store or category, and if the user has a more preferred store or category and the current time is the meal time, the strategies for performing store push or category push may be ranked ahead. Further, the virtual resources currently owned by the user are analyzed, and if it is found that the user currently owns a certain amount of virtual resources but the user does not have a habit of frequently using the virtual resources, the pushing policy issued by the virtual resources can be arranged behind the pushing policy of the store or the category. For another example, by analyzing the historical behavior of the user, it is found that the user reaches 11 o 'clock every Monday to Friday Monday, and if the current time is 9 o' clock, a notification message of store push or category push can be sent to the user after waiting for two hours, so as to promote the user to place an order at lunch time, and therefore, the push strategy with the waiting action can be ranked ahead. Therefore, through carrying out multi-dimensional analysis on the attribute characteristics of the user, various pushing strategies corresponding to the target end events can be sequenced, so that the most suitable target pushing strategy can be screened out, and the message reach effect is improved.
And 103, determining an executable target push strategy from the multiple push strategies according to the sequencing results of the multiple push strategies.
In a specific application scenario, although it may be determined that the first-ranked push policy is more suitable for the user according to the ranking result, during the process of ranking the plurality of push policies, the user may execute some operations at present, so that the first-ranked push policy is not suitable for the user, for example, the push policy that reminds the user to use the virtual resource is ranked first in the ranking result, but if the user has used the existing virtual resource at present in the ranking process, that is, the virtual resource is underwritten, it is considered that the first-ranked push policy that reminds the user to use the virtual resource is not the most suitable target push policy for the user at this time. Therefore, in order to ensure the reach effect of the notification message, before executing the push strategy, the executability of each push strategy needs to be sequentially verified according to the sequencing result, so as to avoid affecting the reach effect of the message and wasting the push resources.
Based on this, step 203 specifically includes: and sequentially carrying out feasibility verification on the multiple push strategies according to the sequencing results of the multiple push strategies, and determining the target push strategy from the multiple push strategies according to the feasibility verification result. Further, the sequentially performing feasibility verification on the multiple push strategies according to the sorting result of the multiple push strategies, and determining the target push strategy from the multiple push strategies according to the feasibility verification result includes: carrying out feasibility verification on the first sorted pushing strategy; if the first-ranked push strategy passes the feasibility verification, determining the first-ranked push strategy as the target push strategy; and if the first-ranked push strategy does not pass the feasibility verification, continuing to perform the feasibility verification on the second-ranked push strategy until the target push strategy is determined.
For example, the ordering result of the multiple push strategies corresponding to the target end event is a push strategy issued by the virtual resource, a shop push strategy and a category push strategy, in order to determine the target push strategy, firstly, feasibility verification is performed on the push strategy issued by the virtual resource, and if the push strategy issued by the virtual resource passes the feasibility verification, the push strategy issued by the virtual resource is determined to be the target push strategy; if the pushing strategy issued by the virtual resource fails to pass the feasibility verification, continuing to perform the feasibility verification on the shop pushing strategy, and if the shop pushing strategy passes the feasibility verification, determining the shop pushing strategy as a target pushing strategy; and if the store pushing strategy does not pass the feasibility verification, continuing to carry out the feasibility verification on the category pushing strategy. Therefore, according to the sequencing result, feasibility verification is sequentially carried out on the multiple pushing strategies, the target pushing strategy can be determined, and the target pushing strategy can be guaranteed to achieve the expected message reaching effect.
Further, in the process of verifying the feasibility of the push policy, the real-time characteristics of the user may be obtained, and the feasibility of the push policy is verified by using the real-time characteristics of the user, and based on this, the feasibility verification of the push policy sorted first includes: collecting user real-time characteristics corresponding to the first sorted pushing strategy; and carrying out feasibility verification on the first sorted pushing strategy based on the real-time characteristics of the user.
For example, the first sorted pushing policy is a pushing policy issued by a virtual resource, the using condition of the virtual resource issuing action in the pushing policy is that the user has not issued an order within 2 days, before executing the pushing policy issued by the virtual resource, the current behavior of the user is detected, and if the user has an order issuing behavior, the pushing policy issued by the virtual resource is determined to be infeasible; and if the user does not have ordering behavior, determining that the pushing strategy issued by the virtual resource is feasible.
And step 104, sequentially pushing corresponding notification messages to the user based on the target pushing strategy.
For the embodiment of the invention, after the target pushing strategy is determined, the corresponding notification messages are sequentially pushed to the user according to at least two intervention actions contained in the target pushing strategy, so that continuous intervention on the user is realized through a series of intervention actions in the target pushing strategy, and the message touch effect is improved.
For example, the target push strategy is a shop push strategy, the first intervention action in the shop push strategy is waiting for two hours, the second intervention action is pushing a user-preferred shop to the user by using a message channel a after two hours, the third intervention action is pushing the user-preferred shop to the user by using a message channel B if the user is not read or interested, when the shop push strategy is executed, because the first intervention action is waiting for two hours, the notification message of shop push is not sent to the user at present, the first intervention action is waited for two hours, the corresponding notification message of shop push is generated according to the push message template corresponding to the second intervention action after two hours, and the notification message is sent to the user by using a short message, if the user is not reading the notification message or is not interested in the notification message, the in-site mail mode of the client is adopted at 11, the notification message is pushed to the user again. Therefore, effective intervention can be performed on the user through a series of intervention actions in the target pushing strategy, so that the message reaching effect can be improved, and the message reaching rate can be comprehensively improved.
Compared with the mode that the network service platform pushes the notification message to the user in time after the current user triggers the event at the client and the user performs one-time action intervention, the message pushing method provided by the embodiment of the invention can acquire the target end event triggered by the user at the client; sequencing a plurality of pushing strategies corresponding to the target end event based on the attribute characteristics corresponding to the user, wherein each pushing strategy at least comprises two intervention actions; meanwhile, determining an executable target push strategy from the multiple push strategies according to the sequencing results of the multiple push strategies; and finally, based on the target pushing strategy, sequentially pushing corresponding notification messages to the user. Therefore, a target pushing strategy is screened from multiple pushing strategies, corresponding notification messages are sequentially sent based on at least two intervention actions in the target pushing strategy, a series of interventions are conducted on a user, the message reaching effect can be improved, meanwhile, the message reaching rate can be comprehensively improved through application of the intervention actions in the pushing strategy, in addition, the pushing messages can be prevented from being limited by a single expression form through measurement of multiple pushing strategies, and therefore result deviation is caused, and the message reaching effect is influenced.
Further, as a refinement and an extension of the specific implementation of the above embodiment, another message pushing method is provided, as shown in fig. 2, the method includes:
step 201, a target end event triggered by a user at a client end is obtained.
For the embodiment of the present invention, after acquiring a target end event triggered by a user at a client, a server needs to determine whether the target end event meets a corresponding trigger condition, specifically, if the target end event is an end exit event of the user, it needs to detect whether the user enters the client again within a first preset time (for example, 30 s) after exiting the client, and if the user does not enter the client again within the first preset time after exiting the client, it indicates that the end exit event meets the trigger condition; if the target end event is an entry end event of the user, detecting whether the user exits the client again within a second preset time (such as 5 s) after entering the client, and if the user does not exit the client within the second preset time after entering the client, indicating that the entry end event meets the triggering condition; if the target end event is a search event, detecting whether the time for searching for categories (such as a barbecue string and a hot pot) on a search page by a user exceeds a third preset time (such as 10 s), and if the time for searching by the user exceeds the third preset time, indicating that the search event meets a trigger condition; if the target end event is a shop page event, whether the browsing time of a user in a certain shop exceeds a fourth preset time (such as 5 s) needs to be detected, and if the browsing time of the user exceeds the fourth preset time, the shop page event meets the triggering condition; if the target end event is a bill picking event, whether the duration of non-payment after ordering by the user exceeds a fifth preset duration (such as 20 s) needs to be detected, and if the duration of non-payment after ordering by the user exceeds the fifth preset duration, the bill picking event meets the triggering condition. Therefore, whether different types of target end events meet corresponding trigger conditions or not can be detected according to the method, and if the target end events meet the corresponding trigger conditions, multiple push strategies corresponding to the target end events are obtained.
Step 202, analyzing the attribute characteristics corresponding to the user based on multiple decision factors related to the target end event to obtain analysis results corresponding to the multiple decision factors respectively.
For the embodiment of the present invention, in order to sequence multiple push policies corresponding to a target end event, multiple aspects of analysis need to be performed on attribute features of a user, so that multiple decision factors are set in the embodiment of the present invention, specifically including a preference factor, a location factor, a rights and interests factor, and the like, and multiple aspects of analysis can be performed on the attribute features of the user through the above factors, based on which step 202 specifically includes: and analyzing attribute characteristics corresponding to the user respectively based on the preference factor, the position factor and the right factor related to the target end event to obtain stores and categories preferred by the user, the predicted position of the user and the virtual resources currently owned by the user. The predicted position is position information of the user at a certain time point in the future.
Specifically, based on the preference factor, the browsing amount of some shops browsed by the user before or the order placing amount of some categories by the user before are counted, and if the browsing amount of the user to a certain shop exceeds a certain amount, the shop is a shop preferred by the user; if the order amount of a certain class by the user exceeds a certain amount, the class is the class which is preferred by the user. Meanwhile, various virtual resources currently owned by the user are counted based on the right factor.
Further, in determining the predicted location of the user, the method further comprises: and analyzing the user historical behavior characteristics in the attribute characteristics based on the position factor related to the target end event and the current position information of the user to obtain the predicted position of the user.
Specifically, by analyzing the historical behavior characteristics of the user, the user is found to be at home at 9 am every Monday to Friday, and 11 am is in units, and since the current time is 9 am of Monday and the user is at home, the user can be predicted to reach units at 11 am today, and therefore the position information of the user two hours later can be predicted.
In a specific application scenario, target variables related to different push policies are different, for example, the target variable related to the push policy issued by the virtual resource is the number of the virtual resource, the target variable related to the store push policy is a store name, and the target variable related to the class push policy is a class name. In the embodiment of the present invention, after determining the analysis result, it is further required to determine a variable value of the target variable involved in each push policy according to the analysis result.
For example, the analysis result is that the virtual resource currently owned by the user is 15 yuan, and it is determined through calculation that a 6-yuan user may place an order for a certain category, so that it is determined that the target variable in the push policy issued by the virtual resource is 6 yuan. For another example, the analysis result is the store name a preferred by the user, and thus the target variable in the store push policy is determined to be the store name a. Thus, according to the analysis result, the target variable values related to the multiple push strategies of the target end event can be determined, so that the notification message template can be completed by utilizing the target variable values when the notification message is pushed.
Step 203, sorting the multiple push strategies corresponding to the target end event according to the analysis result, so as to obtain a sorting result of the multiple push strategies corresponding to the target end event.
For the embodiment of the present invention, in order to order multiple push policies, step 203 specifically includes: and sequencing the multiple pushing strategies corresponding to the target end event according to the shop and the category preferred by the user, the predicted position and the virtual resource currently owned by the user to obtain the sequencing result. Specifically, the process of sorting the multiple push strategies according to the preferred stores and categories of the user, the predicted location, and the virtual resources currently owned by the user is the same as that in step 102, and is not described herein again.
In a specific application scenario, in order to improve the accuracy of pushing policy ordering, when determining virtual resources currently owned by a user, the interest level of the user in different types of virtual resources also needs to be analyzed. Based on this, analyzing the attribute characteristics corresponding to the user based on the interest factor related to the target end event to obtain the virtual resource currently owned by the user, including: and analyzing the attribute characteristics corresponding to the user based on the interest factors to obtain the virtual resources currently owned by the user and the interest degree of the user for different types of virtual resources. Meanwhile, the sorting the multiple push strategies corresponding to the target end event according to the stores and the categories preferred by the user, the predicted position and the virtual resources currently owned by the user to obtain the sorting result includes: and sequencing the multiple pushing strategies corresponding to the target end event according to the shop and the category preferred by the user, the predicted position, the virtual resource currently owned by the user and the interestingness to obtain the sequencing result.
For example, it is determined that the user does not currently have any virtual resource and is already used by the user, and in addition, the interestingness of the user for different types of virtual resources is determined by analyzing the attribute characteristics of the user, that is, analyzing the times that the user uses various types of virtual resources in the past, for example, the user is determined to use the virtual resource of type a 10 times and the virtual resource of type B6 times by analysis, so that the interestingness of the user for the virtual resource of type a is determined to be higher than the interestingness of the user for the virtual resource of type B. Further, in the subsequent process of ordering the multiple push strategies, the ordering position of the push strategy for issuing the type a virtual resource needs to be prior to the ordering position of the push strategy for issuing the type B virtual resource.
It should be noted that, in the process of sorting multiple push policies, if the same notification message is sent by using the same push policy last time, the push policy may be filtered out, or the sorting position of the push policy may be placed behind.
And 204, determining an executable target push strategy from the multiple push strategies according to the sequencing results of the multiple push strategies.
For the embodiment of the present invention, the process of determining the executable target push policy from the multiple push policies is the same as step 103, and is not described herein again.
And 205, sequentially pushing corresponding notification messages to the user based on the target pushing strategy.
For the embodiment of the present invention, in the process of pushing the notification message to the user according to the intervention action in the target pushing policy, step 205 specifically includes: generating notification messages corresponding to the at least two intervention actions according to the variable value and the notification message templates corresponding to the at least two intervention actions in the target pushing strategy; and sequentially pushing notification messages corresponding to the at least two intervention actions to the user according to the message channels corresponding to the at least two intervention actions in the target pushing strategy.
For example, the target push strategy is a shop push strategy, the first intervention action in the shop push strategy is waiting for two hours, so that no notification message is pushed to the user within two hours, the second intervention action is pushing the user's preferred shop to the user using the message channel a after two hours, specifically, after two hours, completing the corresponding notification message template according to the target variable (shop name a) involved in the shop push strategy, i.e. adding the shop name a to the corresponding position of the notification message template, generating the corresponding notification message, and sending the notification message pushed by the shop to the user using the message channel a, further, the third intervention action is pushing the notification message to the user again using the message channel B if the user does not read the notification message or is not interested in the third intervention action, specifically, if the 11-point user does not read the notification message yet, the notification message pushed by the shop can be sent again to the user using the message channel B. Therefore, through a plurality of series of intervention actions in the target pushing strategy, the user can be intervened for a plurality of times, so that the message pushing effect can be improved, and the message triggering rate can be comprehensively improved.
In a specific application scenario, if a virtual resource issuing action exists in a target push policy, generating, according to the variable value and a notification message template corresponding to each of the at least two intervention actions in the target push policy, a notification message corresponding to each of the at least two intervention actions, including: based on the variable value, issuing corresponding virtual resources to the user; and generating a notification message issued by the virtual resource according to the notification message template corresponding to the virtual resource issuing action and the variable value. Meanwhile, according to the message channel corresponding to the virtual resource issuing action, the notification message issued by the virtual resource is pushed to the user.
For example, if the target variable value involved in the push policy of the virtual resource issuing action is a 6-tuple virtual resource, the 6-tuple virtual resource is issued to the user first, then the corresponding notification message template is filled according to the 6-tuple virtual resource, a notification message issued by the virtual resource is generated, and further, the notification message issued by the virtual resource is sent to the user by using the corresponding message channel. Therefore, in the embodiment of the invention, not only the pushing of the notification message can be realized, but also the issuing of rights and interests such as virtual resources can be realized, so that the ordering conversion rate of a user can be improved.
Compared with the mode that the network service platform pushes the notification message to the user in time after the user triggers the event at the client and performs one-time action intervention on the user, the other message pushing method provided by the embodiment of the invention can acquire the target end event triggered by the user at the client; sequencing a plurality of pushing strategies corresponding to the target end event based on the attribute characteristics corresponding to the user, wherein each pushing strategy at least comprises two intervention actions; meanwhile, determining an executable target push strategy from the multiple push strategies according to the sequencing results of the multiple push strategies; and finally, based on the target pushing strategy, sequentially pushing corresponding notification messages to the user. Therefore, a target pushing strategy is screened from multiple pushing strategies, corresponding notification messages are sequentially sent based on at least two intervention actions in the target pushing strategy, a series of interventions are conducted on a user, the message reaching effect can be improved, meanwhile, the message reaching rate can be comprehensively improved through application of the intervention actions in the pushing strategy, in addition, the pushing messages can be prevented from being limited by a single expression form through measurement of multiple pushing strategies, and therefore result deviation is caused, and the message reaching effect is influenced.
Further, as a specific implementation of the method shown in fig. 1, this embodiment provides a message pushing apparatus, as shown in fig. 3, the apparatus includes: an acquisition unit 31, a sorting unit 32, a determination unit 33 and a push unit 34.
The obtaining unit 31 may be configured to obtain a target event triggered by a user at a client.
The sorting unit 32 may be configured to sort, based on the attribute feature corresponding to the user, multiple push policies corresponding to the target end event, where each push policy includes at least two intervention actions.
The determining unit 33 may be configured to determine an executable target push policy from the multiple push policies according to the sorting result of the multiple push policies.
The pushing unit 34 may be configured to sequentially push corresponding notification messages to the user based on the target pushing policy.
In a specific application scenario, as shown in fig. 4, the sorting unit 32 includes: an analysis module 321 and a ranking module 322.
The analysis module 321 may be configured to analyze attribute features corresponding to the user based on multiple decision factors related to the target end event, so as to obtain analysis results corresponding to the multiple decision factors, respectively.
The sorting module 322 may be configured to sort, according to the analysis result, the multiple push policies corresponding to the target end event, so as to obtain a sorting result of the multiple push policies corresponding to the target end event.
In a specific application scenario, the sorting unit 32 further includes a first determining module 323.
The first determining module 323 may be configured to determine, according to the analysis result, variable values corresponding to target variables respectively related to the multiple push policies.
In a specific application scenario, the analysis module 321 may be specifically configured to analyze attribute features corresponding to the user based on a preference factor, a location factor, and a rights factor related to the target event, respectively, to obtain a store and a category preferred by the user, a predicted location of the user, and a virtual resource currently owned by the user.
The sorting module 322 may be specifically configured to sort, according to the store and the category preferred by the user, the predicted location, and the virtual resource currently owned by the user, the multiple push strategies corresponding to the target event to obtain the sorting result.
In a specific application scenario, the analysis module 321 may be further specifically configured to analyze the user historical behavior feature in the attribute feature based on the location factor related to the target end event and the current location information of the user, so as to obtain a predicted location of the user; and analyzing the attribute characteristics corresponding to the user based on the interest factors to obtain the virtual resources currently owned by the user and the interest degree of the user for different types of virtual resources.
The sorting module 322 may be further specifically configured to sort, according to the store and the category preferred by the user, the predicted location, the virtual resource currently owned by the user, and the interest level, the multiple push strategies corresponding to the target event to obtain the sorting result.
In a specific application scenario, the determining unit 33 may be specifically configured to sequentially perform feasibility verification on the multiple push policies according to the sorting results of the multiple push policies, and determine the target push policy from the multiple push policies according to the feasibility verification results.
Further, the determining unit 33 includes: a verification module 331 and a second determination module 332.
The verification module 331 may be configured to perform feasibility verification on the first ranked push policy.
The second determining module 332 may be configured to determine the first-ranked push policy as the target push policy if the first-ranked push policy passes the feasibility verification.
The verification module 331 may be further configured to, if the first ranked push policy fails to pass the feasibility verification, continue to perform the feasibility verification on the second ranked push policy until the target push policy is determined.
Further, the verification module 331 may be specifically configured to collect the real-time user characteristics corresponding to the first sorted push policy; and carrying out feasibility verification on the first sorted pushing strategy based on the real-time characteristics of the user.
In a specific application scenario, the pushing unit 34 includes a generating module 341 and a pushing module 342.
The generating module 341 may be configured to generate the notification message corresponding to each of the at least two intervention actions according to the variable value and the notification message template corresponding to each of the at least two intervention actions in the target push policy.
The pushing module 342 may be configured to sequentially push notification messages corresponding to the at least two intervention actions to the user according to message channels corresponding to the at least two intervention actions in the target pushing policy.
Further, the generating module 341 may be specifically configured to issue, based on the variable value, a corresponding virtual resource to the user; and generating a notification message issued by the virtual resource according to the notification message template corresponding to the virtual resource issuing action and the variable value.
The pushing module 342 may be specifically configured to push the notification message issued by the virtual resource to the user according to the message channel corresponding to the virtual resource issuing action.
In a specific application scenario, the determining unit 33 may be further configured to determine, according to a target group to which the user belongs, multiple push policies corresponding to different types of end events related to the target group from a preset push policy library; and determining a plurality of push strategies corresponding to the target end event according to the plurality of push strategies corresponding to the end events of different types.
In a specific application scenario, the apparatus further includes: a configuration unit 35 and a storage unit 36.
The configuration unit 35 may be configured to configure, for the target group, multiple push policies corresponding to different types of end events, where each push policy includes at least two intervention actions, and a notification message template and a message channel corresponding to each intervention action.
The storage unit 36 may be configured to store multiple push policies corresponding to different types of end events related to the target group in the preset push policy library.
It should be noted that other corresponding descriptions of the functional units related to the message pushing apparatus provided in this embodiment may refer to the corresponding descriptions in fig. 1 and fig. 2, and are not described herein again.
Based on the methods shown in fig. 1 and fig. 2, correspondingly, the embodiment of the present application further provides a storage medium, on which a computer program is stored, and the computer program, when executed by a processor, implements the message pushing method shown in fig. 1 and fig. 2.
Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (which may be a CD-ROM, a usb disk, a removable hard disk, etc.), and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method of the embodiments of the present application.
Based on the method shown in fig. 1 and fig. 2 and the virtual device embodiment shown in fig. 3 and fig. 4, in order to achieve the above object, the present application further provides a computer device, as shown in fig. 5, where the computer device includes a storage medium and a processor; a storage medium for storing a computer program; a processor for executing a computer program to implement the message pushing method as described above in fig. 1 and 2.
Optionally, the above entity devices may further include a user interface, a network interface, a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, and the like. The user interface may include a Display screen (Display), an input unit such as a keypad (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), etc.
It will be understood by those skilled in the art that the client device architecture provided in the present embodiment does not constitute a limitation of such physical devices, and may include more or fewer components, or some components in combination, or a different arrangement of components.
The storage medium may further include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the two physical devices described above, supporting the operation of the information processing program as well as other software and/or programs. The network communication module is used for realizing communication among components in the storage medium and communication with other hardware and software in the information processing entity device.
Through the above description of the embodiments, those skilled in the art can clearly understand that the present application can acquire a target-side event triggered by a user at a client; sequencing a plurality of pushing strategies corresponding to the target end event based on the attribute characteristics corresponding to the user, wherein each pushing strategy at least comprises two intervention actions; meanwhile, determining an executable target push strategy from the multiple push strategies according to the sequencing results of the multiple push strategies; and finally, based on the target pushing strategy, sequentially pushing corresponding notification messages to the user. Therefore, a target pushing strategy is screened from multiple pushing strategies, corresponding notification messages are sequentially sent based on at least two intervention actions in the target pushing strategy, a series of interventions are conducted on a user, the message reaching effect can be improved, meanwhile, the message reaching rate can be comprehensively improved through application of the intervention actions in the pushing strategy, in addition, the pushing messages can be prevented from being limited by a single expression form through measurement of multiple pushing strategies, and therefore result deviation is caused, and the message reaching effect is influenced.
Those skilled in the art will appreciate that the figures are merely schematic representations of one preferred implementation scenario and that the blocks or flow diagrams in the figures are not necessarily required to practice the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario may be distributed in the devices in the implementation scenario according to the description of the implementation scenario, or may be located in one or more devices different from the present implementation scenario with corresponding changes. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above application serial numbers are for description purposes only and do not represent the superiority or inferiority of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of the present application, but the present application is not limited thereto, and any variations that can be made by those skilled in the art are intended to fall within the scope of the present application.

Claims (13)

1. A message pushing method, comprising:
acquiring a target end event triggered by a user at a client;
sequencing a plurality of pushing strategies corresponding to the target end event based on the attribute characteristics corresponding to the user, wherein each pushing strategy at least comprises two intervention actions;
determining an executable target push strategy from the multiple push strategies according to the sequencing results of the multiple push strategies;
and based on the target pushing strategy, sequentially pushing corresponding notification messages to the user.
2. The method according to claim 1, wherein the sorting the plurality of push policies corresponding to the target-side event based on the attribute characteristics corresponding to the user comprises:
analyzing attribute characteristics corresponding to the user based on a plurality of decision factors related to the target end event to obtain analysis results corresponding to the decision factors respectively;
sequencing the multiple push strategies corresponding to the target end event according to the analysis result to obtain a sequencing result of the multiple push strategies corresponding to the target end event;
wherein the method further comprises:
and determining variable values corresponding to the target variables respectively related to the multiple push strategies according to the analysis result.
3. The method according to claim 2, wherein the analyzing the attribute features corresponding to the user based on a plurality of decision factors related to the target event to obtain analysis results corresponding to the plurality of decision factors respectively comprises:
analyzing attribute characteristics corresponding to the user respectively based on a preference factor, a position factor and a rights factor related to the target end event to obtain stores and categories preferred by the user, a predicted position of the user and virtual resources currently owned by the user;
the sorting the multiple push strategies corresponding to the target end event according to the analysis result to obtain a sorting result of the multiple push strategies corresponding to the target end event includes:
and sequencing the multiple pushing strategies corresponding to the target end event according to the shop and the category preferred by the user, the predicted position and the virtual resource currently owned by the user to obtain the sequencing result.
4. The method according to claim 3, wherein analyzing the attribute features corresponding to the user based on the location factor and the interest factor related to the target event respectively to obtain the predicted location of the user and the virtual resource currently owned by the user comprises:
analyzing the user historical behavior characteristics in the attribute characteristics based on the position factor related to the target end event and the current position information of the user to obtain the predicted position of the user;
analyzing attribute characteristics corresponding to the user based on the rights and interests factor to obtain virtual resources currently owned by the user and the interest degree of the user for different types of virtual resources;
the sorting the multiple push strategies corresponding to the target end event according to the shop and the category preferred by the user, the predicted position and the virtual resource currently owned by the user to obtain the sorting result comprises the following steps:
and sequencing the multiple pushing strategies corresponding to the target end event according to the shop and the category preferred by the user, the predicted position, the virtual resource currently owned by the user and the interestingness to obtain the sequencing result.
5. The method of claim 1, wherein determining an executable target push policy from the plurality of push policies according to the sorted results of the plurality of push policies comprises:
and sequentially carrying out feasibility verification on the multiple push strategies according to the sequencing results of the multiple push strategies, and determining the target push strategy from the multiple push strategies according to the feasibility verification result.
6. The method according to claim 5, wherein the sequentially performing feasibility verification on the plurality of push strategies according to the ranking result of the plurality of push strategies, and determining the target push strategy from the plurality of push strategies according to the feasibility verification result comprises:
carrying out feasibility verification on the first sorted pushing strategy;
if the first-ranked push strategy passes the feasibility verification, determining the first-ranked push strategy as the target push strategy;
and if the first-ranked push strategy does not pass the feasibility verification, continuing to perform the feasibility verification on the second-ranked push strategy until the target push strategy is determined.
7. The method of claim 6, wherein performing feasibility verification on the first-ranked push policy comprises:
collecting user real-time characteristics corresponding to the first sorted pushing strategy;
and carrying out feasibility verification on the first sorted pushing strategy based on the real-time characteristics of the user.
8. The method according to claim 2, wherein the pushing the corresponding notification messages to the user in sequence based on the target pushing policy comprises:
generating notification messages corresponding to the at least two intervention actions according to the variable value and the notification message templates corresponding to the at least two intervention actions in the target pushing strategy;
and sequentially pushing notification messages corresponding to the at least two intervention actions to the user according to the message channels corresponding to the at least two intervention actions in the target pushing strategy.
9. The method according to claim 8, wherein if there is a virtual resource issuing action in at least two intervention actions of the target push policy, the generating notification messages corresponding to the at least two intervention actions respectively according to the variable value and the notification message templates corresponding to the at least two intervention actions respectively in the target push policy includes:
based on the variable value, issuing corresponding virtual resources to the user;
generating a notification message issued by the virtual resource according to the notification message template corresponding to the virtual resource issuing action and the variable value;
the sequentially pushing notification messages corresponding to the at least two intervention actions to the user according to the message channels corresponding to the at least two intervention actions in the target pushing strategy comprises:
and pushing the notification message issued by the virtual resource to the user according to the message channel corresponding to the virtual resource issuing action.
10. The method according to claim 1, wherein before the sorting the plurality of push policies corresponding to the target-side event based on the attribute characteristics corresponding to the user, the method further comprises:
determining a plurality of push strategies corresponding to different types of end events related to the target crowd from a preset push strategy library according to the target crowd to which the user belongs;
determining a plurality of push strategies corresponding to the target end event according to the plurality of push strategies corresponding to the end events of different types;
before the obtaining of the target-side event triggered by the user at the client, the method further includes:
configuring a plurality of pushing strategies corresponding to different types of end events aiming at the target crowd, wherein each pushing strategy comprises at least two intervention actions, and a notification message template and a message channel corresponding to each intervention action;
and storing a plurality of push strategies corresponding to different types of end events related to the target crowd into the preset push strategy library.
11. A message push apparatus, comprising:
the acquisition unit is used for acquiring a target end event triggered by a user at a client;
the ordering unit is used for ordering a plurality of pushing strategies corresponding to the target end event based on the attribute characteristics corresponding to the user, wherein each pushing strategy at least comprises two intervention actions;
a determining unit, configured to determine, according to a sorting result of the multiple push policies, an executable target push policy from the multiple push policies;
and the pushing unit is used for sequentially pushing corresponding notification messages to the user based on the target pushing strategy.
12. A storage medium having stored thereon a computer program, characterized in that the computer program, when being executed by a processor, implements the message pushing method of any one of claims 1 to 10.
13. A computer device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the message pushing method according to any one of claims 1 to 10 when executing the computer program.
CN202210165324.5A 2022-02-23 2022-02-23 Message pushing method and device Active CN114244897B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210165324.5A CN114244897B (en) 2022-02-23 2022-02-23 Message pushing method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210165324.5A CN114244897B (en) 2022-02-23 2022-02-23 Message pushing method and device

Publications (2)

Publication Number Publication Date
CN114244897A true CN114244897A (en) 2022-03-25
CN114244897B CN114244897B (en) 2022-08-30

Family

ID=80747789

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210165324.5A Active CN114244897B (en) 2022-02-23 2022-02-23 Message pushing method and device

Country Status (1)

Country Link
CN (1) CN114244897B (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150120849A1 (en) * 2013-10-30 2015-04-30 Qwasi, Inc. Systems and methods for push notification management
WO2015132581A1 (en) * 2014-03-03 2015-09-11 Powa Technologies Limited Devices, systems and methods for message delivery
US20180276734A1 (en) * 2016-07-12 2018-09-27 Tencent Technology (Shenzhen) Company Limited Information push method and apparatus, server, and storage medium
US20180352398A1 (en) * 2015-08-20 2018-12-06 Shanghai Chule (Coo Tek) Information Technology Co., Ltd Method, Device And User Equipment For Pushing Service Information
US20180374141A1 (en) * 2017-06-27 2018-12-27 Alibaba Group Holding Limited Information pushing method and system
CN111898023A (en) * 2020-07-24 2020-11-06 北京口袋财富信息科技有限公司 Message pushing method and device, readable storage medium and computing equipment
US20210067598A1 (en) * 2019-09-03 2021-03-04 International Business Machines Corporation Post-delivery dynamic control of notifications in a push notification life-cycle
US10999416B1 (en) * 2020-12-09 2021-05-04 Coupang Corp. Systems and methods for recurrent and adaptive electronic notifications
CN113821721A (en) * 2021-09-17 2021-12-21 平安养老保险股份有限公司 User portrait based multi-channel message method and device and computer equipment

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150120849A1 (en) * 2013-10-30 2015-04-30 Qwasi, Inc. Systems and methods for push notification management
WO2015132581A1 (en) * 2014-03-03 2015-09-11 Powa Technologies Limited Devices, systems and methods for message delivery
US20180352398A1 (en) * 2015-08-20 2018-12-06 Shanghai Chule (Coo Tek) Information Technology Co., Ltd Method, Device And User Equipment For Pushing Service Information
US20180276734A1 (en) * 2016-07-12 2018-09-27 Tencent Technology (Shenzhen) Company Limited Information push method and apparatus, server, and storage medium
US20180374141A1 (en) * 2017-06-27 2018-12-27 Alibaba Group Holding Limited Information pushing method and system
US20210067598A1 (en) * 2019-09-03 2021-03-04 International Business Machines Corporation Post-delivery dynamic control of notifications in a push notification life-cycle
CN111898023A (en) * 2020-07-24 2020-11-06 北京口袋财富信息科技有限公司 Message pushing method and device, readable storage medium and computing equipment
US10999416B1 (en) * 2020-12-09 2021-05-04 Coupang Corp. Systems and methods for recurrent and adaptive electronic notifications
CN113821721A (en) * 2021-09-17 2021-12-21 平安养老保险股份有限公司 User portrait based multi-channel message method and device and computer equipment

Also Published As

Publication number Publication date
CN114244897B (en) 2022-08-30

Similar Documents

Publication Publication Date Title
KR100692209B1 (en) Method and system for providing information of commodity customized to each user
CN108733706B (en) Method and device for generating heat information
KR101753481B1 (en) Monitoring and changing system for price fluctuations of open market
CN106911801B (en) method for associating user information and information pushing system
CN107784504B (en) Method for generating return visit event of client and terminal equipment
CN107426328B (en) Information pushing method and device
JP2019508756A (en) Method and apparatus for selecting and recommending objects on an electronic delivery platform
JP2009193465A (en) Information processor, information providing system, information processing method, and program
CN111899068A (en) Commodity shopping guide method and device, storage medium and computer equipment
CN108629605A (en) Real-time questionnaire method for pushing based on online customer service
CN111242709A (en) Message pushing method and device, equipment and storage medium thereof
CN111738785A (en) Product selection method, system and storage medium
CN108737486A (en) Information-pushing method and device
EP3543943A1 (en) Purchase information utilization system, purchase information utilization method, and program
CN108833488A (en) A kind of method for pushing and server of recommendation information
CN111612085A (en) Method and device for detecting abnormal point in peer-to-peer group
CN109919704A (en) A kind of distribution method of resource data, apparatus and system
CN114244897B (en) Message pushing method and device
CN112215657A (en) Recommended commodity determining method and device, electronic equipment and storage medium
CN113158032B (en) Information pushing method and device
CN114841781A (en) Commodity information recommendation method, device, equipment and medium
CN111026981B (en) Visual display method, device and equipment for hot topics
CN111784434A (en) Dish information pushing method and device and electronic equipment
CN113327146A (en) Information tracking method and device
CN112347347A (en) User production content pushing method and server

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant