CN114387041A - Multimedia data acquisition method and system - Google Patents
Multimedia data acquisition method and system Download PDFInfo
- Publication number
- CN114387041A CN114387041A CN202210279976.1A CN202210279976A CN114387041A CN 114387041 A CN114387041 A CN 114387041A CN 202210279976 A CN202210279976 A CN 202210279976A CN 114387041 A CN114387041 A CN 114387041A
- Authority
- CN
- China
- Prior art keywords
- multimedia
- user
- information
- platform
- matching
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0269—Targeted advertisements based on user profile or attribute
- G06Q30/0271—Personalized advertisement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a multimedia data acquisition method and a multimedia data acquisition system, wherein a correction model is established based on a historical multimedia data set and multimedia characteristics, and the multimedia characteristics are corrected through the correction model to determine the multimedia data characteristics; processing and correcting the current multimedia information by using the correction model to obtain the data characteristics of the current multimedia, and determining the characteristics of the releasing user; performing platform user set feature matching on a release platform based on release user features to obtain a user information set; and performing multi-platform user characteristic acquisition according to the user information set, performing characteristic analysis on the multi-platform information of each user to obtain a user analysis result, and judging whether the user analysis result conforms to the characteristics of the releasing user to perform releasing adjustment. The technical problems that the accuracy of multimedia data acquisition is not high, the portrait of a user is not reliable, and the advertising promotion effect is not good are solved. The effects of delivering multimedia promotion content according to user characteristics and improving delivery efficiency are achieved.
Description
Technical Field
The present application relates to the field of multimedia data analysis technologies, and in particular, to a multimedia data acquisition method and system.
Background
With the development of multimedia platforms such as internet video social contact and the like, more and more users use the platforms to perform operations such as short video production, movie and television viewing, electronic reading and the like, advertising is carried out in the multimedia platforms along with the development, how to collect customer information to determine the delivery population of multimedia advertisements is important for the advertising effect, and the effect of advertising is influenced. Generally, the advertisement delivery can utilize big data to perform characteristic analysis on a client, and the client data acquired by the big data lacks pertinence from the age, the hobbies and interests and the watching records, so that the problem of poor delivery effect is caused due to inaccurate characteristic pictures of the client.
The above-mentioned techniques have been found to have at least the following technical problems:
the technical problems that in the prior art, the accuracy of multimedia data acquisition is low, the portrait of a user is unreliable, and the advertising promotion effect is poor are caused.
Disclosure of Invention
The application aims to provide a multimedia data acquisition method and a multimedia data acquisition system, which are used for solving the technical problems that in the prior art, the accuracy of multimedia data acquisition is not high, the portrait of a user is not reliable, and the advertising promotion and delivery effect is not good. The comprehensive analysis of multi-platform users is achieved, accurate portrait of the users is achieved, multimedia promotion content is put in according to user characteristics, accuracy of information collection of the put-in users is improved, and therefore the technical effect of multimedia advertisement putting efficiency is improved.
In view of the foregoing, the present application provides a multimedia data collection method and system.
In a first aspect, the present application provides a multimedia data acquisition method, including: acquiring a historical multimedia data set of a plurality of platforms; performing feature algorithm matching according to the historical multimedia data set, and performing feature extraction by using a feature algorithm determined by matching to obtain multimedia features; constructing a correction model based on the historical multimedia data set and the multimedia characteristics, correcting the multimedia characteristics through the correction model, and determining the multimedia data characteristics; acquiring current multimedia information, processing and correcting the current multimedia information by using the correction model to obtain the data characteristics of the current multimedia, matching the characteristics of a release user by using the data characteristics of the current multimedia, and determining the characteristics of the release user; carrying out platform user set feature matching on a release platform based on the release user features to obtain a user information set; acquiring multi-platform user characteristics according to the user information set to obtain multi-platform information of the user; and respectively carrying out characteristic analysis on the multi-platform user information of each user to obtain a user analysis result, judging whether the user analysis result is consistent with the characteristics of the releasing user, and carrying out releasing adjustment on users which are not consistent.
In another aspect, the present application further provides a multimedia data acquisition system for performing the multimedia data acquisition method according to the first aspect, the system including:
the system comprises a first obtaining unit, a second obtaining unit and a third obtaining unit, wherein the first obtaining unit is used for collecting historical multimedia data sets of a plurality of obtained platforms;
the second obtaining unit is used for matching a feature algorithm according to the historical multimedia data set and extracting features by using the feature algorithm determined by matching to obtain multimedia features;
the first execution unit is used for constructing a correction model based on the historical multimedia data set and the multimedia characteristics, correcting the multimedia characteristics through the correction model and determining the multimedia data characteristics;
the second execution unit is used for acquiring current multimedia information, processing and correcting the current multimedia information by using the correction model to obtain the data characteristics of the current multimedia, matching the features of the releasing users by using the data characteristics of the current multimedia and determining the features of the releasing users;
a third obtaining unit, configured to perform platform user set feature matching on a delivery platform based on the delivery user features to obtain a user information set;
a fourth obtaining unit, configured to perform multi-platform user feature acquisition according to the user information set, so as to obtain multi-platform information of a user;
the first releasing unit is used for respectively carrying out characteristic analysis on the user multi-platform information of each user to obtain a user analysis result, judging whether the user analysis result is consistent with the releasing user characteristic, and carrying out releasing adjustment on users which are not consistent.
In a third aspect, the present application further provides a multimedia data acquisition system, including a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect when executing the program.
In a fourth aspect, the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method of any of the first aspects.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
1. acquiring current multimedia information, processing and correcting the current multimedia information by using the correction model to obtain the data characteristics of the current multimedia, and performing feature matching on a release user by using the data characteristics of the current multimedia to determine the release user characteristics; carrying out platform user set feature matching on a release platform based on the release user features to obtain a user information set; acquiring multi-platform user characteristics according to the user information set to obtain multi-platform information of the user; and respectively carrying out characteristic analysis on the multi-platform user information of each user to obtain a user analysis result, judging whether the user analysis result is consistent with the characteristics of the releasing user, and carrying out releasing adjustment on users which are not consistent. The comprehensive analysis of multi-platform users is achieved, accurate portrait of the users is achieved, multimedia promotion content is put in according to user characteristics, accuracy of information collection of the put-in users is improved, and therefore the technical effect of multimedia advertisement putting efficiency is improved.
2. Determining training data based on the historical multimedia data set and the multimedia characteristics, and training and learning the neural network model by using the training data to obtain a characteristic extraction model; and obtaining an output result of the feature extraction model, using the output result as an input model of a data conversion model, and associating the feature extraction model and the data conversion model to obtain the correction model. The data processing efficiency is improved by nesting the two models, the reliability of data processing is effectively improved by adding the neural network model, and a guaranteed technical effect is provided for subsequent data processing.
3. Obtaining insertion playing content according to the insertion time point; according to the inserted playing content, obtaining insertion characteristic information; matching the insertion characteristic information with the pushed multimedia characteristics to obtain matched multimedia characteristics; and determining the pushed multimedia according to the matched multimedia characteristics. The method and the device achieve the purposes that the matched insertion time point is selected to be delivered according to the characteristics of the pushed multimedia, the characteristics of the pushed multimedia are fused with the insertion playing content, and the advertisement delivery effect can be improved.
4. And determining the multimedia category of the pushed multimedia information according to the characteristic distance set by adding a KNN classification algorithm. The intelligent classification of the pushed multimedia is achieved, and the technical effect of reliable guarantee is provided for targeted analysis and processing according to different types of multimedia.
The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only exemplary, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a schematic flowchart of a multimedia data acquisition method according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a multimedia data acquisition system according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an exemplary electronic device according to an embodiment of the present application.
Description of reference numerals: a first obtaining unit 11, a second obtaining unit 12, a first executing unit 13, a second executing unit 14, a third obtaining unit 15, a fourth obtaining unit 16, a first launching unit 17, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 305.
Detailed Description
The embodiment of the application provides a multimedia data acquisition method and system, and solves the technical problems that in the prior art, the accuracy of multimedia data acquisition is not high, the portrait of a user is unreliable, and the advertising promotion effect is not good.
In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings, and it is to be understood that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present application without making any creative effort, shall fall within the protection scope of the present application. It should be further noted that, for the convenience of description, only some but not all of the elements relevant to the present application are shown in the drawings.
The technical scheme provided by the application has the following general idea:
acquiring a historical multimedia data set of a plurality of platforms, matching a feature algorithm, and extracting features by using the feature algorithm determined by matching to obtain multimedia features; constructing a correction model based on the historical multimedia data set and the multimedia characteristics, correcting the multimedia characteristics through the correction model, and determining the multimedia data characteristics; acquiring current multimedia information, processing and correcting the current multimedia information by using the correction model to obtain the data characteristics of the current multimedia, matching the characteristics of a release user by using the data characteristics of the current multimedia, and determining the characteristics of the release user; carrying out platform user set feature matching on a release platform based on the release user features to obtain a user information set; acquiring multi-platform user characteristics according to the user information set to obtain multi-platform information of the user; and respectively carrying out characteristic analysis on the multi-platform user information of each user to obtain a user analysis result, judging whether the user analysis result is consistent with the characteristics of the releasing user, and carrying out releasing adjustment on users which are not consistent. The comprehensive analysis of multi-platform users is achieved, accurate portrait of the users is achieved, multimedia promotion content is put in according to user characteristics, accuracy of information collection of the put-in users is improved, and therefore the technical effect of multimedia advertisement putting efficiency is improved.
Having thus described the general principles of the present application, various non-limiting embodiments thereof will now be described in detail with reference to the accompanying drawings.
Example one
Referring to fig. 1, an embodiment of the present application provides a multimedia data acquisition method, where the method includes:
step S100: historical multimedia data sets obtained for multiple platforms are collected.
Specifically, the multiple platforms are video multimedia platforms, such as judder, fast-hand, Tencent, love and fancy art, the multimedia data sets mainly comprise information of advertisement putting, recommended content and the like, and in the process of collecting historical data of the multiple platforms, the multiple platforms can be set according to needs, if the multimedia content which is put or popularized at present aims at a short video platform such as judder and fast-hand, the multiple platforms are short video type platforms, and the required multimedia playing data of each platform are collected in all directions, including videos, images, audios, texts, playing time, duration, playing platforms and the like.
Step S200: and performing feature algorithm matching according to the historical multimedia data set, and performing feature extraction by using a feature algorithm determined by matching to obtain multimedia features.
Specifically, corresponding feature extraction is performed on collected data types in a historical multimedia data set, such as natural language processing and image processing, different feature algorithms are performed on multimedia attributes such as videos, images, audios and texts, data feature extraction of multimedia historical files is performed on the historical multimedia data set, and features of multimedia historical data are expressed by characters, codes, characters and the like. The multimedia features include the features of the multimedia data collected in all the historical multimedia data sets. In order to ensure the reliability of the historical multimedia data set acquisition, the historical multimedia data set is preprocessed, and data such as noise, incomplete data expression and the like in the historical multimedia data set are screened out, so that the noise reduction processing of the data is realized.
Step S300: and constructing a correction model based on the historical multimedia data set and the multimedia characteristics, correcting the multimedia characteristics through the correction model, and determining the multimedia data characteristics.
Further, the building a correction model based on the historical multimedia data set and the multimedia features includes: constructing a neural network model; determining training data based on the historical multimedia data set and the multimedia characteristics, and training and learning the neural network model by using the training data to obtain a characteristic extraction model; obtaining an output result of the feature extraction model, wherein the output result comprises a multimedia feature result; obtaining a characteristic data requirement; constructing a data conversion model by using the characteristic data requirement and the output result of the characteristic extraction model; and correlating the feature extraction model and the data conversion model to obtain the correction model.
Specifically, in order to avoid data conversion errors occurring in the process of extracting multimedia features of a historical multimedia data set or different data expression types existing in subsequent processing, the embodiment of the application corrects the expression form of the multimedia features by using the correction model, so as to ensure the recognition effect of the system and the uniformity of subsequent data and ensure the reliability of the operation processing result. By constructing a neural network model, selecting training data matched with the type of the historical multimedia data set based on the historical multimedia data set and the multimedia characteristics, wherein the training data has the historical multimedia data set and the multimedia characteristics, the requirements of inputting the multimedia data and outputting the multimedia characteristics can be realized by learning the relation between the historical multimedia data set and the multimedia characteristics in the training data, the training process is a machine learning process, the output result given by the model is corrected by the multimedia characteristics of the training data, when the output result is consistent with the multimedia characteristics of the given corresponding training data or reaches certain accuracy, the training of the model is finished, the characteristic extraction model is the model obtained by converging a large amount of training data matched with the historical multimedia data set and the multimedia characteristics through training learning, the method comprises the steps of utilizing given multimedia characteristics to continuously correct and convert data types, firstly obtaining the data types of multimedia characteristic results based on output multimedia characteristic results, then determining characteristic data requirements, determining how to correct and convert according to the data relationship between the data types of the multimedia characteristic results and the characteristic data requirements, constructing a data conversion model, taking the output results of a characteristic extraction model as input information of the data conversion model, and performing nested association on the two models to form the correction model, so that the correction model has the functions of characteristic extraction and data conversion.
Step S400: acquiring current multimedia information, processing and correcting the current multimedia information by using the correction model to obtain the data characteristics of the current multimedia, matching the characteristics of the releasing user by using the data characteristics of the current multimedia, and determining the characteristics of the releasing user.
Specifically, the current multimedia information is multimedia content which needs to be promoted, such as advertisements, the current multimedia information is input into a correction model, feature extraction and data type conversion of the current multimedia information are realized, the obtained output result is the data feature of the current multimedia, the determined data type of the multimedia is used for analyzing the putting requirement, so that matching of corresponding clients is carried out according to the putting requirement feature, the putting user feature is the client feature matched with the feature of the current multimedia information, and if the current multimedia information is an early education type, the corresponding putting user feature type is a mom with a proper age.
Step S500: and carrying out platform user set characteristic matching on the launching platform based on the launching user characteristics to obtain a user information set.
Specifically, feature matching is carried out among users in a platform needing to be released currently according to the characteristics of releasing users, if the platform needing to be released is flight communication, the platform user set is all users of the flight communication, the releasing user characteristics are used for matching with the user characteristics in the platform user set, and the users successfully matched are recorded in the user information set, so that the user information set comprises user information matched with all the features in the releasing platform. The platform user set comprises basic information of users and characteristic information of the users, and the user characteristics are determined by analyzing and processing according to basic data provided by the users and user historical data acquired by the platform.
Step S600: and acquiring multi-platform user characteristics according to the user information set to obtain multi-platform information of the user.
Specifically, in order to improve the reliability of the user matching result, the characteristics of users in multiple platforms are utilized to carry out comprehensive analysis, because the expression of a single platform user is single, the data volume is limited, the characteristics of users in different platforms are utilized to carry out comprehensive analysis, so that the reliability and the comprehensiveness of the data image characteristics are improved, and the multimedia delivery deviation existing in the customer image deviation is avoided. When the multi-platform user characteristics are collected, corresponding elements are determined according to the types of the multimedia capable of being put in, relevant platforms are collected according to the determined elements, and platforms in the multi-platform user characteristics collection can be not limited to video platforms, and can also comprise shopping platforms, technical communication platforms, forums and the like to carry out characteristic analysis in pertinence and different fields. If the multimedia to be delivered is a consumable, the browsing record, the storage record or the purchase record of the shopping platform user can be analyzed to determine the characteristics of the user. If the current multimedia information is the popularization of the movie, the multiple platforms are all video platforms, and feature analysis is carried out by using the watching history of the user. According to basic information of a user in user information set, such as a mobile phone number, a certificate number and the like, real-name registration is usually required to be carried out on the setting of a platform account number, so that the information of the user has relevance, other platform data are collected by utilizing personal information in the user information, the type of a collection platform can be selected or the name of the collection platform can be determined in a targeted manner before collection, input setting can be carried out according to requirements, and the name and the requirements of multiple platforms needing to be selected can be determined by carrying out attribute and content analysis according to current multimedia information.
Step S700: and respectively carrying out characteristic analysis on the multi-platform user information of each user to obtain a user analysis result, judging whether the user analysis result is consistent with the characteristics of the releasing user, and carrying out releasing adjustment on users which are not consistent.
Specifically, the currently matched user is verified by using a multi-platform user characteristic analysis result, namely a user analysis result, if the user characteristics do not conform to each other, the user is removed from the user information set, if the characteristics completely conform to each other, the user selection is accurate, the user information set continues to be kept, namely, the user information set serves as a released user list, the current multimedia information to be released and promoted is released according to the determined user information, so that the accurate portrait of the user is realized through comprehensive analysis of the multi-platform user, the multimedia promotion content is released according to the user characteristics, the accuracy of user information collection is improved, and the technical effect of multimedia advertisement releasing efficiency is improved. And then solved among the prior art that the multimedia data acquisition accuracy is not high, cause the unreliable and not good technical problem of advertisement popularization and delivery effect of user portrait.
Further, the method further comprises: obtaining platform identification information; determining user information according to the platform identification information, and acquiring user historical access information based on the user information acquisition, wherein the user historical access information comprises the user multi-platform information; obtaining a local platform access record according to the historical user access information, performing characteristic analysis on the local platform access record, and determining a first platform user characteristic; performing characteristic analysis according to the user multi-platform information to determine the user characteristics of a second platform; performing platform relevance analysis on a local platform and multiple platforms, performing weight calculation based on the platform relevance, and acquiring user push characteristic information according to the first platform user characteristics, the second platform user characteristics and the weight; acquiring pushed multimedia information, and performing feature extraction on the pushed multimedia information to determine pushed multimedia features; and matching the user pushing characteristic information with the pushing multimedia characteristics to obtain user matching information, wherein the user matching information is multimedia pushing content matched with the user pushing characteristic information.
Specifically, after multimedia is released every time, or when user characteristic analysis is performed at an early stage to construct user information, when a user scans codes to pay attention and receives water according to the pushed multimedia, identity information of the user is recognized, historical access information of the user on each platform is collected on the basis of an intelligent cloud, the Internet of things or big data and the like by using the user identity information of the recognition result, and the historical access information of the user comprises the collection result of the user. Respectively carrying out characteristic analysis on the records of the user platform and the records of other platforms, wherein the user characteristic of the first platform is the analysis result of the platform, the user characteristic of the second platform is the characteristic analysis result of the other platforms, the comprehensive characteristic of the user is obtained and stored in the user information, in addition, the weight determination can also be carried out according to the relationship between the collected attributes of the multiple platforms and the platform, if the relevance of the other platforms to the platform is not high, the weight of the platform is large, otherwise, the weight is small, the influence of platform data with small relevance can be eliminated according to the setting of the weight, the user characteristic obtained by the comprehensive calculation is used as the characteristic information pushed by the user, and the characteristic analysis is carried out on the multimedia information which needs to be pushed currently, the pushed multimedia characteristics are obtained, the pushed characteristic information of the user is matched with the multimedia characteristics needing to be pushed locally, and the multimedia information is pushed to the user when the pushed multimedia is matched, so that the effect of accurately putting the multimedia advertisement for thousands of people is achieved. Meanwhile, the characteristics of the user are continuously updated and analyzed in real time, so that the portrait characteristics of the user are perfected, and a foundation is laid for accurate later-stage delivery.
Further, the method further comprises: classifying the pushed multimedia information according to the pushed multimedia characteristics to obtain multimedia categories; determining category characteristics according to the multimedia categories; performing multi-platform class matching by using the class characteristics to obtain matching platform information; acquiring access records from the matching platform information based on the user information to obtain matching platform access information; performing characteristic analysis according to the matching platform access information to obtain the matching platform characteristics of the user; and matching the matching platform characteristics of the user with the pushed multimedia characteristics, and obtaining pushed information when the matching degree meets a preset requirement, wherein the pushed information is used for pushing multimedia information to the user information.
Specifically, how to select and analyze multi-platform features in multimedia pushing can classify the multimedia which needs to be pushed by the current platform, divide the multimedia into different types, select a targeted platform and analyze user features according to the different types, improve the reliability of an analysis result, collect and analyze corresponding data according to main parameters of the type, collect the data with the highest correlation degree with the pushing content, avoid the interference of other irrelevant platform data, and further improve the portrait reliability of the targeted class attributes of users, such as classifying the pushing multimedia features into commodity sales classes, education training, security investment and the like, large commodities, consumables and the like in the commodity sales classes, and classifying the pushing multimedia features according to the attributes of mothers and babies, office supplies, digital products and the like, different analyses have corresponding platforms, for example, the analysis of data such as browsing records of shopping platforms such as Taobao and Jingdong, the analysis of data such as shopping cart loading conditions and the like can be performed on the shopping platforms such as Taobao and Jingdong, the analysis can be performed on the viewing records of video platforms such as Aiqiyi and Tengcong for movie promotion and the like, the types of multiple platforms are determined according to the types of pushed multimedia information, the collection of the data of the multiple platforms is performed according to the determined types, and when the matching platform characteristics of the user obtained by analysis in the matching platform can be matched with the pushed multimedia characteristics, the collection and selection of the user are accurate, and the advertisement is delivered. Therefore, the collection and analysis of the platform data according to the category of the pushed multimedia are realized, the reliability of the user corresponding to the category characteristic analysis can be improved, the interference of other platform data is avoided, and the technical effect of the advertisement putting accuracy is further improved.
Further, the method further comprises: acquiring user playing information; extracting and analyzing the content of the user playing information to obtain playing content stage information; obtaining an insertion time point according to the user analysis result and the playing content stage information; and acquiring push playing information according to the insertion time point and the push information, wherein the push playing information is played at the insertion time point.
Further, the method further comprises: obtaining insertion playing content according to the insertion time point; according to the inserted playing content, obtaining insertion characteristic information; matching the insertion characteristic information with the pushed multimedia characteristics to obtain matched multimedia characteristics; and determining the pushed multimedia according to the matched multimedia characteristics.
Specifically, the time point of multimedia delivery also has an influence on the delivery effect, and particularly, when the video platform delivers an advertisement, for example, when the advertisement is inserted in the middle of video playing, if the content of the advertisement is matched with the content of the video, the user can be interested in watching the purchase of the user, or the time of inserting the advertisement is a position with high emotional comfort level, the mood state of the user is good, and the receptivity and the viewability of the advertisement are high. The method can select according to the rhythm and content of video playing when determining the putting position of the multimedia advertisement, select the position matched with the pushed multimedia information for putting, if the video is a high sweet love drama, the user can be influenced by the scene or character when watching, the watching user is concerned by women, the similar clothes advertisement can be inserted, the inserting time point is selected according to the played content and the user characteristic, the characteristic matching is carried out according to the playing content stage information and the user analysis result, the place suitable for the pushing multimedia characteristic attribute requirement is selected to determine the inserting time point by predicting the time point corresponding to the content stage concerned by the user according to the user individual characteristic and the playing content stage, the playing content stage information is that the semantic information of the extracted content is set according to the plot of the playing content to obtain the content information and the degree grade information, the method comprises the steps of carrying out stage division according to content and level degrees, such as conversion of a story line and the like, wherein each stage can be used as an insertion point, selecting one or more insertion points according to the requirements of inter-cut, determining the attention points and interest points of users according to characteristic analysis of viewing history records of the users, determining the attention points of the users according to the preference of the users because the attention points of different users are different, selecting the time points with moderate attention degrees as insertion time points, inserting advertisements when the attention degrees are high to cause the inverse interest of the users, and selecting the positions of the stages with certain attention degrees to play when the attention degrees are low to cause the low-interest of the users. A plurality of inserted time points may exist in a video content, specific matching is carried out according to the required inserting times and the characteristics of multimedia information, an inserting time point matched with the pushed multimedia characteristics is selected for insertion, the attention of a user can be improved, the user generally has substitution when watching the video, the state of a chairman and a favorite role is followed, if the chairman is eating a bubble surface, the advertisement content of the bubble surface can be played after a stage picture after the bubble surface is eaten is played, the click rate and the attention of the user can be improved, and the advertisement putting effect is improved. The insertion playing content is a scene of eating the bubble noodles in the above example, the insertion characteristic information is food and the bubble noodles, the insertion characteristic information is matched with the pushed multimedia characteristics, and if the matching is successful, the insertion time point is determined to play the multimedia advertisement.
Further, the classifying the pushed multimedia information according to the pushed multimedia features to obtain multimedia categories includes: obtaining a classification requirement; obtaining a first classification index and a second classification index according to the classification requirement; obtaining a historical data set based on the classification requirement, wherein the historical data set comprises a first classification index, a second classification index and a multimedia class; constructing a multimedia classification coordinate system, taking the first classification index as a horizontal coordinate and the second classification index as a vertical coordinate, and placing the historical data set in the multimedia classification coordinate system; inputting the pushed multimedia features into the multimedia classification coordinate system, and calculating to obtain Euclidean distances of all the pushed multimedia features; obtaining a characteristic distance set based on Euclidean distances of all the pushed multimedia characteristics, wherein the characteristic distance set is an Euclidean distance set meeting preset requirements; and determining the multimedia category of the pushed multimedia information according to the characteristic distance set.
Specifically, when classifying the types of the pushed multimedia features, the classification requirements can be set by using a KNN (K nearest neighbor) algorithm, a Bayesian algorithm, a decision tree algorithm and the like to improve the classification reliability and the degree of intelligence, for example, the KNN algorithm is taken as an example, when a movie is popularized, the movie is classified into love photos and action photos, classification is performed according to the fighting times and the receiving times when classification is performed, namely, a first classification index and a second classification index are included, a historical data set is historical information with classification results, a multimedia classification coordinate system is constructed by using the first classification index and the second classification index, data with classification results in a historical data set is placed in a multimedia classification coordinate system according to the first classification index and the second classification index, the multimedia features which are required to be pushed currently are input into the multimedia classification coordinate system, calculating Euclidean distances between multimedia features to be pushed and other historical data in a multimedia classification coordinate system to obtain a feature data set, selecting k data with the smallest distance according to the distance, wherein k can be set or can be used for training activities, the preset requirement is the quantity requirement of k, and according to which category is the largest in the historical data sets in the k data, the corresponding promoted multimedia is the classification, namely k closest movies in the first pushed multimedia are love pieces, the first pushed multimedia is a love piece, and the first pushed multimedia is the multimedia needing to be pushed to any one of the pushed multimedia features. The effect of intelligent classification of the pushed multimedia is achieved.
In summary, the present embodiment has at least the following technical effects:
1. acquiring current multimedia information, processing and correcting the current multimedia information by using the correction model to obtain the data characteristics of the current multimedia, and performing feature matching on a release user by using the data characteristics of the current multimedia to determine the release user characteristics; carrying out platform user set feature matching on a release platform based on the release user features to obtain a user information set; acquiring multi-platform user characteristics according to the user information set to obtain multi-platform information of the user; and respectively carrying out characteristic analysis on the multi-platform user information of each user to obtain a user analysis result, judging whether the user analysis result is consistent with the characteristics of the releasing user, and carrying out releasing adjustment on users which are not consistent. The comprehensive analysis of multi-platform users is achieved, accurate portrait of the users is achieved, multimedia promotion content is put in according to user characteristics, accuracy of information collection of the put-in users is improved, and therefore the technical effect of multimedia advertisement putting efficiency is improved.
2. Determining training data based on the historical multimedia data set and the multimedia characteristics, and training and learning the neural network model by using the training data to obtain a characteristic extraction model; and obtaining an output result of the feature extraction model, using the output result as an input model of a data conversion model, and associating the feature extraction model and the data conversion model to obtain the correction model. The data processing efficiency is improved by nesting the two models, the reliability of data processing is effectively improved by adding the neural network model, and a guaranteed technical effect is provided for subsequent data processing.
3. Obtaining insertion playing content according to the insertion time point; according to the inserted playing content, obtaining insertion characteristic information; matching the insertion characteristic information with the pushed multimedia characteristics to obtain matched multimedia characteristics; and determining the pushed multimedia according to the matched multimedia characteristics. The method and the device achieve the purposes that the matched insertion time point is selected to be delivered according to the characteristics of the pushed multimedia, the characteristics of the pushed multimedia are fused with the insertion playing content, and the advertisement delivery effect can be improved.
4. And determining the multimedia category of the pushed multimedia information according to the characteristic distance set by adding a KNN classification algorithm. The intelligent classification of the pushed multimedia is achieved, and the technical effect of reliable guarantee is provided for targeted analysis and processing according to different types of multimedia.
Example two
Based on the same inventive concept as the multimedia data acquisition method in the foregoing embodiment, the present invention further provides a multimedia data acquisition system, referring to fig. 2, where the system includes:
a first obtaining unit 11, where the first obtaining unit 11 is configured to acquire and obtain a multi-platform historical multimedia data set;
a second obtaining unit 12, where the second obtaining unit 12 is configured to perform feature algorithm matching according to the historical multimedia data set, and perform feature extraction by using a feature algorithm determined by matching, so as to obtain multimedia features;
a first executing unit 13, where the first executing unit 13 is configured to construct a correction model based on the historical multimedia data set and the multimedia features, and correct the multimedia features through the correction model to determine multimedia data features;
the second execution unit 14 is configured to collect current multimedia information, process and correct the current multimedia information by using the correction model to obtain data characteristics of the current multimedia, perform feature matching on a release user by using the data characteristics of the current multimedia, and determine release user characteristics;
a third obtaining unit 15, where the third obtaining unit 15 is configured to perform platform user set feature matching on a launching platform based on the launching user features to obtain a user information set;
a fourth obtaining unit 16, where the fourth obtaining unit 16 is configured to perform multi-platform user feature acquisition according to the user information set, so as to obtain multi-platform information of a user;
a first releasing unit 17, where the first releasing unit 17 is configured to perform feature analysis on the user multi-platform information of each user respectively to obtain a user analysis result, determine whether the user analysis result matches the feature of the releasing user, and perform releasing adjustment on users who do not match the user analysis result.
Further, the system further comprises:
a first construction unit for constructing a neural network model;
a third execution unit, configured to determine training data based on the historical multimedia data set and the multimedia features, and perform training and learning on the neural network model by using the training data to obtain a feature extraction model;
a fifth obtaining unit, configured to obtain an output result of the feature extraction model, where the output result includes a multimedia feature result;
a sixth obtaining unit, configured to obtain a feature data requirement;
the second construction unit is used for constructing a data conversion model by utilizing the characteristic data requirement and the output result of the characteristic extraction model;
a seventh obtaining unit, configured to associate the feature extraction model and the data conversion model to obtain the correction model.
Further, the system further comprises:
an eighth obtaining unit configured to obtain platform identification information;
a ninth obtaining unit, configured to determine user information according to the platform identification information, and obtain user historical access information based on the user information acquisition, where the user historical access information includes the user multi-platform information;
the fourth execution unit is used for obtaining a local platform access record according to the historical user access information, performing feature analysis on the local platform access record and determining the first platform user feature;
the first determining unit is used for performing feature analysis according to the user multi-platform information and determining the user features of the second platform;
a tenth obtaining unit, configured to perform platform relevance analysis on the local platform and the multiple platforms, perform weight calculation based on the platform relevance, and obtain user pushed feature information according to the first platform user feature, the second platform user feature, and the weight;
an eleventh obtaining unit, configured to obtain pushed multimedia information, perform feature extraction on the pushed multimedia information, and determine a pushed multimedia feature;
a twelfth obtaining unit, configured to match the pushed multimedia feature according to the user pushed feature information, and obtain user matching information, where the user matching information is multimedia pushed content matched with the user pushed feature information.
Further, the system further comprises:
a thirteenth obtaining unit, configured to classify the pushed multimedia information according to the pushed multimedia features, and obtain a multimedia category;
the second determining unit is used for determining the class characteristics according to the multimedia classes;
a fourteenth obtaining unit, configured to perform multi-platform class matching by using the class features to obtain matching platform information;
a fifteenth obtaining unit, configured to perform access record acquisition from the matching platform information based on the user information, and obtain matching platform access information;
a sixteenth obtaining unit, configured to perform feature analysis according to the matching platform access information, to obtain matching platform features of a user;
a seventeenth obtaining unit, configured to match the pushed multimedia features according to the matching platform features of the user, and obtain pushed information when a matching degree meets a preset requirement, where the pushed information is used to push multimedia information to the user information.
Further, the system further comprises:
an eighteenth obtaining unit, configured to obtain user play information;
a nineteenth obtaining unit, configured to perform content extraction and analysis on the user playing information, and obtain playing content stage information;
a twentieth obtaining unit, configured to obtain an insertion time point according to the user analysis result and the playing content stage information;
a twenty-first obtaining unit, configured to obtain, according to the insertion time point and the push information, push play information, where the push play information is played at the insertion time point.
Further, the system further comprises:
a twenty-second obtaining unit, configured to obtain an insertion play content according to the insertion time point;
a twenty-third obtaining unit, configured to obtain insertion feature information according to the insertion play content;
a twenty-fourth obtaining unit, configured to match the pushed multimedia feature according to the insertion feature information, and obtain a matched multimedia feature;
a third determining unit, configured to determine, according to the matching multimedia feature, a pushed multimedia.
Further, the system further comprises:
a twenty-fifth obtaining unit, configured to obtain a classification requirement;
a twenty-sixth obtaining unit, configured to obtain a first classification index and a second classification index according to the classification requirement;
a twenty-seventh obtaining unit, configured to obtain a historical data set based on the classification requirement, where the historical data set includes a first classification index, a second classification index, and a multimedia category;
a third constructing unit, configured to construct a multimedia classification coordinate system, use the first classification index as an abscissa and the second classification index as an ordinate, and place the historical data set in the multimedia classification coordinate system;
a twenty-eighth obtaining unit, configured to input the pushed multimedia features into the multimedia classification coordinate system, and calculate and obtain euclidean distances of the pushed multimedia features;
a twenty-ninth obtaining unit, configured to obtain a feature distance set based on euclidean distances of the push multimedia features, where the feature distance set is a euclidean distance set that meets a preset requirement;
a fourth determining unit, configured to determine the multimedia category of the pushed multimedia information according to the feature distance set.
In the present specification, the embodiments are described in a progressive manner, and each embodiment focuses on the description of the difference of the embodiments, and the multimedia data acquisition method and the specific example in the first embodiment of fig. 1 are also applicable to the multimedia data acquisition system of the present embodiment. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Exemplary electronic device
The electronic device of the embodiment of the present application is described below with reference to fig. 3.
Fig. 3 illustrates a schematic structural diagram of an electronic device according to an embodiment of the present application.
Based on the inventive concept of a multimedia data acquisition method as described in the previous embodiments, the present invention further provides a multimedia data acquisition system, on which a computer program is stored, which when executed by a processor implements the steps of any one of the methods of the previous multimedia data acquisition methods.
Where in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
In summary, one or more technical solutions provided in the present application have at least the following technical effects or advantages:
the application provides a multimedia data acquisition method and a multimedia data acquisition system, wherein a historical multimedia data set of a plurality of platforms is acquired through acquisition; performing feature algorithm matching according to the historical multimedia data set, and performing feature extraction by using a feature algorithm determined by matching to obtain multimedia features; constructing a correction model based on the historical multimedia data set and the multimedia characteristics, correcting the multimedia characteristics through the correction model, and determining the multimedia data characteristics; acquiring current multimedia information, processing and correcting the current multimedia information by using the correction model to obtain the data characteristics of the current multimedia, matching the characteristics of a release user by using the data characteristics of the current multimedia, and determining the characteristics of the release user; carrying out platform user set feature matching on a release platform based on the release user features to obtain a user information set; acquiring multi-platform user characteristics according to the user information set to obtain multi-platform information of the user; and respectively carrying out characteristic analysis on the multi-platform user information of each user to obtain a user analysis result, judging whether the user analysis result is consistent with the characteristics of the releasing user, and carrying out releasing adjustment on users which are not consistent. The comprehensive analysis of multi-platform users is achieved, accurate portrait of the users is achieved, multimedia promotion content is put in according to user characteristics, accuracy of information collection of the put-in users is improved, and therefore the technical effect of multimedia advertisement putting efficiency is improved. Therefore, the technical problems that in the prior art, the accuracy of multimedia data acquisition is not high, the portrait of a user is unreliable, and the advertising promotion effect is not good are solved.
Therefore, the technical problem that transformation failure is caused due to the fact that transformation strategies do not accord with the enterprise state due to the fact that transformation decision analysis conforming to large environment transformation elements is not performed aiming at enterprise features in the prior art is solved.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, apparatus, or computer program product. Accordingly, the present application may take the form of an entirely software embodiment, an entirely hardware embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application is in the form of a computer program product that may be embodied on one or more computer-usable storage media having computer-usable program code embodied therewith. And such computer-usable storage media include, but are not limited to: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk Memory, a Compact Disc Read-Only Memory (CD-ROM), and an optical Memory.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a system for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction system which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the same technology as the present invention, it is intended that the present invention encompass such modifications and variations as well.
Claims (10)
1. A method for multimedia data acquisition, the method comprising:
acquiring a historical multimedia data set of a plurality of platforms;
performing feature algorithm matching according to the historical multimedia data set, and performing feature extraction by using a feature algorithm determined by matching to obtain multimedia features;
constructing a correction model based on the historical multimedia data set and the multimedia characteristics, correcting the multimedia characteristics through the correction model, and determining the multimedia data characteristics;
acquiring current multimedia information, processing and correcting the current multimedia information by using the correction model to obtain the data characteristics of the current multimedia, matching the characteristics of a release user by using the data characteristics of the current multimedia, and determining the characteristics of the release user;
carrying out platform user set feature matching on a release platform based on the release user features to obtain a user information set;
acquiring multi-platform user characteristics according to the user information set to obtain multi-platform information of the user;
and respectively carrying out characteristic analysis on the multi-platform user information of each user to obtain a user analysis result, judging whether the user analysis result is consistent with the characteristics of the releasing user, and carrying out releasing adjustment on users which are not consistent.
2. The method of claim 1, wherein said constructing a correction model based on said historical multimedia data set, said multimedia features, comprises:
constructing a neural network model;
determining training data based on the historical multimedia data set and the multimedia characteristics, and training and learning the neural network model by using the training data to obtain a characteristic extraction model;
obtaining an output result of the feature extraction model, wherein the output result comprises a multimedia feature result;
obtaining a characteristic data requirement;
constructing a data conversion model by using the characteristic data requirement and the output result of the characteristic extraction model;
and correlating the feature extraction model and the data conversion model to obtain the correction model.
3. The method of claim 1, wherein the method further comprises:
obtaining platform identification information;
determining user information according to the platform identification information, and acquiring user historical access information based on the user information acquisition, wherein the user historical access information comprises the user multi-platform information;
obtaining a local platform access record according to the historical user access information, performing characteristic analysis on the local platform access record, and determining a first platform user characteristic;
performing characteristic analysis according to the user multi-platform information to determine the user characteristics of a second platform;
performing platform relevance analysis on a local platform and multiple platforms, performing weight calculation based on the platform relevance, and acquiring user push characteristic information according to the first platform user characteristics, the second platform user characteristics and the weight;
acquiring pushed multimedia information, and performing feature extraction on the pushed multimedia information to determine pushed multimedia features;
and matching the user pushing characteristic information with the pushing multimedia characteristics to obtain user matching information, wherein the user matching information is multimedia pushing content matched with the user pushing characteristic information.
4. The method of claim 3, wherein the method further comprises:
classifying the pushed multimedia information according to the pushed multimedia characteristics to obtain multimedia categories;
determining category characteristics according to the multimedia categories;
performing multi-platform class matching by using the class characteristics to obtain matching platform information;
acquiring access records from the matching platform information based on the user information to obtain matching platform access information;
performing characteristic analysis according to the matching platform access information to obtain the matching platform characteristics of the user;
and matching the matching platform characteristics of the user with the pushed multimedia characteristics, and obtaining pushed information when the matching degree meets a preset requirement, wherein the pushed information is used for pushing multimedia information to the user information.
5. The method of claim 4, wherein the method further comprises:
acquiring user playing information;
extracting and analyzing the content of the user playing information to obtain playing content stage information;
obtaining an insertion time point according to the user analysis result and the playing content stage information;
and acquiring push playing information according to the insertion time point and the push information, wherein the push playing information is played at the insertion time point.
6. The method of claim 5, wherein the method further comprises:
obtaining insertion playing content according to the insertion time point;
according to the inserted playing content, obtaining insertion characteristic information;
matching the insertion characteristic information with the pushed multimedia characteristics to obtain matched multimedia characteristics;
and determining the pushed multimedia according to the matched multimedia characteristics.
7. The method of claim 4, wherein the classifying the pushed multimedia information according to the pushed multimedia characteristics to obtain a multimedia category comprises:
obtaining a classification requirement;
obtaining a first classification index and a second classification index according to the classification requirement;
obtaining a historical data set based on the classification requirement, wherein the historical data set comprises a first classification index, a second classification index and a multimedia class;
constructing a multimedia classification coordinate system, taking the first classification index as a horizontal coordinate and the second classification index as a vertical coordinate, and placing the historical data set in the multimedia classification coordinate system;
inputting the pushed multimedia features into the multimedia classification coordinate system, and calculating to obtain Euclidean distances of all the pushed multimedia features;
obtaining a characteristic distance set based on Euclidean distances of all the pushed multimedia characteristics, wherein the characteristic distance set is an Euclidean distance set meeting preset requirements;
and determining the multimedia category of the pushed multimedia information according to the characteristic distance set.
8. A multimedia data collection system, the system comprising:
the system comprises a first obtaining unit, a second obtaining unit and a third obtaining unit, wherein the first obtaining unit is used for collecting historical multimedia data sets of a plurality of obtained platforms;
the second obtaining unit is used for matching a feature algorithm according to the historical multimedia data set and extracting features by using the feature algorithm determined by matching to obtain multimedia features;
the first execution unit is used for constructing a correction model based on the historical multimedia data set and the multimedia characteristics, correcting the multimedia characteristics through the correction model and determining the multimedia data characteristics;
the second execution unit is used for acquiring current multimedia information, processing and correcting the current multimedia information by using the correction model to obtain the data characteristics of the current multimedia, matching the features of the releasing users by using the data characteristics of the current multimedia and determining the features of the releasing users;
a third obtaining unit, configured to perform platform user set feature matching on a delivery platform based on the delivery user features to obtain a user information set;
a fourth obtaining unit, configured to perform multi-platform user feature acquisition according to the user information set, so as to obtain multi-platform information of a user;
the first releasing unit is used for respectively carrying out characteristic analysis on the user multi-platform information of each user to obtain a user analysis result, judging whether the user analysis result is consistent with the releasing user characteristic, and carrying out releasing adjustment on users which are not consistent.
9. A multimedia data acquisition system comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 7 are implemented when the processor executes the program.
10. A computer-readable storage medium, characterized in that the storage medium has stored thereon a computer program which, when being executed by a processor, carries out the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210279976.1A CN114387041B (en) | 2022-03-22 | 2022-03-22 | Multimedia data acquisition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210279976.1A CN114387041B (en) | 2022-03-22 | 2022-03-22 | Multimedia data acquisition method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114387041A true CN114387041A (en) | 2022-04-22 |
| CN114387041B CN114387041B (en) | 2022-06-17 |
Family
ID=81205341
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210279976.1A Active CN114387041B (en) | 2022-03-22 | 2022-03-22 | Multimedia data acquisition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114387041B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117789723A (en) * | 2023-11-29 | 2024-03-29 | 广州炸子鸡网络科技有限公司 | Video content processing method and system based on artificial intelligence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104991899A (en) * | 2015-06-02 | 2015-10-21 | 广州酷狗计算机科技有限公司 | Identification method and apparatus of user property |
| US20190147058A1 (en) * | 2017-11-16 | 2019-05-16 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for pushing multimedia content |
| CN111091400A (en) * | 2018-10-23 | 2020-05-01 | 第四范式（北京）技术有限公司 | Method and device for generating advertisement conversion prediction model and delivering advertisement |
| CN112348592A (en) * | 2020-11-24 | 2021-02-09 | 腾讯科技（深圳）有限公司 | Advertisement recommendation method and device, electronic equipment and medium |
| CN113344648A (en) * | 2021-08-05 | 2021-09-03 | 北京龙云科技有限公司 | Advertisement recommendation method and system based on machine learning |
| CN113850416A (en) * | 2021-08-26 | 2021-12-28 | 武汉卓尔数字传媒科技有限公司 | Advertisement promotion cooperation object determining method and device |
-
2022
- 2022-03-22 CN CN202210279976.1A patent/CN114387041B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104991899A (en) * | 2015-06-02 | 2015-10-21 | 广州酷狗计算机科技有限公司 | Identification method and apparatus of user property |
| US20190147058A1 (en) * | 2017-11-16 | 2019-05-16 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for pushing multimedia content |
| CN111091400A (en) * | 2018-10-23 | 2020-05-01 | 第四范式（北京）技术有限公司 | Method and device for generating advertisement conversion prediction model and delivering advertisement |
| CN112348592A (en) * | 2020-11-24 | 2021-02-09 | 腾讯科技（深圳）有限公司 | Advertisement recommendation method and device, electronic equipment and medium |
| CN113344648A (en) * | 2021-08-05 | 2021-09-03 | 北京龙云科技有限公司 | Advertisement recommendation method and system based on machine learning |
| CN113850416A (en) * | 2021-08-26 | 2021-12-28 | 武汉卓尔数字传媒科技有限公司 | Advertisement promotion cooperation object determining method and device |
Non-Patent Citations (1)
| Title |
|---|
| 李娜等: "基于用户特征分类的精准广告投放研究", 《电脑知识与技术》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117789723A (en) * | 2023-11-29 | 2024-03-29 | 广州炸子鸡网络科技有限公司 | Video content processing method and system based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114387041B (en) | 2022-06-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020048084A1 (en) | Resource recommendation method and apparatus, computer device, and computer-readable storage medium | |
| CN110297848A (en) | Recommended models training method, terminal and storage medium based on federation's study | |
| US9607273B2 (en) | Optimal time to post for maximum social engagement | |
| CN112074857A (en) | Combining machine learning and social data to generate personalized recommendations | |
| US10949000B2 (en) | Sticker recommendation method and apparatus | |
| KR20160055930A (en) | Systems and methods for actively composing content for use in continuous social communication | |
| WO2019109724A1 (en) | Item recommendation method and device | |
| CN106776701B (en) | Problem determination method and device for item recommendation | |
| CN111973996A (en) | Game resource putting method and device | |
| CN110933472B (en) | Method and device for realizing video recommendation | |
| CN111597446B (en) | Content pushing method and device based on artificial intelligence, server and storage medium | |
| Jia et al. | Multi-modal learning for video recommendation based on mobile application usage | |
| KR102149035B1 (en) | Advertising page creation and management system for performance marketing | |
| CN116894711A (en) | Commodity recommendation reason generation method and device and electronic equipment | |
| CN114387041B (en) | Multimedia data acquisition method and system | |
| CN113674013A (en) | Advertisement bidding adjustment method and system based on merchant self-defined rules | |
| CN114245185B (en) | Video recommendation method, model training method, device, electronic equipment and medium | |
| CN111881365A (en) | Content recommendation method and device | |
| US20230316106A1 (en) | Method and apparatus for training content recommendation model, device, and storage medium | |
| CN112989177B (en) | Information processing method, information processing device, electronic equipment and computer storage medium | |
| CN111787042B (en) | Method and device for pushing information | |
| KR20210052746A (en) | Method, apparatus and computer program for estimating sales volume of content to be productized | |
| KR20210052745A (en) | Method, apparatus and computer program for selecting promising content | |
| CN112507214B (en) | User name-based data processing method, device, equipment and medium | |
| CN114840659A (en) | Information recommendation method and device, electronic equipment and 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 |