WO2020082733A1 - 基于业务规则的消息推送请求流量控制方法、装置及介质 - Google Patents

基于业务规则的消息推送请求流量控制方法、装置及介质 Download PDF

Info

Publication number
WO2020082733A1
WO2020082733A1 PCT/CN2019/089152 CN2019089152W WO2020082733A1 WO 2020082733 A1 WO2020082733 A1 WO 2020082733A1 CN 2019089152 W CN2019089152 W CN 2019089152W WO 2020082733 A1 WO2020082733 A1 WO 2020082733A1
Authority
WO
WIPO (PCT)
Prior art keywords
push
message
threshold
business
request
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.)
Ceased
Application number
PCT/CN2019/089152
Other languages
English (en)
French (fr)
Inventor
乐志能
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.)
Ping An Technology Shenzhen Co Ltd
Original Assignee
Ping An Technology Shenzhen 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 Ping An Technology Shenzhen Co Ltd filed Critical Ping An Technology Shenzhen Co Ltd
Publication of WO2020082733A1 publication Critical patent/WO2020082733A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/24Traffic characterised by specific attributes, e.g. priority or QoS
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/29Flow control; Congestion control using a combination of thresholds
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/50Network services
    • H04L67/55Push-based network services

Definitions

  • the present application relates to the technical field of big data analysis, and more specifically, to a method, device, and medium for message push request flow control based on business rules.
  • the purpose of the present application is to provide a method for controlling the flow of message push requests based on business rules for flow control of different service dimensions, an electronic device, and a computer-readable storage medium.
  • the present application provides an electronic device, the electronic device includes a memory and a processor, the memory includes a business rule-based message push request flow control program, the business rule-based message push request flow control When the program is executed by the processor, the following steps are realized:
  • the classification includes group push, single push, label push, and alias push.
  • the group push refers to The push-end pre-send message is sent to all pushed-ends related to the push-end;
  • the single push refers to sending the pre-send message from the push-end to a designated pushed-end;
  • the tag push refers to the push-end The pre-sent message is sent to the recommended end of the specified user tag;
  • the alias push refers to pushing the message pre-sent to the push end to the pushed end of the specified alias account;
  • the present application also provides a flow control method for message push requests based on business rules, including:
  • the classification includes group push, single push, label push, and alias push.
  • the group push refers to The push-end pre-send message is sent to all pushed-ends related to the push-end;
  • the single push refers to sending the pre-send message from the push-end to a designated pushed-end;
  • the tag push refers to the push-end The pre-sent message is sent to the recommended end of the specified user tag;
  • the alias push refers to pushing the message pre-sent to the push end to the pushed end of the specified alias account;
  • the present application also provides a computer-readable storage medium, the computer-readable storage medium includes a business rule-based message push request flow control program, the business rule-based message push request flow control When the program is executed by the processor, the steps of the method for controlling the flow of the message push request based on the business rules described above are implemented.
  • the method, device and medium for message push request flow control based on business rules described in this application perform message push flow control by controlling the business dimension of the push party message type (group push, single push, label push, alias push), which can be in different fields
  • the business rules of the company conduct flow control in different business dimensions to meet the needs of personalized flow control of the business.
  • FIG. 1 is a schematic diagram of an application environment of a preferred embodiment of a method for controlling message push request flow control based on a business rule of this application;
  • FIG. 2 is a schematic block diagram of a preferred embodiment of a flow control program for message push request based on business rules in FIG. 1;
  • FIG. 3 is a flowchart of a preferred embodiment of a method for controlling flow of a message push request based on business rules of the present application.
  • the present application provides a flow control method for message push requests based on business rules, which is applied to an electronic device 1.
  • FIG. 1 it is a schematic diagram of an application environment of a preferred embodiment of a method for controlling message push request flow control based on business rules of the present application.
  • the electronic device 1 may be a terminal device having a computing function such as a server, a mobile phone, a tablet computer, a portable computer, a desktop computer, or the like.
  • the electronic device 1 includes a memory 11, a processor 12, a network interface 13, and a communication bus 14.
  • the memory 11 includes at least one type of readable storage medium.
  • the at least one type of readable storage medium may be a non-volatile storage medium such as flash memory, hard disk, multimedia card, card-type memory 11, and the like.
  • the readable storage medium may be an internal storage unit of the electronic device 1, such as a hard disk of the electronic device 1.
  • the readable storage medium may also be the external memory 11 of the electronic device 1, such as a plug-in hard disk equipped on the electronic device 1, a smart memory card (Smart Memory Card, SMC) , Secure Digital (SD) card, Flash card (Flash Card), etc.
  • the readable storage medium of the memory 11 is generally used to store a business rule-based message push request flow control program 10 installed in the electronic device 1, a database, a pre-trained classifier, and a prediction model , Clustering model, etc.
  • the memory 11 can also be used to temporarily store data that has been or will be output.
  • the processor 12 may be a central processing unit (CPU), microprocessor, or other data processing chip, which is used to run program codes or process data stored in the memory 11, for example, to execute based on business rules The message push request flow control program 10 and so on.
  • CPU central processing unit
  • microprocessor or other data processing chip, which is used to run program codes or process data stored in the memory 11, for example, to execute based on business rules The message push request flow control program 10 and so on.
  • the network interface 13 may include a wireless network interface or a wired network interface, and the network interface 13 is generally used to establish a communication connection between the electronic device 1 and other electronic devices.
  • the network interface 13 is used to connect the electronic device 1 to an external terminal through a network, and establish a data transmission channel and a communication connection between the electronic device 1 and the external terminal.
  • the network may be Intranet, Internet, Global System of Mobile (GSM), Wideband Code Division Multiple Access (WCDMA), 4G network, 5G network , Bluetooth (Bluetooth), Wi-Fi and other wireless or wired networks.
  • the communication bus 14 is used to realize connection and communication between these components.
  • FIG. 1 only shows the electronic device 1 having the components 11-14, but it should be understood that not all components shown are required to be implemented, and more or fewer components may be implemented instead.
  • the electronic device 1 may further include a user interface
  • the user interface may include an input unit such as a keyboard, a voice input device such as a microphone (microphone) and other devices with voice recognition functions, and a voice output device such as a stereo and headphones, etc.
  • the user interface may also include a standard wired interface and a wireless interface.
  • the electronic device 1 may further include a display, and the display may also be called a display screen or a display unit.
  • it may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an organic light-emitting diode (OLED) touch device, or the like.
  • the display is used to display information processed in the electronic device 1 and to display a visual user interface.
  • the electronic device 1 further includes a touch sensor.
  • the area provided by the touch sensor for the user to perform a touch operation is called a touch area.
  • the touch sensor described herein may be a resistive touch sensor, a capacitive touch sensor, or the like.
  • the touch sensor includes not only a touch-type touch sensor but also a proximity-type touch sensor and the like.
  • the touch sensor may be a single sensor or a plurality of sensors arranged in an array, for example.
  • the electronic device 1 may further include logic gate circuits, sensors, audio circuits, etc., which will not be repeated here.
  • the memory 11 as a computer storage medium may include an operating system and a message push request flow control program 10; the processor 12 executes the message push request flow control program stored in the memory 11 At 10 o'clock, the following steps are implemented:
  • the classification includes group push, single push, label push, and alias push.
  • the group push refers to The push-end pre-send message is sent to all pushed-ends related to the push-end;
  • the single push refers to sending the pre-send message from the push-end to a designated pushed-end;
  • the tag push refers to the push-end The pre-sent message is sent to the recommended end of the specified user tag.
  • the user tag can be set, obtained from the push end, or obtained from the network through web crawler technology;
  • the alias push refers to push
  • the message pre-sent to the terminal is pushed to the pushed end of the alias account specified for sending, and the alias account may be the user ID of the pushed end set by the pushing end;
  • the processor After obtaining the requested amount of message push for a set time, the processor performs a timing task of clearing the requested amount, and resets the requested amount of message push for each business dimension.
  • the processor assigns different weights to different business dimensions, when the sum of the message push requests of all business dimensions exceeds a set threshold or the message push requests of a business dimension with a greater weight exceeds the set threshold , Increase the threshold of the business dimension with a larger weight, and decrease the threshold of the business dimension with a smaller weight.
  • the message push request flow control program 10 may also be divided into one or more modules, and the one or more modules are stored in the memory 11 and executed by the processor 12 to complete the present application.
  • the module referred to in this application refers to a series of computer program instruction segments capable of performing specific functions.
  • FIG. 2 it is a functional block diagram of a preferred embodiment of the message push request flow control program 10 in FIG. 1.
  • the message push request flow control program 10 may be divided into:
  • the transceiver module 110 obtains the messages pre-sent by the push end;
  • the classifier 120 classifies messages, each category corresponds to a business dimension, and the classification includes group push, single push, label push, and alias push, where the group push refers to sending a pre-sent message from the push end to All pushed terminals related to the push terminal; the single push refers to sending messages pre-sent by the push terminal to a specified pushed terminal; the tag push refers to sending messages pre-sent by the push terminal to the designated The recommended end of the user tag; the alias push refers to pushing the message pre-sent to the push end to the pushed end of the alias account designated to be sent;
  • the setting module 130 sets the threshold of each business dimension
  • the detection module 140 detects the amount of requests pushed by each business dimension message at a set time
  • the judgment module 150 separately judges whether the message push request amount of each business dimension is not greater than the set threshold of the corresponding business dimension, and if the message push request amount of the business dimension is not greater than the corresponding threshold, sends a signal to the push module; If the request volume of the service dimension message push is greater than the corresponding threshold, an alarm signal with a message push request volume exceeding the threshold is sent to the transceiver module 110, thereby returning the alarm signal to the push end.
  • it further includes:
  • the sequence construction module through the detection module 140, constructs a time series of the request volume of the message request volume of each business dimension changing with time;
  • the prediction module predicts the message request volume of the service dimension in the future time through a prediction model
  • the threshold adjustment module adjusts the threshold of each business dimension according to the predicted message request amount of each business dimension.
  • the classifier 120 further sets a classification label on the messages pre-pushed by the push end.
  • the message push request flow control program 10 further includes a clustering module that performs group push, label push or / and The alias pushed message clusters the pushed terminal according to the attention degree of the pushed terminal on the classification label, and sends the message to the pushed terminal after clustering.
  • the present application also provides a method for controlling the flow of message push requests based on business rules.
  • FIG. 3 it is a flowchart of a preferred embodiment of a method for controlling flow of a message push request of the present application.
  • the method may be executed by an apparatus, and the apparatus may be implemented by software and / or hardware.
  • the message push request flow control method includes:
  • Step S1 Obtain the message pre-sent by the push end, enter the classifier to classify the message, and each category corresponds to a business dimension;
  • Step S2 setting a threshold for each business dimension
  • Step S3 detecting the amount of requests pushed by each service dimension message at a set time (for example, 5s);
  • step S4 it is determined whether the amount of messages pushed for each business dimension is not greater than the set threshold of the corresponding business dimension
  • step S5a If the requested amount of service dimension message push is not greater than the corresponding threshold, in step S5a, the service dimension message is pushed.
  • step S5b If the request volume of the message push of the service dimension is greater than the corresponding threshold, in step S5b, an alarm signal that the request volume of the message push exceeds the threshold is returned to the push end.
  • it also includes giving different weights to different business dimensions.
  • the threshold of the business dimension with a greater weight is upgraded, and the business dimension with a smaller weight is degraded, that is, the threshold of the business dimension with a greater weight is increased, and the business dimension with a smaller weight is reduced.
  • the threshold where the weight can be assigned according to the importance of the business, the higher the importance of the business, the greater the weight, the larger and the smaller can be distinguished by setting a benchmark weight, the greater than the benchmark weight is greater, less than The reference weight is smaller, and can also be distinguished by the difference between the weights.
  • the difference exceeds the set range.
  • the two weights corresponding to the difference are the larger weight and the smaller weight, but this application does not Limited to this.
  • steps S3 and S4 are also included between steps S3 and S4:
  • it further includes:
  • Predict the amount of message requests for the business dimension in the future through the prediction model for example: build a prediction model of the neural network, train the prediction model, and substitute the time series of the request volume of each business dimension into the trained prediction model To obtain the message request volume of the business dimension in the future;
  • the method for predicting the message request volume of the service dimension in the future time through a prediction model includes:
  • At least one sequence length is used to divide the first sequence into a plurality of second sequences, the sequence length of the second sequence is shorter than the sequence length of the first sequence;
  • Constructing a dendrogram of the first sequence according to the second sequence including: taking each request volume appearing in the first sequence as a root node, combining various request volume in each second sequence as branches, each root node Each branch connected by the root node constitutes each sub-tree.
  • the frequency of the request volume represented by the root node in the first sequence is the node value of the root node, and the request volume represented by the root node to the child node is combined in each The sum of the frequencies appearing in the two sequences is the node value of the child node;
  • the probability can be calculated according to the following formula (1),
  • i represents the level index of the dendrogram of the first sequence
  • y 1 represents a root node of the subtree of the dendrogram
  • y 2 .
  • y i represents the root node of the subtree y 1
  • y 1 y 2 y i represents the second sequence of sequence length i corresponding to the branch
  • x represents the amount of requests to be predicted
  • y 1 y 2 y i ) represents the internal probability that the request quantity of the second sequence order is i + 1 is x
  • the child node is the node value of x
  • N (y i ) represents the node value of the node y i of the i-th layer of the branch;
  • the maximum value of the probability is used as the request amount in the next order.
  • it further includes:
  • the classification label includes the type of message (product push, notification, purchase, etc.), the identifier of the push end, the keyword of the message, etc .;
  • the attention degree may be the number of times the customer views the message, or it may be After obtaining the message, according to the behavior data of the message, for example, the number of product purchases based on the product push message;
  • the attention matrix of the pushed end is constructed
  • XB represents the information classification label set
  • m represents the number of pieces of information
  • x 1 ... x m is the name of the information
  • [fb m, 1 , ... fb m, k ] represents the information x m 1 to k classification labels
  • k represents the number of classification labels
  • j represents the number of non-zero and non-overlapping classification labels of information x 1 to x m , 0 ⁇ j ⁇ mk
  • G is the attention matrix
  • g nj refers to the degree of attention of the pushed terminal y n to the classification label b j .
  • the vectors in the attention matrix that make up the new cluster are added and averaged separately to obtain the clustering center of each new cluster;
  • the method further includes: analyzing the support and confidence of each classification label and its combination in the above attention matrix, and outputting the association rules of the classification label and its combination satisfying the minimum support or / and minimum confidence requirement, that is, the output is greater than the minimum Association rules supporting classification thresholds and / or minimum confidence thresholds and their combination, specifically:
  • the scan has the information classification label set, and the first classification label set is obtained according to the support of each non-zero and non-overlapping classification label.
  • the support degree (b j ) of the classification label b j is:
  • minsup is the minimum support threshold, which satisfies 0 ⁇ minsup ⁇ 1, which is a set value; a is the number of classification labels greater than the minimum support threshold, 0 ⁇ a ⁇ j, ft 1 ... ft a means The name of the classification label in the first classification label set FT of the classification label.
  • an association rule is generated: It indicates that the classification label or the combination of classification labels in the non-empty real subset that generates the association rule has a strong correlation with the classification label or the combination of classification labels in the complement set of the true subset.
  • an embodiment of the present application also provides a computer-readable storage medium including a business rule-based message push request flow control program, the business rule-based message push request flow control program The following steps are realized when the processor is executed:
  • the classification includes group push, single push, label push, and alias push.
  • the group push refers to The push-end pre-send message is sent to all pushed-ends related to the push-end;
  • the single push refers to sending the pre-send message from the push-end to a designated pushed-end;
  • the tag push refers to the push-end The pre-sent message is sent to the recommended end of the specified user tag;
  • the alias push refers to pushing the message pre-sent to the push end to the pushed end of the specified alias account;
  • the flow control method, electronic device and readable storage medium of the message push request based on the business rules described in this application realize flow control through the perspective of various business attributes of the push end, to meet the refined flow control requirements of the business, and at the same time associate the flow control with the business As a result, downgrade services through business dimensions to ensure the normal operation of core services.
  • the technical solution of the present application can be embodied in the form of a software product in essence or part that contributes to the existing technology, and the computer software product is stored in a storage medium (such as ROM / RAM) as described above , Magnetic disks, optical disks), including several instructions to enable a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to perform the method described in each embodiment of the present application.
  • a storage medium such as ROM / RAM
  • magnetic disks such as described above , Magnetic disks, optical disks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Information Transfer Between Computers (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

本申请涉及大数据分析,提供一种基于业务规则的消息推送请求流量控制方法,包括:获得推送端预发送的消息,输入分类器对消息进行分类,每一类对应一种业务维度,分类包括群推、单推、标签推、别名推;设定每种业务维度阈值;检测设定时间各业务维度消息推送的请求量;分别判断每种业务维度的消息推送的请求量是否不大于设定的对应的业务维度的阈值;如果不大于阈值,推送所述业务维度的消息;如果大于阈值,将消息推送的请求量超过阈值的报警信号返回推送端。本申请还提出了一种电子装置及计算机可读存储介质。本申请进行不同业务维度的流量控制,满足业务个性化流量控制的需求。

Description

基于业务规则的消息推送请求流量控制方法、装置及介质
本申请要求于2018年10月24日提交的中国专利申请号201811242274.6的优先权益,上述案件全部内容以引用的方式并入本文中。
技术领域
本申请涉及大数据分析技术领域,更为具体地,涉及一种基于业务规则的消息推送请求流量控制方法、装置及介质。
背景技术
随着网络技术的发展,用户使用网络运营商提供的服务,通过消耗一定的流量,进行网络访问,流量控制成为用户最关心的内容,目前大部分推送请求流量控制都是通过控制请求网络带宽流量或控制请求频次来控制,这样只能比较粗的控制系统级别的请求量,不能针对特定领域业务规则进行流量控制,不够灵活,也满足不了业务个性化流量控制的需求。
发明内容
鉴于上述问题,本申请的目的是提供一种进行不同业务维度的流量控制的基于业务规则的消息推送请求流量控制方法、电子装置和计算机可读存储介质。
为了实现上述目的,本申请提供一种电子装置,所述电子装置包括存储器和处理器,所述存储器中包括基于业务规则的消息推送请求流量控制程序,所述基于业务规则的消息推送请求流量控制程序被所述处理器执行时实现如下步骤:
获得推送端预发送的消息,输入分类器对消息进行分类,每一类对应一种业务维度,所述分类包括群推、单推、标签推、别名推,其中,所述群推是指将推送端预发送消息发送给与所述推送端有关的所有被推送端;所述单推是指将推送端预发送的消息发送给指定的一个被推送端;所述标签推送是 指将推送端预发送的消息发送给指定用户标签的被推荐端;所述别名推是指将推送端预发送给的消息推送给指定发送的别名账户的被推送端;
设定每种业务维度的阈值;
检测设定时间的各业务维度消息推送的请求量;
分别判断每种业务维度的消息推送的请求量是否不大于设定的对应的业务维度的阈值;
如果业务维度的消息推送的请求量不大于对应的阈值,推送所述业务维度的消息;
如果业务维度的消息推送的请求量大于对应的阈值,将消息推送的请求量超过阈值的报警信号返回推送端。
此外,为了实现上述目的,本申请还提供一种基于业务规则的消息推送请求流量控制方法,包括:
获得推送端预发送的消息,输入分类器对消息进行分类,每一类对应一种业务维度,所述分类包括群推、单推、标签推、别名推,其中,所述群推是指将推送端预发送消息发送给与所述推送端有关的所有被推送端;所述单推是指将推送端预发送的消息发送给指定的一个被推送端;所述标签推送是指将推送端预发送的消息发送给指定用户标签的被推荐端;所述别名推是指将推送端预发送给的消息推送给指定发送的别名账户的被推送端;
设定每种业务维度的阈值;
检测设定时间的各业务维度消息推送的请求量;
分别判断每种业务维度的消息推送的请求量是否不大于设定的对应的业务维度的阈值;
如果业务维度的消息推送的请求量不大于对应的阈值,推送所述业务维度的消息;
如果业务维度的消息推送的请求量大于对应的阈值,将消息推送的请求量超过阈值的报警信号返回推送端。
此外,为了实现上述目的,本申请还提供一种计算机可读存储介质,所述计算机可读存储介质中包括基于业务规则的消息推送请求流量控制程序,所述基于业务规则的消息推送请求流量控制程序被处理器执行时,实现上述的基于业务规则的消息推送请求流量控制方法的步骤。
本申请所述基于业务规则的消息推送请求流量控制方法、装置及介质通过控制推送方消息类型(群推、单推、标签推、别名推)的业务维度进行消息推送的流量控制,可以不同领域的业务规则进行不同业务维度的流量控制,满足业务个性化流量控制的需求。
附图说明
通过参考以下结合附图的说明,并且随着对本申请的更全面理解,本申请的其它目的及结果将更加明白及易于理解。在附图中:
图1是本申请基于业务规则的消息推送请求流量控制方法较佳实施例的应用环境示意图;
图2是图1中基于业务规则的消息推送请求流量控制程序较佳实施例的模块示意图;
图3是本申请基于业务规则的消息推送请求流量控制方法较佳实施例的流程图。
在所有附图中相同的标号指示相似或相应的特征或功能。
具体实施方式
应当理解,此处所描述的具体实施例仅仅用以解释本申请,并不用于限定本申请。
以下将结合附图对本申请的具体实施例进行详细描述。
本申请提供一种基于业务规则的消息推送请求流量控制方法,应用于一种电子装置1。参照图1所示,为本申请基于业务规则的消息推送请求流量控制方法较佳实施例的应用环境示意图。
在本实施例中,电子装置1可以是服务器、手机、平板电脑、便携计算机、桌上型计算机等具有运算功能的终端设备。
该电子装置1包括存储器11、处理器12、网络接口13及通信总线14。
存储器11包括至少一种类型的可读存储介质。所述至少一种类型的可读存储介质可为如闪存、硬盘、多媒体卡、卡型存储器11等的非易失性存储介质。在一些实施例中,所述可读存储介质可以是所述电子装置1的内部存储单元,例如该电子装置1的硬盘。在另一些实施例中,所述可读存储介质也 可以是所述电子装置1的外部存储器11,例如所述电子装置1上配备的插接式硬盘,智能存储卡(Smart Media Card,SMC),安全数字(Secure Digital,SD)卡,闪存卡(Flash Card)等。
在本实施例中,所述存储器11的可读存储介质通常用于存储安装于所述电子装置1的基于业务规则的消息推送请求流量控制程序10、数据库及预先训练好的分类器、预测模型、聚类模型等。所述存储器11还可以用于暂时地存储已经输出或者将要输出的数据。
处理器12在一些实施例中可以是一中央处理器(Central Processing Unit,CPU),微处理器或其他数据处理芯片,用于运行存储器11中存储的程序代码或处理数据,例如执行基于业务规则的消息推送请求流量控制程序10等。
网络接口13可包括无线网络接口或有线网络接口,该网络接口13通常用于在所述电子装置1与其他电子装置之间建立通信连接。例如,所述网络接口13用于通过网络将所述电子装置1与外部终端相连,在所述电子装置1与外部终端之间的建立数据传输通道和通信连接等。所述网络可以是企业内部网(Intranet)、互联网(Intemet)、全球移动通讯系统(Global System of Mobile communication,GSM)、宽带码分多址(Wideband CodeDivision Multiple Access,WCDMA)、4G网络、5G网络、蓝牙(Bluetooth)、Wi-Fi等无线或有线网络。
通信总线14用于实现这些组件之间的连接通信。
图1仅示出了具有组件11-14的电子装置1,但是应理解的是,并不要求实施所有示出的组件,可以替代的实施更多或者更少的组件。
可选地,该电子装置1还可以包括用户接口,用户接口可以包括输入单元比如键盘(Keyboard)、语音输入装置比如麦克风(microphone)等具有语音识别功能的设备、语音输出装置比如音响、耳机等,可选地用户接口还可以包括标准的有线接口、无线接口。
可选地,该电子装置1还可以包括显示器,显示器也可以称为显示屏或显示单元。
在一些实施例中可以是LED显示器、液晶显示器、触控式液晶显示器以及有机发光二极管(Organic Light-Emitting Diode,OLED)触摸器等。显示器用于显示在电子装置1中处理的信息以及用于显示可视化的用户界面。
可选地,该电子装置1还包括触摸传感器。所述触摸传感器所提供的供 用户进行触摸操作的区域称为触控区域。此外,这里所述的触摸传感器可以为电阻式触摸传感器、电容式触摸传感器等。而且,所述触摸传感器不仅包括接触式的触摸传感器,也可包括接近式的触摸传感器等。此外,所述触摸传感器可以为单个传感器,也可以为例如阵列布置的多个传感器。
可选地,该电子装置1还可以包括逻辑门电路,传感器、音频电路等等,在此不再赘述。
在图1所示的装置实施例中,作为一种计算机存储介质的存储器11中可以包括操作系统、以及消息推送请求流量控制程序10;处理器12执行存储器11中存储的消息推送请求流量控制程序10时实现如下步骤:
获得推送端预发送的消息,输入分类器对消息进行分类,每一类对应一种业务维度,所述分类包括群推、单推、标签推、别名推,其中,所述群推是指将推送端预发送消息发送给与所述推送端有关的所有被推送端;所述单推是指将推送端预发送的消息发送给指定的一个被推送端;所述标签推送是指将推送端预发送的消息发送给指定用户标签的被推荐端,所述用户标签可以设定,也可以从推送端获得,还可以是通过网络爬虫技术等从网络中获得;所述别名推是指将推送端预发送给的消息推送给指定发送的别名账户的被推送端,所述别名账户可以是推送端设定的被推送端的用户标识;
设定每种业务维度的阈值;
检测设定时间的各业务维度消息推送的请求量;
分别判断每种业务维度的消息推送的请求量是否不大于设定的对应的业务维度的阈值;
如果业务维度的消息推送的请求量不大于对应的阈值,推送所述业务维度的消息;
如果业务维度的消息推送的请求量大于对应的阈值,将消息推送的请求量超过阈值的报警信号返回推送端。
优选地,所述处理器在获得了设定时间的消息推送的请求量后,执行清除请求量的定时任务,对各业务维度的消息推送的请求量进行重置。
优选地,所述处理器对不同业务维度赋予不同的权重,当所有业务维度的消息推送的请求量之和超过设定阈值或者权重较大的业务维度的消息推送的请求量超过设定阈值时,增大所述权重较大的业务维度的阈值,减小权重 较小的业务维度的阈值。
在其他实施例中,所述消息推送请求流量控制程序10还可以被分割为一个或者多个模块,一个或者多个模块被存储于存储器11中,并由处理器12执行,以完成本申请。本申请所称的模块是指能够完成特定功能的一系列计算机程序指令段。参照图2所示,为图1中消息推送请求流量控制程序10较佳实施例的功能模块图。所述消息推送请求流量控制程序10可以被分割为:
收发模块110,获取推送端预发送的消息;
分类器120,对消息进行分类,每一类对应一种业务维度,所述分类包括群推、单推、标签推、别名推,其中,所述群推是指将推送端预发送消息发送给与所述推送端有关的所有被推送端;所述单推是指将推送端预发送的消息发送给指定的一个被推送端;所述标签推送是指将推送端预发送的消息发送给指定用户标签的被推荐端;所述别名推是指将推送端预发送给的消息推送给指定发送的别名账户的被推送端;
设定模块130,设定每种业务维度的阈值;
检测模块140,检测设定时间的各业务维度消息推送的请求量;
判断模块150,分别判断每种业务维度的消息推送的请求量是否不大于设定的对应的业务维度的阈值,如果业务维度的消息推送的请求量不大于对应的阈值,发送信号给推送模块;如果业务维度的消息推送的请求量大于对应的阈值,发送消息推送的请求量超过阈值的报警信号给收发模块110,从而将所述报警信号返回推送端。
在本申请的一个实施例中,还包括:
序列构建模块,通过检测模块140构建每一种业务维度的消息请求量随时间变化的请求量时间序列;
预测模块,通过预测模型预测未来时间的所述业务维度的消息请求量;
阈值调整模块,根据预测的各业务维度的消息请求量调整各业务维度的阈值。
在本申请的一个实施例中,分类器120还对推送端预推送的消息设置分类标签,所述消息推送请求流量控制程序10还包括:聚类模块,对进行群推、标签推或/和别名推的消息,根据被推送端对分类标签的关注度对被推送端进行聚类,将所述消息发送给聚类后的被推送端。
此外,本申请还提供一种基于业务规则的消息推送请求流量控制方法。参照图3所示,为本申请消息推送请求流量控制方法较佳实施例的流程图。该方法可以由一个装置执行,该装置可以由软件和/或硬件实现。
在本实施例中,消息推送请求流量控制方法包括:
步骤S1,获得推送端预发送的消息,输入分类器对消息进行分类,每一类对应一种业务维度;
步骤S2,设定每种业务维度的阈值;
步骤S3,检测设定时间(例如5s)的各业务维度消息推送的请求量;
步骤S4,分别判断每种业务维度的消息推送的请求量是否不大于设定的对应的业务维度的阈值;
如果业务维度的消息推送的请求量不大于对应的阈值,在步骤S5a,推送所述业务维度的消息。
如果业务维度的消息推送的请求量大于对应的阈值,在步骤S5b中,将消息推送的请求量超过阈值的报警信号返回推送端。
优选地,还包括对不同业务维度赋予不同的权重,当所有业务维度的消息推送的请求量之和超过设定阈值或者权重较大的业务维度的消息推送的请求量超过设定阈值时,对权重较大的业务维度的阈值进行升级,对权重较小的业务维度进行业务维度降级,也就是说,增大所述权重较大的业务维度的阈值,减小所述权重较小的业务维度的阈值,其中所述权重可以根据业务的重要性进行赋值,业务的重要性越高,权重越大,权重较大和较小可以通过设定基准权重进行区分,大于基准权重的为较大,小于基准权重的为较小,也可以通过权重之间的差值进行区分,差值超过设定范围,所述差值对应的两个权重分别为较大权重和较小权重,但是本申请并不限于此。
在步骤S3和S4之间还包括下述步骤:
获得了设定时间的消息推送的请求量后,执行清除请求量的定时任务,对各业务维度的消息推送的请求量进行重置,其中,
在获得设定时间的消息推送的请求量时,计算距离上次重置的时间,如果超过上次重置的时间,清除所述上次重置的时间,例如,例如,计算距离上次重置TSId+broadcast+countKey的时间,Time=Now()-TSId+broadcast+clearTime,TSID是指某个推送段的标识,比如 银行作为推送段的TSID为:5b7245c93290d61a926b09a5,Broadcast是群推的标识,是标识一下群推消息;countKey是取的一个名字,代表计数,Time=Now()-TSId+broadcast+clearTime是指当前时间减去上次清理时间,TSId+broadcast+clearTime指上次清理时间,又如,记录上次的时间计数的时间和清理的时间,比如上次是1点05分05秒,下次到了1点05分10s的时,就把以前计数给清除掉。
在本申请的一个实施例中,还包括:
构建每一种业务维度的消息请求量随时间变化的请求量时间序列;
通过预测模型预测未来时间的所述业务维度的消息请求量,例如:构建神经网络的预测模型,对所述预测模型进行训练,将每一种业务维度的请求量时间序列代入训练后的预测模型,得到未来时刻的所述业务维度的消息请求量;
根据预测的各业务维度的消息请求量调整各业务维度的阈值。
优选地,所述通过预测模型预测未来时间的所述业务维度的消息请求量的方法包括:
将业务维度的请求量时间序列作为第一序列;
采用至少一种序列长度将所述第一序列划分为多个第二序列,所述第二序列的序列长度短于所述第一序列的序列长度;
根据第二序列构建第一序列的树状图,包括:以第一序列中出现的每一个请求量作为一个根节点,各第二序列中各种请求量组合作为各分支,每一根节点与该根节点相连的各分支构成每一个子树,根节点代表的请求量在第一序列中出现的频数为所述根节点的节点值,从根节点到子节点代表的请求量组合在各第二序列中出现的频数之和为所述子节点的节点值;
预测每一个第二序列下一次序的请求量为第一序列中任一请求量的概率,所述概率可以根据下式(1)计算,
Figure PCTCN2019089152-appb-000001
其中,i表示所述第一序列的树状图的层数索引,y 1表示树状图的子树的一个根节点,y 2,…,y i表示所述子树的根节点y 1的一个分支的第2层到第i层的子节点,y 1y 2y i表示所述分支对应的序列长度为i的第二序列,x表示要预测 的请求量,p(x|y 1y 2y i)表示所述第二序列次序为i+1的请求量为x的内部概率,N(y i+1=x)表示所述分支第i层节点y i的第i+1层的子节点为x的节点值,N(y i)表示所述分支的第i层的节点y i的节点值;
将所述概率的最大值作为下一次序的请求量。
在本申请的一个实施例中,还包括:
对消息设置分类标签,所述分类标签包括消息的类型(产品推送、通知、采购等)、推送端标示符、消息的关键字等;
在对消息进行群推、标签推或/和别名推时,根据被推送端对分类标签的关注度对被推送端进行聚类,所述关注度可以是客户对消息的浏览次数,还可以是获得消息后,根据消息的行为数据,例如,根据产品推送消息对产品的购买次数;
将所述消息发送给聚类后的被推送端。
上述根据被推送端对分类标签的关注度对被推送端进行聚类的方法包括:
据被推送端对分类标签的关注度构建被推送端的关注矩阵
Figure PCTCN2019089152-appb-000002
B=[b 1...b j]
Figure PCTCN2019089152-appb-000003
其中,XB表示信息分类标签集合,m表示信息条数,x 1 … x m为信息的名称,表示第1至m条信息,[fb m,1,…fb m,k]表示信息x m的1至k个分类标签,k表示分类标签的个数;
Figure PCTCN2019089152-appb-000004
为信息分类标签集合XB中所有非零和非重叠分类标签的集合,j表示信息x 1至x m的分类标签的非零和非重叠个数,0<j≤mk,G为关注矩阵,g nj是指被推送端y n对分类标签b j的关注度,不同信息中有相同的分类标签时,被推送端对具有相同分类标签的信息的关注度取 平均值作为对所述分类标签的关注度,不重叠的分类标签的关注度就是用户对信息的关注度;
将关注矩阵中的每一行元素看成一个向量,随机选取设定个数的向量,随机选取一个所述向量作为一个初始簇的聚类中心,设定个数的向量形成多个聚类中心,其中是由除了聚类中心的其他向量分别与聚类中心随机聚集形成多个初始簇;
分析关注矩阵中除了聚类中心的其他向量与各聚类中心的欧式距离,将与各聚类中心的欧式距离小于阈值(最相似)的其他向量分别与对应的聚类中心聚集,形成新簇;
将其他向量指向最相似的簇合成新簇以后,将组成新簇的关注矩阵中的向量分别相加求平均,得到各新簇的聚类中心;
判断各新簇的聚类中心是否等于各初始簇的聚类中心。
若是等于,则被推送端聚类分群完成;
若是不等于,将该新簇的中心作为初始簇的聚类中心,返回之前分析向量与各聚类中心之间欧式距离的步骤,直至新簇的中心不再发生变化,即,被推送端聚类分群完成。
优选地,还包括:分析上述关注矩阵中各分类标签及其组合的支持度和置信度,输出满足最小支持度或/和最小置信度要求的分类标签及其组合的关联规则,即输出大于最小支持度阈值或/和最小置信度阈值的分类标签及其组合的关联规则,具体地:
扫描具有信息分类标签集合,根据每一个非零和非重叠分类标签的支持度得到第一分类标签集合,例如,分类标签b j的支持度support(b j)为:
Figure PCTCN2019089152-appb-000005
其中,|b j|表示分类标签b j在信息分类标签集合XB的出现次数,d为信息 分类标签集合XB中的非零消息的总数,0<d≤(n*m);
如果support(b j)满足support(b j)>minsup,将b j作为一个元素纳入到第一分类标签集合FT,得到第一分类标签集合FT,FT=[ft 1 ... ft a],
Figure PCTCN2019089152-appb-000006
其中,minsup为最小支持度阈值,满足0<minsup<1,是一个设定值;a为大于最小支持度阈值的分类标签的个数,0≤a≤j,ft 1...ft a表示分类标签的第一分类标签集合FT中的分类标签名称。
得到第一分类标签集合以后,分别构造第一分类标签集合的非空真子集;
计算每个非空真子集的置信度,例如,第一分类标签集合FT中真子集t的置信度为,
Figure PCTCN2019089152-appb-000007
其中,|FT|表示第一分类标签集合FT在分类标签集合XB中的出现次数,|t|为第一分类标签集合FT的非空真子集t在分类标签集合XB中的出现频次。
得到所有非空真子集的置信度以后,判断非空真子集的置信度是否大于最小置信度阈值。
若是非空真子集的置信度大于最小置信度阈值,产生关联规则:
Figure PCTCN2019089152-appb-000008
说明产生关联规则的非空真子集中的分类标签或分类标签组合与该真子集的补集中的分类标签或者分类标签组合有较强的关联关系,例如,在上例中真子集t的置信度conf(t)>minconf,输出关联规则
Figure PCTCN2019089152-appb-000009
即,真子集t中的分类标签与其补集(FT-t)中的分类标签有较强的关联关系,其中,minconf为最小置信度阈值,是一个设定值,又如,FT为{"打折","日用品","一线品牌"}三个分类标签组成的第一分类标签集合,若产生关联规则
Figure PCTCN2019089152-appb-000010
说明分类标签【打折】和【日用品】组合与分类目标签【一线品牌】具有较强的关联关系,即被推送端的聚类对一线品牌的日用品打折信息感兴趣。
此外,本申请实施例还提出一种计算机可读存储介质,所述计算机可读存储介质中包括基于业务规则的消息推送请求流量控制程序,所述基于业务 规则的消息推送请求流量控制程序被所述处理器执行时实现如下步骤:
获得推送端预发送的消息,输入分类器对消息进行分类,每一类对应一种业务维度,所述分类包括群推、单推、标签推、别名推,其中,所述群推是指将推送端预发送消息发送给与所述推送端有关的所有被推送端;所述单推是指将推送端预发送的消息发送给指定的一个被推送端;所述标签推送是指将推送端预发送的消息发送给指定用户标签的被推荐端;所述别名推是指将推送端预发送给的消息推送给指定发送的别名账户的被推送端;
设定每种业务维度的阈值;
检测设定时间的各业务维度消息推送的请求量;
分别判断每种业务维度的消息推送的请求量是否不大于设定的对应的业务维度的阈值;
如果业务维度的消息推送的请求量不大于对应的阈值,推送所述业务维度的消息;
如果业务维度的消息推送的请求量大于对应的阈值,将消息推送的请求量超过阈值的报警信号返回推送端。
本申请之计算机可读存储介质的具体实施方式与上述基于业务规则的消息推送请求流量控制方法、电子装置的具体实施方式大致相同,在此不再赘述。
本申请所述基于业务规则的消息推送请求流量控制方法、电子装置及可读存储介质通过对推送端的各业务属性角度实现流量管控,满足业务精细化的流量管控要求,同时将流量管控与业务关联起来,通过业务维度降级服务,保障核心服务正常运行。
需要说明的是,在本文中,术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含,从而使得包括一系列要素的过程、装置、物品或者方法不仅包括那些要素,而且还包括没有明确列出的其他要素,或者是还包括为这种过程、装置、物品或者方法所固有的要素。在没有更多限制的情况下,由语句“包括一个……”限定的要素,并不排除在包括该要素的过程、装置、物品或者方法中还存在另外的相同要素。
上述本申请实施例序号仅仅为了描述,不代表实施例的优劣。通过以上的实施方式的描述,本领域的技术人员可以清楚地了解到上述实施例方法可 借助软件加必需的通用硬件平台的方式来实现,当然也可以通过硬件,但很多情况下前者是更佳的实施方式。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分可以以软件产品的形式体现出来,该计算机软件产品存储在如上所述的一个存储介质(如ROM/RAM、磁碟、光盘)中,包括若干指令用以使得一台终端设备(可以是手机,计算机,服务器,或者网络设备等)执行本申请各个实施例所述的方法。
以上仅为本申请的优选实施例,并非因此限制本申请的专利范围,凡是利用本申请说明书及附图内容所作的等效结构或等效流程变换,或直接或间接运用在其他相关的技术领域,均同理包括在本申请的专利保护范围内。

Claims (20)

  1. 一种基于业务规则的消息推送请求流量控制方法,应用于电子装置,其特征在于,所述方法包括:
    获得推送端预发送的消息,输入分类器对消息进行分类,每一类对应一种业务维度,所述分类包括群推、单推、标签推、别名推,其中,所述群推是指将推送端预发送消息发送给与所述推送端有关的所有被推送端;所述单推是指将推送端预发送的消息发送给指定的一个被推送端;所述标签推送是指将推送端预发送的消息发送给指定用户标签的被推荐端;所述别名推是指将推送端预发送给的消息推送给指定发送的别名账户的被推送端;
    设定每种业务维度的阈值;
    检测设定时间的各业务维度消息推送的请求量;
    分别判断每种业务维度的消息推送的请求量是否不大于设定的对应的业务维度的阈值;
    如果业务维度的消息推送的请求量不大于对应的阈值,推送所述业务维度的消息;
    如果业务维度的消息推送的请求量大于对应的阈值,将消息推送的请求量超过阈值的报警信号返回推送端。
  2. 根据权利要求1所述的消息推送请求流量控制方法,其特征在于,还包括:
    获得了设定时间的消息推送的请求量后,执行清除请求量的定时任务,对各业务维度的消息推送的请求量进行重置。
  3. 根据权利要求2所述的消息推送请求流量控制方法,其特征在于,还包括:在获得设定时间的消息推送的请求量时,计算距离上次重置的时间,如果超过上次重置的时间,清除所述上次重置的时间。
  4. 根据权利要求1所述的消息推送请求流量控制方法,其特征在于,还包括:对不同业务维度赋予不同的权重,当所有业务维度的消息推送的请求量之和超过设定阈值或者权重较大的业务维度的消息推送的请求量超过设定阈值时,增大所述权重较大的业务维度的阈值,减小权重较小的业务维度的阈值。
  5. 根据权利要求1所述的消息推送请求流量控制方法,其特征在于,还包括:
    构建每一种业务维度的消息请求量随时间变化的请求量时间序列;
    通过预测模型预测未来时间的所述业务维度的消息请求量;
    根据预测的各业务维度的消息请求量调整各业务维度的阈值。
  6. 根据权利要求1所述的消息推送请求流量控制方法,其特征在于,还包括:
    对消息设置分类标签;
    在对消息进行群推、标签推或/和别名推时,根据被推送端对分类标签的关注度对被推送端进行聚类;
    将所述消息发送给聚类后的被推送端。
  7. 根据权利要求5所述的消息推送请求流量控制方法,其特征在于,
    所述通过预测模型预测未来时间的所述业务维度的消息请求量的方法包括:
    将业务维度的请求量时间序列作为第一序列;
    采用至少一种序列长度将所述第一序列划分为多个第二序列,所述第二序列的序列长度短于所述第一序列的序列长度;
    根据第二序列构建第一序列的树状图,包括:以第一序列中出现的每一个请求量作为一个根节点,各第二序列中各种请求量组合作为各分支,每一根节点与该根节点相连的各分支构成每一个子树,根节点代表的请求量在第一序列中出现的频数为所述根节点的节点值,从根节点到子节点代表的请求量组合在各第二序列中出现的频数之和为所述子节点的节点值;
    预测每一个第二序列下一次序的请求量为第一序列中任一请求量的概率,所述概率根据下式计算,
    Figure PCTCN2019089152-appb-100001
    其中,i表示所述第一序列的树状图的层数索引,y 1表示树状图的子树的一个根节点,y 2,…,y i表示所述子树的根节点y 1的一个分支的第2层到第i层的子节点,y 1y 2…y i表示所述分支对应的序列长度为i的第二序列,x表示要预测的请求量,p(x|y 1y 2…y i)表示所述第二序列次序为i+1的请求量为x的内部概率, N(y i+1=x)表示所述分支第i层节点y i的第i+1层的子节点为x的节点值,N(y i)表示所述分支的第i层的节点y i的节点值;
    将所述概率的最大值作为下一次序的请求量。
  8. 根据权利要求1所述的消息推送请求流量控制方法,其特征在于,还包括:
    对消息设置分类标签;
    在对消息进行群推、标签推或/和别名推时,根据被推送端对分类标签的关注度对被推送端进行聚类,将消息发送给聚类后的被推送端。
  9. 根据权利要求8所述的消息推送请求流量控制方法,其特征在于,还包括:
    根据被推送端对分类标签的关注度对被推送端进行聚类的方法包括:
    据被推送端对分类标签的关注度构建被推送端的关注矩阵
    Figure PCTCN2019089152-appb-100002
    B=[b 1...b j]
    Figure PCTCN2019089152-appb-100003
    其中,XB表示信息分类标签集合,m表示信息条数,x 1 … x m为信息的名称,表示第1至m条信息,[fb m,1,…fb m,k]表示信息x m的1至k个分类标签,k表示分类标签的个数;
    Figure PCTCN2019089152-appb-100004
    为信息分类标签集合XB中所有非零和非重叠分类标签的集合,j表示信息x 1至x m的分类标签的非零和非重叠个数,0<j≤mk,G为关注矩阵,g nj是指被推送端y n对分类标签b j的关注度,不同信息中有相同的分类标签时,被推送端对具有相同分类标签的信息的关注度取平均值作为对所述分类标签的关注度,不重叠的分类标签的关注度就是用户对信息的关注度。
  10. 根据权利要求8所述的消息推送请求流量控制方法,其特征在于,还包括:
    分类标签包括消息的类型、推送端标示符、消息的关键字。
  11. 根据权利要求8所述的消息推送请求流量控制方法,其特征在于,还包括:
    所述关注度是客户对消息的浏览次数,或获得消息后,对消息的行为数据。
  12. 根据权利要求8所述的消息推送请求流量控制方法,其特征在于,对被推送端进行聚类的方法包括:
    将关注矩阵中的每一行元素看成一个向量,随机选取设定个数的向量,随机选取一个所述向量作为一个初始簇的聚类中心,设定个数的向量形成多个聚类中心,其中是由除了聚类中心的其他向量分别与聚类中心随机聚集形成多个初始簇;
    分析关注矩阵中除了聚类中心的其他向量与各聚类中心的欧式距离,将与各聚类中心的欧式距离小于阈值的其他向量分别与对应的聚类中心聚集,形成新簇;
    将其他向量指向最相似的簇合成新簇以后,将组成新簇的关注矩阵中的向量分别相加求平均,得到各新簇的聚类中心;
    判断各新簇的聚类中心是否等于各初始簇的聚类中心,若是等于,则被推送端聚类分群完成,若是不等于,将该新簇的中心作为初始簇的聚类中心,返回至所述分析关注矩阵中除了聚类中心的其他向量与各聚类中心的欧式距离的步骤,并顺序执行直至新簇的中心不再发生变化,从而完成被推送端聚类。
  13. 根据权利要求8所述的消息推送请求流量控制方法,其特征在于,还包括:
    分析关注矩阵中各分类标签及其组合的支持度和置信度,输出大于最小支持度阈值或/和最小置信度阈值的分类标签及其组合的关联规则。
  14. 根据权利要求13所述的消息推送请求流量控制方法,其特征在于,构建支持度大于最小支持度阈值的第一分类标签集合的方法包括:
    扫描具有信息分类标签集合,根据每一个非零和非重叠分类标签的支持度得到第一分类标签集合,分类标签b j的支持度support(b j)为:
    Figure PCTCN2019089152-appb-100005
    其中,|b j|表示分类标签b j在信息分类标签集合XB的出现次数,d为信息分类标签集合XB中的非零消息的总数,0<d≤(n*m);
    如果support(b j)满足support(b j)>minsup,将b j作为一个元素纳入到第一分类标签集合FT,得到第一分类标签集合FT,FT=[ft 1 … ft a],
    Figure PCTCN2019089152-appb-100006
    其中,minsup为最小支持度阈值,满足0<minsup<1,是一个设定值;a为大于最小支持度阈值的分类标签的个数,0≤a≤j,ft 1 … ft a表示分类标签的第一分类标签集合FT中的分类标签名称。
  15. 根据权利要求14所述的消息推送请求流量控制方法,其特征在于,
    构建大于最小置信度阈值的分类标签的方法包括:
    得到第一分类标签集合以后,分别构造第一分类标签集合的非空真子集;
    计算每个非空真子集的置信度,第一分类标签集合FT中非空真子集t的置信度为:
    Figure PCTCN2019089152-appb-100007
    其中,|FT|表示第一分类标签集合FT在分类标签集合XB中的出现次数,|t|为第一分类标签集合FT的非空真子集t在分类标签集合XB中的出现频次,得到所有非空真子集的置信度以后,保留置信度大于最小置信度阈值的非空真子集。
  16. 根据权利要求15所述的消息推送请求流量控制方法,其特征在于,
    输出大于最小支持度阈值或/和最小置信度阈值的分类标签及其组合的关联规则的方法包括:
    对于置信度大于最小置信度阈值的非空真子集,在非空真子集与其补集之间产生关联规则。
  17. 一种电子装置,其特征在于,所述电子装置包括存储器和处理器,所 述存储器中包括基于业务规则的消息推送请求流量控制程序,所述基于业务规则的消息推送请求流量控制程序被所述处理器执行时实现如下步骤:
    获得推送端预发送的消息,输入分类器对消息进行分类,每一类对应一种业务维度,所述分类包括群推、单推、标签推、别名推,其中,所述群推是指将推送端预发送消息发送给与所述推送端有关的所有被推送端;所述单推是指将推送端预发送的消息发送给指定的一个被推送端;所述标签推送是指将推送端预发送的消息发送给指定用户标签的被推荐端;所述别名推是指将推送端预发送给的消息推送给指定发送的别名账户的被推送端;
    设定每种业务维度的阈值;
    检测设定时间的各业务维度消息推送的请求量;
    分别判断每种业务维度的消息推送的请求量是否不大于设定的对应的业务维度的阈值;
    如果业务维度的消息推送的请求量不大于对应的阈值,推送所述业务维度的消息;
    如果业务维度的消息推送的请求量大于对应的阈值,将消息推送的请求量超过阈值的报警信号返回推送端。
  18. 根据权利要求17所述的电子装置,其特征在于,所述处理器在获得了设定时间的消息推送的请求量后,执行清除请求量的定时任务,对各业务维度的消息推送的请求量进行重置。
  19. 根据权利要求17所述的电子装置,其特征在于,所述处理器对不同业务维度赋予不同的权重,当所有业务维度的消息推送的请求量之和超过设定阈值或者权重较大的业务维度的消息推送的请求量超过设定阈值时,增大所述权重较大的业务维度的阈值,减小权重较小的业务维度的阈值。
  20. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质中包括基于业务规则的消息推送请求流量控制程序,所述基于业务规则的消息推送请求流量控制程序被处理器执行时,实现如权利要求1至16中任一项所述的基于业务规则的消息推送请求流量控制方法的步骤。
PCT/CN2019/089152 2018-10-24 2019-05-30 基于业务规则的消息推送请求流量控制方法、装置及介质 Ceased WO2020082733A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811242274.6A CN109474542B (zh) 2018-10-24 2018-10-24 基于业务规则的消息推送请求流量控制方法、装置及介质
CN201811242274.6 2018-10-24

Publications (1)

Publication Number Publication Date
WO2020082733A1 true WO2020082733A1 (zh) 2020-04-30

Family

ID=65666022

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/089152 Ceased WO2020082733A1 (zh) 2018-10-24 2019-05-30 基于业务规则的消息推送请求流量控制方法、装置及介质

Country Status (2)

Country Link
CN (1) CN109474542B (zh)
WO (1) WO2020082733A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112637295A (zh) * 2020-12-15 2021-04-09 平安普惠企业管理有限公司 业务对象的推送方法、装置、设备及存储介质
CN114710556A (zh) * 2022-06-08 2022-07-05 深圳市信润富联数字科技有限公司 多系统集成消息推送方法、装置、设备及存储介质
CN115002691A (zh) * 2021-03-01 2022-09-02 中国移动通信集团四川有限公司 消息发送方法、装置、设备和计算机可读存储介质
CN115665074A (zh) * 2022-10-08 2023-01-31 广州市玄武无线科技股份有限公司 消息限流发送方法、装置、设备及存储介质
CN119030885A (zh) * 2024-07-09 2024-11-26 中移动信息技术有限公司 一种请求数据限流的方法、装置、设备及可读存储介质

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109474542B (zh) * 2018-10-24 2022-05-13 平安科技(深圳)有限公司 基于业务规则的消息推送请求流量控制方法、装置及介质
CN110677824A (zh) * 2019-08-29 2020-01-10 凡普数字技术有限公司 短信发送方法、装置以及存储介质
CN112581150A (zh) * 2019-09-27 2021-03-30 北京国双科技有限公司 一种信息管理方法、装置、设备及存储介质
CN111131063B (zh) * 2019-12-31 2022-03-25 腾讯科技(深圳)有限公司 一种流量控制的方法、相关装置、设备以及存储介质
CN113765969B (zh) * 2020-09-28 2024-10-25 北京沃东天骏信息技术有限公司 一种流量控制方法和装置
CN119883350A (zh) * 2024-12-03 2025-04-25 阳光人寿保险股份有限公司 一种消息推送配置与预警方法及系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101026802A (zh) * 2007-03-16 2007-08-29 华为技术有限公司 一种信息推送方法与装置
CN104731958A (zh) * 2015-04-03 2015-06-24 北京航空航天大学 一种面向用户需求倾向的云制造服务推荐方法
US9317574B1 (en) * 2012-06-11 2016-04-19 Dell Software Inc. System and method for managing and identifying subject matter experts
CN109474542A (zh) * 2018-10-24 2019-03-15 平安科技(深圳)有限公司 基于业务规则的消息推送请求流量控制方法、装置及介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8023981B2 (en) * 2008-05-12 2011-09-20 Qualcomm Incorporated Method and apparatus for adaptive dynamic call setup based on real-time network resource availability
CN105704312B (zh) * 2016-01-20 2019-02-26 Oppo广东移动通信有限公司 消息推送处理方法及消息推送处理装置
CN105791910B (zh) * 2016-03-08 2019-02-12 北京四达时代软件技术股份有限公司 一种多媒体资源推送系统及方法
CN107872483B (zh) * 2016-09-27 2020-12-04 腾讯科技(北京)有限公司 媒体内容的推送方法、装置及系统
CN108400927B (zh) * 2018-01-22 2021-01-26 广州欧赛斯信息科技有限公司 一种针对高并发消息的消息推送方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101026802A (zh) * 2007-03-16 2007-08-29 华为技术有限公司 一种信息推送方法与装置
US9317574B1 (en) * 2012-06-11 2016-04-19 Dell Software Inc. System and method for managing and identifying subject matter experts
CN104731958A (zh) * 2015-04-03 2015-06-24 北京航空航天大学 一种面向用户需求倾向的云制造服务推荐方法
CN109474542A (zh) * 2018-10-24 2019-03-15 平安科技(深圳)有限公司 基于业务规则的消息推送请求流量控制方法、装置及介质

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112637295A (zh) * 2020-12-15 2021-04-09 平安普惠企业管理有限公司 业务对象的推送方法、装置、设备及存储介质
CN112637295B (zh) * 2020-12-15 2023-04-28 平安普惠企业管理有限公司 业务对象的推送方法、装置、设备及存储介质
CN115002691A (zh) * 2021-03-01 2022-09-02 中国移动通信集团四川有限公司 消息发送方法、装置、设备和计算机可读存储介质
CN115002691B (zh) * 2021-03-01 2023-08-15 中国移动通信集团四川有限公司 消息发送方法、装置、设备和计算机可读存储介质
CN114710556A (zh) * 2022-06-08 2022-07-05 深圳市信润富联数字科技有限公司 多系统集成消息推送方法、装置、设备及存储介质
CN114710556B (zh) * 2022-06-08 2022-09-16 深圳市信润富联数字科技有限公司 多系统集成消息推送方法、装置、设备及存储介质
CN115665074A (zh) * 2022-10-08 2023-01-31 广州市玄武无线科技股份有限公司 消息限流发送方法、装置、设备及存储介质
CN115665074B (zh) * 2022-10-08 2023-09-15 广州市玄武无线科技股份有限公司 消息限流发送方法、装置、设备及存储介质
CN119030885A (zh) * 2024-07-09 2024-11-26 中移动信息技术有限公司 一种请求数据限流的方法、装置、设备及可读存储介质

Also Published As

Publication number Publication date
CN109474542B (zh) 2022-05-13
CN109474542A (zh) 2019-03-15

Similar Documents

Publication Publication Date Title
WO2020082733A1 (zh) 基于业务规则的消息推送请求流量控制方法、装置及介质
CN112148987B (zh) 基于目标对象活跃度的消息推送方法及相关设备
CN113536139B (zh) 基于兴趣的内容推荐方法、装置、计算机设备及存储介质
CN106326391B (zh) 多媒体资源推荐方法及装置
JP2021121922A (ja) 特徴抽出に基くマルチモデルトレーニング方法及び装置、電子機器と媒体
WO2020029412A1 (zh) 标签推荐方法、装置、计算机设备及计算机可读存储介质
WO2021068513A1 (zh) 异常对象识别方法、装置、介质及电子设备
WO2019062414A1 (zh) 应用程序管控方法、装置、存储介质及电子设备
US20220019689A1 (en) Privacy Preserving Server-Side Personalized Content Selection
CN113222073B (zh) 训练广告推荐模型的方法及装置
CN106997549A (zh) 一种广告信息的推送方法及系统
US11748452B2 (en) Method for data processing by performing different non-linear combination processing
CN113760521B (zh) 一种虚拟资源的分配方法和装置
CN113743968B (zh) 信息投放方法、装置及设备
WO2019137485A1 (zh) 一种业务分值的确定方法、装置及存储介质
CN115018593A (zh) 独立站点商品推荐方法及其装置、设备、介质、产品
CN112241327A (zh) 分享信息处理方法、装置、存储介质与电子设备
WO2022247666A1 (zh) 一种内容的处理方法、装置、计算机设备和存储介质
CN108520471A (zh) 重叠社区发现方法、装置、设备及存储介质
CN111898033A (zh) 内容推送方法、装置以及电子设备
CN117495485A (zh) 产品推荐方法、设备及可读存储介质
CN110287373A (zh) 基于评分预测和用户特征的协同过滤电影推荐方法及系统
CN115271931A (zh) 一种信用卡产品的推荐方法、装置、电子设备和介质
CN115496523A (zh) 一种广告发布方法、计算机可读存储介质和电子设备
WO2019062404A1 (zh) 应用程序的处理方法、装置、存储介质及电子设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19875044

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19875044

Country of ref document: EP

Kind code of ref document: A1