CN104243501B - Filtering and intercepting method for junk mail - Google Patents
Filtering and intercepting method for junk mail Download PDFInfo
- Publication number
- CN104243501B CN104243501B CN201410543038.3A CN201410543038A CN104243501B CN 104243501 B CN104243501 B CN 104243501B CN 201410543038 A CN201410543038 A CN 201410543038A CN 104243501 B CN104243501 B CN 104243501B
- Authority
- CN
- China
- Prior art keywords
- expression
- node
- user
- feature data
- 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
Links
Abstract
The invention relates to a filtering and intercepting method for junk mail. The method filters and recognizes the mail for multiple layers: obtaining the classification attribute of mail for the user according to the expression and/or phonetic feature data of the user for receiving and sending the mail; for the mail, which cannot be confirmed on category, orderly inquiring the black/white list of the user node local and friend node, the friend node is the network node having higher mail interaction frequency with the current user node; reminding the user for judging the category of the mail. By filtering and recognizing the mail for multiple layers, the problem of the prior art for recognizing the junk mail with larger cost and low efficiency can be solved.
Description
Technical field
The present invention relates to network communication field, more particularly to a kind of multi-level filtration hold-up interception method of spam.
Background technology
With the development of internet, applications, Email is widely used, it has also become Internet is upper most basic
One of service, user can carry out economy by Email and long-distance user, facilitate and efficiently communication for information.However, just
While Email is increasingly becoming a kind of indispensable important information media of communication, also becoming a kind of commercial advertisement
Means.User is while useful information is received, it is necessary to which taking a significant amount of time mails how various with energy is carried out point
Class is recognized, to filter " rubbish " mail, and existing mail classifying identification method or the more single classifying identification method of employing and
Cause result inaccurate, or time cost is improve using excessively complicated recognition method.Therefore, mail classification how is improved
The accuracy rate and efficiency of identification is the hot issue of current research.
At present conventional mail classifying identification method has many kinds.For example, based on SVM, decision tree, black and white lists, pattra leaves
This algorithm, fuzzy theory, intelligence computation, neutral net, inference technology, based on key word and rule-based filtering, taxonomy database, list
One user's discovery learning etc..
Although these methods are each to have respective advantage, each own different shortcoming, classification accuracy up to 80% by oneself
Left and right, can't meet actually used requirement.Due to the cost of unit Spam filtering it is larger, and generally accuracy rate
It is not high, and server is all given by Spam filtering task, and will substantially increase the resource overhead of server end.
Prior art is fruitful in terms of unit Spam filtering is processed.Nowadays, best Spam filtering tires out
Product moment mistake has been far below 1%.This seems to mean that people achieve triumph in the campaign of antagonism spam.But it is another
Outer one side, the investigation report issued over the years from international well-known release mechanism and China Internet association anti-rubbish mail center comes
See, from user perspective observation, although on the whole the amount of spam is remained incessant after repeated prohibition, cannot effected a radical cure in reduction, but panesthesia.Together
When, user is weak for existing anti-spam functionality at wire-speed to be discontented with, and occupies the head that all restriction users use network mailbox factor
Position.
By long-term research, prior art is fruitful in terms of unit Spam filtering is processed.But reflex in recent years
What miscellaneous network and community network aspect were studied carries out in a deep going way, and people generally guess that real world network all has uncalibrated visual servo and little generation
The characteristic on boundary, such as computer network, nervous system, transportation network, electric power networks, mail network, social relation network etc..
Why so big drop is had between existing present situation and Consumer's ExperienceThis should be attributed to conventional spam mistake
Filter technology considers the preventing and treating of spam from personal user's angle mostly, actually a kind of mutual between user so as to have ignored
Affect, co-operating relation and be bound up, and then show some similar characteristics.
There is the isolated node of many in network, and if if there is larger mail between two network user nodes
Interaction (receiving and dispatching mail) frequency, then mean there is higher homogeneity between the two user nodes.The rubbish postal that user receives
The part overwhelming majority transmits/receives part people before coming from from not in contact with the mail crossed；On the other hand, as mail transmits/receives the ripe of part people
Know or trusting degree increase, mail is that the probability of spam will be reduced rapidly.
Due to carrying out with user node, network ip address quantity that mail interacts is huger and continuous dynamic increases, comprehensive
Analyze proprietary mail interactive relation be it is impossible, also it is not necessary that.
The content of the invention
Present invention is primarily targeted at providing a kind of filtration hold-up interception method of spam, the method carries out many to mail
Individual level filters identification：First user's receiving and dispatching mail is obtained according to expression during user's receiving and dispatching mail and/or voice feature data
Categorical attribute；For the mail that cannot confirm classification, user node is inquired about successively locally and its black/white list of friend's node
List, friend's node refers to the network node with higher mail frequency of interaction between active user's node；Finally, may be used
Prompting user judges the classification of the mail.Intercepted by above-mentioned multi-level filtration, prior art can be solved for rubbish postal
Larger, the less efficient problem of the identification cost of part.
To achieve these goals, according to an aspect of the invention, there is provided a kind of filtration interception side of spam
Method, comprises the following steps：
Step 1, the expression and/or voice feature data during acquisition user's receiving and dispatching mail；And according to the expression and/or language
Sound characteristic obtains the categorical attribute of the mail of user's transmitting-receiving, and the categorical attribute includes：Normal email, spam and nothing
Method confirms；
If the categorical attribute for being obtained is normal email or spam, terminate classification, otherwise execution step 2；
Step 2, inquires about the local blacklist list of user node and white list list, to determine the type of current mail.
Further, if the address of the mail of user's transmitting-receiving is not in the local blacklist list of user node and white name
In single-row table, then following steps are performed：
Step 3, user node to all friend's nodes send an inquiry request, and the inquiry request includes current mail
Address information；
Step 4, friend's node searches for blacklist list and the white list list of oneself according to the inquiry request, if sent out
Blacklist list or white list list are now hit, then returns Query Result to the user node, the Query Result represents the postal
The type of part is spam or normal email；
If the Query Result of friend's node return is received, and the email type phase represented by all of Query Result
Together, then execution step 5；Otherwise, execution step 6；
Step 5, user node is according to the local blacklist list of Query Result renewal or white list list；
Step 6, points out user to judge the classification of the mail；
Wherein, friend's node is selected from the network node for having mail to interact between active user's node；
Wherein, friend's node refers to the network section with higher mail frequency of interaction between active user's node
Point.
Further, the locally stored of each node has friend's node listing in network, and the list includes N number of friend
Friendly address of node and degree of association score value, the calculation of the degree of association score value is：
Degree of association score value=(blacklist or white list inquiry are returned in the mail interaction times+B* cycle Ts in A* cycle Ts
As a result number of times)/T；
Wherein, quantity N of coefficient A, B, cycle T and friend's node both can be constant, it is also possible to by default and root
According to being actually needed dynamic adjustment.
Further, the initialization procedure of friend's node listing is：
To be ranked up from high to low according to mail interaction times with the network node for locally having mail to interact, selected and sorted
As a result the top n node in as friend's node, to set up initial friend's node listing；Wherein, the degree of association score value
Initial value is all 0.
Further, the renewal process of friend's node listing is：
At interval of fixed cycle T, calculate in current cycle T with each network node for locally having mail to interact
Degree of association score value, is ranked up according to degree of association score value from high to low, and the top n node in selected and sorted result is saved as friend
Point, so as to update friend's node listing.
Further, quantity N of the coefficient A, B, cycle T and friend's node can be：A=10, B=20, T=24
(hour), N=50.
Further, the expressive features data include：Eye position information, eye shape information, eyebrow positional information,
Eyebrow shape information, face positional information and face shape information；
The voice feature data includes：Tone information, word speed information and filterability key word.
Further, the mail of user's transmitting-receiving is obtained according to the expression and/or voice feature data in the step 1
Categorical attribute includes：
Match with the expression and/or voice feature data from default expression and/or voice feature data library lookup
Default expression and/or voice feature data；
When finding out, the expression and/or voice feature data are default with first to express one's feelings and/or voice feature data phase
Timing, determines that the expression and/or the corresponding expression of voice feature data and/or speech data are the first expression and/or voice
Data, and determine that the type of the mail of user transmitting-receiving is the first kind, wherein, the described first default expression and/or voice
Characteristic be it is described it is default expression and/or voice feature data storehouse in arbitrary expression and/or voice feature data, it is described pre-
If also storing the corresponding relation of espressiove and/or voice feature data and email type in expression and/or voice feature data storehouse；
And
When finding out, the expression and/or voice feature data are default with second to express one's feelings and/or voice feature data phase
Timing, determines that the expression and/or the corresponding expression of voice feature data and/or speech data are the second expression and/or voice
Data, and determine that the type of the mail of user transmitting-receiving is Second Type, wherein, the described second default expression and/or voice
Characteristic is the default expression and/or arbitrary expression and/or voice feature data in voice feature data storehouse, and institute
It is different tables that the second default expression and/or voice feature data are stated from the described first default expression and/or voice feature data
Feelings and/or voice feature data.
Further, it is determined that the user transmitting-receiving mail type be Second Type after, also include：
The priority of comparison first expression and/or speech data and second expression and/or speech data；
The priority of first expression and/or speech data is being compared higher than the described second expression and/or voice number
According to priority when, the mail for controlling the first kind is arranged in before the mail of the Second Type；And
The priority of first expression and/or speech data is being compared less than the described second expression and/or voice number
According to priority when, the mail for controlling the first kind is arranged in after the mail of the Second Type.
Further, in the more described first expression and/or speech data and second expression and/or speech data
Before priority, also include：
Receive the setting instruction of the user；And
First expression and/or speech data and second expression and/or voice are determined according to the setting instruction
The priority of data.
The filtration hold-up interception method of the spam of the present invention is capable of achieving following beneficial effect：
First, by obtaining expression and/or voice feature data during user's receiving and dispatching mail；And according to expression and/or
Voice feature data is classified to the mail that user receives and dispatches.
In general, when user processes mail, emotion often changes because of Mail Contents, or itself has located
In a kind of emotion, different emotions can cause the expressive features data of user different, by expression during user's receiving and dispatching mail
Characteristic is obtained, and then mail is classified based on the expressive features data for getting, due to user it is right to oneself
Emotional memory when processing mail is more deep, thus can be by the expressive features data corresponding with emotion quickly to postal
Part preliminary classification.
Simultaneously for some spams (such as advertisement), or some strange voices are frequently included, or existed very
The voice of many business marketing terms, sensitive word or other set forms, or have more stable due to formatting recording
Word speed and intonation, and these are often easier to identification of classifying.
By expression and/or speech recognition, the Classification and Identification time can be shortened, to realize that the preliminary classification of mail is recognized.
Second, due to based on the more frequently representational friend's node that communicates with local node, will also tend to receive simultaneously
To the characteristic of similar spam and/or normal email, by means of concurrently inquiring about the black, white of these friend's nodes in a network
List list, can rapidly filter out spam and/or normal email, can greatly simplify local Analysis and Screening work
Make.
3rd, the degree of association score value between friend's node and user's local node, both can be embodied in certain time it
Between communication frequency, and the hit probability of black white list list can be embodied.By comprehensive two above factor, can be dynamically determined
The optimal friend's node listing of the degree of association.
4th, for the mail for being finally beyond recognition classification, point out local user to be distinguished, can so prevent rubbish
The missing inspection of mail or the erroneous judgement of normal email.
Description of the drawings
The accompanying drawing for constituting the part of the application is used for providing a further understanding of the present invention, the schematic reality of the present invention
Apply example and its illustrate, for explaining the present invention, not constituting inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is the flow chart of the filtration hold-up interception method of spam according to embodiments of the present invention.
Fig. 2 is the structure of friend's node listing according to embodiments of the present invention.
Specific embodiment
It should be noted that in the case where not conflicting, the feature in embodiment and embodiment in the application can phase
Mutually combination.Below with reference to the accompanying drawings and in conjunction with the embodiments describing the present invention in detail.
The embodiment provides a kind of filtration hold-up interception method of spam, is carried below to the embodiment of the present invention
For the filtration hold-up interception method of spam be specifically introduced：
Fig. 1 is the flow chart of the filtration hold-up interception method of spam according to embodiments of the present invention.As shown in figure 1, the party
Method includes the steps：
Step 1, the expression and/or voice feature data during acquisition user's receiving and dispatching mail；And according to the expression and/or language
Sound characteristic obtains the categorical attribute of the mail of user's transmitting-receiving, and the categorical attribute includes：Normal email, spam and nothing
Method confirms；
If the categorical attribute for being obtained is normal email or spam, terminate classification, otherwise execution step 2；
Step 2, inquires about the local blacklist list of user node and white list list, to determine the type of current mail.
If the local blacklist list of miss user node or white list list, following steps 3-5 are performed：
Step 3, user node to all friend's nodes send an inquiry request, and the inquiry request includes current mail
Address information；
Step 4, friend's node searches for blacklist list and the white list list of oneself according to the inquiry request, if sent out
Blacklist list or white list list are now hit, then returns Query Result to the user node, the Query Result represents the postal
The type of part is spam or normal email；
If the Query Result of friend's node return is received, and the email type phase represented by all of Query Result
Together, then execution step 5；Otherwise, execution step 6；
Step 5, user node is according to the local blacklist list of Query Result renewal or white list list；
Step 6, points out user to judge the classification of the mail；
Wherein, friend's node is selected from the network node for having mail to interact between active user's node；
Wherein, friend's node refers to the network section with higher mail frequency of interaction between active user's node
Point.
Because the cost of unit Spam filtering is larger, and generally accuracy rate is not high, and Spam filtering is appointed
Server is all given in business, and will substantially increase the expense of server end.Therefore, the Spam filtering hold-up interception method of the application
Concurrent type frog collaborative filtering analysis will be carried out using the other users node in network with local interaction.
There is the isolated node of many in network, and if if there is larger mail between two network user nodes
Interaction (receiving and dispatching mail) frequency, then mean there is higher homogeneity between the two user nodes.In this application, will with
The network node with higher mail frequency of interaction is referred to as " friend's node " (for example, same company between the node of family
Multiple user nodes).Due to having roughly the same statistical property between friend's node, then obviously interacted based on mail
The Network Synchronization concurrent type frog Cooperative Analysis of frequency can comparatively fast and relatively easily provide the classification suggestion with regard to local mail, due to
This Cooperative Analysis are that network concurrent is collaborative, therefore efficiency is higher, and will not increase the computational burden of local node.
The local blacklist list that is all stored with of all nodes (including local node, all friend's nodes) in network
With a white list list.Local node can inquire about its blacklist list and white list list；The all of friend of local node
Node can ask local node to inquire about blacklist list and the white list list of the local node, and return Query Result.Its
In, the blacklist list includes the address of spam, and white list list includes the address of normal email.Black, white name
The initial value of single-row table can be obtained by cloud server, it is possible to real-time update.
Meanwhile, the locally stored of all nodes (including local node, all friend's nodes) has friend's section in network
Point list.
In practice, due to based on the more frequently representational friend's node that communicates with local node, will also tend to simultaneously
Receive the characteristic of similar spam and/or normal email, therefore by means of concurrently inquiring about these friend's nodes in a network
Black, white list list, can rapidly filter out spam and/or normal email, local analysis can be greatly simplified
Screening operation.
Fig. 2 is the structure of friend's node listing according to embodiments of the present invention.As shown in Fig. 2 friend's node listing
Including N number of friend address of node and degree of association score value.
During initialization, the value of all of degree of association score value is all 0, and friend's node listing updates once at interval of cycle T.
The initialization of friend's node listing and renewal process are as follows：
A. initialize：With locally there is mail the network node of (sending and receiving mail) will be interacted according to mail interaction times from height
Be ranked up to low, the top n node in selected and sorted result as friend's node, to set up initial friend's node listing.
Wherein, quantity N of cycle T and friend's node both can be constant, it is also possible to by default and according to actual need
Will dynamic adjustment.
B. update：At interval of fixed cycle T, calculating interacts (sending and receiving postal in current cycle T with locally there is mail
Part) each network node degree of association score value, be ranked up from high to low according to degree of association score value, in selected and sorted result
Top n node as friend's node, so as to update friend's node listing；The calculation of the degree of association score value is as follows：
Degree of association score value=(blacklist or white list inquiry are returned in the mail interaction times+B* cycle Ts in A* cycle Ts
As a result number of times)/T；
Wherein, quantity N of coefficient A, B, cycle T and friend's node both can be constant；Can also be by default and root
According to dynamic adjustment is actually needed, for example, can select：
A=10, B=20, T=24 (hour), N=50.
In a preferred embodiment of the invention, by obtaining expression and/or voice feature data during user's receiving and dispatching mail；
And preliminary classification is carried out to the mail that user receives and dispatches according to expression and/or voice feature data.
In general, when user processes mail, emotion often changes because of Mail Contents, or itself has located
In a kind of emotion, different emotions can cause the expression of user and/or voice feature data different, by user's receiving and dispatching mail
When expression and/or voice feature data obtained, then based on the expression and/or voice feature data for getting to mail
Classified, due to user it is more deep to emotional memory when processing mail to oneself, thus can be by relative with emotion
The expression answered and/or voice feature data are quickly to mail preliminary classification.
Simultaneously for some spams (such as advertisement), or some strange voices are frequently included, or existed very
The voice of many business marketing terms, sensitive word or other set forms, and these are often easier to identification of classifying.
By expression and/or speech recognition, the Classification and Identification time can be shortened.
In a preferred embodiment of the invention, the expressive features data can include：Eye position information, eye shape
Information, eyebrow positional information, eyebrow shape information, face positional information and face shape information etc. are relatively easy the expression of identification
Characteristic；
The voice feature data may include：Tone information, word speed information, filterability key word etc..
Wherein, the categorical attribute of the mail of user's transmitting-receiving is obtained according to the expression and/or voice feature data to be included：
After the expression and/or voice feature data that get user, from default expression and/or voice feature data storehouse
Search the default expression and/or voice feature data matched with the expression and/or voice feature data；Wherein, it is described pre-
If being stored with and the type information expressed one's feelings and/or voice feature data is corresponding in expression and/or voice feature data storehouse；
When finding out, the expression and/or voice feature data are default with first to express one's feelings and/or voice feature data phase
Timing, determines that the expression and/or the corresponding expression of voice feature data and/or speech data are the first expression and/or voice
Data, and determine that the type of the mail of user transmitting-receiving is the first kind, wherein, the described first default expression and/or voice
Characteristic be it is described it is default expression and/or voice feature data storehouse in arbitrary expression and/or voice feature data, it is described pre-
If also storing the corresponding relation of espressiove and/or voice feature data and email type in expression and/or voice feature data storehouse；
And
When finding out, the expression and/or voice feature data are default with second to express one's feelings and/or voice feature data phase
Timing, determines that the expression and/or the corresponding expression of voice feature data and/or speech data are the second expression and/or voice
Data, and determine that the type of the mail of user transmitting-receiving is Second Type, wherein, the described second default expression and/or voice
Characteristic is the default expression and/or arbitrary expression and/or voice feature data in voice feature data storehouse, and institute
It is different tables that the second default expression and/or voice feature data are stated from the described first default expression and/or voice feature data
Feelings and/or voice feature data.
Wherein, it is determined that the user transmitting-receiving mail type be Second Type after, also include：
The priority of comparison first expression and/or speech data and second expression and/or speech data；
The priority of first expression and/or speech data is being compared higher than the described second expression and/or voice number
According to priority when, the mail for controlling the first kind is arranged in before the mail of the Second Type；And
The priority of first expression and/or speech data is being compared less than the described second expression and/or voice number
According to priority when, the mail for controlling the first kind is arranged in after the mail of the Second Type.
Wherein, more described first expression and/or speech data and it is described second expression and/or speech data it is preferential
Before level, also include：
Receive the setting instruction of the user；And
First expression and/or speech data and second expression and/or voice are determined according to the setting instruction
The priority of data.
In a preferred embodiment of the invention, the expressive features data of user are obtained mainly by existing recognition of face skill
Art (such as regional characteristics analysis algorithm) being matched, using built skin detection and the user for getting expression
Characteristic carries out feature analysiss, according to the result of analysis providing a similar value, by this value can be determined whether for
User-defined certain expression.
In a preferred embodiment of the invention, the voice feature data of user is obtained mainly by existing speech recognition skill
Art carries out feature analysiss being matched using built phonetic feature template with the user vocal feature data for getting,
One similar value is provided according to the result of analysis, be can be determined whether as user-defined certain voice by this value；Separately
Outward, if making by oneself comprising some common filtration sensitive words, commercial advertisement publicity vocabulary, and some other users in mail
Adopted filterability term and vocabulary, can Classification and Identification be spam.
In a preferred embodiment of the invention, because the definition and identification of respective emotion between different user have many complexity
And diversity, different people may express one's feelings and/or voice performance and actual emotion between have very big difference.It is of the invention preferred real
In applying example, user can extract the current table of user in self-defined expression and/or voice feature data by camera/microphone
The characteristic information of feelings and/or voice, and express one's feelings and/or the corresponding expression of voice and/or phonetic feature mail while arranging these,
Realize that fast and easily self-defined setting is expressed one's feelings and/or voice feature data.Guiding user oneself definition expression and/or voice are special
When levying data, user can be guided for different expressions and/or voice feature data and distribute a unique ID, such as to open
The expression and/or voice feature data shown respectively under the various emotions such as the heart, sad, excited, detest, doubt is correspondingly arranged one
Individual unique ID.
In a preferred embodiment of the invention, it is allowed to which setting of the user to expression and/or voice feature data can be advance
Arranged by User Defined, it is also possible to arrange in procedure below：When user's receiving and dispatching mail, to user's expression now and/
Or voice feature data is obtained in real time, and inquiry presets expression and/or voice feature data storehouse to obtain and get
Expression and/or the corresponding default expression of voice feature data and/or voice feature data, and then determine that user is now received and dispatched
The type of mail be type corresponding to the default expression and/or voice feature data for finding.
But, when not finding and the expression and/or language for currently getting in default expression and/or voice feature data storehouse
If the corresponding default expression of sound characteristic and/or voice feature data, then illustrate user also not to current this expression
And/or voice feature data is defined, now the categorical attribute in step 1 is to confirm, i.e., special in expression and/or voice
After the step of levying Classification and Identification, if the categorical attribute that not can determine that mail is normal email or spam, need
Classification and Identification is proceeded to these mails that cannot be confirmed by building grader.
The preferred embodiments of the present invention are the foregoing is only, the present invention is not limited to, for the skill of this area
For art personnel, the present invention can have various modifications and variations.It is all within the spirit and principles in the present invention, made any repair
Change, equivalent, improvement etc., should be included within the scope of the present invention.
Claims (1)
1. the filtration hold-up interception method of a kind of spam, it is characterised in that the method is comprised the following steps：
Step 1, the expression and/or voice feature data during acquisition user's receiving and dispatching mail；And it is special according to the expression and/or voice
The categorical attribute that data obtain the mail of user's transmitting-receiving is levied, the categorical attribute includes：Normal email, spam and cannot be true
Recognize；
If the categorical attribute for being obtained is normal email or spam, terminate classification, otherwise execution step 2；
Step 2, inquires about the local blacklist list of user node and white list list, to determine the type of current mail；
If the address of the mail of user's transmitting-receiving is held not in the local blacklist list of user node and white list list
Row step 3- step 6：
Step 3, user node to all friend's nodes send an inquiry request, ground of the inquiry request comprising current mail
Location information；
Step 4, friend's node searches for blacklist list and the white list list of oneself according to the inquiry request, if it find that life
Middle blacklist list or white list list, then return Query Result to the user node, and the Query Result represents the mail
Type is spam or normal email；
If the Query Result of friend's node return is received, and the email type represented by all of Query Result is identical, then
Execution step 5；Otherwise, execution step 6；
Step 5, user node is according to the local blacklist list of Query Result renewal or white list list；
Step 6, points out user to judge the classification of the mail；
Wherein, friend's node refers to the network node with higher mail frequency of interaction between active user's node；
The locally stored of each node has friend's node listing in network, and the list includes N number of friend address of node
With degree of association score value, the calculation of the degree of association score value is：
Degree of association score value=(blacklist or white list Query Result are returned in the mail interaction times+B* cycle Ts in A* cycle Ts
Number of times)/T；
Wherein, quantity N of coefficient A, B, cycle T and friend's node both can be constant, it is also possible to by default and according to reality
Border needs dynamic adjustment；
The initialization procedure of friend's node listing is：Will be secondary according to mail interaction with the network node for locally having mail to interact
Number be ranked up from high to low, the top n node in selected and sorted result as friend's node, to set up initial friend's node
List；Wherein, the initial value of the degree of association score value is all 0；
The renewal process of friend's node listing is：At interval of fixed cycle T, calculate in current cycle T with it is local
There is the degree of association score value of each network node of mail interaction, be ranked up from high to low according to degree of association score value, selected and sorted
As a result the top n node in as friend's node, so as to update friend's node listing；
Quantity N of the coefficient A, B, cycle T and friend's node can be：A=10, B=20, T=24, N=50；
The expressive features data include：Eye position information, eye shape information, eyebrow positional information, eyebrow shape information,
Face positional information and face shape information；
The voice feature data includes：Tone information, word speed information and filterability key word；
Obtaining the categorical attribute of the mail of user's transmitting-receiving in the step 1 according to the expression and/or voice feature data includes：
It is default with what the expression and/or voice feature data matched from default expression and/or voice feature data library lookup
Expression and/or voice feature data；
When the expression and/or voice feature data and the first default expression is found out and/or voice feature data matches,
Determine that the expression and/or the corresponding expression of voice feature data and/or speech data are expressed one's feelings and/or speech data for first,
And determine that the type of the mail of user transmitting-receiving is the first kind, wherein, the described first default expression and/or phonetic feature number
According to for it is described it is default expression and/or voice feature data storehouse in arbitrary expression and/or voice feature data, the default expression
And/or also store the corresponding relation of espressiove and/or voice feature data and email type in voice feature data storehouse；And
When the expression and/or voice feature data and the second default expression is found out and/or voice feature data matches,
Determine that the expression and/or the corresponding expression of voice feature data and/or speech data are expressed one's feelings and/or speech data for second,
And determine that the type of the mail of user transmitting-receiving is Second Type, wherein, the described second default expression and/or phonetic feature number
According to for the default expression and/or arbitrary expression and/or voice feature data in voice feature data storehouse, and described second
Default expression and/or voice feature data and the described first default expression and/or voice feature data be different expression and/or
Voice feature data；
It is determined that the user transmitting-receiving mail type be Second Type after, also include：
The priority of comparison first expression and/or speech data and second expression and/or speech data；
It is higher than the described second expression and/or speech data in the priority for comparing first expression and/or speech data
During priority, the mail for controlling the first kind is arranged in before the mail of the Second Type；And
The priority of first expression and/or speech data is being compared less than the described second expression and/or speech data
During priority, the mail for controlling the first kind is arranged in after the mail of the Second Type；
Before the priority of the more described first expression and/or speech data and second expression and/or speech data, also
Including：
Receive the setting instruction of the user；And
First expression and/or speech data and second expression and/or speech data are determined according to the setting instruction
Priority.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410543038.3A CN104243501B (en) | 2014-10-14 | 2014-10-14 | Filtering and intercepting method for junk mail |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410543038.3A CN104243501B (en) | 2014-10-14 | 2014-10-14 | Filtering and intercepting method for junk mail |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104243501A CN104243501A (en) | 2014-12-24 |
| CN104243501B true CN104243501B (en) | 2017-04-12 |
Family
ID=52230850
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410543038.3A Active CN104243501B (en) | 2014-10-14 | 2014-10-14 | Filtering and intercepting method for junk mail |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104243501B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108710606B (en) * | 2018-04-09 | 2021-10-26 | 平安科技（深圳）有限公司 | Task progress monitoring method, computer readable storage medium and terminal equipment |
| CN108766416B (en) * | 2018-04-26 | 2021-06-25 | Oppo广东移动通信有限公司 | Speech recognition method and related product |
| CN109523241A (en) * | 2018-12-13 | 2019-03-26 | 杭州安恒信息技术股份有限公司 | A kind of E-mail communication method for limiting and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999067731A1 (en) * | 1998-06-23 | 1999-12-29 | Microsoft Corporation | A technique which utilizes a probabilistic classifier to detect 'junk' e-mail |
| CN101026593A (en) * | 2006-02-23 | 2007-08-29 | 腾讯科技（深圳）有限公司 | Anti-spam method and system |
| CN101166159A (en) * | 2006-10-18 | 2008-04-23 | 阿里巴巴公司 | A method and system for identifying rubbish information |
| CN101262524A (en) * | 2008-04-23 | 2008-09-10 | 沈阳东软软件股份有限公司 | Rubbish voice filtration method and system |
| CN103812826A (en) * | 2012-11-08 | 2014-05-21 | 中国电信股份有限公司 | Identification method, identification system, and filter system of spam mail |
-
2014
- 2014-10-14 CN CN201410543038.3A patent/CN104243501B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1999067731A1 (en) * | 1998-06-23 | 1999-12-29 | Microsoft Corporation | A technique which utilizes a probabilistic classifier to detect 'junk' e-mail |
| CN101026593A (en) * | 2006-02-23 | 2007-08-29 | 腾讯科技（深圳）有限公司 | Anti-spam method and system |
| CN101166159A (en) * | 2006-10-18 | 2008-04-23 | 阿里巴巴公司 | A method and system for identifying rubbish information |
| CN101262524A (en) * | 2008-04-23 | 2008-09-10 | 沈阳东软软件股份有限公司 | Rubbish voice filtration method and system |
| CN103812826A (en) * | 2012-11-08 | 2014-05-21 | 中国电信股份有限公司 | Identification method, identification system, and filter system of spam mail |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104243501A (en) | 2014-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105487663B (en) | A kind of intension recognizing method and system towards intelligent robot | |
| CN107329967B (en) | Question answering system and method based on deep learning | |
| CN103458056B (en) | Speech intention judging system based on automatic classification technology for automatic outbound system | |
| CN106095833B (en) | Human-computer dialogue content processing method | |
| CN103680497B (en) | Speech recognition system and method based on video | |
| Rosenfeld et al. | NegoChat: a chat-based negotiation agent. | |
| CN105808590B (en) | Search engine implementation method, searching method and device | |
| CN110138982A (en) | Service based on artificial intelligence is realized | |
| CN102866990A (en) | Thematic conversation method and device | |
| CN107240398A (en) | Intelligent sound exchange method and device | |
| CN107146610A (en) | A kind of determination method and device of user view | |
| CN104254852A (en) | Method and system for hybrid information query | |
| CN107368572A (en) | Multifunctional intellectual man-machine interaction method and system | |
| CN106294854A (en) | A kind of man-machine interaction method for intelligent robot and device | |
| CN109885761A (en) | A kind of position of human resources enterprise and talent's matching and recommended method | |
| KR20090074108A (en) | Method for recommending contents with context awareness | |
| CN108228559A (en) | A kind of human-computer interaction realization method and system for customer service | |
| CN104243501B (en) | Filtering and intercepting method for junk mail | |
| CN106230689A (en) | Method, device and the server that a kind of voice messaging is mutual | |
| CN108074571A (en) | Sound control method, system and the storage medium of augmented reality equipment | |
| CN110019742A (en) | Method and apparatus for handling information | |
| CN110362753A (en) | A kind of personalized neural network recommendation method and system based on user concealed feedback | |
| CN110597987A (en) | Search recommendation method and device | |
| CN114331512A (en) | Method for modeling visual data and portraying big data | |
| CN105354343B (en) | User characteristics method for digging based on remote dialogue |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230613 Address after: F13, Building 11, Zone D, New Economic Industrial Park, No. 99, West Section of Hupan Road, Xinglong Street, Tianfu New District, Chengdu, Sichuan, 610000 Patentee after: Sichuan Shenhu Technology Co.,Ltd. Address before: 610041 No. 5, floor 1, unit 1, building 19, No. 177, middle section of Tianfu Avenue, high tech Zone, Chengdu, Sichuan Province Patentee before: SICHUAN CINGHOO TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |