WO2019184111A1

WO2019184111A1 - Push message processing method and apparatus, readable storage medium, and terminal device

Info

Publication number: WO2019184111A1
Application number: PCT/CN2018/093347
Authority: WO
Inventors: 姜翔
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-03-30
Filing date: 2018-06-28
Publication date: 2019-10-03
Also published as: CN108616444A; CN108616444B

Abstract

The present application pertains to the technical field of computers, and in particular, to a push message processing method and apparatus, a readable storage medium, and a terminal device. The method comprises: receiving a push message delivered by a message pushing server; sequentially matching the push message with keywords in a preset keyword set, and determining a message type corresponding to a successfully matched keyword as a message type of the push message, the keyword set comprising keyword subsets respectively corresponding to various preset message types, and each keyword subset comprising more than one keyword; acquiring a user acceptance degree corresponding to the message type of the push message; if the user acceptance degree corresponding to the message type is greater than or equal to a preset acceptance threshold, displaying the push message on a specified terminal interface; and if the user acceptance degree corresponding to the message type is less than the acceptance threshold, prohibiting display of the push message on the terminal interface.

Description

Push message processing method, readable storage medium, terminal device and device

This application claims priority to Chinese Patent Application No. 201101293168.4, entitled "Pushing Message Processing Method, Computer Readable Storage Media, and Terminal Equipment", filed on March 30, 2018, the entire disclosure of which is incorporated herein by reference. The content is incorporated herein by reference.

Technical field

The present application belongs to the field of computer technology, and in particular, to a push message processing method, a computer readable storage medium, a terminal device and a device.

Background technique

Users often install a large number of applications (APPs) on mobile devices such as mobile phones and tablet computers, and various types of apps also push various types of information, notifications, and the like to users. As a mobile phone user, it is often disturbed by the push message of the advertisement class. In the prior art, in order to solve this problem, the push message is often blocked, but this often blocks the push information that some users want to see. Drop, affecting the user's experience.

technical problem

In view of this, the embodiment of the present application provides a push message processing method, a computer readable storage medium, a terminal device, and a device, to solve the push that some users want to see when shielding a push message in the prior art. Information is also blocked, affecting the user experience.

Technical solution

A first aspect of the embodiment of the present application provides a method for processing a push message, which may include:

Receiving a push message sent by the message push server;

Matching the push message with the keywords in the preset keyword set, and determining a message type corresponding to the successfully matched keyword as the message type of the push message, where the keyword set includes Each of the preset keyword types corresponds to each of the keyword subsets, and each keyword subset includes more than one keyword;

Obtaining a user acceptance degree corresponding to the message type of the push message, where the user acceptance degree is used to indicate a degree of acceptance of the push message of the specified message type by the user, according to the specified message type of the user within a specified time period The historical feedback record of the push message is calculated;

And if the user acceptance degree corresponding to the message type is greater than or equal to a preset acceptance threshold, displaying the push message to a specified terminal interface;

And if the user acceptance corresponding to the message type is less than the acceptance threshold, the display of the push message on the terminal interface is prohibited.

A second aspect of embodiments of the present application provides a computer readable storage medium storing computer readable instructions that, when executed by a processor, implement the push message processing method described above step.

A third aspect of embodiments of the present application provides a push message processing terminal device including a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, the processor executing The computer readable instructions implement the steps of the push message processing method described above.

A fourth aspect of the embodiments of the present application provides a push message processing apparatus, which may include a module for implementing the steps of the above-described push message processing method.

Beneficial effect

Compared with the prior art, the embodiment of the present application has the beneficial effects of: in the embodiment of the present application, while shielding the push message that the user does not want to see, the normal push of the push message that the user really needs is ensured, and the user is greatly improved. The experience of using.

DRAWINGS

FIG. 1 is a flowchart of an embodiment of a method for processing a push message according to an embodiment of the present application;

2 is a schematic flowchart of initial calculation of a user acceptance degree and an acceptance threshold in the embodiment of the present application;

FIG. 3 is a schematic flowchart of updating and calculating a user acceptance degree and an acceptance threshold in the embodiment of the present application;

4 is a structural diagram of an embodiment of a push message processing apparatus according to an embodiment of the present application;

FIG. 5 is a schematic block diagram of a push message processing terminal device according to an embodiment of the present application.

Embodiments of the invention

Referring to FIG. 1, an embodiment of a method for processing a push message in an embodiment of the present application may include:

Step S101: Receive a push message sent by the message push server.

The protocol on which the message push server delivers the push message may include, but is not limited to, Android Cloud to Device Messaging (C2DM), Message Queuing Telemetry Transport (MQTT), and scalable communication and representation. Specific protocols such as the Extensible Messaging and Presence Protocol (XMPP).

The message push server may include, but is not limited to, a message push server provided by a terminal manufacturer and a message push server provided by a third party server.

In this embodiment, the terminal device may receive only the push message delivered by the message push server, and may also receive the push message sent by the multiple message push server.

Step S102: The push message is matched with the keywords in the preset keyword set, and the message type corresponding to the successfully matched keyword is determined as the message type of the push message.

The keyword set includes respective subsets of keywords corresponding to preset various message types, and each keyword subset includes more than one keyword. For example, the push message can be classified into a message type such as an advertisement class, a news information class, and a system notification class, and each type of push information is set with a corresponding keyword subset. For example, the keyword subset of the advertisement category may include keywords such as "advertisement", "promotion", "offer", and "price reduction".

The order in which the keywords are used for matching may be arbitrary, but considering that the comparison process may take a lot of time when there are a large number of push messages, the following optimized comparison scheme may be adopted: selecting from the keyword set a keyword having the highest priority and not yet selected as the current keyword; searching for the current keyword in the push message; if the current keyword is not found in the push message, returning to the execution Determining, from the keyword set, a step that has the highest priority and has not been selected as a current keyword; if the current keyword is found in the push message, determining the push message and The current keyword is successfully matched, and the message type corresponding to the current keyword is determined as the message type of the push message.

In this way, keywords with higher priority are compared first, and keywords with lower priority are compared, which can greatly reduce the number of comparisons required for comparison.

The calculation process of the priority level may include: acquiring a history matching record in a preset statistical time period; and counting, according to the historical matching record, the number of successful matching of each keyword in the keyword set; The number of times each keyword is successfully matched determines the priority of the respective keywords. The priority of each keyword is positively correlated with the number of successful matching of the respective keywords, that is, the more times a keyword is successfully matched, the higher the priority of the keyword is. The fewer the number of successful matches, the lower the priority of the keyword.

It should be noted that the above manner is to determine the message type by using a keyword, and optionally, the type of the message may be determined by the type identifier. Each push message is sent with a type identifier to identify its type. The different values of the type identifier correspond to different message types. For example, a type identifier of 1 means it is an advertisement, a type identifier of 2 means it is news information, and so on. When the push message is received, the value of the type identifier is read therefrom and its message type is determined accordingly.

Step S103: Acquire a user acceptance degree corresponding to the message type of the push message.

The user acceptance is used to indicate the degree of acceptance of the push message by the user for the specified message type, and is calculated according to the historical feedback record of the push message of the specified message type by the user within a specified time period.

For example, the terminal device prompts the user to feed back the push message, that is, whether it is willing to accept the push message, while displaying the push message to the user. For example, a prompt box may be displayed, in which "whether or not the push message is accepted" is displayed, and then two selection buttons "yes" and "no" are given. If the user selects "yes", it is determined that the user has feedback on the push message. A positive feedback, if the user selects "No", it is determined that the user has fed back a negative feedback to the push message. If the user does not make a selection, it is determined that the user has fed back a neutral feedback to the push message.

In addition, the feedback data may also be determined according to the click behavior of the user: if the user clicks on a certain push message, it is considered to have fed back a positive feedback to the push message, and if the user deletes a push message, it is considered to be The push message feeds back a negative feedback. If the user does not perform any operation on the push message, the user is considered to have fed back a neutral feedback to the push message.

The historical feedback record is obtained by recording the feedback of the user. Through the analysis thereof, the user's acceptance degree of the push message of the specified message type, that is, the user acceptance degree, can be obtained.

Step S104: Determine whether the user acceptance level corresponding to the message type is less than a preset acceptance degree threshold.

If the user acceptance degree corresponding to the message type is greater than or equal to the acceptance degree threshold, step S105 is performed, and if the user acceptance degree corresponding to the message type is less than the acceptance degree threshold, step S106 is performed.

Step S105, displaying the push message to a specified terminal interface.

Generally, in order to improve the convenience of the user to view the push message, the operating system of the terminal device may display the push message to the user through the notification bar of the terminal device, and the user may open the notification bar to view the notification message in real time. Because the screen size of the terminal device is different, and the operation habits of different users on the display interface of the terminal device are different, the specific push message display interface can be adjusted according to actual conditions.

Step S106, prohibiting display of the push message on the terminal interface.

After the push message is forbidden to be displayed, the user will not be able to view the push message, thereby greatly reducing the interference caused by the push message that the user is not interested in.

In order to prevent type curing, the message message of the minimum frequency can be kept for the push message of the message type determined to be prohibited from being displayed, such as no more than one per day or no more than one every two days.

Preferably, the initial calculation process of the user acceptance degree and the acceptance threshold includes the steps shown in FIG. 2:

Step S201: Acquire a historical feedback record of the user within a preset initial time period.

The initial time period may be set according to actual conditions, but it should be noted that if the initial time period is set longer, the calculation result is more accurate, but the calculation amount is larger, and vice versa, some initial time periods are set. The shorter the calculation, the coarser the calculation, but the smaller the calculation, the more you need to balance the two.

Step S202, respectively, according to the historical feedback record, respectively, the number of times that the user forwardly feeds the push messages of various message types in the initial time period, the number of times of negative feedback, and the number of times of neutral feedback are performed.

In step S203, the acceptance threshold is calculated.

Specifically, the acceptance threshold can be calculated according to the following formula:

The Pos _n is the number of times the user forwardly feeds the push message of the message type labeled n in the initial time period, and the Neg _n is the user labeled n in the initial time period. The number of times the message type push message performs negative feedback, and Neu _n is the number of times the user performs neutral feedback on the push message of the message type labeled n in the initial time period, 1≤n≤N, N is The total number of various message types, λ is a preset adjustment coefficient, and Acc _Thresh is the acceptance threshold.

Step S204, respectively calculating user acceptance levels corresponding to various message types.

Specifically, the user acceptance corresponding to the message type labeled n can be calculated according to the following formula:

Among them, Acc _n is the user acceptance corresponding to the message type labeled n.

The above process calculates an initial user acceptance and acceptance threshold, but the user's usage behavior may be constantly changing, so it is necessary to constantly adjust it. The user acceptance and the acceptance threshold are updated every predetermined time period (eg, one week, two weeks, one month, etc.), and the specific update process may include the steps shown in FIG. 3:

Step S301: Acquire a historical feedback record of the user during the update period.

The update period is a period of time from the user acceptance or the last update time of the acceptance threshold to the current time.

Step S302, respectively, according to the historical feedback record, respectively, the number of times that the user forwardly feeds the push messages of various message types during the update time period, the number of times of negative feedback, and the number of times of neutral feedback are performed.

Step S303, calculating an update amount of the acceptance threshold.

Specifically, the update amount of the acceptance threshold may be calculated according to the following formula:

The Pos′ _n is the number of times the user forwardly feeds the push message of the message type labeled n in the update period, and Neg′ _n is the _number of the user in the update period. n message type push message number negative feedback, Neu _'n for the user in reference to the neutral feedback message type push message n times the update period, Acc' _Thresh is the The amount of update of the acceptance threshold.

Step S304, performing an update calculation on the acceptance threshold.

Specifically, the acceptance threshold may be updated and calculated according to the following formula:

Acc _Thresh =k ₁ *Acc _Thresh +(1-k ₁ )*Acc' _Thresh .

Step S305, respectively calculating update amounts of user acceptance levels corresponding to various message types.

Specifically, the update amount of the user acceptance corresponding to the message type labeled n can be calculated according to the following formula:

Where Acc' _n is the update amount of the user acceptance corresponding to the message type labeled n.

Step S306, performing update calculation on the user acceptance levels corresponding to the various message types.

Specifically, the user acceptance corresponding to the message type labeled n can be updated according to the following formula:

Acc _n =k ₂ *Acc _n +(1-k ₂ )*Acc' _n

Where k ₁ and k ₂ are preset weight coefficients. In general, the weight of the user's recent behavior should be slightly larger, so it is preferable to set k ₁ >0.5, k ₂ >0.5.

Through the above process, the shielding mode of the push information is constantly adjusted according to the user's preference, and the user's current usage habit is always matched, so that the user obtains the best use experience.

In summary, in the embodiment of the present application, while the push message that the user does not want to see is shielded, the normal push of the push message that the user really needs is ensured, and the user experience is greatly improved.

Corresponding to a push message processing method according to the above embodiment, FIG. 4 is a structural diagram of an embodiment of a push message processing apparatus provided by an embodiment of the present application.

In this embodiment, a push message processing apparatus may include:

The push message receiving module 401 is configured to receive a push message delivered by the message push server;

The message type determining module 402 is configured to sequentially match the push message with a keyword in a preset keyword set, and determine a message type corresponding to the successfully matched keyword as a message type of the push message. The keyword set includes a respective subset of keywords corresponding to preset various message types, and each keyword subset includes more than one keyword;

The user acceptance degree obtaining module 403 is configured to acquire a user acceptance degree corresponding to the message type of the push message, where the user acceptance degree is used to indicate the acceptance degree of the user for the push message of the specified message type, and the user is specified according to the user Calculating the historical feedback record of the push message of the specified message type in the time period;

The push message display module 404 is configured to display the push message to a specified terminal interface if the user acceptance degree corresponding to the message type is greater than or equal to a preset acceptance degree threshold;

The push message screening module 405 is configured to prohibit display of the push message on the terminal interface if the user acceptance degree corresponding to the message type is less than the acceptance degree threshold.

Further, the push message processing apparatus may further include:

a first record obtaining module, configured to acquire a historical feedback record of the user within a preset initial time period;

a first statistic module, configured to separately count, according to the historical feedback record, the number of times that the user performs positive feedback on push messages of various message types in the initial time period, the number of times of negative feedback, and the neutrality The number of feedbacks;

The acceptance threshold calculation module is configured to calculate the acceptance threshold according to the following formula:

The Pos _n is the number of times the user forwardly feeds the push message of the message type labeled n in the initial time period, and the Neg _n is the user labeled n in the initial time period. the number of messages the message type push negative feedback, Neu _n for the user in the initial period of the numeral n is the number of the push message type neutral feedback messages, 1≤n≤N, N is The total number of various message types, λ is a preset adjustment coefficient, and Acc _Thresh is the acceptance threshold;

The user acceptance calculation module is configured to calculate the user acceptance corresponding to the message type labeled n according to the following formula:

Further, the push message processing apparatus may further include:

a second record obtaining module, configured to acquire a historical feedback record of the user during an update period, where the update period is from a last update time of the user acceptance or the acceptance threshold to a current time Time period

a second statistic module, configured to separately count, according to the historical feedback record, the number of times that the user performs positive feedback on push messages of various message types during the update time period, the number of times of negative feedback, and the neutrality The number of feedbacks;

a first update amount calculation module, configured to calculate an update amount of the acceptance threshold according to the following formula:

The Pos′ _n is the number of times the user forwardly feeds the push message of the message type labeled n in the update period, and Neg′ _n is the _number of the user in the update period. n message type push message number negative feedback, Neu _'n for the user in reference to the neutral feedback message type push message n times the update period, Acc' _Thresh is the The amount of update of the acceptance threshold;

The acceptance threshold update module is configured to perform an update calculation on the acceptance threshold according to the following formula:

Acc _Thresh =k ₁ *Acc _Thresh +(1-k ₁ )*Acc'_Thresh;

The second update amount calculation module is configured to calculate, according to the following formula, the update amount of the user acceptance corresponding to the message type labeled n:

Where Acc' _n is an update amount of user acceptance corresponding to the message type labeled n;

The user acceptance update module is configured to update the user acceptance corresponding to the message type labeled n according to the following formula:

Acc _n =k ₂ *Acc _n +(1-k ₂ )*Acc' _n

Where k ₁ and k ₂ are preset weight coefficients.

Further, the message type determining module may include:

a current keyword selection unit, configured to select, from the keyword set, a keyword with the highest priority and not yet selected as the current keyword;

a current keyword search unit, configured to search for the current keyword in the push message;

a message type determining unit, configured to determine that the push message matches the current keyword successfully, and determine a message type corresponding to the current keyword, if the current keyword is found in the push message The type of message for which the message is pushed.

Further, the push message processing apparatus may further include:

a history matching record obtaining module, configured to acquire a history matching record in a preset statistical time period;

a matching record statistic module, configured to count, according to the historical matching record, a number of times that each keyword in the keyword set matches successfully;

The priority determining module is configured to determine a priority of each keyword according to the number of times the respective keywords match successfully, and the priorities of the keywords are positively correlated with the number of successful matching of the keywords.

FIG. 5 is a schematic block diagram of a push message processing terminal device provided by an embodiment of the present application. The push message processing terminal device 5 may include a processor 50, a memory 51, and computer readable instructions 52 stored in the memory 51 and operable on the processor 50, for example, performing the push message processing method described above Computer readable instructions. When the processor 50 executes the computer readable instructions 52, the steps in the foregoing embodiments of the respective push message processing methods are implemented, such as steps S101 to S106 shown in FIG. Alternatively, when the processor 50 executes the computer readable instructions 52, the functions of the modules/units in the various apparatus embodiments described above are implemented, such as the functions of the modules 401 to 405 shown in FIG.

The functional units in the various embodiments of the present application may be stored in a computer readable storage medium if implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, the technical solution of the present application, in essence or the contribution to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium. A number of computer readable instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application.

Claims

A push message processing method, comprising:

Receiving a push message sent by the message push server;

Matching the push message with the keywords in the preset keyword set, and determining a message type corresponding to the successfully matched keyword as the message type of the push message, where the keyword set includes Each of the preset keyword types corresponds to each of the keyword subsets, and each keyword subset includes more than one keyword;

Obtaining a user acceptance degree corresponding to the message type of the push message, where the user acceptance degree is used to indicate a degree of acceptance of the push message of the specified message type by the user, according to the specified message type of the user within a specified time period The historical feedback record of the push message is calculated;

And if the user acceptance degree corresponding to the message type is greater than or equal to a preset acceptance threshold, displaying the push message to a specified terminal interface;

And if the user acceptance corresponding to the message type is less than the acceptance threshold, the display of the push message on the terminal interface is prohibited.
The push message processing method according to claim 1, wherein the initial calculation process of the user acceptance degree and the acceptance threshold comprises:

Obtaining a historical feedback record of the user within a preset initial time period;

And counting, according to the historical feedback record, the number of times the user forwardly feeds the push messages of the various message types in the initial time period, the number of times of negative feedback, and the number of times of neutral feedback;

The acceptance threshold is calculated according to the following formula:

The Pos n is the number of times the user forwardly feeds the push message of the message type labeled n in the initial time period, and the Neg n is the user labeled n in the initial time period. The number of times the message type push message performs negative feedback, and Neu n is the number of times the user performs neutral feedback on the push message of the message type labeled n in the initial time period, 1≤n≤N, N is The total number of various message types, λ is a preset adjustment coefficient, and Acc Thresh is the acceptance threshold;

Calculate the user acceptance corresponding to the message type labeled n according to the following formula:

Among them, Acc n is the user acceptance corresponding to the message type labeled n.
The push message processing method according to claim 2, wherein the updating process of the user acceptance degree and the acceptance threshold comprises:

Obtaining a historical feedback record of the user during an update period, where the update period is a period of time from the user acceptance or the last update time of the acceptance threshold to the current time;

And counting, according to the historical feedback record, the number of times the user forwardly feeds the push messages of the various message types in the update time period, the number of times of negative feedback, and the number of times of neutral feedback;

The update amount of the acceptance threshold is calculated according to the following formula:

The Pos′ n is the number of times the user forwardly feeds the push message of the message type labeled n in the update period, and Neg′ n is the number of the user in the update period. n message type push message number negative feedback, Neu 'n for the user in reference to the neutral feedback message type push message n times the update period, Acc' Thresh is the The amount of update of the acceptance threshold;

The acceptance threshold is updated according to the following formula:

Acc Thresh =k 1 *Acc Thresh +(1-k 1 )*Acc'Thresh;

The amount of user acceptance corresponding to the message type labeled n is calculated according to the following formula:

Where Acc' n is an update amount of user acceptance corresponding to the message type labeled n;

The user acceptance corresponding to the message type labeled n is updated according to the following formula:

Acc n =k 2 *Acc n +(1-k 2 )*Acc' n

Where k 1 and k 2 are preset weight coefficients.
The push message processing method according to any one of claims 1 to 3, wherein the pushing the message and the keywords in the preset keyword set are sequentially matched, and the matching is successful. The message type corresponding to the keyword type determined as the push message includes:

Selecting, from the keyword set, a keyword with the highest priority and not yet selected as the current keyword;

Finding the current keyword in the push message;

If the current keyword is not found in the push message, returning to performing the step of selecting, from the keyword set, a keyword with the highest priority and not yet selected as the current keyword;

If the current keyword is found in the push message, determining that the push message matches the current keyword successfully, and determining a message type corresponding to the current keyword as the message of the push message Types of.
The push message processing method according to claim 4, wherein the calculation process of the priority comprises:

Obtaining a history matching record within a preset statistical time period;

Counting, according to the historical matching record, the number of successful matching of each keyword in the keyword set;

Determining priorities of the respective keywords according to the number of times the respective keywords match successfully, and the priorities of the respective keywords are positively correlated with the number of successful matching of the respective keywords.
A computer readable storage medium storing computer readable instructions, wherein the computer readable instructions, when executed by a processor, implement the following steps:

Receiving a push message sent by the message push server;

Matching the push message with the keywords in the preset keyword set, and determining a message type corresponding to the successfully matched keyword as the message type of the push message, where the keyword set includes Each of the preset keyword types corresponds to each of the keyword subsets, and each keyword subset includes more than one keyword;

Obtaining a user acceptance degree corresponding to the message type of the push message, where the user acceptance degree is used to indicate a degree of acceptance of the push message of the specified message type by the user, according to the specified message type of the user within a specified time period The historical feedback record of the push message is calculated;

And if the user acceptance degree corresponding to the message type is greater than or equal to a preset acceptance threshold, displaying the push message to a specified terminal interface;

And if the user acceptance corresponding to the message type is less than the acceptance threshold, the display of the push message on the terminal interface is prohibited.
The computer readable storage medium of claim 6, wherein the initial calculation process of the user acceptance and the acceptance threshold comprises:

Obtaining a historical feedback record of the user within a preset initial time period;

And counting, according to the historical feedback record, the number of times the user forwardly feeds the push messages of the various message types in the initial time period, the number of times of negative feedback, and the number of times of neutral feedback;

The acceptance threshold is calculated according to the following formula:

The Pos n is the number of times the user forwardly feeds the push message of the message type labeled n in the initial time period, and the Neg n is the user labeled n in the initial time period. The number of times the message type push message performs negative feedback, and Neu n is the number of times the user performs neutral feedback on the push message of the message type labeled n in the initial time period, 1≤n≤N, N is The total number of various message types, λ is a preset adjustment coefficient, and Acc Thresh is the acceptance threshold;

Calculate the user acceptance corresponding to the message type labeled n according to the following formula:

Among them, Acc n is the user acceptance corresponding to the message type labeled n.
The computer readable storage medium according to claim 7, wherein the updating process of the user acceptance degree and the acceptance threshold comprises:

Obtaining a historical feedback record of the user during an update period, where the update period is a period of time from the user acceptance or the last update time of the acceptance threshold to the current time;

And counting, according to the historical feedback record, the number of times the user forwardly feeds the push messages of the various message types in the update time period, the number of times of negative feedback, and the number of times of neutral feedback;

The update amount of the acceptance threshold is calculated according to the following formula:

The Pos′ n is the number of times the user forwardly feeds the push message of the message type labeled n in the update period, and Neg′ n is the number of the user in the update period. n message type push message number negative feedback, Neu 'n for the user in reference to the neutral feedback message type push message n times the update period, Acc' Thresh is the The amount of update of the acceptance threshold;

The acceptance threshold is updated according to the following formula:

Acc Thresh =k 1 *Acc Thresh +(1-k 1 )*Acc'Thresh;

The amount of user acceptance corresponding to the message type labeled n is calculated according to the following formula:

Where Acc' n is an update amount of user acceptance corresponding to the message type labeled n;

The user acceptance corresponding to the message type labeled n is updated according to the following formula:

Acc n =k 2 *Acc n +(1-k 2 )*Acc' n

Where k 1 and k 2 are preset weight coefficients.
The computer readable storage medium according to any one of claims 6 to 8, wherein the matching the push message with the keywords in the preset keyword set, and matching the match successfully The message type corresponding to the keyword type determined as the push message includes:

Selecting, from the keyword set, a keyword with the highest priority and not yet selected as the current key word;

Finding the current keyword in the push message;

If the current keyword is not found in the push message, returning to performing the step of selecting, from the keyword set, a keyword with the highest priority and not yet selected as the current keyword;

If the current keyword is found in the push message, determining that the push message matches the current keyword successfully, and determining a message type corresponding to the current keyword as the message of the push message Types of.
The computer readable storage medium of claim 9, wherein the calculating process of the priority comprises:

Obtaining a history matching record within a preset statistical time period;

Counting, according to the historical matching record, the number of successful matching of each keyword in the keyword set;

Determining priorities of the respective keywords according to the number of times the respective keywords match successfully, and the priorities of the respective keywords are positively correlated with the number of successful matching of the respective keywords.
A push message processing terminal device comprising a memory, a processor, and computer readable instructions stored in the memory and executable on the processor, wherein the processor executes the computer readable instructions The following steps are implemented:

Receiving a push message sent by the message push server;

Matching the push message with the keywords in the preset keyword set, and determining a message type corresponding to the successfully matched keyword as the message type of the push message, where the keyword set includes Each of the preset keyword types corresponds to each of the keyword subsets, and each keyword subset includes more than one keyword;

Obtaining a user acceptance degree corresponding to the message type of the push message, where the user acceptance degree is used to indicate a degree of acceptance of the push message of the specified message type by the user, according to the specified message type of the user within a specified time period The historical feedback record of the push message is calculated;

And if the user acceptance degree corresponding to the message type is greater than or equal to a preset acceptance threshold, displaying the push message to a specified terminal interface;

And if the user acceptance corresponding to the message type is less than the acceptance threshold, the display of the push message on the terminal interface is prohibited.
The push message processing terminal device according to claim 11, wherein the initial calculation process of the user acceptance degree and the acceptance threshold comprises:

Obtaining a historical feedback record of the user within a preset initial time period;

And counting, according to the historical feedback record, the number of times the user forwardly feeds the push messages of the various message types in the initial time period, the number of times of negative feedback, and the number of times of neutral feedback;

The acceptance threshold is calculated according to the following formula:

The Pos n is the number of times the user forwardly feeds the push message of the message type labeled n in the initial time period, and the Neg n is the user labeled n in the initial time period. The number of times the message type push message performs negative feedback, and Neu n is the number of times the user performs neutral feedback on the push message of the message type labeled n in the initial time period, 1≤n≤N, N is The total number of various message types, λ is a preset adjustment coefficient, and Acc Thresh is the acceptance threshold;

Calculate the user acceptance corresponding to the message type labeled n according to the following formula:

Among them, Acc n is the user acceptance corresponding to the message type labeled n.
The push message processing terminal device according to claim 12, wherein the updating process of the user acceptance degree and the acceptance threshold comprises:

Obtaining a historical feedback record of the user during an update period, where the update period is a period of time from the user acceptance or the last update time of the acceptance threshold to the current time;

And counting, according to the historical feedback record, the number of times the user forwardly feeds the push messages of the various message types in the update time period, the number of times of negative feedback, and the number of times of neutral feedback;

The update amount of the acceptance threshold is calculated according to the following formula:

The Pos′ n is the number of times the user forwardly feeds the push message of the message type labeled n in the update period, and Neg′ n is the number of the user in the update period. n message type push message number negative feedback, Neu 'n for the user in reference to the neutral feedback message type push message n times the update period, Acc' Thresh is the The amount of update of the acceptance threshold;

The acceptance threshold is updated according to the following formula:

Acc Thresh =k 1 *Acc Thresh +(1-k 1 )*Acc'Thresh;

The amount of user acceptance corresponding to the message type labeled n is calculated according to the following formula:

Where Acc' n is an update amount of user acceptance corresponding to the message type labeled n;

The user acceptance corresponding to the message type labeled n is updated according to the following formula:

Acc n =k 2 *Acc n +(1-k 2 )*Acc' n

Where k 1 and k 2 are preset weight coefficients.
The push message processing terminal device according to any one of claims 11 to 13, wherein the push message is sequentially matched with a keyword in a preset keyword set, and the matching is successful. The message type corresponding to the keyword type determined as the push message includes:

Selecting, from the keyword set, a keyword with the highest priority and not yet selected as the current keyword;

Finding the current keyword in the push message;

If the current keyword is not found in the push message, returning to performing the step of selecting, from the keyword set, a keyword with the highest priority and not yet selected as the current keyword;

If the current keyword is found in the push message, determining that the push message matches the current keyword successfully, and determining a message type corresponding to the current keyword as the message of the push message Types of.
The push message processing terminal device according to claim 14, wherein the calculation process of the priority comprises:

Obtaining a history matching record within a preset statistical time period;

Counting, according to the historical matching record, the number of successful matching of each keyword in the keyword set;

Determining priorities of the respective keywords according to the number of times the respective keywords match successfully, and the priorities of the respective keywords are positively correlated with the number of successful matching of the respective keywords.
A push message processing device, comprising:

a push message receiving module, configured to receive a push message delivered by the message push server;

a message type determining module, configured to sequentially match the push message with a keyword in a preset keyword set, and determine a message type corresponding to the successfully matched keyword as a message type of the push message, where The keyword set includes a subset of each keyword corresponding to each of the preset various message types, and each keyword subset includes more than one keyword;

a user acceptance obtaining module, configured to acquire a user acceptance degree corresponding to a message type of the push message, where the user acceptance degree is used to indicate a user acceptance degree of a push message of a specified message type, according to the user at a specified time The historical feedback record of the push message of the specified message type is calculated in the segment;

a push message display module, configured to display the push message to a specified terminal interface if a user acceptance degree corresponding to the message type is greater than or equal to a preset acceptance threshold;

The push message screening module is configured to prohibit display of the push message on the terminal interface if the user acceptance level corresponding to the message type is less than the acceptance degree threshold.
The push message processing device according to claim 16, further comprising:

a first record obtaining module, configured to acquire a historical feedback record of the user within a preset initial time period;

a first statistic module, configured to separately count, according to the historical feedback record, the number of times that the user performs positive feedback on push messages of various message types in the initial time period, the number of times of negative feedback, and the neutrality The number of feedbacks;

The acceptance threshold calculation module is configured to calculate the acceptance threshold according to the following formula:

The Pos n is the number of times the user forwardly feeds the push message of the message type labeled n in the initial time period, and the Neg n is the user labeled n in the initial time period. The number of times the message type push message performs negative feedback, and Neu n is the number of times the user performs neutral feedback on the push message of the message type labeled n in the initial time period, 1≤n≤N, N is The total number of various message types, λ is a preset adjustment coefficient, and Acc Thresh is the acceptance threshold;

The user acceptance calculation module is configured to calculate the user acceptance corresponding to the message type labeled n according to the following formula:

Among them, Acc n is the user acceptance corresponding to the message type labeled n.
The push message processing device according to claim 17, further comprising:

a second record obtaining module, configured to acquire a historical feedback record of the user during an update period, where the update period is from a last update time of the user acceptance or the acceptance threshold to a current time Time period

a second statistic module, configured to separately count, according to the historical feedback record, the number of times that the user performs positive feedback on push messages of various message types during the update time period, the number of times of negative feedback, and the neutrality The number of feedbacks;

a first update amount calculation module, configured to calculate an update amount of the acceptance threshold according to the following formula:

The Pos′ n is the number of times the user forwardly feeds the push message of the message type labeled n in the update period, and Neg′ n is the number of the user in the update period. n message type push message number negative feedback, Neu 'n for the user in reference to the neutral feedback message type push message n times the update period, Acc' Thresh is the The amount of update of the acceptance threshold;

The acceptance threshold update module is configured to perform an update calculation on the acceptance threshold according to the following formula:

Acc Thresh =k 1 *Acc Thresh +(1-k 1 )*Acc'Thresh;

The second update amount calculation module is configured to calculate, according to the following formula, the update amount of the user acceptance corresponding to the message type labeled n:

Where Acc' n is an update amount of user acceptance corresponding to the message type labeled n;

The user acceptance update module is configured to update the user acceptance corresponding to the message type labeled n according to the following formula:

Acc n =k 2 *Acc n +(1-k 2 )*Acc' n

Where k 1 and k 2 are preset weight coefficients.
The push message processing apparatus according to any one of claims 16 to 18, wherein the message type determining module comprises:

a current keyword selection unit, configured to select, from the keyword set, a keyword with the highest priority and not yet selected as the current keyword;

a current keyword search unit, configured to search for the current keyword in the push message;

a message type determining unit, configured to determine that the push message matches the current keyword successfully, and determine a message type corresponding to the current keyword, if the current keyword is found in the push message The type of message for which the message is pushed.
The push message processing device of claim 19, further comprising:

a history matching record obtaining module, configured to acquire a history matching record in a preset statistical time period;

a matching record statistic module, configured to count, according to the historical matching record, a number of times that each keyword in the keyword set matches successfully;

The priority determining module is configured to determine a priority of each keyword according to the number of times the respective keywords match successfully, and the priorities of the keywords are positively correlated with the number of successful matching of the keywords.