CN116822805A - Education video quality monitoring method based on big data - Google Patents
Education video quality monitoring method based on big data Download PDFInfo
- Publication number
- CN116822805A CN116822805A CN202311094874.3A CN202311094874A CN116822805A CN 116822805 A CN116822805 A CN 116822805A CN 202311094874 A CN202311094874 A CN 202311094874A CN 116822805 A CN116822805 A CN 116822805A
- Authority
- CN
- China
- Prior art keywords
- video
- coefficient
- health
- information
- blogger
- 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.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000036541 health Effects 0.000 claims abstract description 80
- 238000011156 evaluation Methods 0.000 claims abstract description 67
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 238000001514 detection method Methods 0.000 claims description 10
- 238000007405 data analysis Methods 0.000 claims description 8
- 230000007246 mechanism Effects 0.000 claims description 5
- 241000533950 Leucojum Species 0.000 claims description 3
- 238000013499 data model Methods 0.000 claims description 2
- 230000002950 deficient Effects 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 8
- 238000012550 audit Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000004630 mental health Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000001680 brushing effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 239000000470 constituent Substances 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
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000007493 shaping process Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Abstract
The application discloses an educational video quality monitoring method based on big data, which relates to the technical field of educational videos and comprises a data acquisition module, a video health degree evaluation module, a processing module, a video blog evaluation module, a comparison analysis module and a recording feedback module; the data acquisition module acquires the published educational video information with story and literature labels on the video platform, wherein the educational video information comprises video bad content information and audience report information, and the video bad content information and the audience report information are transmitted to the video health evaluation module after the data acquisition module acquires the educational video information. According to the application, through monitoring the education video facing the minors, when the education video is low in quality, monitoring, finding and reporting are carried out, and platform monitoring auditors are prompted to process the video, audit and pushing of the follow-up video of the video bloggers are reduced or increased, the workload of the platform auditors is reduced in a dynamic mode, the pertinence of work is improved, the outflow of bad videos is reduced, and the stable order of the education video industry is ensured.
Description
Technical Field
The application relates to the technical field of education videos, in particular to an education video quality monitoring method based on big data.
Background
The educational video quality monitoring method based on big data can monitor the quality of educational video through various means to ensure the correctness of video guidance, and the specific means comprise means such as content assessment, learning effect assessment, user feedback and investigation, watching analysis, interaction participation analysis, user behavior analysis, user satisfaction investigation, technical performance monitoring, social media analysis, privacy and security inspection and the like.
The video platform is used as a responsible person for video release and auditing, plays the role of screening excellent works meeting social value and shaping forward cognition of audiences, has various interest requirements of establishing user trust, promoting video innovation, maintaining platform reputation and the like, and under the purposes of the two aspects, the establishment of an educational video quality monitoring method with high accuracy and labor saving is imperative.
The prior art has the following defects:
since the quality detection of educational videos has a certain guiding effect on audiences, especially for minors, video websites not only pay attention to the quality of videos, but also avoid the occurrence of topics and talk which are not beneficial to the physical and mental health of minors. However, the conventional video website is not thorough in this aspect, and according to the conventional video pushing mechanism, big data can often push the works of the same video blogger according to the browsing records, but the video website does not have a related video pushing monitoring mechanism, so that the quality of the pushed video cannot be guaranteed to be consistent with the education of minors, especially for the education videos related to stories and literature, and many video bloggers may be converted from full-age to video authors. Therefore, the current education video monitoring method needs to be improved, thereby guaranteeing the learning quality and the user experience, and contributing to the sustainable development of the education field.
The above information disclosed in the background section is only for enhancement of understanding of the background of the disclosure and therefore it may include information that does not form the prior art that is already known to a person of ordinary skill in the art.
Disclosure of Invention
The application aims to provide a method for monitoring the quality of educational videos based on big data, which monitors, discovers and reports the educational videos for minors when the quality of the educational videos is low and prompts a platform monitoring auditor to process the videos, reduces or increases auditing and pushing follow-up videos of video bloggers, reduces the workload of the platform auditor in a dynamic mode, improves the working pertinence, reduces the outflow of bad videos and ensures the stable order of the educational video industry so as to solve the problems in the background technology.
In order to achieve the above object, the present application provides the following technical solutions: the education video quality monitoring method based on big data comprises a data acquisition module, a video health degree evaluation module, a processing module, a video blogger evaluation module, an comparison analysis module and a record feedback module;
the data acquisition module acquires the published educational video information with story and literature labels on the video platform, wherein the educational video information comprises video bad content information and audience report information, and the video bad content information and the audience report information are transmitted to the video health evaluation module after the data acquisition module acquires the educational video information with story and literature labels;
the video health evaluation module establishes a data analysis model with the collected video bad content information and audience report information, generates a video health evaluation index, and transmits the video health evaluation index to the processing module;
the processing module is used for comparing the video health degree evaluation index with the education video content standard reaching threshold value to generate a health video data signal, reducing the auditing strength of the generated health video data signal video and transmitting the health video data signal and the video health degree evaluation index to the video blogger evaluation module;
the video blogger assessment module is used for generating video violation information after integrating the health video data signals and the video health degree scoring indexes transmitted from the processing module, establishing a data model by combining the updated frequency information and the technical force information, generating a video blogger assessment index, and transmitting the generated video blogger assessment index to the comparison analysis module;
and the comparison analysis module is used for arranging the video blogger evaluation indexes transmitted by the video blogger evaluation module into a sequence according to the numerical value, identifying the video ranked in the front blogger as high-quality video, transmitting the high-quality video related information to the recording feedback module, and increasing the pushing quantity corresponding to the ranking.
Preferably, the video bad content information comprises a bad content duty ratio coefficient and a forward video health degree coefficient, and after the acquisition, the data acquisition module respectively marks the bad content duty ratio coefficient and the forward video health degree coefficient asThe audience report information comprises audience report coefficients, and after acquisition, the data acquisition module marks the audience report coefficients as +.>. Preferably, the logic for obtaining the bad content duty factor is as follows:
s1, monitoring occurrence frequency of bad content of a target video by searching bad content fields of the target videoAnd total duration of bad content +.>Setting the total length of video to +.>；
S2, when the bad content is frequentWhen the threshold value set by the video website is more than that set by the video website, the intelligent detection is changed into the manual detection, and the length of the removed bad content is set as +.>；
S3, the value of the bad content duty ratio coefficient is=/>；
The logic for acquiring the current video health coefficient is as follows:
s1, acquiring other video health evaluation indexes of the same video blogger before target video delivery in time sequenceN represents the number of the previous video, n=1, 2, 3, 4, … …, m being a positive integer;
s2, setting a corresponding video push weight as K according to a push mechanism of a video platform, such as push probability increased by the same label or labels;
s3, the video health degree coefficient of the past period is=/>/n；
The logic for the audience report coefficient acquisition is as follows:
s1, acquiring the report quantity and play quantity values of target video audiences, and setting the report quantity and play quantity values as values respectively；
S2, when the play quantity is lower than a threshold value set by the video platform, the audience report coefficient is always 0;
s3, when the play quantity is greater than or equal to a threshold value set by the video platform, reporting the coefficient by the audience=/>。
Preferably, the video health assessment module obtains bad content duty ratio coefficientsThe video health degree coefficient of the past period->Viewer reporting coefficient->Establishing a data analysis model to generate a video health evaluation index +.>The formula according to is:
wherein e1, e2 and e3 are respectively bad content duty ratio coefficientsThe video health degree coefficient of the past period->Viewer reporting coefficient->E1, e2, e3 are all greater than 0;
the processing module compares the video health evaluation index with the education video content standard reaching threshold value, and the video health evaluation index is divided into the following cases:
if the video health evaluation index is greater than or equal to the education video content standard reaching threshold, generating a health video data signal through a processing module, and reducing auditing strength of follow-up videos of the same video blogger;
if the video health evaluation index is smaller than the education video content standard reaching threshold, the processing module is not used for generating the health video data signal, and meanwhile, the auditing strength is increased for the follow-up video of the video blogger which does not generate the health video data signal.
Preferably, the video blogger evaluation module generates video violation information, update frequency information and technical force information after receiving the summary of the health video data signal and the video health score index transmitted from the processing module, wherein the video violation information comprises video violation coefficients and is calibrated asThe update frequency information includes update frequency coefficients, calibrated to +.>The technical force information comprises a technical force coefficient, which is marked as +.>。
Preferably, the logic for video violation coefficient acquisition is as follows:
s1, selecting all videos of a target video blogger, counting the total number of the videos, and setting the total number as；
S2, calculating an evaluation index difference value that the evaluation index of the video health degree is smaller than the education video content standard reaching threshold valueY represents the number of the selected low-evaluation index video, y=1, 2, 3, 4, … …, h being a positive integer;
s3, video violation coefficients=/>；
The logic for updating the frequency coefficient acquisition is as follows:
s1, acquiring the latest update quantity of a video of a target video blogger, and taking the video with story and literature education labels which reach the standard of the specified duration of a platform as a collection object;
s2, taking the last month, the last week and the last day as video update quantity collection periods, respectively calculating the values of update frequency coefficients, and respectively setting the update video quantity as；
S3, updating the frequency coefficient=/>；
The logic for obtaining the technical force coefficient is as follows:
acquiring total duration, standard and definition duration above of a target video blog main video, and the number of times of occurrence of problems affecting the look and feel such as snowflake points, stripes, play interface fluctuation and the like, and respectively setting as、/> 、/>And->Technical force coefficient->//>。
Preferably, the video blogger evaluation module obtains the video violation coefficientsUpdate frequency coefficient->Technical force coefficient->Establishing a data analysis model to generate a video blogger assessment index +.>The formula according to is:
wherein e1, e2 and e3 are video violation coefficients +.>Update frequency coefficient->Technical force coefficient->E1, e2, e3 are all greater than 0;
the comparison analysis module is used for comparing the video blogger evaluation index received from the video blogger evaluation moduleRanking all juveniles relevant to stories and literature in the website to video bloggers of educational videos, wherein the ranking order is in accordance with video blogger evaluation index +.>The video ranked in the front blogger is regarded as high-quality video, and the related information of the high-quality video is transmitted to a record feedback module, so that the pushing amount corresponding to the ranking is increased.
In the technical scheme, the application has the technical effects and advantages that:
according to the application, through monitoring the education video facing the minors, when the education video is low in quality, monitoring, finding and reporting, prompting platform monitoring auditors to process the video, reducing or increasing auditing and pushing of the follow-up video of the video bloggers, reducing the workload of the platform auditors in a dynamic mode, improving the pertinence of work, reducing the outflow of bad videos and guaranteeing the stable order of the education video industry;
according to the application, through comprehensively analyzing the evaluation indexes of the video health degree generated by evaluating the educational videos of the juveniles related to stories and literature, the accidental anomaly in the educational video quality monitoring process is eliminated through the modes of real-time adjustment of the platform threshold value, too few samples, no influence coefficient and the like, the accuracy of collecting the educational video quality monitoring data is improved, the trust of monitoring personnel of a video platform to the method is further improved, and the efficient operation of the educational video quality monitoring method is ensured.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments described in the present application, and other drawings may be obtained according to these drawings for those skilled in the art.
Fig. 1 is a schematic block diagram of an educational video quality monitoring method based on big data in the present application.
Description of the embodiments
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.
The application provides an educational video quality monitoring method based on big data as shown in figure 1, which comprises a data acquisition module, a video health degree evaluation module, a processing module, a video blogger evaluation module, an comparison analysis module and a record feedback module;
the data acquisition module acquires the published educational video information with story and literature labels on the video platform, wherein the educational video information comprises video bad content information and audience report information, and the video bad content information and the audience report information are transmitted to the video health evaluation module after acquisition;
the video bad content information comprises a bad content duty ratio coefficient and a forward video health degree coefficient, and after the acquisition, the data acquisition module respectively marks the bad content duty ratio coefficient and the forward video health degree coefficient asThe audience report information comprises audience report coefficients, and after acquisition, the data acquisition module marks the audience report coefficients as +.>。
In embodiment 1, when bad content appears in an educational video in the educational video quality monitoring method based on big data, bad guidance and physical and mental health influence may be caused to minors, and reputation of a video platform is damaged, so that distrust on the video platform is caused. Therefore, in order to expand the breadth of the video platform for educational video monitoring and improve the quality of educational video, the following quantitative values should be specifically used for evaluation and description:
audience report coefficient: the educational video is taken as one of the constituent components of the video platform, is supposed to be supervised and reported by audiences, but in order to avoid the occurrence of malicious brushing and reporting, the audience reporting coefficient is only one link for evaluating the video health degree, and whether the video content is healthy or not is determined through multiple-aspect evaluation.
Poor content duty ratio coefficient: the method aims at education videos with story and literature labels for minors, resists the plots with relevant detailed descriptions of bad guidance such as bloody fishy smell, violence, pornography, horror, crime and the like, and ensures that errors do not occur in the manner of intelligent retrieval and manual confirmation of pronunciation and captions containing relevant contents.
Technical force coefficient: the technical power contained in video directly affects the viewing experience of the viewer. High definition, smooth play, good sound effect, etc. can promote audience satisfaction. In the education field, high-technical-force education videos can clearly and accurately transmit knowledge and teaching contents, and understanding and learning effects of students are improved. The technical capability of the video can not only improve the efficiency and accuracy of information transmission, but also improve the user experience, shape the brand image and promote creative expression, and has important roles in the development of society and culture.
The evaluation is carried out on educational videos related to stories and literature for minors, correct guiding of the videos is ensured, the auditing strength of the subsequent videos is determined by the score of a single video, the video quality evaluation is influenced, meanwhile, a video blogger with generally higher video quality is given with rewards for increasing pushing amount, and the video blogger is encouraged to recreate high-quality videos.
Therefore, the logic for bad content duty factor acquisition is as follows:
s1, monitoring occurrence frequency of bad content of a target video through intelligent detection of modes such as searching bad content fields of the target videoAnd total duration of bad content +.>The duration of bad content is determined according to the duration of a sentence appearing in the bad field, and the total length of the video is set as +.>；
S2, when the bad content is frequentWhen the threshold value set by the video website is more than that set by the video website, the intelligent detection is changed into the manual detection, and the length of the removed bad content is set as +.>；
S3, the value of the bad content duty ratio coefficient is=/>The bad frequency threshold set by the video website is determined by the intelligent detection accuracy of the video website, and bad content duration information after intelligent detection errors are removed as far as possible is obtained.
The logic for acquiring the current video health coefficient is as follows:
S1、acquiring other video health evaluation indexes of the same video footstep before target video delivery in time sequenceN represents the number of the previous video, n=1, 2, 3, 4, … …, m being a positive integer;
s2, setting a corresponding video push weight as K according to a push mechanism of a video platform, such as push probability increased by the same label or labels;
s3, the video health degree coefficient of the past period is=/>And/n, through detecting the health degree coefficient of the video in the forward period of the same video, the auditing strength of the subsequent video is directly influenced, and the video pushing force is indirectly influenced, so that the phenomenon that other bad videos of the same blog are pushed after the education video is played is reduced.
The logic for the audience report coefficient acquisition is as follows:
s1, acquiring the report quantity and play quantity values of target video audiences, and setting the report quantity and play quantity values as values respectively；
S2, when the play quantity is lower than a threshold value set by the video platform, the audience report coefficient is always 0, so that errors caused by accidental events when the data value is too small are avoided;
s3, when the play quantity is greater than or equal to a threshold value set by the video platform, reporting the coefficient by the audience=/>。
The video health evaluation module obtains bad content duty ratio coefficientThe video health degree coefficient of the past period->Viewer reporting coefficient->Establishing a data analysis model to generate a video health evaluation index +.>The formula according to is:
wherein e1, e2 and e3 are respectively bad content duty ratio coefficientsThe video health degree coefficient of the past period->Viewer reporting coefficient->E1, e2, e3 are all greater than 0;
from the calculated expression, the larger the expression value of the video health evaluation index is, the fewer unhealthy guides in the education video are indicated, and conversely, the more unhealthy guides are indicated, the lower the quality is;
the processing module compares the video health evaluation index generated during wholesale of the electronic product with the education video content standard reaching threshold value, and the video health evaluation index is divided into the following cases:
if the video health evaluation index is greater than or equal to the education video content standard reaching threshold, generating a health video data signal through a processing module, and reducing auditing strength of follow-up videos of the same video blogger;
if the video health evaluation index is smaller than the education video content standard reaching threshold, the processing module is not used for generating the health video data signal, and meanwhile, the auditing strength is increased for the follow-up video of the video blogger which does not generate the health video data signal.
Embodiment 2, after the video blogger evaluation module receives the high frequency disqualification signal, the video violationsRule information, update frequency information and technical force information, the video violation information comprises video violation coefficients, and is calibrated asThe update frequency information includes update frequency coefficients, calibrated to +.>The technical force information comprises a technical force coefficient, which is marked as +.>。
The logic for video violation coefficient acquisition is as follows:
s1, selecting all videos of a target video blogger, counting the total number of the videos, and setting the total number as；
S2, calculating an evaluation index difference value that the evaluation index of the video health degree is smaller than the education video content standard reaching threshold valueY represents the number of the selected low-evaluation index video, y=1, 2, 3, 4, … …, h being a positive integer;
s3, video violation coefficients=/>；
The logic for updating the frequency coefficient acquisition is as follows:
s1, acquiring the latest update quantity of a video of a target video blogger, and taking the video with story and literature education labels which reach the standard of the specified duration of a platform as a collection object;
s2, taking the last month, the last week and the last day as video update quantity collection periods, respectively calculating the values of update frequency coefficients, and respectively setting the update video quantity as；
S3, updating the frequency coefficient=/>；
The logic for obtaining the technical force coefficient is as follows:
acquiring total duration, standard and definition duration (such as 1080P standard definition of part of websites) of a target video blog main video, and the number of times of occurrence of problems affecting the look and feel such as snowflake points, stripes and play interface fluctuation, and setting as follows respectively、/>And->Technical force coefficient->//>。
The video doctor evaluation module obtains the video violation coefficientsUpdate frequency coefficient->Coefficient of technical forceEstablishing a data analysis model to generate a video blogger assessment index +.>The formula according to is:
wherein e1, e2 and e3 are video violation coefficients +.>Update frequency coefficient->Technical force coefficient->E1, e2, e3 are all greater than 0;
the comparison analysis module is used for comparing the video blogger evaluation index received from the video blogger evaluation moduleRanking all juveniles relevant to stories and literature in the website to video bloggers of educational videos, wherein the ranking order is in accordance with video blogger evaluation index +.>The video ranked in the front blogger is regarded as high-quality video, and the related information of the high-quality video is transmitted to a record feedback module, so that the pushing amount corresponding to the ranking is increased.
According to the application, through monitoring the education video facing the minors, when the education video is low in quality, monitoring, finding and reporting, prompting platform monitoring auditors to process the video, reducing or increasing auditing and pushing of the follow-up video of the video bloggers, reducing the workload of the platform auditors in a dynamic mode, improving the pertinence of work, reducing the outflow of bad videos and guaranteeing the stable order of the education video industry;
the above formulas are all formulas with dimensions removed and numerical values calculated, the formulas are formulas with a large amount of data collected for software simulation to obtain the latest real situation, and preset parameters in the formulas are set by those skilled in the art according to the actual situation.
The above embodiments may be implemented in whole or in part by software, hardware, firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired or wireless means (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software 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 application.
In the several embodiments provided by the present application, it should be understood that the disclosed systems and methods may be implemented in other ways. For example, the embodiments described above are merely illustrative, e.g., the division of the elements is merely a logical functional division, and there may be additional divisions in actual implementation, e.g., multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (7)
1. The educational video quality monitoring method based on big data is characterized in that: the method comprises the following steps:
s1: the method comprises the steps of collecting education video information which is published on a video platform and has story and literature labels, including video bad content information and audience report information, and sorting multi-source data;
s2: establishing a data analysis model for the collected bad content information of the video and the audience report information to generate a video health evaluation index;
s3: and comparing the video health evaluation index with the education video content standard reaching threshold value to generate a health video data signal.
2. The educational video quality monitoring method based on big data according to claim 1, wherein the information of the bad content of the video comprises a bad content duty ratio coefficient and a forward video health degree coefficient, and the data acquisition module respectively marks the bad content duty ratio coefficient and the forward video health degree coefficient asThe audience report information comprises audience report coefficients, and after acquisition, the data acquisition module marks the audience report coefficients as +.>。
3. The educational video quality monitoring method based on big data according to claim 2, wherein the logic for obtaining the bad content duty factor is as follows:
s1, monitoring occurrence frequency of bad content of a target video by searching bad content fields of the target videoAnd total duration of bad content +.>Setting the total length of video to +.>；
S2, when the bad content is frequentWhen the threshold value set by the video website is more than that set by the video website, the intelligent detection is changed into the manual detection, and the length of the removed bad content is set as +.>；
S3, the value of the bad content duty ratio coefficient is=/>；
The logic for acquiring the current video health coefficient is as follows:
s1, acquiring other video health evaluation indexes of the same video blogger before target video delivery in time sequenceN represents the number of the previous video, n=1, 2, 3, 4, … …, m being a positive integer;
s2, setting a corresponding video pushing weight as K according to a pushing mechanism of the video platform;
s3, the video health degree coefficient of the past period is=/>/n；
The logic for the audience report coefficient acquisition is as follows:
s1, acquiring the report quantity and play quantity values of target video audiences, and setting the report quantity and play quantity values as values respectively；
S2, when the play quantity is lower than a threshold value set by the video platform, the audience report coefficient is always 0;
s3, when the play quantity is greater than or equal to a threshold value set by the video platform, reporting the coefficient by the audience=/>。
4. The educational video quality monitoring method based on big data according to claim 3, wherein the video health evaluation module obtains bad content duty factorThe video health degree coefficient of the past period->Viewer reporting coefficient->Establishing a data analysis model to generate a video health evaluation index +.>The formula according to is:
wherein e1, e2 and e3 are each the defective content duty ratio coefficient +.>The video health degree coefficient of the past period->Viewer reporting coefficient->E1, e2, e3 are all greater than 0;
the processing module compares the video health evaluation index with the education video content standard reaching threshold value, and the video health evaluation index is divided into the following cases: if the video health evaluation index is greater than or equal to the education video content standard reaching threshold, generating a health video data signal through a processing module, and reducing auditing strength of follow-up videos of the same video blogger;
if the video health evaluation index is smaller than the education video content standard reaching threshold, the processing module is not used for generating the health video data signal, and meanwhile, the auditing strength is increased for the follow-up video of the video blogger which does not generate the health video data signal.
5. The method for educational video quality monitoring based on big data according to claim 4, further comprising the steps of;
s4: generating video violation information after summarizing the health video data signals and the video health degree scoring indexes sent out based on the processing results, and establishing a data model by combining the updating frequency information and the technical force information to generate a video blogger assessment index; s5: arranging the video blogger evaluation indexes into a sequence according to the numerical value, and recognizing the video ranked in the front blogger as high-quality video, and increasing the pushing quantity corresponding to the ranking;
the video blogger evaluation module receivesAfter the health video data signals and the video health degree scoring indexes transmitted from the processing module are summarized, video violation information, updating frequency information and technical force information are generated, wherein the video violation information comprises video violation coefficients and is calibrated asThe update frequency information includes update frequency coefficients, calibrated to +.>The technical force information comprises a technical force coefficient, which is marked as +.>。
6. The educational video quality monitoring method based on big data according to claim 5, wherein the logic for obtaining the video violation coefficients is as follows:
s1, selecting all videos of a target video blogger, counting the total number of the videos, and setting the total number as；
S2, calculating an evaluation index difference value that the evaluation index of the video health degree is smaller than the education video content standard reaching threshold valueY represents the number of the selected low-evaluation index video, y=1, 2, 3, 4, … …, h being a positive integer;
s3, video violation coefficients=/>The method comprises the steps of carrying out a first treatment on the surface of the The logic for updating the frequency coefficient acquisition is as follows:
s1, acquiring the latest update quantity of a video of a target video blogger, and taking the video with story and literature education labels which reach the standard of the specified duration of a platform as a collection object;
s2, taking the last month, the last week and the last day as video update quantity collection periods, respectively calculating the values of update frequency coefficients, and respectively setting the update video quantity as；
S3, updating the frequency coefficient=/>；
The logic for obtaining the technical force coefficient is as follows:
acquiring total duration, standard and definition duration above of a target video blog main video, and the number of times of occurrence of problems affecting the look and feel such as snowflake points, stripes, play interface fluctuation and the like, and respectively setting as、/>And->Technical force coefficient->=。
7. The method of claim 6, wherein the video score evaluation module obtains a video violation coefficientUpdate frequency coefficient->Technical force coefficient->Establishing a data analysis model to generate a video blogger assessment index +.>The formula according to is:
wherein e1, e2 and e3 are video violation coefficients +.>Updating frequency coefficientsTechnical force coefficient->E1, e2, e3 are all greater than 0; the comparison analysis module is used for receiving the video blogger assessment index from the video blogger assessment module>Ranking all juveniles relevant to stories and literature in the website to video bloggers of educational videos, wherein the ranking order is in accordance with video blogger evaluation index +.>The video ranked in the front blogger is regarded as high-quality video, and the related information of the high-quality video is transmitted to a record feedback module, so that the pushing amount corresponding to the ranking is increased.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311094874.3A CN116822805B (en) | 2023-08-29 | 2023-08-29 | Education video quality monitoring method based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311094874.3A CN116822805B (en) | 2023-08-29 | 2023-08-29 | Education video quality monitoring method based on big data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116822805A true CN116822805A (en) | 2023-09-29 |
| CN116822805B CN116822805B (en) | 2023-12-15 |
Family
ID=88139521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311094874.3A Active CN116822805B (en) | 2023-08-29 | 2023-08-29 | Education video quality monitoring method based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116822805B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090102954A (en) * | 2008-03-27 | 2009-10-01 | 오비에스경인티브이 주식회사 | Remote broadcasting program producing system using of a wire/wireless communication means and method of the same |
| CN101834846A (en) * | 2010-03-30 | 2010-09-15 | 王兴强 | Minor health website authentication system and method |
| CN103020123A (en) * | 2012-11-16 | 2013-04-03 | 中国科学技术大学 | Method for searching bad video website |
| CN108170813A (en) * | 2017-12-29 | 2018-06-15 | 智搜天机（北京）信息技术有限公司 | A kind of method and its system of full media content intelligent checks |
| CN109819267A (en) * | 2018-12-30 | 2019-05-28 | 广东彼雍德云教育科技有限公司 | A kind of online cloud is straight, recording and broadcasting system |
| CN110365996A (en) * | 2019-07-25 | 2019-10-22 | 深圳市元征科技股份有限公司 | Management method, live streaming management platform, electronic equipment and storage medium is broadcast live |
| CN112492343A (en) * | 2020-12-16 | 2021-03-12 | 浙江大华技术股份有限公司 | Video live broadcast monitoring method and related device |
| CN112995696A (en) * | 2021-04-20 | 2021-06-18 | 共道网络科技有限公司 | Live broadcast room violation detection method and device |
| CN113315994A (en) * | 2021-04-23 | 2021-08-27 | 北京达佳互联信息技术有限公司 | Live broadcast data processing method and device, electronic equipment and storage medium |
| CN113765895A (en) * | 2021-08-13 | 2021-12-07 | 北京奇艺世纪科技有限公司 | Auditing method and device for live broadcast room |
| CN114786038A (en) * | 2022-03-29 | 2022-07-22 | 慧之安信息技术股份有限公司 | Low-custom live broadcast behavior monitoring method based on deep learning |
| WO2022161328A1 (en) * | 2021-01-26 | 2022-08-04 | 北京有竹居网络技术有限公司 | Video processing method and apparatus, storage medium, and device |
| CN116074543A (en) * | 2021-11-02 | 2023-05-05 | 上海奥拉维网络科技有限公司 | Live broadcast data supervision system based on live broadcast interaction platform |
-
2023
- 2023-08-29 CN CN202311094874.3A patent/CN116822805B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20090102954A (en) * | 2008-03-27 | 2009-10-01 | 오비에스경인티브이 주식회사 | Remote broadcasting program producing system using of a wire/wireless communication means and method of the same |
| CN101834846A (en) * | 2010-03-30 | 2010-09-15 | 王兴强 | Minor health website authentication system and method |
| CN103020123A (en) * | 2012-11-16 | 2013-04-03 | 中国科学技术大学 | Method for searching bad video website |
| CN108170813A (en) * | 2017-12-29 | 2018-06-15 | 智搜天机（北京）信息技术有限公司 | A kind of method and its system of full media content intelligent checks |
| CN109819267A (en) * | 2018-12-30 | 2019-05-28 | 广东彼雍德云教育科技有限公司 | A kind of online cloud is straight, recording and broadcasting system |
| CN110365996A (en) * | 2019-07-25 | 2019-10-22 | 深圳市元征科技股份有限公司 | Management method, live streaming management platform, electronic equipment and storage medium is broadcast live |
| CN112492343A (en) * | 2020-12-16 | 2021-03-12 | 浙江大华技术股份有限公司 | Video live broadcast monitoring method and related device |
| WO2022161328A1 (en) * | 2021-01-26 | 2022-08-04 | 北京有竹居网络技术有限公司 | Video processing method and apparatus, storage medium, and device |
| CN112995696A (en) * | 2021-04-20 | 2021-06-18 | 共道网络科技有限公司 | Live broadcast room violation detection method and device |
| CN113315994A (en) * | 2021-04-23 | 2021-08-27 | 北京达佳互联信息技术有限公司 | Live broadcast data processing method and device, electronic equipment and storage medium |
| CN113765895A (en) * | 2021-08-13 | 2021-12-07 | 北京奇艺世纪科技有限公司 | Auditing method and device for live broadcast room |
| CN116074543A (en) * | 2021-11-02 | 2023-05-05 | 上海奥拉维网络科技有限公司 | Live broadcast data supervision system based on live broadcast interaction platform |
| CN114786038A (en) * | 2022-03-29 | 2022-07-22 | 慧之安信息技术股份有限公司 | Low-custom live broadcast behavior monitoring method based on deep learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116822805B (en) | 2023-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Muric et al. | COVID-19 vaccine hesitancy on social media: building a public Twitter data set of antivaccine content, vaccine misinformation, and conspiracies | |
| US10945043B2 (en) | Methods and apparatus to create a panel of media device users | |
| US20170289619A1 (en) | Method for positioning video, terminal apparatus and cloud server | |
| Taneja et al. | Media consumption across platforms: Identifying user-defined repertoires | |
| US20180082313A1 (en) | Systems and methods for prioritizing user reactions to content for response on a social-media platform | |
| US20180341877A1 (en) | Escalation of machine-learning inputs for content moderation | |
| CN104657425A (en) | Topic management type network public opinion evaluation management system and method | |
| Ngai et al. | Impact of COVID-19 vaccine misinformation on social media virality: content analysis of message themes and writing strategies | |
| CN105068935B (en) | Method and device for processing software test result | |
| CN105183925A (en) | Content association recommending method and content association recommending device | |
| Heerwegh | Internet survey paradata | |
| RU2583764C1 (en) | Method of processing request for user to access web resource and server | |
| Wiertsema et al. | Bullying perpetration and social status in the peer group: A meta‐analysis | |
| EP3620936A1 (en) | System and method for recommending multimedia data | |
| CN112073757B (en) | Emotion fluctuation index acquisition method, emotion fluctuation index display method and multimedia content production method | |
| Jing et al. | A visual analytic tool (VIADS) to assist the hypothesis generation process in clinical research: mixed methods Usability study | |
| Kren et al. | Modeling opinion of IPTV viewers based on implicit feedback and content metadata | |
| Couper | Birth and Diffusion of the Concept of Paradata | |
| Tian | Impact of social media news overload on social media news avoidance and filtering: Moderating effect of media literacy | |
| CN116822805B (en) | Education video quality monitoring method based on big data | |
| Ntoa et al. | UXAmI observer: an automated user experience evaluation tool for ambient intelligence environments | |
| CN114640884B (en) | Online video playing quality analysis method, system and computer storage medium | |
| US20170295126A1 (en) | Real-time collection, analysis and presentation of aggregated selection data by users of social media | |
| CN110139160B (en) | Prediction system and method | |
| Weinauer | Be a detective for a day: how to detect falsified interviews with statistics |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231113 Address after: 1102, 10th Floor, Building 1, No. 113 Zhichun Road, Haidian District, Beijing, 100086 Applicant after: Beijing Cainiao Wuyou Education Technology Co.,Ltd. Address before: 518000 Room 101, No. 88, zone 1, No. 5 Industrial Zone, Shangfen community, Minzhi street, Longhua District, Shenzhen, Guangdong Province Applicant before: SHENZHEN V-SENT TECHNOLOGY CO.,LTD. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |