CN113065052A - Method and device for analyzing authenticity of video comment, electronic equipment and storage medium - Google Patents
Method and device for analyzing authenticity of video comment, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN113065052A CN113065052A CN202110374043.6A CN202110374043A CN113065052A CN 113065052 A CN113065052 A CN 113065052A CN 202110374043 A CN202110374043 A CN 202110374043A CN 113065052 A CN113065052 A CN 113065052A
- Authority
- CN
- China
- Prior art keywords
- comment
- information
- scoring
- comment information
- video
- 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
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 238000013473 artificial intelligence Methods 0.000 claims abstract description 10
- 238000012512 characterization method Methods 0.000 claims abstract description 9
- 238000002372 labelling Methods 0.000 claims abstract description 4
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000012552 review Methods 0.000 claims description 7
- 238000010224 classification analysis Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 abstract description 3
- 238000013481 data capture Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000009471 action Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 206010044565 Tremor Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000011157 data evaluation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F16/955—Retrieval from the web using information identifiers, e.g. uniform resource locators [URL]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method and a device for analyzing the authenticity of video comments, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a network address of a target video to be analyzed; obtaining all comment information of the same category of videos by using a crawler technology; labeling the comment information, classifying, and performing variable analysis to obtain variable parameters; acquiring an AI model corresponding to the variable parameter, wherein the AI model is a characterization variable model based on artificial intelligence learning; acquiring first comment information of a target video to be analyzed and a comment scoring system associated with the target video to be analyzed; and scoring each comment in the first comment information based on a first preset scoring rule and a comment scoring system to obtain a first scoring result. The invention has the advantages that: data capture and analysis are automatically completed, and the cost is low; the AI model automatically matches data to obtain a comment authenticity result, and the method is strong in timeliness and high in accuracy; and an early warning system is arranged, so that the system is convenient to track in time and maintain the interests of all parties.
Description
Technical Field
The invention relates to a method and a device for analyzing the authenticity of video comments, electronic equipment and a storage medium.
Background
With the rapid development of domestic short videos in recent years, more and more people begin to watch short videos as a popular leisure and entertainment option. Meanwhile, the prosperity of the short videos is brought, the number of the short videos and the blowout of the subject matter are increased, and particularly, a plurality of bloggers sell the commodities through the short videos, so that the prosperity of the short videos is brought. The review of short videos becomes an important reference for the user to select the merchandise displayed in the video.
Correspondingly, comments which are not generated by users appear on various large and short video websites, the comments greatly interfere the selection of the users, and the reliability of the short video frequency band goods is reduced. At present, a mature method for filtering short video comments does not exist, but the short video comments greatly influence the selection of many users and also cause the adverse effects of false publicity, inferior products, counterfeit goods and the like.
Disclosure of Invention
In view of the problems in the prior art, it is an object of the present invention to provide a method for analyzing the authenticity of video comments for short videos, and another object of the present invention is to provide an apparatus, an electronic device and a storage medium for implementing the method.
In order to achieve the above object, the present invention provides a method for analyzing video review authenticity, which specifically comprises:
step 1: acquiring a network address of a target video to be analyzed;
step 2: obtaining all comment information of the same category of videos by using a crawler technology;
and step 3: labeling the comment information, classifying, and performing variable analysis to obtain variable parameters;
and 4, step 4: acquiring an AI model corresponding to the variable parameter, wherein the AI model is a characterization variable model based on artificial intelligence learning;
and 5: acquiring first comment information of a target video to be analyzed and a comment scoring system associated with the target video to be analyzed; scoring each comment in the first comment information based on a first preset scoring rule and a comment scoring system to obtain a first scoring result;
step 6: acquiring information of all comment users in the first comment information, and acquiring historical comment information of the comment users; and scoring each comment in the first comment information based on the historical comment information and a second preset scoring rule, obtaining the score of the comment information made by each comment user, and obtaining a second scoring result.
And 7: and based on the first grading result and the second grading result, when the credibility of the video comment information is reduced to a set value, triggering an early warning system to give an alarm.
Further, in the step 3, on the basis of obtaining all comment information of the same category of video, the comment information is divided according to a set label rule, the comment information is labeled to refine the classification, and the label information can be used as an analysis parameter.
Further, the variable parameters comprise parameter types, parameter keywords, parameter names, keyword codes, request parameter values and path information.
Further, in the step 4, the real comment of the known video is obtained, the tag information of the known real comment is obtained, and the known tag information is subjected to variable analysis to obtain a real-time variable parameter; inputting the real-time variable parameters into a machine learning model trained in advance; and acquiring an AI model of the machine learning model based on real-time variable output.
Further, the AI model includes a comment scoring system, and the comment scoring system includes the first preset scoring rule and the second preset scoring rule.
An apparatus for analyzing the authenticity of video comments, which implements the method, comprises:
the network address acquisition module of the target video is used for acquiring the network address of the target video to be analyzed;
the comment information acquisition module is used for acquiring all comment information of videos of the same category in the network address;
the variable analysis module is used for carrying out classification analysis on the comment information by marking a label to obtain a variable parameter;
and the AI model unit is used for evaluating the comment information of the video based on the characterization variable model learned by artificial intelligence.
Further, the AI model unit comprises a comment scoring system, and the comment scoring system comprises a first preset scoring rule module, a second preset scoring rule module, a first feedback module and a second feedback module.
Further, the first preset scoring rule module is used for scoring each comment in the first comment information to obtain a first scoring result; the second preset scoring rule module is used for acquiring information of all the comment users in the first comment information and acquiring historical comment information of the comment users; scoring each comment in the first comment information based on the historical comment information and a second preset scoring rule, obtaining the score of comment information made by each comment user, and obtaining a second scoring result; the first feedback module is used for feeding back a first scoring result; and the second feedback module is used for feeding back a second grading result.
An electronic device implementing the method comprises a memory and a processor, wherein the memory is connected with the processor; the memory is used for storing programs; the processor is used for calling a program stored in the memory to execute the method for analyzing the video comment authenticity.
A storage medium storing program code executable by a processor in a computer for implementing the method described above, the storage medium comprising instructions configured to cause the processor to perform the method described above for analyzing the authenticity of video reviews.
The invention has the following technical advantages:
1. data capture and analysis are automatically completed, and the cost is low;
2. the AI model automatically matches data to obtain a comment authenticity result, and the timeliness is strong;
3. the artificial intelligence learning is carried out in a classification mode aiming at videos of different industries and different types, and the method is strong in pertinence and high in accuracy;
4. and an early warning system is arranged, so that the system is convenient to track in time and maintain the interests of all parties.
Drawings
FIG. 1 is a flow diagram of a framework for a method of analyzing the authenticity of video reviews in accordance with the present invention;
fig. 2 is a structural framework diagram of the device for analyzing the authenticity of the video comment.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The following detailed description of embodiments of the invention refers to the accompanying drawings. It should be understood that the detailed description and specific examples, while indicating the present invention, are given by way of illustration and explanation only, not limitation.
Example 1
As shown in fig. 1, the method for analyzing the authenticity of the video comment comprises the following specific steps:
step 1: the method comprises the steps of obtaining a network address of a target video to be analyzed, namely obtaining a network address corresponding to a given target video, wherein the target video can be various types of videos such as short videos, TV plays, movies, art programs, documentaries and the like. The short video may be the video of a tremble, video number, fast-hand, etc. platform.
Step 2: and acquiring all comment information of the same category of videos by using a crawler technology. Videos of the same category have the same commonality, and comments of the videos of the same category also have a certain commonality, so that obtaining the comment information of the videos of the same category is helpful for data analysis and evaluation of subsequent AI models. The video category comprises a fun category, a movie and television entertainment category, a culture category, a favorite category, a delicacy category, a health category, a game cartoon category, a fashion art category, a civilian category, an emotion category, a life category, a music category, a mother and infant child category, an education category, a makeup category, a travel category, a photography category, a sports category, a workplace category, a current government affairs category, an enterprise category, an automobile category, a finance category, a scientific science popularization category, a scientific and technological internet category and the like. If all the comment information of the automobile type videos is obtained, a preliminary database of the automobile type videos is formed.
And step 3: and labeling the comment information, classifying, and analyzing variables to obtain variable parameters. On the basis of obtaining all comment information of videos of the same category, the comment information is further subdivided, the comment information is divided according to a set label rule, the comment information is labeled to be refined and classified, and the label information can be used as one of analysis parameters. For example, in an automobile video, brand labels are set according to the difference of automobile brands, accessory labels are set according to the difference of automobile accessories, labels are set according to automobile models, automobile modification labels are set, automobile accident labels are set, automobile maintenance labels are set, automobile evaluation labels are set, and the like.
And classifying the comment information of each type of label, and analyzing variables to obtain variable parameters. The variable parameters comprise parameter types, parameter keywords, parameter names, keyword codes, request parameter values, path information and the like.
And 4, step 4: obtaining an AI model corresponding to the variable parameter, wherein the AI model is a characterization variable model based on artificial intelligence learning, and the characterization variable model based on artificial intelligence learning specifically comprises the following steps: acquiring real comments of a known video, acquiring tag information of the known real comments, and performing variable analysis on the known tag information to obtain real-time variable parameters; inputting the real-time variable parameters into a machine learning model trained in advance; and acquiring an AI model of the machine learning model based on the real-time variable output.
And forming a comment scoring system through the AI model, wherein the comment scoring system comprises a first preset scoring rule and a second preset scoring rule.
The first preset scoring rule and the second preset scoring rule may be the same rule or different rules set according to the target parameter.
The AI model may be a BLP model. In this embodiment, in order to improve the accuracy of the judgment of the video comment authenticity, the variable parameter is judged through the AI model of the comment scoring system, that is, after the variable parameter is obtained by performing variable analysis on the tag information of the video to be detected, whether the variable parameter is real is accurately judged according to the corresponding AI model.
The model of the characterization variable based on artificial intelligence learning has automatic learning ability and strong adaptability, and can also automatically generate an AI model by means of a machine learning model and input known variable parameters into a machine learning model trained in advance; and acquiring an AI model of the machine learning model based on the known variable output.
Taking the automobile industry as an example, the impact of video review authenticity on the selection of different automobiles by consumers:
assume that the utility function for consumer selection of product j is:
Uij＝Xjβi+αln(yi-pj)+ξj+εij
wherein XjIs a characteristic of the product (e.g. in the automotive field, i.e. performance, size, brand, etc., XjMay be derived from the tag information described above), PjIs the price and alpha is the revenue coefficient. Although the revenue factor is the same for all people, because of revenue yiThere is a difference between individuals and therefore price sensitivity (price sensitivity) between individuals (note: BLP uses the revenue distribution of the United states to model yi)。
βiThe preference of the consumer to different product characteristics can be found from the comment information for the kth product dimension, and the product preference of the consumer i is as follows:
wherein
Thus betaikDistribution parameter of
Consumer utility may also be decomposed into mean components
And a deviation portion
Namely:
Ui0＝αlog(yi)+ξ0+σ0vi0+εi0)
wherein v isi0Is mainly to control the greater volatility of the utility in non-purchasing decisions.
Nevo (2000) simplifies the form of revenue in the utility function to be able to fully distinguish between personally relevant and non-personally relevant utility factors into:
uijt＝αi(yi-pjt)+xjtβi+ξjt+εijt＝δjt+μijt+εijt
wherein i, j, t represent consumer, product and time, respectively,
δjt＝xjtβ-αpjt+ξjt，uijt＝[-pjt，xjt](ΠDi+∑vi)。
because of eijtObey Type I Error, so the product market share at the individual level is:
the demand elasticity of the price is:
the data necessary for the BLP includes market share, average selling price, and product characteristics of the product. Meanwhile, the method preferably has related variables of characteristic distribution, and information related to marketing aspects, such as comment information for guiding users, short video advertisement information, discounting promotion activities and the like, can also increase the estimation accuracy.
And 5: acquiring first comment information of a target video to be analyzed and a comment scoring system associated with the target video to be analyzed; and scoring each comment in the first comment information based on a first preset scoring rule and a comment scoring system to obtain a first scoring result. The first comment information comprises all comment information of the target video, the first comment information comprises information of multiple dimensions, such as background dimension information of the video, the target video to be analyzed is provided with comment information of videos participated by at least one same producer, distributor, director and/or director, comment information of a series of videos of the target video to be analyzed, grading dimension information, such as comment information of the target video to be analyzed in other referenced videos, and the like.
Step 6: and feeding back the first scoring result.
And 7: acquiring information of all comment users in the first comment information, and acquiring historical comment information of the comment users; scoring each comment in the first comment information based on the historical comment information and a second preset scoring rule, obtaining the score of comment information made by each comment user, and obtaining a second scoring result; and feeding back the second scoring result.
The comment scoring system comprises: the method comprises the following steps that comment information of videos participated by at least one same offeror, distributor, director and/or lead actor with the target video to be analyzed and comment information of a series of videos of the target video to be analyzed are provided, and each comment in the first comment information is graded based on a first preset grading rule and a comment grading system, and the method comprises the following steps: judging whether the comment scoring system and the first comment information have the same comment users or not; when the comment scoring system and the first comment information have no identical comment users, the credibility of each comment in the first comment information is unchanged or is increased, or when the comment scoring system and the first comment information have identical comment users, whether the comment content of the comment user in the comment scoring system is consistent with the comment content of the comment user in the first comment information is judged. And when the comment content of the comment user in the comment scoring system is consistent with the comment content in the first comment information, the comment user is judged as a fan user, and the credibility of the comment content of the comment user is reduced. Or when the comment content of the comment user in the comment scoring system is different from the comment content in the first comment information, the credibility of the comment content of the comment user is increased or unchanged.
The comment scoring system comprises: the method for scoring each comment in the first comment information based on a first preset scoring rule and the comment scoring system includes the following steps: judging whether the comment scoring system and the first comment information have consistent comments or not; when the comment scoring system does not have a consistent comment with the first comment information, the credibility of each comment in the first comment information is not changed, or when the comment scoring system has a consistent comment with the first comment information, whether the personal information of a user corresponding to the comment in the comment scoring system is consistent with the personal information of the user corresponding to the comment in the first comment information is judged; when the personal information of the user corresponding to the comment in the comment scoring system is consistent with the personal information of the user corresponding to the first comment information in the comment, the reliability of the comment in the first comment information is unchanged or increased on the basis of the current reliability, or when the personal information of the user corresponding to the comment scoring system is inconsistent with the personal information of the user corresponding to the first comment information in the comment, the comment is judged to be a batch comment, and the reliability of the comment in the first comment information is reduced on the basis of the current reliability.
The historical comment information includes: the type of a historical watching video of the comment user in the first comment information; scoring each comment in the first comment information based on the historical comment information and a second preset scoring rule, including: and judging whether the type of the video watched by the comment user at this time in the first comment information is consistent with the type of the video watched historically. If the type of the video watched by the comment user at this time is consistent with that of the historical watching video, the credibility of the comment content of the comment user is unchanged or increased on the basis of the current credibility. Or if the type of the video watched by the comment user at this time is inconsistent with the type of the video watched historically, the credibility of the comment content of the comment user is reduced on the basis of the current credibility.
The historical comment information includes: historical comment content of the comment user in the first comment information; scoring each comment in the first comment information based on the historical comment information and a second preset scoring rule, including: and judging whether the current comment content of the comment user in the first comment information is consistent with the historical comment content. If the comment content of the comment user is inconsistent with the historical comment content, the credibility of the comment content of the comment user is unchanged or increased on the basis of the current credibility. Or if the comment content of the comment user at this time is consistent with the history comment content at this time, the credibility of the comment content of the comment user is reduced on the basis of the current credibility.
According to the method and the device, whether the bad comments such as fan comments, batch comments, water army comments, machine comments and the like exist or not can be effectively analyzed, and after the judgment result of the comment reliability is obtained through the AI model, the obtained result is fed back, so that a real and effective reference is provided for a user when the user selects to watch the video.
And 8: and the early warning system is triggered when the reliability is reduced to a set value.
And based on the first grading result and the second grading result, when the credibility of the video comment information is reduced to a set value, triggering an early warning system to give an alarm.
When the credibility of the comment information of the short video is reduced to a set threshold value, the system prompts information such as false propaganda, inferior products, counterfeit goods and the like, the information can be fed back to a platform supervision department for quality monitoring, and can also be directly fed back to a consumer to remind the consumer to confirm the credibility of the video and prevent cheating; the information can also be fed back to the video producers, distributors and authors to remind the producers, distributors and authors to guarantee the authenticity of comments and increase the credibility of the video.
Example 2
As shown in fig. 2, an apparatus for analyzing the authenticity of a video comment of the present invention includes:
the network address acquisition module of the target video is used for acquiring the network address of the target video to be analyzed;
the comment information acquisition module is used for acquiring all comment information of videos of the same category in the network address;
the variable analysis module is used for carrying out classification analysis on the comment information by marking a label to obtain a variable parameter;
and the AI model unit is used for evaluating the comment information of the video based on the characterization variable model learned by artificial intelligence.
The AI model unit comprises a comment scoring system, and the comment scoring system comprises a first preset scoring rule module, a second preset scoring rule module, a first feedback module and a second feedback module.
And the first preset scoring rule module is used for scoring each comment in the first comment information to obtain a first scoring result.
The second preset scoring rule module is used for acquiring information of all the comment users in the first comment information and acquiring historical comment information of the comment users; and scoring each comment in the first comment information based on the historical comment information and a second preset scoring rule, obtaining the score of the comment information made by each comment user, and obtaining a second scoring result.
And the first feedback module is used for feeding back the first scoring result.
And the second feedback module is used for feeding back a second grading result.
Example 3
An electronic device comprising a memory and a processor, the memory being connected to the processor; the memory is used for storing programs; the processor is used for calling a program stored in the memory to execute the method for analyzing the video comment authenticity.
Example 4
A storage medium storing program code executable by a processor in a computer, the storage medium comprising instructions configured to cause the processor to perform the above-described method of analyzing the authenticity of video commentary.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways, and that the apparatus embodiments described above are merely illustrative, for example, the flowchart and block diagrams in the figures illustrate the architectural functions and operations of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s).
It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved, and it is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, may be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part. The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a notebook computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes. It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The method for analyzing the authenticity of the video comment is characterized by comprising the following steps:
step 1: acquiring a network address of a target video to be analyzed;
step 2: obtaining all comment information of the same category of videos by using a crawler technology;
and step 3: labeling the comment information, classifying, and performing variable analysis to obtain variable parameters;
and 4, step 4: acquiring an AI model corresponding to the variable parameter, wherein the AI model is a characterization variable model based on artificial intelligence learning;
and 5: acquiring first comment information of a target video to be analyzed and a comment scoring system associated with the target video to be analyzed; scoring each comment in the first comment information based on a first preset scoring rule and a comment scoring system to obtain a first scoring result;
step 6: acquiring information of all comment users in the first comment information, and acquiring historical comment information of the comment users; scoring each comment in the first comment information based on the historical comment information and a second preset scoring rule, obtaining the score of comment information made by each comment user, and obtaining a second scoring result;
and 7: and based on the first grading result and the second grading result, when the credibility of the video comment information is reduced to a set value, triggering an early warning system to give an alarm.
2. The method as claimed in claim 1, wherein in step 3, on the basis of obtaining all comment information of the same category of video, the comment information is divided according to a set label rule, and the comment information is labeled to refine the classification, wherein the label information can be used as an analysis parameter.
3. The method of claim 1, wherein the variable parameters include parameter type, parameter keyword, parameter name, keyword encoding, request parameter value, path information.
4. The method of claim 1, wherein in step 4, a real comment of a known video is obtained, tag information of the known real comment is obtained, and variable analysis is performed on the known tag information to obtain a real-time variable parameter; inputting the real-time variable parameters into a machine learning model trained in advance; and acquiring an AI model of the machine learning model based on real-time variable output.
5. The method of claim 4, wherein the AI model includes a review scoring system that includes the first pre-set scoring rule, the second pre-set scoring rule.
6. An apparatus for analyzing video for plausibility, comprising:
the network address acquisition module of the target video is used for acquiring the network address of the target video to be analyzed;
the comment information acquisition module is used for acquiring all comment information of videos of the same category in the network address;
the variable analysis module is used for carrying out classification analysis on the comment information by marking a label to obtain a variable parameter;
and the AI model unit is used for evaluating the comment information of the video based on the characterization variable model learned by artificial intelligence.
7. The apparatus of claim 6, wherein the AI model element comprises a review scoring system comprising a first pre-set scoring rule module, a second pre-set scoring rule module, a first feedback module, and a second feedback module.
8. The apparatus of claim 7, wherein the first preset scoring rule module is configured to score each comment in the first comment information to obtain a first scoring result; the second preset scoring rule module is used for acquiring information of all the comment users in the first comment information and acquiring historical comment information of the comment users; scoring each comment in the first comment information based on the historical comment information and a second preset scoring rule, obtaining the score of comment information made by each comment user, and obtaining a second scoring result; the first feedback module is used for feeding back a first scoring result; and the second feedback module is used for feeding back a second grading result.
9. An electronic device comprising a memory and a processor, the memory coupled to the processor; the memory is used for storing programs; the processor is configured to invoke a program stored in the memory to perform the method of any of claims 1-5.
10. A storage medium having stored therein program code executable by a processor, the storage medium comprising instructions configured to cause the processor to perform the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110374043.6A CN113065052A (en) | 2021-04-07 | 2021-04-07 | Method and device for analyzing authenticity of video comment, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110374043.6A CN113065052A (en) | 2021-04-07 | 2021-04-07 | Method and device for analyzing authenticity of video comment, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113065052A true CN113065052A (en) | 2021-07-02 |
Family
ID=76565911
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110374043.6A Pending CN113065052A (en) | 2021-04-07 | 2021-04-07 | Method and device for analyzing authenticity of video comment, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113065052A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108550065A (en) * | 2018-04-10 | 2018-09-18 | 百度在线网络技术（北京）有限公司 | comment data processing method, device and equipment |
| CN108804682A (en) * | 2018-06-12 | 2018-11-13 | 北京顶象技术有限公司 | Analyze method, apparatus, electronic equipment and the storage medium of video comments authenticity |
| CN110825876A (en) * | 2019-11-07 | 2020-02-21 | 上海德拓信息技术股份有限公司 | Movie comment viewpoint emotion tendency analysis method |
-
2021
- 2021-04-07 CN CN202110374043.6A patent/CN113065052A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108550065A (en) * | 2018-04-10 | 2018-09-18 | 百度在线网络技术（北京）有限公司 | comment data processing method, device and equipment |
| CN108804682A (en) * | 2018-06-12 | 2018-11-13 | 北京顶象技术有限公司 | Analyze method, apparatus, electronic equipment and the storage medium of video comments authenticity |
| CN110825876A (en) * | 2019-11-07 | 2020-02-21 | 上海德拓信息技术股份有限公司 | Movie comment viewpoint emotion tendency analysis method |
Non-Patent Citations (1)
| Title |
|---|
| 惊记: "BLP模型", 《HTTPS://ZHUANLAN.ZHIHU.COM/P/111889827?IVK_SA=1024320U》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8458046B2 (en) | Social media fact checking method and system | |
| US8543454B2 (en) | Generating audience response metrics and ratings from social interest in time-based media | |
| US10939165B2 (en) | Facilitating television based interaction with social networking tools | |
| Baveye et al. | A large video database for computational models of induced emotion | |
| CN110069663B (en) | Video recommendation method and device | |
| US20140298364A1 (en) | Recommendations for media content based on emotion | |
| US20120317046A1 (en) | Candidate fact checking method and system | |
| CN110019943B (en) | Video recommendation method and device, electronic equipment and storage medium | |
| CN105635824A (en) | Personalized channel recommendation method and system | |
| TW201340690A (en) | Video recommendation system and method thereof | |
| US8706655B1 (en) | Machine learned classifiers for rating the content quality in videos using panels of human viewers | |
| CN101281540A (en) | Apparatus, method and computer program for processing information | |
| CN116797282A (en) | Real-time monitoring system and monitoring method for advertisement delivery | |
| CN110851718A (en) | Movie recommendation method based on long-time memory network and user comments | |
| Deldjoo et al. | Using Visual Features and Latent Factors for Movie Recommendation. | |
| Ramprasad et al. | Spammer detection and tagging based user generated video search system—A survey | |
| CN111861550A (en) | OTT (over the Top) equipment-based family portrait construction method and system | |
| CN109063080B (en) | Video recommendation method and device | |
| CN113065052A (en) | Method and device for analyzing authenticity of video comment, electronic equipment and storage medium | |
| CN114443898B (en) | Video big data pushing method for Internet intelligent education | |
| Arya et al. | Predicting behavioural patterns in discussion forums using deep learning on hypergraphs | |
| Amali et al. | Semantic video recommendation system based on video viewers impression from emotion detection | |
| Wang et al. | A matrix factorization based framework for fusion of physical and social sensors | |
| Wit | Evaluating recommender systems: an evaluation framework to predict user satisfaction for recommender systems in an electronic programme guide context | |
| Kannan et al. | Improving video summarization based on user preferences |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210702 |