CN115580841B - Method for reducing short message sending delay - Google Patents

Method for reducing short message sending delay Download PDF

Info

Publication number
CN115580841B
CN115580841B CN202211545490.4A CN202211545490A CN115580841B CN 115580841 B CN115580841 B CN 115580841B CN 202211545490 A CN202211545490 A CN 202211545490A CN 115580841 B CN115580841 B CN 115580841B
Authority
CN
China
Prior art keywords
short message
reference element
attribute
elements
similarity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202211545490.4A
Other languages
Chinese (zh)
Other versions
CN115580841A (en
Inventor
吴锋
吴宪
余超
朱庆红
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Chonry Information Technology Co ltd
Original Assignee
Anhui Chonry Information Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anhui Chonry Information Technology Co ltd filed Critical Anhui Chonry Information Technology Co ltd
Priority to CN202211545490.4A priority Critical patent/CN115580841B/en
Publication of CN115580841A publication Critical patent/CN115580841A/en
Application granted granted Critical
Publication of CN115580841B publication Critical patent/CN115580841B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/12—Messaging; Mailboxes; Announcements
    • H04W4/14—Short messaging services, e.g. short message services [SMS] or unstructured supplementary service data [USSD]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)

Abstract

The invention relates to the technical field of short message service, and discloses a method for reducing short message sending delay, which comprises the following steps: extracting short message data from a historical short message database to generate a historical short message set; extracting three reference elements from the historical short message set; respectively bringing short message elements in the historical short message sets into the three sets; updating the three reference elements and the three sets; extracting short message elements from a short message database to be sent and respectively incorporating the short message elements into a fourth set, a fifth set and a sixth set; respectively assigning the short message elements in the fourth set, the fifth set and the sixth set to the same category labels as the first reference element, the second reference element and the third reference element; judging the order of sending the short messages based on the category labels of the short message elements; the invention is based on the mining of historical short message data, and quickly classifies the short messages to be sent by a small number of iterations, thus having little influence on the average sending time of the short messages.

Description

Method for reducing short message sending delay
Technical Field
The present invention relates to the technical field of short message service, and more particularly, to a method for reducing short message transmission delay.
Background
In the process of sending the short message by the client, the short message is sent to a short message service platform of a third-party agent, the short message service platform is also called as a short message platform, the short message service platform forwards the short message submitted by the user to an operator for processing, the operator receives the short message and then returns response information to the short message service platform, and the response information is a short message submitting state returned to the short message service platform by the operator. For some short message platforms with large access quantity, the short message sending quantity is very large, although the sending delay of a single short message is short, the delay of a part of short messages can still be caused after accumulation, and for some short messages requiring low delay, the existing queuing mechanism according to the access time cannot distinguish the short messages, and the actual delay time of the short messages can be caused to be long.
Disclosure of Invention
The invention provides a method for reducing short message sending delay, which solves the technical problem that the existing queuing mechanism according to access time can not distinguish short messages requiring low delay in the related technology.
According to an aspect of the present invention, a method for reducing short message transmission delay is provided, which includes the following steps:
step 110, extracting short message data from a historical short message database to generate a historical short message set, wherein the historical short message set comprises a plurality of short message elements, and the short message elements comprise a first attribute, a second attribute and a third attribute;
step 120, extracting three short message elements from the historical short message set as a first reference element, a second reference element and a third reference element respectively;
step 130, respectively bringing the short message elements in the historical short message set into a first set, a second set and a third set;
step 140, updating the attributes of the first reference element, the second reference element and the third reference element, and updating the first set, the second set and the third set;
step 150, repeating the step 140 until the total entropy of the first set, the second set and the third set is less than the set entropy threshold;
the categories of the short message elements are respectively A, B and C, the categories of the short message elements with the largest quantity proportion are respectively used as category labels by the first set, the second set and the third set, and the category labels of the first reference element, the second reference element and the third reference element are respectively the same as those of the first set, the second set and the third set;
step 160, extracting short message data from a short message database to be sent to generate a short message set to be sent, and bringing short message elements of the short message set to be sent into a fourth set, a fifth set and a sixth set respectively;
step 170, updating the attributes of the first reference element, the second reference element and the third reference element, and updating the fourth set, the fifth set and the sixth set;
step 180, repeating the iteration of step 170 three to five times;
step 190, assigning the short message elements in the fourth set, the fifth set and the sixth set to the same category labels as the first reference element, the second reference element and the third reference element respectively; respectively incorporating short messages corresponding to the short message elements of the type A, the type B and the type C into a first echelon, a second echelon and a third echelon of a short message sending queuing sequence; the short messages of the first echelon are sent in preference to the short messages of the second echelon, and the short messages of the second echelon are sent in preference to the short messages of the third echelon.
Further, the value of the first attribute includes trade, verify, and edit;
if the content of the short message element contains any transaction keyword, taking trade from the value of the first attribute of the short message element;
if the content of the short message element contains any verification keyword, the value of the first attribute of the short message element is changed;
if the content of the short message element does not contain the transaction key word and the verification key word, the value of the first attribute of the short message element is selected as the edit;
the priority of the first attribute with the value of trade of the short message element is greater than the priority with the value of verify, and the priority with the value of verify is greater than the priority with the value of edit.
Further, the value of the second attribute is the short message sending state receipt time of the previous short message received by the sending target of the short message element, and the short message sending state receipt time is the time from the short message sending to the operator to the short message sending state receipt returned by the operator.
Further, the value of the third attribute is the number of characters contained in the short message content of the short message element.
Further, the short message elements in the first set need to satisfy the following conditions:
Figure DEST_PATH_IMAGE001
wherein
Figure 457637DEST_PATH_IMAGE002
Represents->
Figure 170771DEST_PATH_IMAGE003
And &>
Figure 630703DEST_PATH_IMAGE004
Is based on the similarity of (4)>
Figure 142587DEST_PATH_IMAGE005
Represents->
Figure 528306DEST_PATH_IMAGE003
And &>
Figure 492851DEST_PATH_IMAGE006
The degree of similarity of (a) to (b),
Figure 22053DEST_PATH_IMAGE007
represents->
Figure 612610DEST_PATH_IMAGE003
And &>
Figure 936275DEST_PATH_IMAGE008
Is based on the similarity of (4)>
Figure 653695DEST_PATH_IMAGE003
Represents SMS elements in the first set, and>
Figure 219544DEST_PATH_IMAGE004
represents a first reference element, is selected>
Figure 174861DEST_PATH_IMAGE006
Represents a second reference element, <' > is combined with>
Figure 669428DEST_PATH_IMAGE008
Represents a third reference element;
the conditions that the short message elements in the second set need to satisfy are as follows:
Figure 844451DEST_PATH_IMAGE009
wherein
Figure 981034DEST_PATH_IMAGE010
Represents->
Figure 790858DEST_PATH_IMAGE011
And &>
Figure 486019DEST_PATH_IMAGE006
Is based on the similarity of (4)>
Figure 381294DEST_PATH_IMAGE012
Represents->
Figure 524831DEST_PATH_IMAGE011
And &>
Figure 956205DEST_PATH_IMAGE004
The degree of similarity of (a) to (b),
Figure 58154DEST_PATH_IMAGE013
represents->
Figure 440724DEST_PATH_IMAGE011
And &>
Figure 417645DEST_PATH_IMAGE008
In a degree of similarity of (c), in a manner of (d)>
Figure 733220DEST_PATH_IMAGE011
Represents the SMS element in the second set, and/or>
Figure 6070DEST_PATH_IMAGE004
Represents a first reference element, is present>
Figure 642981DEST_PATH_IMAGE006
Represents a second reference element, is selected>
Figure 128320DEST_PATH_IMAGE008
Represents a third reference element;
the conditions that the short message elements in the third set need to satisfy are as follows:
Figure 298401DEST_PATH_IMAGE014
wherein
Figure 709529DEST_PATH_IMAGE015
Represents->
Figure 332271DEST_PATH_IMAGE016
And &>
Figure 886880DEST_PATH_IMAGE008
Is based on the similarity of (4)>
Figure 424652DEST_PATH_IMAGE017
Represents->
Figure 976987DEST_PATH_IMAGE016
And &>
Figure 54402DEST_PATH_IMAGE004
The degree of similarity of (a) to (b),
Figure 147123DEST_PATH_IMAGE018
represents->
Figure 557376DEST_PATH_IMAGE016
And &>
Figure 47656DEST_PATH_IMAGE006
Is based on the similarity of (4)>
Figure 644991DEST_PATH_IMAGE016
Represents the SMS element in the third set, and/or>
Figure 541403DEST_PATH_IMAGE004
Represents a first reference element, is selected>
Figure 304697DEST_PATH_IMAGE006
Represents a second reference element, is selected>
Figure 729993DEST_PATH_IMAGE008
A third reference element is indicated.
Further, the similarity between the short message element and the reference element is calculated as follows:
Figure 549045DEST_PATH_IMAGE019
wherein
Figure 750612DEST_PATH_IMAGE020
，
Figure 338720DEST_PATH_IMAGE021
，
Figure 466076DEST_PATH_IMAGE022
In which>
Figure 536538DEST_PATH_IMAGE023
，
Figure 40331DEST_PATH_IMAGE024
，
Figure 748524DEST_PATH_IMAGE025
Respectively represent the values of the first attribute, the second attribute and the third attribute of the short message element, wherein ^ is greater than or equal to ^>
Figure 282667DEST_PATH_IMAGE026
，
Figure 279573DEST_PATH_IMAGE027
，
Figure 55899DEST_PATH_IMAGE028
Respectively representing the values of the first attribute, the second attribute and the third attribute of the reference element.
Further, the method of updating the attributes of the first reference element, the second reference element and the third reference element is:
taking the value of the first attribute of the short message element with the largest number and the same value of the first attribute of the short message elements in the first set as the value of the first attribute of the first reference element;
taking the average value of the second attributes of the short message elements in the first set as the value of the first attribute of the first reference element;
taking the average value of the third attribute of the short message elements in the first set as the value of the first attribute of the third reference element;
the method for updating the first set, the second set and the third set comprises the steps of clearing the first set, the second set and the third set, calculating the similarity between the short message elements in the historical short message set and three reference elements, and then bringing the short message elements in the historical short message set into the first set, the second set and the third set according to the conditions which need to be met by the short message elements in the first set, the second set and the third set.
Further, the calculation formula of the total entropy value s is as follows:
Figure 382713DEST_PATH_IMAGE029
wherein
Figure 320713DEST_PATH_IMAGE030
Represents the number of the short message elements in the jth category in the ith set, and/or the number of the short message elements in the jth category in the ith set>
Figure 825820DEST_PATH_IMAGE031
Indicating the number of short message elements in the ith set.
Further, the conditions that the short message elements in the fourth set need to satisfy are:
Figure 671416DEST_PATH_IMAGE032
wherein
Figure 823043DEST_PATH_IMAGE033
Represents->
Figure 696059DEST_PATH_IMAGE034
And &>
Figure 464295DEST_PATH_IMAGE004
Is based on the similarity of (4)>
Figure 848003DEST_PATH_IMAGE035
Represents->
Figure 886759DEST_PATH_IMAGE034
And &>
Figure 697720DEST_PATH_IMAGE006
The degree of similarity of (a) to (b),
Figure 422094DEST_PATH_IMAGE036
represents->
Figure 842449DEST_PATH_IMAGE034
And &>
Figure 499826DEST_PATH_IMAGE008
Is based on the similarity of (4)>
Figure 216109DEST_PATH_IMAGE034
Represents the SMS element in the fourth set, and/or>
Figure 725982DEST_PATH_IMAGE004
Represents a first reference element, is selected>
Figure 185913DEST_PATH_IMAGE006
Represents a second reference element, is selected>
Figure 166638DEST_PATH_IMAGE008
Represents a third reference element;
the conditions that the short message elements in the fifth set need to satisfy are as follows:
Figure 83516DEST_PATH_IMAGE037
wherein
Figure 782482DEST_PATH_IMAGE038
Represents->
Figure 311684DEST_PATH_IMAGE039
And &>
Figure 179539DEST_PATH_IMAGE004
Degree of similarity,. Or>
Figure 972046DEST_PATH_IMAGE040
Represents->
Figure 689466DEST_PATH_IMAGE039
And &>
Figure 989735DEST_PATH_IMAGE006
Degree of similarity,. Or>
Figure 945053DEST_PATH_IMAGE041
Represents->
Figure 705198DEST_PATH_IMAGE039
And &>
Figure 157519DEST_PATH_IMAGE008
Degree of similarity,. Or>
Figure 497365DEST_PATH_IMAGE039
Represents SMS elements in the fifth set, and>
Figure 103926DEST_PATH_IMAGE004
represents a first reference element, is selected>
Figure 2350DEST_PATH_IMAGE006
Represents a second reference element, is selected>
Figure 897625DEST_PATH_IMAGE008
Represents a third reference element;
the conditions that the short message elements in the sixth set need to satisfy are as follows:
Figure 73785DEST_PATH_IMAGE042
wherein
Figure 269274DEST_PATH_IMAGE043
Represents->
Figure 840063DEST_PATH_IMAGE044
And &>
Figure 252328DEST_PATH_IMAGE004
Is based on the similarity of (4)>
Figure 465135DEST_PATH_IMAGE045
Represents->
Figure 249551DEST_PATH_IMAGE044
And &>
Figure 23865DEST_PATH_IMAGE006
The degree of similarity of (a) to (b),
Figure 893732DEST_PATH_IMAGE046
represents->
Figure 910230DEST_PATH_IMAGE044
And &>
Figure 578846DEST_PATH_IMAGE008
Is based on the similarity of (4)>
Figure 757018DEST_PATH_IMAGE044
Represents the SMS element in the sixth set, and/or>
Figure 645340DEST_PATH_IMAGE004
Represents a first reference element, is present>
Figure 435834DEST_PATH_IMAGE006
Denotes a second reference element，
Figure 194843DEST_PATH_IMAGE008
A third reference element is indicated.
Further, the method of updating the attributes of the first reference element, the second reference element and the third reference element is:
taking the value of the first attribute of the short message element with the largest number and the same value of the first attribute of the short message elements in the fourth set as the value of the first attribute of the first reference element;
taking the average value of the second attribute of the short message elements in the fourth set as the value of the first attribute of the first reference element;
taking the average value of the third attribute of the short message elements in the fourth set as the value of the first attribute of the third reference element;
the method for updating the fourth set, the fifth set and the sixth set is to clear the fourth set, the fifth set and the sixth set, calculate the similarity between the short message elements in the short message set to be sent and the three reference elements, and then bring the short message elements in the short message set to be sent into the fourth set, the fifth set and the sixth set according to the conditions which need to be met by the short message elements in the fourth set, the fifth set and the sixth set.
The invention has the beneficial effects that:
the invention is based on the mining of historical short message data, and quickly classifies the short messages to be sent by a small number of iterations, thereby having little influence on the average sending time of the short messages, but greatly shortening the sending time of the short messages needing to be sent preferentially, and improving the quality of short message service of a short message platform.
Drawings
FIG. 1 is a first flowchart of a method for reducing SMS transmission delay according to the present invention;
fig. 2 is a flowchart of a method for reducing the short message transmission delay according to the present invention.
Detailed Description
The subject matter described herein will now be discussed with reference to example embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and thereby implement the subject matter described herein, and are not intended to limit the scope, applicability, or examples set forth in the claims. Changes may be made in the function and arrangement of elements discussed without departing from the scope of the disclosure. Various examples may omit, substitute, or add various procedures or components as needed. In addition, features described with respect to some examples may also be combined in other examples.
Example one
As shown in fig. 1 and fig. 2, a method for reducing short message transmission delay includes the following steps:
step 110, extracting short message data from a historical short message database to generate a historical short message set, wherein the historical short message set comprises a plurality of short message elements, and the short message elements comprise a first attribute, a second attribute and a third attribute;
the value of the first attribute comprises trade, verify and edit;
if the content of the short message element contains any transaction keyword, taking trade from the value of the first attribute of the short message element;
if the content of the short message element contains any verification keyword, the value of the first attribute of the short message element is changed;
in one embodiment of the invention, the transaction keywords include "money", "wallet", "transaction", "renewal", and "open".
The verification keywords include "code", "verification".
If the content of the short message element does not contain the transaction key word and the verification key word, the value of the first attribute of the short message element is selected as the edit;
the priority of the first attribute with the value of trade of the short message element is greater than the priority with the value of verify, and the priority with the value of verify is greater than the priority with the value of edit;
if the content of the short message element comprises keywords 'money' and 'verification', the first attribute of the short message element meets the conditions of taking the value as trade and verify, and the value of the first attribute is taken as trade according to the priority.
The value of the second attribute is the short message sending state receipt time of the previous short message received by the sending target of the short message element, and the short message sending state receipt time is the time for returning the short message sending state receipt from the short message to the operator.
For example, if the message transmission status receipt time of the previous message received by the transmission target of one message element is 26ms, the value of the second attribute is 26.
The value of the third attribute is the number of characters contained in the short message content of the short message element;
for example, if the short message content of one short message element includes 16 characters, the value of the third attribute is 16;
step 120, extracting three short message elements from the historical short message set as a first reference element, a second reference element and a third reference element respectively;
step 130, respectively including the short message elements in the historical short message set into the first set, the second set and the third set, wherein the short message elements in the first set need to meet the following conditions:
Figure 543916DEST_PATH_IMAGE001
wherein
Figure 152489DEST_PATH_IMAGE002
Represents->
Figure 510790DEST_PATH_IMAGE003
And &>
Figure 389884DEST_PATH_IMAGE004
Is based on the similarity of (4)>
Figure 175437DEST_PATH_IMAGE005
Represents->
Figure 996939DEST_PATH_IMAGE003
And &>
Figure 893351DEST_PATH_IMAGE006
The degree of similarity of (a) to (b),
Figure 859907DEST_PATH_IMAGE007
represents->
Figure 816362DEST_PATH_IMAGE003
And &>
Figure 369834DEST_PATH_IMAGE008
Is based on the similarity of (4)>
Figure 571402DEST_PATH_IMAGE003
Represents the SMS element in the first set, and/or>
Figure 425088DEST_PATH_IMAGE004
Represents a first reference element, is selected>
Figure 286865DEST_PATH_IMAGE006
Represents a second reference element, <' > is combined with>
Figure 357327DEST_PATH_IMAGE008
Represents a third reference element;
the conditions that the short message elements in the second set need to satisfy are as follows:
Figure 595541DEST_PATH_IMAGE047
wherein
Figure 38155DEST_PATH_IMAGE010
Represents->
Figure 837877DEST_PATH_IMAGE011
And &>
Figure 631521DEST_PATH_IMAGE006
Is based on the similarity of (4)>
Figure 407847DEST_PATH_IMAGE012
Represents->
Figure 469082DEST_PATH_IMAGE011
And &>
Figure 672661DEST_PATH_IMAGE004
The degree of similarity of (a) to (b),
Figure 422442DEST_PATH_IMAGE013
represents->
Figure 238345DEST_PATH_IMAGE011
And &>
Figure 921130DEST_PATH_IMAGE008
Is based on the similarity of (4)>
Figure 528567DEST_PATH_IMAGE011
Represents the SMS element in the second set, and/or>
Figure 296803DEST_PATH_IMAGE004
Represents a first reference element, is selected>
Figure 414932DEST_PATH_IMAGE006
Represents a second reference element, is selected>
Figure 199828DEST_PATH_IMAGE008
Represents a third reference element;
the conditions that the short message elements in the third set need to satisfy are as follows:
Figure 745210DEST_PATH_IMAGE048
wherein
Figure 469583DEST_PATH_IMAGE015
Represents->
Figure 889938DEST_PATH_IMAGE016
And &>
Figure 281736DEST_PATH_IMAGE008
Is based on the similarity of (4)>
Figure 529178DEST_PATH_IMAGE017
Represents->
Figure 242312DEST_PATH_IMAGE016
And &>
Figure 967823DEST_PATH_IMAGE004
The degree of similarity of (a) to (b),
Figure 479707DEST_PATH_IMAGE018
represents->
Figure 131006DEST_PATH_IMAGE016
And &>
Figure 95551DEST_PATH_IMAGE006
Is based on the similarity of (4)>
Figure 595058DEST_PATH_IMAGE016
Represents the SMS element in the third set, and/or>
Figure 961449DEST_PATH_IMAGE004
Represents a first reference element, is present>
Figure 285114DEST_PATH_IMAGE006
Represents a second reference element, is selected>
Figure 969911DEST_PATH_IMAGE008
Represents a third reference element;
in one embodiment of the present invention, the similarity between the short message element and the reference element is calculated as follows:
Figure 771645DEST_PATH_IMAGE049
wherein
Figure 258121DEST_PATH_IMAGE020
，
Figure 254152DEST_PATH_IMAGE021
，
Figure 662131DEST_PATH_IMAGE022
Wherein->
Figure 798714DEST_PATH_IMAGE023
，
Figure 372653DEST_PATH_IMAGE024
，
Figure 38120DEST_PATH_IMAGE025
Respectively represent the values of the first attribute, the second attribute and the third attribute of the short message element, wherein ^ is greater than or equal to ^>
Figure 464554DEST_PATH_IMAGE026
，
Figure 363415DEST_PATH_IMAGE027
，
Figure 558905DEST_PATH_IMAGE028
Respectively representing the values of the first attribute, the second attribute and the third attribute of the reference element.
Step 140, updating the attributes of the first reference element, the second reference element and the third reference element, and updating the first set, the second set and the third set;
the method for updating the attributes of the first reference element, the second reference element and the third reference element is as follows:
taking the value of the first attribute of the short message element with the largest number and the same value of the first attribute of the short message elements in the first set as the value of the first attribute of the first reference element;
for example, if the value of the first attribute of 90% of the short message elements in the first set is trade, the trade is taken as the value of the first attribute of the first reference element;
taking the average value of the second attributes of the short message elements in the first set as the value of the first attribute of the first reference element;
taking the average value of the third attribute of the short message elements in the first set as the value of the first attribute of the third reference element;
the method for updating the first set, the second set and the third set comprises the steps of clearing the first set, the second set and the third set, calculating the similarity between short message elements in the historical short message set and three reference elements, and then bringing the short message elements in the historical short message set into the first set, the second set and the third set according to the conditions which need to be met by the short message elements in the first set, the second set and the third set;
step 150, repeating the step 140 until the total entropy of the first set, the second set and the third set is less than the set entropy threshold;
the calculation formula of the total entropy value s is as follows:
Figure 129694DEST_PATH_IMAGE029
wherein
Figure 541959DEST_PATH_IMAGE050
Represents the number of the short message elements in the jth category in the ith set, and/or the number of the short message elements in the jth category in the ith set>
Figure 489186DEST_PATH_IMAGE031
Representing the number of short message elements in the ith set;
the short message element classes comprise three types, namely A, B and C, and a class label is given to a first reference element, a second reference element and a third reference element, the classes of the short message elements with the largest quantity proportion are taken as class labels by the first set, the second set and the third set, and the class labels of the first reference element, the second reference element and the third reference element are respectively the same as the class labels of the first set, the second set and the third set;
step 160, extracting short message data from a short message database to be sent to generate a short message set to be sent, and bringing short message elements of the short message set to be sent into a fourth set, a fifth set and a sixth set respectively, wherein the short message elements in the fourth set need to satisfy the following conditions:
Figure 539182DEST_PATH_IMAGE032
wherein
Figure 47917DEST_PATH_IMAGE033
Represents->
Figure 448942DEST_PATH_IMAGE034
And &>
Figure 934282DEST_PATH_IMAGE004
Is based on the similarity of (4)>
Figure 602898DEST_PATH_IMAGE035
Represents->
Figure 781070DEST_PATH_IMAGE034
And &>
Figure 403812DEST_PATH_IMAGE006
The degree of similarity of (a) to (b),
Figure 194307DEST_PATH_IMAGE036
represents->
Figure 218895DEST_PATH_IMAGE034
And &>
Figure 567968DEST_PATH_IMAGE008
Is based on the similarity of (4)>
Figure 176541DEST_PATH_IMAGE034
Represents the SMS element in the fourth set, and/or>
Figure 269262DEST_PATH_IMAGE004
Represents a first reference element, is selected>
Figure 148356DEST_PATH_IMAGE006
Represents a second reference element, is selected>
Figure 435375DEST_PATH_IMAGE008
Represents a third reference element;
the conditions that the short message elements in the fifth set need to satisfy are as follows:
Figure 767130DEST_PATH_IMAGE051
wherein
Figure 630919DEST_PATH_IMAGE038
Represents->
Figure 630099DEST_PATH_IMAGE039
And &>
Figure 320974DEST_PATH_IMAGE004
Degree of similarity,. Or>
Figure 387630DEST_PATH_IMAGE040
Represents->
Figure 353312DEST_PATH_IMAGE039
And &>
Figure 941419DEST_PATH_IMAGE006
Degree of similarity,. Or>
Figure 567310DEST_PATH_IMAGE041
Represents->
Figure 873658DEST_PATH_IMAGE039
And &>
Figure 580714DEST_PATH_IMAGE008
Degree of similarity,. Or>
Figure 790372DEST_PATH_IMAGE039
Represents the SMS element in the fifth set, and/or>
Figure 354208DEST_PATH_IMAGE004
Represents a first reference element, is selected>
Figure 616693DEST_PATH_IMAGE006
Represents a second reference element, is selected>
Figure 157134DEST_PATH_IMAGE008
Represents a third reference element;
the conditions that the short message elements in the sixth set need to satisfy are as follows:
Figure 719833DEST_PATH_IMAGE052
wherein
Figure 923413DEST_PATH_IMAGE043
Represents->
Figure 440238DEST_PATH_IMAGE044
And &>
Figure 20255DEST_PATH_IMAGE004
Is based on the similarity of (4)>
Figure 437461DEST_PATH_IMAGE045
Represents->
Figure 576056DEST_PATH_IMAGE044
And &>
Figure 344292DEST_PATH_IMAGE006
The degree of similarity of (a) to (b),
Figure 462421DEST_PATH_IMAGE046
represents->
Figure 501177DEST_PATH_IMAGE044
And &>
Figure 312138DEST_PATH_IMAGE008
Is based on the similarity of (4)>
Figure 302091DEST_PATH_IMAGE044
Represents the SMS element in the sixth set, and/or>
Figure 988025DEST_PATH_IMAGE004
Represents a first reference element, is selected>
Figure 114244DEST_PATH_IMAGE006
Represents a second reference element, is selected>
Figure 320274DEST_PATH_IMAGE008
Represents a third reference element;
step 170, updating the attributes of the first reference element, the second reference element and the third reference element, and updating the fourth set, the fifth set and the sixth set;
the method for updating the attributes of the first reference element, the second reference element and the third reference element is as follows:
taking the value of the first attribute of the short message element with the largest number and the same value of the first attribute of the short message elements in the fourth set as the value of the first attribute of the first reference element;
taking the average value of the second attribute of the short message elements in the fourth set as the value of the first attribute of the first reference element;
taking the average value of the third attribute of the short message elements in the fourth set as the value of the first attribute of the third reference element;
the method for updating the fourth set, the fifth set and the sixth set comprises the steps of clearing the fourth set, the fifth set and the sixth set, calculating the similarity between the short message elements in the short message set to be sent and three reference elements, and then bringing the short message elements in the short message set to be sent into the fourth set, the fifth set and the sixth set according to the conditions which need to be met by the short message elements in the fourth set, the fifth set and the sixth set;
step 180, repeating the iteration of step 170 three to five times;
step 190, assigning the short message elements in the fourth set, the fifth set and the sixth set to the same category labels as the first reference element, the second reference element and the third reference element respectively;
the short messages corresponding to the short message elements of the type A, the type B and the type C are respectively brought into a first echelon, a second echelon and a third echelon of the short message sending queuing sequence.
The short messages of the first echelon are sent in preference to the short messages of the second echelon, and the short messages of the second echelon are sent in preference to the short messages of the third echelon.
The short messages of the same echelon can be sent randomly.
The invention is based on the mining of historical short message data, and quickly classifies the short messages to be sent by a small number of iterations, thereby having little influence on the average sending time of the short messages, but greatly shortening the sending time of the short messages needing to be sent preferentially, and improving the quality of short message service of a short message platform.
The embodiments of the present invention have been described with reference to the drawings, but the present invention is not limited to the above-mentioned specific embodiments, which are only illustrative and not restrictive, and those skilled in the art can make many forms without departing from the spirit and scope of the present invention and the protection scope of the claims.

Claims (6)

1. A method for reducing short message transmission delay is characterized by comprising the following steps:
step 110, extracting short message data from a historical short message database to generate a historical short message set, wherein the historical short message set comprises a plurality of short message elements, and the short message elements comprise a first attribute, a second attribute and a third attribute;
step 120, extracting three short message elements from the historical short message set as a first reference element, a second reference element and a third reference element respectively;
step 130, respectively bringing the short message elements in the historical short message set into a first set, a second set and a third set; the conditions that the short message elements in the first set need to satisfy are as follows:
Figure FDA0004055241050000011
wherein D (x) 1 ，c 1 ) Denotes x 1 And c 1 Similarity of (2), D (x) 1 ，c 2 ) Denotes x 1 And c 2 Similarity of (2), D (x) 1 ，c 3 ) Represents x 1 And c 3 Similarity of (2), x 1 Representing SMS elements in the first set, c 1 Denotes a first reference element, c 2 Denotes a second reference element, c 3 Represents a third reference element;
the conditions that the short message elements in the second set need to satisfy are as follows:
Figure FDA0004055241050000013
wherein D (x) 2 ，c 2 ) Denotes x 2 And c 2 Similarity of (c), D (x) 2 ，c 1 ) Denotes x 2 And c 1 Similarity of (2), D (x) 2 ，c 3 ) Denotes x 2 And c 3 Similarity of (2), x 2 Representing SMS elements in the second set, c 1 Denotes a first reference element, c 2 Denotes a second reference element, c 3 Represents a third reference element;
the conditions that the short message elements in the third set need to satisfy are as follows:
Figure FDA0004055241050000012
wherein D (x) 3 ，c 3 ) Denotes x 3 And c 3 Similarity of (c), D (x) 3 ，c 1 ) Denotes x 3 And c 1 Similarity of (2), D (x) 3 ，c 2 ) Denotes x 3 And c 2 Similarity of (2), x 3 Representing SMS elements in the third set, c 1 Denotes a first reference element, c 2 Denotes a second reference element, c 3 Represents a third reference element;
step 140, updating the attributes of the first reference element, the second reference element and the third reference element, and updating the first set, the second set and the third set; the method for updating the attributes of the first reference element, the second reference element and the third reference element is as follows:
taking the value of the first attribute of the short message element with the largest number and the same value of the first attribute of the short message elements in the first set as the value of the first attribute of the first reference element;
taking the average value of the second attributes of the short message elements in the first set as the value of the first attribute of the first reference element;
taking the average value of the third attribute of the short message elements in the first set as the value of the first attribute of the third reference element;
the method for updating the first set, the second set and the third set comprises the steps of clearing the first set, the second set and the third set, calculating the similarity between short message elements in the historical short message set and three reference elements, and then bringing the short message elements in the historical short message set into the first set, the second set and the third set according to the conditions which need to be met by the short message elements in the first set, the second set and the third set;
step 150, repeating the step 140 until the total entropy of the first set, the second set and the third set is less than the set entropy threshold;
the categories of the short message elements are respectively A, B and C, the categories of the short message elements with the largest quantity proportion are respectively used as category labels by the first set, the second set and the third set, and the category labels of the first reference element, the second reference element and the third reference element are respectively the same as those of the first set, the second set and the third set;
step 160, extracting short message data from a short message database to be sent to generate a short message set to be sent, and bringing short message elements of the short message set to be sent into a fourth set, a fifth set and a sixth set respectively;
the conditions that the short message elements in the fourth set need to satisfy are as follows:
Figure FDA0004055241050000031
wherein D (x) 4 ，c 1 ) Represents x 4 And c 1 Similarity of (c), D (x) 4 ，c 2 ) Denotes x 4 And c 2 Similarity of (c), D (x) 4 ，c 3 ) Represents x 4 And c 3 Similarity of (2), x 4 Representing SMS elements in the fourth set, c 1 Denotes a first reference element, c 2 Denotes a second reference element, c 3 Represents a third reference element;
the conditions that the short message elements in the fifth set need to satisfy are as follows:
Figure FDA0004055241050000032
wherein D (x) 5 ，c 1 ) Denotes x 5 And c 1 Similarity, D (x) 5 ，c 2 ) Represents x 5 And c 2 Similarity, D (x) 5 ，c 3 ) Denotes x 5 And c 3 Degree of similarity, x 5 Representing SMS elements in the fifth set, c 1 Denotes a first reference element, c 2 Denotes a second reference element, c 3 Represents a third reference element;
the conditions that the short message elements in the sixth set need to satisfy are as follows:
Figure FDA0004055241050000033
wherein D (x) 6 ，c 1 ) Represents x 6 And c 1 Similarity of (2), D (x) 6 ，c 2 ) Denotes x 6 And c 2 Similarity of (2), D (x) 6 ，c 3 ) Represents x 6 And c 3 Similarity of (2), x 6 Representing SMS elements in the sixth set, c 1 Denotes a first reference element, c 2 Denotes a second reference element, c 3 Represents a third reference element;
step 170, updating the attributes of the first reference element, the second reference element and the third reference element, and updating the fourth set, the fifth set and the sixth set; the method for updating the attributes of the first reference element, the second reference element and the third reference element is as follows:
taking the value of the first attribute of the short message element with the same value and the largest number of the first attributes of the short message elements in the fourth set as the value of the first attribute of the first reference element;
taking the average value of the second attribute of the short message elements in the fourth set as the value of the first attribute of the first reference element;
taking the average value of the third attribute of the short message elements in the fourth set as the value of the first attribute of the third reference element;
the method for updating the fourth set, the fifth set and the sixth set comprises the steps of clearing the fourth set, the fifth set and the sixth set, calculating the similarity between the short message elements in the short message set to be sent and three reference elements, and then bringing the short message elements in the short message set to be sent into the fourth set, the fifth set and the sixth set according to the conditions which need to be met by the short message elements in the fourth set, the fifth set and the sixth set;
step 180, repeating the iteration of step 170 three to five times;
step 190, assigning the short message elements in the fourth set, the fifth set and the sixth set to the same category labels as the first reference element, the second reference element and the third reference element respectively; respectively incorporating short messages corresponding to the short message elements of the type A, the type B and the type C into a first echelon, a second echelon and a third echelon of a short message sending queuing sequence; the short messages of the first echelon are sent in preference to the short messages of the second echelon, and the short messages of the second echelon are sent in preference to the short messages of the third echelon.
2. The method of claim 1, wherein the values of the first attribute include trade, verify, and edit;
if the content of the short message element contains any transaction keyword, taking trade from the value of the first attribute of the short message element;
if the content of the short message element contains any verification keyword, the value of the first attribute of the short message element is changed;
if the content of the short message element does not contain the transaction key word and the verification key word, the value of the first attribute of the short message element is selected as the edit;
the priority of the first attribute with the value of trade of the short message element is greater than the priority with the value of verify, and the priority with the value of verify is greater than the priority with the value of edit.
3. The method of claim 1, wherein the value of the second attribute is a message sending status receipt time of a previous message received by a sending target of the message element, and the message sending status receipt time is a time from sending the message to an operator to returning the message sending status receipt.
4. The method of claim 1, wherein the value of the third attribute is the number of characters contained in the short message content of the short message element.
5. The method of claim 1, wherein the similarity between the SMS element and the reference element is calculated as follows:
Figure FDA0004055241050000051
wherein
Figure FDA0004055241050000061
Wherein q is 1 ，q 2 ，q 3 Respectively representing the values of the first attribute, the second attribute and the third attribute of the short message element, wherein y 1 ，y 2 ，y 3 Respectively representing the values of the first attribute, the second attribute and the third attribute of the reference element.
6. The method of claim 1, wherein the total entropy s in step 150 is calculated as follows:
Figure FDA0004055241050000062
wherein m is ij The number of short message elements of j category in the ith set is represented, n i Indicating the number of short message elements in the ith set.
CN202211545490.4A 2022-12-05 2022-12-05 Method for reducing short message sending delay Active CN115580841B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211545490.4A CN115580841B (en) 2022-12-05 2022-12-05 Method for reducing short message sending delay

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211545490.4A CN115580841B (en) 2022-12-05 2022-12-05 Method for reducing short message sending delay

Publications (2)

Publication Number Publication Date
CN115580841A CN115580841A (en) 2023-01-06
CN115580841B true CN115580841B (en) 2023-03-28

Family

ID=84590490

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211545490.4A Active CN115580841B (en) 2022-12-05 2022-12-05 Method for reducing short message sending delay

Country Status (1)

Country Link
CN (1) CN115580841B (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114885334A (en) * 2022-07-13 2022-08-09 安徽创瑞信息技术有限公司 High-concurrency short message processing method

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102098638A (en) * 2010-12-15 2011-06-15 成都市华为赛门铁克科技有限公司 Short message sorting method and device, and terminal
CN108920475B (en) * 2018-03-30 2021-09-14 西北师范大学 Short text similarity calculation method
CN110913354A (en) * 2018-09-17 2020-03-24 阿里巴巴集团控股有限公司 Short message classification method and device and electronic equipment
CN112533156B (en) * 2019-09-17 2022-05-13 中国移动通信有限公司研究院 Short message processing method and device
CN112085219B (en) * 2020-10-13 2024-02-13 北京百度网讯科技有限公司 Model training method, short message auditing method, device, equipment and storage medium
CN112270379B (en) * 2020-11-13 2023-09-19 北京百度网讯科技有限公司 Training method of classification model, sample classification method, device and equipment
CN114866966B (en) * 2022-07-08 2022-09-06 安徽创瑞信息技术有限公司 Short message user management method based on big data

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114885334A (en) * 2022-07-13 2022-08-09 安徽创瑞信息技术有限公司 High-concurrency short message processing method

Also Published As

Publication number Publication date
CN115580841A (en) 2023-01-06

Similar Documents

Publication Publication Date Title
EP2075720B1 (en) Method and system of determining garbage information
US9317592B1 (en) Content-based classification
JP7440565B2 (en) Electronic message filtering
CN111835760B (en) Alarm information processing method and device, computer storage medium and electronic equipment
US20190281000A1 (en) Detection of Spam Messages
US20090089279A1 (en) Method and Apparatus for Detecting Spam User Created Content
WO2006047532A1 (en) Probabilistic model for record linkage
CN113139876B (en) Risk model training method, risk model training device, computer equipment and readable storage medium
CN106446149B (en) Notification information filtering method and device
CN113868368A (en) Method, electronic device and computer program product for information processing
CN113887214B (en) Willingness presumption method based on artificial intelligence and related equipment thereof
US7685120B2 (en) Method for generating and prioritizing multiple search results
CN114118816B (en) Risk assessment method, apparatus, device and computer storage medium
CN111177362A (en) Information processing method, device, server and medium
CN115580841B (en) Method for reducing short message sending delay
CN109450963B (en) Message pushing method and terminal equipment
CN116992052B (en) Long text abstracting method and device for threat information field and electronic equipment
CN110972086A (en) Short message processing method and device, electronic equipment and computer readable storage medium
US20210397636A1 (en) Text object management system
CN109214640A (en) Determination method, equipment and the computer readable storage medium of index result
CN112949290A (en) Text error correction method and device and communication equipment
CN112330427A (en) Method, electronic device and storage medium for commodity sorting
CN111401959A (en) Risk group prediction method and device, computer equipment and storage medium
CN116739795A (en) Knowledge graph-based insurance risk assessment method and device and electronic equipment
CN110807702A (en) Method, device, equipment and storage medium for managing information after loan

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant