CN107770738A - For realizing method and user terminal that short message classifies automatically - Google Patents
For realizing method and user terminal that short message classifies automatically Download PDFInfo
- Publication number
- CN107770738A CN107770738A CN201610707910.2A CN201610707910A CN107770738A CN 107770738 A CN107770738 A CN 107770738A CN 201610707910 A CN201610707910 A CN 201610707910A CN 107770738 A CN107770738 A CN 107770738A
- Authority
- CN
- China
- Prior art keywords
- short message
- classification
- sender number
- text
- folder
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000007547 defect Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 13
- 230000005540 biological transmission Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
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]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72403—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality
- H04M1/7243—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages
- H04M1/72436—User interfaces specially adapted for cordless or mobile telephones with means for local support of applications that increase the functionality with interactive means for internal management of messages for text messaging, e.g. short messaging services [SMS] or e-mails
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Human Computer Interaction (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The present invention discloses a kind of method and user terminal for being used to realize that short message is classified automatically, is related to big data field.Wherein after user terminal receives short message, judge whether short message matches with sender number rule, if short message matches with sender number rule, then short message is stored in corresponding classification folder, if short message mismatches with sender number rule, then determine whether short message matches with text classifier, if short message matches with text classifier, short message is stored in corresponding classification folder.The present invention realizes SMS classified without user entered keyword and sender number can, overcomes sender number changeable and the defects of artificial determination keyword difficulty, so as to more intelligently solve the problems, such as that short message is classified automatically.
Description
Technical field
The present invention relates to big data field, more particularly to a kind of method and user's end for being used to realize that short message is classified automatically
End.
Background technology
SMS includes a large amount of announcement informations, such as electric business promotion, bank financing, family's school contact, weather forecast, user
There is the notable demand that Classification Management is carried out to short message.
The method that Fig. 1 gives a kind of SMS classification of the prior art, passes through the hair set in advance with user
The side's of sending number and keyword text matches realize the automatic classification of short message.Wherein:
Step 101, classification folder is created.Then step 102a and step 102b is performed.
Step 102a, phone number matching condition is set, then performs step 103.
Wherein, can be by directly inputting number, number is selected from address list, selecting the mode such as number to enter from message registration
Row is set.
Step 102b, short message content matching condition is set.
Wherein, the condition of the matching completely of input text or input textual portions matching can be set.
Step 103, after the setup, new message is received.
Step 104, judge new message whether with setting matching criteria.If matching, step 105 is performed, is otherwise performed
Step 106.
Step 105, new message is stored in the classification folder of matching.
Step 106, new message is stored in inbox.
But there is problems with the prior art:Businessman may use multiple port numbers transmitting short messages;Manually determine all kinds of
Other Key comparison is difficult, for example, for weather forecast class many short messages in fact and the word not comprising " weather ".
The content of the invention
The embodiment of the present invention provides a kind of method and user terminal for being used to realize that short message is classified automatically, is inputted without user
Keyword and sender number can are realized SMS classified, overcome sender number changeable and artificial determination keyword is difficult
Defect, so as to more intelligently solve the problems, such as that short message is classified automatically.
According to an aspect of the present invention, there is provided it is a kind of to be used to realize the method that short message is classified automatically, including:
After user terminal receives short message, judge whether short message matches with sender number rule;
If short message matches with sender number rule, short message is stored in corresponding classification folder;
If short message mismatches with sender number rule, determine whether short message matches with text classifier;
If short message matches with text classifier, short message is stored in corresponding classification folder.
In one embodiment, after short message is stored in corresponding classification folder, in addition to:
The classification center vector of corresponding classification folder is recalculated, to update text classifier.
In one embodiment, if short message mismatches with text classifier, short message is stored in short message inbox.
In one embodiment, judge that the step of whether short message matches with text classifier includes:
Determine the text vector of short message;
The similarity of each classification center vector in the text vector and text classifier of short message is calculated respectively;
In the case where at least one similarity exceedes predetermined threshold, judge that short message matches with text classifier, and will
Classification folder corresponding to maximum similarity is as the classification folder corresponding with short message.
In one embodiment, the above method also includes study sender number rule and the step of structure text classifier
Suddenly, wherein:
Create classification folder;
Short message will have been received to add in the classification folder created;
Learn sender number rule, to require that increase will receive the sender number and this point of short message according to user
Sender number rule corresponding to class file folder, and whole short messages that the sender number for having received short message is sent are added to this
In classification folder;
The classification center vector in the classification folder is calculated, to build text classifier.
In one embodiment, study sender number rule includes:
Whether the sender number for judging to have received short message has been included in sender number rule;
If the sender number for having received short message is not included in sender number rule, further whether user is inquired about
It is required that the sender number for having received short message is bound with the classification folder;
If user requires to bind the sender number for having received short message with the classification folder, increase will receive short
The sender number of letter sender number rule corresponding with the classification folder, and the sender number for having received short message is sent out
The whole short messages sent are added in the classification folder.
In one embodiment, if the sender number for having received short message is included in sender number rule, one is entered
Step judge received short message sender number whether with sender number rule conflict;
If having received the sender number and sender number rule conflict of short message, sender number rule is deleted.
In one embodiment, the step of classification center vector in the classification folder is to build text classifier is calculated
Including:
Calculate the text vector of each short message in the classification folder;
Using the average value of the text vector of each short message in the classification folder as the classification folder classification center to
Amount, to build text classifier.
According to another aspect of the present invention, there is provided a kind of to be used to realize the user terminal that short message is classified automatically, including interface
Module, number rule module, text classification module and Classification Management module, wherein:
Interface module, for receiving short message;
Number rule module, for after interface module receives short message, judging whether short message is regular with sender number
Match;
Text classification module, for short message and sender number rule it is unmatched in the case of, judge short message whether with
Text classifier matches;
Classification Management module, for judging the situation that short message and sender number rule match in number rule module
Under, or in the case where text classification module judges that short message matches with text classifier, short message is stored in corresponding point
In class file folder.
In one embodiment, above-mentioned user terminal also includes update module, wherein:
Update module, for after short message is stored in corresponding classification folder by Classification Management module, recalculating
The classification center vector of corresponding classification folder, to update text classifier.
In one embodiment, Classification Management module is additionally operable in the case of short message and text classifier are unmatched, will
In short message deposit short message inbox.
In one embodiment, text classification module is specifically when judging whether short message matches with text classifier, really
Determine the text vector of short message, calculate the similarity of each classification center vector in the text vector and text classifier of short message respectively,
In the case where at least one similarity exceedes predetermined threshold, judge that short message matches with text classifier, and will be maximum similar
Classification folder corresponding to degree is as the classification folder corresponding with short message.
In one embodiment, above-mentioned user terminal also includes classification annotation module, wherein:
Classification annotation module, for creating classification folder, short message will be received and added in the classification folder created;Learn
Sender number rule is practised, to require that increase will receive the sender number and the classification folder pair of short message according to user
The sender number rule answered, and whole short messages that the sender number for having received short message is sent are added to the classification folder
In;The classification center vector in the classification folder is calculated, to build text classifier.
In one embodiment, for classification annotation module specifically when learning sender number rule, judgement has received short message
Sender number whether be included in sender number rule, if the sender number for having received short message is not included in transmission
In square number rule, then further whether inquiry user requires to tie up the sender number for having received short message with the classification folder
It is fixed;If user requires to bind the sender number for having received short message with the classification folder, increase will receive short message
Sender number sender number rule corresponding with the classification folder, and the sender number for having received short message is sent
Whole short messages are added in the classification folder.
In one embodiment, classification annotation module is additionally operable to be included in sender in the sender number for having received short message
In the case of in number rule, determine whether to have received short message sender number whether with sender number rule conflict;
If having received the sender number and sender number rule conflict of short message, sender number rule is deleted.
In one embodiment, classification annotation module calculates each short in the classification folder when building text classifier
The text vector of letter, using the average value of the text vector of each short message in the classification folder as in the classification of the classification folder
Heart vector, to build text classifier.
By referring to the drawings to the present invention exemplary embodiment detailed description, further feature of the invention and its
Advantage will be made apparent from.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the required accompanying drawing used in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, without having to pay creative labor, may be used also
To obtain other accompanying drawings according to these accompanying drawings.
Fig. 1 is SMS classified schematic flow sheet in the prior art.
Fig. 2 is the schematic diagram that the present invention is used to realize method one embodiment that short message is classified automatically.
Fig. 3 is that the present invention judges whether short message matches the schematic diagram of one embodiment with text classifier.
Fig. 4 is the schematic diagram of classification annotation process one embodiment of the present invention.
Fig. 5 is the schematic diagram of present invention study sender number rule one embodiment.
Fig. 6 is the schematic diagram of present invention structure text classifier one embodiment.
Fig. 7 is the schematic diagram that the present invention is used to realize user terminal one embodiment that short message is classified automatically.
Fig. 8 is the schematic diagram of the user terminal another embodiment of the invention for being used to realize that short message is classified automatically.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, rather than whole embodiments.Below
Description only actually at least one exemplary embodiment is illustrative, is never used as to the present invention and its application or makes
Any restrictions.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creative work premise
Lower obtained every other embodiment, belongs to the scope of protection of the invention.
Unless specifically stated otherwise, the part and positioned opposite, the digital table of step otherwise illustrated in these embodiments
Do not limited the scope of the invention up to formula and numerical value.
Simultaneously, it should be appreciated that for the ease of description, the size of the various pieces shown in accompanying drawing is not according to reality
Proportionate relationship draw.
It may be not discussed in detail for technology, method and apparatus known to person of ordinary skill in the relevant, but suitable
In the case of, the technology, method and apparatus should be considered as authorizing part for specification.
In shown here and discussion all examples, any occurrence should be construed as merely exemplary, without
It is as limitation.Therefore, the other examples of exemplary embodiment can have different values.
It should be noted that:Similar label and letter represents similar terms in following accompanying drawing, therefore, once a certain Xiang Yi
It is defined, then it need not be further discussed in subsequent accompanying drawing in individual accompanying drawing.
Fig. 2 is the schematic diagram that the present invention is used to realize method one embodiment that short message is classified automatically.Wherein:
Step 201, short message is received.
Step 202, after user terminal receives short message, judge whether short message matches with sender number rule.Its
In, if short message matches with sender number rule, perform step 204;If short message mismatches with sender number rule,
Perform step 203.
Wherein, if sender number rule includes the short message, the short message and sender number rule phase be can determine whether
Match somebody with somebody.
Step 203, judge whether short message matches with text classifier.If short message matches with text classifier, hold
Row step 204;If short message mismatches with text classifier, step 205 is performed.
Step 204, short message is stored in corresponding classification folder.
Step 205, short message is stored in short message inbox.
Alternatively, after step 204, it can also carry out step 206.
Step 206, the classification center vector of corresponding classification folder is recalculated, to update text classifier.
It is used for the method for realizing that short message is classified automatically based on what the above embodiment of the present invention provided, is advised based on sender number
The classification belonging to short message to be sorted is then determined with text classifier, it is real without user entered keyword and sender number can
It is existing SMS classified, overcome sender number changeable and the defects of artificial determination keyword difficulty, so as to more intelligently solve
The problem of short message is classified automatically.
Alternatively, it is above-mentioned to judge that the step of whether short message matches with text classifier be as shown in Figure 3.Wherein:
Step 301, the text vector of short message is determined.
Wherein, vectorization expression is carried out to short message text to be sorted, it may include following processing:Short message text normalized
(capital and small letter, the conversion of full-shape half-angle) → denoising (removing stop words, function word) → participle → word frequency statisticses → text vector represents.
Step 302, the similarity of each classification center vector in the text vector and text classifier of short message is calculated respectively.
For example, vector space cosine similarity formula can be used, calculate successively short message to be sorted it is vectorial with each classification
The similarity of Heart vector.
Step 303, the similarity more than predetermined threshold is judged whether.If exist at least one more than predetermined threshold
Similarity, then perform step 304;Otherwise step 305 is performed.
Step 304, judge short message match with text classifier, and using classification folder corresponding to maximum similarity as
The classification folder corresponding with short message.
Step 305, judge that short message mismatches with text classifier.
Fig. 4 gives the schematic diagram of classification annotation process one embodiment of the present invention, can be real by the classification annotation process
Now learn sender number rule and structure text classifier.Wherein:
Step 401, classification folder is created.
Step 402, short message will have been received to add in the classification folder created.
Step 403, sender number rule is learnt, to require that increase will receive the sender number of short message according to user
Code sender number rule corresponding with the classification folder, and whole short messages that the sender number for having received short message is sent
It is added in the classification folder.
Step 404, the classification center vector in the classification folder is calculated, to build text classifier.
Study sender number rule and structure text classifier are specifically described separately below.
Fig. 5 is the schematic diagram of present invention study sender number rule one embodiment.Wherein:
Step 501, judge whether the sender number for having received short message has been included in sender number rule.If connect
The sender number for receiving short message is not included in sender number rule, then performs step 502;If the sender of short message is received
Number is included in sender number rule, then performs step 504.
Step 502, further whether inquiry user requires that the sender number and the classification folder of short message will have been received
Binding.If user requires to bind the sender number for having received short message with the classification folder, step 503 is performed;Otherwise
Terminate this flow.
Step 503, the sender number that will receive short message sender number rule corresponding with the classification folder are increased
Then, and by the sender number for having received short message the whole short messages sent are added in the classification folder.Then this stream is terminated
Journey.
Step 504, determine whether to have received short message sender number whether with sender number rule conflict.If
The sender number and sender number rule conflict of short message are received, then performs step 505;Otherwise this flow is terminated.
Step 505, sender number rule is deleted, then terminates this flow.
By the flow, sender number rule can be learnt automatically by the short message having been received by.
Fig. 6 is the schematic diagram of present invention structure text classifier one embodiment.Wherein:
Step 601, the text vector of each short message in the classification folder is calculated.
Wherein, vectorization can be carried out to every short message text under the classification successively:Short message text normalized (size
Write, the conversion of full-shape half-angle) → denoising (removing stop words function word) → participle → word frequency statisticses → text vector expression.
Step 602, point using the average value of the text vector of each short message in the classification folder as the classification folder
Class center vector, to build text classifier.
For example, calculate the arithmetic mean of instantaneous value of each short message text vector under classification center vector=category.
By the flow, text classifier can be built automatically by the short message having been received by.
Fig. 7 is the schematic diagram that the present invention is used to realize user terminal one embodiment that short message is classified automatically.Such as Fig. 7 institutes
Show, user terminal may include interface module 701, number rule module 702, text classification module 703 and Classification Management module
704.Wherein:
Interface module 701 is used to receive short message.
Number rule module 702 be used for after interface module 701 receives short message, judge short message whether with sender number
Rule matches.
Text classification module 703 is used in the case of short message and sender number rule are unmatched, whether judges short message
Match with text classifier.
Classification Management module 704 is used to judge what short message matched with sender number rule in number rule module 702
In the case of, or in the case where text classification module 703 judges that short message matches with text classifier, short message is stored in relative
In the classification folder answered.
Alternatively, Classification Management module 704 is additionally operable in the case of short message and text classifier are unmatched, and short message is deposited
Enter in short message inbox.
Alternatively, text classification module 704 determines short message also when judging whether short message matches with text classifier
Text vector, the similarity of each classification center vector in the text vector and text classifier of short message is calculated respectively, at least one
In the case that individual similarity exceedes predetermined threshold, judge that short message matches with text classifier, and by corresponding to maximum similarity
Classification folder is as the classification folder corresponding with short message.
It is used for the user terminal for realizing that short message is classified automatically based on what the above embodiment of the present invention provided, based on sender number
Code rule and text classifier determine the classification belonging to short message to be sorted, can without user entered keyword and sender number
It is SMS classified to realize, overcome sender number changeable and the defects of artificial determination keyword difficulty, so as to more intelligently
Solve the problems, such as that short message is classified automatically.
Fig. 8 is the schematic diagram of the user terminal another embodiment of the invention for being used to realize that short message is classified automatically.Shown in Fig. 7
Embodiment is compared, in the embodiment shown in fig. 8, except interface module 801, number rule module 802, the and of text classification module 803
Outside Classification Management module 804, in addition to update module 805.Wherein:
Update module 805 is used for after short message is stored in corresponding classification folder by Classification Management module 804, again
The classification center vector of corresponding classification folder is calculated, to update text classifier.
Alternatively, as shown in figure 8, user terminal also includes classification annotation module 806.Wherein:
Classification annotation module 806 is used to create classification folder, will receive short message and has added in the classification folder created;
Learn sender number rule, to require that increase will receive the sender number and the classification folder of short message according to user
Corresponding sender number rule, and whole short messages that the sender number for having received short message is sent are added to the sort file
In folder;The classification center vector in the classification folder is calculated, to build text classifier.
Alternatively, classification annotation module 806 judges to have received the transmission of short message specifically when learning sender number rule
Whether square number has been included in sender number rule, if the sender number for having received short message is not included in sender number
In rule, then further whether inquiry user requires to bind the sender number for having received short message with the classification folder;If
User requires to bind the sender number for having received short message with the classification folder, then increase will receive the sender of short message
Number sender number rule corresponding with the classification folder, and the whole that the sender number for having received short message is sent is short
Letter is added in the classification folder.
In addition, in the case where the sender number for having received short message is included in sender number rule, classification annotation
Module 806 also determine whether to have received short message sender number whether with sender number rule conflict;If receive short
The sender number of letter and sender number rule conflict, then delete sender number rule.
Alternatively, classification annotation module 806 is additionally operable to, when building text classifier, calculate each short in the classification folder
The text vector of letter, using the average value of the text vector of each short message in the classification folder as in the classification of the classification folder
Heart vector, to build text classifier.
By implementing the present invention, following beneficial effect can be obtained:
1) when user's taxonomic revision existing short message, by pulling in the short message in classification folder, sender is established
Number rule, input without user or chosen from address list;
2) by pulling in the short message in classification folder, automatic learning Content classifying rules, without user's defining classification
Keyword text;
3) overcome sender number changeable and the defects of artificial determination keyword difficulty, it is short so as to more intelligently solve
The problem of letter is classified automatically.
One of ordinary skill in the art will appreciate that hardware can be passed through by realizing all or part of step of above-described embodiment
To complete, by program the hardware of correlation can also be instructed to complete, described program can be stored in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only storage, disk or CD etc..
Description of the invention provides for the sake of example and description, and is not exhaustively or by the present invention
It is limited to disclosed form.Many modifications and variations are obvious for the ordinary skill in the art.Select and retouch
State embodiment and be to more preferably illustrate the principle and practical application of the present invention, and one of ordinary skill in the art is managed
The present invention is solved so as to design the various embodiments with various modifications suitable for special-purpose.
Claims (16)
1. a kind of be used to realize the method that short message is classified automatically, it is characterised in that including:
After user terminal receives short message, judge whether the short message matches with sender number rule;
If the short message matches with sender number rule, the short message is stored in corresponding classification folder;
If the short message and sender number rule mismatch, determine whether the short message whether with text classifier phase
Match somebody with somebody;
If the short message matches with text classifier, the short message is stored in corresponding classification folder.
2. according to the method for claim 1, it is characterised in that
After the short message is stored in corresponding classification folder, in addition to:
The classification center vector of the corresponding classification folder is recalculated, to update text classifier.
3. according to the method for claim 1, it is characterised in that
If the short message mismatches with text classifier, the short message is stored in short message inbox.
4. according to the method for claim 1, it is characterised in that
Judge that the step of whether short message matches with text classifier includes:
Determine the text vector of the short message;
The similarity of each classification center vector in the text vector and text classifier of the short message is calculated respectively;
In the case where at least one similarity exceedes predetermined threshold, judge that the short message matches with text classifier, and will
Classification folder corresponding to maximum similarity is as the classification folder corresponding with the short message.
5. according to the method any one of claim 1-4, it is characterised in that also include study sender number rule and
The step of building text classifier, wherein:
Create classification folder;
Short message will have been received to add in the classification folder created;
Learn sender number rule, to require that increase will receive the sender number and classification text of short message according to user
Sender number rule corresponding to part folder, and whole short messages that the sender number for having received short message is sent are added to the classification
In file;
The classification center vector in the classification folder is calculated, to build text classifier.
6. according to the method for claim 5, it is characterised in that
Study sender number rule includes:
Whether the sender number for judging to have received short message has been included in sender number rule;
If the sender number for having received short message is not included in sender number rule, further inquire about whether user requires
The sender number for having received short message is bound with the classification folder;
If user requires to bind the sender number for having received short message with the classification folder, increase will receive short message
Sender number sender number rule corresponding with the classification folder, and the sender number for having received short message is sent
Whole short messages are added in the classification folder.
7. according to the method for claim 6, it is characterised in that
If the sender number for having received short message is included in sender number rule, determine whether to have received the hair of short message
The side's of sending number whether with sender number rule conflict;
If having received the sender number and sender number rule conflict of short message, sender number rule is deleted.
8. according to the method for claim 5, it is characterised in that
Calculating the step of classification center vector in the classification folder is to build text classifier includes:
Calculate the text vector of each short message in the classification folder;
Classification center vector using the average value of the text vector of each short message in the classification folder as the classification folder, with
Build text classifier.
9. a kind of be used to realize the user terminal that short message is classified automatically, it is characterised in that including interface module, number rule mould
Block, text classification module and Classification Management module, wherein:
Interface module, for receiving short message;
Number rule module, for after interface module receives short message, judging whether the short message is regular with sender number
Match;
Text classification module, in the case of the short message and sender number rule are unmatched, judging that the short message is
It is no to match with text classifier;
Classification Management module, for judging the situation that the short message and sender number rule match in number rule module
Under, or in the case where text classification module judges that the short message matches with text classifier, the short message is stored in phase
In corresponding classification folder.
10. user terminal according to claim 9, it is characterised in that also including update module, wherein:
Update module, for after the short message is stored in corresponding classification folder by Classification Management module, recalculating
The classification center vector of the corresponding classification folder, to update text classifier.
11. user terminal according to claim 9, it is characterised in that
Classification Management module is additionally operable in the case of the short message and text classifier are unmatched, and the short message is stored in into short message
In inbox.
12. user terminal according to claim 9, it is characterised in that
Text classification module specifically when judging whether the short message matches with text classifier, determines the text of the short message
Vector, the similarity of each classification center vector in the text vector and text classifier of the short message is calculated respectively, at least one
In the case that individual similarity exceedes predetermined threshold, judge that the short message matches with text classifier, and by maximum similarity pair
The classification folder answered is as the classification folder corresponding with the short message.
13. according to the user terminal any one of claim 9-12, it is characterised in that also including classification annotation module,
Wherein:
Classification annotation module, for creating classification folder, short message will be received and added in the classification folder created;Study hair
The side's of sending number rule, to require that increase is corresponding with the classification folder by the sender number for having received short message according to user
Sender number rule, and whole short messages that the sender number for having received short message is sent are added in the classification folder;
The classification center vector in the classification folder is calculated, to build text classifier.
14. user terminal according to claim 13, it is characterised in that
Whether classification annotation module specifically when learning sender number rule, wrapped by the sender number for judging to have received short message
Include in sender number rule, if the sender number for having received short message is not included in sender number rule, enter one
Whether step inquiry user requires to bind the sender number for having received short message with the classification folder;If user requires to have connect
The sender number and the classification folder for receiving short message are bound, then increase will receive the sender number and classification text of short message
Sender number rule corresponding to part folder, and whole short messages that the sender number for having received short message is sent are added to the classification
In file.
15. user terminal according to claim 14, it is characterised in that
Classification annotation module is additionally operable in the case where the sender number for having received short message is included in sender number rule,
Determine whether to have received short message sender number whether with sender number rule conflict;If the sender of short message is received
Number and sender number rule conflict, then delete sender number rule.
16. user terminal according to claim 13, it is characterised in that
Classification annotation module calculates the text vector of each short message in the classification folder, by this point when building text classifier
Classification center vector of the average value of the text vector of each short message as the classification folder in class file folder, to build text point
Class device.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610707910.2A CN107770738B (en) | 2016-08-23 | 2016-08-23 | Method and user terminal for realizing automatic short message classification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610707910.2A CN107770738B (en) | 2016-08-23 | 2016-08-23 | Method and user terminal for realizing automatic short message classification |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107770738A true CN107770738A (en) | 2018-03-06 |
CN107770738B CN107770738B (en) | 2021-06-04 |
Family
ID=61263476
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610707910.2A Active CN107770738B (en) | 2016-08-23 | 2016-08-23 | Method and user terminal for realizing automatic short message classification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107770738B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108491535A (en) * | 2018-03-29 | 2018-09-04 | 北京小米移动软件有限公司 | The classification storage method and device of information |
CN110913353A (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 |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101645971A (en) * | 2009-05-18 | 2010-02-10 | 上海闻泰电子科技有限公司 | Method for establishing classification rule of short messages of mobile phone |
CN104023109A (en) * | 2014-06-27 | 2014-09-03 | 深圳市中兴移动通信有限公司 | Incoming call prompt method and device as well as incoming call classifying method and device |
CN105101124A (en) * | 2015-08-07 | 2015-11-25 | 北京奇虎科技有限公司 | Method and device for marking category of short messages |
CN105488031A (en) * | 2015-12-09 | 2016-04-13 | 北京奇虎科技有限公司 | Method and apparatus for detecting similar short messages |
-
2016
- 2016-08-23 CN CN201610707910.2A patent/CN107770738B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101645971A (en) * | 2009-05-18 | 2010-02-10 | 上海闻泰电子科技有限公司 | Method for establishing classification rule of short messages of mobile phone |
CN104023109A (en) * | 2014-06-27 | 2014-09-03 | 深圳市中兴移动通信有限公司 | Incoming call prompt method and device as well as incoming call classifying method and device |
CN105101124A (en) * | 2015-08-07 | 2015-11-25 | 北京奇虎科技有限公司 | Method and device for marking category of short messages |
CN105488031A (en) * | 2015-12-09 | 2016-04-13 | 北京奇虎科技有限公司 | Method and apparatus for detecting similar short messages |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108491535A (en) * | 2018-03-29 | 2018-09-04 | 北京小米移动软件有限公司 | The classification storage method and device of information |
CN110913353A (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 |
Also Published As
Publication number | Publication date |
---|---|
CN107770738B (en) | 2021-06-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107977415A (en) | Automatic question-answering method and device | |
CN109582949A (en) | Event element abstracting method, calculates equipment and storage medium at device | |
CN105787025B (en) | Network platform public account classification method and device | |
CN104717124A (en) | Friend recommendation method, device and server | |
CN106296195A (en) | A kind of Risk Identification Method and device | |
CN107784051A (en) | Online customer service answering system and method | |
CN105045919B (en) | A kind of information output method and device | |
CN106997339A (en) | Text feature, file classification method and device | |
CN106897290B (en) | Method and device for establishing keyword model | |
CN110442842A (en) | The extracting method and device of treaty content, computer equipment, storage medium | |
CN107918904A (en) | A kind of crowdsourcing interpretation method and platform | |
CN107341157B (en) | Customer service conversation clustering method and device | |
CN110147427A (en) | Project case method for pushing and device | |
CN108596637A (en) | A kind of electric business service problem discovery system | |
CN107770738A (en) | For realizing method and user terminal that short message classifies automatically | |
CN109993417A (en) | A kind of service condition mark adding method, device and storage medium | |
CN115858741A (en) | Intelligent question answering method and device suitable for multiple scenes and storage medium | |
CN108334353A (en) | Skill development system and method | |
CN105869058A (en) | Method for user portrait extraction based on multilayer latent variable model | |
CN111708887B (en) | Bad call identification method for multi-model fusion of user-defined rules | |
CN107506407A (en) | A kind of document classification, the method and device called | |
CN115687754B (en) | Active network information mining method based on intelligent dialogue | |
CN101119543A (en) | Screening method and system of relationship matching | |
CN112818689A (en) | Entity identification method, model training method and device | |
CN116304078A (en) | Legal case applicable legal condition recommendation method and device |
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 |