CN109657144A - Methods of marking, device, storage medium and the terminal device of works - Google Patents
Methods of marking, device, storage medium and the terminal device of works Download PDFInfo
- Publication number
- CN109657144A CN109657144A CN201811541347.1A CN201811541347A CN109657144A CN 109657144 A CN109657144 A CN 109657144A CN 201811541347 A CN201811541347 A CN 201811541347A CN 109657144 A CN109657144 A CN 109657144A
- Authority
- CN
- China
- Prior art keywords
- comment
- works
- target
- target works
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention proposes methods of marking, device, storage medium and the terminal device of a kind of works, wherein the described method includes: obtaining the score data of target works, comment data and search data;According to the score data of the target works, the first appraisal result of the target works is obtained;According to the comment data of the target works, the second appraisal result of the target works is obtained;According to the search data of the target works, the search temperature of the target works is determined;And first appraisal result, second appraisal result and described search temperature according to the target works, determine the comprehensive score result of the target works.Using the present invention, scoring quality can be improved.
Description
Technical field
The present invention relates to field of computer technology more particularly to a kind of methods of marking of works, device, storage medium and ends
End equipment.
Background technique
With the development of technology and people's culture life becomes increasingly abundant, and emerges in large numbers rich and varied works.For example, electric
The miscellaneous works such as shadow, TV play, modern drama, variety, animation, the network novel, music, application program, game or commodity.And
These works, so that people appreciate or use to works, meet people by carrying out exhibition view on one or more websites
Spiritual culture demand.
At the same time, people can be scored or be commented on for works, with table in the process for appreciating or using works
Up to its impression to this works.Then, website can be weighted statistics to the scoring of works by people and obtain a work
The comprehensive score of product.Finally, this comprehensive score and people show in page the comment of works when exhibition is regarded as the details of product
On face.
But above scheme there are the problem of when, the scoring of works only relies upon the marking of people, we have no way of understanding this
Whether marking is marking or user that a user is carried out after understanding works based on personal feeling because of some cause specifics
And it deliberately gives a mark, such as waterborne troops.So the comprehensive marking quality of the works of above scheme is relatively low, embody with being unable to fully
Evaluation of the people to this works.In turn, during recommending according to works comprehensive score works, recommend quality also phase
To lower.
Summary of the invention
The embodiment of the present invention provides methods of marking, device, storage medium and the terminal device of a kind of works, to solve or delay
Solve above one or more technical problems in the prior art.
In a first aspect, the embodiment of the invention provides a kind of methods of marking of works, comprising:
Obtain the score data, comment data and search data of target works;
According to the score data of the target works, the first appraisal result of the target works is obtained;
According to the comment data of the target works, the second appraisal result of the target works is obtained;
According to the search data of the target works, the search temperature of the target works is determined;And
According to first appraisal result, second appraisal result and described search temperature of the target works, really
The comprehensive score result of the fixed target works.
In one embodiment, the method also includes:
According to preset examination standard, is filtered out from the comment data of the target works and do not meet the examination standard
Comment;
Obtain the quality score for meeting the comment of the examination standard;And
The comment that quality score is less than given threshold is filtered out from the comment for meeting the examination standard.
In one embodiment, according to the comment data of the target works, obtain the target works second is commented
Divide result, comprising:
Sentiment analysis is carried out to filtered comment, obtains the emotion of the comment expression;And
According to the quality score and emotion of the comment, the second appraisal result of the target works is obtained.
In one embodiment, the quality score for meeting the comment of the examination standard is obtained, comprising:
Plot, personage, scene and the personal view for including are commented on according to described, determines the abundant in content of the comment
Degree;
Count the number of words of the comment;And
According to the abundant in content degree and number of words of the comment, the quality score of the comment is determined.
In one embodiment, the quality score for meeting the comment of the examination standard is obtained, further includes:
Obtain the opposition number approved of number and oppose the comment for approving of the comment;
According to the approval number and the opposition number, the quality score of the comment is corrected.
In one embodiment, the method also includes:
According to comment emotion it is positive and negative, classify to the comment data of the target works, obtain the mesh
It is denoted as the positive net exploxer comment and negative net exploxer comment of product;And
According to the height of quality score, the positive net exploxer comment and the negative net exploxer comment are ranked up respectively,
Obtain the front comment ranking results and negative reviews ranking results of the target works.
In one embodiment, the method also includes:
Obtain the access request of the target works;
Retrieve the works details of the target works;Wherein, the works details include that the synthesis of the target works is commented
Divide result;And
Exhibition regards the works details of the target works.
Second aspect, the embodiment of the present invention provide a kind of scoring apparatus of works, comprising:
Data acquisition module, for obtaining the score data, comment data and search data of target works;
First grading module obtains the target works for the score data according to the target works
First appraisal result;
Second grading module, for the comment data according to the target works, obtain the target works second is commented
Divide result;
Temperature determining module determines the search heat of the target works for the search data according to the target works
Degree;And
Comprehensive score module, for first appraisal result, second appraisal result according to the target works
With described search temperature, the comprehensive score result of the target works is determined.
In one embodiment, described device further include:
Filtering module is examined, for being filtered out from the comment data of the target works according to preset examination standard
The comment of the examination standard is not met;
Quality score obtains module, for obtaining the quality score for meeting the comment of the examination standard;And quality mistake
Module is filtered, the comment for being less than given threshold for filtering out quality score from the comment for meeting the examination standard.
In one embodiment, second grading module includes:
Emotion acquiring unit obtains the emotion of the comment expression for carrying out sentiment analysis to filtered comment;With
And
Scoring computing unit obtains the second of the target works for the quality score and emotion according to the comment
Appraisal result.
In one embodiment, the quality score acquisition module includes:
Richness determination unit is determined for commenting on the plot, personage, scene and the personal view that include according to described
The abundant in content degree of the comment;
Word counting unit, for counting the number of words of the comment;And
Quality score determination unit determines the matter of the comment for the abundant in content degree and number of words according to the comment
Amount scoring.
In one embodiment, the quality score obtains module further include:
It approves of and opposes number acquiring unit, for obtaining the approval number of the approval comment and opposing the comment
Oppose number;
Quality score amending unit, for correcting the matter of the comment according to the approval number and the opposition number
Amount scoring.
In one embodiment, further includes:
Positive negative reviews obtain module, the comment for the positive and negative of the emotion according to comment, to the target works
Data are classified, and the positive net exploxer comment and negative net exploxer comment of the target works are obtained;And
Positive negative reviews sorting module, for the height according to quality score, respectively to the positive net exploxer comment and institute
It states negative net exploxer comment to be ranked up, obtains the front comment ranking results and negative reviews ranking results of the target works.
In one embodiment, further includes:
Access obtains module, for obtaining the access request of the target works;
Works retrieval module, for retrieving the works details of the target works;Wherein, the works details include described
The comprehensive score result of target works;And
Details exhibition view module, for opening up the works details for regarding the target works.
The third aspect, the embodiment of the invention provides a kind of scoring apparatus of works, the function of described device can pass through
Hardware realization can also execute corresponding software realization by hardware.The hardware or software include it is one or more with it is above-mentioned
The corresponding module of function.
It include processor and memory in the scoring structure of works in a possible design, the memory is used for
The scoring apparatus of works executes the scoring procedures of above-mentioned works, the processor is configured to depositing in the memory for executing
The program of storage.The scoring apparatus of the works can also include communication interface, for works scoring apparatus and other equipment or
Communication.
Fourth aspect, the embodiment of the present invention also provide a kind of computer readable storage medium, the scoring apparatus for works
Computer software instructions used, including program involved in the methods of marking for executing above-mentioned works.
Any one technical solution in above-mentioned technical proposal have the following advantages that or the utility model has the advantages that
The embodiment of the present invention can use score data, comment data and search this three's data of data come for works into
Row comprehensive score improves scoring quality.
Above-mentioned general introduction is merely to illustrate that the purpose of book, it is not intended to be limited in any way.Except foregoing description
Schematical aspect, except embodiment and feature, by reference to attached drawing and the following detailed description, the present invention is further
Aspect, embodiment and feature, which will be, to be readily apparent that.
Detailed description of the invention
In the accompanying drawings, unless specified otherwise herein, otherwise indicate the same or similar through the identical appended drawing reference of multiple attached drawings
Component or element.What these attached drawings were not necessarily to scale.It should be understood that these attached drawings depict only according to the present invention
Disclosed some embodiments, and should not serve to limit the scope of the present invention.
Fig. 1 is the flow diagram of one embodiment of the methods of marking of works provided by the invention.
Fig. 2 is the flow diagram of one embodiment of process of data preprocessing provided by the invention.
Fig. 3 is the flow diagram of one embodiment of the calculating process of the second scoring provided by the invention.
Fig. 4 is the flow diagram of one embodiment of the process provided by the invention for comment marking.
Fig. 5 is the flow diagram of one embodiment of the process of amendment quality score provided by the invention.
Fig. 6 is the flow diagram of one embodiment of the process of access works provided by the invention.
Fig. 7-1 is the block schematic illustration of data handling procedure provided in an embodiment of the present invention.
Fig. 7-2 is the block schematic illustration of the intervention of data processing provided in an embodiment of the present invention.
Fig. 7-3 is that one of works scoring and comment the exhibition view page provided in an embodiment of the present invention applies exemplary signal
Figure.
Fig. 7-4 is an exemplary signal of application of works scoring provided in an embodiment of the present invention with comment input page
Figure.
Fig. 7-5 is works scoring and the rear end of Commentary Systems and the block schematic illustration of front end of the embodiment of the present invention.
Fig. 8 is the structural schematic diagram of one embodiment of the scoring apparatus of works provided by the invention.
Fig. 9 is the structural schematic diagram of one embodiment of terminal device provided by the invention.
Specific embodiment
Hereinafter, certain exemplary embodiments are simply just described.As one skilled in the art will recognize that
Like that, without departing from the spirit or scope of the present invention, described embodiment can be modified by various different modes.
Therefore, attached drawing and description are considered essentially illustrative rather than restrictive.
Referring to Fig. 1, the embodiment of the invention provides a kind of methods of marking of works.The methods of marking of the present embodiment can be with
It applies all kinds of in film, TV play, modern drama, variety, animation, the network novel, music, application program, game or commodity etc.
Works scoring in.The present embodiment may include step S100 to S500, as follows:
S100 obtains the score data, comment data and search data of target works.
In some embodiments, from the number of all works obtained in major website that exhibition is regarded as product in crawl a period of time
According to by scoring, comment and searching for the forms of data and classify, and be referred to corresponding works.Illustratively, made with video display
For product.Using the work title of target films and television programs as keyword, from major website obtain films and television programs scoring, comment with
And the data of search.Works generally comprise multiple versions, and the data retrieved with work title may also be related to multi version.Cause
This, the works information and target video display of films and television programs corresponding to the data of the scoring, comment and the search that need will acquire are made
The works information of product carries out similarity calculation.Then, the data that similarity is met to similarity threshold, as target films and television programs
Scoring, comment and search data.
Therefore Ming Siyi, score data may include that each user gives a mark to target works and obtains numerical value.Comment data
It may include the comment that each user carries out verbal description or diagram description to target works and makes.It may include each for searching for data
User scans for target works in website to obtain search diary.Search diary can record user and search for target works
Time, browsing duration and browsing content.The frequency that each user scans for target works can be counted by searching for diary
Secondary, interest level etc..
Wherein, the standards of grading that different websites uses have can be different.For example, the website A carries out works by hundred-mark system
Scoring.The website B precentagewise scores to works.Therefore, the score data that can be obtained to different standards of grading turns
Change the score data of unified score standard into.For example, being made as unified standards of grading with percentage.If getting mesh from the website B
A scoring for being denoted as product is 0.8, then switching to the corresponding scoring of hundred-mark system is 80 points.
S200 obtains the first appraisal result of target works according to the score data of target works.
In some embodiments, same user comment target works generally all can include scoring and comment.It can be according to commenting
By judging whether the comment of user is true.For example, whether the comment for passing through user is waterborne troops, if it is waterborne troops, then this is used
The scoring at family is deleted from score data.By comment of the rank and user of user on major website to target works,
It can judge whether this user is waterborne troops.For example, user class is low, and repeatedly target works are made together on major website
The comment of sample, it is believed that this user is waterborne troops.
In some embodiments, score data includes that a large amount of scoring can in conjunction with the user class for the corresponding user that scores
To determine the weighted value of this scoring.User class is higher, and the weighted value of scoring is higher.And comment the authority of the website in source
It can also determine the weighted value of this scoring.Website user is more, more has authority, then the weighted value to score is higher.Using each
Scoring and the weighted value respectively to score are weighted and averaged processing, obtain the first appraisal result of target works.
S300 obtains the second appraisal result of target works according to the comment data of target works.
In some embodiments, comment data can be pre-processed, for example, being filtered to waterborne troops's comment.
In some embodiments, it can give a mark to each comment in comment data, obtain a quality score.So
Afterwards, the commenting to scoring lower than given threshold is filtered.
In some embodiments, it can use yellow anti-identification model, to yellow, violence involved in comment data or reaction etc.
Comment as defined in examination is not met to be identified and filtered.Yellow anti-identification model can advance with training data generation.
In the second appraisal result for calculating target works, is changed using the quality score of each comment, emotion, can be calculated
Obtain the second commenting result.
S400 determines the search temperature of target works according to the search data of target works.
In some embodiments, by the way that search data are counted or calculated, available each user is to target works
The search frequency that scans for, interest level and number of users with target works.Then.According to the search frequency, with mesh
It is denoted as the interest level and number of users of product, determines the search temperature of target works.Search for the number of users of target works
More, the search temperature of target works is higher.Same user is higher to the search frequency of target works, the search heat of target works
It spends higher.User is higher to the interest level of target works, and the search temperature of target works is higher.
In some embodiments, the search temperature of target works can be directly acquired by search engine.
S500 determines target works according to the first appraisal result of target works, the second appraisal result and search temperature
Comprehensive score result.
In some embodiments, one can be determined respectively for the first appraisal result, the second appraisal result and search temperature
The first appraisal result, the second appraisal result and search temperature is weighted in weighted value, and the synthesis for obtaining target works is commented
Divide result.
The embodiment of the present invention can use score data, comment data and search this three's data of data come for works into
Row comprehensive score improves scoring quality.Works recommendation is carried out in the subsequent comprehensive score result that can use, improves and recommends quality.
It in some embodiments, may include step S610 referring to Fig.2, being pre-processed to the comment data got
It is as follows to step S630:
S610 is filtered out from the comment data of target works according to preset examination standard and is not met examination standard
Comment.Such as: the comment vulgar to yellow, violence involved in comment data or reaction etc. is identified and is filtered.It can use
Yellow anti-identification model carries out identification filtering.Yellow anti-identification model can advance with training data generation.Training data can wrap
Include sample comment and according to preset examination standard to sample comment in text or pattern be identified obtained from sample
Mark.
S620 obtains the quality score for meeting the comment of examination standard.
For example, a numerical value is taken between from 0 to 1 according to the content of comment, for assessing the quality of comment.
S630 filters out the comment that quality score is less than given threshold from the comment for meet examination standard.
Example is connected, the numerical value of quality score is lower than 0.1 comment, can be filtered.
In some embodiments, the threshold value of examination standard and filtering used by filtering can according to need into setting
It sets.It can also be with manual intervention, filtration fraction comment.
In some embodiments, after to comment data filtration treatment, the second scoring calculating process of above-mentioned steps S300,
As shown in figure 3, may include step S710 and step S720, it is as follows:
S710 carries out sentiment analysis to filtered comment, obtains the emotion of comment expression.
S720 obtains the second appraisal result of target works according to the quality score and emotion of comment.
In some embodiments, for the sentiment analysis of comment, comment can be carried out using language identification tool of speaking to oneself
Identification, gives a mark respectively to positive, negative and neutral three kinds of emotions of comment.Then, using comment it is positive, negatively with
And the score of neutral three kinds of emotions, it is calculated, obtains the fractional value of the emotion of this comment.If point of the positive emotion of comment
Numerical value is higher, then the emotion score commented on is higher.If the negative emotion fractional value of comment is higher, the emotion score commented on is got over
It is low.For example, taking the emotion fractional value of comment between from -1 to 1.The fractional value of the positive emotion of comment is higher, the emotion point of comment
Numerical value levels off to 1.The negative emotion fractional value of comment is higher, and the emotion fractional value of comment levels off to -1.Wherein, the neutrality of comment
Emotion fractional value is higher, and the emotion fractional value of comment levels off to 0.
In some embodiments, the front of comment, the score of the three kinds of emotions in front and neutrality can be determined, then press and divide
Several height determines that comment is one of in positive, negative or neutrality.
In some embodiments, it is accounting for for negative comment that the emotion in statistics comment data, which is positive comments on emotion,
Than.Then the second commenting result of target works is calculated in the quality score commented on according to this accounting numerical value and respectively.
In some embodiments, above-mentioned steps S620 is the process of comment marking, as shown in figure 4, may include:
S622 determines the abundant in content degree of comment according to plot, personage, scene and personal view that comment includes.
In some embodiments, judge comment include plot, personage, scene whether with the plot in works, personage, field
Scape is consistent, and counts the quantity of the plot being consistent, personage, scene, and determines the emotion of personal view expression.Then,
According to the emotion of the plot, personage, the quantity of scene and the personal view expression that are consistent, the abundant in content degree of comment is determined.
Wherein, plot, personage, the quantity of scene being consistent are more, and the abundant in content degree of comment is bigger.The emotion of individual's viewing expression
Variation is more complicated, and the abundant in content degree of comment is bigger.
S624 counts the number of words of comment.
S626 determines the quality score of comment according to the abundant in content degree and number of words of comment.
In the present embodiment, the abundant in content degree of comment is bigger, number of words is more, and the quality score of comment is higher.
In some embodiments, quality score model can be used to give a mark for comment.Quality score model can be pre-
Generation is first trained using training data.Training data may include that the sample quality that sample is commented on and sample is commented on is commented
Point.
In some embodiments, when exhibition view comment, the control of approval or opposition can be provided, selected to other users
It selects approval or opposes this comment.Therefore, as shown in figure 5, the process of amendment quality score, may include S6281 and S6283, such as
Under:
S6281 obtains the opposition number approved of number and oppose comment for approving of comment.
S6283 corrects the quality score of comment according to approving of number and opposing number.
In some embodiments, if the comment of more multi-user's approval, illustrate that this comment evaluation works is more pertinent.If
More multi-user oppose comment, illustrate this comment evaluation works content and greatly flow and it is inconsistent.If same comment is approved of
Number and opposition number are on a par, it may be considered that controversial caused by this works is quite big.
Therefore, if the approval number of comment is more, oppose that number is also more, then can keep the quality score of comment.
If the approval number of comment is more but opposes that number is general, the quality score of comment can be improved.If the approval of comment
Number is general, but opposes that number is higher, then can reduce the quality score of comment.
In some embodiments, the embodiment of the present invention also provides the sequencer procedure of comment, may include: the feelings according to comment
That feels is positive and negative, classifies to the comment data of target works, and the positive net exploxer comment and negative online friend for obtaining target works are commented
By;And the height according to quality score, positive net exploxer comment and negative net exploxer comment are ranked up respectively, target is obtained and makees
The front comment ranking results and negative reviews ranking results of product.
In the present embodiment, the ranking results got can open up view in the user interface, and user is facilitated to watch hot topic
Front comment and negative reviews.For example, showing front comment and negative reviews respectively on the both sides at interface, comment is shown
Diversity.
In some embodiments, it according to the website of comment source, can sort to front comment ranking results, negative reviews
As a result it carries out breaing up sequence.To avoid exhibition depending on comment concentrate on some website and have ignored the sound of the user of other websites
Sound.
In some embodiments, accession page can be provided, user can access the details of works by accession page.Such as
Shown in Fig. 6, access process may include step S810 to step S830, as follows:
S810 obtains the access request of target works.
S820, the works details of searched targets works.Wherein, works details include the comprehensive score result of target works.
S830, the works details of exhibition view target works.
Illustratively, in accession page, user inputs the target works to be accessed by voice or keyboard.Alternatively,
It is opened up in accession page in multiple works of view, clicks target works.Then, the works details exhibition view of target works is returned at interface
In.Wherein, works details may include the information such as the general view of works, encyclopaedia information, scoring comment situation, photo.
In the present embodiment, works details are in addition to including the comprehensive score of target works as a result, can also comment including first
Divide result, the second appraisal result and search temperature.Wherein, the first appraisal result indicates that user is the case where works are given a mark.The
Two appraisal results indicate the case where user comment works.And can also include comment ranking results, it is commented with opening up depending on popular
By.
In some embodiments, the commentary page can be provided, so that user is that works are given a mark or commented on.
Fig. 7-1 is please referred to 7-5.Wherein, Fig. 7-1 is that the frame of data handling procedure provided in an embodiment of the present invention is illustrated
Figure.Fig. 7-2 is the block schematic illustration of the intervention of data processing provided in an embodiment of the present invention.Fig. 7-3 is implementation of the present invention
One of works scoring and the comment exhibition view page that example provides applies exemplary schematic diagram.Fig. 7-4 is that the embodiment of the present invention provides
Works scoring apply exemplary schematic diagram with comment one of input page.Fig. 7-5 is that the works of the embodiment of the present invention score
With the rear end of Commentary Systems and the block schematic illustration of front end.
The present embodiment may include four modules, specific as follows by taking films and television programs as an example:
1, data acquisition module.
Data acquisition module is the foundation stone of the present embodiment, and the letter that we need to pay close attention to is obtained from the massive information of internet
Breath.
By the way of structural data excavation: from each website that online movie hangs down class obtain data, parse including
Video display entity information, score data, comment data, the structural data for searching for temperature.
2, data processing module
After grabbing structural data, the method which mainly utilizes all kinds of machine learning, data mining, to commenting
Processing is further processed by data.
2.1, multi-source data association fusion: to the data of the same works of description of source different web sites, data deduplication is carried out
And association, the comprehensive survey data of each side's viewpoint have been merged with output.
2.2, quality score: quality evaluation is carried out to the comment grabbed, exports the score between one [0,1], is indicated
The quality condition of the comment.
2.3, yellow back mark: yellow, reaction label are carried out to the comment grabbed, marked with filtering with yellow, reaction
Comment, to resist vulgar information.
2.4, sentiment analysis: calling NLP (Natural Language Processing, natural language processing) tool, right
The content of comment carries out front, negative, neutral three kinds of emotions are analyzed respectively, and given a mark.
2.5, according to the website of comment source, the row of breaing up offline Rank (sequence): is carried out to the comment data that will show
Sequence.To avoid exhibition depending on data be not concentrated on certain primary sites, and have ignored the sound of the user of other websites.
2.6, video display scoring calculates: according to the accounting of the positive negative term of emotion in the score data of online friend, comment data and searching
Rope temperature calculates the comprehensive score of target films and television programs.
3, data application module
The data of working process are applied in the searching system of films and television programs.It before application, can also be to processing number
According to being adjusted, including the following:
3.1, it risk control: is filtered for the comment data of yellow, reaction, low quality marking.
3.2, emergency data Interference service platform: for opened up on line depending on comment increased, delete, adjust sequence etc. operation.
3.3, the big badcase in face is influenced, the means of urgent intervention are provided.Badcase includes not meeting search user's body
The works search result and the abnormal works search result of performance during opening up view tested.The means of intervention are including again
Retrieval or manual retrieval etc..
4, in wire module
It may include receiving the online access of user to ask for instructions in the function of wire module, the information for retrieving films and television programs returns to
User terminal shows in the user terminal.
4.1, data retrieval: the online retrieving function based on inverted index is provided, retardation rate is less than 1/1000, the response time
Less than 50ns.The information of the films and television programs of retrieval is shown into the page in the user terminal, it can be as shown in Fig. 7-3.Scoring can
To include: comprehensive score result for 9.0 points, online friend's marking (the first appraisal result) is 9.2 points, and search temperature is 7.4 points, the whole network
Public sentiment (the second appraisal result) is 6.7 points.
4.2, the collection of user's scoring and comment: the function of allowing user to score films and television programs and comment on is provided.
As shown in Fig. 7-4." very rotten ", " poor ", " general ", " good " and " very good " this five standards of grading can be provided to user
Selection.And comment input frame is provided, input frame display reminding language " how is this film? evaluation several ".Pass through comment
Input frame can input the comment of user.
Referring to Fig. 8, the embodiment of the present invention provides a kind of scoring apparatus of works, comprising:
Data acquisition module 100, for obtaining the score data, comment data and search data of target works;
First grading module 200 obtains the first of the target works for the score data according to the target works
Appraisal result;
Second grading module 300 obtains the second of the target works for the comment data according to the target works
Appraisal result;
Temperature determining module 400 determines the search of the target works for the search data according to the target works
Temperature;And
Comprehensive score module 500, for being tied according to first appraisal result of the target works, second scoring
Fruit and described search temperature determine the comprehensive score result of the target works.
In one embodiment, described device further include:
Filtering module is examined, for being filtered out from the comment data of the target works according to preset examination standard
The comment of the examination standard is not met;
Quality score obtains module, for obtaining the quality score for meeting the comment of the examination standard;And quality mistake
Module is filtered, the comment for being less than given threshold for filtering out quality score from the comment for meeting the examination standard.
In one embodiment, second grading module includes:
Emotion acquiring unit obtains the emotion of the comment expression for carrying out sentiment analysis to filtered comment;With
And
Scoring computing unit obtains the second of the target works for the quality score and emotion according to the comment
Appraisal result.
In one embodiment, the quality score acquisition module includes:
Richness determination unit is determined for commenting on the plot, personage, scene and the personal view that include according to described
The abundant in content degree of the comment;
Word counting unit, for counting the number of words of the comment;And
Quality score determination unit determines the matter of the comment for the abundant in content degree and number of words according to the comment
Amount scoring.
In one embodiment, the quality score obtains module further include:
It approves of and opposes number acquiring unit, for obtaining the approval number of the approval comment and opposing the comment
Oppose number;
Quality score amending unit, for correcting the matter of the comment according to the approval number and the opposition number
Amount scoring.
In one embodiment, further includes:
Positive negative reviews obtain module, the comment for the positive and negative of the emotion according to comment, to the target works
Data are classified, and the positive net exploxer comment and negative net exploxer comment of the target works are obtained;And
Positive negative reviews sorting module, for the height according to quality score, respectively to the positive net exploxer comment and institute
It states negative net exploxer comment to be ranked up, obtains the front comment ranking results and negative reviews ranking results of the target works.
In one embodiment, further includes:
Access obtains module, for obtaining the access request of the target works;
Works retrieval module, for retrieving the works details of the target works;Wherein, the works details include described
The comprehensive score result of target works;And
Details exhibition view module, for opening up the works details for regarding the target works.
The function of described device can also execute corresponding software realization by hardware realization by hardware.It is described
Hardware or software include one or more modules corresponding with above-mentioned function.
It include processor and memory in the scoring structure of works in a possible design, the memory is used for
The scoring apparatus of works executes the scoring procedures of works in above-mentioned first aspect, the processor is configured to described for executing
The program stored in memory.The scoring apparatus of the works can also include communication interface, for works scoring apparatus with
Other equipment or communication.
The embodiment of the present invention also provides a kind of scoring terminal device of works, as shown in figure 9, the equipment includes: memory
21 and processor 22, being stored in memory 21 can be in the computer program on processor 22.Processor 22 executes computer journey
The methods of marking of the works in above-described embodiment is realized when sequence.The quantity of memory 21 and processor 22 can be one or more
It is a.
The equipment further include:
Communication interface 23, for the communication between processor 22 and external equipment.
Memory 21 may include high speed RAM memory, it is also possible to further include nonvolatile memory (non-volatile
Memory), a for example, at least magnetic disk storage.
If memory 21, processor 22 and the independent realization of communication interface 23, memory 21, processor 22 and communication are connect
Mouth 23 can be connected with each other by bus and complete mutual communication.Bus can be industry standard architecture (ISA,
Industry Standard Architecture) bus, external equipment interconnection (PCI, Peripheral Component) be total
Line or extended industry-standard architecture (EISA, Extended Industry Standard Component) bus etc..Always
Line can be divided into address bus, data/address bus, control bus etc..Only to be indicated with a thick line in Fig. 9, but simultaneously convenient for indicating
Only a bus or a type of bus are not indicated.
Optionally, in specific implementation, if memory 21, processor 22 and communication interface 23 are integrated in chip piece
On, then memory 21, processor 22 and communication interface 23 can complete mutual communication by internal interface.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment of the present invention or example.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
In addition, term " first ", " second " are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance
Or implicitly indicate the quantity of indicated technical characteristic." first " is defined as a result, the feature of " second " can be expressed or hidden
It include at least one this feature containing ground.In the description of the present invention, the meaning of " plurality " is two or more, unless otherwise
Clear specific restriction.
Any process described otherwise above or method description are construed as in flow chart or herein, and expression includes
It is one or more for realizing specific logical function or process the step of executable instruction code module, segment or portion
Point, and the range of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discussed suitable
Sequence, including according to related function by it is basic simultaneously in the way of or in the opposite order, Lai Zhihang function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicating, propagating or passing
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.
The computer-readable medium of the embodiment of the present invention can be computer-readable signal media or computer-readable deposit
Storage media either the two any combination.The more specific example at least (non-exclusive of computer readable storage medium
List) include the following: there is the electrical connection section (electronic device) of one or more wirings, portable computer diskette box (magnetic dress
Set), random access memory (RAM), read-only memory (ROM), erasable edit read-only storage (deposit by EPROM or flash
Reservoir), fiber device and portable read-only memory (CDROM).In addition, computer readable storage medium can even is that
Can the paper of print routine or other suitable media on it because can for example be swept by carrying out optics to paper or other media
It retouches, is then edited, interprets or handled when necessary with other suitable methods electronically to obtain program, then will
It is stored in computer storage.
In embodiments of the present invention, computer-readable signal media may include in a base band or as carrier wave a part
The data-signal of propagation, wherein carrying computer-readable program code.The data-signal of this propagation can use a variety of
Form, including but not limited to electromagnetic signal, optical signal or above-mentioned any appropriate combination.Computer-readable signal media is also
It can be any computer-readable medium other than computer readable storage medium, which can send, pass
It broadcasts or transmits for instruction execution system, input method or device use or program in connection.Computer can
The program code for reading to include on medium can transmit with any suitable medium, including but not limited to: wirelessly, electric wire, optical cable, penetrate
Frequently (Radio Frequency, RF) etc. or above-mentioned any appropriate combination.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: having a logic gates for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
Those skilled in the art are understood that realize all or part of step that above-described embodiment method carries
It suddenly is the program that relevant hardware can be instructed to complete by program, which can store in a kind of computer-readable storage
In medium, which when being executed, includes the steps that one or a combination set of embodiment of the method.
It, can also be in addition, each functional unit in each embodiment of the present invention can integrate in a processing module
It is that each unit physically exists alone, can also be integrated in two or more units in a module.Above-mentioned integrated mould
Block both can take the form of hardware realization, can also be realized in the form of software function module.If integrated module with
The form of software function module is realized and when sold or used as an independent product, also can store computer-readable at one
In storage medium.Storage medium can be read-only memory, disk or CD etc..
More than, only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto, and it is any to be familiar with
Those skilled in the art in the technical scope disclosed by the present invention, can readily occur in its various change or replacement, these
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of protection of the claims
It is quasi-.
Claims (16)
1. a kind of methods of marking of works characterized by comprising
Obtain the score data, comment data and search data of target works;
According to the score data of the target works, the first appraisal result of the target works is obtained;
According to the comment data of the target works, the second appraisal result of the target works is obtained;
According to the search data of the target works, the search temperature of the target works is determined;And
According to first appraisal result, second appraisal result and described search temperature of the target works, institute is determined
State the comprehensive score result of target works.
2. the method as described in claim 1, which is characterized in that further include:
According to preset examination standard, is filtered out from the comment data of the target works and do not meet commenting for the examination standard
By;
Obtain the quality score for meeting the comment of the examination standard;And
The comment that quality score is less than given threshold is filtered out from the comment for meeting the examination standard.
3. method according to claim 2, which is characterized in that according to the comment data of the target works, obtain the mesh
It is denoted as the second appraisal result of product, comprising:
Sentiment analysis is carried out to filtered comment, obtains the emotion of the comment expression;And
According to the quality score and emotion of the comment, the second appraisal result of the target works is obtained.
4. method according to claim 2, which is characterized in that the quality score for meeting the comment of the examination standard is obtained,
Include:
Plot, personage, scene and the personal view for including are commented on according to described, determines the abundant in content degree of the comment;
Count the number of words of the comment;And
According to the abundant in content degree and number of words of the comment, the quality score of the comment is determined.
5. method as claimed in claim 4, which is characterized in that the quality score for meeting the comment of the examination standard is obtained,
Further include:
Obtain the opposition number approved of number and oppose the comment for approving of the comment;
According to the approval number and the opposition number, the quality score of the comment is corrected.
6. method as claimed in claim 3, which is characterized in that further include:
According to comment emotion it is positive and negative, classify to the comment data of the target works, obtain the target and make
The positive net exploxer comment and negative net exploxer comment of product;And
According to the height of quality score, the positive net exploxer comment and the negative net exploxer comment are ranked up respectively, obtained
The front comment ranking results and negative reviews ranking results of the target works.
7. the method as described in claim 1, which is characterized in that further include:
Obtain the access request of the target works;
Retrieve the works details of the target works;Wherein, the works details include the comprehensive score knot of the target works
Fruit;And
Exhibition regards the works details of the target works.
8. a kind of scoring apparatus of works characterized by comprising
Data acquisition module, for obtaining the score data, comment data and search data of target works;
First grading module obtains the first scoring knot of the target works for the score data according to the target works
Fruit;
Second grading module obtains the second scoring knot of the target works for the comment data according to the target works
Fruit;
Temperature determining module determines the search temperature of the target works for the search data according to the target works;With
And
Comprehensive score module, for first appraisal result, second appraisal result and institute according to the target works
Search temperature is stated, determines the comprehensive score result of the target works.
9. device as claimed in claim 8, which is characterized in that further include:
Filtering module is examined, for filtering out and not being inconsistent from the comment data of the target works according to preset examination standard
Close the comment of the examination standard;
Quality score obtains module, for obtaining the quality score for meeting the comment of the examination standard;And
Mass filter module, for filtering out quality score commenting less than given threshold from the comment for meeting the examination standard
By.
10. device as claimed in claim 9, which is characterized in that second grading module includes:
Emotion acquiring unit obtains the emotion of the comment expression for carrying out sentiment analysis to filtered comment;And
Score computing unit, for the quality score and emotion according to the comment, obtains the second scoring of the target works
As a result.
11. device as claimed in claim 9, which is characterized in that the quality score obtains module and includes:
Richness determination unit, for according to it is described comment on include plot, personage, scene and personal view, determine described in
The abundant in content degree of comment;
Word counting unit, for counting the number of words of the comment;And
Quality score determination unit determines that the quality of the comment is commented for the abundant in content degree and number of words according to the comment
Point.
12. device as claimed in claim 11, which is characterized in that the quality score obtains module further include:
It approves of and opposes number acquiring unit, for obtaining the opposition approved of number and oppose the comment for approving of the comment
Number;
Quality score amending unit, for according to the approval number and the opposition number, the quality for correcting the comment to be commented
Point.
13. device as claimed in claim 10, which is characterized in that further include:
Positive negative reviews obtain module, for the positive and negative of the emotion according to comment, to the comment data of the target works
Classify, obtains the positive net exploxer comment and negative net exploxer comment of the target works;And
Positive negative reviews sorting module, for the height according to quality score, respectively to the positive net exploxer comment and described negative
Face net exploxer comment is ranked up, and obtains the front comment ranking results and negative reviews ranking results of the target works.
14. device as claimed in claim 13, which is characterized in that further include:
Access obtains module, for obtaining the access request of the target works;
Works retrieval module, for retrieving the works details of the target works;Wherein, the works details include the target
The comprehensive score result of works;And
Details exhibition view module, for opening up the works details for regarding the target works.
15. a kind of scoring terminal device for realizing works, which is characterized in that the terminal device includes:
One or more processors;
Storage device, for storing one or more programs;
When one or more of programs are executed by one or more of processors, so that one or more of processors
Realize the method as described in any in claim 1-7.
16. a kind of computer readable storage medium, is stored with computer program, which is characterized in that the program is held by processor
The method as described in any in claim 1-7 is realized when row.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811541347.1A CN109657144A (en) | 2018-12-17 | 2018-12-17 | Methods of marking, device, storage medium and the terminal device of works |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811541347.1A CN109657144A (en) | 2018-12-17 | 2018-12-17 | Methods of marking, device, storage medium and the terminal device of works |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109657144A true CN109657144A (en) | 2019-04-19 |
Family
ID=66113641
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811541347.1A Pending CN109657144A (en) | 2018-12-17 | 2018-12-17 | Methods of marking, device, storage medium and the terminal device of works |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109657144A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334265A (en) * | 2019-07-10 | 2019-10-15 | 杭州二更网络科技有限公司 | A kind of novel video methods of marking and device |
CN110569377A (en) * | 2019-09-11 | 2019-12-13 | 腾讯科技(深圳)有限公司 | Media file processing method and device |
CN111563154A (en) * | 2020-04-28 | 2020-08-21 | 掌阅科技股份有限公司 | Method for determining score of electronic book, computing equipment and computer storage medium |
CN111737566A (en) * | 2020-05-15 | 2020-10-02 | 深圳市战音科技有限公司 | Work sorting method, device and storage medium |
CN111898015A (en) * | 2020-08-28 | 2020-11-06 | 深圳市欢太科技有限公司 | Book heat value acquisition method and device, terminal device and storage medium |
CN113792162A (en) * | 2021-07-27 | 2021-12-14 | 深圳市星范儿文化科技有限公司 | Reading match processing method and system based on intelligent reading pavilion |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140081990A1 (en) * | 2007-08-28 | 2014-03-20 | International Business Machines Corporation | Managing user ratings in a web services environment |
CN104932966A (en) * | 2015-06-19 | 2015-09-23 | 广东欧珀移动通信有限公司 | Method and device for detecting false downloading times of application software |
CN106296282A (en) * | 2016-08-08 | 2017-01-04 | 南京大学 | A kind of net purchase Product evaluation method marked based on user comment and history |
CN108090175A (en) * | 2017-12-15 | 2018-05-29 | 四川长虹电器股份有限公司 | Film temperature appraisal procedure |
CN108460010A (en) * | 2018-01-17 | 2018-08-28 | 南京邮电大学 | A kind of comprehensive grade model implementation method based on sentiment analysis |
CN108595527A (en) * | 2018-03-28 | 2018-09-28 | 中山大学 | A kind of personalized recommendation method and system of the multi-source heterogeneous information of fusion |
-
2018
- 2018-12-17 CN CN201811541347.1A patent/CN109657144A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140081990A1 (en) * | 2007-08-28 | 2014-03-20 | International Business Machines Corporation | Managing user ratings in a web services environment |
CN104932966A (en) * | 2015-06-19 | 2015-09-23 | 广东欧珀移动通信有限公司 | Method and device for detecting false downloading times of application software |
CN106296282A (en) * | 2016-08-08 | 2017-01-04 | 南京大学 | A kind of net purchase Product evaluation method marked based on user comment and history |
CN108090175A (en) * | 2017-12-15 | 2018-05-29 | 四川长虹电器股份有限公司 | Film temperature appraisal procedure |
CN108460010A (en) * | 2018-01-17 | 2018-08-28 | 南京邮电大学 | A kind of comprehensive grade model implementation method based on sentiment analysis |
CN108595527A (en) * | 2018-03-28 | 2018-09-28 | 中山大学 | A kind of personalized recommendation method and system of the multi-source heterogeneous information of fusion |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334265A (en) * | 2019-07-10 | 2019-10-15 | 杭州二更网络科技有限公司 | A kind of novel video methods of marking and device |
CN110569377A (en) * | 2019-09-11 | 2019-12-13 | 腾讯科技(深圳)有限公司 | Media file processing method and device |
CN110569377B (en) * | 2019-09-11 | 2021-08-24 | 腾讯科技(深圳)有限公司 | Media file processing method and device |
CN111563154A (en) * | 2020-04-28 | 2020-08-21 | 掌阅科技股份有限公司 | Method for determining score of electronic book, computing equipment and computer storage medium |
CN111737566A (en) * | 2020-05-15 | 2020-10-02 | 深圳市战音科技有限公司 | Work sorting method, device and storage medium |
CN111898015A (en) * | 2020-08-28 | 2020-11-06 | 深圳市欢太科技有限公司 | Book heat value acquisition method and device, terminal device and storage medium |
CN113792162A (en) * | 2021-07-27 | 2021-12-14 | 深圳市星范儿文化科技有限公司 | Reading match processing method and system based on intelligent reading pavilion |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109657144A (en) | Methods of marking, device, storage medium and the terminal device of works | |
US20200372018A1 (en) | Query Results Ranked for Original & Real-Time Parameters | |
CN104899302B (en) | Recommend the method and apparatus of music to user | |
US9710825B1 (en) | Meaning-based advertising and document relevance determination | |
CN108197330B (en) | Data digging method and device based on social platform | |
CN109543111A (en) | Recommendation information screening technique, device, storage medium and server | |
US11080323B2 (en) | Search method and apparatus | |
US20100125540A1 (en) | System And Method For Providing Robust Topic Identification In Social Indexes | |
CN110737859B (en) | UP master matching method and device | |
CN110704674A (en) | Video playing integrity prediction method and device | |
CN107229666B (en) | A kind of interest heuristic approach and device based on recommender system | |
CN102929966B (en) | A kind of for providing the method and system of personalized search list | |
CN106021449A (en) | Searching method and device for mobile terminal and mobile terminal | |
CN104636448B (en) | A kind of music recommends method and device | |
DE112012003366T5 (en) | Synthesis of directories, domains and subdomains | |
CN108280124A (en) | Product classification method and device, ranking list generation method and device, electronic equipment | |
CN110457566A (en) | Method, device, electronic equipment and storage medium | |
CN108255840A (en) | A kind of recommendation method and system of song | |
CN108416627A (en) | A kind of brand influence force monitoring method and system based on internet data | |
CN106021302A (en) | Intelligent recommendation technique based wireless music recommendation method and system | |
CN109657043A (en) | Automatically generate the method, apparatus, equipment and storage medium of article | |
CN108804491A (en) | item recommendation method, device, computing device and storage medium | |
Vargas et al. | Term-by-term query auto-completion for mobile search | |
Toma et al. | To read or not to read: Modeling online newspaper reading satisfaction and its impact on revisit intention and word-of-mouth | |
CN112085980A (en) | Intelligent education machine starting system |
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 |