CN112069802A - Article quality scoring method, article quality scoring device and storage medium - Google Patents
Article quality scoring method, article quality scoring device and storage medium Download PDFInfo
- Publication number
- CN112069802A CN112069802A CN202010873079.4A CN202010873079A CN112069802A CN 112069802 A CN112069802 A CN 112069802A CN 202010873079 A CN202010873079 A CN 202010873079A CN 112069802 A CN112069802 A CN 112069802A
- Authority
- CN
- China
- Prior art keywords
- article
- static
- feature
- score
- quality
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013077 scoring method Methods 0.000 title claims abstract description 46
- 230000003068 static effect Effects 0.000 claims abstract description 341
- 238000012545 processing Methods 0.000 claims description 20
- 230000004044 response Effects 0.000 claims description 4
- 238000000034 method Methods 0.000 abstract description 45
- 230000008569 process Effects 0.000 abstract description 22
- 230000006399 behavior Effects 0.000 description 20
- 238000010586 diagram Methods 0.000 description 14
- 238000004891 communication Methods 0.000 description 10
- 238000005516 engineering process Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 230000002829 reductive effect Effects 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012552 review Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 230000009967 tasteless effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
-
- 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
- G06F16/953—Querying, e.g. by the use of web search engines
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Data Mining & Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The disclosure relates to an article quality scoring method, an article quality scoring device and a storage medium. The article quality scoring method comprises the following steps: determining a plurality of static features contained in a chapter to be scored, and determining a static feature score and a static feature weight of each static feature in the plurality of static features; the static characteristic score corresponding to each static characteristic in the plurality of static characteristics is multiplied by the static characteristic weight and then accumulated to obtain a static characteristic total score; and determining the article quality score of the article to be scored based on the total static characteristic score. By the article quality scoring method provided by the disclosure, the article quality scoring of the article to be scored can be efficiently and accurately determined, a high-quality article is recommended for a user, and a foundation is laid for improving the satisfaction degree of the user in the process of acquiring the recommended article.
Description
Technical Field
The present disclosure relates to the field of article quality scoring technologies, and in particular, to an article quality scoring method, an article quality scoring apparatus, and a storage medium.
Background
With the rapid development of internet technology, accessing the internet through a browser or some other browser-like application has become an important means for users to obtain information.
In order to provide a good use experience for the user, a browser or a browser-like application program will recommend articles to the user to be added every day. However, since there are many low-quality articles in the newly added articles, if a large number of articles are recommended to the user, the user will be lost. In order to reduce the loss of the user and increase the experience of the user, it becomes important to recommend high-quality articles to the user. Therefore, in the related art, article recommendation is performed on a user by scoring the quality of the article and based on the scoring result.
At present, in the related art, the quality scoring of the article to be scored is realized through a text scoring feature based on the article to be scored and a pre-constructed scoring model. However, this method only uses text data of an article, and does not take into full consideration other features of the article, such as a text picture of the article, a classification of the article, and the like, and therefore, the accuracy of scoring the quality of the article to be scored is low.
In the related technology, browsing behavior information of a user when browsing a target article (which may also be called an article to be scored) is obtained, a browsing behavior score of the user on the target article is obtained according to the browsing behavior information and a corresponding browsing behavior coefficient, and finally, an article quality score of the target article is obtained according to the obtained browsing behavior scores of the plurality of users on the target article. However, this method only uses the browsing behavior data of the articles by the user, and does not fully utilize the existing features of the articles themselves, thereby resulting in the accuracy of the quality score of the target article. Further, based on the method, if the quality of the target article is to be evaluated, the target article needs to be recommended to a plurality of users, and the possibility of recommending the low-quality target article to the users is easy to occur in the application process, so that poor experience is brought to the users.
Therefore, how to efficiently and accurately score the quality of articles becomes a focus of current attention.
Disclosure of Invention
In order to overcome the problems in the related art, the present disclosure provides an article quality scoring method, an article quality scoring apparatus, and a storage medium.
According to a first aspect of the embodiments of the present disclosure, there is provided an article quality scoring method, including: determining a plurality of static features contained in a chapter to be scored, and determining a static feature score and a static feature weight of each static feature in the plurality of static features; multiplying the static feature score corresponding to each static feature in the plurality of static features by the static feature weight, and accumulating to obtain a total static feature score; and determining the article quality score of the article to be scored based on the static characteristic total score.
In one embodiment, the article quality scoring method further comprises: presetting a plurality of characteristic threshold intervals based on the article type and the characteristic threshold of at least one reference static characteristic, wherein each characteristic threshold interval corresponds to a weight combination, and each weight combination comprises the weights of the plurality of static characteristics; the determining a static feature weight for each static feature of the plurality of static features comprises: determining a feature threshold value interval corresponding to the static feature of the article to be scored, which corresponds to the reference static feature, based on the type of the article to be scored, the static feature of the article to be scored, which corresponds to the reference static feature, and the feature threshold value; determining a static feature weight for each static feature of the plurality of static features based on a combination of weights corresponding to the feature threshold interval.
In another embodiment, presetting a plurality of feature threshold intervals based on article types and at least one feature threshold of a reference static feature comprises: setting at least one characteristic threshold value for each preset reference static characteristic in a plurality of reference static characteristics, and setting different characteristic threshold values for the reference static characteristics of different article types; and combining any two characteristic thresholds in the characteristic thresholds corresponding to all the reference static characteristics in the plurality of reference static characteristics to form a plurality of characteristic threshold intervals.
In another embodiment, the article quality scoring method further comprises: determining whether the chapter to be scored meets preset additional scoring standards, wherein the additional scoring standards comprise an adding standard and/or a subtracting standard; the determining the article quality score of the article to be scored based on the total static feature score comprises the following steps: and if the article to be scored meets a preset additional scoring standard, adding and/or subtracting the total score of the static features according to the adding and/or subtracting standard to obtain the article quality score of the article to be scored.
In another embodiment, before determining a plurality of static features contained in a document to be scored, the method for scoring the quality of the article further comprises: determining the article to be scored as a non-low quality article.
In another embodiment, the article quality scoring method further comprises: and in response to determining that the article to be scored is a low-quality article, determining that the article quality score of the article to be scored is the lowest score.
In yet another embodiment, the static features include one or more of a body length, a paragraph, a number of body pictures, a body picture clarity, a low quality feature, and an author, and the determining a static feature score for each of the plurality of static features includes: determining the text length score of the article according to the text length of the article; determining a paragraph score according to the number of paragraphs; determining the number value of the text pictures according to the number of the text pictures; determining the definition score of the text picture according to the definition of the text picture; determining a low-quality feature score according to the low-quality features; the author score is determined according to the rank of the author.
According to a second aspect of the embodiments of the present disclosure, there is provided an article quality scoring apparatus, including: the static feature determining module is used for determining a plurality of static features contained in the chapter to be scored, and determining the static feature score and the static feature weight of each static feature in the plurality of static features; the processing module is used for multiplying the static feature score corresponding to each static feature in the plurality of static features by the static feature weight and then accumulating to obtain a total static feature score; and the article quality scoring module is used for determining the article quality score of the article to be scored based on the static characteristic total score.
In one embodiment, the article quality scoring apparatus further comprises: a feature threshold interval setting module, configured to preset a plurality of feature threshold intervals based on an article type and a feature threshold of at least one reference static feature, where each feature threshold interval corresponds to a weight combination, and each weight combination includes weights of the plurality of static features; the determine static characteristics module is to: determining a feature threshold value interval corresponding to the static feature of the article to be scored, which corresponds to the reference static feature, based on the type of the article to be scored, the static feature of the article to be scored, which corresponds to the reference static feature, and the feature threshold value; determining a static feature weight for each static feature of the plurality of static features based on a combination of weights corresponding to the feature threshold interval.
In yet another embodiment, the set feature threshold interval module is configured to: setting at least one characteristic threshold value for each preset reference static characteristic in a plurality of reference static characteristics, and setting different characteristic threshold values for the reference static characteristics of different article types; and combining any two characteristic thresholds in the characteristic thresholds corresponding to all the reference static characteristics in the plurality of reference static characteristics to form a plurality of characteristic threshold intervals.
In another embodiment, the article quality scoring apparatus further comprises: the judgment module is used for determining whether the seal to be scored meets a preset additional scoring standard or not, wherein the additional scoring standard comprises an adding standard and/or a subtracting standard; the article quality scoring module determines the article quality score of the article to be scored based on the total static feature score in the following mode: and if the article to be scored meets a preset additional scoring standard, adding and/or subtracting the total score of the static features according to the adding and/or subtracting standard to obtain the article quality score of the article to be scored.
In another embodiment, the article quality scoring apparatus further comprises: and the non-low-quality article determining module is used for determining the article to be scored as a non-low-quality article.
In another embodiment, the article quality scoring apparatus further comprises: and the low-quality article processing module is used for responding to the determination that the article to be scored is a low-quality article, and determining that the article quality score of the article to be scored is the lowest score.
In yet another embodiment, the static features include one or more of a length of text, a paragraph, a number of text pictures, a text picture clarity, a low quality feature, and an author, and the determine static features module determines the static feature score for each of the plurality of static features as follows: determining the text length score of the article according to the text length of the article; determining a paragraph score according to the number of paragraphs; determining the number value of the text pictures according to the number of the text pictures; determining the definition score of the text picture according to the definition of the text picture; determining a low-quality feature score according to the low-quality features; the author score is determined according to the rank of the author.
The technical scheme provided by the embodiment of the disclosure can have the following beneficial effects: the article quality scoring method provided by the disclosure fully utilizes each static feature of the article to be scored, obtains the total score of the static features by determining each static feature score and the static feature weight, determines the article quality score of the article to be scored based on the total score of the static features, can efficiently and accurately determine the article quality score of the article to be scored, recommends a high-quality article for a user, and lays a foundation for improving the satisfaction degree of the user in the process of obtaining the recommended article.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and together with the description, serve to explain the principles of the disclosure.
Fig. 1 shows a flow chart of a current method of quality scoring an article to be scored.
Figure 2 illustrates a flow chart of another current method for quality scoring of articles to be scored.
Fig. 3 is a flow diagram illustrating a method for article quality scoring in accordance with an exemplary embodiment.
Fig. 4 shows a schematic diagram of an application scenario in which the article quality scoring method is applied.
Fig. 5 is a flow diagram illustrating another article quality scoring method in accordance with an exemplary embodiment.
FIG. 6 illustrates a flow chart for determining a static feature weight for each of a plurality of static features.
Fig. 7 shows a flowchart for presetting a plurality of feature threshold intervals based on article types and at least one feature threshold of a reference static feature.
FIG. 8 is a flow diagram illustrating yet another article quality scoring method in accordance with an illustrative embodiment.
Fig. 9 is a flow diagram illustrating another article quality scoring method in accordance with an exemplary embodiment.
Fig. 10 is a block diagram illustrating an article quality scoring apparatus in accordance with an exemplary embodiment.
Fig. 11 is a block diagram illustrating an apparatus for article quality scoring in accordance with an example embodiment.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
Currently in an era of information explosion, browsers or browser-like applications, for example: clients such as a news push application and an MIUI browser add a large amount of articles every day. These new articles are various and may contain low quality articles, such as: advertisement articles, headline party articles, and the like. If a large number of articles are recommended to the user, the reading experience of the user is greatly reduced, and the loss of the user is caused. In addition, the newly-added articles also contain articles with good quality, and if related articles are pushed to the user according to the characteristics and the preference of the user, the experience feeling of the user can be improved, so that the user can be better kept. Therefore, how to efficiently and accurately score the quality of the articles becomes especially important.
Fig. 1 shows a flow chart of a current method of quality scoring an article to be scored.
As shown in fig. 1, in the related art, the quality scoring of the article to be scored may be implemented by a scoring model constructed in advance based on the text scoring features of the article to be scored. However, this method only uses text data of an article, and does not take into full consideration other features of the article, such as a text picture of the article, a classification of the article, and the like, and therefore, the accuracy of scoring the quality of the article to be scored is low.
In one example, the stereotactic characteristics, chapter structure characteristics and vocabulary semantic characteristics of some articles to be scored are good, but if the texts of the articles do not have any pictures, the articles are boring and tasteless for the user to read, and the articles have poor visual sense, which finally results in poor experience of the user. Or, if some advertisement content is included in the article to be scored, the user can feel the article to be scored. From a practical point of view, the overall quality of these articles is not high, but under this scheme, the quality scores of such articles would be made high.
Figure 2 illustrates a flow chart of another current method for quality scoring of articles to be scored.
As shown in fig. 2, in the related art, browsing behavior information of a user when browsing a target article (which may also be referred to as a to-be-scored article) may also be obtained, a browsing behavior score of the user on the target article is obtained according to the browsing behavior information and a corresponding browsing behavior coefficient, and finally, an article quality score of the target article is obtained according to the obtained browsing behavior scores of the plurality of users on the target article. However, this method only uses the browsing behavior data of the articles by the user, and does not fully utilize the existing features of the articles themselves, thereby resulting in the accuracy of the quality score of the target article.
Further, under the scheme, if the target article itself belongs to an article with good quality, but when browsing behaviors of a plurality of collected users are collected, if most of the selected users are users who are not interested in the article, but other users who are not collected and interested in the article exist in reality, the target article is scored into a low-quality article according to the scheme, and the scoring accuracy is reduced.
Further, in the scheme for scoring the quality of the articles based on the browsing information of the users, if the quality of the target article is evaluated, the article to be scored needs to be recommended to a plurality of users first, and then browsing behaviors of the articles to be scored of the plurality of users are acquired. In this process, if the target article recommended to the user belongs to a low-quality article, the quality score of the article to be scored can be calculated to be a low score according to the browsing behavior of the user, but the low-quality article brings a bad experience to the user, and thus the user may be lost.
Thus, the method for scoring the quality of the article in the related art needs to be further optimized.
The embodiment of the disclosure provides an article quality scoring method, in which scoring is performed based on a plurality of static features of an article, so that the article quality scoring of the article to be scored is efficiently and accurately determined, a high-quality article is recommended to a user, and a foundation is laid for the satisfaction of the user in the process of acquiring the recommended article.
In an embodiment of the present disclosure, article quality scoring is performed before pushing to a user, so as to further ensure the quality of the pushed article.
Fig. 3 is a flow diagram illustrating a method for article quality scoring in accordance with an exemplary embodiment.
In an exemplary embodiment of the present disclosure, as shown in fig. 3, the article scoring method may include steps S11-S13. The steps will be described separately below.
In step S11, a plurality of static features included in the chapter to be scored are determined, and a static feature score and a static feature weight of each of the plurality of static features are determined.
In an example of the present disclosure, a static feature may be understood as a non-dynamic feature about an article to be scored. For example, static features of an article to be scored may include text length, paragraphs, number of text pictures, text picture clarity, low quality features, authors, and so forth. In the present disclosure, the static features are not specifically limited, and if new static features exist subsequently to evaluate the quality of the article, the new static features can still be applied to the article quality scoring method related to the present disclosure.
As can be seen from the above description, the static features of the article to be evaluated basically cover various aspects related to the features of the article itself, such as texts, pictures, paragraphs, authors, low-quality features, and the like.
The method and the device for scoring the article quality can determine the static feature scores and the static feature weights respectively aiming at the static features of the article to be scored, score the article quality based on the static feature scores and the static feature weights of the static features of the article to be scored, and score the article quality more accurately.
In step S12, the static feature score corresponding to each of the plurality of static features is multiplied by the static feature weight and then accumulated to obtain a total static feature score.
In the application process, the static feature score corresponding to each static feature in the plurality of static features can be multiplied by the static feature weight and then accumulated to obtain the total static feature score of the article to be scored.
It should be noted that each static feature weight may be determined according to the article type of the article to be evaluated, the text of the article, and the picture condition of the article, and each static feature weight may also be determined according to other manners.
In step S13, an article quality score for the article to be scored is determined based on the static feature total score.
In one example, the article quality scores of the articles to be scored may be determined according to the total scores of the static features determined by the respective static features. In one possible implementation, the articles to be scored may be divided into high quality articles, medium quality articles, and low quality articles based on the article quality scores of the articles to be scored.
In a possible implementation manner, when an article to be pushed to a user is newly added to a browser or an application program similar to the browser, the article quality scoring method provided by the embodiment of the disclosure may be used to score the newly added article, and based on the result of the article quality scoring, the newly added article is recommended to the user in a targeted manner.
In an example, if the article quality scores of some newly added articles are low and are evaluated as low-quality articles, the low-quality articles can be filtered out when article recommendation is performed on the user according to needs. For example, if a certain user is found to be very repugnant to a headline party or advertisement-type article through behavior analysis of the user, then when article recommendation is made to the user, low-quality articles belonging to the headline party or advertisement-type can be actively filtered out to avoid the user from receiving the articles of the type.
Fig. 4 shows a schematic diagram of an application scenario in which the article quality scoring method is applied. In fig. 4, 1 is an article, 2 is an article quality scoring method according to the present disclosure, 3 is a personalized recommendation system, and 4 is a user. When newly added articles exist, the quality scores of the articles are determined according to the article quality method related to the disclosure, then the articles with different qualities are recommended to the user through the personalized recommendation system according to the user characteristics, after the articles are exposed to the user, the user can feed back the articles, and then behavior data of the articles are collected according to the feedback of the user, so that the articles are more accurately recommended to the user later.
In one example, as shown in fig. 4, if the user 4 is very interested in the gourmet article 1, and the user finds through the previous behavior data analysis that the user has a short reading time and no other operation on the article with the article quality score of the gourmet article 1, while the user has a long reading time and often reviews or collects the article with the higher quality score. Then, for a food article 1 newly added to a browser or an application program similar to the browser, the article quality scoring method 2 provided in the embodiment of the present disclosure may be used to score the article quality of the newly added food article 1, and recommend the food article with higher article quality score to the user 4 through the personalized recommendation system 3.
In yet another example, a user often reads or reviews high quality articles and medium quality articles and does not have a clear preference for article type, then article recommendations may be made to the user by multi-categorizing high quality articles and medium quality articles.
It should be noted that, after recommending the article to the user, the user may give feedback to the article. In an embodiment, behavior data of the user can be obtained based on feedback made by the user, and a basis is laid for recommending articles which meet requirements of the user better to the user in the future.
The article quality scoring method provided by the disclosure fully utilizes each static feature of the article to be scored, obtains the total score of the static features by determining the score and the weight of the static features, and determines the article quality score of the article to be scored based on the total score of the static features. The method and the device can efficiently and accurately determine the article quality score of the article to be scored, recommend the article with high quality for the user, and lay a foundation for improving the satisfaction degree of the user in the process of acquiring the recommended article.
The process of article quality scoring will be illustrated by the following examples.
In the embodiment of the present disclosure, a static feature score determination process is first described.
In an exemplary embodiment of the present disclosure, the static features include one or more of a text length, a paragraph, a number of text pictures, a text picture clarity, low quality features, and an author. Determining the static feature score for each static feature of the plurality of static features may be performed in the following manner.
In an example, an article text length score can be determined from the article text length. The method for determining the text length score of the article can be realized by the following formula:
wherein, body Len represents the text length of the article to be scored. l1 and l2 respectively represent two thresholds of text length of the article to be scored corresponding to different article types, where l1 is the smaller threshold (e.g., X above)Small600), l2 is a larger threshold (e.g., X above)Big (a)1000). w1 and w2 denote two parameters, w1 and w2 can be set according to l1 and l 2.
In an example, a paragraph score may be determined according to the number of paragraphs. Wherein determining the paragraph score can be accomplished by the following equation:
wherein, the paragraphNum represents the number of paragraphs of the article.
In an example, the text picture score value may be determined from the text picture count. Wherein, the determination of the text picture score value can be realized by the following formula:
wherein imgNum represents the number of text pictures. n2 denotes the article pair to be scoredThe larger of the two thresholds for the number of text pictures for different article types (e.g., P above)Big (a)=5)。
In an example, the text picture clarity score may be determined from the text picture clarity. The definition score of the text picture can be determined through the following formula:
wherein imgcrity represents the sharpness value of a picture, and n represents the number of text pictures.
In an example, a low-quality feature score may be determined from the low-quality features. Wherein determining the low-quality feature score may be accomplished by:
negFeatureScore=min(negFeatureScore1,negFeatureScore2……)
wherein the score of the total low-quality features is the minimum of all the low-quality feature scores.
In an example, the author score may be determined according to the rank of the author. Wherein determining the author score may be accomplished by the following formula:
authorScore=0.2*level
wherein: level represents the number of author levels. In one example, the author level may be divided into 5 levels: 1. 2, 3, 4 and 5. The author score is defined in terms of author rating size, with higher author ratings being the higher the author score.
Further, the total static feature score may be obtained by multiplying the static feature score of the 6 static features by the static feature weight and then accumulating the result. Wherein the static feature total score can be determined by the following formula:
wherein: i represents the ith static feature, factor represents the score of the static feature, and weight represents the weight of the static feature corresponding to the static feature. In the embodiment of the present disclosure, the total number of the above 6 static features is referred to: text length, paragraphs, number of text pictures, text picture sharpness, low quality features, and author.
The following description of the determination process of the static feature weight is provided in the embodiments of the present disclosure.
In an implementation manner of the embodiment of the present disclosure, weights of static features may be preset, the weights of the static features corresponding to each article type form a weight combination, each weight combination includes weights of a plurality of static features, and when determining the static feature weight, the static feature weight may be determined according to a preset weight combination, and the article quality score may be performed.
Fig. 5 is a flow diagram illustrating another article quality scoring method in accordance with an exemplary embodiment.
In an exemplary embodiment of the present disclosure, as shown in fig. 5, the article quality scoring method may include steps S21-S24. The steps will be described separately below.
In step S21, a plurality of feature threshold intervals are preset based on the article type and the feature threshold of at least one reference static feature, each feature threshold interval corresponds to a weight combination, wherein each weight combination includes weights of a plurality of static features.
In step S22, a plurality of static features included in the chapter to be scored are determined, and a static feature score and a static feature weight of each of the plurality of static features are determined.
In step S23, the static feature score corresponding to each of the plurality of static features is multiplied by the static feature weight and then accumulated to obtain a total static feature score.
In step S24, an article quality score for the article to be scored is determined based on the static feature total score.
The steps S22 to S24 are the same as the steps S11 to S13 in the previous embodiment, and the related explanation, description and beneficial effects thereof are please refer to the above description of the steps S11 to S13, which is not repeated herein. Step S21 will be described in detail below.
In the application process, a plurality of characteristic threshold intervals can be preset based on the article type and the characteristic threshold of at least one reference static characteristic. The article types can include gourmet articles, hour articles, comic articles and the like. Reference to static features may be understood as features that to some extent characterize an article. In an example, the reference static feature can be a length of a body of an article, a number of pictures of the body, and the like. In the present disclosure, the reference static feature is not particularly limited.
In a possible embodiment, the feature threshold value of each reference static feature may be at least one. In one example, for a gourmet article, when the reference static feature is body length, there may be two feature thresholds corresponding, for example, a larger threshold (1000) and a smaller threshold (800). Further, three feature threshold intervals (L ≧ 1000, 800 < L < 1000, L ≦ 800, where L represents the text length) may be set for static features with respect to the text length based on the larger threshold and the smaller threshold.
It should be noted that each feature threshold interval corresponds to a weight combination, and each weight combination includes weights of a plurality of static features. In the application process, the static feature weight of the static feature in the article to be scored can be determined based on the weight of the corresponding static feature in the feature threshold interval.
And further, multiplying the static feature score of the article to be scored by the static feature weight, accumulating to obtain a static feature total score, and determining the article quality score of the article to be scored based on the static feature total score.
As can be seen from the above description, in the embodiment of the present disclosure, the static feature weight of the static feature in the article to be scored may be determined based on the weight of the corresponding static feature in the feature threshold interval.
The present disclosure will describe a process of determining a static feature weight of each static feature in a plurality of static features in an article to be scored based on a weight of a static feature corresponding to a feature threshold interval by the following embodiments.
FIG. 6 illustrates a flow chart for determining a static feature weight for each of a plurality of static features.
In an exemplary embodiment of the present disclosure, determining the static feature weight of each of the plurality of static features may include steps S31 and S32. The steps will be described separately below.
In step S31, a feature threshold interval corresponding to the reference static feature in the article to be scored is determined based on the type of the article to be scored, the static feature corresponding to the reference static feature in the article to be scored, and the feature threshold.
In the application process, because the types of the articles are different, the static features have different feature thresholds for the same reference static feature. In one example, for a gourmet article, when the reference static feature is body length, there may be two feature thresholds corresponding, for example, a larger threshold (1000) and a smaller threshold (800). For an article of the political class, when the reference static feature is a text length, there may be two feature thresholds corresponding, for example, a larger threshold (2000) and a smaller threshold (1000).
In step S32, a static feature weight for each of the plurality of static features is determined based on the combination of weights corresponding to the feature threshold interval.
It should be noted that the characteristic threshold interval may also represent a value range of the reference static characteristic, besides including the weight combination. Whether the static feature weight of the article to be scored can be determined according to the weight combination included in the feature threshold interval is determined by judging whether the static feature corresponding to the reference static feature in the article to be scored is located in the feature threshold interval.
The present disclosure will explain a process of determining a plurality of characteristic threshold intervals by the following embodiments.
Fig. 7 shows a flowchart for presetting a plurality of feature threshold intervals based on article types and at least one feature threshold of a reference static feature.
In an exemplary embodiment of the present disclosure, the presetting of the plurality of feature threshold intervals may include steps S41 and S42 based on the article type and the feature threshold of the at least one reference static feature.
In step S41, at least one feature threshold is set for each of a plurality of preset reference static features, and different feature thresholds are set for reference static features of different article types.
In step S42, any two feature threshold values of the feature threshold values corresponding to all of the plurality of reference static features are combined to form a plurality of feature threshold value sections.
In an example, two reference static features (e.g., body length and number of body pictures) may be determined. Continuing with the gourmet article example, the text length may include two thresholds, and the number of text pictures may also include two thresholds. For convenience of description, let the larger threshold for text length be XBig (a)(1000) (ii) a The smaller threshold for text length is XSmall(800) (ii) a The larger threshold for the number of text pictures is YBig (a)(5) (ii) a The smaller threshold for the number of text pictures is YSmall(0). Further, based on XBig (a)And XSmallThree feature threshold intervals (L is more than or equal to 1000, L is more than 800 and less than 1000, L is less than or equal to 800, wherein L represents the text length) can be set for the static features related to the text length; based on YBig (a)And YSmallThree feature threshold intervals (P ≧ 5, 0 < P < 5, P ≦ 5, where P represents the number of text pictures) may be set for static features with respect to the number of text pictures.
Further, the two reference static features of the text length and the text picture number can be combined, and the feature threshold interval is combined, so that 9(3 × 3) different feature threshold interval conditions can be formed, and a feature threshold interval similar to a nine-square grid is formed. Table 1 may be referred to.
TABLE 1 Sudoku of different characteristic threshold intervals
L≤XSmall,P≥YBig (a) | XSmall<L<XBig (a),P≥YBig (a) | L≥XBig (a),P≥YBig (a) |
L≤XSmall,YSmall<P<YBig (a) | XSmall<L<XBig (a),YSmall<P<YBig (a) | L≥XBig (a),YSmall<P<YBig (a) |
L≤XSmall,P≤YSmall | XSmall<L<XBig (a),P≤YSmall | L≥XBig (a),P≤YSmall |
It should be noted that each article type may correspond to one of the squared figures in table 1. For static features of articles to be scored, different lattices (feature threshold intervals) have different weight combinations, and articles to be evaluated of different article types have the same weight combination in the same lattices (feature threshold intervals).
In the application process, for a document to be scored, a corresponding grid (L is less than or equal to X) in the nine-square grid can be found according to the article type of the article to be scored and the numerical value (for example, the text length is 600, and the number of text pictures is 0) of the static feature corresponding to the reference static featureSmall,P≤YSmall) And the static feature weight is determined by the combination of weights in the lattice.
In one example, for gourmet articles, the text is longThe two thresholds for degrees may be 800 and 1000, and the two thresholds for number of text pictures may be 0 and 5. When the text length of an article to be scored is 600 and the number of text pictures is 0, determining that the characteristic threshold interval is (L is less than or equal to X)Small,P≤YSmall) (ii) a When the text length of a chapter to be scored is 900 and the number of text pictures is 3, the characteristic threshold interval can be determined to be (X)Small<L<XBig (a),YSmall<P<YBig (a)) (ii) a When the text length of a chapter to be scored is 950 and the number of text pictures is 5, the characteristic threshold interval can be determined to be (X)Small<L<XBig (a),P≥YBig (a)) (ii) a When the text length of an article to be scored is 1200 and the number of text pictures is 6, the characteristic threshold interval can be determined to be (L is more than or equal to X)Big (a),P≥YBig (a))。
Further, the static feature score of the article to be scored and the static feature weight can be multiplied and then accumulated to obtain a static feature total score, and the article quality score of the article to be scored is determined based on the static feature total score.
In the application process, if the article to be scored meets some additional scoring standards, the final article quality score of the article to be scored is affected.
The following examples of the present disclosure will illustrate the processing of article quality scoring when the article to be scored meets some additional scoring criteria.
FIG. 8 is a flow diagram illustrating yet another article quality scoring method in accordance with an illustrative embodiment.
In an exemplary embodiment of the present disclosure, as shown in fig. 8, the article quality scoring method includes steps S51-S54. The steps will be described separately below.
In step S51, a plurality of static features included in the chapter to be scored are determined, and a static feature score and a static feature weight of each of the plurality of static features are determined.
In step S52, the static feature score corresponding to each of the plurality of static features is multiplied by the static feature weight and then accumulated to obtain a total static feature score.
In step S53, it is determined whether the article to be scored meets a preset additional scoring criterion. Wherein the additional scoring criteria include an adding criteria and/or a subtracting criteria.
In step S54, if the chapter to be scored meets the preset additional scoring standard, the static feature total score is added and/or subtracted according to the adding and/or subtracting standard, so as to obtain the article quality score of the article to be scored.
The steps S51 to S52 are the same as the steps S11 to S12 in the previous embodiment, and the related explanation, description and beneficial effects thereof are please refer to the above description of the steps S11 to S12, which is not repeated herein. The step S53 and the step S54 will be described in detail below.
In the application process, whether the seal to be scored meets the preset accessory scoring standard or not can be judged. Wherein the additional scoring criteria include an adding criteria and/or a subtracting criteria. In one example, when the punctuation mark at the tail of the article to be evaluated is detected to be ": "indicates that the content of the chapter to be scored is not finished and is incomplete, so that the preset score reduction standard is met. In the application process, the total score of the static features can be subtracted to obtain the article quality score of the article to be scored. In yet another example, the pre-set bonus criteria are met because the chapter to be scored has subtitles for the passage in the body. In the application process, the total score of the static features can be added to obtain the article quality score of the article to be scored.
It should be noted that the preset additional scoring standard may be adjusted according to actual situations, and in the present disclosure, the preset additional scoring standard is not specifically limited.
Based on the title and text of the article to be scored, whether the article is a low-quality article (title party, advertisement, competitive product, build lost, low style, text content repetition and the like) can be simply judged. Therefore, when a chapter to be scored is acquired, whether the article is a low-quality article can be judged firstly.
The article quality scoring method will be illustrated by the following examples.
In an exemplary embodiment of the present disclosure, before determining the plurality of static features contained in the article to be scored, the article to be scored may also be determined as a non-low quality article first. If the article to be scored is judged not to be a non-low-quality article, the article can be directly defined as a low-quality article without steps of determining a plurality of static features contained in the article to be scored and the like. By the embodiment, the operation process of determining the article quality scores of the articles to be scored can be reduced.
In an exemplary embodiment of the present disclosure, in response to determining that the article to be scored is a low quality article, the article quality score of the article to be scored is determined to be the lowest score. In one example, the lowest score may be 0.
The quality scoring method of the article according to the embodiment is described below with reference to practical applications.
Fig. 9 is a flow diagram illustrating another article quality scoring method in accordance with an exemplary embodiment.
As shown in fig. 9, in an example, information such as title, text picture, article classification and author of the article to be scored may be acquired. And judging whether the article to be scored belongs to a low-quality article or has a phenomenon of repeated content based on the information of the article to be scored, and if the article to be scored belongs to the low-quality article or has the phenomenon of repeated content, directly setting the article quality score of the article to be scored to be 0 without performing the following steps.
If the article to be scored is judged not to belong to the low-quality article and the phenomenon of content repetition does not occur, further calculating each static feature score (such as text length, paragraph, number of text pictures, text picture definition, low-quality feature and author) of the article to be scored. And according to the type, the text length and the text picture number of the article, the weight combination corresponding to each grid (characteristic threshold value interval) in the nine-square grid of the table 1 is searched, so that the static characteristic weight corresponding to each static characteristic of the article to be scored is determined. And multiplying each static feature by the static feature weight and accumulating to obtain the total quality score of the static features of the article to be scored.
Further, whether the article to be scored meets a preset additional scoring standard is determined. Wherein the additional scoring criteria include an adding criteria and/or a subtracting criteria. And if the to-be-scored articles meet the preset additional scoring standard, adding and/or subtracting the total score of the static features according to an adding standard and/or a subtracting standard to obtain the final article quality score of the to-be-scored articles.
According to the description, the article quality scoring method provided by the disclosure fully utilizes each static feature of the article to be scored, obtains the total score of the static features by determining each static feature score and the static feature weight, and determines the article quality score of the article to be scored based on the total score of the static features. The method and the device can efficiently and accurately determine the article quality score of the article to be scored, recommend the article with high quality for the user, and lay a foundation for improving the satisfaction degree of the user in the process of acquiring the recommended article.
The article quality scoring method provided by the embodiment of the disclosure is directed to the disadvantage that the accuracy of a quality scoring scheme based on text is low in a related technical scheme, fully uses each static feature of an article, obtains each static feature score of the article based on information such as title, text, text picture, author and the like of the article, and gives different weights to each static feature according to characteristics of text length and text picture number of different classification articles, so that whether the article is a low-quality article or a high-quality article can be accurately identified, wherein if the article is a party, an advertisement, a competitive product, a building lost message, a low tone, repeated content of the article, short and no picture of the article, incomplete content of the article, hydrology content of the article and the like, the article is defined as the low-quality article. If the content of the article has depth, strong speciality, luxuriant pictures and texts, distinct layers, complete structure and the like, the article is defined as a high-quality article, and other articles can be defined as medium-quality articles. The technical scheme greatly improves the accuracy of article quality scoring.
The article quality scoring method provided by the embodiment of the disclosure aims at the defect that the user is easily lost when the article quality scoring is determined based on the user browsing behavior in the related technical scheme, the quality of the article is evaluated before the article is recommended to the user, so that the recommendation of some low-quality articles to the user is avoided, and different articles can be directionally recommended to the user according to different user characteristics, so that the user can be well reflected, the interest and hobbies of the user are met, and the user can be retained.
Based on the same conception, the embodiment of the disclosure also provides an article quality scoring device.
It is understood that, in order to implement the above functions, the article quality scoring apparatus provided in the embodiments of the present disclosure includes a hardware structure and/or a software module corresponding to the execution of each function. The disclosed embodiments can be implemented in hardware or a combination of hardware and computer software, in combination with the exemplary elements and algorithm steps disclosed in the disclosed embodiments. Whether a function is performed as hardware or computer software drives hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
Fig. 10 is a block diagram illustrating an article quality scoring apparatus according to an example embodiment. Referring to fig. 10, the article quality scoring apparatus includes a static feature determination module 110, a processing module 120, and an article quality scoring module 130. Each module will be described separately below.
The determine static features module 110 may be configured to: the method comprises the steps of determining a plurality of static features contained in a chapter to be scored, and determining a static feature score and a static feature weight of each static feature in the plurality of static features.
The processing module 120 may be configured for: and multiplying the static feature score corresponding to each static feature in the plurality of static features by the static feature weight, and accumulating to obtain a total static feature score.
The article quality scoring module 130 can be configured to: and determining the article quality score of the article to be scored based on the total static characteristic score.
In an exemplary embodiment of the disclosure, the article quality scoring apparatus further includes a feature threshold interval setting module.
The set feature threshold interval module may be configured to: presetting a plurality of characteristic threshold intervals based on the article type and the characteristic threshold of at least one reference static characteristic, wherein each characteristic threshold interval corresponds to a weight combination, and each weight combination comprises the weights of the plurality of static characteristics;
the determine static features module 110 may be configured to: determining a feature threshold interval corresponding to the static feature of the corresponding reference static feature in the article to be scored based on the type of the article to be scored, the static feature of the corresponding reference static feature in the article to be scored and a feature threshold; a static feature weight for each static feature in the plurality of static features is determined based on a combination of weights corresponding to the feature threshold intervals.
In an exemplary embodiment of the disclosure, the set feature threshold interval module may be configured to: setting at least one characteristic threshold value for each preset reference static characteristic in a plurality of reference static characteristics, and setting different characteristic threshold values for the reference static characteristics of different article types; and combining any two characteristic thresholds of the characteristic thresholds corresponding to all the reference static characteristics in the plurality of reference static characteristics to form a plurality of characteristic threshold intervals.
In an exemplary embodiment of the disclosure, the article quality scoring apparatus further includes a determining module.
The determination module may be configured to: and determining whether the article to be scored meets preset additional scoring criteria, wherein the additional scoring criteria comprise an adding score criterion and/or a subtracting score criterion.
The article quality scoring module 130 may determine the article quality score of the article to be scored based on the static feature total score in the following manner: and if the article to be scored meets the preset additional scoring standard, adding and/or subtracting the total score of the static features according to an adding standard and/or a subtracting standard to obtain the article quality score of the article to be scored.
In an exemplary embodiment of the present disclosure, the article quality scoring apparatus further comprises a determine non-low quality article module.
The determine non-low quality articles module may be configured to: and determining the article to be scored as a non-low-quality article.
In an exemplary embodiment of the present disclosure, the article quality scoring apparatus further comprises a low quality article processing module.
The low-quality article processing module may be configured to: and in response to determining that the article to be scored is a low-quality article, determining the article quality score of the article to be scored as the lowest score.
In an exemplary embodiment of the present disclosure, the static features include one or more of a length of text, a paragraph, a number of text pictures, a clarity of text pictures, a low quality feature, and an author, and the determine static features module 110 may determine the static feature score for each of the plurality of static features as follows: determining the text length score of the article according to the text length of the article; determining a paragraph score according to the number of paragraphs; determining the number value of the text pictures according to the number of the text pictures; determining the definition score of the text picture according to the definition of the text picture; determining a low-quality feature score according to the low-quality features; the author score is determined according to the rank of the author.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
Fig. 11 is a block diagram illustrating an apparatus 200 for article quality scoring in accordance with an exemplary embodiment. For example, the apparatus 200 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, an exercise device, a personal digital assistant, and the like.
Referring to fig. 11, the apparatus 200 may include one or more of the following components: a processing component 202, a memory 204, a power component 206, a multimedia component 208, an audio component 210, an input/output (I/O) interface 212, a sensor component 214, and a communication component 216.
The processing component 202 generally controls overall operation of the device 200, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing components 202 may include one or more processors 220 to execute instructions to perform all or a portion of the steps of the methods described above. Further, the processing component 202 can include one or more modules that facilitate interaction between the processing component 202 and other components. For example, the processing component 202 can include a multimedia module to facilitate interaction between the multimedia component 208 and the processing component 202.
The memory 204 is configured to store various types of data to support operations at the apparatus 200. Examples of such data include instructions for any application or method operating on the device 200, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 204 may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks.
The multimedia component 208 includes a screen that provides an output interface between the device 200 and the user. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive an input signal from a user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundary of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 208 includes a front facing camera and/or a rear facing camera. The front camera and/or the rear camera may receive external multimedia data when the device 200 is in an operating mode, such as a shooting mode or a video mode. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.
The audio component 210 is configured to output and/or input audio signals. For example, audio component 210 includes a Microphone (MIC) configured to receive external audio signals when apparatus 200 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may further be stored in the memory 204 or transmitted via the communication component 216. In some embodiments, audio component 210 also includes a speaker for outputting audio signals.
The I/O interface 212 provides an interface between the processing component 202 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to: a home button, a volume button, a start button, and a lock button.
The sensor component 214 includes one or more sensors for providing various aspects of status assessment for the device 200. For example, the sensor assembly 214 may detect an open/closed state of the device 200, the relative positioning of components, such as a display and keypad of the device 200, the sensor assembly 214 may also detect a change in the position of the device 200 or a component of the device 200, the presence or absence of user contact with the device 200, the orientation or acceleration/deceleration of the device 200, and a change in the temperature of the device 200. The sensor assembly 214 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 214 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 214 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
The communication component 216 is configured to facilitate wired or wireless communication between the apparatus 200 and other devices. The device 200 may access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 216 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 216 further includes a Near Field Communication (NFC) module to facilitate short-range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, Ultra Wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
In an exemplary embodiment, the apparatus 200 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors or other electronic components for performing the article quality scoring methods described above.
In an exemplary embodiment, a non-transitory computer-readable storage medium comprising instructions, such as the memory 204 comprising instructions, executable by the processor 220 of the apparatus 200 to perform the article quality scoring method described above is also provided. For example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
It is understood that "a plurality" in this disclosure means two or more, and other words are analogous. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. The singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It will be further understood that the terms "first," "second," and the like are used to describe various information and that such information should not be limited by these terms. These terms are only used to distinguish one type of information from another and do not denote a particular order or importance. Indeed, the terms "first," "second," and the like are fully interchangeable. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present disclosure.
It will be further understood that the terms "central," "longitudinal," "lateral," "front," "rear," "upper," "lower," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are used in an orientation or positional relationship indicated in the drawings for convenience in describing the present embodiment and to simplify the description, but do not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation.
In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are only a subset of the embodiments of the present disclosure, and not all embodiments. The embodiments described above by reference to the drawings are exemplary and intended to be illustrative of the present disclosure, and should not be construed as limiting the present disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure. The embodiments of the present disclosure are described in detail above with reference to the accompanying drawings.
It will be further understood that, unless otherwise specified, "connected" includes direct connections between the two without the presence of other elements, as well as indirect connections between the two with the presence of other elements.
It is further to be understood that while operations are depicted in the drawings in a particular order, this is not to be understood as requiring that such operations be performed in the particular order shown or in serial order, or that all illustrated operations be performed, to achieve desirable results. In certain environments, multitasking and parallel processing may be advantageous.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (16)
1. An article quality scoring method, comprising:
determining a plurality of static features contained in a chapter to be scored, and determining a static feature score and a static feature weight of each static feature in the plurality of static features;
multiplying the static feature score corresponding to each static feature in the plurality of static features by the static feature weight, and accumulating to obtain a total static feature score;
and determining the article quality score of the article to be scored based on the static characteristic total score.
2. The article quality scoring method of claim 1, further comprising:
presetting a plurality of characteristic threshold intervals based on the article type and the characteristic threshold of at least one reference static characteristic, wherein each characteristic threshold interval corresponds to a weight combination, and each weight combination comprises the weights of the plurality of static characteristics;
the determining a static feature weight for each static feature of the plurality of static features comprises:
determining a feature threshold value interval corresponding to the static feature of the article to be scored, which corresponds to the reference static feature, based on the type of the article to be scored, the static feature of the article to be scored, which corresponds to the reference static feature, and the feature threshold value;
determining a static feature weight for each static feature of the plurality of static features based on a combination of weights corresponding to the feature threshold interval.
3. The article quality scoring method according to claim 2, wherein presetting a plurality of feature threshold intervals based on the article type and a feature threshold of at least one reference static feature comprises:
setting at least one characteristic threshold value for each preset reference static characteristic in a plurality of reference static characteristics, and setting different characteristic threshold values for the reference static characteristics of different article types;
and combining any two characteristic thresholds in the characteristic thresholds corresponding to all the reference static characteristics in the plurality of reference static characteristics to form a plurality of characteristic threshold intervals.
4. The article quality scoring method of claim 1, further comprising:
determining whether the chapter to be scored meets preset additional scoring standards, wherein the additional scoring standards comprise an adding standard and/or a subtracting standard;
the determining the article quality score of the article to be scored based on the total static feature score comprises the following steps:
and if the article to be scored meets a preset additional scoring standard, adding and/or subtracting the total score of the static features according to the adding and/or subtracting standard to obtain the article quality score of the article to be scored.
5. The article quality scoring method according to claim 1, wherein before determining the plurality of static features contained in the article to be scored, the article quality scoring method further comprises:
determining the article to be scored as a non-low quality article.
6. The article quality scoring method of claim 5, further comprising:
and in response to determining that the article to be scored is a low-quality article, determining that the article quality score of the article to be scored is the lowest score.
7. The article quality scoring method of claim 1, wherein the static features include one or more of text length, paragraph, number of text pictures, text picture clarity, low quality features, and author, and wherein the determining the static feature score for each of the plurality of static features comprises:
determining the text length score of the article according to the text length of the article;
determining a paragraph score according to the number of paragraphs;
determining the number value of the text pictures according to the number of the text pictures;
determining the definition score of the text picture according to the definition of the text picture;
determining a low-quality feature score according to the low-quality features; and
the author score is determined according to the rank of the author.
8. An article quality scoring apparatus, comprising:
the static feature determining module is used for determining a plurality of static features contained in the chapter to be scored, and determining the static feature score and the static feature weight of each static feature in the plurality of static features;
the processing module is used for multiplying the static feature score corresponding to each static feature in the plurality of static features by the static feature weight and then accumulating to obtain a total static feature score;
and the article quality scoring module is used for determining the article quality score of the article to be scored based on the static characteristic total score.
9. The article quality scoring apparatus according to claim 8, wherein the apparatus further comprises:
a feature threshold interval setting module, configured to preset a plurality of feature threshold intervals based on an article type and a feature threshold of at least one reference static feature, where each feature threshold interval corresponds to a weight combination, and each weight combination includes weights of the plurality of static features;
the determine static characteristics module is to: determining a feature threshold value interval corresponding to the static feature of the article to be scored, which corresponds to the reference static feature, based on the type of the article to be scored, the static feature of the article to be scored, which corresponds to the reference static feature, and the feature threshold value; determining a static feature weight for each static feature of the plurality of static features based on a combination of weights corresponding to the feature threshold interval.
10. The article quality scoring apparatus of claim 9, wherein the set feature threshold interval module is configured to:
setting at least one characteristic threshold value for each preset reference static characteristic in a plurality of reference static characteristics, and setting different characteristic threshold values for the reference static characteristics of different article types;
and combining any two characteristic thresholds in the characteristic thresholds corresponding to all the reference static characteristics in the plurality of reference static characteristics to form a plurality of characteristic threshold intervals.
11. The article quality scoring apparatus according to claim 8, wherein the apparatus further comprises:
the judgment module is used for determining whether the seal to be scored meets a preset additional scoring standard or not, wherein the additional scoring standard comprises an adding standard and/or a subtracting standard;
the article quality scoring module determines the article quality score of the article to be scored based on the total static feature score in the following mode:
and if the article to be scored meets a preset additional scoring standard, adding and/or subtracting the total score of the static features according to the adding and/or subtracting standard to obtain the article quality score of the article to be scored.
12. The article quality scoring apparatus according to claim 8, wherein the apparatus further comprises:
and the non-low-quality article determining module is used for determining the article to be scored as a non-low-quality article.
13. The article quality scoring apparatus of claim 12, wherein the apparatus further comprises:
and the low-quality article processing module is used for responding to the determination that the article to be scored is a low-quality article, and determining that the article quality score of the article to be scored is the lowest score.
14. The article quality scoring apparatus of claim 8, wherein the static features include one or more of a length of text, a paragraph, a number of text pictures, a text picture clarity, a low quality feature, and an author, and wherein the determine static features module determines the static feature score for each of the plurality of static features as follows:
determining the text length score of the article according to the text length of the article;
determining a paragraph score according to the number of paragraphs;
determining the number value of the text pictures according to the number of the text pictures;
determining the definition score of the text picture according to the definition of the text picture;
determining a low-quality feature score according to the low-quality features; and
the author score is determined according to the rank of the author.
15. An image processing apparatus characterized by comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to: performing the article quality scoring method of any one of claims 1 to 7.
16. A non-transitory computer readable storage medium having instructions therein which, when executed by a processor of a mobile terminal, enable the mobile terminal to perform the article quality scoring method of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010873079.4A CN112069802A (en) | 2020-08-26 | 2020-08-26 | Article quality scoring method, article quality scoring device and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010873079.4A CN112069802A (en) | 2020-08-26 | 2020-08-26 | Article quality scoring method, article quality scoring device and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112069802A true CN112069802A (en) | 2020-12-11 |
Family
ID=73658949
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010873079.4A Pending CN112069802A (en) | 2020-08-26 | 2020-08-26 | Article quality scoring method, article quality scoring device and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112069802A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022161470A1 (en) * | 2021-01-29 | 2022-08-04 | 腾讯科技(深圳)有限公司 | Content evaluation method and apparatus, and device and medium |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104850642A (en) * | 2015-05-26 | 2015-08-19 | 广州神马移动信息科技有限公司 | Internet content quality evaluation method and internet content quality evaluation device |
CN107193805A (en) * | 2017-06-06 | 2017-09-22 | 北京百度网讯科技有限公司 | Article Valuation Method, device and storage medium based on artificial intelligence |
CN107729473A (en) * | 2017-10-13 | 2018-02-23 | 东软集团股份有限公司 | Article recommends method and its device |
CN109214614A (en) * | 2017-06-29 | 2019-01-15 | 北京嘀嘀无限科技发展有限公司 | Net about vehicle driver credit-graded approach, credit scoring system and computer installation |
CN110019814A (en) * | 2018-07-09 | 2019-07-16 | 暨南大学 | A kind of news information polymerization based on data mining and deep learning |
CN111488931A (en) * | 2020-04-10 | 2020-08-04 | 腾讯科技(深圳)有限公司 | Article quality evaluation method, article recommendation method and corresponding devices |
-
2020
- 2020-08-26 CN CN202010873079.4A patent/CN112069802A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104850642A (en) * | 2015-05-26 | 2015-08-19 | 广州神马移动信息科技有限公司 | Internet content quality evaluation method and internet content quality evaluation device |
CN107193805A (en) * | 2017-06-06 | 2017-09-22 | 北京百度网讯科技有限公司 | Article Valuation Method, device and storage medium based on artificial intelligence |
US20180349734A1 (en) * | 2017-06-06 | 2018-12-06 | Beijing Baidu Netcom Science And Technology Co., Ltd. | Method and apparatus for evaluating article value based on artificial intelligence, and storage medium |
CN109214614A (en) * | 2017-06-29 | 2019-01-15 | 北京嘀嘀无限科技发展有限公司 | Net about vehicle driver credit-graded approach, credit scoring system and computer installation |
CN107729473A (en) * | 2017-10-13 | 2018-02-23 | 东软集团股份有限公司 | Article recommends method and its device |
CN110019814A (en) * | 2018-07-09 | 2019-07-16 | 暨南大学 | A kind of news information polymerization based on data mining and deep learning |
CN111488931A (en) * | 2020-04-10 | 2020-08-04 | 腾讯科技(深圳)有限公司 | Article quality evaluation method, article recommendation method and corresponding devices |
Non-Patent Citations (1)
Title |
---|
刘涛;刘佐;: "一种面向新文章的个性化推荐算法研究", 控制工程, no. 06, 20 June 2018 (2018-06-20), pages 56 - 60 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2022161470A1 (en) * | 2021-01-29 | 2022-08-04 | 腾讯科技(深圳)有限公司 | Content evaluation method and apparatus, and device and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110827253A (en) | Training method and device of target detection model and electronic equipment | |
CN111160448B (en) | Training method and device for image classification model | |
CN111859020B (en) | Recommendation method, recommendation device, electronic equipment and computer readable storage medium | |
CN104113780A (en) | Advertisement processing method and apparatus | |
CN111461304B (en) | Training method of classified neural network, text classification method, device and equipment | |
CN112148980B (en) | Article recommending method, device, equipment and storage medium based on user click | |
CN110941727B (en) | Resource recommendation method and device, electronic equipment and storage medium | |
CN111199730B (en) | Voice recognition method, device, terminal and storage medium | |
CN112685599B (en) | Video recommendation method and device | |
CN107247794B (en) | Topic guiding method in live broadcast, live broadcast device and terminal equipment | |
CN112069802A (en) | Article quality scoring method, article quality scoring device and storage medium | |
CN111274444B (en) | Method and device for generating video cover determination model, and method and device for determining video cover | |
CN111291268B (en) | Information processing method, information processing apparatus, and storage medium | |
CN114462410A (en) | Entity identification method, device, terminal and storage medium | |
CN107301188B (en) | Method for acquiring user interest and electronic equipment | |
CN113870195A (en) | Target map detection model training and map detection method and device | |
CN111221710B (en) | Method, device and equipment for identifying user type | |
CN111753182B (en) | Multimedia information recommendation method and device, electronic equipment and readable storage medium | |
CN109088920B (en) | Evaluation method, device and equipment of intelligent sound box and storage medium | |
CN112863499A (en) | Speech recognition method and device, storage medium | |
CN115374256A (en) | Question and answer data processing method, device, equipment, storage medium and product | |
CN113254707B (en) | Model determination method and device and associated media resource determination method and device | |
CN111898019A (en) | Information pushing method and device | |
CN112307353B (en) | Data processing method and device, electronic equipment and storage medium | |
CN117350824B (en) | Electronic element information uploading and displaying method, device, medium and equipment |
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 |