CN117333800B - Cross-platform content operation optimization method and system based on artificial intelligence - Google Patents
Cross-platform content operation optimization method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN117333800B CN117333800B CN202311320007.7A CN202311320007A CN117333800B CN 117333800 B CN117333800 B CN 117333800B CN 202311320007 A CN202311320007 A CN 202311320007A CN 117333800 B CN117333800 B CN 117333800B
- Authority
- CN
- China
- Prior art keywords
- information
- platform
- analysis
- video
- rule
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 43
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000004458 analytical method Methods 0.000 claims abstract description 289
- 230000006978 adaptation Effects 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims description 39
- 238000001514 detection method Methods 0.000 claims description 37
- 238000006243 chemical reaction Methods 0.000 claims description 18
- 238000012544 monitoring process Methods 0.000 claims description 17
- 238000012549 training Methods 0.000 claims description 16
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 12
- 230000000694 effects Effects 0.000 claims description 11
- 238000010586 diagram Methods 0.000 claims description 10
- 230000008451 emotion Effects 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 230000003044 adaptive effect Effects 0.000 claims description 8
- 238000009472 formulation Methods 0.000 claims description 8
- 239000000203 mixture Substances 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 238000003058 natural language processing Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 description 9
- 238000004088 simulation Methods 0.000 description 8
- 238000012502 risk assessment Methods 0.000 description 7
- 238000003860 storage Methods 0.000 description 7
- 230000008901 benefit Effects 0.000 description 3
- 230000010354 integration Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000013486 operation strategy Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000699 topical effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
-
- 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
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a cross-platform content operation optimization method and a system based on artificial intelligence, comprising the following steps: acquiring initial video information, and performing video semantic analysis on the initial video information to obtain first analysis result information; constructing a language analysis model, and performing word recognition and semantic analysis on the initial video information to obtain second analysis result information; acquiring the usage rule information and notice information of each platform, and analyzing the usage rule and notice of each platform to obtain platform rule analysis information; acquiring characteristic information of each platform, and carrying out platform characteristic analysis and user preference analysis to obtain platform characteristic analysis information and user preference analysis information; performing platform adaptation and delivery recommendation, optimizing video content according to delivery recommendation information, and automatically delivering the optimized video to a corresponding platform. The efficiency of content operation and the coverage rate of the released content are improved, the requirements of different platforms are automatically met, and personalized content creation and release suggestions are provided.
Description
Technical Field
The invention relates to the technical field of content operation optimization, in particular to a cross-platform content operation optimization method and system based on artificial intelligence.
Background
With the rapid growth of the internet and social media, the content authoring and digital advertising industry is facing increasing challenges. Different digital platforms have different audience groups and requirements, so content creators or operators need customized content and advertisement creation according to the characteristics of each platform. This results in high cost and inefficiency, making cross-platform content operations complex and expensive.
Currently, content creators or operators often need to manually adapt to the needs of different platforms, including text, visual elements, advertisement formats, keywords, and the like. This is not only time consuming and laborious, but also prone to errors and inconsistencies. And with the rapid development of social media platforms, content creators or operators need to publish and operate content on each platform, but the requirements and specifications of each platform are different, which brings great challenges to the content creators. The multi-platform content operation at present is generally finished by specially arranging operators, normally each operator can only face the content processing of a plurality of platforms, the operation efficiency is low, and the coverage of most of domestic platforms cannot be finished at the same time in time. Therefore, how to improve the working efficiency of operators and achieve low-cost full coverage of content creation is an important problem.
Disclosure of Invention
The invention overcomes the defects of the prior art, and provides a cross-platform content operation optimization method and system based on artificial intelligence, which aim at improving operation efficiency and content coverage.
In order to achieve the above object, the first aspect of the present invention provides a cross-platform content operation optimization method based on artificial intelligence, which includes:
acquiring initial video information, and performing video semantic analysis on the initial video information to obtain first analysis result information;
constructing a language analysis model, and performing word recognition and semantic analysis on the initial video information to obtain second analysis result information;
acquiring the usage rule information and notice information of each platform, and analyzing the usage rule and notice of each platform to obtain platform rule analysis information;
acquiring characteristic information of each platform, and carrying out platform characteristic analysis and user preference analysis to obtain platform characteristic analysis information and user preference analysis information;
performing platform adaptation and delivery recommendation, optimizing video content according to delivery recommendation information, and automatically delivering the optimized video to a corresponding platform.
In this scheme, the video semantic analysis is performed on the initial video information, specifically:
Acquiring initial video information, and performing noise reduction, filtering and enhancement preprocessing on the initial video information to obtain preprocessed video information;
the preprocessing video information is subjected to video segmentation, the preprocessing video information is segmented into a series of discrete image frames based on a frame extraction algorithm, and each image frame is subjected to time sequence marking to obtain marked image frame information;
performing target detection on each frame image in the marked image frame information based on a target detection algorithm to obtain target objects, scenes and elements of each frame image, and obtaining target detection result information;
extracting features of the target detection result information, and further extracting image features, scene features and texture features to obtain feature extraction information;
constructing a video analysis model, importing the feature extraction information and the marked image frame information into the video analysis model for analysis, and analyzing the scene and object changes to obtain a key frame of a target video to obtain first analysis result information;
the first analysis result information includes: video scene analysis information, video character analysis information, and scene break analysis information.
In this scheme, the text recognition and semantic analysis are performed on the initial video information to obtain second analysis result information, specifically:
Constructing a language analysis model, inputting the initial video information into the language analysis model for processing, and extracting the audio information of the initial video information to obtain audio extraction information;
retrieving and acquiring the text and audio track information of each medium language based on the big data to form an audio comparison database;
acquiring text information of various emotion categories based on big data retrieval, forming a semantic analysis training data set, and training the language analysis model through the semantic analysis training data set;
performing similarity calculation on the audio extraction information and the audio comparison database, judging with a preset threshold value, and performing text conversion according to a judgment result to obtain text conversion information;
performing scene matching on the character conversion information and the initial video information, and marking the video scene and the character corresponding to each character to obtain character marking information;
and importing the text marking information and the text conversion information into a language analysis model for semantic analysis, and identifying text emotion and text meaning of the analysis target video to obtain second analysis result information.
In this scheme, the acquiring the usage rule information and the notice information of each platform, analyzing the usage rule and the notice of each platform specifically includes:
Acquiring usage rule information and notice information of each platform, and performing text extraction, cleaning and text correction pretreatment on the usage rule information and the notice information;
carrying out keyword detection and extraction on the usage rule information and the notice information to obtain keyword extraction information;
constructing a topic identification model based on a natural language processing technology, and carrying out topic identification and keyword detection on the usage rule information and the notice information through the topic identification model to obtain topic identification information and keyword detection information;
content segmentation is carried out on the usage rule information and the notice information according to the topic identification information, and sentences or paragraphs with related topics are segmented to obtain content segmentation information;
extracting key contents according to the key word detection information and the content segmentation information, and generating a content abstract and a rule abstract according to the extracted key content information to obtain platform rule analysis information;
presetting a regular monitoring interval, and periodically monitoring the usage rules and notes of each platform according to the regular monitoring interval to obtain monitoring rule information;
analyzing the monitoring rule information to obtain each piece of platform rule information at the current moment, and calculating the similarity with the platform rule analysis information to obtain a similarity value;
And updating a judgment threshold value by a preset rule, judging the similarity value and the preset threshold value, and updating the rule according to a judgment result.
In this scheme, the platform feature analysis and user preference analysis are performed specifically as follows:
acquiring characteristic information of each platform, wherein the characteristic information of each platform comprises: platform user information, platform main stream content information and user use information;
constructing a data analysis model, inputting the platform characteristic information into the data analysis model, and carrying out platform characteristic analysis and user preference analysis;
determining user use groups of each platform by analyzing the age, sex and geographic position of the users of each platform to obtain user use group information;
presetting a plurality of type judgment thresholds, judging the user group information and the type judgment thresholds, and classifying each platform according to the age tendency and the geographic position of the user to obtain platform class classification information;
carrying out platform hot spot analysis through the platform main stream content information and the user use information, extracting the browsing amount of each main stream content and the use frequency of the interaction mode, and carrying out sequential sorting to obtain a main stream content sorting diagram;
carrying out platform hot spot analysis through the main stream content ranking chart, and analyzing hot spot content and interaction modes of each platform in unit time to obtain hot spot analysis information;
And fusing the platform category division information and the hot spot analysis information to form platform characteristic analysis information.
In this solution, the performing platform feature analysis and user preference analysis further includes:
acquiring characteristic information of each platform, carrying out characteristic extraction on the characteristic information of each platform, acquiring the activity of each platform user in each time period, and sorting according to the activity to obtain an activity sorting table;
presetting a selection threshold, and carrying out user peak use time period analysis according to the selection threshold and an active amount ranking table to obtain peak use time period analysis information;
carrying out hot spot statistics by combining platform characteristic analysis information and peak use time period analysis information to acquire user preference browsing information;
presetting a plurality of browsing categories, carrying out correlation analysis on user preference browsing information and browsing categories based on a mahalanobis distance algorithm, and analyzing the user preference browsing categories to obtain user preference browsing category information;
the user preference analysis information is formed by combining the user browsing category information and peak use time period analysis information.
In this scheme, carry out platform adaptation and put in the recommendation, carry out the video content optimization according to putting in recommendation information to put in the video after optimizing to corresponding platform voluntarily, specifically:
Acquiring release demand information and platform characteristic analysis information, performing adaptation platform analysis, and calculating a similarity value of the release demand information and the platform characteristic information;
judging the calculated similarity value and a preset threshold value, selecting an adaptive platform according to a judging result, and carrying out release recommendation according to the selected adaptive platform to obtain release recommendation information;
platform rule analysis information is obtained, rule extraction is carried out on the platform rule analysis information according to the release recommendation information, and release platform rule information is obtained;
acquiring first analysis result information and second analysis result information;
constructing a content optimization model, inputting the first analysis result information, the second analysis result information and the delivery platform rule information into the content optimization model for video optimization, and enabling the video to be delivered to conform to the delivery rule of the delivery platform to obtain optimized video information;
acquiring user preference analysis information, and carrying out release strategy formulation by combining the release recommendation information, the first analysis result information and the second analysis result information, wherein the release strategy formulation comprises video theme generation, distribution diagram generation, text adjustment and release time selection, so as to acquire release strategy information;
And delivering the optimized video information to a corresponding adaptation platform according to the delivery strategy information.
The second aspect of the present invention provides a cross-platform content operation optimization system based on artificial intelligence, the system comprising: the system comprises a memory and a processor, wherein the memory contains an artificial intelligence-based cross-platform content operation optimization method program, and the artificial intelligence-based cross-platform content operation optimization method program realizes the following steps when being executed by the processor:
acquiring initial video information, and performing video semantic analysis on the initial video information to obtain first analysis result information;
constructing a language analysis model, and performing word recognition and semantic analysis on the initial video information to obtain second analysis result information;
acquiring the usage rule information and notice information of each platform, and analyzing the usage rule and notice of each platform to obtain platform rule analysis information;
acquiring characteristic information of each platform, and carrying out platform characteristic analysis and user preference analysis to obtain platform characteristic analysis information and user preference analysis information;
performing platform adaptation and delivery recommendation, optimizing video content according to delivery recommendation information, and automatically delivering the optimized video to a corresponding platform.
The invention discloses a cross-platform content operation optimization method and a system based on artificial intelligence, comprising the following steps: acquiring initial video information, and performing video semantic analysis on the initial video information to obtain first analysis result information; constructing a language analysis model, and performing word recognition and semantic analysis on the initial video information to obtain second analysis result information; acquiring the usage rule information and notice information of each platform, and analyzing the usage rule and notice of each platform to obtain platform rule analysis information; acquiring characteristic information of each platform, and carrying out platform characteristic analysis and user preference analysis to obtain platform characteristic analysis information and user preference analysis information; performing platform adaptation and delivery recommendation, optimizing video content according to delivery recommendation information, and automatically delivering the optimized video to a corresponding platform. The efficiency of content operation and the coverage rate of the released content are improved, the requirements of different platforms are automatically met, and personalized content creation and release suggestions are provided.
Drawings
In order to more clearly illustrate the technical solutions of embodiments or examples of the present invention, the drawings that are required to be used in the embodiments or examples of the present invention will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive efforts for those skilled in the art.
FIG. 1 is a flowchart of a cross-platform content operation optimization method based on artificial intelligence according to an embodiment of the present invention;
FIG. 2 is a data processing flow chart of a cross-platform content operation method based on artificial intelligence according to an embodiment of the present invention;
FIG. 3 is a block diagram of a cross-platform content operation optimization system based on artificial intelligence according to an embodiment of the present invention;
the achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
FIG. 1 is a flowchart of a cross-platform content operation optimization method based on artificial intelligence according to an embodiment of the present invention;
As shown in fig. 1, the present invention provides a cross-platform content operation optimization method flowchart based on artificial intelligence, which includes:
s102, acquiring initial video information, and performing video semantic analysis on the initial video information to obtain first analysis result information;
acquiring initial video information, and performing noise reduction, filtering and enhancement preprocessing on the initial video information to obtain preprocessed video information;
the preprocessing video information is subjected to video segmentation, the preprocessing video information is segmented into a series of discrete image frames based on a frame extraction algorithm, and each image frame is subjected to time sequence marking to obtain marked image frame information;
performing target detection on each frame image in the marked image frame information based on a target detection algorithm to obtain target objects, scenes and elements of each frame image, and obtaining target detection result information;
extracting features of the target detection result information, and further extracting image features, scene features and texture features to obtain feature extraction information;
constructing a video analysis model, importing the feature extraction information and the marked image frame information into the video analysis model for analysis, and analyzing the scene and object changes to obtain a key frame of a target video to obtain first analysis result information;
The first analysis result information includes: video scene analysis information, video character analysis information, and scene break analysis information.
It should be noted that by dividing the initial video information into a series of discrete image frames and assigning a timing mark to each frame. The timing relationship of the video is facilitated to be established so that subsequent analysis may take into account time factors. Target objects, scenes, and elements in the image frames are identified using a target detection algorithm. This helps identify important elements that appear in the video, such as people, objects, actions, etc. Various features are extracted from the object detection result, including image features (e.g., color, texture), scene features (e.g., indoor or outdoor), and texture features (e.g., horizontal or vertical texture). Facilitating further analysis of the video content. The feature extraction information and the marker image frame information are input into a video analysis model. Changes in scenes, objects, and elements are further analyzed, including information of video scenes, characters, and scene breaks. The conversion of the original video data into structured information through a series of steps provides a basis for subsequent analysis of the video content. For example, it may be used to identify key frames in a video, detect turning points of a scene, analyze character behavior, etc., to enable in-depth understanding and analysis of video content.
S104, constructing a language analysis model, and performing word recognition and semantic analysis on the initial video information to obtain second analysis result information;
constructing a language analysis model, inputting the initial video information into the language analysis model for processing, and extracting the audio information of the initial video information to obtain audio extraction information;
retrieving and acquiring the text and audio track information of each medium language based on the big data to form an audio comparison database;
acquiring text information of various emotion categories based on big data retrieval, forming a semantic analysis training data set, and training the language analysis model through the semantic analysis training data set;
performing similarity calculation on the audio extraction information and the audio comparison database, judging with a preset threshold value, and performing text conversion according to a judgment result to obtain text conversion information;
performing scene matching on the character conversion information and the initial video information, and marking the video scene and the character corresponding to each character to obtain character marking information;
and importing the text marking information and the text conversion information into a language analysis model for semantic analysis, and identifying text emotion and text meaning of the analysis target video to obtain second analysis result information.
It should be noted that, the language analysis model is used to perform text conversion on the audio information in the video, generate text information, perform semantic analysis on the generated text information, further analyze text meaning and emotion in the video, and mark scenes and pictures corresponding to the text, so as to facilitate further analysis of video content, further understand the video more accurately, discover important turning points and important content of the video content, and facilitate optimization of the video content.
S106, acquiring the usage rule information and notice information of each platform, and analyzing the usage rule and notice of each platform to obtain platform rule analysis information;
acquiring usage rule information and notice information of each platform, and performing text extraction, cleaning and text correction pretreatment on the usage rule information and the notice information;
carrying out keyword detection and extraction on the usage rule information and the notice information to obtain keyword extraction information;
constructing a topic identification model based on a natural language processing technology, and carrying out topic identification and keyword detection on the usage rule information and the notice information through the topic identification model to obtain topic identification information and keyword detection information;
Content segmentation is carried out on the usage rule information and the notice information according to the topic identification information, and sentences or paragraphs with related topics are segmented to obtain content segmentation information;
extracting key contents according to the key word detection information and the content segmentation information, and generating a content abstract and a rule abstract according to the extracted key content information to obtain platform rule analysis information;
presetting a regular monitoring interval, and periodically monitoring the usage rules and notes of each platform according to the regular monitoring interval to obtain monitoring rule information;
analyzing the monitoring rule information to obtain each piece of platform rule information at the current moment, and calculating the similarity with the platform rule analysis information to obtain a similarity value;
and updating a judgment threshold value by a preset rule, judging the similarity value and the preset threshold value, and updating the rule according to a judgment result.
S108, acquiring characteristic information of each platform, and carrying out platform characteristic analysis and user preference analysis to obtain platform characteristic analysis information and user preference analysis information;
acquiring characteristic information of each platform, wherein the characteristic information of each platform comprises: platform user information, platform main stream content information and user use information;
Constructing a data analysis model, inputting the platform characteristic information into the data analysis model, and carrying out platform characteristic analysis and user preference analysis;
determining user use groups of each platform by analyzing the age, sex and geographic position of the users of each platform to obtain user use group information;
presetting a plurality of type judgment thresholds, judging the user group information and the type judgment thresholds, and classifying each platform according to the age tendency and the geographic position of the user to obtain platform class classification information;
carrying out platform hot spot analysis through the platform main stream content information and the user use information, extracting the browsing amount of each main stream content and the use frequency of the interaction mode, and carrying out sequential sorting to obtain a main stream content sorting diagram;
carrying out platform hot spot analysis through the main stream content ranking chart, and analyzing hot spot content and interaction modes of each platform in unit time to obtain hot spot analysis information;
fusing the platform category division information and the hot spot analysis information to form platform characteristic analysis information;
acquiring characteristic information of each platform, carrying out characteristic extraction on the characteristic information of each platform, acquiring the activity of each platform user in each time period, and sorting according to the activity to obtain an activity sorting table;
Presetting a selection threshold, and carrying out user peak use time period analysis according to the selection threshold and an active amount ranking table to obtain peak use time period analysis information;
carrying out hot spot statistics by combining platform characteristic analysis information and peak use time period analysis information to acquire user preference browsing information;
presetting a plurality of browsing categories, carrying out correlation analysis on user preference browsing information and browsing categories based on a mahalanobis distance algorithm, and analyzing the user preference browsing categories to obtain user preference browsing category information;
the user preference analysis information is formed by combining the user browsing category information and peak use time period analysis information.
It should be noted that, by analyzing the characteristics of the platforms, audience users of the respective platforms are further known, and the mainstream trend of the platform content can be further judged by the ages of the audience users, so that the dominant content of each platform is analyzed, and the audience users are better close to the users; through analyzing the preference of the user, the user preference content of the frequency-finding platform, such as user preference browsing content, user preference theme content and user preference entry content, can further reflect the content information of the audience, so that the operation can be selectively performed, the exposure of the video is improved to obtain more benefits, the video release time is changed by analyzing the peak use time of the user, the exposure of the video can be improved by releasing in the peak use time period, more users can watch in the first time, and the timeliness of the video operation is improved.
Further, obtaining user behavior information of each platform, extracting features of the user behavior information of each platform, and obtaining explicit semantics, implicit semantics, context features and aggregation features of the user behavior of each platform to obtain user behavior feature information; building a long-short-term preference analysis model, and importing the user behavior characteristic information into the long-short-term preference analysis model for analysis to obtain long-short-term preference analysis information; acquiring user behavior information of the existing platform, and acquiring long-short-period preference similar users of the existing platform by combining the long-short-period preference information to acquire similar user information; acquiring long-term preference, preference attribute and category of the existing platform according to the similar user information, and performing multi-mode integration to obtain preference integration information; constructing a user portrait according to the preference integration information and the similar user information to obtain user portrait information; user behavior information of the target platform is obtained, user characteristic extraction and long-short-term preference analysis are carried out, and target platform user characteristic information and target platform long-short-term preference analysis information are obtained; performing recommendation scene simulation according to the target platform user characteristic information and the target platform long-short-term preference analysis information, wherein the recommendation scene simulation comprises behavior simulation, attribute simulation, preference browsing type simulation and browsing factor simulation of a user, and recommendation scene simulation information is obtained; performing similarity calculation on the recommended scene simulation information and the user image information, sorting according to the similarity value, and screening similar image attributes to obtain similar image attribute information; and performing migration learning on the target platform according to the similar portrait attribute information to acquire a content operation strategy of a recommended scene, and performing content operation recommendation on the target platform according to the content operation strategy, so that the user fit degree of content operation is improved, and the exposure and browsing amount of the released content are improved.
S110, performing platform adaptation and delivery recommendation, optimizing video content according to delivery recommendation information, and automatically delivering the optimized video to a corresponding platform;
acquiring release demand information and platform characteristic analysis information, performing adaptation platform analysis, and calculating a similarity value of the release demand information and the platform characteristic information;
judging the calculated similarity value and a preset threshold value, selecting an adaptive platform according to a judging result, and carrying out release recommendation according to the selected adaptive platform to obtain release recommendation information;
platform rule analysis information is obtained, rule extraction is carried out on the platform rule analysis information according to the release recommendation information, and release platform rule information is obtained;
acquiring first analysis result information and second analysis result information;
constructing a content optimization model, inputting the first analysis result information, the second analysis result information and the delivery platform rule information into the content optimization model for video optimization, and enabling the video to be delivered to conform to the delivery rule of the delivery platform to obtain optimized video information;
acquiring user preference analysis information, and carrying out release strategy formulation by combining the release recommendation information, the first analysis result information and the second analysis result information, wherein the release strategy formulation comprises video theme generation, distribution diagram generation, text adjustment and release time selection, so as to acquire release strategy information;
And delivering the optimized video information to a corresponding adaptation platform according to the delivery strategy information.
It should be noted that, by analyzing the initial video information, the first analysis result information and the second analysis result information are obtained, including the analysis result of the video picture content and the analysis result of the video audio, so as to be helpful for summarizing and editing the video; according to the release rule of the release platform, summarizing and refining video content is automatically carried out according to the analysis result, and unimportant scenes, pictures and characters are further removed, so that video information conforming to the release rule is obtained; meanwhile, according to the user preference analysis information and the platform characteristic information, topical subject matching is carried out by combining the first analysis result information and the second analysis result information, important scene fragments and corresponding characters are extracted, a distribution diagram and a document are generated, videos which better accord with platform rules and user preferences are optimized, the user preferences are further attached to the video covers and the video documents, and users can be attracted to watch and browse in the first time; further, by making video delivery time, the video can be accurately delivered in the time period with the maximum user activity, so that the exposure of the video is improved, and the timeliness of the video can be improved.
Further, topic category information, duration information and user watching amount information of various videos of each platform are obtained; presetting a time length distinguishing interval, and classifying time length information according to the time length distinguishing interval by a clustering algorithm to obtain time length classification information; performing data matching on the time length classification information according to the topic category information and the user time length information, and matching the video topic category and the user watching amount under the corresponding video time length to the corresponding time length category to obtain data matching information; analyzing the optimal video time length according to the data matching information, sorting the data matching information according to the watching amount of the user, and selecting the optimal video time length according to the sorting result to obtain the optimal video time length information; acquiring optimized video information, performing feature extraction on the optimized video information, and extracting video duration and video topics to obtain optimized video feature information; performing topic similarity calculation on the optimized video characteristic information and the data matching information to obtain a topic similarity value; judging the topic similarity value and a preset threshold value to obtain topic judgment result information; constructing a video duration recommendation model, constructing a training data set based on the optimal video duration information and the data matching information, and performing deep learning and training on the video duration recommendation model; inputting the topic judgment result information and the optimized video feature information into the video duration recommendation model to recommend video duration, so as to obtain video duration recommendation information; pushing the most popular video time of the target video theme category according to the video time recommendation information, and generating a time optimization prompt; the video is optimized by selecting the most popular video time length of the user, so that the video is further close to the use habit of the user, and the operation effect of the video is improved.
FIG. 2 is a data processing flow chart of a cross-platform content operation method based on artificial intelligence according to an embodiment of the present invention;
as shown in fig. 2, the present invention provides a data processing flow chart of a cross-platform content operation method based on artificial intelligence, which comprises the following steps:
s202, acquiring initial video information, and performing video semantic analysis and video text semantic analysis to obtain first analysis result information and second analysis result information;
s204, acquiring release requirement information, and performing release platform adaptation and recommendation to obtain release recommendation information;
s206, recommending the rule analysis of the delivery platform to obtain the rule information of the delivery platform;
s208, video optimization is carried out according to the first analysis result information, the second analysis result information and the delivery platform rule information, and optimized video information is obtained;
s210, acquiring user preference analysis information, and making a delivery strategy to acquire delivery strategy information;
s212, the optimized video information is launched to the corresponding adaptation platform according to the launching strategy information.
Further, first analysis result information and second analysis result information are obtained; acquiring image information and text information which do not accord with network security rules based on big data retrieval to form a risk detection data set; extracting features of the risk detection data set, segmenting a risk image, and extracting risk characters to obtain risk feature information; constructing a risk assessment model, constructing a training data set according to the risk characteristic information, and performing deep learning and training on the risk assessment model; acquiring optimized video information, importing the optimized video information into a risk assessment model for risk assessment, analyzing the optimized video information from vision, keywords and emotion, and calculating the similarity between the optimized video information and a risk detection data set as a risk score to obtain risk score information; presetting a risk judgment threshold value, and judging the risk score information and the risk judgment threshold value to obtain risk assessment result information; performing problem marking and re-optimization on the optimized video information according to risk assessment result information; performing problem detection on the optimized video information through risk assessment result information, and extracting pictures and characters with risk scores larger than a risk judgment threshold value to obtain problem detection information; re-optimizing the optimized video information according to the problem detection information, and removing problem pictures and characters to obtain re-optimized video information; re-evaluating the re-optimized video information through a risk evaluation model, and judging whether the re-optimized video information accords with the release standard according to an evaluation result; and acquiring optimized video information meeting the release standard and problem detection information in the optimization process, generating a risk optimization report, and carrying out risk prompt and reporting, thereby ensuring the effectiveness of video operation.
Fig. 3 is a block diagram 3 of a cross-platform content operation system based on artificial intelligence according to an embodiment of the present invention, where the system includes: the system comprises a memory 31 and a processor 32, wherein the memory 31 contains an artificial intelligence-based cross-platform content operation method program, and the artificial intelligence-based cross-platform content operation method program realizes the following steps when being executed by the processor 32:
acquiring initial video information, and performing video semantic analysis on the initial video information to obtain first analysis result information;
constructing a language analysis model, and performing word recognition and semantic analysis on the initial video information to obtain second analysis result information;
acquiring the usage rule information and notice information of each platform, and analyzing the usage rule and notice of each platform to obtain platform rule analysis information;
acquiring characteristic information of each platform, and carrying out platform characteristic analysis and user preference analysis to obtain platform characteristic analysis information and user preference analysis information;
performing platform adaptation and delivery recommendation, optimizing video content according to delivery recommendation information, and automatically delivering the optimized video to a corresponding platform.
It is to be noted that the invention provides a cross-platform content operation method and system based on artificial intelligence, which can understand the content of the initial video information deeply by carrying out video semantic analysis and video text analysis on the initial video; analyzing and understanding notes and usage rules of each platform, setting regular monitoring rules, and updating rule information of the platforms by monitoring rule change of each platform in real time so as to ensure effectiveness of video operation; then, analyzing the characteristics of the platform and the user preference, analyzing audience users and main stream hot content information of each platform, reflecting the content trend, such as entertainment trend or administrative trend, of the platform, and providing a video delivery strategy by analyzing the user preference content and peak use time of each platform, so as to optimize the topic content and text more in line with the user and improve the fitting degree with the user; and finally, carrying out platform adaptation and delivery recommendation, providing a recommended delivery platform which is more suitable for initial video information, attaching an audience user of the platform, maximizing the video content value, providing recommended delivery time, and delivering in the time period when the user is most active, so that the probability of browsing and watching of the user can be increased, and the video exposure is improved. The invention provides a more comprehensive content operation optimization method, which can improve the efficiency of content operation and the exposure of video, and further fit the preference of users, thereby improving the fit of the video and the users.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to 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 each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention 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 invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. The cross-platform content operation optimization method based on artificial intelligence is characterized by comprising the following steps of:
acquiring initial video information, and performing video semantic analysis on the initial video information to obtain first analysis result information;
constructing a language analysis model, and performing word recognition and semantic analysis on the initial video information to obtain second analysis result information;
acquiring the usage rule information and notice information of each platform, and analyzing the usage rule and notice of each platform to obtain platform rule analysis information;
acquiring characteristic information of each platform, and carrying out platform characteristic analysis and user preference analysis to obtain platform characteristic analysis information and user preference analysis information;
performing platform adaptation and delivery recommendation, optimizing video content according to delivery recommendation information, and automatically delivering the optimized video to a corresponding platform;
The platform adaptation and delivery recommendation are carried out, video content optimization is carried out according to delivery recommendation information, and optimized video is automatically delivered to a corresponding platform, and the method specifically comprises the following steps:
acquiring release demand information and platform characteristic analysis information, performing adaptation platform analysis, and calculating a similarity value of the release demand information and the platform characteristic information;
judging the calculated similarity value and a preset threshold value, selecting an adaptive platform according to a judging result, and carrying out release recommendation according to the selected adaptive platform to obtain release recommendation information;
platform rule analysis information is obtained, rule extraction is carried out on the platform rule analysis information according to the release recommendation information, and release platform rule information is obtained;
acquiring first analysis result information and second analysis result information;
constructing a content optimization model, inputting the first analysis result information, the second analysis result information and the delivery platform rule information into the content optimization model for video optimization, and enabling the video to be delivered to conform to the delivery rule of the delivery platform to obtain optimized video information;
acquiring user preference analysis information, and carrying out release strategy formulation by combining the release recommendation information, the first analysis result information and the second analysis result information, wherein the release strategy formulation comprises video theme generation, distribution diagram generation, text adjustment and release time selection, so as to acquire release strategy information;
And delivering the optimized video information to a corresponding adaptation platform according to the delivery strategy information.
2. The method for optimizing cross-platform content operation based on artificial intelligence according to claim 1, wherein the performing video semantic analysis on the initial video information specifically comprises:
acquiring initial video information, and performing noise reduction, filtering and enhancement preprocessing on the initial video information to obtain preprocessed video information;
the preprocessing video information is subjected to video segmentation, the preprocessing video information is segmented into a series of discrete image frames based on a frame extraction algorithm, and each image frame is subjected to time sequence marking to obtain marked image frame information;
performing target detection on each frame image in the marked image frame information based on a target detection algorithm to obtain target objects, scenes and elements of each frame image, and obtaining target detection result information;
extracting features of the target detection result information, and further extracting image features, scene features and texture features to obtain feature extraction information;
constructing a video analysis model, importing the feature extraction information and the marked image frame information into the video analysis model for analysis, and analyzing the scene and object changes to obtain a key frame of a target video to obtain first analysis result information;
The first analysis result information includes: video scene analysis information, video character analysis information, and scene break analysis information.
3. The method for optimizing cross-platform content operation based on artificial intelligence according to claim 1, wherein the performing text recognition and semantic analysis on the initial video information to obtain second analysis result information specifically comprises:
constructing a language analysis model, inputting the initial video information into the language analysis model for processing, and extracting the audio information of the initial video information to obtain audio extraction information;
retrieving and acquiring the text and audio track information of each medium language based on the big data to form an audio comparison database;
acquiring text information of various emotion categories based on big data retrieval, forming a semantic analysis training data set, and training the language analysis model through the semantic analysis training data set;
performing similarity calculation on the audio extraction information and the audio comparison database, judging with a preset threshold value, and performing text conversion according to a judgment result to obtain text conversion information;
performing scene matching on the character conversion information and the initial video information, and marking the video scene and the character corresponding to each character to obtain character marking information;
And importing the text marking information and the text conversion information into a language analysis model for semantic analysis, and identifying text emotion and text meaning of the analysis target video to obtain second analysis result information.
4. The method for optimizing cross-platform content operation based on artificial intelligence according to claim 1, wherein the steps of obtaining usage rule information and notice information of each platform and analyzing the usage rule and notice of each platform specifically comprise:
acquiring usage rule information and notice information of each platform, and performing text extraction, cleaning and text correction pretreatment on the usage rule information and the notice information;
carrying out keyword detection and extraction on the usage rule information and the notice information to obtain keyword extraction information;
constructing a topic identification model based on a natural language processing technology, and carrying out topic identification and keyword detection on the usage rule information and the notice information through the topic identification model to obtain topic identification information and keyword detection information;
content segmentation is carried out on the usage rule information and the notice information according to the topic identification information, and sentences or paragraphs with related topics are segmented to obtain content segmentation information;
Extracting key contents according to the key word detection information and the content segmentation information, and generating a content abstract and a rule abstract according to the extracted key content information to obtain platform rule analysis information;
presetting a regular monitoring interval, and periodically monitoring the usage rules and notes of each platform according to the regular monitoring interval to obtain monitoring rule information;
analyzing the monitoring rule information to obtain each piece of platform rule information at the current moment, and calculating the similarity with the platform rule analysis information to obtain a similarity value;
and updating a judgment threshold value by a preset rule, judging the similarity value and the preset threshold value, and updating the rule according to a judgment result.
5. The method for optimizing cross-platform content operation based on artificial intelligence according to claim 1, wherein the performing of platform feature analysis and user preference analysis specifically comprises:
acquiring characteristic information of each platform, wherein the characteristic information of each platform comprises: platform user information, platform main stream content information and user use information;
constructing a data analysis model, inputting the platform characteristic information into the data analysis model, and carrying out platform characteristic analysis and user preference analysis;
Determining user use groups of each platform by analyzing the age, sex and geographic position of the users of each platform to obtain user use group information;
presetting a plurality of type judgment thresholds, judging the user group information and the type judgment thresholds, and classifying each platform according to the age tendency and the geographic position of the user to obtain platform class classification information;
carrying out platform hot spot analysis through the platform main stream content information and the user use information, extracting the browsing amount of each main stream content and the use frequency of the interaction mode, and carrying out sequential sorting to obtain a main stream content sorting diagram;
carrying out platform hot spot analysis through the main stream content ranking chart, and analyzing hot spot content and interaction modes of each platform in unit time to obtain hot spot analysis information;
and fusing the platform category division information and the hot spot analysis information to form platform characteristic analysis information.
6. The method for optimizing cross-platform content operation based on artificial intelligence according to claim 1, wherein the performing platform feature analysis and user preference analysis further comprises:
acquiring characteristic information of each platform, carrying out characteristic extraction on the characteristic information of each platform, acquiring the activity of each platform user in each time period, and sorting according to the activity to obtain an activity sorting table;
Presetting a selection threshold, and carrying out user peak use time period analysis according to the selection threshold and an active amount ranking table to obtain peak use time period analysis information;
carrying out hot spot statistics by combining platform characteristic analysis information and peak use time period analysis information to acquire user preference browsing information;
presetting a plurality of browsing categories, carrying out correlation analysis on user preference browsing information and browsing categories based on a mahalanobis distance algorithm, and analyzing the user preference browsing categories to obtain user preference browsing category information;
the user preference analysis information is formed by combining the user browsing category information and peak use time period analysis information.
7. An artificial intelligence-based cross-platform content operation optimization system, comprising: the system comprises a memory and a processor, wherein the memory contains an artificial intelligence-based cross-platform content operation optimization method program, and the artificial intelligence-based cross-platform content operation optimization method program realizes the following steps when being executed by the processor:
acquiring initial video information, and performing video semantic analysis on the initial video information to obtain first analysis result information;
constructing a language analysis model, and performing word recognition and semantic analysis on the initial video information to obtain second analysis result information;
Acquiring the usage rule information and notice information of each platform, and analyzing the usage rule and notice of each platform to obtain platform rule analysis information;
acquiring characteristic information of each platform, and carrying out platform characteristic analysis and user preference analysis to obtain platform characteristic analysis information and user preference analysis information;
performing platform adaptation and delivery recommendation, optimizing video content according to delivery recommendation information, and automatically delivering the optimized video to a corresponding platform;
the platform adaptation and delivery recommendation are carried out, video content optimization is carried out according to delivery recommendation information, and optimized video is automatically delivered to a corresponding platform, and the method specifically comprises the following steps:
acquiring release demand information and platform characteristic analysis information, performing adaptation platform analysis, and calculating a similarity value of the release demand information and the platform characteristic information;
judging the calculated similarity value and a preset threshold value, selecting an adaptive platform according to a judging result, and carrying out release recommendation according to the selected adaptive platform to obtain release recommendation information;
platform rule analysis information is obtained, rule extraction is carried out on the platform rule analysis information according to the release recommendation information, and release platform rule information is obtained;
Acquiring first analysis result information and second analysis result information;
constructing a content optimization model, inputting the first analysis result information, the second analysis result information and the delivery platform rule information into the content optimization model for video optimization, and enabling the video to be delivered to conform to the delivery rule of the delivery platform to obtain optimized video information;
acquiring user preference analysis information, and carrying out release strategy formulation by combining the release recommendation information, the first analysis result information and the second analysis result information, wherein the release strategy formulation comprises video theme generation, distribution diagram generation, text adjustment and release time selection, so as to acquire release strategy information;
and delivering the optimized video information to a corresponding adaptation platform according to the delivery strategy information.
8. The artificial intelligence based cross-platform content operation optimization system according to claim 7, wherein the video semantic analysis of the initial video information specifically comprises:
acquiring initial video information, and performing noise reduction, filtering and enhancement preprocessing on the initial video information to obtain preprocessed video information;
the preprocessing video information is subjected to video segmentation, the preprocessing video information is segmented into a series of discrete image frames based on a frame extraction algorithm, and each image frame is subjected to time sequence marking to obtain marked image frame information;
Performing target detection on each frame image in the marked image frame information based on a target detection algorithm to obtain target objects, scenes and elements of each frame image, and obtaining target detection result information;
extracting features of the target detection result information, and further extracting image features, scene features and texture features to obtain feature extraction information;
constructing a video analysis model, importing the feature extraction information and the marked image frame information into the video analysis model for analysis, and analyzing the scene and object changes to obtain a key frame of a target video to obtain first analysis result information;
the first analysis result information includes: video scene analysis information, video character analysis information, and scene break analysis information.
9. The cross-platform content operation optimization system based on artificial intelligence according to claim 7, wherein the performing text recognition and semantic analysis on the initial video information to obtain second analysis result information specifically comprises:
constructing a language analysis model, inputting the initial video information into the language analysis model for processing, and extracting the audio information of the initial video information to obtain audio extraction information;
Retrieving and acquiring the text and audio track information of each medium language based on the big data to form an audio comparison database;
acquiring text information of various emotion categories based on big data retrieval, forming a semantic analysis training data set, and training the language analysis model through the semantic analysis training data set;
performing similarity calculation on the audio extraction information and the audio comparison database, judging with a preset threshold value, and performing text conversion according to a judgment result to obtain text conversion information;
performing scene matching on the character conversion information and the initial video information, and marking the video scene and the character corresponding to each character to obtain character marking information;
and importing the text marking information and the text conversion information into a language analysis model for semantic analysis, and identifying text emotion and text meaning of the analysis target video to obtain second analysis result information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311320007.7A CN117333800B (en) | 2023-10-12 | 2023-10-12 | Cross-platform content operation optimization method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311320007.7A CN117333800B (en) | 2023-10-12 | 2023-10-12 | Cross-platform content operation optimization method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117333800A CN117333800A (en) | 2024-01-02 |
| CN117333800B true CN117333800B (en) | 2024-04-05 |
Family
ID=89294942
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311320007.7A Active CN117333800B (en) | 2023-10-12 | 2023-10-12 | Cross-platform content operation optimization method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117333800B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107357889A (en) * | 2017-07-11 | 2017-11-17 | 北京工业大学 | A kind of across social platform picture proposed algorithm based on interior perhaps emotion similitude |
| CN111882361A (en) * | 2020-07-31 | 2020-11-03 | 苏州云开网络科技有限公司 | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium |
| CN111949869A (en) * | 2020-08-11 | 2020-11-17 | 杭州鑫通信息技术有限公司 | Content information recommendation method and system based on artificial intelligence |
| CN115292528A (en) * | 2022-08-26 | 2022-11-04 | 青岛心法传媒科技有限公司 | Intelligent operation method, equipment and storage medium for new media video |
| CN116261009A (en) * | 2022-12-26 | 2023-06-13 | 北京奇树有鱼文化传媒有限公司 | Video detection method, device, equipment and medium for intelligently converting video audience |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020206066A1 (en) * | 2019-04-03 | 2020-10-08 | ICX Media, Inc. | Method for optimizing media and marketing content using cross-platform video intelligence |
-
2023
- 2023-10-12 CN CN202311320007.7A patent/CN117333800B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107357889A (en) * | 2017-07-11 | 2017-11-17 | 北京工业大学 | A kind of across social platform picture proposed algorithm based on interior perhaps emotion similitude |
| CN111882361A (en) * | 2020-07-31 | 2020-11-03 | 苏州云开网络科技有限公司 | Audience accurate advertisement pushing method and system based on artificial intelligence and readable storage medium |
| CN111949869A (en) * | 2020-08-11 | 2020-11-17 | 杭州鑫通信息技术有限公司 | Content information recommendation method and system based on artificial intelligence |
| CN115292528A (en) * | 2022-08-26 | 2022-11-04 | 青岛心法传媒科技有限公司 | Intelligent operation method, equipment and storage medium for new media video |
| CN116261009A (en) * | 2022-12-26 | 2023-06-13 | 北京奇树有鱼文化传媒有限公司 | Video detection method, device, equipment and medium for intelligently converting video audience |
Non-Patent Citations (2)
| Title |
|---|
| 基于关联规则挖掘的跨网络知识关联及协同应用;黄晓雯;严明;桑基韬;徐常胜;;计算机科学;20160715(第07期);全文 * |
| 媒体融合发展下关于短视频平台运营现状与对策探析;陈俏;;中国传媒科技;20191115(第11期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117333800A (en) | 2024-01-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110020437B (en) | Emotion analysis and visualization method combining video and barrage | |
| CN112749608B (en) | Video auditing method, device, computer equipment and storage medium | |
| CN106547908B (en) | Information pushing method and system | |
| CN112533051B (en) | Barrage information display method, barrage information display device, computer equipment and storage medium | |
| CN107291780B (en) | User comment information display method and device | |
| CN110888990B (en) | Text recommendation method, device, equipment and medium | |
| CN110557659B (en) | Video recommendation method and device, server and storage medium | |
| CN112231484B (en) | News comment auditing method, system, device and storage medium | |
| EP2568429A1 (en) | Method and system for pushing individual advertisement based on user interest learning | |
| CN110287314B (en) | Long text reliability assessment method and system based on unsupervised clustering | |
| CN110956037B (en) | Multimedia content repeated judgment method and device | |
| US10922492B2 (en) | Content optimization for audiences | |
| CN112883734B (en) | Block chain security event public opinion monitoring method and system | |
| US11361759B2 (en) | Methods and systems for automatic generation and convergence of keywords and/or keyphrases from a media | |
| CN110958472A (en) | Video click rate rating prediction method and device, electronic equipment and storage medium | |
| KR102093790B1 (en) | Evnet information extraciton method for extracing the event information for text relay data, and user apparatus for perfromign the method | |
| CN112995690B (en) | Live content category identification method, device, electronic equipment and readable storage medium | |
| CN117333800B (en) | Cross-platform content operation optimization method and system based on artificial intelligence | |
| CN111986259A (en) | Training method of character and face detection model, auditing method of video data and related device | |
| CN116071134A (en) | Intelligent user experience display method, system and storage medium | |
| CN111198957A (en) | Push method and device, electronic equipment and storage medium | |
| CN105868271B (en) | Surname statistical method and device | |
| CN115130453A (en) | Interactive information generation method and device | |
| CN113935307A (en) | Method and device for extracting features of advertisement case | |
| CN114547435A (en) | Content quality identification method, device, equipment and readable storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |