CN105740434B - Network information methods of marking and device - Google Patents
Network information methods of marking and device Download PDFInfo
- Publication number
- CN105740434B CN105740434B CN201610069153.0A CN201610069153A CN105740434B CN 105740434 B CN105740434 B CN 105740434B CN 201610069153 A CN201610069153 A CN 201610069153A CN 105740434 B CN105740434 B CN 105740434B
- Authority
- CN
- China
- Prior art keywords
- network information
- scored
- scoring
- reference grade
- associated user
- 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
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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Telephonic Communication Services (AREA)
Abstract
The invention discloses a kind of network information methods of marking and devices, belong to network technique field.Method includes: to obtain the network information to be scored;The reference grade of the associated user of the network information to be scored is obtained, the associated user is the user that predetermined registration operation is carried out to the network information to be scored;According to the weighing factor of the quantity of associated user described in each reference grade and each reference grade, the scoring of the network information to be scored is calculated.Using such network information methods of marking, realize the technical effect that the reference grade based on associated user scores to the network information, compared to the methods of marking for being based only upon associated user's quantity, the accuracy of network information space is improved, and then improves the utilization efficiency of the network information.
Description
Technical field
The present invention relates to network technique field, in particular to a kind of network information methods of marking and device.
Background technique
With the development of network technology, the information of magnanimity is based on internet and generates and propagate.And then facing such sea
When measuring the network information, how to realize that the functions such as the examination to the network information, screening, sequence become important technology in the art
One of problem.
In order to realize the functions such as examination, screening, sequence to the network information, it usually needs according to specific index to network
Information scores.Currently, mainly including reading quantity, the forwarding number according to the network information to the methods of marking of the network information
The indexs such as amount, collection quantity score.
However in practical applications, due to network information source and content often complexity with higher, based on above-mentioned
The methods of marking of index may lead to the problem of evaluation inaccuracy, to reduce user to the utilization efficiency of the network information.
Summary of the invention
In order to solve problems in the prior art, the embodiment of the invention provides a kind of network information methods of marking and devices.
The technical solution is as follows:
In a first aspect, providing a kind of network information methods of marking, which is characterized in that the described method includes:
Obtain the network information to be scored;
The reference grade of the associated user of the network information to be scored is obtained, the associated user is to described to be evaluated
The network information divided carries out the user of predetermined registration operation;
According to the weighing factor of the quantity of associated user described in each reference grade and each reference grade, described in calculating
The scoring of the network information to be scored.
Second aspect provides a kind of network information scoring apparatus, which is characterized in that described device includes:
Module is obtained, for obtaining the network information to be scored;
Reference grade module, the reference grade of the associated user for obtaining the network information to be scored, the phase
Closing user is the user that predetermined registration operation is carried out to the network information to be scored;
Computing module, the influence of quantity and each reference grade for the associated user according to each reference grade
Weight calculates the scoring of the network information to be scored.
Technical solution provided in an embodiment of the present invention has the benefit that
By obtaining the network information to be scored;Obtain the reference etc. of the associated user of the network information to be scored
Grade, the associated user are the user that predetermined registration operation is carried out to the network information to be scored;According in each reference grade
The weighing factor of the quantity of the associated user and each reference grade calculates the scoring of the network information to be scored.It adopts
With such network information methods of marking, the technology that the reference grade based on associated user scores to the network information is realized
Effect improves the accuracy of network information space compared to the methods of marking for being based only upon associated user's quantity, and then improves
The utilization efficiency of the network information.
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 schematic diagram that the present invention implements a kind of network information points-scoring system provided;
Fig. 2 is a kind of flow chart of network information methods of marking provided in an embodiment of the present invention;
Fig. 3 is a kind of flow chart of network information methods of marking provided in an embodiment of the present invention;
Fig. 4 is a kind of block diagram of network information scoring apparatus provided in an embodiment of the present invention;
Fig. 5 is a kind of schematic diagram of network information scoring server 500 provided in an 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.
Fig. 1 is the schematic diagram that the present invention implements a kind of network information points-scoring system provided.Referring to Fig. 1, which includes:
Network scoring server 101, predetermined registration operation staqtistical data base 102, user's reference score database 103, history score data library
104, network information search server 105, user terminal 106.
Network score server 101, for from predetermined registration operation staqtistical data base 102, user's reference score database 103,
Corresponding data is read in history score data library 104, and the data based on the reading execute following any network information scorings
The result of the scoring after completing primary scoring, is stored in history score data library to score the network information by side
104.Network scoring server 101 is also used to according to network information scoring as a result, being screened, being sieved to multiple network informations
Choosing, sequence, shielding.
Predetermined registration operation staqtistical data base 102, for counting and storing the number of users to network information execution predetermined registration operation,
That is the quantity of associated user.The predetermined registration operation include reading operations, forwarding operation, in interactive operation at least one of, the interaction
It operates and specifically includes return operation, thumbs up operation etc..Specifically, which may include being directed to appoint
The staqtistical data base of one predetermined registration operation, in the present invention is implemented only to include reading operations staqtistical data base 102a and forwarding behaviour
It takes statistics and is illustrated for database 102b, can also include the statistical data of other predetermined registration operations in practical applications
Library, which is not limited by the present invention.
User's reference score database 103 has the reference fractional data of user for savings bank, which refers to use
In the numerical indication of evaluation user's loan repayment ability and repayment wish.
History score data library 104, for storing the appraisal result data of each network information, specifically, which is commented
Divided data library 104 may include the score data library for any one predetermined registration operation, in the present invention is implemented only to include reading
It is illustrated for history score data library 104a and forwarding history score data library 104b, in practical applications, can also wrap
The history score data library for other predetermined registration operations is included, which is not limited by the present invention.
Network information search server 105, the searching request for being sent according to user terminal determine multiple network services,
And according to the appraisal result of the multiple network service obtained from history score data library 104, to multiple network service
It is ranked up.
User terminal 106, for sending searching request depending on the user's operation, and from network information search server
105 when receiving the ranking results of multiple network informations, according to the multiple network information of the sequencing display.
Fig. 2 is a kind of flow chart of network information methods of marking provided in an embodiment of the present invention.Referring to fig. 2, this method packet
It includes:
201, the network information to be scored is obtained.
202, the reference grade of the associated user of the network information to be scored is obtained, the associated user is to described
The network information to be scored carries out the user of predetermined registration operation.
203, the weighing factor of the quantity of the associated user according to each reference grade and each reference grade calculates
The scoring of the network information to be scored.
Using such network information methods of marking, realizes the reference grade based on associated user and the network information is carried out
The technical effect of scoring improves the accuracy of network information space compared to the methods of marking for being based only upon associated user's quantity,
And then improve the utilization efficiency of the network information.
Optionally, the weighing factor according to the quantity of the associated user and each reference grade in each reference grade,
The scoring for calculating the network information to be scored includes:
Using formula:
Score in above-mentioned formulatotalIndicating the scoring of the network information to be scored, i indicates the label of the reference grade,
N indicates the maximum label of all reference grades, usersiIndicate the quantity of the associated user in i-th of reference grade, scoreiTable
Show the weighing factor of the i-th reference grade, usersavgIndicate preset associated user's quantity radix, scoreavgIndicate all
The average weighing factor of reference grade.
Optionally, which includes: reading operations, forwarding operation, interactive operation;Correspondingly, this is according to each sign
Believe the quantity of the associated user and the weighing factor of each reference grade in grade, calculates the scoring of the network information to be scored
It include: according to the weighing factor for the associated user's quantity and each reference grade for executing reading operations in each reference grade, meter
Calculate the reading scoring of the network information to be scored;With or, according in each reference grade execute forwarding operation associated user
The weighing factor of quantity and each reference grade calculates the forwarding scoring of the network information to be scored;With or, according to each sign
The weighing factor for believing associated user's quantity and each reference grade that interactive operation is executed in grade, calculates the network to be scored
The interaction scoring of information;At least two item ratings in reading scoring, forwarding scoring and interaction scoring are weighted and are asked
With the result of the weighted sum is determined as to the scoring of the network information to be scored.
Optionally, which further includes masking operation;Correspondingly, according to the associated user in each reference grade
The weighing factor of quantity and each reference grade, the scoring for calculating the network information to be scored includes: according to each reference etc.
Associated user's quantity of masking operation and the weighing factor of each reference grade are executed in grade, calculate the network information to be scored
Negative scoring;The scoring of the network information to be scored is subtracted into the negative scoring, obtains the network information to be scored
Final scoring.
Optionally, before obtaining the network information to be scored, this method further include: asked according to the network information search of user
It asks, obtains multiple network informations to be scored;For each network information in multiple network information, executes the network information and comment
Divide process;Correspondingly, after the scoring that multiple network information is calculated, according to the scoring of each network information, to this
Multiple network informations are ranked up;The result of the sequence is sent to terminal locating for the user, so that the terminal is according to the sequence
Show multiple network information.
Optionally, the reference grade of acquisition associated user includes: to obtain the reference of associated user in the current statistic period
Grade;Correspondingly, according to the weighing factor of the quantity of the associated user and each reference grade in each reference grade, calculating should
The scoring of the network information to be scored includes: the quantity according to the associated user in reference grade each in the current measurement period
And the weighing factor of each reference grade, calculate the scoring of the network information that should be to be scored in the current measurement period.
Optionally, after the scoring for calculating the network information that should be to be scored in the current measurement period, this method further include:
The scoring for comparing the network information that should be to be scored being calculated at least two measurement periods, by least two statistics week
Interim highest score is determined as the final scoring of the network information to be scored.
All the above alternatives can form the alternative embodiment of the disclosure, herein no longer using any combination
It repeats one by one.
Fig. 3 is a kind of flow chart of network information methods of marking provided in an embodiment of the present invention, referring to fig. 2, this method packet
It includes:
301, the network information to be scored is obtained.
The network information refers to the information issuing, propagate by internet, using, and concrete form includes text information, chain
Information, pictorial information, video information etc. are connect, for example, every search knot that the article information of public platform push, searched page are shown
Fruit information, personal status information issued in circle of friends etc..It, should be to it should be noted that those skilled in the art
The network information of scoring can also have other concrete forms, and the present invention is not especially limited this.
In embodiments of the present invention, the specific opportunity for obtaining the network information to be scored includes but is not limited to following two feelings
Condition:
The first situation, the network information for having carried out scoring had been carried out every a measurement period by all
The network information of scoring is retrieved as the network information to be scored, so that in each measurement period, all has commented to this
The network information divided re-starts primary scoring, and the result of the scoring is stored in history score data library.
For example, currently carried out scoring to ten articles, and the case where set measurement period as 1 day, then daily
Ten articles are retrieved as the network information to be scored, and then are once scored this ten, and will be to ten articles
The result of scoring is stored in history score data library.
Using securing mechanism periodic in this way, so that ensure that the stylish of scoring on the basis of saving computing resource
Property.
Second situation, for not carrying out the network information of scoring, depending on the user's operation, the net which is related to
Network acquisition of information is the network information to be scored, so that once scored the network information to be scored, and by the scoring
Result be stored in history score data library.
For example, when user sends a searching request, and the search result that the searching request is related to does not carry out including ten
When the article of scoring, then ten articles are retrieved as the network information to be scored, and then once scored this ten, and
The appraisal result of ten articles will be stored in history score data library.
Using the securing mechanism triggered in this way by user's operation, so that ensure that and comment on the basis of saving computing resource
Enough network informations can be covered by dividing.It should be noted that in practical applications, in order to save process resource, for not
The network information of scoring was carried out, the average value that current all-network information scores can also be retrieved as the network to be scored
The appraisal result of information, the present invention to whether to do not carried out scoring the network information execute scoring process be not especially limited.
It should be noted that in practical applications, the network information to be scored can also be obtained on other opportunitys, for example,
When detect a network information be published reach certain time length after, then the network information to be scored is retrieved as wait score
The network information, the disclosure is not especially limited the specific opportunity and mode that obtain the network information to be scored.
302, the reference grade of associated user is obtained, which is that default behaviour is carried out to the network information to be scored
The user of work, the reference grade is for indicating interval range locating for associated user's reference score.
Wherein, which refers to for evaluating user's loan repayment ability and repaying the numerical indication of wish.This hair
Bright to recognize on the basis of sample investigation, the higher crowd's reading of reference score, the network information used usually have more excellent
Quality, be based on the recognition, the present invention is directed to the crowd of different reference grades, the case where statistics network information is used,
And then accurately evaluate the superiority and inferiority quality of the network information.
In order to accurately evaluate the superiority and inferiority quality of the network information, so that the network information to be scored to this be ranked up, sieves
It selects, in the embodiment of the present invention, before carrying out network information scoring, it is thus necessary to determine that the reference grade of each user.The reference etc.
Grade is for indicating interval range locating for user's reference score.Specifically, it is determined that the process of the reference grade of each user includes:
Reference score is divided into multiple interval ranges, the corresponding reference grade of each interval range, when the reference for getting user
When score, the corresponding reference grade of interval range locating for the reference score by the user is determined as the reference grade of the user.Example
Such as, for reference score be 0 to 100 the case where, reference score is divided into 0 to 60,61 to 80,81 to 100 three sections
Range, the corresponding first reference grade in 0 to 60 sections, the corresponding second reference grade in 61 to 80 sections, 81 to 100 sections correspond to third
Reference grade, when the reference score for obtaining user is 76, the interval range as locating for 76 is 61 to 80 sections, it is determined that the use
The reference grade at family is the second reference grade.
User's reference score analyze and then be obtained based on local data, for example, based on local payment platform institute
The user balance data and transaction data of storage using reference computation model, and then obtain the reference score of the user.It needs
It is bright, in practical applications, third party's data acquisition user's reference score can also be called, the embodiment of the present invention is to user
The source of reference score is not especially limited.
For the superiority and inferiority quality of the accurate evaluation network information, the embodiment of the present invention obtains the reference grade of associated user, should
Associated user is the user that predetermined registration operation is carried out to the network information to be scored, which includes reading operations, forwarding
At least one of in operation, interactive operation, which specifically includes return operation, thumbs up operation etc..Present invention recognizes that
For a network information, the reference distribution of grades of associated user group is able to reflect the network information to be scored
Superiority and inferiority quality, for example, the quantity of associated user is 100 people, but in the associated user of first article for two articles
There is a 80 high reference class user, 20 low reference class users, and all low references in the associated user of second article
Class user, then the superiority and inferiority quality of usual first article is higher than second article, is based on the recognition, and the present invention is implemented
Example calculates the scoring of the network information, compared to commenting for only statistical correlation number of users based on the reference grade for obtaining associated user
Divide method, improves the accuracy of evaluation.
303, according to the weighing factor of the quantity of the associated user and each reference grade in each reference grade, calculating should
The scoring of the network information to be scored.
One network information has a certain number of associated users in a period of time.The correlation is obtained in step 302
The reference grade of user, and then for the network service, the reference distribution of grades of its associated user can be determined by counting, i.e.,
It can determine the quantity of associated user in each reference grade.For example, being taken for a network with 100 associated users
Business can determine that the quantity of associated user in its first reference grade is 80, associated user in the second reference grade by statistics
Quantity be 15, the quantity of associated user is 5 in third reference grade.
The present invention is by each reference tier definition weighing factor, so that associated user's quantity pair of higher reference grade
The influence of network information scoring is bigger.The specific method for calculating network information scoring includes: to be multiplied with the weighing factor of reference grade
Using associated user's quantity in the reference grade as the efficiently individual quantity of the reference grade, the efficiently individual quantity of all reference grades is calculated
The sum of, the sum of the efficiently individual quantity is obtained into the net to be scored divided by whole associated user's quantity of the network information to be scored
The scoring of network information.Preferably, the weighing factor of each reference grade can be defined as the corresponding reference score of the reference grade, example
Such as, for the first reference grade, corresponding reference score interval range is 0 to 60, then can define the interval range
Interior median 30 is weighing factor.It should be noted that in practical applications, one reference can also be divided according to other rules
Number is defined as weighing factor, can not also independently define the weighing factor, the present invention is to each using reference score as quantizating index
The numerical value that is specifically defined of reference grade weighing factor is not construed as limiting.
Present invention recognizes that one, when associated user's quantity is very low, contingency is excessively high, be easy to cause the erroneous judgement of scoring;
Two, influence of associated user's quantity to scoring how is distinguished, for example, A has 10 height for two network informations of A, B
The associated user of reference grade, the associated user of 1 low reference grade, associated user of the B with 100 high reference grade, 10
The associated user of a low reference grade, if the weighing factor for defining high reference grade is 1, the weighing factor of low reference grade is 0,
According to the method described above, the scoring of A is (10*1+1*0)/(10+1)=0.90 point, and the scoring of B is (100*1+10*0)/(100+
10)=0.90 point, as a result cause the scoring of two network informations of A, B identical, and in fact since associated user's total quantity of B is remote
Greater than A, so the scoring of B should be made to be higher than A in the identical situation of reference distribution of grades.
It is based on the recognition, in order to overcome above-mentioned technical problem, and then more accurately evaluates the excellent of the network information
Bad quality, inventor joined the setting of associated user's quantity radix during calculating reference grade.
Specifically, the scoring of the network information is calculated using following formula:
Wherein, score in above-mentioned formulatotalIndicate the scoring of the network information to be scored, i indicates the reference grade
Label, n indicate the maximum label of all reference grades, usersiIndicate the quantity of the associated user in i-th of reference grade,
scoreiIndicate the weighing factor of the i-th reference grade, usersavgIndicate preset associated user's quantity radix, scoreavg
Indicate the average weighing factor of all reference grades.
Due to joined associated user's quantity radix in formula on denominator, and it joined associated user's number on molecule
Radix is measured multiplied by the product of average influence weight, so that the appraisal result is approached all when associated user's quantity approaches 0
Score represented by reference grade average influence weight, and when associated user's quantity is much larger than associated user's quantity radix, then
The influence of associated user's quantity radix can be ignored.
For example, A has the associated user of 10 high reference grade, 1 low reference for two network informations of A, B
The associated user of grade, B have the associated user of 100 high reference grade, the associated user of 10 low reference grades, if definition
The weighing factor of high reference grade is 1, and the weighing factor of low reference grade is 0, and number of users radix is 100, average influence power
Weight is 0.5, then according to above-mentioned formula, the scoring of A is (10*1+1*0+50*0.5)/(10+1+50)=0.57 point, and the scoring of B is
(100*1+10*0+50*0.5)/(100+10+50)=0.78 point can be seen that being both higher than average influence weighs by the result
Score 0.5 represented by weight, but since associated user's quantity of B is more compared with A, score is also higher compared with A.It should be noted that
It will be appreciated by those skilled in the art that can also add in light of the circumstances on the basis of formula provided in an embodiment of the present invention
Enter other settings, for example, the setting based on confidence interval, is modified for the situation very few to associated user's quantity, it is all
Within the spirit and principle of scoring calculation method provided by the invention, made any usual modification, equivalent replacement, improvement etc.,
It should all be included in the protection scope of the present invention.
As stated in step 302, predetermined registration operation include reading operations, forwarding operation, in interactive operation at least one of, this
Invention is recognized, for executing the associated user of different predetermined registration operations, should be caused to the final scoring of the network information different
It influences, for example, the user for executing reading operations and executing forwarding operation is associated user for a network information, but
In fact, executing the associated user of forwarding operation, compared to the associated user for executing reading operations, to be more able to reflect this to be scored
The superiority and inferiority quality of the network information.
In order to further increase the accuracy of network information superiority and inferiority quality evaluation, it is reading operations for predetermined registration operation, turns
The case where at least two in hair operation, interactive operation, methods of marking provided in an embodiment of the present invention further include:
According in each reference grade execute reading operations associated user's quantity and each reference grade weighing factor,
Calculate the reading scoring of the network information to be scored;
Associated user's quantity of operation and the weighing factor of each reference grade are forwarded according to execution in each reference grade,
Calculate the forwarding scoring of the network information to be scored;
According in each reference grade execute interactive operation associated user's quantity and each reference grade weighing factor,
Calculate the interaction scoring of the network information to be scored;
At least two item ratings in reading scoring, forwarding scoring and interaction scoring are weighted summation, by this
The result of weighted sum is determined as the scoring of the network information to be scored.Wherein, the specific value of the weighting can be according to tune
It looks into statistical result to be set, this is not limited by the present invention.
It should be noted that calculating reading scoring, scoring, interaction being forwarded to score for the network information to be scored above
Similarly, details are not described herein for detailed process and the above-mentioned process calculated for single predetermined registration operation.
The above predetermined registration operation is the front-operated to the network information, and the associated user's quantity for executing the front-operated is more
Illustrate that the superiority and inferiority quality of the network information is higher.In practical applications there is also negative operation, such as masking operation etc., executing should
The associated user's quantity negatively operated, and the superiority and inferiority quality for illustrating the network information is lower.In order to which network is determined more accurately
The superiority and inferiority quality of information, the present invention implement to provide correspondingly deduction mechanism for the negative operation, specifically, below to shield behaviour
The mechanism is illustrated as example.
According in each reference grade execute masking operation associated user's quantity and each reference grade weighing factor,
The scoring of the network information to be scored is subtracted the negative scoring, obtained by the negative scoring for calculating the network information to be scored
The final scoring of the network information to be scored to this.It calculates the detailed process negatively to score and any front of above-mentioned calculating is grasped
Make the process to score similarly, therefore not to repeat here.
As described in step 301, the process that the network information scores can be carried out in each measurement period, in turn
In order to further improve the accurate fixed of network information superiority and inferiority quality evaluation, in multiple measurement periods to network
Information carried out the case where scoring, methods of marking provided by the invention further include:
Obtain the reference grade of associated user in the current statistic period;
Correspondingly, according to the weighing factor of the quantity of the associated user and each reference grade in each reference grade, meter
The scoring for calculating the network information to be scored includes: according to the associated user in reference grade each in the current measurement period
The weighing factor of quantity and each reference grade calculates the scoring of the network information that should be to be scored in the current measurement period.?
After the scoring for calculating the network information that should be to be scored in the current measurement period, the result of the scoring is stored in history scoring
In database, compare the network that should be to be scored being calculated at least two measurement periods present in history score data library
Highest score at least two measurement period is determined as the most final review of the network information to be scored by the scoring of information
Point.Such as shown in the following table 1, for a network information, the appraisal result that the current statistic period (20150729) calculates is 0.65 point,
The appraisal result of 4 measurement periods before being had existed in history score data library, respectively 0.63,0.55,0.5,
0.71, then this 5 highest 0.71 point of mid-score of scorings are determined as to the final scoring of the network information to be scored.
Table 1
20150725 | 20150726 | 20150727 | 20150728 | 20150729 |
0.71 | 0.5 | 0.55 | 0.63 | 0.65 |
304, after determining the scoring to multiple network informations, multiple network information is arranged according to appraisal result
Sequence.
Above step 301 to 303, which is realized, scores to the network information based on user's reference grade, which can
To provide judgment basis to screen, screening, sort, shield the network information.In embodiments of the present invention, user carries out the network information
The use of appraisal result is illustrated for the application scenarios of search.
It is requested according to the network information search of user, obtains multiple network informations to be scored.Specifically, according to user's
Network information search request executes search process, and then obtains search result;Judge multiple networks letter that the search result is related to
Whether breath had carried out scoring;For having carried out the network information of scoring, then directly read from history score data library
Take the scoring;For not carrying out the network information of scoring also, network information scoring process is executed, calculating acquisition, this is to be scored
The scoring of the network information, or the average value that current all-network information scores is retrieved as commenting for the network information to be scored
Point.
After the scoring that multiple network information is calculated, according to the scoring of each network information, to multiple net
Network information is ranked up, and specifically, the network information sequence for scoring higher is more forward, and the lower network information that will score sorts
More rearward.
The result of the sequence is sent to terminal locating for the user, so that the terminal is in the form of search result according to the row
Sequence shows multiple network information.
It should be noted that after the scoring for obtaining the network information, it can also be based on the network information to be scored
Other function is realized in scoring, for example, the information by scoring lower than preset threshold is deleted etc., the present invention is to the acquisition network information
Scoring after realize other function be not especially limited.
Network information methods of marking provided in an embodiment of the present invention, by obtaining the network information to be scored;It obtains related
The reference grade of user, the associated user are the user that predetermined registration operation is carried out to the network information to be scored, the reference grade
For indicating interval range locating for associated user's reference score;According to the quantity of the associated user in each reference grade and
The weighing factor of each reference grade, calculates the scoring of the network information to be scored.Using such network information scoring side
Method realizes the technical effect that the reference grade based on associated user scores to the network information, compared to being based only upon correlation
The methods of marking of number of users, improves the accuracy of network information space, and then improves the utilization efficiency of the network information.
Fig. 4 is a kind of block diagram of network information scoring apparatus provided in an embodiment of the present invention.Referring to fig. 4, which includes:
Obtain module 401, reference grade module 402, computing module 403.
Module 401 is obtained, for obtaining the network information to be scored;
Reference grade module 402, for obtaining the reference grade of associated user, which is the net to be scored to this
Network information carries out the user of predetermined registration operation, and the reference grade is for indicating interval range locating for associated user's reference score;
Computing module 403, for the shadow according to the quantity of the associated user and each reference grade in each reference grade
Weight is rung, the scoring of the network information to be scored is calculated.
Optionally, which is used for:
Using formula:
Score in above-mentioned formulatotalIndicating the scoring of the network information to be scored, i indicates the label of the reference grade,
N indicates the maximum label of all reference grades, usersiIndicate the quantity of the associated user in i-th of reference grade, scoreiTable
Show the weighing factor of the i-th reference grade, usersavgIndicate preset associated user's quantity radix, scoreavgIndicate all
The average weighing factor of reference grade.
Optionally, which includes: reading operations, forwarding operation, interactive operation;Correspondingly, which uses
In: according to the weighing factor for the associated user's quantity and each reference grade for executing reading operations in each reference grade, calculate
The reading of the network information to be scored is scored;With or, according in each reference grade execute forwarding operation associated user's number
The weighing factor of amount and each reference grade calculates the forwarding scoring of the network information to be scored;With or, according to each reference
Associated user's quantity of interactive operation and the weighing factor of each reference grade are executed in grade, calculate the network letter to be scored
The interaction scoring of breath;At least two item ratings in reading scoring, forwarding scoring and interaction scoring are weighted summation,
The result of the weighted sum is determined as to the scoring of the network information to be scored.
Optionally, which is also used to: reference score being divided into multiple interval ranges, each interval range is one corresponding
Reference grade;When getting the reference score of user, corresponding reference of interval range etc. locating for the reference score by the user
Grade is determined as the reference grade of the user.
Optionally, which is also used to: being requested according to the network information search of user, obtains multiple networks letter to be scored
Breath;For each network information in multiple network information, network information scoring process is executed;Correspondingly, which also wraps
Include: sorting module is ranked up multiple network information for the scoring according to each network information;Sending module is used for
The result of the sequence is sent to terminal locating for the user, so that the terminal is according to the multiple network information of the sequencing display.
Optionally, which is used for: obtaining the reference grade of associated user in the current statistic period;Accordingly
Ground, computing module are also used to: according to the quantity and each sign of the associated user in each reference grade in the current measurement period
The weighing factor for believing grade calculates the scoring of the network information that should be to be scored in the current measurement period.
Optionally, the device further include: comparison module, for compare be calculated at least two measurement periods should be to
Scoring highest at least two measurement period is determined as the network to be scored and believed by the scoring of the network information of scoring
The final scoring of breath.
It should be understood that network information scoring apparatus provided in an embodiment of the present invention, can be based on a server reality
It is existing, it can also be realized based on a terminal, be also based on and realized including the network system of server and terminal.The present invention is implemented
In should the comprising modules of network information scoring apparatus be scored be only division functionally, it is real without regard to specific equipment
Body in practical application, can according to need and complete above-mentioned function distribution by different physical equipments, or set by same physics
Standby internal structure presses function division to complete all or part of the functions described above.In addition, provided by the above embodiment
Network information scoring apparatus and network information methods of marking embodiment belong to same design, and specific implementation process is detailed in method reality
Example is applied, which is not described herein again.
Network information scoring apparatus provided in an embodiment of the present invention, by obtaining the network information to be scored;It obtains related
The reference grade of user, the associated user are the user that predetermined registration operation is carried out to the network information to be scored, the reference grade
For indicating interval range locating for associated user's reference score;According to the quantity of the associated user in each reference grade and
The weighing factor of each reference grade, calculates the scoring of the network information to be scored.It is scored and is filled using such network information
It sets, realizes the technical effect that the reference grade based on associated user scores to the network information, compared to being based only upon correlation
The methods of marking of number of users, improves the accuracy of network information space, and then improves the utilization efficiency of the network information.
Fig. 5 is a kind of schematic diagram of network information scoring server 500 provided in an embodiment of the present invention.The server can be with
For executing the network information methods of marking provided in above-mentioned each embodiment.Referring to Fig. 5, server 500 includes processing component
522, it further comprise one or more processors, and the memory resource as representated by memory 532, it can for storing
By the instruction of the execution of processing component 522, such as application program.The application program stored in memory 532 may include one
Or it is more than one each correspond to one group of instruction module.In addition, processing component 522 is configured as executing instruction, to hold
Network information methods of marking in the above-mentioned Fig. 1 or Fig. 2 of row.
Server 500 can also include that a power supply module 525 be configured as the power management of execute server 500, and one
A wired or wireless network interface 550 is configured as server 500 being connected to network and input and output (I/O) interface
558.Server 500 can be operated based on the operating system for being stored in memory 532, such as Windows ServerTM, Mac OS
XTM, UnixTM,LinuxTM, FreeBSDTMOr it is similar.
It should be only above presently preferred embodiments of the present invention, be not intended to limit the invention, it is all in spirit and original of the invention
Within then, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (14)
1. a kind of network information methods of marking, which is characterized in that the described method includes:
Obtain the network information to be scored;
The reference grade of the associated user of the network information to be scored is obtained, the associated user is to described wait score
The user of network information progress predetermined registration operation;
Using the weighing factor of reference grade multiplied by associated user's quantity in the reference grade as the effective of the reference grade
Number calculates the sum of the efficiently individual quantity of all reference grades, by the sum of described efficiently individual quantity and associated user's quantity radix multiplied by
The sum of the product of average influence weight divided by the network information to be scored whole associated user's quantity and associated user's number
The sum for measuring radix obtains the network information scoring to be scored.
2. the method according to claim 1, wherein the method also includes:
It is based on confidence interval during calculating the scoring, the situation very few to the quantity of the associated user is modified.
3. the method according to claim 1, wherein the predetermined registration operation include: reading operations, forwarding operation,
Interactive operation;
Correspondingly, the weighing factor of the quantity and each reference grade of the associated user according to each reference grade,
The scoring for calculating the network information to be scored includes:
According to the weighing factor for the associated user's quantity and each reference grade for executing reading operations in each reference grade, calculate
The reading of the network information to be scored is scored;
With or, according in each reference grade execute forwarding operation associated user's quantity and each reference grade influence weigh
Weight calculates the forwarding scoring of the network information to be scored;
With or, according in each reference grade execute interactive operation associated user's quantity and each reference grade influence weigh
Weight calculates the interaction scoring of the network information to be scored;
By it is described read scoring, it is described forwarding scoring and it is described interaction scoring at least two item ratings be weighted summation, by
The result of the weighted sum is determined as the scoring of the network information to be scored.
4. according to the method described in claim 3, it is characterized in that, the predetermined registration operation further includes masking operation;
Correspondingly, the weighing factor of the quantity of the associated user according to each reference grade and each reference grade calculates
The scoring of the network information to be scored includes:
According to the weighing factor for the associated user's quantity and each reference grade for executing masking operation in each reference grade, calculate
The negative scoring of the network information to be scored;
The scoring of the network information to be scored is subtracted into the negative scoring, obtains the network information to be scored most
Final review point.
5. the method according to claim 1, wherein the method is also before obtaining the network information to be scored
Include:
It is requested according to the network information search of user, obtains multiple network informations to be scored;
For each network information in multiple network informations to be scored, network information scoring process is executed;
Correspondingly, after the scoring that multiple network informations to be scored are calculated, according to commenting for each network information
Point, the multiple network information is ranked up;
The result of the sequence is sent to terminal locating for the user, so that the terminal is according to more described in the sequencing display
A network information.
6. the method according to claim 1, wherein the related of the network information to be scored described in the acquisition is used
The reference grade at family includes:
Obtain the reference grade of associated user in the current statistic period;
Correspondingly, the weighing factor of the quantity of the associated user according to each reference grade and each reference grade calculates
The scoring of the network information to be scored includes:
According to the shadow of the quantity of associated user described in reference grade each in the current statistic period and each reference grade
Weight is rung, the scoring of the network information to be scored in the current statistic period is calculated.
7. according to the method described in claim 6, it is characterized in that, calculating the net to be scored in the current statistic period
After the scoring of network information, the method also includes:
The scoring for comparing the network information to be scored being calculated at least two measurement periods, by described at least two
Highest scoring is determined as the final scoring of the network information to be scored in the measurement period.
8. a kind of network information scoring apparatus, which is characterized in that described device includes:
Module is obtained, for obtaining the network information to be scored;
Reference grade module, the reference grade of the associated user for obtaining the network information to be scored, the related use
Family is the user that predetermined registration operation is carried out to the network information to be scored;
Computing module, for using the weighing factor of reference grade multiplied by associated user's quantity in the reference grade as the sign
The efficiently individual quantity for believing grade, calculates the sum of the efficiently individual quantity of all reference grades, by the sum of described efficiently individual quantity and associated user
Quantity radix multiplied by the product of average influence weight sum divided by the network information to be scored whole associated user's quantity
With associated user's quantity radix and, obtain the network information scoring to be scored.
9. device according to claim 8, which is characterized in that the computing module is also used to calculate the process of the scoring
In be based on confidence interval, the situation very few to the quantity of the associated user be modified.
10. device according to claim 8, which is characterized in that the predetermined registration operation include: reading operations, forwarding operation,
Interactive operation;
Correspondingly, the computing module is used for:
According to the weighing factor for the associated user's quantity and each reference grade for executing reading operations in each reference grade, calculate
The reading of the network information to be scored is scored;
With or, according in each reference grade execute forwarding operation associated user's quantity and each reference grade influence weigh
Weight calculates the forwarding scoring of the network information to be scored;
With or, according in each reference grade execute interactive operation associated user's quantity and each reference grade influence weigh
Weight calculates the interaction scoring of the network information to be scored;
By it is described read scoring, it is described forwarding scoring and it is described interaction scoring at least two item ratings be weighted summation, by
The result of the weighted sum is determined as the scoring of the network information to be scored.
11. device according to claim 10, which is characterized in that the predetermined registration operation further includes masking operation;
Correspondingly, the computing module is used for:
According to the weighing factor for the associated user's quantity and each reference grade for executing masking operation in each reference grade, calculate
The negative scoring of the network information to be scored;
The scoring of the network information to be scored is subtracted into the negative scoring, obtains the network information to be scored most
Final review point.
12. device according to claim 8, which is characterized in that described device is also used to:
It is requested according to the network information search of user, obtains multiple network informations to be scored;
For each network information in multiple network informations to be scored, network information scoring process is executed;
Correspondingly, described device further include:
Sorting module is ranked up the multiple network information for the scoring according to each network information;
Sending module, for the result of the sequence to be sent to terminal locating for the user, so that the terminal is according to described
The multiple network information of sequencing display.
13. device according to claim 8, which is characterized in that the reference grade module is used for:
Obtain the reference grade of associated user in the current statistic period;
Correspondingly, computing module is also used to:
According to the shadow of the quantity of associated user described in reference grade each in the current statistic period and each reference grade
Weight is rung, the scoring of the network information to be scored in the current statistic period is calculated.
14. device according to claim 13, which is characterized in that described device further include:
Comparison module, for compare be calculated at least two measurement periods described in the network information to be scored scoring,
Scoring highest in described at least two measurement periods is determined as to the final scoring of the network information to be scored.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610069153.0A CN105740434B (en) | 2016-02-01 | 2016-02-01 | Network information methods of marking and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610069153.0A CN105740434B (en) | 2016-02-01 | 2016-02-01 | Network information methods of marking and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105740434A CN105740434A (en) | 2016-07-06 |
CN105740434B true CN105740434B (en) | 2019-05-28 |
Family
ID=56241791
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610069153.0A Active CN105740434B (en) | 2016-02-01 | 2016-02-01 | Network information methods of marking and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105740434B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107766316B (en) * | 2016-08-15 | 2021-03-30 | 株式会社理光 | Evaluation data analysis method, device and system |
CN107870912A (en) * | 2016-09-22 | 2018-04-03 | 广州市动景计算机科技有限公司 | Article quality score method, equipment, client, server and programmable device |
CN110502473A (en) * | 2019-08-27 | 2019-11-26 | 许灵辉 | A kind of file automating processing method of reference |
CN110990719B (en) * | 2019-12-05 | 2024-03-12 | 上海信联信息发展股份有限公司 | Information pushing method and device, readable storage medium and electronic equipment |
CN113099255B (en) * | 2021-04-01 | 2023-05-30 | 北京沃东天骏信息技术有限公司 | Data generation method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101470887A (en) * | 2007-12-24 | 2009-07-01 | 阿里巴巴集团控股有限公司 | Credit early-warning system and method |
CN102651025A (en) * | 2012-04-01 | 2012-08-29 | 百度在线网络技术(北京)有限公司 | Method and equipment for positioning published information in network community |
CN103259805A (en) * | 2013-06-09 | 2013-08-21 | 中国科学院计算技术研究所 | Domain name access control method and system based on user evaluation |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9548000B2 (en) * | 2013-03-21 | 2017-01-17 | Telecommunication Systems, Inc. | Scoring server |
-
2016
- 2016-02-01 CN CN201610069153.0A patent/CN105740434B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101470887A (en) * | 2007-12-24 | 2009-07-01 | 阿里巴巴集团控股有限公司 | Credit early-warning system and method |
CN102651025A (en) * | 2012-04-01 | 2012-08-29 | 百度在线网络技术(北京)有限公司 | Method and equipment for positioning published information in network community |
CN103259805A (en) * | 2013-06-09 | 2013-08-21 | 中国科学院计算技术研究所 | Domain name access control method and system based on user evaluation |
Also Published As
Publication number | Publication date |
---|---|
CN105740434A (en) | 2016-07-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105740434B (en) | Network information methods of marking and device | |
CN103593350B (en) | Method and device for recommending promotion keyword price parameters | |
CN106251174A (en) | Information recommendation method and device | |
CN108446210A (en) | Measure, storage medium and the server of system performance | |
CN108335137A (en) | Sort method and device, electronic equipment, computer-readable medium | |
CN108415960B (en) | A kind of implementation method and device of geo-location service, electronic equipment | |
TW201401089A (en) | Search ranking method and device based on click through rates | |
CN109872232A (en) | It is related to illicit gain to legalize account-classification method, device, computer equipment and the storage medium of behavior | |
CN110490625A (en) | User preference determines method and device, electronic equipment, storage medium | |
CN106815452A (en) | A kind of cheat detection method and device | |
CN109388657A (en) | Data processing method, device, computer equipment and storage medium | |
CN109345109A (en) | A kind of Stakeholder Evaluation method and terminal device based on classification prediction model | |
CN110490419A (en) | Processing method, device, computer equipment and the storage medium of Bus information data | |
CN112487283A (en) | Method and device for training model, electronic equipment and readable storage medium | |
CN109740036A (en) | OTA platform hotel's sort method and device | |
CN109213664A (en) | Method for analyzing performance, device, storage medium and the electronic equipment of SQL statement | |
CN105335363A (en) | Object pushing method and system | |
CN110443265A (en) | A kind of behavioral value method and apparatus based on corporations | |
CN110516062A (en) | A kind of search processing method and device of document | |
CN109934631A (en) | Question and answer information processing method, device and computer equipment | |
Soltani et al. | Ranking decision making units based on the multi-directional efficiency measure | |
WO2024098682A1 (en) | Xai model evaluation method and apparatus, device, and medium | |
CN110210978A (en) | Determine the method, apparatus, equipment and storage medium of fund factor validity | |
CN109492142A (en) | Influence power detection method, electric terminal and storage medium suitable for perpetual object | |
CN104462416A (en) | Keywords initial state configuration method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |