CN106777341A - Information processing method, device and computer equipment - Google Patents
Information processing method, device and computer equipment Download PDFInfo
- Publication number
- CN106777341A CN106777341A CN201710026441.2A CN201710026441A CN106777341A CN 106777341 A CN106777341 A CN 106777341A CN 201710026441 A CN201710026441 A CN 201710026441A CN 106777341 A CN106777341 A CN 106777341A
- Authority
- CN
- China
- Prior art keywords
- comment
- queue
- user
- user comment
- information
- 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.)
- Pending
Links
Classifications
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
Abstract
The invention discloses a kind of information processing method, device and computer equipment.Described information processing method includes:Obtain user comment, and comment queue is traveled through, whether the number of reviews same or similar with the user comment reaches first threshold in judging the comment queue, wherein the comment queue is fifo queue and length has Second Threshold, if so, user comment then is defined as into comment spam;If it is not, user comment then is added into comment queue, and the comment of the tail of the queue of the fifo queue is processed according to the Second Threshold.The embodiment of the present invention can effectively identify comment spam, and when user comment is identified as non-junk comment, it is only necessary to update comment queue, it is to avoid all the elements in database are processed, mitigate system operation burden, improve information processing efficiency.
Description
Technical field
The present invention relates to communication technical field, more particularly to Internet technical field, and in particular to a kind of information processing side
Method, device and computer equipment.
Background technology
With the development of Internet technology, user can be various public flat in each forum, community, website etc. by network
Related commentary is delivered on platform.However, the speech based on common platform is open, certain customers are commented by by advertising commentary, distribution
By, other contain it is dysgenic comment etc. comment spam be largely published on common platform, user is influenceed to useful letter with this
The acquisition of breath, and bring harmful effect to user.Existing computer equipment is during use, and comment spam is more next
How more puzzlement effectively recognizes comment spam increasingly by the common concern of industry to user.
The content of the invention
The embodiment of the present invention provides a kind of information processing method, device and computer equipment, can improve information processing effect
Rate.
The embodiment of the present invention provides a kind of information processing method, and methods described includes:
Obtain user comment;
Traversal comment queue, judge it is described comment on queue in the number of reviews same or similar with the user comment be
It is no to reach first threshold, wherein the comment queue is fifo queue and length has Second Threshold;
If so, the user comment then is defined as into comment spam;
If it is not, the user comment is then added into comment queue, and according to the Second Threshold to the first in first out team
The tail of the queue comment of row is processed.
The embodiment of the present invention also provides a kind of information processor, and described device includes:
Acquisition module, for obtaining user comment;
First judge module, for travel through comment queue, judge it is described comment on queue in it is identical with the user comment or
Whether the similar number of reviews of person reaches first threshold, wherein the comment queue is that fifo queue and length have second
Threshold value;
Determining module, for same or similar with user comment number of reviews in the comment queue is judged
When reaching first threshold, the user comment is defined as comment spam;
Processing module, for same or similar with user comment number of reviews in the comment queue is judged
Not up to first threshold when, the user comment is added into comment queue, and according to the Second Threshold to the first in first out
The tail of the queue comment of queue is processed.
The embodiment of the present invention also provides a kind of computer equipment, including memory, and processor and storage are on a memory simultaneously
The computer program that can be run on the processor, wherein, the processor calls the meter stored in the memory
Calculation machine program, performs the information processing method described in any embodiment of the present invention.
Brief description of the drawings
Below in conjunction with the accompanying drawings, described in detail by specific embodiment of the invention, technical scheme will be made
And other beneficial effects are apparent.
Fig. 1 is a kind of schematic flow sheet of information processing method provided in an embodiment of the present invention.
Fig. 2 is a kind of the first use state schematic diagram of information processing method provided in an embodiment of the present invention.
Fig. 3 is a kind of the second use state schematic diagram of information processing method provided in an embodiment of the present invention.
Fig. 4 is a kind of another schematic flow sheet of information processing method provided in an embodiment of the present invention.
Fig. 5 is a kind of the 3rd use state schematic diagram of information processing method provided in an embodiment of the present invention.
Fig. 6 is a kind of the 4th use state schematic diagram of information processing method provided in an embodiment of the present invention.
Fig. 7 is a kind of structural representation of information processor provided in an embodiment of the present invention.
Fig. 8 is a kind of another structural representation of information processor provided in an embodiment of the present invention.
Fig. 9 is a kind of structural representation of computer equipment provided in an embodiment of the present invention.
Specific 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 is described.It is understood that specific embodiment described herein is only used for explaining the present invention, rather than to limit of the invention
It is fixed.It also should be noted that, for the ease of description, illustrate only part related to the present invention in accompanying drawing and not all knot
Structure.Based on the embodiment in the present invention, what those of ordinary skill in the art were obtained under the premise of creative work is not made
Every other embodiment, belongs to the scope of protection of the invention.
Term " first ", " second " and " the 3rd " in the present invention etc. is for distinguishing different objects, rather than for retouching
State particular order.Additionally, term " comprising " and " having " and their any deformations, it is intended that covering is non-exclusive to be included.
For example contain series of steps or module process, method, system, product or equipment be not limited to the step of having listed or
Module, but alternatively also include the step of not listing or module, or alternatively also include for these processes, method, product
Product or equipment intrinsic other steps or module.
Referenced herein " embodiment " is it is meant that the special characteristic, structure or the characteristic that describe can be wrapped in conjunction with the embodiments
Containing at least one embodiment of the present invention.Each position in the description occur the phrase might not each mean it is identical
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
A kind of executive agent of information processing method provided in an embodiment of the present invention, can be provided in an embodiment of the present invention
A kind of information processor, or be integrated with described information processing unit computer equipment (for example desktop computer, notebook,
Palm PC, panel computer, smart mobile phone etc.), described information processing unit can be realized by the way of hardware or software.
Fig. 1 is referred to, Fig. 1 is a kind of schematic flow sheet of information processing method provided in an embodiment of the present invention.The side
Method includes:
Step S101, obtains user comment.
Step S102, traversal comment queue, judge it is described comment on queue in it is same or similar with the user comment
Whether number of reviews reaches first threshold, wherein it is described comment queue be fifo queue and
Length has Second Threshold;If it is not, then performing step S103;If so, then performing step S104.
In some implementation methods, can be by judging the similarity present in the comment queue with the user comment
Reach the historical review of the 3rd threshold value number of reviews whether reach first threshold judge it is described comment queue in the use
Family comments on whether same or similar number of reviews reaches first threshold.When judge it is described comment queue present in it is described
The similarity of user comment reach the number of reviews of the historical review of the 3rd threshold value not up to first threshold when, determine the comment
The number of reviews same or similar with the user comment is not up to first threshold in queue, then perform step S103.When sentencing
The number of reviews of the historical review of the 3rd threshold value is reached present in the disconnected comment queue with the similarity of the user comment
When reaching first threshold, the number of reviews same or similar with the user comment reaches first in determining the comment queue
Threshold value, then perform step S104.
Step S103, comment queue is added by the user comment, and according to the Second Threshold to the comment queue
Tail of the queue comment processed.
In some implementation methods, the user comment can be added the comment queue to be commented on as head of the queue, and will overflow
The tail of the queue comment for going out the Second Threshold is deleted.
Step S104, comment spam is defined as by the user comment.
In order to be even further appreciated that technical solution of the present invention, it is provided in an embodiment of the present invention to refer to Fig. 2 and Fig. 3, Fig. 2
A kind of first use state schematic diagram of information processing method, Fig. 3 is a kind of information processing method provided in an embodiment of the present invention
The second use state schematic diagram.
As shown in Fig. 2 in a certain forum, " tiger that can fly " has delivered the text of entitled " sensor in mobile phone "
Chapter, it is the user comment of " striving for carrying out a haze sensor again early " that user's " code agriculture " submits content in the forum.The forum
Server traversal comment queue, judge it is described comment on queue in the number of reviews same or similar with the user comment be
It is no to reach first threshold;If the user comment then is defined as into comment spam;If otherwise the user comment is defined as
Non-junk is commented on, then the user comment is added into comment queue, and according to the Second Threshold to the fifo queue
Tail of the queue comment processed.
For example, the comment queue is that fifo queue and length have 1000.
As shown in figure 3, when the user comment is defined as non-junk comment, comment queue is updated, will be described
User comment " strive for come again early haze a sensor " added in the comment queue as the head of the queue commented on shown by area
Comment, and the tail of the queue comment of the time of comment is earliest and the 1000th article of spilling " seeks formaldehyde sensor." deleted.
The embodiment of the present invention travels through comment queue by obtaining user comment, judge it is described comment queue in it is described
Whether the same or similar number of reviews of user comment reaches first threshold, wherein the comment queue is fifo queue
And length has Second Threshold, if so, the user comment then is defined as into comment spam;If it is not, then by the user comment
Comment queue is added, and the comment of the tail of the queue of the fifo queue is processed according to the Second Threshold.It is of the invention real
Applying example can effectively identify comment spam, and when user comment is identified as non-junk comment, it is only necessary to comment queue is updated,
Avoid processing all the elements in database, mitigate system operation burden, effectively improve information processing efficiency.
In some implementation methods, after the acquisition user comment, also include:
The comment information in the user comment is judged with the presence or absence of in blacklist storehouse, if then that the user comment is true
It is set to comment spam.
In some implementation methods, the comment information judged in the user comment is wrapped with the presence or absence of in blacklist storehouse
Include:
Judge whether include the information matched with the characteristic information in blacklist storehouse in the user comment, if then
The user comment is defined as comment spam.
In some implementation methods, when the user comment is defined as comment spam, detect in the user comment whether
Containing contact method, if then the contact method is added in blacklist storehouse as characteristic information.
In some implementation methods, the comment similar to the user comment includes the similarity with the user comment
Reach the historical review of the 3rd threshold value.
Above-mentioned all optional technical schemes, can form alternative embodiment of the invention, herein no longer using any combination
Repeat one by one.
Fig. 4 is referred to, Fig. 4 is a kind of another schematic flow sheet of information processing method provided in an embodiment of the present invention.Institute
The method of stating includes:
Step S201, obtains user comment.
For example, as shown in Fig. 2 in a certain forum, " tiger that can fly " has delivered entitled " sensor in mobile phone "
Article, it is the user comment of " strive for come again early haze a sensor " that user's " code agriculture " submits content in the forum, this
The server of forum gets the user comment from backstage.
Step S202, judges the comment information in the user comment with the presence or absence of in blacklist storehouse.If it is not, then performing step
Rapid S203;If so, then performing step S205.
It is understood that comment information in the user comment can include user name, ID, comment content,
The information such as comment issuing time.
In some implementation methods, judge whether include and the characteristic information phase in blacklist storehouse in the user comment
The information matched somebody with somebody.If so, then performing step S205;If it is not, then performing step S203.
At present, many common platforms support the mutual-action behavior between user, and the form of expression of the common platform can be wrapped
Include e-commerce platform, forum, community, website, microblogging, mhkc, blog, using download platform etc..Such as, when user is in website
It is upper registration and by certification after, possess the subscriber identity information of the website, the user as the website, user can be in website
Middle its user behavior of displaying, for example, issue article, release product, send out microblogging, post, reply comment etc., can also be to other hairs
The information of cloth is commented on, thumb up etc..For above-mentioned comment content, it is same or like that certain user may issue a large amount of contents
Comment spam, such as advertising commentary, promote comment, contain the bad shadow such as reaction, violence, pornographic, hyperlink, abuse, calumny
Loud comment.
It is understood that blacklist storehouse can be pre-set, multiple characteristic informations are included in the blacklist storehouse.
In some implementation methods, the characteristic information includes user name, ID, contact method, keyword, keyword
In partials any one or it is various.
It is understood that the form of the contact method can be the combination of letter and number, length is more than 7 words
Section.Such as telephone number, phone number, wechat number, QQ numbers.
For example, the keyword can be including hyperlink and advertising words, violated word, additional character etc..
For example, user submit to user comment in include hyperlink and advertising words, such as including product distribution, shop or
Recommendation of websites, company's publicity, promoting service etc..The hyperlink is general to be occurred with website form, it may appear that multiple continuous English
Alphabetic character, such as http:// ..., " http " character by described in is set to keyword, can be by scanning the pass in user comment
Key word detects whether to contain hyperlink;If including hyperlink, that is, think that the user comment may be comment spam, then enter
One step judges whether to include advertising words again.For advertising words, such as by QQ, special price, sell fast, Taobao, the vocabulary such as bag postal are set
It is the keyword of the bulletin word, also including the combination of Any Digit and " unit " is set into characteristic information.When in user comment
When including the keyword, it is determined that the comment information in the user comment is present in blacklist storehouse, then perform step
S205。
For example, the violated word is the vocabulary containing personal attack.
For example, some users may add when user comment is submitted in the middle of the word of keyword or comment information
Enter additional character, the detection to comment spam of related platform is avoided with this.Therefore, it can the spy such as " ★ ", " * ", " # ", " & "
Different symbol is set to keyword, used as in characteristic information storage to blacklist storehouse.
For example, user may replace original keyword with homophonic or nearly sound, with this avoid related platform to rubbish
The detection of comment, such as " fishing intelligent 3 flee fish carry line character used in proper names and in rendering some foreign names Wei Xin a5a7a9 classes and carry line ".Therefore for it is above-mentioned include it is homophonic or
The partials of keyword can be set to characteristic information and stored in blacklist storehouse by the situation of the nearly sound of person.
For example, the user comment that user submits in a certain forum is " generation draw a bill, plus Q (22222211) ", detect
Include the information matched with the contact method in blacklist storehouse in the user comment, then perform step S205.Such as, use
The user comment that family is submitted to is for " the good text of depth, is worth study.", Bao Wei contains and blacklist storehouse in detecting the user comment
In the information that matches of characteristic information, then perform step S203.
As shown in Fig. 2 in a certain forum, " tiger that can fly " has delivered the text of entitled " sensor in mobile phone "
Chapter, it is the user comment of " striving for carrying out a haze sensor again early " that user's " code agriculture " have submitted content in the forum.When sentencing
When not including the information matched with the characteristic information in blacklist storehouse in the user comment that disconnected user submits to, then step is performed
S203。
Fig. 5 is referred to, Fig. 5 is that a kind of the 3rd use state of information processing method provided in an embodiment of the present invention is illustrated
Figure.
In a certain forum, " tiger that can fly " has delivered the article of entitled " sensor in mobile phone ", and user is at this
It is the user comment of " fishing intelligent 3 flee fish carry line character used in proper names and in rendering some foreign names Wei Xin a5a7a9 classes and carry line " that content is have submitted in forum.When judging user
When including the information matched with the characteristic information in blacklist storehouse in the user comment of submission, then step S205 is performed.
In some embodiments, setting white list storehouse is may also be, judges whether is comment information in the user comment
In there is white list storehouse, if then the user comment can be defined as into non-junk comment;If otherwise can be by the user
Comment is defined as comment spam.
For example, for the user comment of product, the user comment related to product is generally classified as useful information, therefore can
So that by screening the conjunctive word related to product description, such as whether descriptor or emotion word to be really comment spam.Example
Such as by taking the product issued on e-commerce platform as an example, the descriptor can be the core noun related to product, can be pre-
The descriptor that will first be described on product standard is stored in white list storehouse, if detecting user for commenting that the product is submitted to
By any descriptor in not described containing product standard in information, then the user comment can be defined as comment spam;
If containing any one in product standard description or multiple in detecting the comment information that user submits to for the product
During descriptor, then the user comment can be defined as non-junk comment.
For example, the emotion word expresses subjectivity view, attitude, sensation, the mood of oneself including user's actual wishes
Deng emotion vocabulary.Such as by taking the evaluation of the product sold to a certain website as an example, the comment of the product is people to product
The evaluation of relevant parameter and buying experience and words, people by comment can really give expression to oneself subjectivity view,
Attitude, sensation, mood etc..Therefore, product review necessarily includes the emotion of commentator.Emotion word word number is fewer, is more possible to category
In comment spam.
Step S203, traversal comment queue, judge it is described comment on queue in it is same or similar with the user comment
Whether number of reviews reaches first threshold;If it is not, then performing step S204;If so, then performing step S205.
It is understood that can be by whether including same or similar with the user comment in detection comment queue
Historical review determine the number of reviews same or similar with the user comment in the comment queue.For example, working as institute
Also exist when stating the comment information in user comment in the absence of in blacklist storehouse, in the comment queue and largely commented with the user
The same or similar historical review of the content of opinion, when the number of reviews of the same or analogous comment information of content reaches certain threshold
During value, acquisition of the user to useful information is may interfere with, in fact, the user comment of the duplicate contents can also be classified as rubbish commenting
By.Therefore in order to more accurately identify comment spam, can further detect comment queue in whether include and the user
The same or similar historical review of comment, and judge same or similar with the user comment in the comment queue commenting
Whether first threshold is reached by quantity.Wherein, the comment queue is the fifo queue being made up of historical review.
In some implementation methods, the comment similar to user comment includes being reached with the similarity of the user comment
The historical review of the 3rd threshold value.Can be by judging to be reached with the similarity of the user comment present in the comment queue
Whether the number of reviews of the historical review of the 3rd threshold value reaches first threshold to determine to be commented with the user in the comment queue
Whether first threshold is reached by same or similar number of reviews.
Such as, journey can be matched with contained information in the historical review in comment queue by comparing user comment
Spend to determine the size of the similarity.Such as, the 3rd threshold value can be 80%, when in user comment with comment queue
Historical review in the matching degree of contained information when reaching 90%, be defined as similar;When user comment and comment queue
In historical review in the matching degree of contained information when reaching 100%, be defined as identical.
In some implementation methods, the comment queue can be including any one in linked queue, array queue.
It is understood that being called the turn in program design language, queue is a kind of linear list, and the data element of queue is also called team
Column element.Insert a queue element (QE) in queue to be referred to as joining the team, a queue element (QE) is deleted from queue to be turned into and team.Because
Queue is only allowed to insert at one end, is deleted in the other end, i.e., the element for entering enqueue earliest could be deleted from queue at first, therefore
Queue is also called first in first out (FIFO-first in first out) linear list.Therefore, the comment queue is properly termed as
Fifo queue.
For example, queue can be stored with array Q [1 ... m], the upper bound m of array is the maximum capacity that queue is allowed.
Need to set two pointers in the computing of queue:Head, front pointer points to actual head of the queue element;Tail, rear pointer is pointed to
Next position of actual tail of the queue element.Generally, the initial value of two pointers is set to 0, and at this moment queue is sky, without unit
Element.When the number of queue element (QE) reaches the upper bound m of array, when there is new queue element (QE) to join the team, the team of enqueue is entered earliest
Column element is deleted from queue.
For example, queue can also be stored with chained list, the priority neighbouring relations element data on mathematical logic
The pointer of storage address is indicated, and linked queue is formed with this, can dynamically carry out storage distribution.
For example, the comment queue is array queue, then the Second Threshold that the length of the comment queue has is
The maximum capacity of the array queue, such as be 1000 user comments.
Such as, when including with the user comment identical historical review in detection comment queue, in order to avoid commenting
By repeatedly duplicating the user comment of content in queue, and then the information acquisition efficiency of user is influenceed, can refused to comment
Queue is updated, and Jia 1 in thumb up array of the record with the user comment identical historical review, to indicate other
People deliver with the same or analogous user comment of the content of the historical review, or indicate that other people approve of the history to comment
The content of opinion.
As shown in Fig. 2 such as described first threshold is 5, it is " to strive for carrying out an individual mist again early with content in the comment queue
The user comment identical number of reviews of haze sensor " be 1, then judge commentary opinion queue in it is identical with the user comment or
Similar number of reviews is not up to first threshold, then perform step S204.
As shown in figure 5, such as described first threshold is 5, with content for " fish of fleing of intelligent 3 carries for fishing in the comment queue
Line character used in proper names and in rendering some foreign names Wei Xin a5a7a9 classes carry line " user comment identical number of reviews be 7, judge it is described comment queue in the user
The same or similar number of reviews of comment has reached first threshold, then perform step S205.
Step S204, the user comment is added the comment queue commented on as head of the queue, and will overflow described second
The tail of the queue comment of threshold value is deleted.
It is understood that the length of the fifo queue can be preset as Second Threshold.The length can be used
The packet sum that can be accommodated in array queue represents that array needed to be set to fixed size in advance before foundation,
As each queue element (QE) sets a suitable byte length, to meet demand of the single queue element to byte length, can
A packet is represented to be interpreted as each queue element (QE), each packet has fixed size, such as array is N [1 ...
1000], then the Second Threshold is 1000.The length of the fifo queue can also use the storage list in linked queue
The pointer number of unit represents that chained list need not in advance distribute the memory space of fixed size, when data storage is needed, can be with
It is used for data storage for each queue element (QE) sets a suitable memory cell, and the memory cell is passed through into pointer and team
Other memory cell in row are linked together.The content of the comment queue is real-time change, such as, in comment institute of area
When there is new user comment enqueue in the region of displaying, the user comment is added to as head of the queue comment in comment queue,
The historical review then dequeue commented on as tail of the queue, the queue number of other historical reviews Jia 1 on the basis of original respectively.
As shown in figure 3, number of reviews same or similar with the user comment in the comment queue is less than first
During threshold value, the comment queue is updated, the user comment " striving for carrying out a haze sensor again early " is added to
The head of the queue No.1 of the comment queue, and deletion " asks formaldehyde to pass positioned at the historical review of the tail of the queue No.1000 of the comment queue
Sensor ".Originally numbering is historical review " the good article of No.1!The numbering of thumb up " is changed into No.2, and it is shown in numbering No.2's
Display field, remaining historical review is moved rearwards by a display field.
Step S205, comment spam is defined as by the user comment.
It is understood that when it is determined that the user comment is comment spam, can refuse to carry out more comment queue
Newly.
Fig. 6 is referred to, the 4th use state that Fig. 6 is respectively a kind of information processing method provided in an embodiment of the present invention is shown
It is intended to.
When it is determined that the content is rubbish for the user comment of " fishing intelligent 3 flee fish carry line character used in proper names and in rendering some foreign names Wei Xin a5a7a9 classes and carry line "
During comment, refusal is updated to comment queue.
In some implementation methods, when refusal is updated to comment queue, prompting frame can also be ejected, to remind user
Its comment information delivers the prompt message of failure.As shown in fig. 6, after user point " comment " button, ejection content is " comment
Examination & verification does not pass through:It is comment spam!" prompting frame, while refusal to comment queue be updated, on the mobile phone interface show
The comment area for making comments be not changed in.
Whether step S206, contact method is contained in the detection user comment, if then adding the contact method
To in blacklist storehouse as characteristic information.
In some implementation methods, when contact method is included in detecting the user comment, and the contact method
During for new contact method, the new contact method that will be extracted in the user comment increase newly into the blacklist storehouse as
Characteristic information.When the contact method is old contact method, original contact method in the blacklist storehouse can be entered
Row covering, or be not added in the blacklist storehouse.
It is understood that when new contact method is detected in the user comment, extracting the new correspondent party
Formula, and increase newly into the blacklist storehouse as characteristic information, as the detection foundation of next user comment.
As shown in fig. 6, such as content is for the user comment of " fishing intelligent 3 flee fish carry line character used in proper names and in rendering some foreign names Wei Xin a5a7a9 classes and carry line "
During comment spam, the new contact method " a5a7a9 " in the user comment is extracted, and " a5a7a9 " is increased newly to described black
As characteristic information in list storehouse.
Whether the embodiment of the present invention include in user comment and match with the characteristic information in blacklist storehouse by detecting
Information, to determine whether the user comment is comment spam, when the user comment is commented on for non-junk, traversal comment
Queue, and same or similar with user comment number of reviews in the comment queue is judged is not up to first threshold
When, the user comment is added the comment queue commented on as head of the queue, and the tail of the queue comment of the Second Threshold will be overflowed
Deleted.The embodiment of the present invention identify user submit to user comment commented on for non-junk when, further detection content
The historical review for repeating, the user comment for avoiding adding a large amount of duplicate contents is excluded with this, mitigates system operation burden, is effectively carried
Information processing efficiency high, lifting user obtains the efficiency of useful information.
The embodiment of the present invention also provides a kind of information processor, as shown in fig. 7, Fig. 7 is provided in an embodiment of the present invention
A kind of structural representation of information processor.Described information processing unit 30 include acquisition module 31, the first judge module 33,
Processing module 34, and determining module 35.
Wherein, the acquisition module 31, for obtaining user comment.
First judge module 33, for travel through comment queue, judge it is described comment on queue in the user comment
Whether same or similar number of reviews reaches first threshold, wherein the comment queue is fifo queue and length having
There is Second Threshold.
The determining module 35, comments for same or similar with the user comment in the comment queue is judged
When reaching first threshold by quantity, the user comment is defined as comment spam.
The processing module 34, comments for same or similar with the user comment in the comment queue is judged
When being not up to first threshold by quantity, the user comment is added into comment queue, and according to the Second Threshold to institute's commentary
Processed by the tail of the queue comment of queue.
Fig. 8 is referred to, Fig. 8 is a kind of another structural representation of information processor provided in an embodiment of the present invention.Institute
Information processor 30 is stated including acquisition module 31, the second judge module 32, the first judge module 33, processing module 34, it is determined that
Module 35, and detection module 36.
Wherein described acquisition module 31, for obtaining user comment.
For example, as shown in Fig. 2 in a certain forum, " tiger that can fly " has delivered entitled " sensor in mobile phone "
Article, it is the user comment of " strive for come again early individual haze a sensor ", institute that user's " code agriculture " submits content in the forum
State acquisition module 31 and get the user comment.
Second judge module 32, for judging that the comment information in the user comment whether there is blacklist storehouse
In, if the user comment then is defined as into comment spam.
It is understood that comment information in the user comment can include user name, ID, comment content,
The information such as comment issuing time.
In some implementation methods, whether second judge module 32 is additionally operable to judge include in the user comment
The information matched with the characteristic information in blacklist storehouse, if the user comment then is defined as into comment spam.
At present, many common platforms support the mutual-action behavior between user, and the form of expression of the common platform can be wrapped
Include e-commerce platform, forum, community, website, microblogging, mhkc, blog, using download platform etc..Such as, when user is in website
It is upper registration and by certification after, possess the subscriber identity information of the website, the user as the website, user can be in website
Middle its user behavior of displaying, for example, issue article, release product, send out microblogging, post, reply comment etc., can also be to other hairs
The information of cloth is commented on, thumb up etc..For above-mentioned comment content, it is same or like that certain user may issue a large amount of contents
Comment spam, such as advertising commentary, promote comment, contain the bad shadow such as reaction, violence, pornographic, hyperlink, abuse, calumny
Loud comment.
It is understood that blacklist storehouse can be pre-set, multiple characteristic informations are included in the blacklist storehouse.
In some implementation methods, the characteristic information includes user name, ID, contact method, keyword, keyword
In partials any one or it is various.
It is understood that the form of the contact method can be the combination of letter and number, length is more than 7 words
Section.Such as telephone number, phone number, wechat number, QQ numbers.
For example, the keyword can be including hyperlink and advertising words, violated word, additional character etc..
For example, user submit to user comment in include hyperlink and advertising words, such as including product distribution, shop or
Recommendation of websites, company's publicity, promoting service etc..The hyperlink is general to be occurred with website form, it may appear that multiple continuous English
Alphabetic character, such as http:// ..., " http " character by described in is set to keyword, can be by scanning the pass in user comment
Key word detects whether to contain hyperlink;If including hyperlink, that is, think that the user comment may be comment spam, then enter
One step judges whether to include advertising words again.For advertising words, such as by QQ, special price, sell fast, Taobao, the vocabulary such as bag postal are set
It is the keyword of the bulletin word, also including the combination of Any Digit and " unit " is set into characteristic information.When in user comment
When including the keyword, then second judge module 32 judges that the comment information in the user comment has blacklist
In storehouse, then the user comment is defined as comment spam.
For example, the violated word is the vocabulary containing personal attack.
For example, some users may add when user comment is submitted in the middle of the word of keyword or comment information
Enter additional character, the detection to comment spam of related platform is avoided with this.Therefore, it can the spy such as " ★ ", " * ", " # ", " & "
Different symbol is set to keyword, used as in characteristic information storage to blacklist storehouse.
For example, user may replace original keyword with homophonic or nearly sound, with this avoid related platform to rubbish
The detection of comment, such as " fishing intelligent 3 flee fish carry line character used in proper names and in rendering some foreign names Wei Xin a5a7a9 classes and carry line ".Therefore for it is above-mentioned include it is homophonic or
The partials of keyword can be set to characteristic information and stored in blacklist storehouse by the situation of the nearly sound of person.
For example, the user comment that user submits in a certain forum is " generation draw a bill, plus Q (22222211) ", when described
When second judge module 32 judges to include the information matched with the contact method in blacklist storehouse in the user comment, then
The user comment is defined as comment spam.
As shown in figure 5, in a certain forum, " tiger that can fly " has delivered the text of entitled " sensor in mobile phone "
Chapter, it is the user comment of " fishing intelligent 3 flee fish carry line character used in proper names and in rendering some foreign names Wei Xin a5a7a9 classes and carry line " that user have submitted content in the forum.
Include and the characteristic information phase in blacklist storehouse in second judge module 32 judges the user comment that user submits to
During the information matched somebody with somebody, the user comment is defined as comment spam.
In some embodiments, may also be setting white list storehouse.Second judge module 32, it is also possible to for judging
Comment information in the user comment whether there is in white list storehouse, if then the user comment can be defined as into non-rubbish
Rubbish is commented on;If otherwise the user comment can be defined as into comment spam.
For example, for the user comment of product, the user comment related to product is generally classified as useful information, therefore can
So that by screening the conjunctive word related to product description, such as whether descriptor or emotion word to be really comment spam.Example
Such as by taking the product issued on e-commerce platform as an example, the descriptor can be the core noun related to product, can be pre-
The descriptor that will first be described on product standard is stored in white list storehouse, if detecting user for commenting that the product is submitted to
By any descriptor in not described containing product standard in information, then the user comment can be defined as comment spam;
If containing any one in product standard description or multiple in detecting the comment information that user submits to for the product
During descriptor, then the user comment can be defined as non-junk comment.
For example, the emotion word expresses subjectivity view, attitude, sensation, the mood of oneself including user's actual wishes
Deng emotion vocabulary.Such as by taking the evaluation of the product sold to a certain website as an example, the comment of the product is people to product
The evaluation of relevant parameter and buying experience and words, people by comment can really give expression to oneself subjectivity view,
Attitude, sensation, mood etc..Therefore, product review necessarily includes the emotion of commentator.Emotion word word number is fewer, is more possible to category
In comment spam.
First judge module 33, for travel through comment queue, judge it is described comment on queue in the user comment
Whether same or similar number of reviews reaches first threshold, wherein the comment queue is fifo queue and length having
There is Second Threshold.
It is understood that can be by whether including same or similar with the user comment in detection comment queue
Historical review determine the number of reviews same or similar with the user comment in the comment queue.For example, working as institute
Also exist when stating the comment information in user comment in the absence of in blacklist storehouse, in the comment queue and largely commented with the user
The same or similar historical review of the content of opinion, when the number of reviews of the same or analogous comment information of content reaches certain threshold
During value, acquisition of the user to useful information is may interfere with, in fact, the user comment of the duplicate contents can also be classified as rubbish commenting
By.Therefore in order to more accurately identify comment spam, can further detect comment queue in whether include and the user
The same or similar historical review of comment, and by first judge module 33 judge in the comment queue with the use
Family comments on whether same or similar number of reviews reaches first threshold.Wherein, the comment queue is by historical review group
Into fifo queue.
In some implementation methods, the comment similar to user comment includes being reached with the similarity of the user comment
The historical review of the 3rd threshold value.Can by first judge module 33 judge it is described comment queue present in the use
Whether the number of reviews of the historical review that the similarity of family comment reaches the 3rd threshold value reaches first threshold to determine the comment
Whether the number of reviews same or similar with the user comment reaches first threshold in queue.
Such as, journey can be matched with contained information in the historical review in comment queue by comparing user comment
Spend to determine the size of the similarity.Such as, the 3rd threshold value can be 80%, when in user comment with comment queue
Historical review in the matching degree of contained information when reaching 90%, be defined as similar;When user comment and comment queue
In historical review in the matching degree of contained information when reaching 100%, be defined as identical.
In some implementation methods, the comment queue can be including any one in linked queue, array queue.
It is understood that being called the turn in program design language, queue is a kind of linear list, and the data element of queue is also called team
Column element.Insert a queue element (QE) in queue to be referred to as joining the team, a queue element (QE) is deleted from queue to be turned into and team.Because
Queue is only allowed to insert at one end, is deleted in the other end, i.e., the element for entering enqueue earliest could be deleted from queue at first, therefore
Queue is also called first in first out (FIFO-first in first out) linear list.Therefore, the comment queue is properly termed as
Fifo queue.
For example, queue can be stored with array Q [1 ... m], the upper bound m of array is the maximum capacity that queue is allowed.
Need to set two pointers in the computing of queue:Head, front pointer points to actual head of the queue element;Tail, rear pointer is pointed to
Next position of actual tail of the queue element.Generally, the initial value of two pointers is set to 0, and at this moment queue is sky, without unit
Element.When the number of queue element (QE) reaches the upper bound m of array, when there is new queue element (QE) to join the team, the team of enqueue is entered earliest
Column element is deleted from queue.
For example, queue can also be stored with chained list, the priority neighbouring relations element data on mathematical logic
The pointer of storage address is indicated, and linked queue is formed with this, can dynamically carry out storage distribution.
For example, the comment queue is array queue, then the Second Threshold that the length of the comment queue has is
The maximum capacity of the array queue, such as be 1000 user comments.
Such as, when including with the user comment identical historical review in detection comment queue, in order to avoid commenting
By repeatedly duplicating the user comment of content in queue, and then the information acquisition efficiency of user is influenceed, can refused to comment
Queue is updated, and Jia 1 in thumb up array of the record with the user comment identical historical review, to indicate other
People deliver with the same or analogous user comment of the content of the historical review, or indicate that other people approve of the history to comment
The content of opinion.
As shown in Fig. 2 such as described first threshold is 5, it is " to strive for carrying out an individual mist again early with content in the comment queue
The user comment identical number of reviews of haze sensor " is 1, then first judge module 33 judge in commentary opinion queue with institute
State the same or similar number of reviews of user comment not up to first threshold.
As shown in figure 5, such as described first threshold is 5, with content for " fish of fleing of intelligent 3 carries for fishing in the comment queue
Line character used in proper names and in rendering some foreign names Wei Xin a5a7a9 classes carry line " user comment identical number of reviews be 7, first judge module 33 judges institute's commentary
First threshold has been reached by number of reviews same or similar with the user comment in queue.
The processing module 34, for adding the user comment comment queue to be commented on as head of the queue, and will overflow
The tail of the queue comment for going out the Second Threshold is deleted.
It is understood that the length of the fifo queue can be preset as Second Threshold.The length can be used
The packet sum that can be accommodated in array queue represents that array needed to be set to fixed size in advance before foundation,
As each queue element (QE) sets a suitable byte length, to meet demand of the single queue element to byte length, can
A packet is represented to be interpreted as each queue element (QE), each packet has fixed size, such as array is N [1 ...
1000], then the Second Threshold is 1000.The length of the fifo queue can also use the storage list in linked queue
The pointer number of unit represents that chained list need not in advance distribute the memory space of fixed size, when data storage is needed, can be with
It is used for data storage for each queue element (QE) sets a suitable memory cell, and the memory cell is passed through into pointer and team
Other memory cell in row are linked together.The content of the comment queue is real-time change, such as, in comment institute of area
When there is new user comment enqueue in the region of displaying, be added to the user comment in comment queue by the processing module 34
Commented on as head of the queue, the historical review then dequeue commented on as tail of the queue, the queue number of other historical reviews is respectively in original
Jia 1 on the basis of coming.
As shown in figure 3, number of reviews same or similar with the user comment in the comment queue is less than first
During threshold value, the comment queue is updated, the user comment " is striven for carrying out a haze again early by the processing module 34
Sensor " deletes the history positioned at the tail of the queue No.1000 for commenting on queue added to the head of the queue No.1 for commenting on queue
Comment " seeking formaldehyde sensor ".Originally numbering is historical review " the good article of No.1!The numbering of thumb up " is changed into No.2, its display
In the display field of numbering No.2, remaining historical review is moved rearwards by a display field.
The determining module 35, comments for same or similar with the user comment in the comment queue is judged
When reaching first threshold by quantity, the user comment is defined as comment spam.
It is understood that when it is comment spam that the determining module 35 determines the user comment, the treatment mould
Block 34 can be refused to be updated comment queue.
As shown in fig. 6, when the determining module 35 determines the content for " the fishing fish of fleing of intelligent 3 carries line character used in proper names and in rendering some foreign names Wei Xin
A5a7a9 classes carry line " user comment be comment spam when, the processing module 34 refuse to comment queue be updated.
In some implementation methods, the processing module 34 can also be ejected and carried when refusal is updated to comment queue
Show frame, to remind user that its comment information delivers the prompt message of failure.As shown in fig. 6, after user point " comment " button,
Ejection content is for " comment examination & verification does not pass through:It is comment spam!" prompting frame, while refusal to comment queue be updated, institute
The comment area for making comments shown on mobile phone interface is stated to be not changed in.
The detection module 36, for when the user comment is defined as comment spam, in detecting the user comment
Whether contact method is contained, if then the contact method is added in blacklist storehouse as characteristic information.
In some implementation methods, when the detection module 36 is detected includes contact method in the user comment,
And the contact method is when being new contact method, the new contact method that will be extracted in the user comment is increased newly to described
As characteristic information in blacklist storehouse.When the contact method is old contact method, can be to blacklist storehouse Central Plains
Some contact methods are covered, or are not added in the blacklist storehouse.
It is understood that when new contact method is detected in the user comment, extracting the new correspondent party
Formula, and increase newly into the blacklist storehouse as characteristic information, as the detection foundation of next user comment.
As shown in fig. 6, such as content is for the user comment of " fishing intelligent 3 flee fish carry line character used in proper names and in rendering some foreign names Wei Xin a5a7a9 classes and carry line "
During comment spam, the new contact method " a5a7a9 " in the user comment is extracted, and " a5a7a9 " is increased newly to described black
As characteristic information in list storehouse.
The embodiment of the present invention also provides a kind of computer equipment, as shown in figure 9, Fig. 9 is provided in an embodiment of the present invention one
Plant the structural representation of computer equipment.The computer equipment 400 can include radio frequency (RF, Radio Frequency) circuit
401st, memory 402, the input block 403, display unit of one or more computer-readable recording mediums are included
404th, sensor 405, voicefrequency circuit 406, Wireless Fidelity (WiFi, Wireless Fidelity) module 407, include one
Or the part such as the processor 408 and power supply 409 of more than one processing core.It will be understood by those skilled in the art that Fig. 9
In the computer equipment structure that shows do not constitute restriction to computer equipment, can include than illustrating more or less portion
Part, or some parts are combined, or different part arrangements.
Radio circuit 401 can be used to receive and send messages, or in communication process signal reception and transmission.
Memory 402 can be used to store application program and data.Include calculating in the application program of the storage of memory 402
Machine program.
Input block 403 can be used to receive numeral, character information or the user's characteristic information (such as fingerprint) of input, and
Produce the keyboard relevant with user's setting and function control, mouse, action bars, optics or trace ball signal input.
Display unit 404 can be used for display by the information of user input or be supplied to the information and computer equipment of user
Various graphical user interface, these graphical user interface can by figure, text, icon, video and its any combination come structure
Into.
Computer equipment may also include at least one sensor 405, such as optical sensor, motion sensor and other biographies
Sensor.
Voicefrequency circuit 406 can provide the COBBAIF between user and computer equipment by loudspeaker, microphone.
Wireless Fidelity (WiFi) module 407 can be used for short range wireless transmission, user can be helped to send and receive e-mail, clear
Look at and website and access streaming video etc., it has provided the user wireless broadband internet and has accessed.
Processor 408 is the control centre of computer equipment, and whole computer equipment is linked using various interfaces and circuit
Various pieces, by running or performing application program of the storage in memory 402, and call storage in memory 402
Interior data, perform the various functions and processing data of computer equipment, so as to carry out integral monitoring to computer equipment.
Computer equipment also includes the power supply 409 (such as battery) powered to all parts.
Although not shown in Fig. 9, computer equipment can also will not be repeated here including camera, bluetooth module etc..
Specifically in the present embodiment, the processor 408 in computer equipment can be according to following instruction, by one or one
More than application program the corresponding computer program loads of process in memory 402, and storage is run by processor 408
Application program in memory 402, performs following operation:
Obtain user comment;
Traversal comment queue, judge it is described comment on queue in the number of reviews same or similar with the user comment be
It is no to reach first threshold, wherein the comment queue is fifo queue and length has Second Threshold;
If so, the user comment then is defined as into comment spam;
If it is not, the user comment is then added into comment queue, and according to the Second Threshold to the comment queue
Tail of the queue comment is processed.
In some implementation methods, processor 408 is used for described add the user comment and comments on queue, and according to described
Tail of the queue comment of the Second Threshold to the comment queue is processed, including:
The user comment is added the comment queue commented on as head of the queue, and the tail of the queue of the Second Threshold will be overflowed
Comment is deleted.
In some implementation methods, processor 408 is used for after the acquisition user comment, also includes:
The comment information in the user comment is judged with the presence or absence of in blacklist storehouse, if then that the user comment is true
It is set to comment spam.
In some implementation methods, processor 408 is used for the comment information judged in the user comment and whether there is
In blacklist storehouse, including:
Judge whether include the information matched with the characteristic information in blacklist storehouse in the user comment, if then
In determining that the comment information in the user comment has a blacklist storehouse.
In some implementation methods, processor 408 is additionally operable to:
When the user comment is defined as comment spam, whether contact method is contained in the detection user comment, if
It is that the contact method is added in blacklist storehouse.
In some implementation methods, processor 408 is used for identical with the user comment in the judgement comment queue
Or whether similar number of reviews reaches first threshold, including:
Judge the historical review commented on and reach the 3rd threshold value present in queue with the similarity of the user comment
Number of reviews whether reach first threshold, if then determine it is described comment queue in it is same or similar with the user comment
Number of reviews reach first threshold.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion described in detail in certain embodiment
Point, may refer to the associated description of other embodiment.
In the embodiment of the present invention, described information processing unit belongs to same with a kind of information processing method in foregoing embodiments
One design, can run the either method provided in described information processing method embodiment in described information processing unit, its
The process of implementing refers to described information processing method embodiment, and here is omitted.
It should be noted that for information processing method of the present invention, this area common test personnel be appreciated that
All or part of flow of embodiment of the present invention described information processing method is realized, can be by computer program to control phase
The hardware of pass is completed, and the computer program can be stored in a computer read/write memory medium, and such as storage is in computer
In the memory of equipment, and by least one computing device in the computer equipment, may include in the process of implementation such as institute
State the flow of the embodiment of information processing method.Wherein, described storage medium can for magnetic disc, CD, read-only storage (ROM,
Read Only Memory), random access memory (RAM, Random Access Memory) etc..
For the described information processing unit of the embodiment of the present invention, its each functional module can be integrated in a treatment core
In piece, or modules are individually physically present, it is also possible to which two or more modules are integrated in a module.On
Stating integrated module can both be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.The collection
If into module to realize in the form of software function module and as independent production marketing or when using, it is also possible to storage exists
In one computer read/write memory medium, the storage medium is for example read-only storage, disk or CD etc..
A kind of information processing method, device and the computer equipment for being provided the embodiment of the present invention above have been carried out in detail
Introduce, specific case used herein is set forth to principle of the invention and implementation method, the explanation of above example
It is only intended to help and understands technical scheme and its core concept;It will be understood by those within the art that:Its
The technical scheme described in foregoing embodiments can still be modified, or which part technical characteristic is equal to
Replace;And these modifications or replacement, do not make the technical scheme of the essence disengaging various embodiments of the present invention of appropriate technical solution
Scope.
Claims (13)
1. a kind of information processing method, it is characterised in that methods described includes:
Obtain user comment;
Traversal comment queue, judge it is described comment on queue in the number of reviews same or similar with the user comment whether reach
To first threshold, wherein the comment queue is fifo queue and length has Second Threshold;
If so, the user comment then is defined as into comment spam;
If it is not, the user comment is then added into comment queue, and according to the Second Threshold to the tail of the queue for commenting on queue
Comment is processed.
2. information processing method according to claim 1, it is characterised in that described that the user comment is added into comment team
Row, and the tail of the queue comment for commenting on queue is processed according to the Second Threshold, including:
The user comment is added the comment queue commented on as head of the queue, and the tail of the queue comment of the Second Threshold will be overflowed
Deleted.
3. information processing method according to claim 1, it is characterised in that after the acquisition user comment, also wrap
Include:
The comment information in the user comment is judged with the presence or absence of in blacklist storehouse, if being then defined as the user comment
Comment spam.
4. information processing method according to claim 1, it is characterised in that the comment in the judgement user comment
Information whether there is in blacklist storehouse, including:
Judge whether include the information matched with the characteristic information in blacklist storehouse in the user comment, if then by institute
State user comment and be defined as comment spam.
5. the information processing method according to claim any one of 1-4, it is characterised in that methods described also includes:
When the user comment is defined as comment spam, whether contain contact method in the detection user comment, if then
The contact method is added in blacklist storehouse as characteristic information.
6. information processing method according to claim 1, it is characterised in that the comment similar to user comment includes
With the historical review that the similarity of the user comment reaches the 3rd threshold value.
7. a kind of information processor, it is characterised in that described device includes:
Acquisition module, for obtaining user comment;
First judge module, for traveling through comment queue, judges or phase identical with the user comment in the comment queue
As number of reviews whether reach first threshold, wherein the comment queue is that fifo queue and length have the second threshold
Value;
Determining module, reaches for same or similar with user comment number of reviews in the comment queue is judged
During first threshold, the user comment is defined as comment spam;
Processing module, does not reach for same or similar with user comment number of reviews in the comment queue is judged
During to first threshold, the user comment is added into comment queue, and according to the Second Threshold to the team for commenting on queue
Tail comment is processed.
8. information processor according to claim 7, it is characterised in that the processing module, for by the user
Comment adds the comment queue to be commented on as head of the queue, and will overflow the tail of the queue comment of the Second Threshold and be deleted.
9. information processor according to claim 7, it is characterised in that described device also includes:
Second judge module, for judging the comment information in the user comment with the presence or absence of in blacklist storehouse, if then will
The user comment is defined as comment spam.
10. information processor according to claim 7, it is characterised in that second judge module, for judging
State and whether include the information matched with the characteristic information in blacklist storehouse in user comment, if then by the user comment
It is defined as comment spam.
11. information processor according to claim any one of 7-10, it is characterised in that described device also includes:
Detection module, for when the user comment is defined as comment spam, whether connection being contained in the detection user comment
It is mode, if then the contact method is added in blacklist storehouse as characteristic information.
12. information processors according to claim 7, it is characterised in that the comment bag similar to user comment
Include the historical review that the 3rd threshold value is reached with the similarity of the user comment.
A kind of 13. computer equipments, including memory, processor and storage can run on a memory and on the processor
Computer program, it is characterised in that the processor calls the computer program stored in the memory, performs such as
Information processing method described in claim any one of 1-6.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710026441.2A CN106777341A (en) | 2017-01-13 | 2017-01-13 | Information processing method, device and computer equipment |
PCT/CN2017/107191 WO2018129978A1 (en) | 2017-01-13 | 2017-10-21 | Information processing method, device, storage medium and computer device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710026441.2A CN106777341A (en) | 2017-01-13 | 2017-01-13 | Information processing method, device and computer equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106777341A true CN106777341A (en) | 2017-05-31 |
Family
ID=58945583
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710026441.2A Pending CN106777341A (en) | 2017-01-13 | 2017-01-13 | Information processing method, device and computer equipment |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN106777341A (en) |
WO (1) | WO2018129978A1 (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018129978A1 (en) * | 2017-01-13 | 2018-07-19 | 广东欧珀移动通信有限公司 | Information processing method, device, storage medium and computer device |
CN109933775A (en) * | 2017-12-15 | 2019-06-25 | 腾讯科技(深圳)有限公司 | UGC content processing method and device |
CN110020057A (en) * | 2017-12-29 | 2019-07-16 | 中国移动通信集团陕西有限公司 | A kind of comment spam information identifying method and device |
CN110175851A (en) * | 2019-02-28 | 2019-08-27 | 腾讯科技(深圳)有限公司 | A kind of cheating detection method and device |
CN114245163A (en) * | 2021-12-15 | 2022-03-25 | 四川启睿克科技有限公司 | Method for filtering bullet screen of robot |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111241377B (en) * | 2020-01-02 | 2023-05-26 | 华数传媒网络有限公司 | Live broadcast real-time comment system with auditing function |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102315953A (en) * | 2010-06-29 | 2012-01-11 | 百度在线网络技术(北京)有限公司 | Method and device for detecting junk posts based on occurrence rule of posts |
CN103226576A (en) * | 2013-04-01 | 2013-07-31 | 杭州电子科技大学 | Comment spam filtering method based on semantic similarity |
US20140122584A1 (en) * | 2012-10-25 | 2014-05-01 | Google, Inc. | Soft posting to social activity streams |
CN104869467A (en) * | 2015-03-26 | 2015-08-26 | 腾讯科技(北京)有限公司 | Information output method and system for media playing, and apparatuses |
CN104933191A (en) * | 2015-07-09 | 2015-09-23 | 广东欧珀移动通信有限公司 | Spam comment recognition method and system based on Bayesian algorithm and terminal |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101159704A (en) * | 2007-10-23 | 2008-04-09 | 浙江大学 | Microcontent similarity based antirubbish method |
CN104050195B (en) * | 2013-03-15 | 2017-11-03 | 暴风集团股份有限公司 | A kind of advertisement sticker processing method and system |
CN106777341A (en) * | 2017-01-13 | 2017-05-31 | 广东欧珀移动通信有限公司 | Information processing method, device and computer equipment |
-
2017
- 2017-01-13 CN CN201710026441.2A patent/CN106777341A/en active Pending
- 2017-10-21 WO PCT/CN2017/107191 patent/WO2018129978A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102315953A (en) * | 2010-06-29 | 2012-01-11 | 百度在线网络技术(北京)有限公司 | Method and device for detecting junk posts based on occurrence rule of posts |
US20140122584A1 (en) * | 2012-10-25 | 2014-05-01 | Google, Inc. | Soft posting to social activity streams |
CN103226576A (en) * | 2013-04-01 | 2013-07-31 | 杭州电子科技大学 | Comment spam filtering method based on semantic similarity |
CN104869467A (en) * | 2015-03-26 | 2015-08-26 | 腾讯科技(北京)有限公司 | Information output method and system for media playing, and apparatuses |
CN104933191A (en) * | 2015-07-09 | 2015-09-23 | 广东欧珀移动通信有限公司 | Spam comment recognition method and system based on Bayesian algorithm and terminal |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2018129978A1 (en) * | 2017-01-13 | 2018-07-19 | 广东欧珀移动通信有限公司 | Information processing method, device, storage medium and computer device |
CN109933775A (en) * | 2017-12-15 | 2019-06-25 | 腾讯科技(深圳)有限公司 | UGC content processing method and device |
CN109933775B (en) * | 2017-12-15 | 2022-02-18 | 腾讯科技(深圳)有限公司 | UGC content processing method and device |
CN110020057A (en) * | 2017-12-29 | 2019-07-16 | 中国移动通信集团陕西有限公司 | A kind of comment spam information identifying method and device |
CN110020057B (en) * | 2017-12-29 | 2021-05-25 | 中国移动通信集团陕西有限公司 | Method and device for identifying spam comment information |
CN110175851A (en) * | 2019-02-28 | 2019-08-27 | 腾讯科技(深圳)有限公司 | A kind of cheating detection method and device |
CN110175851B (en) * | 2019-02-28 | 2023-09-12 | 腾讯科技(深圳)有限公司 | Cheating behavior detection method and device |
CN114245163A (en) * | 2021-12-15 | 2022-03-25 | 四川启睿克科技有限公司 | Method for filtering bullet screen of robot |
Also Published As
Publication number | Publication date |
---|---|
WO2018129978A1 (en) | 2018-07-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106777341A (en) | Information processing method, device and computer equipment | |
CN108369709B (en) | System and method for network-based advertisement data traffic latency reduction | |
KR101863981B1 (en) | Using text messages to interact with spreadsheets | |
CN107301213A (en) | Intelligent answer method and device | |
CN108509569A (en) | Generation method, device, electronic equipment and the storage medium of enterprise's portrait | |
US20160357616A1 (en) | Application management method and application management apparatus | |
CN107306355A (en) | A kind of content recommendation method and server | |
CN108427761B (en) | News event processing method, terminal, server and storage medium | |
CN102708453A (en) | Method and device for providing terminal fault solution | |
CN107577755A (en) | A kind of searching method | |
CN107807935B (en) | Using recommended method and device | |
CN114726947B (en) | Message display method, device, user terminal and readable storage medium | |
CN106599759A (en) | Terminal information processing method and apparatus | |
CN110069769A (en) | Using label generating method, device and storage equipment | |
CN111523035B (en) | Recommendation method, device, server and medium for APP browsing content | |
CN102959539A (en) | Method and system for item recommendation in service crossing situation | |
US11010687B2 (en) | Detecting abusive language using character N-gram features | |
CN108401005A (en) | A kind of expression recommendation method and apparatus | |
CN108021713B (en) | Document clustering method and device | |
CN103780592A (en) | Method and apparatus for determining being stolen of user account | |
CN105022821B (en) | Content filtering method and terminal | |
CN107146098A (en) | Advertisement operation configuration method and equipment | |
CN113138702B (en) | Information processing method, device, electronic equipment and storage medium | |
CN105653533A (en) | Method and device for updating classified associated word set | |
CN109450963A (en) | Information push method and terminal 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 | ||
CB02 | Change of applicant information |
Address after: 523860 No. 18, Wu Sha Beach Road, Changan Town, Dongguan, Guangdong Applicant after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: 523860 No. 18, Wu Sha Beach Road, Changan Town, Dongguan, Guangdong Applicant before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
CB02 | Change of applicant information | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170531 |
|
RJ01 | Rejection of invention patent application after publication |