CN116112879A

CN116112879A - Information pushing method, device, electronic equipment and computer program product

Info

Publication number: CN116112879A
Application number: CN202111322396.8A
Authority: CN
Inventors: 邓逸斌; 谭丽丽; 张晓川; 谢伟斌
Original assignee: China Mobile Communications Group Co Ltd; China Mobile Group Guangdong Co Ltd
Current assignee: China Mobile Communications Group Co Ltd; China Mobile Group Guangdong Co Ltd
Priority date: 2021-11-09
Filing date: 2021-11-09
Publication date: 2023-05-12

Abstract

The application relates to the technical field of information communication, and provides an information pushing method, an information pushing device, electronic equipment and a computer program product, wherein the information pushing method comprises the following steps: calculating the preference time, the preference channel information and the preference product information of each user through an information anti-disturbance model and a stream processing method; generating anti-disturbance frequency and push strategies of each user according to the preference channel information and the preference product information of each user; and pushing marketing information for each user according to the pushing strategy, the preference time and the anti-disturbing frequency of each user. The information pushing method provided by the embodiment of the application realizes that one user corresponds to one pushing strategy, combines the preference time and the anti-disturbing frequency of each user to perform double limitation, and improves the utilization rate of information resources.

Description

Information pushing method, device, electronic equipment and computer program product

Technical Field

The present disclosure relates to the field of information communication technologies, and in particular, to an information pushing method, an apparatus, an electronic device, and a computer program product.

Background

The short message group attack is one of the common propaganda and popularization means in the communication industry and is widely applied to product marketing. However, the current short message group sending lacks a filtering mechanism, so that users which have been sent by the short message group for many times cannot be filtered, namely, one pushing strategy corresponds to a plurality of users, one user cannot correspond to one pushing strategy, when marketing information needs to be pushed to a certain user, the marketing information is pushed to all users through the short message group sending, and even if the users are not receiving users of the marketing information, the users are forced to receive the marketing information. Moreover, the current short message group sending lacks management and control, and can only be controlled based on a time period, namely, marketing information can be pushed to a user for many times in a certain time period, so that the utilization rate of information resources is low.

Disclosure of Invention

The application provides an information pushing method, an information pushing device, electronic equipment and a computer program product, and aims to improve the utilization rate of information resources.

In a first aspect, the present application provides an information pushing method, including:

calculating the preference time, the preference channel information and the preference product information of each user through an information anti-disturbance model and a stream processing method;

generating anti-disturbance frequencies and push strategies of the users according to the preference channel information and the preference product information of the users;

and pushing marketing information for each user according to the pushing strategy, the preference time and the anti-disturbing frequency of each user.

In one embodiment, the step of pushing the marketing message for each user according to the pushing policy, the preference time and the anti-disturbing frequency of each user includes:

determining whether the push strategy of each user meets push requirements according to the execution period of the push strategy of each user and the anti-disturbing frequency of each user;

if the push strategy of each user is determined to meet the push requirement, determining the remaining month quota of the push strategy of each user;

And pushing marketing information for each user according to the remaining month quota of the pushing strategy of each user and the preference time of each user.

The step of determining the remaining month quota of the push policy of each user comprises the following steps:

calculating batch push remaining month quota of the push strategy of each user according to the total daily contact number, the mass-sending contact ratio, the first preset day information and the mass-sending contact floating ratio of the push strategy of each user;

and calculating the real-time push remaining month quota of the push strategy of each user according to the total daily contact number, the event contact ratio, the second preset day information and the event contact floating ratio of the push strategy of each user.

The step of pushing marketing information for each user according to the remaining month quota of the pushing strategy of each user and the preference time of each user comprises the following steps:

if the batch push remaining month quota of each user is determined to be greater than the corresponding batch push contact total number, and the real-time push remaining month quota of each user is determined to be greater than the corresponding real-time push contact total number, determining whether the push time of the push strategy of each user is within the preference time of each user;

And if the push time of the push strategy of each user is determined to be within the preference time of each user, pushing marketing information for each user according to the priority of the push strategy of each user.

The step of pushing the marketing information for each user according to the priority of the pushing strategy of each user comprises the following steps:

sorting the push strategies of the users according to the original priority from high to low to obtain a push strategy after the first sorting;

re-ordering the push strategies after the first ordering according to the priority set by an administrator from high to low to obtain push strategies after the second ordering;

and pushing marketing information for each user in turn according to the sequence of the push strategies after the second sequencing.

Before the step of calculating the preference time, the preference channel information and the preference product information of each user through the information anti-disturbance model and the stream processing method, the method further comprises the following steps:

sample selection is carried out on a preset marked data set through an up-down sampling method, and a data set to be processed is obtained;

performing feature preprocessing selection on the data set to be processed by a numerical value missing value method and a category reduction method to obtain feature preprocessing data;

Performing feature selection on each feature preprocessing data by a mutual information feature selection method and a regularization feature selection method to obtain a training data set;

training a preset model file through the training data set, and combining a category weighting algorithm and a model fusion method to obtain an initial model;

and optimizing the initial model according to the algorithm super-parameters and the key super-parameters of the class weighting algorithm to obtain the information anti-disturbance model.

After the step of pushing the marketing information for each user according to the pushing strategy, the preference time and the anti-disturbing frequency of each user, the method further comprises the following steps:

recording node data of each node in the marketing information pushing process, wherein the node data comprises a target user number, a special list user number, a quota user number, a frequency user number, a product user number and a channel user number;

and creating a funnel diagram according to the target user number, the special list user number, the quota user number, the frequency user number, the product user number and the channel user number, so that service personnel can determine the filtering user number of each node according to the funnel diagram.

In a second aspect, the present application further provides an information pushing apparatus, including:

the calculating module is used for calculating the preference time, the preference channel information and the preference product information of each user through the information anti-disturbance model and the stream processing method;

the generation module is used for generating anti-disturbance frequencies and pushing strategies of the users according to the preference channel information and the preference product information of the users;

and the pushing module is used for pushing marketing information for each user according to the pushing strategy, the preference time and the anti-disturbing frequency of each user.

In a third aspect, the present application further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the information pushing method according to the first aspect when the processor executes the program.

In a fourth aspect, the present application also provides a computer program product comprising a computer program which, when executed by the processor, implements the steps of the information pushing method of the first aspect.

According to the information pushing method, the information pushing device, the electronic equipment and the computer program product, in the information pushing process, pushing strategies of all users are generated according to the preference channel information and the preference product information of all users, one pushing strategy corresponding to one user is achieved, marketing information does not need to be pushed to all users through the same pushing strategy, accurate pushing of the marketing information is achieved, and the utilization rate of information resources is improved. Meanwhile, the preference time and the anti-disturbing frequency of each user are combined to carry out double limitation, so that marketing information cannot be pushed to the user for multiple times in a certain time period, and the utilization rate of information resources is improved.

Drawings

For a clearer description of the present application or of the prior art, the drawings that are used in the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description below are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person skilled in the art.

Fig. 1 is one of flow diagrams of an information pushing method provided in the present application;

FIG. 2 is a second flow chart of the information pushing method provided in the present application;

FIG. 3 is a third flow chart of the information pushing method provided in the present application;

FIG. 4 is a schematic structural diagram of an information pushing device provided in the present application;

fig. 5 is a schematic structural diagram of an electronic device provided in the present application.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the present application will be clearly and completely described below with reference to the drawings in the present application, and it is apparent that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.

The information pushing method, device, electronic equipment and computer program product provided by the application are described below with reference to fig. 1 to 5.

Specifically, referring to fig. 1, fig. 1 is one of flow diagrams of an information pushing method provided in the present application.

The embodiments of the present application provide embodiments of information pushing methods, and it should be noted that, although a logic sequence is shown in the flowchart, the steps shown or described may be performed in a different order than the sequence shown or described herein under certain data.

In the embodiment of the application, the electronic device is taken as an execution body for example, and the information push system is taken as one of the expression forms of the electronic device, so that the electronic device is not limited.

The information pushing method provided by the embodiment of the application comprises the following steps:

and step S10, calculating the preference time, the preference channel information and the preference product information of each user through an information anti-disturbance model and a stream processing method.

Before calculating the preference time, preference channel information and preference product information of each user, the information pushing system needs to construct an intelligent real-time information anti-interference control system, the technical level of the information anti-interference control system can be divided into 3 parts, and the 3 parts are the real-time access of customer contact data through a stream processing method, the real-time calculation of anti-interference frequency and resource flow control, and the construction of an information anti-interference model.

The real-time access of the customer contact data is specifically as follows: when contact data is generated, data acquisition is carried out through kafka (open source stream processing platform), after the data acquisition is completed, batch processing, cleaning, calculation and loading are carried out on the acquired data through a dispatching tool, and then a real-time stream calculation framework is constructed through spark+Flink (distributed stream data stream engine), so that data calculation is completed. Then, the processed customer contact data is received through kaka, and the customer contact data is converted at the same time so as to perform offline analysis, real-time monitoring, real-time prediction and the like, and the information pushing system calculates once every preset time. Further, each client's real-time contact data is implemented by a flank task, even though flank sql is implemented, for example, a Kafka Topic is consumed, the latest contact, order, complaint, etc. data of the client are calculated, and meanwhile, the whole OLAP is implemented by flank to one set of clickHouse. The method comprises the steps of constructing a client contact data stream batch integrated platform based on spark+Flink, innovating new visual data arrangement capability, shielding data forms (such as batch, stream; files, tables, messages and the like) for data developers, shielding data processing engines (such as M/R, spark, flink) for the data developers, shielding technical operators for the data developers, providing uniform arrangement experience based on a service view angle, and improving data processing efficiency.

The anti-disturbing frequency and the resource flow control are calculated in real time as follows: AI (Artificial Intelligence ) capability is introduced into the data center, model construction such as anti-disturbance frequency prediction, optimal recommendation time identification and the like is supported, and model results are directly referenced by frequency control in IOP marketing through FI and are used for marketing activity frequency control and resource real-time flow control. Under the condition that input parameters are unchanged, the capability of automatically retraining and updating the model according to the marketing effect is provided, and the effect data directly acts on production operation. After the user actively or passively contacts, the contact frequency and the channel available resources are updated in real time according to marketing contact data, and channel flow control is taken as an example, after the user further 10086 WeChat public number contacts and handles 5-element flow packages, the channel contact data and the channel resource use condition are updated in real time, and at the next contact time of the user, additional offers are pushed according to the latest product condition of the user or the marketing offers are recommended according to the user preference data.

The information anti-disturbance model construction is specifically described in the steps A to E. The specific descriptions of steps a to E are as follows:

step A, selecting samples of a preset marked data set by an up-down sampling method to obtain a data set to be processed;

Step B, performing feature preprocessing selection on the data set to be processed by a numerical value missing value method and a category reduction method to obtain feature preprocessing data;

step C, performing feature selection on each feature preprocessing data by a mutual information feature selection method and a regularization feature selection method to obtain a training data set;

step D, training a preset model file through the training data set, and combining a category weighting algorithm and a model fusion method to obtain an initial model;

and E, optimizing the initial model according to the algorithm super parameters and the key super parameters of the class weighting algorithm to obtain the information anti-disturbance model.

Specifically, the information push system performs sample selection on a preset labeling data set through an up-down sampling method to obtain a data set to be processed, the preset labeling data set is selected in advance, and the problem of reduction of classification effects of unbalanced data transformation can be effectively solved through the up-down sampling method in the embodiment. Then, the information push system performs feature preprocessing selection on the data set to be processed through a numerical value missing value method and a category reduction method to obtain various feature preprocessing numbers, and the numerical value missing value method and the category reduction method in the embodiment effectively improve the effect and performance of big data analysis. Then, the information pushing system performs feature selection on each feature preprocessing data through a mutual information feature selection method and a regularization feature selection method to obtain a training data set, and the problems of service experience, simple data analysis and repeated attempts for long time in feature selection can be effectively relieved through the mutual information feature selection method and the regularization feature selection method in the embodiment. And then, the information pushing system trains a preset model file through a training data set and combines a category weighting algorithm and a model fusion method to obtain an initial model, wherein the preset model file is preset, and the prediction effect is improved through the model fusion method and the diversity of the category weighting algorithm. And finally, the information pushing system determines an algorithm super parameter of the category weighting algorithm according to network searching, identifies a key super parameter of the category weighting algorithm and an effective range of the key super parameter, optimizes the initial model through the effective ranges of the algorithm super parameter, the key super parameter and the key super parameter to obtain an information anti-interference model, and can effectively solve the problem of unordered repeated manual adjustment and the problem of convexity through the algorithm super parameter and the key super parameter in the embodiment.

Further, the information anti-disturbing model comprises a real-time data model and an offline data model, wherein the real-time data model can be divided into three types according to application scenes and is respectively a dynamic model, an event model and a space-time model; the offline data model can be divided into two types according to application scenes, namely a user contact preference time model and a user service subscription preference period model.

Further, the dynamic model is used for real-time summarizing statistics, and supports real-time data offline operation, such as report indexes and the like. The event model is used to abstract real-time customer contact class data into a series of events that will mine marketing and real-time push services. The space-time model is used for channel residence, and channel preference information of the user is calculated according to channel residence time of the user.

Further, the user contact preference time model is used for continuously carrying out cluster analysis on the user through the machine modeling platform according to contact behavior data of the user on the passive contact (mobile APP application program, 10086 public number and micor video), excavating user access preference time, forming a timed refreshing preference model, and providing a pushing strategy by combining preference product information and preference channel information of the user in the automatic scene strategy module. An application scenario is as follows: and the user orders the Aiqi directional flow packages in the month from 20 to 25, so that similar flow packages or other directional rights packages can be recommended to the user in advance in the user preference period, and the viscosity and satisfaction of the user are improved. The user service subscription preference period model is used for predicting the subscription time period preference degree of a client according to the user service handling records, and daily and holiday model subscription preference data are respectively formed by using a Ranking algorithm mechanical energy clustering analysis on service subscription habits of different months and holidays of the user and are used for daily and holiday service subscription preference recommendation. An application scenario example: the user logs in the mobile APP to check the consumption bill in the month 3 to 5 days, so that the corresponding marketing products can be recommended in the mobile APP during the month login of the user, the utilization rate of marketing resources is improved, and the waste of marketing resources is reduced.

Further, the algorithm of the information anti-disturbance model is described as follows, taking the construction of a potential complaint user clustering model as an example, mining and analyzing according to user complaint contact data of 4 months in 2021, selecting 20% of users with highest contact coefficients (48000 complaint users and 24000 contact users in total) for clustering and grouping, and obtaining 5 groups, wherein the group numbers of the 5 groups are respectively group number 0, group number 1, group number 2, group number 3 and TOP3 feature data of 4,5 groups, and the feature indexes of the TOP3 feature data are shown in table 1, and table 1 is TOP3 feature data of 5 groups and the feature indexes of the TOP3 feature data.

Table 1 5 TOP3 characterization data and characterization index for each group

According to TOP3 characteristic data and characteristic index analysis thereof, the difference among user groups is mainly represented in dimensions such as whether users are double-card users, contact conditions, recommended times, ordering conditions, superset tariffs, contact time and the like in the current month, the specific difference expression results are shown in table 2, and table 2 is the difference expression result.

TABLE 2 differential performance results

The machine modeling platform is used for continuously carrying out cluster analysis and user feature mining on users to construct a potential complaint user cluster grouping model, and the construction processes of other models such as a real-time data model, a user contact preference time period model, a user business subscription preference period model and the like are similar.

Further, after the information anti-interference control system is built, namely after the information anti-interference model is built, the information pushing system determines contact behavior data of each user, and calculates the contact behavior data of each user according to the information anti-interference model to obtain preference time, preference channel information and preference product information of each user. And then, the information pushing system dynamically updates the preference time, the preference channel information and the preference product information through a stream processing method and provides services for the outside in a real-time interface mode, and when each user contacts, the latest preference time, the latest preference channel information and the latest preference product information of each user are queried in real time.

In this embodiment, for example, the contact behavior data of the user 1 is: and continuously recharging the video members of the loving art through the mobile APP in Guangdong in the number 1 to the number 3 of each month for 3 months, wherein the preference time of the user 1 is the number 1 to the number 3 of each month, the preference channel information is the mobile APP in Guangdong, and the preference product information is the video members of the loving art. The contact behavior data of the user 2 are: and carrying out mobile phone bill inquiry through the Guangdong mobile public numbers at 15 of each month for 3 continuous months, wherein the preference time of the user 2 is 15 of each month, the preference channel information is the Guangdong mobile public numbers, and the preference product information is the mobile phone bill inquiry.

And step S20, generating anti-interference frequencies and push strategies of the users according to the preference channel information and the preference product information of the users.

The information pushing system analyzes the preference channel information and the preference product information of each user through the user contact preference time model, and generates anti-interference frequencies and pushing strategies of each user. It should be noted that, the anti-interference frequency and the push policy generated in this embodiment are the latest anti-interference frequency and the latest push policy obtained by the stream processing method, which further can be understood that the information push system analyzes the latest preference channel information and the latest preference product information of each user through the user contact preference time model, and generates the latest anti-interference frequency and the latest push policy of each user.

In this embodiment, for example, the preferred channel information of the user 1 is 10086 public numbers, the preferred product information is an aiqi video member, and since the recharging period of the video member is 1 month, the anti-disturbance frequency of the user 1 is 1 month, and the pushing strategy of the user 1 is to push the marketing information of recharging the aiqi video member to the user 1 through 10086 public numbers every month. The preference channel information of the user 2 is Guangdong mobile APP, the preference product information is 7-day flow superposition packet, and because the recharging period of the 7-day flow superposition packet is 1 month 3 times, the anti-disturbance frequency of the user 2 is 3 times a month, and the pushing strategy of the user 2 is marketing information for recharging the 7-day flow superposition packet for the user 2 by the Guangdong mobile APP every 7 days.

Furthermore, the embodiment also supports regular contact, such as contact preset times or customer reply preset times, namely replacing the push strategy, wherein the preset times are set according to actual conditions. Methods of exchanging push strategies include, but are not limited to, the following three: the first is showing the number of times strategy, namely recommending one push strategy at a time according to the priority order of the strategy by all push strategies associated with the group-sending channel, and recommending N (set according to actual conditions) times of replacing the push strategy. And the second is a filling strategy, namely if the number of the information contents in a certain recommended pushing strategy is less than the recommended number, filling is carried out by using the filling strategy. And thirdly, filtering and pushing strategies are limited according to the feedback state of the user and the recommended times of each marketing message.

According to the embodiment of the application, the push strategy corresponding to one user is realized, so that the user who is not a receiving user of the marketing information cannot be forced to receive the marketing information, the disturbance to the user is reduced, the user satisfaction is greatly improved, and the complaint rate of the user is reduced.

And step S30, pushing marketing information for each user according to the pushing strategy, the preference time and the anti-disturbing frequency of each user.

When the information push system receives an execution instruction of executing the push strategy of each user, determining whether the execution period of the push strategy of each user accords with the anti-interference frequency of each user, and obtaining a corresponding determination result, wherein the determination result can be that the execution period of the push strategy of each user does not accord with the anti-interference frequency of each user, and the determination result can also accord with the anti-interference frequency of each user for the execution period of the push strategy of each user. In this embodiment, for example, the anti-interference frequency of the user 1 is 1 time a month, and if it is determined that the execution period of the push policy of the user 1 is the first time a month, the execution period of the push policy is determined to be in accordance with the anti-interference frequency of the user 1. And determining that the execution period of the push strategy of the user 1 is the second time of the month, and determining that the execution period of the push strategy does not accord with the anti-disturbing frequency of the user 1.

If the determined result is that the execution period of the push strategy of each user does not accord with the anti-disturbing frequency of each user, the information push system refuses to release the push strategy of each user, namely does not execute the push strategy of each user. If the determined execution period of the push policy of each user meets the anti-interference frequency of each user, the information push system needs to determine the push time of the push policy of each user, and determine whether to push the marketing information for each user according to the push time of the push policy of each user and the preference time of each user, as described in step S301 to step S303.

The embodiment provides an information pushing method, in the information pushing process, pushing strategies of all users are generated according to preference channel information and preference product information of all users, one user corresponds to one pushing strategy, marketing information is not required to be pushed to all users through the same pushing strategy, accurate pushing of the marketing information is achieved, and the utilization rate of information resources is improved. Meanwhile, the preference time and the anti-disturbing frequency of each user are combined to carry out double limitation, so that marketing information cannot be pushed to the user for multiple times in a certain time period, and the utilization rate of information resources is improved.

Further, referring to fig. 2, fig. 2 is a second flowchart of the information pushing method provided in the present application, and the step S30 includes:

step S301, determining whether the push strategy of each user meets push requirements according to the execution period of the push strategy of each user and the anti-disturbing frequency of each user;

step S302, if the push strategy of each user is determined to meet the push requirement, determining the remaining month quota of the push strategy of each user;

step S303, pushing marketing information for each user according to the remaining month quota of the pushing strategy of each user and the preference time of each user.

Specifically, when the information push system receives an execution instruction for executing the push strategy of each user, determining whether the execution period of the push strategy of each user accords with the anti-interference frequency of each user, namely determining whether the push strategy of each user accords with the push requirement. If it is determined that the execution period of the push strategy of each user meets the anti-interference frequency of each user, the information push system determines that the push strategy of each user meets the push requirement, and determines the area information, the channel information and the current month day information of the push strategy of each user, wherein the day information includes, but is not limited to, the current month day, the month day of the beginning busy hour and the month day of the end busy hour are set according to actual conditions, and under the default condition, the default value of the month day of the beginning busy hour is 4 days, and the first 4 days of the beginning of the month are the month busy hour. The default day of the month end busy hour is 1 day, which means that the last day of the month end is the month busy hour.

Next, the information push system determines remaining month quota of the current month of the push policy of each user in the corresponding region and channel according to the region information, the channel information and the day information of the current month of the push policy of each user, which is specifically described in step S3021 to step S3022. And finally, the information push system checks the remaining month quota of the current month of the push strategy of each user to obtain a check result, wherein the check result can be insufficient remaining month quota and can be sufficient remaining month quota. If the verification result is determined to be insufficient in the remaining month quota, the information push system determines that the remaining month quota is insufficient to execute the push strategy of each user. If the verification result is that the remaining month quota is sufficient, the information pushing system determines whether the pushing time of the pushing strategy of each user is within the preference time of each user, so as to obtain a corresponding determination result, and determines whether to push the marketing information for each user according to the determination result, as described in step S3031 to step S3032, wherein the determination result may be that the pushing time of the pushing strategy of each user is within the preference time of each user, and the determination result may also be that the pushing time of the pushing strategy of each user is not within the preference time of each user.

In the process of pushing marketing information for each user, the embodiment of the application combines the preference time, the disturbing frequency and the remaining month quota of the pushing strategy of each user to carry out multiple limitation, so that the marketing information cannot be pushed to the user for multiple times at will, and the utilization rate of information resources is improved.

Further, the specific description of step S3021 to step S3022 is as follows:

step S3021, calculating a batch push remaining month quota of the push policy of each user according to a total daily contact number, a mass-sending contact ratio, first preset day information and a mass-sending contact floating ratio of the push policy of each user;

step S3022, calculating a real-time push remaining month quota of each user 'S push policy according to the total daily contact number, the event contact ratio, the second preset day information, and the event contact floating ratio of each user' S push policy.

It should be noted that, the remaining month quota of the current month of the push policy includes a batch push remaining month quota and a real-time push remaining month quota.

Specifically, the information push system obtains the total daily contact number, the mass-sending contact ratio, the first preset day information and the mass-sending contact floating ratio of the push strategy of each user, the first preset day information comprises the current month day, the month busy hour day and the month end busy hour day. Then, the information pushing system multiplies the total daily contact number, the mass-sending contact ratio, the mass-sending contact floating ratio and the difference value of the month day, the month initial busy hour day and the month final busy hour day to obtain a batch pushing residual month quota of the pushing strategy of each user, wherein the calculation formula is as follows: the remaining month quota = total daily contact amount of mass hair contact ratio (days of month-1+ mass hair contact up-float ratio). Further, the information push system acquires the total daily contact number, the event contact ratio, second preset day information and the event contact floating ratio of the push strategy of each user, wherein the second preset day information is the current month day. Then, the information pushing system multiplies the total daily contact number, the event contact ratio, the current month number and the event contact floating ratio to obtain a real-time pushing residual month quota of the pushing strategy of each user, and the calculation formula is as follows: real-time push remaining month quota = total daily contact amount event contact ratio number of days of the month (1+ event contact up-float ratio), it should be noted that when calculating batch push remaining month quota and real-time push remaining month quota, if the calculation result has a decimal place, the decimal place is discarded and the decimal place is reserved.

According to the method and the device for pushing the marketing information, the remaining month quota of the pushing strategy of each user is determined together according to the batch pushing remaining month quota and the real-time pushing remaining month quota of the pushing strategy of each user, so that the remaining month quota of the pushing strategy of each user can represent the occurrence of the vast majority, the remaining month quota of the pushing strategy of each user is more accurate and representative, and a premise and a guarantee are provided for whether the accuracy of pushing marketing information for each user is to follow-up.

Further, the specific description of step S3031 to step S3032 is as follows:

step S3031, if it is determined that the batch push remaining month quota of each user is greater than the corresponding batch push contact total number, and it is determined that the real-time push remaining month quota of each user is greater than the corresponding real-time push contact total number, determining whether the push time of the push policy of each user is within the preference time of each user;

step S3032, if it is determined that the push time of the push policy of each user is within the preference time of each user, pushing marketing information for each user according to the priority of the push policy of each user.

Specifically, the information pushing system calculates the batch pushing contact total number and the real-time pushing contact total number of the pushing strategies of each user, and a specific calculation formula is as follows: total number of batch push contacts = number of customer groups the number of contact times accumulated for each user within the push policy. Total number of real-time push contacts = number of customer groups the number of contacts is accumulated for each user within the policy. Then, the information pushing system checks the residual month quota of the pushing strategy of each user according to the batch pushing contact total number and the real-time pushing contact total number of the pushing strategy of each user, specifically, determines whether the batch pushing residual month quota of the pushing strategy of each user is larger than the batch pushing contact total number of the pushing strategy of each user, determines whether the real-time pushing residual month quota of the pushing strategy of each user is larger than the real-time pushing contact total number of the pushing strategy of each user, and if the batch pushing residual month quota of the pushing strategy of each user is larger than the batch pushing contact total number of the pushing strategy of each user, and determines that the real-time pushing residual month quota of the pushing strategy of each user is larger than the real-time pushing contact total number of the pushing strategy of each user, the information pushing system determines whether the pushing time of the pushing strategy of each user is within the preference time of each user. If it is determined that the push time of the push policy of each user is within the preference time of each user, the information push system pushes the marketing information for each user according to the priority of the push policy of each user, specifically as described in step S30321 to step S30323. If the batch push residual month quota of the push strategy of each user is determined to be smaller than or equal to the batch push contact total number of the push strategy of each user, or the real-time push residual month quota of the push strategy of each user is determined to be smaller than or equal to the real-time push contact total number of the push strategy of each user, the information push system determines that the push strategy of each user does not meet the push requirement.

In the process of pushing marketing information for each user, the method combines the total number of batch pushing residual month quota and batch pushing contact, the total number of real-time pushing residual month quota and real-time pushing contact and the preference time to carry out multiple limitation, so that the marketing information cannot be pushed to the user for multiple times at will, and the utilization rate of information resources is improved.

Further, the specific description of step S30321 to step S30323 is as follows:

step S30321, sorting the push strategies of the users from high to low according to the original priority, so as to obtain a push strategy after the first sorting;

step S30322, the push strategies after the first sorting are sorted again according to the priority set by the administrator from high to low, and the push strategies after the second sorting are obtained;

step S30323, pushing marketing information for each user in turn according to the order of the push strategies after the second ordering.

Specifically, the information push system determines an original priority of a push policy of each user, where the original priority is a priority of willingness of a marketing information creator, and sorts the push policies of each user according to the original priority from high to low, so as to obtain a push policy after first sorting, and of course, the embodiment may also sort according to the original priority from low to high. And then, the information pushing system determines whether a setting instruction of the administrator level exists currently, and if the setting instruction of the administrator level does not exist, the information pushing system sequentially pushes marketing information for each user according to the order of the pushing strategies after the first ordering. If it is determined that the setting instruction of the administrator level exists, the information push system determines that the administrator sets the priority for the administrator of the push policies of each user according to the setting instruction of the administrator level, and reorders the push policies after the first ordering from high to low according to the administrator setting priority to obtain the push policies after the second ordering. And finally, the information pushing system sequentially pushes marketing information for each user according to the sequence of the pushing strategies after the second sequencing.

According to the method and the device for the batch mass distribution, the sequence of the pushing strategy is determined through the original priority of the pushing strategy and the priority set by the administrator, and marketing information is pushed to each user according to the sequence, so that the batch mass distribution is controlled more reasonably and orderly.

Further, referring to fig. 3, fig. 3 is a third flow chart of the information pushing method provided in the present application, and after the step S30, the method further includes:

step S40, recording node data of each node in the marketing information pushing process, wherein the node data comprises a target user number, a special list user number, a quota user number, a frequency user number, a product user number and a channel user number;

step S50, creating a funnel diagram according to the target user number, the special list user number, the quota user number, the frequency user number, the product user number and the channel user number;

and step S60, determining the number of filtered users of each node according to the funnel diagram.

In the process of pushing marketing information to each user, the information pushing system records node data of each node in the marketing information pushing process, wherein the node data comprises a target user number, a special list user number, a quota user number, a frequency user number, a product user number and a channel user number. Then, the information pushing system sorts the target user number, the special list user number, the quota user number, the frequency user number, the product user number and the channel user number from top to bottom or from bottom to top, and creates a funnel diagram. And finally, the information push system determines the number of the filtered users of the client group at each node according to the funnel diagram, and sends the number of the filtered users of each node to the user terminal of the service personnel. Further, the information push system may also send the funnel diagram to a user terminal of a service person, and the service person knows the number of filtered users of the client group at each node according to the funnel diagram in the user terminal.

In this embodiment, for example, the target user number is 342346, the special list user number is 271734, the quota user number is 237892, the frequency user number is 221654, the product user number is 81534, and the channel user number is 17353, then the filtered user number of the special list user node is 70612, the filtered user number of the quota user node is 33842, the filtered user number of the frequency user node is 16238, the filtered user number of the product user node is 140120, and the filtered user number of the channel user node is 64181.

The embodiment provides an information pushing method, which realizes the whole-course visualization of information anti-disturbance control through a funnel diagram, clearly knows the number of users of each node and the number of filtered users of each node, enables the anti-disturbance filtering condition in the information pushing process to be known in real time, and further enables the channel anti-disturbance condition in the information pushing process to be dynamically monitored.

Further, the information pushing device provided in the present application is described below, and the information pushing device described below and the information pushing method described above may be referred to correspondingly to each other.

As shown in fig. 4, fig. 4 is a schematic structural diagram of an information pushing device provided in the present application, where the information pushing device includes:

The calculating module 401 is configured to calculate, through the information anti-disturbance model and the stream processing method, a preference time, preference channel information and preference product information of each user;

a generating module 402, configured to generate anti-disturbing frequencies and push policies of the users according to the preference channel information and the preference product information of the users;

and the pushing module 403 is configured to push marketing information for each user according to a pushing policy, a preference time and an anti-disturbing frequency of each user.

Further, the pushing module 403 is further configured to:

Further, the information pushing device further includes: a model building module; the model building module is used for:

Further, the information pushing device further includes: a determining module; the determining module is used for:

Creating a funnel diagram according to the target user number, the special list user number, the quota user number, the frequency user number, the product user number and the channel user number;

and determining the number of filtering users of each node according to the funnel diagram.

The specific embodiments of the information pushing device provided in the present application are substantially the same as the embodiments of the information pushing method described above, and are not described herein.

Fig. 5 illustrates a physical schematic diagram of an electronic device, as shown in fig. 5, which may include: processor 510, communication interface (Communications Interface) 520, memory 530, and communication bus 540, wherein processor 510, communication interface 520, memory 530 complete communication with each other through communication bus 540. Processor 510 may invoke logic instructions in memory 530 to perform an information push method comprising:

Further, the logic instructions in the memory 530 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

In another aspect, the present application also provides a computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, are capable of performing the information pushing method provided by the above methods, the method comprising:

In yet another aspect, the present application further provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, is implemented to perform the above provided information pushing methods, the method comprising:

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims

1. An information pushing method is characterized by comprising the following steps:

2. The information pushing method according to claim 1, wherein the step of pushing marketing information for each user according to a pushing policy, a preference time and an anti-disturbance frequency of each user comprises:

3. The information pushing method according to claim 2, wherein the step of determining a remaining month quota of the push policy of each of the users includes:

4. The information pushing method according to claim 2, wherein the step of pushing marketing information for each of the users according to the remaining month quota of the pushing policy of each of the users and the preference time of each of the users comprises:

5. The information pushing method according to claim 4, wherein the step of pushing marketing information for each of the users according to the priority of the pushing policy of each of the users comprises:

6. The information pushing method according to any one of claims 1 to 5, wherein before the step of calculating the preference time, the preference channel information, and the preference product information of each user by the information anti-disturbance model and the stream processing method, further comprising:

7. The information pushing method according to any one of claims 1 to 5, wherein after the step of pushing marketing information for each user according to the pushing policy, the preference time and the anti-disturbance frequency of each user, the method further comprises:

8. An information pushing apparatus, characterized by comprising:

9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the information pushing method according to any of claims 1 to 7 when the computer program is executed by the processor.

10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the steps of the information pushing method of any of claims 1 to 7.