Short message interception method and device based on anti-complaint probability prediction, equipment and medium

By predicting the probability of users' counter-complaints on marketing notification text messages and intercepting corresponding text messages, the problem of inefficient SMS interception in the existing technology is solved, and effective interception of marketing notification text messages and improving the quality of SMS reach is achieved.

CN118945667AInactive Publication Date: 2024-11-12SHANGHAI CHUANGLAN CULTURE COMM CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410960623.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2024-06-20
Filing Date
2024-07-17
Publication Date
2024-11-12
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

It is difficult to effectively intercept all marketing notification text messages in the existing technology, and the interception efficiency of SMS is inefficient.

Method used

By obtaining the response data of the target device to the marketing notification text message, determining the target attribute characteristics, and entering it into the counter-complaint probability prediction model, predicting the counter-complaint probability. If the probability is greater than or equal to the preset threshold, the corresponding text message will be intercepted.

Benefits of technology

It realizes effective interception of marketing notification text messages, improving the efficiency of SMS interception and the quality of users' SMS reach.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118945667A_ABST
    Figure CN118945667A_ABST
Patent Text Reader

Abstract

The invention provides a short message interception method and device based on anti-complaint probability prediction, equipment and a medium. The method comprises the steps of obtaining target response data of a target equipment identification number to a marketing notification short message; determining a corresponding target attribute feature based on the target response data; inputting the target attribute feature into an anti-complaint probability prediction model to obtain an anti-complaint probability of the target equipment identification number to the marketing notification short message; obtaining the type of an equipment service short message to be sent to the target equipment identification number; if the type of the equipment service short message of the target equipment identification number is a non-marketing notification type, sending the equipment service short message to the target equipment identification number; and if the type of the equipment service short message of the target equipment identification number is a marketing notification type and the anti-complaint probability of the target equipment identification number to the marketing notification short message is greater than or equal to a preset probability threshold, intercepting the equipment service short message. Therefore, the sending constraint of all marketing notification short messages is effectively realized, and meanwhile, the short message reaching quality of the user is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of SMS interception, and in particular, to a method, device, equipment and medium for SMS interception based on counter-complaint probability prediction. Background Art

[0002] In today's highly competitive market environment, companies need to promptly understand and manage people at risk of SMS complaints in order to reduce complaint rates, improve service quality and protect channel resources.

[0003] In the prior art, the anti-complaint platform mainly restricts the marketing notification text messages sent to the user side through the user's complaint feedback on the marketing notification text messages. For example, after receiving the marketing notification text message, user A replies with unsubscribe or numbers / letters used to indicate the unsubscribe behavior. The anti-complaint platform restricts this marketing notification text message and will no longer send the corresponding text message to user A in the future.

[0004] However, using existing technologies, it is difficult to effectively intercept all marketing notification text messages, and the efficiency of text message interception is low. Summary of the invention

[0005] The embodiments described herein provide a method, apparatus, device and medium for intercepting short messages based on anti-complaint probability prediction, which overcome the above-mentioned problems.

[0006] In a first aspect, according to the content of the present disclosure, a method for intercepting short messages based on anti-complaint probability prediction is provided, comprising:

[0007] Obtaining target response data of the target device identification number to the marketing notification SMS, wherein the target response data is used to describe the unsubscribe instruction replied by the target device identification number based on the marketing notification SMS;

[0008] Determine corresponding target attribute characteristics based on the target response data of the target device identification number to the marketing notification SMS, wherein the target attribute characteristics include: target unsubscribe behavior characteristics, target device reach characteristics, and target field category characteristics;

[0009] The target attribute features are input into the anti-complaint probability prediction model, and the anti-complaint probability of the target device identification number for the marketing notification SMS is obtained based on the output result of the anti-complaint probability prediction model, wherein the anti-complaint probability prediction model is used to predict the anti-complaint probability through the target unsubscribe behavior features, the target device reach features, and the target domain category features;

[0010] Obtain the type of the device service SMS to be sent to the target device identification number, where the type of the device service SMS includes: marketing notification type and non-marketing notification type;

[0011] If it is detected that the type of the device service SMS to be sent to the target device identification number is the non-marketing notification type, sending the device service SMS to the target device identification number;

[0012] If it is detected that the type of the device service SMS to be sent to the target device identification number is the marketing notification type, and the counter-complaint probability of the target device identification number to the marketing notification SMS is greater than or equal to the preset probability threshold, the device service SMS is intercepted so that the target device identification number cannot receive the device service SMS.

[0013] In a second aspect, according to the content of the present disclosure, a text message interception device based on counter-complaint probability prediction is provided, comprising:

[0014] A first acquisition module is used to acquire target response data of a target device identification number to a marketing notification SMS, wherein the target response data is used to describe an unsubscribe instruction replied by the target device identification number based on the marketing notification SMS;

[0015] A first determination module is used to determine corresponding target attribute characteristics based on the target device identification number to the target response data of the marketing notification SMS, wherein the target attribute characteristics include: target unsubscribe behavior characteristics, target device reach characteristics, and target field category characteristics;

[0016] A second determination module is used to input the target attribute characteristics into an anti-complaint probability prediction model, and obtain the anti-complaint probability of the target device identification number for the marketing notification SMS based on the output result of the anti-complaint probability prediction model, wherein the anti-complaint probability prediction model is used to predict the anti-complaint probability through the target unsubscribe behavior characteristics, the target device reach characteristics and the target field category characteristics;

[0017] A second acquisition module is used to acquire the type of the device service SMS to be sent to the target device identification number, where the type of the device service SMS includes: marketing notification type and non-marketing notification type;

[0018] a sending module, configured to send the device service SMS to the target device identification number if it is detected that the type of the device service SMS to be sent to the target device identification number is the non-marketing notification type;

[0019] An interception module is used to intercept the device service SMS to be sent to the target device identification number, if it is detected that the type of the device service SMS to be sent to the target device identification number is the marketing notification type, and the counter-complaint probability of the target device identification number to the marketing notification SMS is greater than or equal to a preset probability threshold, so that the target device identification number cannot receive the device service SMS.

[0020] In a third aspect, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the SMS interception method based on counter-complaint probability prediction in any of the above embodiments are implemented.

[0021] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the SMS interception method based on counter-complaint probability prediction in any of the above embodiments are implemented.

[0022] The SMS interception method based on anti-complaint probability prediction provided in the embodiment of the present application obtains the target response data of the target device identification number to the marketing notification SMS, and the target response data is used to describe the unsubscribe instruction replied by the target device identification number based on the marketing notification SMS; based on the target response data of the target device identification number to the marketing notification SMS, the corresponding target attribute characteristics are determined, and the target attribute characteristics include: target unsubscribe behavior characteristics, target device reach characteristics and target field category characteristics; the target attribute characteristics are input into the anti-complaint probability prediction model, and the anti-complaint probability of the target device identification number to the marketing notification SMS is obtained based on the output result of the anti-complaint probability prediction model, and the anti-complaint probability prediction model is used to The target unsubscribe behavior characteristics, target device reach characteristics and target domain category characteristics are used to predict the counter-complaint probability; the type of device service SMS to be sent to the target device identification number is obtained, and the types of device service SMS include: marketing notification type and non-marketing notification type; if it is detected that the type of device service SMS to be sent to the target device identification number is non-marketing notification type, and the counter-complaint probability of the target device identification number for the marketing notification SMS is greater than or equal to the preset probability threshold, then the device service SMS is sent to the target device identification number; if it is detected that the type of device service SMS to be sent to the target device identification number is marketing notification type, then the device service SMS is intercepted so that the target device identification number cannot receive the device service SMS. In this way, by predicting the user's counter-complaint probability for marketing notification SMS, the user's reception degree of marketing notification SMS is measured. Before the sending of marketing notification SMS is detected, SMS interception is performed on users with low reception degree of marketing notification SMS, effectively implementing the sending constraints of all marketing notification SMS, and at the same time, improving the SMS reach quality of users.

[0023] The above description is only an overview of the technical solution of the embodiment of the present application. In order to more clearly understand the technical means of the embodiment of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the embodiment of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments will be briefly described below. It should be noted that the drawings described below only relate to some embodiments of the present disclosure, but are not intended to limit the present disclosure, wherein:

[0025] Figure 1 It is a flow chart of a method for intercepting short messages based on anti-complaint probability prediction provided by the present invention.

[0026] Figure 2 It is a structural schematic diagram of a text message interception device based on counter-complaint probability prediction provided by the present invention.

[0027] Figure 3 It is a structural schematic diagram of a computer device provided by the present disclosure.

[0028] It should be noted that the elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the embodiments of the present disclosure clearer, the technical solution of the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all of the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without creative work also fall within the scope of protection of the present disclosure.

[0030] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by a person skilled in the art to which the subject matter of the present disclosure belongs. It will be further understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the specification and the relevant art, and will not be interpreted in an idealized or overly formal form unless otherwise explicitly defined herein. As used herein, a statement that two or more parts are "connected" or "coupled" together shall mean that the parts are joined together directly or through one or more intermediate components.

[0031] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase "embodiments" in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists, A and B exist at the same time, and B exists. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. Terms such as "first" and "second" are only used to distinguish one component (or a part of a component) from another component (or another part of a component).

[0033] In the description of the present application, unless otherwise specified, "plurality" means more than two (including two), and similarly, "multiple groups" means more than two groups (including two).

[0034] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0035] Figure 1 is a flow chart of a method for intercepting short messages based on anti-complaint probability prediction provided by an embodiment of the present disclosure, such as Figure 1 As shown, the specific process of the SMS interception method based on anti-complaint probability prediction includes:

[0036] S110. Obtain target response data of the target device identification number to the marketing notification SMS.

[0037] The target response data is used to describe the unsubscribe instruction replied by the target device identification number based on the marketing notification SMS. The target device identification number can be the mobile phone number of the device used by the user, the device serial number, etc.

[0038] It should be noted that the unsubscribe instruction replied by the user in this embodiment may be an unsubscribe feedback within a limited time (e.g., within 2 minutes of receiving the SMS). That is, the target response data may be an unsubscribe instruction replied by the target device identification number within a limited time after receiving the marketing notification SMS. This facilitates the statistics of the user's immediate and effective unsubscribe and improves the accuracy of the prediction of the user's counter-complaint probability.

[0039] S120. Determine corresponding target attribute characteristics based on the target device identification number and the target response data to the marketing notification SMS.

[0040] Among them, the target attribute characteristics include: target unsubscribe behavior characteristics, target device reach characteristics and target field category characteristics.

[0041] The target unsubscribe behavior feature is generated based on the target response data of the target device identification number to the marketing notification SMS. The target device reach feature is determined based on the reach type of the marketing notification SMS corresponding to the target device identification number. The target domain category feature is determined based on the text description information of the marketing notification SMS.

[0042] In some embodiments, determining corresponding target attribute characteristics based on the target device identification number to the target response data of the marketing notification SMS message includes:

[0043] Based on the target response data of the target device identification number to the marketing notification SMS, the target unsubscribe behavior characteristics corresponding to the target device identification number are generated; based on the reach type of the marketing notification SMS corresponding to the target device identification number, the target device reach characteristics corresponding to the marketing notification SMS are determined; based on the text description information of the marketing notification SMS, the target domain category characteristics corresponding to the marketing notification SMS are determined; based on the target unsubscribe behavior characteristics, the target device reach characteristics and the target domain category characteristics, the target attribute characteristics are determined.

[0044] Among them, the target unsubscribe behavior features include: SMS category, SMS signature and reply text identifier. SMS category refers to the type of marketing notification SMS, i.e., marketing category or notification category. SMS signature refers to the identity information of the SMS sender. Reply text identifier can be the text, numbers, letters, or a combination of text, numbers, and letters that the user replies to indicate the unsubscribe behavior.

[0045] Based on the target response data of the target device identification number to the marketing notification SMS, a target unsubscribe behavior feature corresponding to the target device identification number is generated, which may include: determining the reply text identification based on the target response data of the target device identification number to the marketing notification SMS; detecting the category of the marketing notification SMS to obtain the SMS category; identifying the sender of the marketing notification SMS to obtain the SMS signature.

[0046] In addition, the target unsubscribe behavior characteristics may also include: time information, SMS content format. Time information includes the sending time of the marketing notification SMS, and SMS content format includes the display format of the marketing notification SMS, which may include but is not limited to: text, picture, link, etc.

[0047] The reach type of the marketing notification SMS corresponding to the target device identification number can be used to describe the sending method of the SMS sender, such as sending from a personal device (mobile phone number), sending from an official system, sending on behalf of a third party, etc.

[0048] Correspondingly, the target device reach feature may include: a first reach feature, a second reach feature, and a third reach feature. The first reach feature can be used to describe that the text message sender's sending form is sent by a personal device (mobile phone number), which can be represented by the number 1; the second reach feature can be used to describe that the text message sender's sending form is sent by an official system, which can be represented by the number 2; the third reach feature can be used to describe that the text message sender's sending form is sent by a third party, which can be represented by the number 3.

[0049] The text description information of the marketing notification SMS is the text content of the marketing notification SMS, such as product discount promotion, remaining call fee reminder, system verification code, etc. Correspondingly, the target domain category features may include: consumption features, service features, life features, etc.

[0050] Determining target attribute characteristics based on target cancellation behavior characteristics, target device reach characteristics, and target domain category characteristics may include: quantizing / normalizing the target cancellation behavior characteristics, target device reach characteristics, and target domain category characteristics to unify the data format of the target cancellation behavior characteristics, target device reach characteristics, and target domain category characteristics to obtain target attribute characteristics with unified data format.

[0051] Thus, by determining the target cancellation behavior characteristics, target device reach characteristics and target domain category characteristics, the cancellation behavior of the target device identification number is characterized, and the target attribute characteristics adapted to the cancellation behavior of the user belonging to the target device identification number are effectively obtained.

[0052] S130. Input the target attribute features into the anti-complaint probability prediction model, and obtain the anti-complaint probability of the target device identification number for the marketing notification SMS based on the output result of the anti-complaint probability prediction model.

[0053] Among them, the counter-complaint probability prediction model can be used to predict the counter-complaint probability through target cancellation behavior characteristics, target device reach characteristics and target field category characteristics.

[0054] In some embodiments, the anti-complaint probability prediction model training process includes:

[0055] Based on the historical response data of the historical device identification number to the marketing notification SMS, the corresponding historical attribute characteristics are determined, and the historical attribute characteristics include: historical unsubscribe behavior characteristics, historical device reach characteristics, and historical field category characteristics; based on the historical unsubscribe behavior characteristics, historical device reach characteristics, and historical field category characteristics, the preset network model is trained to obtain an anti-complaint probability prediction model;

[0056] Among them, the historical unsubscribe behavior feature is generated based on the historical response data of the historical device identification number to the marketing notification SMS, the historical device reach feature is determined based on the reach type of the marketing notification SMS corresponding to the historical device identification number, and the historical domain category feature is determined based on the text description information of the marketing notification SMS.

[0057] The historical unsubscribe behavior features include: SMS category, SMS signature and reply text identifier. SMS category refers to the type of historical marketing notification SMS, i.e., marketing or notification. SMS signature refers to the identity information of the SMS sender. Reply text identifier can be the text, numbers, letters, or a combination of text, numbers, and letters that the user replies to indicate the unsubscribe behavior.

[0058] In addition, historical unsubscribe behavior characteristics may also include: time information, SMS content format. Time information includes the sending time of historical marketing notification SMS, and SMS content format includes the display format of historical marketing notification SMS, which may include but is not limited to: text, picture, link, etc.

[0059] The reach type of the historical device reach feature can be used to describe the sending method of the SMS sender, such as sending from a personal device (mobile phone number), sending from an official system, or sending on behalf of a third party.

[0060] Correspondingly, the historical device contact features may include: the first contact feature, the second contact feature and the third contact feature. The first contact feature can be used to describe that the text message sender's sending form is sent by a personal device (mobile phone number), which can be represented by the number 1; the second contact feature can be used to describe that the text message sender's sending form is sent by the official system, which can be represented by the number 2; the third contact feature can be used to describe that the text message sender's sending form is sent by a third party, which can be represented by the number 3.

[0061] Category characteristics in the historical field may include: consumption characteristics, service characteristics, life characteristics, etc.

[0062] Based on the historical unsubscribe behavior characteristics, historical device reach characteristics and historical domain category characteristics, the preset network model is trained to obtain the anti-complaint probability prediction model, which may include: using the historical unsubscribe behavior characteristics, historical device reach characteristics and historical domain category characteristics to train the preset network model to obtain the model output, using the loss function to compare the model output with the expected output, if the loss value is lower than the preset loss threshold, it is determined that the preset network model training is completed and the anti-complaint probability prediction model is obtained; otherwise, continue training until the loss value is lower than the preset loss threshold. Thus, the anti-complaint probability prediction model is effectively trained.

[0063] S140: Obtain the type of the device service SMS to be sent to the target device identification number.

[0064] Among them, the types of device service SMS include: marketing notification type and non-marketing notification type.

[0065] The judgment can be made based on the SMS content of the device service SMS, such as performing keyword recognition on the SMS content of the device service SMS. If the identified content keyword matches the representation word corresponding to the marketing notification class, then the type of the device service SMS is determined to be the marketing notification class; if the identified content keyword does not match the representation word corresponding to the marketing notification class, then the type of the device service SMS is determined to be non-marketing notification class.

[0066] S150: If it is detected that the type of the device service SMS to be sent to the target device identification number is non-marketing notification type, send the device service SMS to the target device identification number.

[0067] Among them, if it is detected that the type of the device service SMS to be sent to the target device identification number is non-marketing notification, the device service SMS can be sent to the target device identification number in a timely manner, so that the corresponding user can query the SMS content in a timely manner.

[0068] S160. If it is detected that the type of the device service SMS to be sent to the target device identification number is a marketing notification type, and the counter-complaint probability of the target device identification number to the marketing notification SMS is greater than or equal to a preset probability threshold, the device service SMS is intercepted.

[0069] Among them, by determining that the type of device service SMS to be sent to the target device identification number is a marketing notification type, and the counter-complaint probability of the target device identification number to the marketing notification SMS is greater than or equal to a preset probability threshold, the device service SMS is intercepted so that the target device identification number cannot receive the device service SMS.

[0070] The preset probability threshold may be a fixed threshold set in advance, or a non-fixed threshold quantified based on the number of historical complaints of the target device identification number, or determined based on the category of the device service SMS, that is, the preset probability threshold is a counter-complaint probability threshold.

[0071] In this embodiment, the target response data of the target device identification number to the marketing notification SMS is obtained, and the target response data is used to describe the unsubscribe instruction replied by the target device identification number based on the marketing notification SMS; based on the target response data of the target device identification number to the marketing notification SMS, the corresponding target attribute characteristics are determined, and the target attribute characteristics include: target unsubscribe behavior characteristics, target device reach characteristics and target field category characteristics; the target attribute characteristics are input into the anti-complaint probability prediction model, and the anti-complaint probability of the target device identification number to the marketing notification SMS is obtained based on the output result of the anti-complaint probability prediction model. The anti-complaint probability prediction model is used to The target device reach feature and the target domain category feature are used to predict the counter-complaint probability; the type of device service SMS to be sent to the target device identification number is obtained, and the types of device service SMS include: marketing notification type and non-marketing notification type; if it is detected that the type of device service SMS to be sent to the target device identification number is non-marketing notification type, then the device service SMS is sent to the target device identification number; if it is detected that the type of device service SMS to be sent to the target device identification number is marketing notification type, and the counter-complaint probability of the target device identification number for the marketing notification SMS is greater than or equal to the preset probability threshold, then the device service SMS is intercepted so that the target device identification number cannot receive the device service SMS. In this way, by predicting the user's counter-complaint probability for the marketing notification SMS, the user's reception degree of the marketing notification SMS is measured. Before the sending of the marketing notification SMS is detected, SMS interception is performed on users with a low reception degree of the marketing notification SMS, effectively realizing the sending constraints of all marketing notification SMS, and at the same time, improving the SMS reach quality of users.

[0072] In some embodiments, after intercepting the device service SMS, the process further includes:

[0073] The target device identification number and the counter-complaint probability of the target device identification number for the marketing notification SMS are updated into the counter-complaint library; based on the counter-complaint probability corresponding to each storage device identification number in the counter-complaint library, the first device identification number for SMS interception and the second device identification number for the device service SMS to be sent are determined, and the target device identification number is not included in the first device identification number; for the first device identification number, the device service SMS is intercepted, and the device service SMS is sent to the second device identification number.

[0074] The anti-complaint database includes: multiple storage device identification numbers and the anti-complaint probability of each storage device identification number for marketing notification SMS. The storage device identification number included in the anti-complaint database can also be the mobile phone number of the current user complaint and the corresponding anti-complaint probability value (this value can be determined based on the number / frequency of user complaints).

[0075] Therefore, before the device service SMS needs to be sent, the device identification numbers that need to be intercepted and the device identification numbers that do not need to be intercepted are determined in the anti-complaint database, so as to effectively meet the reception needs of different users for marketing notification SMS and improve the quality of SMS reach.

[0076] In some embodiments, based on the counter-complaint probability corresponding to each storage device identification number in the counter-complaint library, determining the first device identification number for SMS interception and the second device identification number for the device service SMS to be sent includes:

[0077] Based on the category of the device service SMS, set the anti-complaint probability threshold corresponding to the device service SMS; determine the storage device identification number whose anti-complaint probability is greater than or equal to the anti-complaint probability threshold as the first device identification number; determine the storage device identification number whose anti-complaint probability is less than the anti-complaint probability threshold as the second device identification number.

[0078] Among them, the anti-complaint probability threshold can effectively measure the user's reception degree of marketing notification SMS. The anti-complaint probability threshold is used to divide the storage device identification numbers in the anti-complaint library into the first device identification number with a low reception degree of marketing notification SMS and the second device identification number with a high reception degree of marketing notification SMS, which is convenient for the management of marketing notification SMS recipients.

[0079] In some embodiments, the counter-complaint probability threshold corresponding to the device service text message is set based on the category to which the device service text message belongs, including:

[0080] If the SMS category of the device service SMS belongs to the preset SMS category, then obtain the historical response data of other device identification numbers to the device service SMS; based on the historical response data of other device identification numbers to the device service SMS, determine the historical unsubscribe probability corresponding to the device service SMS; based on the historical unsubscribe probability corresponding to the device service SMS, determine the counter-complaint probability threshold corresponding to the device service SMS.

[0081] The preset SMS categories may be marketing, promotional, etc. Since such SMS are prone to counter-complaints, the counter-complaint probability threshold corresponding to the device service SMS is effectively determined through the historical response data of other device identification numbers to the device service SMS.

[0082] Historical response data can be used to describe unsubscribe instructions responded to by device service SMS messages based on other device identification numbers.

[0083] When determining the historical unsubscribe probability corresponding to the device service SMS based on the historical response data of other device identification numbers to the device service SMS, it can be determined by the number / frequency of the historical response data of the device service SMS.

[0084] Exemplarily, if the number of historical response data of other device identification numbers to the device service SMS is greater than or equal to a preset number threshold, then the historical unsubscription probability corresponding to the device service SMS is determined to be a first probability value; if the number of historical response data of other device identification numbers to the device service SMS is less than the preset number threshold, then the historical unsubscription probability corresponding to the device service SMS is determined to be a second probability value; the first probability value is greater than the second probability value.

[0085] If the frequency of historical response data of other device identification numbers to device service SMS within a set time period (such as one month) is greater than or equal to the preset frequency threshold, the historical unsubscription probability corresponding to the device service SMS is determined to be a third probability value; if the frequency of historical response data of other device identification numbers to device service SMS within a set time period (such as one month) is less than the preset frequency threshold, the historical unsubscription probability corresponding to the device service SMS is determined to be a fourth probability value; the third probability value is greater than the fourth probability value.

[0086] Determining the anti-complaint probability threshold corresponding to the device service SMS based on the historical unsubscribe probability corresponding to the device service SMS may include: determining the historical unsubscribe probability corresponding to the device service SMS as the anti-complaint probability threshold corresponding to the device service SMS; or determining the anti-complaint probability threshold corresponding to the device service SMS based on the product of the historical unsubscribe probability corresponding to the device service SMS and the numerical value representing the category level corresponding to the device service SMS, so as to make the anti-complaint probability threshold corresponding to the device service SMS correspond to the category of the device service SMS, thereby improving the efficiency of SMS interception under this category.

[0087] In some embodiments, the counter-complaint probability threshold corresponding to the device service text message is set based on the category to which the device service text message belongs, including:

[0088] If the category of the device service SMS does not belong to the preset SMS category, the preset unsubscription probability is determined to be the current unsubscription probability corresponding to the device service SMS, and the current unsubscription probability corresponding to the device service SMS is less than the historical unsubscription probability corresponding to the device service SMS; based on the current unsubscription probability corresponding to the device service SMS, the anti-complaint probability threshold corresponding to the device service SMS is determined.

[0089] The category that does not belong to the preset short message category may be a service category or a notification category. The preset unsubscribe probability may be a preset fixed probability value.

[0090] Determining the anti-complaint probability threshold corresponding to the device service SMS based on the current unsubscribe probability corresponding to the device service SMS may include: determining the current unsubscribe probability corresponding to the device service SMS as the anti-complaint probability threshold corresponding to the device service SMS; or, determining the anti-complaint probability threshold corresponding to the device service SMS based on the product of the current unsubscribe probability corresponding to the device service SMS and the numerical value representing the category level corresponding to the device service SMS, so as to make the anti-complaint probability threshold corresponding to the device service SMS correspond to the category of the device service SMS, thereby further improving the efficiency of SMS interception under this category.

[0091] In summary, the method of this embodiment is simple to interact with, intelligent and flexible when used, can realize customized interception probability value and the whole process does not require additional investment cost. It more intelligently meets the message interception needs and ensures that information is conveyed more reasonably and standardizedly, thereby improving the efficiency and quality of reaching messages.

[0092] Figure 2 A structural schematic diagram of a text message interception device based on counter-complaint probability prediction is provided for this embodiment, wherein the text message interception device based on counter-complaint probability prediction may include: a first acquisition module 210, a first determination module 220, a second determination module 230, a second acquisition module 240, a sending module 250 and an interception module 260.

[0093] The first acquisition module 210 is used to acquire target response data of the target device identification number to the marketing notification SMS, where the target response data is used to describe the unsubscribe instruction replied by the target device identification number based on the marketing notification SMS.

[0094] The first determination module 220 is used to determine the corresponding target attribute characteristics based on the target response data of the marketing notification SMS message based on the target device identification number. The target attribute characteristics include: target unsubscribe behavior characteristics, target device reach characteristics and target field category characteristics.

[0095] The second determination module 230 is used to input the target attribute characteristics into the anti-complaint probability prediction model, and obtain the anti-complaint probability of the target device identification number for the marketing notification SMS based on the output result of the anti-complaint probability prediction model. The anti-complaint probability prediction model is used to predict the anti-complaint probability through the target unsubscribe behavior characteristics, the target device reach characteristics and the target field category characteristics.

[0096] The second acquisition module 240 is used to acquire the type of the device service SMS to be sent to the target device identification number, and the types of the device service SMS include: marketing notification type and non-marketing notification type.

[0097] The sending module 250 is configured to send the device service SMS to the target device identification number if it is detected that the type of the device service SMS to be sent to the target device identification number is not a marketing notification type.

[0098] The interception module 260 is used to intercept the device service SMS to be sent to the target device identification number if it is detected that the type of the device service SMS to be sent to the target device identification number is a marketing notification type, and the counter-complaint probability of the target device identification number to the marketing notification SMS is greater than or equal to a preset probability threshold, so that the target device identification number cannot receive the device service SMS.

[0099] In this embodiment, optionally, the first determining module 220 is specifically configured to:

[0100] Based on the target response data of the target device identification number to the marketing notification SMS, the target unsubscribe behavior characteristics corresponding to the target device identification number are generated, and the target unsubscribe behavior characteristics include: SMS category, SMS signature and reply text identification; based on the reach type of the marketing notification SMS corresponding to the target device identification number, the target device reach characteristics corresponding to the marketing notification SMS are determined; based on the text description information of the marketing notification SMS, the target field category characteristics corresponding to the marketing notification SMS are determined; based on the target unsubscribe behavior characteristics, the target device reach characteristics and the target field category characteristics, the target attribute characteristics are determined.

[0101] In this embodiment, optionally, it also includes: a model training module.

[0102] The model training module is used to determine the corresponding historical attribute characteristics based on the historical response data of the historical device identification number to the marketing notification SMS, and the historical attribute characteristics include: historical unsubscribe behavior characteristics, historical device reach characteristics and historical domain category characteristics; based on the historical unsubscribe behavior characteristics, historical device reach characteristics and historical domain category characteristics, the preset network model is trained to obtain an anti-complaint probability prediction model; wherein, the historical unsubscribe behavior characteristics are generated based on the historical response data of the historical device identification number to the marketing notification SMS, the historical device reach characteristics are determined based on the reach type of the marketing notification SMS corresponding to the historical device identification number, and the historical domain category characteristics are determined based on the text description information of the marketing notification SMS.

[0103] In this embodiment, optionally, it also includes: an updating module and a third determining module.

[0104] The update module is used to update the target device identification number and the counter-complaint probability of the target device identification number to the marketing notification SMS into the counter-complaint library, which includes: multiple storage device identification numbers and the counter-complaint probability of each storage device identification number to the marketing notification SMS.

[0105] The third determination module is used to determine the first device identification number for SMS interception and the second device identification number for the device service SMS to be sent based on the anti-complaint probability corresponding to each storage device identification number in the anti-complaint library, and the first device identification number does not include the target device identification number.

[0106] The interception module 260 is further configured to intercept the device service SMS message for the first device identification number.

[0107] The sending module 250 is further configured to send a device service SMS message to the second device identification number.

[0108] In this embodiment, optionally, the third determining module is specifically configured to:

[0109] Based on the category of the device service SMS, set the anti-complaint probability threshold corresponding to the device service SMS; determine the storage device identification number whose anti-complaint probability is greater than or equal to the anti-complaint probability threshold as the first device identification number; determine the storage device identification number whose anti-complaint probability is less than the anti-complaint probability threshold as the second device identification number.

[0110] In this embodiment, optionally, the third determining module is specifically configured to:

[0111] If the SMS category of the device service SMS belongs to the preset SMS category, then obtain the historical response data of other device identification numbers to the device service SMS; based on the historical response data of other device identification numbers to the device service SMS, determine the historical unsubscribe probability corresponding to the device service SMS; based on the historical unsubscribe probability corresponding to the device service SMS, determine the counter-complaint probability threshold corresponding to the device service SMS.

[0112] In this embodiment, optionally, the third determining module is specifically configured to:

[0113] If the category of the device service SMS does not belong to the preset SMS category, the preset unsubscription probability is determined to be the current unsubscription probability corresponding to the device service SMS, and the current unsubscription probability corresponding to the device service SMS is less than the historical unsubscription probability corresponding to the device service SMS; based on the current unsubscription probability corresponding to the device service SMS, the anti-complaint probability threshold corresponding to the device service SMS is determined.

[0114] The SMS interception device based on anti-complaint probability prediction provided by the present disclosure can execute the above method embodiments. Its specific implementation principles and technical effects can be found in the above method embodiments, and the present disclosure will not repeat them here.

[0115] The present application also provides a computer device. Figure 3 , Figure 3 This is a basic structural block diagram of the computer device in this embodiment.

[0116] The computer device includes a memory 310 and a processor 320 that are connected to each other through a system bus. It should be noted that the figure only shows a computer device with a memory 310 and a processor 320, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0117] Computer devices can be computing devices such as desktop computers, notebooks, PDAs, and cloud servers. Computer devices can interact with users through keyboards, mice, remote controls, touch pads, or voice control devices.

[0118] The memory 310 includes at least one type of readable storage medium, and the readable storage medium includes a non-volatile memory or a volatile memory, for example, a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc., and the RAM may include a static RAM or a dynamic RAM. In some embodiments, the memory 310 may be an internal storage unit of a computer device, for example, a hard disk or a memory of the computer device. In other embodiments, the memory 310 may also be an external storage device of the computer device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, or a flash card (FlashCard) equipped on the computer device. Of course, the memory 310 may also include both the internal storage unit of the computer device and its external storage device. In this embodiment, the memory 310 is generally used to store the operating system and various application software installed on the computer device, such as the program code of the above method. In addition, the memory 310 may also be used to temporarily store various data that have been output or are to be output.

[0119] The processor 320 is generally used to perform the overall operation of the computer device. In this embodiment, the memory 310 is used to store program codes or instructions, the program code includes computer operation instructions, and the processor 320 is used to execute the program codes or instructions stored in the memory 310 or process data, such as running the program code of the above method.

[0120] In this article, the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus system can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0121] Another embodiment of the present application also provides a computer-readable medium, which may be a computer-readable signal medium or a computer-readable medium. A processor in a computer reads a computer-readable program code stored in the computer-readable medium, so that the processor can execute the functional actions specified in each step or a combination of steps in the above method; and generate a device for implementing the functional actions specified in each block or a combination of blocks in the block diagram.

[0122] Computer-readable media include but are not limited to electronic, magnetic, optical, electromagnetic, infrared memory or semiconductor systems, devices or apparatuses, or any appropriate combination of the foregoing, the memory is used to store program codes or instructions, the program codes include computer operating instructions, and the processor is used to execute the program codes or instructions of the above methods stored in the memory.

[0123] For the definitions of memory and processor, please refer to the description of the aforementioned computer device embodiment and will not be repeated here.

[0124] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0125] Each functional unit or module in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0126] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), disk or optical disk and other media that can store program code.

[0127] In the claims, any reference symbols placed between brackets shall not be construed as limiting the claims. The word "comprising" described in the present application does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present application can be implemented with the aid of hardware comprising several different elements and with the aid of a suitably programmed computer. In a unit claim that lists a number of devices, several units of these devices may be embodied by the same hardware item. The use of first, second, and third, etc. does not indicate any order, and these words may be interpreted as names. The steps in the above embodiments, unless otherwise specified, should not be understood as limitations on the order of execution.

[0128] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A SMS interception method based on anti-complaint probability prediction, It is characterized in that include: Obtaining target response data of the target device identification number to the marketing notification SMS, wherein the target response data is used to describe the unsubscribe instruction replied by the target device identification number based on the marketing notification SMS; Determine corresponding target attribute characteristics based on the target response data of the target device identification number to the marketing notification SMS, wherein the target attribute characteristics include: target unsubscribe behavior characteristics, target device reach characteristics, and target field category characteristics; The target attribute features are input into the anti-complaint probability prediction model, and the anti-complaint probability of the target device identification number for the marketing notification SMS is obtained based on the output result of the anti-complaint probability prediction model, wherein the anti-complaint probability prediction model is used to predict the anti-complaint probability through the target unsubscribe behavior features, the target device reach features, and the target domain category features; Obtain the type of the device service SMS to be sent to the target device identification number, where the type of the device service SMS includes: marketing notification type and non-marketing notification type; If it is detected that the type of the device service SMS to be sent to the target device identification number is the non-marketing notification type, sending the device service SMS to the target device identification number; If it is detected that the type of the device service SMS to be sent to the target device identification number is the marketing notification type, and the counter-complaint probability of the target device identification number to the marketing notification SMS is greater than or equal to the preset probability threshold, the device service SMS is intercepted so that the target device identification number cannot receive the device service SMS.

2. The method according to claim 1, It is characterized in that The determining of the corresponding target attribute characteristics of the target response data of the marketing notification SMS based on the target device identification number includes: Based on the target response data of the target device identification number to the marketing notification SMS, generating the target unsubscribe behavior feature corresponding to the target device identification number, the target unsubscribe behavior feature including: SMS category, SMS signature and reply text identifier; Determining the target device contact feature corresponding to the marketing notification SMS based on the contact type of the marketing notification SMS corresponding to the target device identification number; Determine the target domain category feature corresponding to the marketing notification SMS based on the text description information of the marketing notification SMS; The target attribute characteristics are determined based on the target unsubscribe behavior characteristics, the target device reach characteristics and the target domain category characteristics.

3. The method according to claim 1, It is characterized in that The anti-complaint probability prediction model training process includes: Determine corresponding historical attribute features based on historical response data of the historical device identification number to the marketing notification SMS, wherein the historical attribute features include: historical unsubscribe behavior features, historical device reach features, and historical field category features; Based on the historical unsubscribe behavior characteristics, the historical device reach characteristics, and the historical domain category characteristics, a preset network model is trained to obtain the anti-complaint probability prediction model; Among them, the historical unsubscribe behavior feature is generated based on the historical response data of the historical device identification number to the marketing notification SMS, the historical device contact feature is determined based on the contact type of the marketing notification SMS corresponding to the historical device identification number, and the historical domain category feature is determined based on the text description information of the marketing notification SMS.

4. The method according to claim 1, It is characterized in that After intercepting the device service SMS, the method further includes: The target device identification number and the counter-complaint probability of the target device identification number to the marketing notification SMS are updated to the counter-complaint library, wherein the counter-complaint library includes: multiple storage device identification numbers and the counter-complaint probability of each storage device identification number to the marketing notification SMS; Based on the counter-complaint probability corresponding to each storage device identification number in the counter-complaint library, determine the first device identification number for SMS interception and the second device identification number to send the device service SMS, wherein the first device identification number does not include the target device identification number; For the first device identification number, the device service SMS is intercepted, and the device service SMS is sent to the second device identification number.

5. The method according to claim 4, It is characterized in that The determining, based on the counter-complaint probability corresponding to each storage device identification number in the counter-complaint library, the first device identification number for SMS interception and the second device identification number for sending the device service SMS, comprises: Based on the category of the device service text message, a counter-complaint probability threshold corresponding to the device service text message is set; Determine the storage device identification number whose counter-complaint probability is greater than or equal to the counter-complaint probability threshold as the first device identification number; Determine that the storage device identification number whose counter-complaint probability is less than the counter-complaint probability threshold is the second device identification number.

6. The method according to claim 5, It is characterized in that The step of setting a counter-complaint probability threshold corresponding to the device service text message based on the text message category to which the device service text message belongs includes: If the SMS category of the device service SMS belongs to the preset SMS category, obtaining historical response data of other device identification numbers to the device service SMS; Determine a historical unsubscribe probability corresponding to the device service SMS based on historical response data of the other device identification number to the device service SMS; Based on the historical unsubscribe probability corresponding to the device service SMS, a counter-complaint probability threshold corresponding to the device service SMS is determined.

7. The method according to claim 6, It is characterized in that The step of setting a counter-complaint probability threshold corresponding to the device service text message based on the text message category to which the device service text message belongs includes: If the category to which the device service message belongs does not belong to the preset message category, determining the preset unsubscribe probability to be the current unsubscribe probability corresponding to the device service message, and the current unsubscribe probability corresponding to the device service message is less than the historical unsubscribe probability corresponding to the device service message; Based on the current unsubscribe probability corresponding to the device service text message, a counter-complaint probability threshold corresponding to the device service text message is determined.

8. A SMS interception device based on anti-complaint probability prediction, It is characterized in that include: A first acquisition module is used to acquire target response data of a target device identification number to a marketing notification SMS, wherein the target response data is used to describe an unsubscribe instruction replied by the target device identification number based on the marketing notification SMS; A first determination module is used to determine corresponding target attribute characteristics based on the target device identification number to the target response data of the marketing notification SMS, wherein the target attribute characteristics include: target unsubscribe behavior characteristics, target device reach characteristics, and target field category characteristics; A second determination module is used to input the target attribute characteristics into an anti-complaint probability prediction model, and obtain the anti-complaint probability of the target device identification number for the marketing notification SMS based on the output result of the anti-complaint probability prediction model, wherein the anti-complaint probability prediction model is used to predict the anti-complaint probability through the target unsubscribe behavior characteristics, the target device reach characteristics and the target field category characteristics; A second acquisition module is used to acquire the type of the device service SMS to be sent to the target device identification number, where the type of the device service SMS includes: marketing notification type and non-marketing notification type; a sending module, configured to send the device service SMS to the target device identification number if it is detected that the type of the device service SMS to be sent to the target device identification number is the non-marketing notification type; An interception module is used to intercept the device service SMS to be sent to the target device identification number, if it is detected that the type of the device service SMS to be sent to the target device identification number is the marketing notification type, and the counter-complaint probability of the target device identification number to the marketing notification SMS is greater than or equal to a preset probability threshold, so that the target device identification number cannot receive the device service SMS.

9. A computer device, It is characterized in that The method comprises a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, a text message interception method based on anti-complaint probability prediction as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the text message interception method based on anti-complaint probability prediction as described in any one of claims 1 to 7 is implemented.

Citation Information

Patent Citations

  • Financial institution marketing activity reach optimization method, system and device and storage medium

    CN115689638A

  • Analysis of message service provider quality of service

    US8504083B1