CN107807941B - Information processing method and device - Google Patents
Information processing method and device Download PDFInfo
- Publication number
- CN107807941B CN107807941B CN201610816185.2A CN201610816185A CN107807941B CN 107807941 B CN107807941 B CN 107807941B CN 201610816185 A CN201610816185 A CN 201610816185A CN 107807941 B CN107807941 B CN 107807941B
- Authority
- CN
- China
- Prior art keywords
- information
- scoring
- credit
- quality score
- quality
- 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
- 230000010365 information processing Effects 0.000 title claims abstract description 20
- 238000003672 processing method Methods 0.000 title claims abstract description 16
- 238000012545 processing Methods 0.000 claims abstract description 48
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000001914 filtration Methods 0.000 claims description 19
- 230000003993 interaction Effects 0.000 claims description 18
- 238000003860 storage Methods 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 10
- 230000035945 sensitivity Effects 0.000 claims description 7
- 230000003542 behavioural effect Effects 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 abstract description 7
- 230000000875 corresponding effect Effects 0.000 description 44
- 238000004422 calculation algorithm Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 230000015654 memory Effects 0.000 description 8
- 238000004458 analytical method Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 210000004218 nerve net Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a kind of information processing method and devices, belong to computer and Internet technical field.The described method includes: obtaining the information that target user's account number is sent；Obtain the quality score of information and the credit scoring of target user's account number；Wherein, quality score is used to indicate the quality condition of information, and credit scoring is used to indicate the credit standing of target user's account number；According to quality score and credit scoring, the processing mode for corresponding to information is determined.The present invention solves the prior art and screens only in accordance with the information content to information, based on reference information it is more single, lead to the lower problem of accuracy for screening result；When being screened to information, except also referring to the credit scoring of the sender user of the information in addition to this angle of information, information is screened in conjunction with reference information and two aspect factor of user, helps to improve the accuracy for screening result.
Description
Technical field
The present embodiments relate to computer and Internet technical field, in particular to a kind of information processing method and dress
It sets.
Background technique
With the development of computer and Internet technology, mountable miscellaneous application program in terminal, with abundant whole
The function at end.It is interacted for example, user can be linked up by social category application program with other users, passes through video class application program
Video can be watched, Online Video live streaming, etc. can be watched by the way that class application program is broadcast live.
For being provided with for the application program of information transmit-receive function, the information sent to user is screened, to this
It is developer's problem in need of consideration that information, which takes reasonable processing mode,.For example, information and low-quality letter to high quality
Breath is screened, and the information of high quality is allowed normally to issue, and by low-quality information filtering (namely not issuing).In existing skill
In art, usually from information content angle, the content for the information that user sends is analyzed, determines the quality condition of the information.
For example, determining the information for lower-quality information when in the information that user sends including vulgar, violence, abusing property words.
In the prior art, information is screened only in accordance with the information content, based on reference information it is more single, lead
Cause the accuracy for screening result lower.
Summary of the invention
In order to solve in the prior art, information is screened only in accordance with the information content, based on reference information compared with
It is problem that is single, causing the accuracy for screening result lower, the embodiment of the invention provides a kind of information processing method and dresses
It sets.The technical solution is as follows:
In a first aspect, providing a kind of information processing method, which comprises
Obtain the information that target user's account number is sent；
Obtain the quality score of the information and the credit scoring of target user's account number；Wherein, the quality score
It is used to indicate the quality condition of the information, the credit scoring is used to indicate the credit standing of target user's account number；
According to the quality score and the credit scoring, the processing mode for corresponding to the information is determined.
Second aspect, provides a kind of information processing unit, and described device includes:
Data obtaining module, for obtaining the information of target user's account number transmission；
Quality score obtains module, and for obtaining the quality score of the information, the quality score is used to indicate described
The quality condition of information；
Credit scoring obtains module, and for obtaining the credit scoring of target user's account number, the credit scoring is used for
Indicate the credit standing of target user's account number；
Mode determining module, for determining and corresponding to the information according to the quality score and the credit scoring
Processing mode.
Technical solution bring beneficial effect provided in an embodiment of the present invention includes:
By obtaining the quality score and target user's account of information after the information for getting the transmission of target user's account number
Number credit scoring, the processing mode for corresponding to the information is determined according to quality score and credit scoring；Solves the prior art
Information is screened only in accordance with the information content, based on reference information it is more single, cause screen result accuracy compared with
Low problem；When being screened to information, except also referring to the letter of the sender user of the information in addition to this angle of information
With scoring, information is screened in conjunction with reference information and two aspect factor of user, helps to improve the accuracy for screening result.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other
Attached drawing.
Fig. 1 is the flow chart of information processing method provided by one embodiment of the present invention；
Fig. 2 be another embodiment of the present invention provides information processing method flow chart；
Fig. 3 be another embodiment of the present invention provides information processing method flow chart；
Fig. 4 is the block diagram of information processing unit provided by one embodiment of the present invention；
Fig. 5 is the structural schematic diagram of server provided by one embodiment of the present invention.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, below in conjunction with attached drawing to embodiment party of the present invention
Formula is described in further detail.
Before the embodiment of the present invention is described in detail, first to some concepts involved in the embodiment of the present invention into
Row description below:
1, credit scoring
Credit scoring is used to indicate the credit standing of user, refers to the evaluation score value of the credit standing for characterizing user.
For example, the credit standing correlation of credit scoring and user, credit score is higher, and the credit standing for indicating user is better,
Credit score is lower, and the credit standing for indicating user is poorer.In embodiments of the present invention, not for the point system of credit scoring
It limits, such as can be hundred-mark system, can also be ten point system or normalization mode, etc..
Credit scoring can be determined according to the characteristic information of user.The characteristic information of user refers to the credit for being able to reflect user
The personal information of situation.For example, features described above information includes but is not limited at least one of following: social information, Financial Information, row
For information, identity information.Social information refers to information relevant to user social contact situation, the social circle as belonging to user,
The information delivered in social application, basic document in social application etc..Social information can be obtained from social application platform.
Financial Information refers to information relevant to user's economic conditions, such as bank debit and credit data, bank card consumption record, shopping at network letter
Breath, on-line payment information etc..Financial Information can be obtained from bank, shopping at network application platform, payment platform etc..Behavioural information
Refer to information relevant to individual subscriber behavior, such as behavioral data under behavioral data, line on line.Identity information refers to and user
The relevant information of personal identification, such as age, gender, educational background, work.Certainly, above-mentioned various features information is merely exemplary,
In practical applications, the personal information of other credit standings for being able to reflect user also may be selected as characteristic information.
2, quality score
Quality score is used to indicate the quality condition of information, refers to the evaluation score value of the quality condition for characterization information.
In embodiments of the present invention, the point system of quality score is not construed as limiting, such as can be hundred-mark system, can also be very
System or normalization mode, etc..
In one example, quality score is susceptibility scoring.Susceptibility scoring is negatively correlated with the quality condition of information
Relationship, susceptibility scoring is higher, and the quality condition for indicating information is poorer, and the lower quality condition for indicating information of susceptibility scoring is more
It is good.Susceptibility scoring can be determined according to the sensitive words for including in information.Sensitive words, which refers to, not the quality condition of information
The words that benefit influences, such as vulgar, violence, abusing property words.
In another example, quality score is value scoring.The quality condition correlation of value scoring and information,
Value scoring is higher, and the quality condition for indicating information is better, and value scoring is lower, and the quality condition for indicating information is poorer.Value is commented
Dividing can determine according to the valuable value tag of information.Valuable feature refers to the feature for having Beneficial Effect to the quality condition of information,
The degree of correlation etc. between the classification as belonging to information, information and current user's interaction scenarios.
The executing subject of method provided in an embodiment of the present invention, each step can be server.For example, the server can be with
It is a server, is also possible to the server cluster being made of multiple servers or a cloud computing service center.For
Convenient for description, in following each embodiments of the method, only it is illustrated using the executing subject of each step as server, but
Restriction is not constituted to this.
In addition, method provided in an embodiment of the present invention, can be applied to the application scenarios of any information publication, such as to contact person
Message is sent, personal multidate information is issued, publication circle of friends message, sends barrage message, information, etc. of making comments.
Referring to FIG. 1, it illustrates the flow charts of information processing method provided by one embodiment of the present invention.This method can
To comprise the following steps.
Step 101, the information that target user's account number is sent is obtained.
Target user's account number is identity of the target user in target application.In embodiments of the present invention, to target
The specific type of application is not construed as limiting, and target application can be any application program for having information transmit-receive function, as social activity is answered
With, instant messaging application, video class application, live streaming class application etc..
For example, when target application is social application or instant messaging application, information that target user's account number is sent can be with
It is the communication information sent to other user account numbers, is also possible to personal multidate information, the circle of friends of the publication of target user's account number
Message.In another example when target application is video class application or live streaming class in application, the information that target user's account number is sent can be
Barrage message, is also possible to comment information.
Step 102, the quality score of information and the credit scoring of target user's account number are obtained.
Quality score is used to indicate the quality condition of information.Credit scoring is used to indicate the letter of credit of target user's account number
Condition.Introduction in relation to quality score and credit scoring can be found in above, and details are not described herein again.
In one example, the quality score of information is obtained in the following way:
1, the sensitive words for including in identification information；
2, it is scored according to the corresponding susceptibility of each sensitivity words, calculates the susceptibility scoring of information.
Wherein, the quality condition negative correlation of the susceptibility scoring and information of information.Jie of related susceptibility scoring
Continuing can be found in above, and details are not described herein again.In practical applications, sensitive character word stock can be preset, which wraps from dictionary
Several preset sensitive words are included, and each sensitive words is set with corresponding susceptibility scoring.Server can be adopted
With segmentation methods, keyword recognition algorithm, semantic analysis algorithm etc., the sensitive words for including in identification information.In a kind of possibility
Embodiment in, the corresponding susceptibility scoring of each sensitive word is added by server, obtains the susceptibility scoring of information.?
I.e., it is assumed that the quantity of the sensitive words identified from information is n, then the susceptibility scoring of informationWherein, aiTable
Show the corresponding susceptibility scoring of i-th of sensitivity words, n is positive integer.In addition, if from information it is unidentified go out sensitive words,
Then the susceptibility scoring of information can be denoted as 0.In alternatively possible embodiment, server is corresponding quick by each sensitive word
Sensitivity scoring is added, and the summed result that will add up obtains the susceptibility scoring of information divided by message length.Wherein, believe
Breath length can be indicated with the number of words or number of characters that include in information.Namely, it is assumed that the sensitive words identified from information
Quantity is n, then the susceptibility scoring of informationWherein, aiIndicate the corresponding susceptibility scoring of i-th of sensitivity words, k
Indicate message length, n and k are positive integer.In addition, if from information it is unidentified go out sensitive words, the susceptibility of information
Scoring can be denoted as 0.
In another example, the quality score of information is obtained in the following way:
1, classification belonging to information is obtained；
In practical applications, multiple information categories can be preset.For different user's interaction scenarios, set letter
It is also different to cease classification.User's interaction scenarios refer to interaction scenarios when user sends information between application, such as Instant Messenger
Letter, publication circle of friends message send barrage message when watching Online Video or live streaming, send out when watching Online Video or live streaming
Send comment information, etc..For sending barrage message when user's interaction scenarios are viewing Online Video, set info class
It can not be determined according to video classification, such as include sport category, variety class, TV play class, film class, animation class, etc..Example again
It such as, is when issuing circle of friends message with user's interaction scenarios, set information category may include personal dynamic class, advertising
Class, content forwarding class, etc..Information is analyzed by using relevant natural language processing method, such as analysis information
In crucial words or semanteme, it may be determined that classification belonging to information.Optionally, it for different information categories, presets pair
The value scoring answered.
2, the degree of correlation between information and current user's interaction scenarios is obtained；
The value scoring correlation of the degree of correlation and information between information and current user's interaction scenarios is related
Spend it is more high, be worth scoring it is also higher, the degree of correlation the low, be worth scoring it is also lower.
In practical applications, machine learning algorithm building relatedness computation model can be used.Relatedness computation model it is defeated
Enter parameter be from the feature extracted in information and the feature extracted from current user's interaction scenarios, relatedness computation model
Export the degree of correlation of the result between information and current user's interaction scenarios.
By taking current user's interaction scenarios are viewing Online Video as an example, relevant natural language is can be used in the feature of information
Processing method is analyzed to obtain to information, such as crucial words or the semantic feature as information in analysis information；Currently
The features of user's interaction scenarios can title to currently playing video, description (such as brief introduction), comment or video content
It is analyzed, obtains feature of the theme of video as current user's interaction scenarios.
3, the classification according to belonging to information and the degree of correlation calculate the value scoring of information；
Wherein, the quality condition correlation of the value scoring and information of information.Introduction in relation to value scoring can
It sees above, details are not described herein again.Optionally, the scoring of the corresponding value of the classification according to belonging to information and the degree of correlation, using adding
Power summation algorithm calculates the value scoring of information.
In one example, the credit scoring of target user's account number is obtained in the following way:
1, the characteristic information of target user's account number is obtained；
2, according to the characteristic information of target user's account number, the credit scoring of target user's account number is calculated.
Characteristic information includes but is not limited at least one of following: social information, Financial Information, behavioural information, identity information.
Introduction in relation to above-mentioned various features information can be found in above, and details are not described herein again.In practical applications, machine learning can be used
(Machine Learning, ML) algorithm constructs credit scoring computation model.The input parameter of credit scoring computation model is to use
The characteristic information of family account number, output result are the credit scoring of user account number.In embodiments of the present invention, to machine learning algorithm
Specific type be not construed as limiting, such as regression tree algorithm, logistic regression algorithm, random forests algorithm, nerve net can be used
Network algorithm, deep learning algorithm, etc..Credit scoring computation model is trained by a certain number of training samples, and
Corresponding credit scoring is predicted according to the characteristic information of user account number using the model that training is completed afterwards.In addition, in other possibility
Embodiment in, the credit scoring of target user's account number can also be obtained directly from existing credit scoring library.
Step 103, according to quality score and credit scoring, the processing mode for corresponding to information is determined.
It optionally, include: to filter information (namely not issuing the information) and do not filter letter corresponding to the processing mode of information
It ceases (namely normally issuing the information).In practical applications, a variety of different processing modes can be preset.For different use
Family interaction scenarios, set processing mode are also different.
In one example, step 103 includes following several sub-steps:
1, from multiple quality categories, quality category belonging to quality score is determined；
2, from multiple credit categories, credit category belonging to credit scoring is determined；
3, credit category belonging to the quality category according to belonging to quality score and credit scoring is determined using decision matrix
Processing mode corresponding to information.
In practical applications, multiple quality categories are preset, each quality category corresponds to a quality score
Value range；Multiple credit categories are preset, each credit category corresponds to the value range of a credit scoring.At this
In inventive embodiments, the value range of the quantity of classification and the corresponding scoring of each classification is not construed as limiting, it can root
It is set according to actual conditions.
Illustratively, it is assumed that preset 3 quality categories, the value model of the corresponding quality score of 3 quality categories
It encloses as shown in following table -1:
| Quality category | The value range of quality score (note quality score is S) |
| 1 | The first threshold value of S < |
| 2 | First threshold value≤S≤the second threshold value |
| 3 | The second threshold value of S > |
Table -1
Assuming that 3 credit categories are preset, the value range such as following table -2 of the corresponding credit scoring of 3 credit categories
It is shown:
| Credit category | The value range of credit scoring (note credit scoring is T) |
| 1 | T < third threshold value |
| 2 | Third threshold value≤T≤third threshold value |
| 3 | The 4th threshold value of T > |
Table -2
Optionally, the corresponding m credit category of the row of decision matrix, and corresponding n quality category is arranged, the i-th of decision matrix
Item in row jth column is used to indicate i-th of credit category and the corresponding processing mode of j-th of quality category；Alternatively, decision matrix
Row correspond to n quality category, and arrange corresponding m credit category, the i-th row jth of decision matrix arrange in item be used to indicate
I-th of quality category and the corresponding processing mode of j-th of credit category；Wherein, m is the quantity of preset credit category, n
For the quantity of preset quality category, m, n are the integer greater than 1.
Illustratively, decision matrix can be as shown in following table -3:
Table -3
For example, the quality score when information belongs to quality category 2, the credit scoring of target user's account number belongs to credit category
When 1, according to above-mentioned decision matrix, it may be determined that the processing side corresponding to the information is filtering.
In another example, step 103 includes following several sub-steps:
1, according to quality score and credit scoring, the comprehensive score of information is calculated；
Optionally, the corresponding weight of quality score and the corresponding weight of credit scoring are preset, is calculated using weighted sum
The comprehensive score of method calculating information.For example, comprehensive score E=a × S+b × T of information；Wherein, a indicates that quality score is corresponding
Weight, b indicate the corresponding weight of credit scoring, and S indicates that quality score, T indicate credit scoring.Optionally, a+b=1, and a, b
It is positive number.
2, the processing mode for corresponding to information is determined according to comprehensive score.
Optionally, from multiple comprehensive score classifications, comprehensive score classification belonging to comprehensive score is determined；Default pair of inquiry
It should be related to, obtain processing mode corresponding with comprehensive score classification belonging to comprehensive score.Wherein, default corresponding relationship includes comprehensive
Close the corresponding relationship between scoring classification and processing mode.In practical applications, multiple comprehensive score classifications are preset, it is each
A comprehensive score classification corresponds to the value range of a comprehensive score.
Optionally, when the processing mode for corresponding to information includes filtering and do not filter, method provided in this embodiment is also
Include the following steps:
First, whether detection target user's account number meets preset condition；
Second, if target user's account number meets preset condition, do not filtered according to quality score and credit scoring determination
In the case where information, the sample filtering information.
Wherein, preset condition includes: that the credit scoring of target user's account number is less than first threshold and/or target user's account number
The information content sent in objective time interval is greater than second threshold.Filtering is sampled to information, refers to and selectively filters out
Information.Sampling probability can be preset, it is assumed that sampling probability is set as 90%, then is carried out using sample filtering mode to information
When filter, the probability for filtering out the information is 90%, and the probability for not filtering out the information is 10%.It is poor for some credit standings
User and/or frequently send the user of information, the processing of the information sent to it is being determined using above-mentioned steps 101-103
Mode is further to use above-mentioned sample filtering mode when not filtering, and selectively filters out the information of user transmission, can be into
One step improves the filter effect to lower-quality information, improves systematic entirety energy.
What is needed to add explanation is a bit, in practical applications, the quality score of information and the credit of target user's account number
Scoring can obtain parallel (namely simultaneously), successively can also successively obtain.In a kind of possible embodiment, above-mentioned steps 102
Including following several sub-steps:
1, the quality score of information is obtained；
2, whether the quality score of detection information belongs to default value range；
If 3, the quality score of information belongs to default value range, the credit scoring of target user's account number is obtained.
For example, whether the susceptibility scoring of detection information is less than first default point when quality score is that susceptibility scores
Value obtains the credit scoring of target user's account number if the susceptibility of information scores less than the first default score value.In another example when
When quality score is value scoring, whether the value scoring of detection information is greater than the second default score value, if the value of information scores
Greater than the second default score value, then the credit scoring of target user's account number is obtained.
Optionally, if the quality score of information is not belonging to default value range, the information is filtered.For example, when quality is commented
When being divided into susceptibility scoring, if the susceptibility scoring of information is greater than the first default score value, the information is filtered.In another example working as matter
When amount scoring is scored for value, if the value of information scores less than the second default score value, the information is filtered.
By the above-mentioned means, directly filtering for some lower-quality informations, subsequent acquisition credit scoring and root can be saved
The step of processing done to the information according to quality score and credit scoring decision, helps to save processing expense.
In conclusion method provided in this embodiment, by obtaining after the information for getting the transmission of target user's account number
It wins the confidence the quality score of breath and the credit scoring of target user's account number, is determined according to quality score and credit scoring and correspond to the letter
The processing mode of breath；Solve the prior art and information screened only in accordance with the information content, based on reference information more
Problem that is single, causing the accuracy for screening result lower；When being screened to information, except in addition to this angle of information,
The credit scoring for also referring to the sender user of the information discriminates information in conjunction with reference information and two aspect factor of user
Not, the accuracy for screening result is helped to improve.
In addition, in embodiments of the present invention, providing the mode of the quality score of two kinds of acquisition information, being commented using susceptibility
Point mode from identification lower-quality information angle analysis information quality condition, using value scoring by the way of from identify it is high-quality
The quality condition of the angle analysis information of information is measured, in practical applications, applicable mode can be selected according to user's interaction scenarios.
Referring to FIG. 2, it illustrates another embodiment of the present invention provides information processing method flow chart.In this implementation
In example, by taking information is the communication information that user sends in social application/instant messaging application as an example, to skill provided by the invention
Art scheme is introduced and illustrates.This method may include the following steps.
Step 201, the information that target user's account number is sent is obtained.
In the present embodiment, information is user's leading to other users transmission in social application or instant messaging application
Believe message.For example, information can be the anonymous message that user sends in anonymous social application to other users.
Step 202, the credit scoring of the susceptibility scoring and target user's account number of information is obtained.
The introduction and acquisition modes scored in relation to credit scoring and susceptibility can be found in above, and details are not described herein again.
In one example, step 202 includes:
1, the susceptibility scoring of information is obtained；
2, whether the susceptibility of detection information scores less than the first default score value；
If 3, the susceptibility of information scores less than the first default score value, the credit scoring of target user's account number is obtained.
Optionally, if the susceptibility scoring of information is greater than the first default score value, the information is filtered.
Step 203, from multiple susceptibility classifications, susceptibility classification belonging to susceptibility scoring is determined；From multiple credits
In classification, credit category belonging to credit scoring is determined.
In practical applications, multiple susceptibility classifications are preset, each susceptibility classification corresponds to a susceptibility
The value range of scoring；Multiple credit categories are preset, each credit category corresponds to the value model of a credit scoring
It encloses.In embodiments of the present invention, the value range of the quantity of classification and the corresponding scoring of each classification is not limited
It is fixed, it can be set according to the actual situation.
Step 204, credit category belonging to susceptibility classification and credit scoring according to belonging to susceptibility scoring, using certainly
Plan matrix determines the processing mode for corresponding to information.
Processing mode corresponding to information include: filtering information (namely not issuing the information) and do not filter information (namely
Normally issue the information).Optionally, corresponding to the processing mode of information further include: prompt is not filtered but is added in small range publication,
Etc..Wherein, the processing mode of small range publication, is directed to certain customers and normally issues the information, such as only to partial information
The stronger user of discrimination capabilities (user of such as age at 18-40 years old) normally issues the information.Do not filter but add the processing of prompt
Mode refers to and normally issues the information, but corresponding display reminding information, the prompt information may be low-quality for prompting the information
Measure information, such as there are fraud risk, security risk, there are uncivil terms.
In the present embodiment, in conjunction with the susceptibility of the credit scoring of user and information two aspect factors of scoring, exist to user
The communication information sent in social application/instant messaging application is screened, and for some lower-quality informations, small range can be used
Prompt, or even the processing mode of filtering are not filtered but are added in publication, can effectively contain the propagation of lower-quality information.
Referring to FIG. 3, it illustrates another embodiment of the present invention provides information processing method flow chart.In this implementation
In example, by taking information is the barrage message that user sends in video class application/live streaming class application as an example, to skill provided by the invention
Art scheme is introduced and illustrates.This method may include the following steps.
Step 301, the information that target user's account number is sent is obtained.
In the present embodiment, information is the barrage message that user sends in video class application/live streaming class application.
Step 302, the credit scoring of the value scoring and target user's account number of information is obtained.
Introduction and acquisition modes in relation to credit scoring and value scoring can be found in above, and details are not described herein again.
In one example, step 302 includes:
1, the value scoring of information is obtained；
2, whether the value scoring of detection information is greater than the second default score value；
If 3, the value scoring of information is greater than the second default score value, the credit scoring of target user's account number is obtained.
Optionally, if the value of information scores less than the second default score value, the information is filtered.
Step 303, according to value scoring and credit scoring, the comprehensive score of information is calculated.
Step 304, the processing mode for corresponding to information is determined according to comprehensive score.
Processing mode corresponding to information include: filtering information (namely not issuing the information) and do not filter information (namely
Normally issue the information).Optionally, corresponding to the processing mode of information further include: show the information with different display modes.
For example, being shown with different fonts, color, display position to barrage message.Barrage higher for comprehensive score disappears
Breath can show etc. that display modes are shown with big font, highlighted, screen middle position；Barrage lower for comprehensive score
Message can be shown with display modes such as small font, screen edge locations, or even filtering is not shown.
In the present embodiment, in conjunction with the value of the credit scoring of user and information two aspect factors of scoring, user is being regarded
The barrage message sent in frequency class application/live streaming class application is screened, and can effectively filter out some rubbish barrage message, have
Help construct good barrage environment.
Following is apparatus of the present invention embodiment, can be used for executing embodiment of the present invention method.For apparatus of the present invention reality
Undisclosed details in example is applied, embodiment of the present invention method is please referred to.
Referring to FIG. 4, it illustrates the block diagrams of information processing unit provided by one embodiment of the present invention.The device has
Realize that the exemplary function of the above method, the function can also be executed corresponding software realization by hardware realization by hardware.It should
Device may include: data obtaining module 410, quality score obtains module 420, credit scoring obtains module 430 and mode is true
Cover half block 440.
Data obtaining module 410, for executing above-mentioned steps 101.
Quality score obtains module 420, for obtaining the quality score of information.
Credit scoring obtains module 430, for obtaining the credit scoring of target user's account number.
Mode determining module 440, for executing above-mentioned steps 103.
In one example, mode determining module 440, comprising: quality category determination unit is used for from multiple quality categories
In, determine quality category belonging to quality score；Credit category determination unit, for determining credit from multiple credit categories
Credit category belonging to scoring；Processing mode determination unit, for the quality category according to belonging to quality score and credit scoring
Affiliated credit category determines the processing mode for corresponding to information using decision matrix.
In another example, mode determining module 440, comprising: scoring computing unit, for according to quality score and credit
Scoring, calculates the comprehensive score of information；Mode determination unit, for determining the processing side for corresponding to information according to comprehensive score
Formula.
Optionally, described device further include: whether quality score detection module, the quality score for detection information belong to
Default value range.Credit scoring obtains module 430 and obtains if the quality score for being also used to information belongs to default value range
Take the credit scoring of target user's account number.
Optionally, described device further include: information filtering module, if the quality score for information is not belonging to default value
Range then filters the information.
In one example, quality score obtains module, comprising: sensitive words recognition unit wraps in information for identification
The sensitive words contained；Sensitivity scoring computing unit calculates information for scoring according to the corresponding susceptibility of each sensitivity words
Susceptibility scoring.
In another example, quality score obtains module, comprising: information classification acquiring unit, for obtaining belonging to information
Classification；Degree of correlation acquiring unit, for obtaining the degree of correlation between information and current user's interaction scenarios；Value scoring meter
Unit is calculated, for the classification according to belonging to information and the degree of correlation, calculates the value scoring of information.
In one example, credit scoring obtains module, comprising: characteristic acquisition unit, for obtaining target user
The characteristic information of account number；Credit scoring computing unit calculates target user's account for the characteristic information according to target user's account number
Number credit scoring.
Correlative detail is in combination with reference to above method embodiment.
It should be understood that device provided by the above embodiment is when realizing its function, only with above-mentioned each functional module
It divides and carries out for example, can according to need in practical application and be completed by different functional modules above-mentioned function distribution,
The internal structure of equipment is divided into different functional modules, to complete all or part of the functions described above.In addition,
Apparatus and method embodiment provided by the above embodiment belongs to same design, and specific implementation process is detailed in embodiment of the method, this
In repeat no more.
Referring to FIG. 5, it illustrates the structural schematic diagrams of server provided by one embodiment of the present invention.The server is used
In the information processing method for implementing to provide in above-described embodiment.Specifically:
The server 500 is including central processing unit (CPU) 501 including random access memory (RAM) 502 and only
Read the system storage 504 of memory (ROM) 503, and the system of connection system storage 504 and central processing unit 501
Bus 505.The server 500 further includes the basic input/output that information is transmitted between each device helped in computer
System (I/O system) 506, and large capacity for storage program area 513, application program 514 and other program modules 515 are deposited
Store up equipment 507.
The basic input/output 506 includes display 508 for showing information and inputs letter for user
The input equipment 509 of such as mouse, keyboard etc of breath.Wherein the display 508 and input equipment 509 are all by being connected to
The input and output controller 510 of system bus 505 is connected to central processing unit 501.The basic input/output 506
Can also include input and output controller 510 with for receive and handle from keyboard, mouse or electronic touch pen etc. it is multiple its
The input of his equipment.Similarly, input and output controller 510 also provides output to display screen, printer or other kinds of defeated
Equipment out.
The mass-memory unit 507 is by being connected to the bulk memory controller (not shown) of system bus 505
It is connected to central processing unit 501.The mass-memory unit 507 and its associated computer-readable medium are server
500 provide non-volatile memories.That is, the mass-memory unit 507 may include such as hard disk or CD-ROM
The computer-readable medium (not shown) of driver etc.
Without loss of generality, the computer-readable medium may include computer storage media and communication media.Computer
Storage medium includes information such as computer readable instructions, data structure, program module or other data for storage
The volatile and non-volatile of any method or technique realization, removable and irremovable medium.Computer storage medium includes
RAM, ROM, EPROM, EEPROM, flash memory or other solid-state storages its technologies, CD-ROM, DVD or other optical storages, tape
Box, tape, disk storage or other magnetic storage devices.Certainly, skilled person will appreciate that the computer storage medium
It is not limited to above-mentioned several.Above-mentioned system storage 504 and mass-memory unit 507 may be collectively referred to as memory.
According to various embodiments of the present invention, the server 500 can also be arrived by network connections such as internets
Remote computer operation on network.Namely server 500 can be by the network interface that is connected on the system bus 505
Unit 511 is connected to network 512, in other words, Network Interface Unit 511 also can be used be connected to other kinds of network or
Remote computer system (not shown).
The memory further includes that one or more than one program, the one or more programs are stored in
In memory, and it is configured to be executed by one or more than one processor.Said one or more than one program include
For executing the instruction of the above method.
It should be understood that referenced herein " multiple " refer to two or more."and/or", description association
The incidence relation of object indicates may exist three kinds of relationships, for example, A and/or B, can indicate: individualism A exists simultaneously A
And B, individualism B these three situations.Character "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or".
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (17)
1. a kind of information processing method, which is characterized in that the described method includes:
Obtain the information that target user's account number is sent；The information is that user sends in anonymous social application to other users
Anonymous message；
Obtain the quality score of the information and the credit scoring of target user's account number；Wherein, the quality score is used for
Indicate the quality condition of the information, the credit scoring is used to indicate the credit standing of target user's account number；
According to the quality score and the credit scoring, the processing mode for corresponding to the information is determined；
When the processing mode of the information is not filter, detect whether target user's account number meets preset condition；
If target user's account number meets the preset condition, filtering is sampled to the information.
2. the method according to claim 1, wherein described according to the quality score and the credit scoring,
Determine the processing mode for corresponding to the information, comprising:
From multiple quality categories, quality category belonging to the quality score is determined；
From multiple credit categories, credit category belonging to the credit scoring is determined；
It is true using decision matrix according to credit category belonging to quality category belonging to the quality score and the credit scoring
Surely correspond to the processing mode of the information.
3. the method according to claim 1, wherein described according to the quality score and the credit scoring,
Determine the processing mode for corresponding to the information, comprising:
According to the quality score and the credit scoring, the comprehensive score of the information is calculated；
The processing mode for corresponding to the information is determined according to the comprehensive score.
4. the method according to claim 1, wherein the quality score for obtaining the information and the target
The credit scoring of user account number, comprising:
Obtain the quality score of the information；
Whether the quality score for detecting the information belongs to default value range；
If the quality score of the information belongs to the default value range, the credit for obtaining target user's account number is commented
Point.
5. according to the method described in claim 4, it is characterized in that, the quality score of the detection information whether belong to it is pre-
If after value range, further includes:
If the quality score of the information is not belonging to the default value range, the information is filtered.
6. method according to any one of claims 1 to 5, which is characterized in that the quality score for obtaining the information,
Include:
Identify the sensitive words for including in the information；
According to the corresponding susceptibility scoring of each sensitive words, the susceptibility scoring of the information is calculated；
Wherein, the quality condition negative correlation of the susceptibility scoring and the information of the information.
7. method according to any one of claims 1 to 5, which is characterized in that the quality score for obtaining the information,
Include:
Obtain classification belonging to the information；
Obtain the degree of correlation between the information and current user's interaction scenarios；
According to classification belonging to the information and the degree of correlation, the value scoring of the information is calculated；
Wherein, the quality condition correlation of the value scoring and the information of the information.
8. method according to any one of claims 1 to 5, which is characterized in that acquisition target user's account number
Credit scoring, comprising:
Obtain the characteristic information of target user's account number；Wherein, the characteristic information includes at least one of the following: social letter
Breath, Financial Information, behavioural information, identity information；
According to the characteristic information of target user's account number, the credit scoring of target user's account number is calculated.
9. a kind of information processing unit, which is characterized in that described device includes:
Data obtaining module, for obtaining the information of target user's account number transmission；The information is user in anonymous social application
The middle anonymous message sent to other users；
Quality score obtains module, and for obtaining the quality score of the information, the quality score is used to indicate the information
Quality condition；
Credit scoring obtains module, and for obtaining the credit scoring of target user's account number, the credit scoring is used to indicate
The credit standing of target user's account number；
Mode determining module, for determining the processing for corresponding to the information according to the quality score and the credit scoring
Mode；When the processing mode of the information is not filter, detect whether target user's account number meets preset condition；If institute
It states target user's account number and meets the preset condition, filtering is sampled to the information.
10. device according to claim 9, which is characterized in that the mode determining module, comprising:
Quality category determination unit, for determining quality category belonging to the quality score from multiple quality categories；
Credit category determination unit, for determining credit category belonging to the credit scoring from multiple credit categories；
Processing mode determination unit, for letter belonging to the quality category according to belonging to the quality score and the credit scoring
With classification, the processing mode for corresponding to the information is determined using decision matrix.
11. device according to claim 9, which is characterized in that the mode determining module, comprising:
Score computing unit, for calculating the comprehensive score of the information according to the quality score and the credit scoring；
Mode determination unit, for determining the processing mode for corresponding to the information according to the comprehensive score.
12. device according to claim 9, which is characterized in that described device further include:
Whether quality score detection module, the quality score for detecting the information belong to default value range；
Credit scoring obtains module and obtains institute if the quality score for being also used to the information belongs to the default value range
State the credit scoring of target user's account number.
13. device according to claim 12, which is characterized in that described device further include:
Information filtering module filters the letter if the quality score for the information is not belonging to the default value range
Breath.
14. according to the described in any item devices of claim 9 to 13, which is characterized in that the quality score obtains module, packet
It includes:
Sensitive words recognition unit, the sensitive words for including in the information for identification；
Sensitivity scoring computing unit calculates the information for scoring according to the corresponding susceptibility of each sensitive words
Susceptibility scoring；
Wherein, the quality condition negative correlation of the susceptibility scoring and the information of the information.
15. according to the described in any item devices of claim 9 to 13, which is characterized in that the quality score obtains module, packet
It includes:
Information classification acquiring unit, for obtaining classification belonging to the information；
Degree of correlation acquiring unit, for obtaining the degree of correlation between the information and current user's interaction scenarios；
Value scoring computing unit calculates the valence of the information for the classification according to belonging to the information and the degree of correlation
Value scoring；
Wherein, the quality condition correlation of the value scoring and the information of the information.
16. according to the described in any item devices of claim 9 to 13, which is characterized in that the credit scoring obtains module, packet
It includes:
Characteristic acquisition unit, for obtaining the characteristic information of target user's account number；Wherein, the characteristic information includes
At least one of below: social information, Financial Information, behavioural information, identity information；
Credit scoring computing unit calculates target user's account number for the characteristic information according to target user's account number
Credit scoring.
17. a kind of computer storage medium, which is characterized in that the storage medium is stored with program, and described program is by processor
For realizing information processing method as described in any of the claims 1 to 8 when execution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610816185.2A CN107807941B (en) | 2016-09-09 | 2016-09-09 | Information processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610816185.2A CN107807941B (en) | 2016-09-09 | 2016-09-09 | Information processing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107807941A CN107807941A (en) | 2018-03-16 |
| CN107807941B true CN107807941B (en) | 2019-07-02 |
Family
ID=61569761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610816185.2A Active CN107807941B (en) | 2016-09-09 | 2016-09-09 | Information processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107807941B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108540864A (en) * | 2018-04-13 | 2018-09-14 | 上海哔哩哔哩科技有限公司 | Internet video barrage cloud screen method, system and storage medium |
| CN108833962B (en) * | 2018-05-25 | 2020-12-22 | 咪咕音乐有限公司 | Display information processing method and device and storage medium |
| CN109033266B (en) * | 2018-07-09 | 2021-08-20 | 北京三快在线科技有限公司 | Information delivery method and device, electronic equipment and computer readable medium |
| CN110830834A (en) * | 2018-08-09 | 2020-02-21 | 北京优酷科技有限公司 | Method and device for adjusting bullet screen information color |
| CN111107380B (en) * | 2018-10-10 | 2023-08-15 | 北京默契破冰科技有限公司 | Method, apparatus and computer storage medium for managing audio data |
| CN111031329B (en) * | 2018-10-10 | 2023-08-15 | 北京默契破冰科技有限公司 | Method, apparatus and computer storage medium for managing audio data |
| CN109831682B (en) * | 2018-12-28 | 2021-07-23 | 广州方硅信息技术有限公司 | Information auditing method and device, electronic equipment and storage medium |
| CN110120912A (en) * | 2019-05-10 | 2019-08-13 | 腾讯科技（深圳）有限公司 | Rich-media content processing method, device, readable storage medium storing program for executing and computer equipment |
| CN112243156B (en) * | 2019-07-18 | 2022-11-08 | 腾讯科技（深圳）有限公司 | Barrage display method and device and storage medium |
| CN111949876B (en) * | 2020-08-14 | 2024-10-01 | 抖音视界有限公司 | Information processing method and device, electronic equipment and computer readable storage medium |
| CN113139025B (en) * | 2021-05-14 | 2024-06-07 | 恒安嘉新（北京）科技股份公司 | Threat information evaluation method, device, equipment and storage medium |
| CN116647615A (en) * | 2023-07-06 | 2023-08-25 | 维沃移动通信有限公司 | Voice message sending method, device, electronic equipment and readable storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101132590A (en) * | 2007-07-27 | 2008-02-27 | 中国移动通信集团江苏有限公司 | Communication network soft quality improving method based on client perception |
| CN102291369A (en) * | 2010-06-21 | 2011-12-21 | 上海薄荷信息科技有限公司 | Control method and corresponding control device for verifying junk information settings |
| CN102902675A (en) * | 2011-07-26 | 2013-01-30 | 腾讯科技（深圳）有限公司 | Picture content approval method and device |
| CN105635080A (en) * | 2014-11-12 | 2016-06-01 | 江苏威盾网络科技有限公司 | E-mail safety management system and method based on content filtering |
-
2016
- 2016-09-09 CN CN201610816185.2A patent/CN107807941B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101132590A (en) * | 2007-07-27 | 2008-02-27 | 中国移动通信集团江苏有限公司 | Communication network soft quality improving method based on client perception |
| CN102291369A (en) * | 2010-06-21 | 2011-12-21 | 上海薄荷信息科技有限公司 | Control method and corresponding control device for verifying junk information settings |
| CN102902675A (en) * | 2011-07-26 | 2013-01-30 | 腾讯科技（深圳）有限公司 | Picture content approval method and device |
| CN105635080A (en) * | 2014-11-12 | 2016-06-01 | 江苏威盾网络科技有限公司 | E-mail safety management system and method based on content filtering |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107807941A (en) | 2018-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107807941B (en) | Information processing method and device | |
| Zannettou et al. | On the origins of memes by means of fringe web communities | |
| Zhao et al. | Detecting health misinformation in online health communities: Incorporating behavioral features into machine learning based approaches | |
| Mostafa | Clustering halal food consumers: A Twitter sentiment analysis | |
| CN103793484B (en) | The fraud identifying system based on machine learning in classification information website | |
| Lin et al. | Voices of victory: A computational focus group framework for tracking opinion shift in real time | |
| CN110442712B (en) | Risk determination method, risk determination device, server and text examination system | |
| US20150113018A1 (en) | Interactive visual analytics for situational awareness of social media | |
| US20140006153A1 (en) | System for making personalized offers for business facilitation of an entity and methods thereof | |
| Siering et al. | Information processing on online review platforms | |
| Sen et al. | A total error framework for digital traces of humans | |
| CN104281622A (en) | Information recommending method and information recommending device in social media | |
| CN110990683B (en) | Microblog rumor integrated identification method and device based on region and emotional characteristics | |
| CN111522724B (en) | Method and device for determining abnormal account number, server and storage medium | |
| Alahmadi et al. | Twitter-based recommender system to address cold-start: A genetic algorithm based trust modelling and probabilistic sentiment analysis | |
| KR102407057B1 (en) | Systems and methods for analyzing the public data of SNS user channel and providing influence report | |
| CN110008336B (en) | Public opinion early warning method and system based on deep learning | |
| Habib et al. | Making a radical misogynist: How online social engagement with the manosphere influences traits of radicalization | |
| CN111754241A (en) | User behavior perception method, device, equipment and medium | |
| CN113934941A (en) | User recommendation system and method based on multi-dimensional information | |
| CN109168051A (en) | A kind of network direct broadcasting platform supervision evidence-obtaining system based on blue-ray storage | |
| KR102228737B1 (en) | Method And Apparatus for Detecting Fake News by Using Artificial Intelligence | |
| CN111914542A (en) | Suspected illegal investment market subject identification method, device, terminal and storage medium | |
| KR20200062520A (en) | Source analysis based news reliability evaluation system and method thereof | |
| CN108737138B (en) | Service providing method and service platform |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |