CN117579689A

CN117579689A - Message touch method, storage medium and electronic equipment

Info

Publication number: CN117579689A
Application number: CN202311568325.5A
Authority: CN
Inventors: 付立宪
Original assignee: Seashell Housing Beijing Technology Co Ltd
Current assignee: Seashell Housing Beijing Technology Co Ltd
Priority date: 2023-11-22
Filing date: 2023-11-22
Publication date: 2024-02-20

Abstract

The embodiment of the disclosure discloses a message touch method, a storage medium and electronic equipment, wherein the method comprises the following steps: responding to the received touch message to be audited, and generating the content to be audited of the touch message according to the configuration information of the touch message; inputting the content to be checked into a pre-trained deep learning model, and checking the touch message according to the content to be checked through the deep learning model; responding to the deep learning model to output a first checking result, and acquiring a sending frequency control rule of the touch message according to the first checking result and a target touch user, wherein the first checking result comprises checking passing indication information and the message type of the touch message; and sending a touch message to the target touch user according to the sending frequency control rule. The embodiment of the disclosure can realize the content auditing and classification of the touch message based on the model, reduce the manual participation degree and realize the frequency control rule based on the user portrait.

Description

Message touch method, storage medium and electronic equipment

Technical Field

The disclosure relates to the technical field of data processing, and in particular relates to a message touch method, a storage medium and electronic equipment.

Background

With the development of internet technology, the variety of internet services is also increasing, and how to reach a user quickly and effectively is an important factor for enhancing the interaction experience between a service party and the user.

In the related art, when a message needs to be touched to a user, an operator generally performs message content configuration and message content auditing, so that the workload of the operator is increased, and the accuracy of the touched message cannot be ensured.

Disclosure of Invention

In order to solve the technical problems described above, embodiments of the present disclosure provide a message touch method, a storage medium, and an electronic device.

According to an aspect of the disclosed embodiments, there is provided a message touchdown method, applied to a touchdown system, including:

responding to a received touch message to be audited, and generating the content to be audited of the touch message according to the configuration information of the touch message;

inputting the content to be checked into a pre-trained deep learning model, and checking the touch message according to the content to be checked through the deep learning model;

responding to the deep learning model to output a first checking result, and acquiring a sending frequency control rule of the touch message according to the first checking result and a target touch user of the touch message, wherein the first checking result comprises checking passing indication information and a message type of the touch message;

And sending the touch message to the target touch user according to the sending frequency control rule.

In some alternative embodiments, the configuration information includes touch content data;

the generating the content to be audited of the touch message according to the configuration information of the touch message comprises the following steps:

acquiring configuration information of the touch message;

and carrying out text processing on the touch content data to generate the content to be audited of the touch message.

In some alternative embodiments, the touch content data includes a message title, a message digest, and a message content link;

the text processing is performed on the touch content data to generate the content to be audited of the touch message, which comprises the following steps:

acquiring page source code data corresponding to the message content links;

performing text processing on the page source code data to obtain message content data of a touch message;

and determining the message content data, the message title and the message abstract as the content to be audited.

In some alternative embodiments, the first audit result further includes a message type of the touch-up message;

the obtaining, according to the first checking result and the target touch user of the touch message, a sending frequency control rule of the touch message includes:

Generating a user portrait of the target touch user based on the user data of the target touch user in a database, wherein the user portrait comprises an activity label of the user and a message feedback label of the user;

acquiring a user frequency control rule matched with a user portrait of the target touch user and a type frequency control rule matched with a message type of the touch message;

and determining the sending frequency control rule of the target touch user according to the type frequency control rule and the user frequency control rule.

In some alternative embodiments, the method further comprises:

acquiring operation log information of each user in a first set time period according to a first set period, wherein each user comprises the target touch user;

determining activity labels of the users according to operation log information of the users in a first set time period;

and updating user data of each user in the database according to the activity label of each user.

In some alternative embodiments, the method further comprises:

acquiring feedback behavior information of each user in a second set time period according to a second set period, wherein each user comprises the target touch user;

Determining message feedback labels of the users according to feedback behavior information of the users in a second set time period;

and updating user data of each user in the database according to the message feedback labels of each user.

In some optional embodiments, after the obtaining the sending frequency control rule of the touch up message, the method further includes:

setting the value of the frequency control counting field as a first preset value;

the sending the touch message to the target touch user according to the sending frequency control rule comprises the following steps:

sending the touch message to the target touch user;

in response to successful sending of the touch message to the target touch user, updating the value of the frequency control count field once;

determining whether the touch message which is sent at present is sent for the last time or not based on whether the updated value of the frequency control counting field is a second preset value or not;

responding to the touch message which is sent at present as the last time, and stopping sending the touch message;

and responding to the fact that the currently transmitted touch message is not transmitted for the last time, and executing the operation of transmitting the touch message to the target touch user.

In some alternative embodiments, the method further comprises:

and responding to a second audit result output by the pre-trained deep learning model, and sending the second audit result to an operation client so that the operation client can send corrected touch information to the touch system after correcting the touch information, wherein the second audit result is used for indicating audit failure and audit failure reason data.

According to another aspect of an embodiment of the present disclosure, there is provided a message touchdown device, applied to a touchdown system, including:

the generating module is used for responding to the received touch message to be audited and generating the content to be audited of the touch message according to the configuration information of the touch message;

the sending module is used for inputting the content to be checked into a pre-trained deep learning model, and checking the touch message according to the content to be checked through the deep learning model;

the frequency control module is used for responding to the deep learning model to output a first checking result, and acquiring a sending frequency control rule of the touch message according to the first checking result and a target touch user of the touch message, wherein the first checking result comprises checking passing indication information and a message type of the touch message;

And the touch module is used for sending the touch message to the target touch user according to the sending frequency control rule.

In some alternative embodiments, the apparatus further comprises:

and the auditing failure module is used for responding to a second auditing result output by the pre-trained deep learning model, sending the second auditing result to an operation client so that the operation client can send corrected touch information to the touch system after correcting the touch information, and the second auditing result is used for indicating auditing failure and auditing failure reason data.

In some optional embodiments, the configuration information further includes touch content data; the generation module comprises:

the first acquisition sub-module is used for acquiring configuration information of the touch message;

and the generation sub-module is used for carrying out text processing on the touch content data and generating the content to be audited of the touch message.

the generating submodule includes:

the acquisition unit is used for acquiring page source code data corresponding to the message content links;

The text processing unit is used for performing text processing on the page source code data to obtain message content data of the touch message;

and the determining unit is used for determining the message content data, the message title and the message abstract as the content to be audited.

In some alternative embodiments, the first audit result further includes a message subtype of the touch-up message;

the frequency control module comprises:

the second acquisition sub-module is used for generating a user portrait of the target touch user based on the user data of the target touch user in the database, wherein the user portrait comprises an activity label of the user and a message feedback label of the user;

the matching sub-module is used for acquiring a user frequency control rule matched with the user portrait of the target touch user and a type frequency control rule matched with the message type of the touch message;

and the first determining submodule is used for determining the sending frequency control rule of the target touch user according to the type frequency control rule and the user frequency control rule.

In some alternative embodiments, the apparatus further comprises:

the first acquisition module is used for acquiring operation log information of each user in a first set time period according to a first set period, wherein each user comprises the target touch user;

The liveness determining module is used for determining liveness labels of the users according to operation log information of the users in a first set time period;

and the first updating module is used for updating the user data of each user in the database according to the activity label of each user.

In some alternative embodiments, the apparatus further comprises:

the second acquisition module is used for acquiring feedback behavior information of each user in a second set time period according to a second set period, wherein each user comprises the target touch user;

the feedback determining module is used for determining message feedback labels of the users according to feedback behavior information of the users in a second set time period;

and the second updating module is used for updating the user data of each user in the database according to the message feedback labels of each user.

In some alternative embodiments, the apparatus further comprises:

the setting module is used for setting the value of the frequency control counting field to be a first preset value;

the touch module comprises:

the sending submodule is used for sending the touch message to the target touch user;

an updating sub-module, configured to update the value of the frequency control count field once in response to successfully sending a touch message to the target touch user;

A second determining submodule, configured to determine whether the touch message that is currently sent is sent for the last time based on whether the updated value of the frequency control count field is a second preset value;

the first response sub-module is used for responding to the touch message which is sent out at present and is sent out for the last time, and stopping sending the touch message;

and the second response sub-module is used for responding that the touch message which is sent out at present is not sent for the last time, and executing the operation of sending the touch message to the target touch user.

According to a further aspect of the disclosed embodiments, a computer readable storage medium is provided, the storage medium storing a computer program for performing the method of the preceding claims.

According to still another aspect of an embodiment of the present disclosure, there is provided an electronic device including:

a processor;

a memory for storing the processor-executable instructions;

the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method of the preceding claim.

Based on the message reaching method, device and storage medium provided by the embodiments of the present disclosure, when a scene requiring reaching a message, for example, an application platform has a new marketing activity or has burst news, a reaching system may receive a reaching message to be audited, and then may generate the content to be audited of the reaching message according to the configuration information of the reaching message; inputting the content to be checked into a pre-trained deep learning model, and checking the touch message according to the content to be checked through the deep learning model; responding to the deep learning model to output a first checking result, and acquiring a sending frequency control rule of the touch message according to the first checking result and a target touch user, wherein the first checking result comprises checking passing indication information and a message type of the touch message; and sending the touch message to the target touch user according to the sending frequency control rule. Therefore, the technical scheme can adopt the pre-trained deep learning model to audit the message content of the touch message and classify the touch message, so that the participation of operators in message audit is reduced; after the verification is passed, the matched sending frequency control rule is determined according to the message type and the target touch user, so that personalized frequency control is realized, and the dissatisfaction and unsupervised rate of the user can be reduced.

The technical scheme of the present disclosure is described in further detail below through the accompanying drawings and examples.

Drawings

The above and other objects, features and advantages of the present disclosure will become more apparent by describing embodiments thereof in more detail with reference to the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the disclosure, and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the disclosure, without limitation to the disclosure. In the drawings, like reference numerals generally refer to like parts or steps.

The disclosure may be more clearly understood from the following detailed description taken in conjunction with the accompanying drawings in which:

FIG. 1 is an exemplary application scenario diagram of a message touchdown method of the present disclosure;

FIG. 2 is a schematic diagram of a touch system in a message touch method of the present disclosure;

FIG. 3 is a flow chart of one embodiment of a message touchdown method of the present disclosure;

FIG. 4 is a flow diagram of one embodiment of generating to-be-audited content of a reach-in message of the present disclosure;

FIG. 5 is a flow chart of one embodiment of obtaining a transmit frequency rule in a message touchdown method of the present disclosure;

FIG. 6 is a flow chart of one embodiment of frequency control in a message touchdown method of the present disclosure;

FIG. 7 is a schematic diagram of a structure of one embodiment of a messaging device of the present disclosure;

FIG. 8 is a schematic diagram of a message touchdown device of another embodiment of the present disclosure;

fig. 9 is a block diagram of an electronic device provided in an exemplary embodiment of the present disclosure.

Detailed Description

Hereinafter, example embodiments according to the present disclosure will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present disclosure and not all of the embodiments of the present disclosure, and that the present disclosure is not limited by the example embodiments described herein.

It should be noted that: the relative arrangement of the components and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless it is specifically stated otherwise.

It will be appreciated by those of skill in the art that the terms "first," "second," etc. in embodiments of the present disclosure are used merely to distinguish between different steps, devices or modules, etc., and do not represent any particular technical meaning nor necessarily logical order between them.

It should also be understood that in embodiments of the present disclosure, "plurality" may refer to two or more, and "at least one" may refer to one, two or more.

It should also be appreciated that any component, data, or structure referred to in the presently disclosed embodiments may be generally understood as one or more without explicit limitation or the contrary in the context.

In addition, the term "and/or" in this disclosure is merely an association relationship describing an association object, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the front and rear association objects are an or relationship.

It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and that the same or similar features may be referred to each other, and for brevity, will not be described in detail.

Meanwhile, it should be understood that the sizes of the respective parts shown in the drawings are not drawn in actual scale for convenience of description.

The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.

Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail, but are intended to be part of the specification where appropriate.

It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further discussion thereof is necessary in subsequent figures.

Embodiments of the present disclosure may be applicable to electronic devices such as terminal devices, computer systems, servers, etc., which may operate with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with the terminal device, computer system, server, or other electronic device include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments that include any of the above systems, and the like.

Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc., that perform particular tasks or implement particular abstract data types. The computer system/server may be implemented in a distributed cloud computing environment in which tasks are performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computing system storage media including memory storage devices.

Summary of the disclosure

The technical scheme provided by the embodiment of the disclosure is used in a scene that a system or each application program needs to reach a message to a user, for example, when an emergency notification needs to be issued to the user in one application program or a marketing activity needs to be pushed to the user, an operator can firstly create a reach message, set some configuration information of the reach message, realize content audit and service classification of the reach message according to the technical scheme of the disclosure, and send the reach message to a target reach user according to a matched frequency control rule.

Exemplary application

The embodiment of the disclosure can be applied to a touch system to push various types of touch messages. For example, messaging is performed for periodic tasks or bursty tasks of various applications. The embodiment of the disclosure does not limit specific application scenarios and touch message attributes (whether the touch message attributes belong to periodic tasks or bursty tasks, etc.).

Fig. 1 is an exemplary application scenario diagram of a message touchdown method of the present disclosure. As shown in fig. 1, when a message is delivered, an operator 1 may first create a delivering message to be audited through an operation platform 2 of a service party, and set configuration information of the delivering message, where the configuration information includes a target delivering user, delivering content data (delivering content data includes a message title, a message abstract and a message content link) and delivering configuration information, then submit the delivering message to be audited to a delivering system 3, the delivering system 3 generates content to be audited of the delivering message according to the configuration information of the delivering message, and invokes an interface of a pre-trained deep learning model 4, requests to audit the content to be audited of the delivering message through the pre-trained deep learning model 4, and if the auditing result is auditing failure, returns the auditing result of the delivering message to the delivering system 3, and the delivering system 3 is prompted to regenerate and submit an auditing message to the operator 1. If the auditing result is that the auditing result passes, the auditing result of the touch message is returned to the touch system 3, and the touch system 3 acquires the sending frequency control rule corresponding to the target starting user to send the touch message.

One exemplary architecture of the touch system 3 can be seen in fig. 2, wherein the service is an access party of the touch system, such as a new house, a research institute, a second house, a benefit house, a home decoration, etc.; the access layer is used for indicating a mode of accessing the service into the touch system, the mode of accessing the service into the touch system can be a dubbo mode, a hypertext transfer protocol (Hypertext Transfer Protocol, abbreviated as HTTP) mode, and after accessing the touch system, messages can be transmitted between a service party and the touch system by an application program interface (Application Programming Interface, abbreviated as API) mode, wherein a management background module is used for configuring configuration information of background service for the service party; the core capability module can set the message style, the frequency control rule and the sending mode of the touch message respectively through the preprocessing layer, the control layer and the policy layer, in specific implementation, the preprocessing layer can realize the configuration of the touch message content through content replacement, field verification and the like by generating unique identification information of the touch message, carrying out style matching selection message style of the touch message, and the control layer can set the sending configuration through frequency control, time interval control, limit control, rule control and the like, and the policy layer can set the sending mode, for example, the sending mode can be real-time sending, time delay sending, asynchronous sending, batch sending and the like for message touch; the touch mode is set through the touch layer, including instant messaging (Instant Messaging, abbreviated as IM), PUSH (PUSH) message, short message, coupon platform, enterprise micro-message, etc., and the message can be ensured to reach the user through touch guarantee; the bottom layer dependence module is used for controlling data stored in the system, and various algorithms are utilized to meet the requirements of users on access, information acquisition and the like, including a touch channel, a rule engine and the like.

Exemplary method

FIG. 3 is a flow chart of one embodiment of a message touchdown method of the present disclosure; the message touch method can be applied to an electronic device (such as a computer system or a server), and as shown in fig. 3, the message touch method comprises the following steps 301 to 304. The steps are described below.

In step 301, in response to receiving the touch message to be audited, the content to be audited of the touch message is generated according to the configuration information of the touch message.

The configuration information of the touch message comprises touch sending configuration information and a target touch user.

In some alternative embodiments, the service may set a touch message on the operation platform by an operator in various scenarios where there are marketing activities, emergency notification, version update, breaking news, etc. that require pushing a message to the user.

When the service sends the touch-up message to be audited to the touch-up system, the sent content can comprise configuration information of the touch-up message. The configuration information may include touch-up transmission configuration information, target touch-up users, and touch-up content data.

The touch-up sending configuration information may include sending time, touch-up mode, touch-up policy, and the like. For example, the set sending time is 2023-07-18:14:30:00, and the set touch mode is push message; the set touch strategy is batch transmission, etc.

The target touch user is used for indicating the user to which the touch message needs to be pushed, and the target touch user can be set by limiting the characteristics of the user, for example, the target touch user is set to be a user about 30 years old, more active and located in Beijing, so that user identification information meeting the condition can be obtained, and message touch can be realized through the user identification information when the message is pushed.

The touch content data is used for indicating message content of a touch message, for example, one touch message is a push message, and the message content of the push message comprises a message title, a message abstract and a message content link.

In some alternative embodiments, taking a push message as an example, the touch system may acquire the content linked to by the message content link after receiving the touch message to be audited, and perform text processing on the linked content to obtain text content, so as to obtain message content data.

In step 302, the content to be audited is input into a pre-trained deep learning model, and the touch message is audited according to the content to be audited through the deep learning model.

Optionally, the pre-trained deep learning model includes: the obtained initial model is trained in advance, and a classification module to be trained is obtained. The initial model may be ChatGPT (generated Pre-Trained Transformer), a Pre-training transformation model.

Here, the initial model is used to process natural language. The classification module to be trained is used for classifying the touch message and outputting the message type of the touch message.

In specific implementation, the training sample set can be utilized to train the initial model to obtain a pre-trained deep learning model. The training sample set comprises a plurality of training samples, and each training sample comprises to-be-audited content of the touch message and a corresponding sample classification label. The sample classification labels corresponding to each training sample can be marked by operators.

The pre-trained deep learning model can utilize the input to-be-checked content to check and classify the touch message, and output the checking result of the touch message, wherein the checking result comprises whether the touch message passes the checking and the message type of the touch message.

In some of these embodiments, the message types may include a service class, a marketing class; further, the message type may further include a touch manner, for example, the message may be a message type such as instant chat, audio-video call, instant subscription, event reminder, account dynamic, transaction information, non-instant subscription, content recommendation, news, research, other, marketing promotion, function recommendation, operation campaign, etc.

For example, the result of the audit is that the audit is passed and there are no wrongly written words. The message type is a service class message, or an instant subscription message of a service class.

The initial model for processing the natural language may be other models in the related art, which is not limited thereto.

In some optional embodiments, after receiving the content to be audited, the pre-trained deep learning model can audit and classify the touch message according to the content to be audited.

In step 303, in response to the deep learning model outputting the first result, according to the first result and the target touch user of the touch message, a sending frequency control rule of the touch message is obtained.

The first audit result comprises the indication information of the audit passing and the message type of the touch message.

In some optional embodiments, the pre-trained deep learning model may audit the content to be audited to obtain an audit result, and if a first audit result is obtained, the audit is passed; and if the second auditing result is obtained, the auditing is failed. The first audit result may include, in addition to the indication information that the audit is passed, a classification result, such as a message type including a touch message.

In some optional embodiments, when the audit result is the first audit result, the matched sending frequency control rule may be obtained according to the message type of the touch message and the target touch user to be pushed, and the specific implementation manner may refer to an embodiment shown in fig. 5, which will not be described in detail herein.

In step 304, a touch message is sent to the target touch user according to the sending frequency control rule.

In some optional embodiments, the touch system may send the touch message to the downstream push interface according to the sending frequency control rule, so as to achieve that the message touches the user end.

In some alternative embodiments, the implementation of sending the touch-up message according to the sending frequency control rule may refer to the embodiment shown in fig. 6, which is not described in detail herein.

In the above steps 301 to 304, when the application platform has a new marketing campaign or has burst news, the touch system may receive the touch message to be audited, and then may generate the content to be audited of the touch message according to the configuration information of the touch message; inputting the content to be checked into a pre-trained deep learning model, and checking the touch message according to the content to be checked through the deep learning model; responding to the deep learning model to output a first checking result, and acquiring a sending frequency control rule of the touch message according to the first checking result and a target touch user, wherein the first checking result comprises checking passing indication information and a message type of the touch message; and sending the touch message to the target touch user according to the sending frequency control rule. Therefore, the technical scheme can adopt the pre-trained deep learning model to audit the message content of the touch message and classify the touch message, so that the participation of operators in message audit is reduced; after the verification is passed, the matched sending frequency control rule is determined according to the message type and the target touch user, so that personalized frequency control is realized, and the dissatisfaction and unsupervised rate of the user can be reduced.

In an alternative embodiment, in response to receiving a second audit result output by the pre-trained deep learning model, the second audit result is sent to the operation client, so that after the operation client corrects the touch message, the corrected touch message is sent to the touch system, and the second audit result is used for indicating the audit failure and audit failure reason data.

When the pre-trained deep learning model is not checked, for example, if the pre-trained deep learning model is wrongly written and the sentence is not smooth, a second checking result can be returned to the touch system, and the touch system is returned to the operation client side, so that the operator can submit the check again after correcting the problem in the touch message.

FIG. 4 is a flow chart of yet another embodiment of a message touchdown method of the present disclosure; the present embodiment is exemplified by how to generate the content to be audited of the touch-up message, as shown in fig. 4, and includes the following steps 401 to 402. The following steps are described:

in step 401, configuration information of a touchdown message is acquired.

Taking a push message as an example, the touch content data included in the message content data of the push message may include a message header, a message abstract, and a message content link.

In step 402, the touch content data is text processed to generate the content to be audited of the touch message.

Optionally, page source code data corresponding to the message content link can be obtained; performing text processing on the page source code data to obtain message content data of the touch message; message content data, message titles, and message digests are determined to be the content to be checked. In particular implementations, the touch system may request a uniform resource locator (Uniform Resource Locator, abbreviated as URL) link through a hypertext transfer protocol (Hypertext Transfer Protocol, abbreviated as HTTP) client to obtain linked page source code data. Since the page source code data contains hypertext markup language (HyperText Markup Language, abbreviated as HTML) tags, HTML tags in the page source code data can be deleted to obtain message content data.

In the implementation process, page source code data can be analyzed by adopting a parse method of an html Parser class of an Apache Tika framework (or other text processing libraries), and text contents after html labels are deleted, so that three fields of a message title, a message abstract and message content data are obtained.

And utilizing a pre-trained deep learning model to audit and classify the input content to be audited (comprising a message title, a message abstract and message content data), and outputting indication information of whether the audit of the trigger message is passed or not and the message type of the trigger message.

Through the steps 401 to 402, the generation of the content data to be checked and the checking configuration information according to the configuration information of the touch message is realized, so that the touch message can be checked and classified according to the content to be checked by a pre-trained deep learning model, the participation of operators in message checking is reduced, and the checking efficiency can be improved.

FIG. 5 is a flow chart of one embodiment of obtaining a transmit frequency rule in a message touchdown method of the present disclosure; as shown in fig. 5, in this embodiment, step 303 may include steps 331 to 333. The respective steps are explained below.

In step 331, a user representation of the target touch user is generated based on the user data of the target touch user in the database, the user representation including an liveness tag of the user and a message feedback tag of the user.

The user data may include identification information of the user, login operation data of the user, feedback behavior data, age groups to which the user belongs, cities, interests and hobbies and the like. Based on the user data, a user profile for the user may be generated, including a user liveness tag, a user message feedback tag. The database may store user representations of the respective users and periodically update the user representations of the respective users according to a set period of time.

It should be noted that, the user data (including, but not limited to, data uploaded by the user, data pre-stored in the cloud server, etc.) related to the present application are all information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data all need to comply with related laws and regulations and standards of related countries and regions, and a corresponding operation entry is provided for the user to select authorization or refusing or revoke authorization.

Alternatively, the user's liveness flag may update the settings according to the user's operation log information within the first set period of time. The value of the user liveness flag may be preset, for example, active, inactive, very active, etc.

Specifically, the operation log information of each user in a first set time period can be obtained according to a first set period; determining activity labels of all users according to operation log information of all users in a first set time period; and updating the user data of each user in the database according to the activity label of each user. For example, log information such as login information and browsing access time in the last seven days of the user may be counted once a week, and if the log information indicates that the number of logins and accesses in the last seven days of the user exceeds a set number, the activity level flag of the user may be determined to be very active, and updated and recorded in the database.

In the implementation manner, the activity label of the user is updated regularly according to the operation log information of the user in the first set time period, so that the activity label of the user can be dynamically adjusted, and the real-time effectiveness of the activity label of the user is ensured.

Optionally, the message feedback tag of the user may update the setting according to feedback behavior information of the user in the second set period. The value of the message feedback tag may be preset, for example, may be active, inactive, etc. Specifically, feedback behavior information of each user in a second set time period can be obtained according to a second set period; determining message feedback labels of all users according to feedback behavior information of all users in a second set time period; and updating user data of the users in the database according to the message feedback labels of the users. For example, feedback behaviors of the user in the last three days can be counted every three days, including click viewing, neglecting, unsubscribing and the like, if the operation modes of all touch messages in the last three days of the user are neglected, the message feedback label of the user is not positive, and the message feedback label of the user can be updated and recorded in a database.

In the implementation manner, the message feedback label of the user is updated periodically according to the feedback behavior information of the user in the second set time period, so that the message feedback label can be dynamically adjusted according to the feedback behavior information of the user.

It will be appreciated that there is typically a positive correlation between the liveness tag of a user and the message feedback tag, which may typically be positive if a user is active on an application.

In step 332, user frequency rules matching the user representation of the target touch user are obtained, as well as type frequency rules matching the message type of the touch message.

In some optional embodiments, the database may further store a user frequency control rule matched with the user portrait, for example, if the activity label is very active, the corresponding user frequency control rule may be that the frequency control amount of a single-day push message is 5, the frequency control amount of a single-day non-instant message is 3, and so on; or if the message feedback label is not positive, the corresponding user frequency control rule can be that the frequency control limit of the single-day push message is 2, the frequency control limit of the single-day non-instant message is 1, and the like.

In some optional embodiments, if the user frequency control rule corresponding to the liveness tag of the user and the message feedback tag are different, the value with the smaller frequency control limit may be used as the user frequency control rule. For example, if the liveness tag is very active, the corresponding user frequency control rule may be that the frequency control limit of the single-day push message is 5; and the message feedback label of the user is not positive, the corresponding user frequency control rule can be 2 frequency control units of the single-day push message, and the user frequency control rule of the user can be set as the user frequency control rule and can be 2 frequency control units of the single-day push message.

In some optional embodiments, different priorities may be set for different user portraits in the touch system, where when the user frequency control rules corresponding to different user portraits are different, the user frequency control rules may be set according to the user portraits with high priorities. For example, if the liveness tag is very active, the corresponding user frequency control rule may be 5 frequency control units of the single-day push message, while the message feedback tag is not active, and the corresponding user frequency control rule may be 2 frequency control units of the single-day push message. The priority of the liveness tag is higher than that of the message feedback tag, and then the user frequency control rule of the user can be set to be 5 frequency control units of a single-day push message.

In some optional embodiments, the click rate of the message of each message type may be counted every set period of time, for example, the click rate of the message of each message type is counted every ten days, and the importance degree of each message is calculated according to the click rate of each message, so as to set the type frequency control rule of each message type. For example, by calculation, it can be found that the message types such as instant chat, audio-video call, instant subscription, item reminding, account dynamic, transaction information and the like have a relatively high degree of correlation with the user, and the user usually cannot resist the messages, so that the messages can not be controlled frequently; and the information such as non-instant subscription, content recommendation, news, investigation, other, marketing popularization, function recommendation, operation activities and the like has small relativity with the user, so that the information types can be controlled frequently to avoid causing dissatisfaction and unsubscribing rate of the user.

After the pre-trained deep learning model performs auditing and classification on the to-be-audited content of the touch message, an auditing result can be returned, wherein the auditing result also comprises the message type, and according to the message type, a type frequency control rule corresponding to the message type can be acquired from a database.

In step 333, the transmission frequency control rule of the target touch user is determined according to the type frequency control rule and the user frequency control rule.

In some optional embodiments, different priorities may be set for the type frequency control rule and the user frequency control rule in the touch system, and when the user frequency control rule determined for one user is different from the type frequency control rule, the user frequency control rule with a high priority may be selected as the transmission frequency control rule. For example, the user frequency control rule determined according to the user portrait is 5 frequency control limits of the single-day push message, and the type frequency control rule determined according to the message type is 2 frequency control limits of the single-day push message. And if the priority of the user frequency control rule is higher than that of the type frequency control rule, setting the frequency control rule to be the frequency control limit of a single-day push message to be 5.

In some alternative embodiments, if the type of frequency control rule and the user frequency control rule are not the same, a smaller value (or a larger value) of the frequency control unit may be used as the transmission frequency control rule. For example, the type frequency control rule is that the frequency control limit of a single-day push message is 5; and the frequency control rule of the user corresponding to the user portrait is that the frequency control limit of the single-day push message is 2, and the frequency control rule of the user for sending can be set to be that the frequency control limit of the single-day push message is 2.

Step 331 to step 333 described above may be implemented to set different user frequency control rules for different target touch users by determining the user frequency control rules according to the user portrait, so as to improve the push effect of the touch message; and the corresponding type frequency control rule is selected according to the message type, so that different frequency control rules can be set for different types of messages, the pushing effect of the touch message can be further improved, personalized frequency control is realized, and the dissatisfaction and unsubscribing rate of a user can be reduced.

In some alternative embodiments, after setting the transmission frequency control rule of the message, the touch-up message may be transmitted according to the determined transmission frequency control rule by a variable (frequency control count field). After determining the transmission frequency control rule according to the embodiment shown in fig. 5, the value of the frequency control count field is set to a first preset value, where the first preset value may be the value of a single daily frequency control quota in the transmission frequency control rule. For example, if the transmission frequency control rule is "the frequency control credit of a single day push message is 2", the value of the frequency control count field may be set to 2. It should be noted that, since the transmission frequency control rules of different target touch users may be different, a value of a frequency control count field may be set for each target touch user.

After determining the transmission frequency control rule of each target touch user and setting the corresponding frequency control count field, message touch can be achieved through the embodiment shown in fig. 6.

FIG. 6 is a flow chart of one embodiment of frequency control in a message touchdown method of the present disclosure; as shown in fig. 6, in this embodiment, step 304 may include steps 341 through 345. The respective steps are explained below.

In step 341, a reach message is sent to the target reach user.

Optionally, the message touch can be sent to a downstream push interface, so as to achieve the purpose of achieving the message touch to the target touch user.

In step 342, the value of the frequency count field is updated once in response to successfully sending the touch down message to the target touch down user.

Optionally, after a successful sending of a touch message to a target touch user, the value of the frequency control calculation field corresponding to the target touch user may be subtracted by 1.

In step 343, it is determined whether the currently transmitted touch message is the last transmission based on whether the value of the updated frequency count field is a second preset value.

Wherein, since the first preset value is the value of the single day frequency control quota in the sending frequency control rule, the second preset value may be 0, and when the touch message is sent once, the 1-subtracting operation is performed, and when the value of the frequency control count field becomes the second preset value (0), it may be determined that the touch message that is sent completely at present is sent for the last time, and step 344 may be performed; when the value of the frequency count field has not changed to the second preset value, it indicates that the currently sent touch-up message is not the last sent, and step 345 may be performed.

In step 344, in response to the currently sent touch down message being the last transmission, the touch down message is stopped.

In step 345, in response to the currently transmitted reach message not being the last transmission, an operation is performed to transmit the reach message to the target reach user.

The steps 341 to 345 provide a specific implementation manner of implementing the sending of the touch message according to the corresponding sending frequency control rule after determining the sending frequency control rule, so as to ensure that the touch message can touch the user according to the sending frequency control rule.

Corresponding to the foregoing embodiments of the messaging method, the present disclosure also provides corresponding embodiments of the messaging device.

Exemplary apparatus

Fig. 7 is a schematic structural diagram of an embodiment of a messaging device of the present disclosure, where the device is applied to an electronic apparatus (e.g., a computer system, a server), as shown in fig. 7, and the device includes:

a generating module 71, configured to generate, in response to receiving a reach message to be audited, content to be audited of the reach message according to configuration information of the reach message;

a sending module 72, configured to input the content to be checked into a pre-trained deep learning model, and check the touch message according to the content to be checked through the deep learning model;

The frequency control module 73 is configured to respond to the deep learning model to output a first audit result, and obtain a sending frequency control rule of the touch message according to the first audit result and a target touch user of the touch message, where the first audit result includes indication information that the audit is passed and a message type of the touch message;

and the touch module 74 is configured to send the touch message to a target touch user according to the sending frequency control rule.

Fig. 8 is a schematic structural diagram of yet another embodiment of a messaging device of the present disclosure, as shown in fig. 8, and in an embodiment, based on the embodiment shown in fig. 7, the device further includes:

and the audit failure module 75 is configured to send a second audit result to an operation client in response to receiving the second audit result output by the pre-trained deep learning model, so that after the operation client corrects the touch message, the operation client sends a corrected touch message to the touch system, where the second audit result is used to indicate audit failure and audit failure reason data.

In an embodiment, the configuration information further includes touch content data;

the generation module 71 includes:

A first obtaining sub-module 711, configured to obtain configuration information of the touch message;

and the generating sub-module 712 is configured to perform text processing on the touch content data, and generate content to be audited of the touch message.

In one embodiment, the touch content data includes a message title, a message digest, and a message content link;

the generating sub-module 712 includes:

an acquiring unit 7121, configured to acquire page source code data corresponding to the message content link;

a text processing unit 7122, configured to perform text processing on the page source code data to obtain message content data of the touch message;

a determining unit 7123 for determining the message content data, the message header, and the message digest as to-be-checked content.

In an embodiment, the first audit result further includes a message type of the touch message;

the frequency control module 73 includes:

a second obtaining sub-module 731, configured to generate, based on user data of the target touch user in the database, a user portrait of the target touch user, where the user portrait includes an activity label of the user and a message feedback label of the user;

a matching sub-module 732, configured to obtain a user frequency control rule matching with the user portrait of the target touch user, and a type frequency control rule matching with the message type of the touch message;

The first determining sub-module 733 is configured to determine a transmission frequency control rule of the target touch user according to the type frequency control rule and the user frequency control rule.

In an embodiment, the apparatus further comprises:

a first obtaining module 76, configured to obtain, according to a first setting period, operation log information of each user in a first setting period, where each user includes the target touch user;

an activity determining module 77, configured to determine an activity label of each user according to operation log information of each user in a first set period of time;

a first updating module 78, configured to update user data of each user in the database according to the activity label of each user.

In an embodiment, the apparatus further comprises:

a second obtaining module 79, configured to obtain feedback behavior information of each user in a second set period according to a second set period, where each user includes the target touch user;

the feedback determining module 80 is configured to determine a message feedback tag of each user according to feedback behavior information of each user in a second set period of time;

and the second updating module 81 is configured to update user data of each user in the database according to the message feedback labels of each user.

In an embodiment, the apparatus further comprises:

a setting module 82, configured to set a value of the frequency control count field to a first preset value;

the touchdown module 74 includes:

a sending sub-module 741, configured to send the touch message to the target touch user;

an update sub-module 742, configured to update the value of the frequency count field once in response to successfully sending the touch message to the target touch user;

a second determining submodule 743, configured to determine whether the touch message that is currently sent is sent for the last time based on whether the value of the updated frequency control count field is a second preset value;

a first response sub-module 744, configured to stop sending the touch-up message in response to the touch-up message that is currently sent being sent for the last time;

a second response sub-module 745, configured to perform an operation of sending the touch-up message to the target touch-up user in response to the touch-up message that is currently sent being sent out is not the last time.

Each module and unit in the device can be further divided into finer granularity according to actual demands, and the device can be specifically arranged according to the actual demands.

The device of the embodiment of the present disclosure may be used to implement the method of each embodiment of the present disclosure, and the two correspond to each other in specific implementation, and specific implementations of relevant portions are referred to each other, which is not repeated herein.

Exemplary electronic device, computer program product, and computer-readable storage Medium

The embodiment of the disclosure also provides an electronic device, including: a memory for storing a computer program; and a processor, configured to execute the computer program stored in the memory, where the computer program is executed to implement the message triggering method according to any one of the embodiments of the disclosure.

An electronic device according to an embodiment of the present disclosure, in which an apparatus for implementing a method of an embodiment of the present disclosure may be integrated, is described below with reference to fig. 9. Fig. 9 is a block diagram of an electronic device provided in an exemplary embodiment of the present disclosure, as shown in fig. 9, the electronic device including one or more processors 91, a memory 92 of one or more computer-readable storage media, and a computer program stored on the memory and executable on the processor. The message tactile method described above may be implemented when the program of the memory 92 is executed.

In particular, in practice, the electronic device may further comprise input means 93, output means 94, etc., which are interconnected by a bus system and/or other form of connection mechanism (not shown). It will be appreciated by those skilled in the art that the structure of the electronic device shown in fig. 9 is not limiting of the electronic device and may include more or fewer components than shown, or certain components, or a different arrangement of components.

Wherein:

processor 91 may be a Central Processing Unit (CPU) or other form of processing unit having messaging capability and/or instruction execution capability that performs various functions and processes data by running or executing software programs and/or modules stored in memory 92 and invoking data stored in memory 92 to thereby monitor the electronic device as a whole.

Memory 92 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. Volatile memory can include, for example, random Access Memory (RAM) and/or cache memory (cache) and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on a computer readable storage medium and the processor 91 may execute the program instructions to implement the message touchdown method and/or other desired functions of the various embodiments of the present disclosure above. Various contents such as an input signal, a signal component, a noise component, and the like may also be stored in the computer-readable storage medium.

The input device 93 may be used to receive input numeric or character information and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

The output device 94 may output various information to the outside, including the determined distance information, direction information, and the like. The output device 94 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.

The electronic device may further include a power supply for supplying power to the respective components, and may be logically connected to the processor 91 through a power management system, so that functions of managing charging, discharging, power consumption management, and the like are implemented through the power management system. The power supply may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.

Of course, only some of the components of the electronic device relevant to the present disclosure are shown in fig. 9 for simplicity, components such as buses, input/output interfaces, and the like being omitted. In addition, the electronic device may include any other suitable components depending on the particular application.

In addition to the methods and apparatus described above, embodiments of the present disclosure may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform steps in a message touchdown method according to various embodiments of the present disclosure described in the "exemplary methods" section of the present description.

The computer program product may write program code for performing the operations of embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.

Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium, having stored thereon computer program instructions, which when executed by a processor, cause the processor to perform steps in a message touchdown method according to various embodiments of the present disclosure described in the above "exemplary method" section of the present description.

The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

The basic principles of the present disclosure have been described above in connection with specific embodiments, however, it should be noted that the advantages, benefits, effects, etc. mentioned in the present disclosure are merely examples and not limiting, and these advantages, benefits, effects, etc. are not to be considered as necessarily possessed by the various embodiments of the present disclosure. Furthermore, the specific details disclosed herein are for purposes of illustration and understanding only, and are not intended to be limiting, since the disclosure is not necessarily limited to practice with the specific details described.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different manner from other embodiments, so that the same or similar parts between the embodiments are mutually referred to. For system embodiments, the description is relatively simple as it essentially corresponds to method embodiments, and reference should be made to the description of method embodiments for relevant points.

Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware associated with program instructions, where the foregoing program may be stored in a computer readable storage medium, and when executed, the program performs steps including the above method embodiments; and the aforementioned storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.

The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, firmware. The above-described sequence of steps for the method is for illustration only, and the steps of the method of the present disclosure are not limited to the sequence specifically described above unless specifically stated otherwise. Furthermore, in some embodiments, the present disclosure may also be implemented as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.

The description of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the disclosure in the form disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments were chosen and described in order to best explain the principles of the disclosure and the practical application, and to enable others of ordinary skill in the art to understand the disclosure for various embodiments with various modifications as are suited to the particular use contemplated.

Claims

1. A message touchdown method, applied to a touchdown system, comprising:

2. The method of claim 1, wherein the configuration information includes touch content data; the generating the content to be audited of the touch message according to the configuration information of the touch message comprises the following steps:

acquiring configuration information of the touch message;

3. The method of claim 2, wherein the touch content data includes a message title, a message digest, and a message content link;

acquiring page source code data corresponding to the message content links;

4. A method according to any one of claims 1-3, wherein the first audit result further includes a message type of a touch up message;

5. The method according to claim 4, wherein the method further comprises:

6. The method according to claim 4 or 5, characterized in that the method further comprises:

7. The method of claim 1, wherein after the obtaining the transmission frequency control rule of the touch-up message, the method further comprises:

sending the touch message to the target touch user;

8. The method according to claim 1, wherein the method further comprises:

9. A computer readable storage medium, characterized in that the storage medium stores a computer program for executing the method of any of the preceding claims 1-8.

10. An electronic device, the electronic device comprising:

a processor;

a memory for storing the processor-executable instructions;

the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method of any of the preceding claims 1-8.