WO2015196689A1

WO2015196689A1 - Short message filtering method and apparatus

Info

Publication number: WO2015196689A1
Application number: PCT/CN2014/090365
Authority: WO
Inventors: 饶正国
Original assignee: 中兴通讯股份有限公司
Priority date: 2014-06-27
Filing date: 2014-11-05
Publication date: 2015-12-30
Also published as: CN105323733A

Abstract

Disclosed is a short message filtering method. The method comprises the following steps: receiving short message information of an information center, and rating the content of short message information of a corresponding calling number according to a preset content unit rating value sample; accumulating rating values of the content of short message information of the calling number in a preset statistical time period; and when an accumulated rating value of the content of the short message information of the calling number is greater than or equal to a preset threshold value, performing a threshold operation corresponding to the preset threshold value. Also disclosed is a short message filtering apparatus.

Description

SMS filtering method and device

Technical field

The present invention relates to the field of mobile communications, and in particular, to a short message filtering method and apparatus.

Background technique

At present, most operators use a keyword-based real-time interception system. The real-time interception system sets different keyword rules and trigger thresholds according to keyword classification, and the trigger threshold is that the same terminal continuously transmits the same time within a certain period of time. The keyword is given to the monitoring processor, and the monitoring processor can intercept it. For the same terminal, different keywords are continuously sent for a period of time. Different keywords represent different spam information to the monitoring processor, and the monitoring processor cannot intercept. In response to this problem, it is urgent to seek a technical solution to solve the problem that the same terminal transmits different garbage information within a certain period of time, and the monitoring processor cannot intercept.

The above content is only used to assist in understanding the technical solutions of the present invention, and does not constitute an admission that the above is prior art.

Summary of the invention

In order to solve the problem that the same terminal sends different garbage information and the monitoring processor cannot perform the interception, the embodiment of the present invention mainly provides a short message filtering method and device.

An embodiment of the present invention provides a method for filtering a short message, and the method for filtering a short message based on a short message content score includes the following steps:

Receiving the short message information of the information center, and scoring the content of the short message information of the corresponding calling number according to the preset content unit score value sample;

Accumulating a score value of the content of the short message information of the calling number in a preset statistical time period;

When the accumulated score value of the short message content of the calling number is greater than or equal to a preset threshold, performing a threshold operation corresponding to the preset threshold.

In addition, the embodiment of the present invention further provides a short message filtering device, where the short message filtering device includes: a scoring module, an accumulating module, and a processing module;

The scoring module is configured to receive the short message information of the information center, and score the content of the short message information of the corresponding calling number according to the preset content unit score value sample;

The accumulating module is configured to accumulate a score value of the content of the short message information of the calling number within a preset statistical time period;

The processing module is configured to perform a threshold operation corresponding to the preset threshold when the cumulative score of the content of the short message information of the calling number is greater than or equal to a preset threshold.

After receiving the short message information of the information center, the short message filtering method and device of the embodiment of the present invention scores the content of the short message information of the corresponding calling number according to the preset content unit score value sample; and presets statistics During the time period, the score value of the short message content of the calling number is accumulated; when the accumulated score value of the short message content of the calling number is greater than or equal to the preset threshold, the threshold operation corresponding to the preset threshold is performed. The problem that the same terminal sends spam messages of different types of content cannot be effectively intercepted within a certain period of time.

DRAWINGS

1 is a schematic flowchart of a first embodiment of a short message filtering method according to the present invention;

2 is a schematic diagram of a refinement process for scoring short message information in FIG. 1;

FIG. 3 is a schematic diagram of functional modules of an embodiment of a short message filtering apparatus according to the present invention.

detailed description

It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

The invention provides a short message filtering method.

Referring to FIG. 1, FIG. 1 is a schematic flowchart diagram of a first embodiment of a short message filtering method according to the present invention.

In an embodiment, the short message filtering method includes:

Step S10: Receive short message information of the information center, and score the content of the short message information of the corresponding calling number according to the preset content unit score value sample;

Step S20: accumulating a score value of the content of the short message information of the calling number in the preset statistical time period;

Step S30, when the cumulative score value of the short message content of the calling number is greater than or equal to the preset threshold, performing a threshold operation corresponding to the preset threshold.

The information center receives the short message information of the user terminal, and the user terminal includes a mobile phone, a tablet computer, and the like, and sends the information to the monitoring system for real-time monitoring of the short message information. After receiving the short message information, the monitoring system according to the preset The content unit score value sample scoring the received short message information, and accumulating the score value of the short message information content of the same calling number within a preset statistical time period. The content unit score value sample is generated by the offline content analysis device using sufficiently known spam message content and ordinary short message content, specifically using a Bayesian probability statistical method to extract the ordinary short message of the content unit and the spam text bias. A content unit score value sample is formed, and the content unit score value sample is used to initialize a content scoring module that the user in the monitoring system scores the short message information content. The offline content analysis device may also update the ordinary short message information and the spam short message information according to actual needs, and use the updated ordinary short message information and the spam short message information to refine the ordinary short message bias and the spam short message to form a new content unit score value sample. Then, the content scoring module in the monitoring system is re-initialized with the new content unit scoring value sample, so that the monitoring system can be expanded, and dynamic adjustment can be made according to actual needs.

In this embodiment, the preset time period is set in various manners, for example, 1. The time when the current short message information is received is used as a starting point, and the subsequent time period is the foregoing preset time period; Divide an hour into 6 time segments, each of which is 10 minutes, and each time period For the above preset time period; adding the score of the other short message information to the current short message information score value to obtain an updated score cumulative value. When the cumulative score of the content of the short message of the calling number is greater than or equal to the preset threshold, the threshold information corresponding to the preset threshold is performed on the received short message, and the preset threshold is the intercept threshold. , the interception operation is performed, and the short message information is refused to be sent to the destination user. The threshold value includes the threshold value, the black threshold value, and the suspicious threshold value, and the threshold value for determining the operation of the short message information. In this embodiment, the preset threshold value may be set to the foregoing interception. A combination of one or more of a threshold, a black threshold, and a suspect threshold.

When the accumulated score value of the short message content of the calling number is greater than or equal to the preset threshold, the corresponding operation may be performed on the short message information according to the following manner: when the cumulative value of the calling number score is greater than or equal to the preset suspicious short message threshold Value, the user of the calling number is set as a suspicious user; when the accumulated value of the calling number score is greater than or equal to the preset intercepting threshold, the current short message information is intercepted, and the short message is rejected and sent to the destination user; when the calling number is scored The accumulated value is greater than or equal to the preset black limit value. The user of the calling number is added to the blacklist and the validity period is set.

After receiving the short message information of the information center, the embodiment classifies the content of the short message information of the corresponding calling number according to the preset content unit score value sample; and accumulates the calling party within a preset statistical time period. The score value of the content of the short message information of the number; when the cumulative score value of the content of the short message information of the calling number is greater than or equal to the preset threshold, the threshold operation corresponding to the preset threshold is performed. The problem that the same terminal sends spam messages of different types of content cannot be effectively intercepted within a certain period of time.

Referring to FIG. 2, FIG. 2 is a schematic diagram of a refinement process for scoring short message information in FIG.

Preferably, step S20 includes:

Step S201: Receive short message information sent by the information center through the access gateway, and perform word segmentation processing on the received short message information;

Step S202, performing scoring processing on each participle after the word segmentation process, and accumulating the word segmentation The score of the short message information is obtained.

After receiving the short message information transmitted by the information center through the access gateway, the first message processing is performed on the received short message information, and then each word segmentation processed by the word segmentation is scored, and the scores of the respective word segments are accumulated to obtain the short message information. The score value, and further preferably, according to the set basic score threshold value, determining whether the content of the current short message information is valuable according to the current score value, if the value is continued, otherwise setting the current short message record status to release, and finally executing The result is release; the basic score threshold set in it is mainly used to filter out some small value-free SMS content records, and avoid excessive accumulation leading to false monitoring. Further, if the content score of the current short message information is valuable, the cumulative score value of the short message information content of the calling number is obtained. At this time, if it is a new user, the accumulated score value of the recorded short message information content is 0; and the accumulated score value is obtained. It needs to be determined according to the preset time period. If the preset time period is exceeded, the accumulated score value of the current user's short message information content is 0. Update the SMS record to record the cumulative score of the calling user, save it, and use the current new score cumulative value to compare with the preset threshold; if it is less than the preset threshold, set the SMS record status to Release, the final execution result is release; if it is greater than or equal to the preset threshold, it will be intercepted according to the set action, set the state, and the final execution result is interception; the preset threshold comparison process can set various thresholds. And set the SMS record status according to the action corresponding to the threshold value, such as adding a black threshold and action.

In this embodiment, by setting a preset basic score value, the false monitoring caused by the possible worthless short message information is filtered, and on the one hand, the cumulative score of the present invention is more scientific and reasonable, and on the other hand, the processing speed is also accelerated. The monitoring system has higher processing efficiency.

The invention also provides a short message filtering device.

Referring to FIG. 3, FIG. 3 is a schematic diagram of functional modules of an SMS filtering device according to an embodiment of the present invention.

In an embodiment, the short message filtering device includes:

The scoring module 10 can be implemented by the receiver, configured to receive the short message information of the information center, and perform the content of the short message information of the corresponding calling number according to the preset content unit score value sample. score;

The accumulating module 20 may be implemented by a memory, and configured to accumulate a score value of the short message information content of the calling number within a preset statistical time period;

The processing module 30 may be implemented by the processor, and configured to perform a threshold operation corresponding to the preset threshold when the cumulative score value of the short message content of the calling number is greater than or equal to a preset threshold.

The information center receives the short message information of the user terminal, and the user terminal includes a mobile phone, a tablet computer, and the like, and sends the information to the monitoring system for real-time monitoring of the short message information. After the monitoring system receives the short message information, the scoring module 10 The scoring operation is performed on the received short message information according to the preset content unit score value sample, and the accumulating module 20 accumulates the score value of the short message information content of the same calling number within the preset statistical time period. The content unit score value sample is generated by the offline content analysis device using sufficiently known spam message content and ordinary short message content, specifically using a Bayesian probability statistical method to extract the ordinary short message of the content unit and the spam text bias. A content unit score value sample is formed, and the content unit score value sample is used to initialize a content scoring module that the user in the monitoring system scores the short message information content. The offline content analysis device may also update the ordinary short message information and the spam short message information according to actual needs, and use the updated ordinary short message information and the spam short message information to refine the ordinary short message bias and the spam short message to form a new content unit score value sample. Then, the content scoring module in the monitoring system is re-initialized with the new content unit scoring value sample, so that the monitoring system can be expanded, and dynamic adjustment can be made according to actual needs.

In this embodiment, the preset time period is set in various manners, for example, 1. The time when the current short message information is received is used as a starting point, and the subsequent time period is the foregoing preset time period; Divide an hour into 6 time segments, each of which is 10 minutes, and each time period is the above-mentioned preset time period; add the score of the other short message information to the current short message information score value to obtain an update. The cumulative value of the score. When the accumulated score value of the content of the short message information of the calling number is greater than or equal to the preset threshold, the processing module 30 performs the received short message information. Threshold operation corresponding to the preset threshold. If the preset threshold is the intercept threshold, the interception operation is performed, and the short message is rejected from being sent to the destination user. The threshold value includes the threshold value, the black threshold value, and the suspicious threshold value, and the threshold value for determining the operation of the short message information. In this embodiment, the preset threshold value may be set to the foregoing interception. A combination of one or more of a threshold, a black threshold, and a suspect threshold.

Preferably, the scoring module 10 is specifically configured to:

The receiving information center performs the word segmentation processing on the received short message information by using the short message information transmitted by the access gateway;

Each participle after the word segmentation is scored, and the score of the accumulated participle is scored by the short message information.

After receiving the short message information transmitted by the information center through the access gateway, the scoring module 10 first performs segmentation processing on the received short message information, and then scores each word segmentation processed by the word segmentation, and accumulates the scores of the respective word segments to obtain the scores of the respective word segments. The rating value of the short message information, and then preferred, According to the set basic score threshold value, according to the current score value, it is determined whether the content of the current short message information has value, if it has value, then continue, otherwise the current short message record status is set to release, and the final execution result is release; The basic scoring threshold is set to filter out some of the valuable non-valued SMS content records, and avoid excessive accumulation leading to false monitoring. Further, if the content score of the current short message information is valuable, the cumulative score value of the short message information content of the calling number is obtained. At this time, if it is a new user, the accumulated score value of the recorded short message information content is 0; and the accumulated score value is obtained. It needs to be determined according to the preset time period. If the preset time period is exceeded, the accumulated score value of the current user's short message information content is 0. Update the SMS record to record the cumulative score of the calling user, save it, and use the current new score cumulative value to compare with the preset threshold; if it is less than the preset threshold, set the SMS record status to Release, the final execution result is release; if it is greater than or equal to the preset threshold, it will be intercepted according to the set action, set the state, and the final execution result is interception; the preset threshold comparison process can set various thresholds. And set the SMS record status according to the action corresponding to the threshold value, such as adding a black threshold and action.

The above are only the preferred embodiments of the present invention, and are not intended to limit the scope of the invention, and the equivalent structure or equivalent process transformations made by the description of the present invention and the drawings are directly or indirectly applied to other related technical fields. The same is included in the scope of patent protection of the present invention.

Industrial applicability

In the embodiment of the present invention, by setting a preset basic score value, the false monitoring caused by the possible valueless short message information is filtered, and on the one hand, the cumulative score of the present invention is more scientific and reasonable, and on the other hand, the processing speed is also accelerated. This makes the monitoring system more efficient.

Claims

A short message filtering method, where the method performs short message filtering based on a short message content rating, including the following steps:

Receiving the short message information of the information center, and scoring the content of the short message information of the corresponding calling number according to the preset content unit score value sample;

Accumulating a score value of the content of the short message information of the calling number in a preset statistical time period;

When the accumulated score value of the short message content of the calling number is greater than or equal to a preset threshold, performing a threshold operation corresponding to the preset threshold.
The short message filtering method according to claim 1, wherein the content unit score value sample is generated based on known spam message content and normal short message content.
The short message filtering method according to claim 1, wherein the step of receiving the short message information of the information center and scoring the content of the short message information of the corresponding calling number according to the preset content unit score value sample comprises:

The receiving information center performs the word segmentation processing on the received short message information by using the short message information transmitted by the access gateway;

Each participle after the word segmentation is scored, and the score of the accumulated participle obtains the score value of the short message information.
The short message filtering method according to claim 1, wherein the preset threshold value comprises at least one of the following: a preset intercept threshold, a preset black threshold, and a preset suspicious short message threshold.
The short message filtering method according to claim 4, wherein when the cumulative value of the score of the sender is greater than or equal to a preset threshold, the monitoring processor performs a threshold operation corresponding to the preset threshold, and sends the threshold The steps of the party behavior to be disposed of include:

When the accumulated value of the calling number score is greater than or equal to the preset suspicious short message threshold, the user of the calling number is set as a suspicious user;

When the accumulated value of the calling number score is greater than or equal to a preset intercept threshold, intercepting the current short message information, and refusing to send the short message information to the destination user;

When the accumulated value of the calling number score is greater than or equal to the preset blackening threshold, the user of the calling number is added to the blacklist, and the validity period is set.
A short message filtering device, the short message filtering device includes: a scoring module, an accumulating module, and a processing module; wherein

The scoring module is configured to receive the short message information of the information center, and score the content of the short message information of the corresponding calling number according to the preset content unit score value sample;

The accumulating module is configured to accumulate a score value of the content of the short message information of the calling number within a preset statistical time period;

The processing module is configured to perform a threshold operation corresponding to the preset threshold when the cumulative score of the content of the short message information of the calling number is greater than or equal to a preset threshold.
The short message filtering device according to claim 6, wherein said content unit score value sample is generated based on known spam message content and normal message content.
The short message filtering device of claim 6, wherein the scoring module is further configured to:

The receiving information center performs the word segmentation processing on the received short message information by using the short message information transmitted by the access gateway;

Each participle after the word segmentation is scored, and the score of the accumulated participle obtains the score value of the short message information.
The short message filtering device of claim 6, wherein the preset threshold value comprises at least one of the following: a preset intercept threshold, a preset black threshold, and a preset suspicious short message threshold.
The short message filtering device of claim 9, wherein the processing module is further configured to:

When the accumulated value of the calling number score is greater than or equal to the preset suspicious short message threshold, the user of the calling number is set as a suspicious user;

When the accumulated value of the calling number score is greater than or equal to a preset intercept threshold, intercepting the current short message information, and refusing to send the short message information to the destination user;

When the accumulated value of the calling number score is greater than or equal to the preset blackening threshold, the user of the calling number is added to the blacklist, and the validity period is set.