CN112511865A - Video content recommendation system based on social media - Google Patents
Video content recommendation system based on social media Download PDFInfo
- Publication number
- CN112511865A CN112511865A CN202011432029.9A CN202011432029A CN112511865A CN 112511865 A CN112511865 A CN 112511865A CN 202011432029 A CN202011432029 A CN 202011432029A CN 112511865 A CN112511865 A CN 112511865A
- Authority
- CN
- China
- Prior art keywords
- video content
- user
- coefficient
- browsing
- marking
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9536—Search customisation based on social or collaborative filtering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
- H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies
- H04N21/4668—Learning process for intelligent management, e.g. learning user preferences for recommending movies for recommending content, e.g. movies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/47—End-user applications
- H04N21/475—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data
- H04N21/4756—End-user interface for inputting end-user data, e.g. personal identification number [PIN], preference data for rating content, e.g. scoring a recommended movie
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Human Computer Interaction (AREA)
- Information Transfer Between Computers (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a video content recommendation system based on social media, which relates to the technical field of video content recommendation and solves the technical problem that in the prior art, favorite users cannot reasonably and accurately push video content information; the method and the device analyze the surrounding users of the users who do not browse, recommend the users who do not browse through the interested resources of the surrounding users, avoid pushing useless resources, improve the working efficiency and improve the use quality of the users.
Description
Technical Field
The invention relates to the technical field of video content recommendation, in particular to a video content recommendation system based on social media.
Background
The appearance and popularization of the internet bring a great deal of information to users, the demand of the users on the information in the information age is met, but the quantity of the information on the internet greatly increases along with the rapid development of the network, so that the users cannot obtain the information which is really useful for the users when facing a great amount of information, the use efficiency of the information is reduced on the contrary, the problem of information overload is called, a very potential method for solving the problem of information overload is a recommendation system, and the recommendation system is a personalized information recommendation system which recommends the information, products and the like which are interested by the users to the users according to the information demand, interest and the like of the users. Compared with a search engine, the recommendation system carries out personalized calculation by researching the interest preference of the user, and the system finds the interest points of the user, thereby guiding the user to find the own information requirement; a good recommendation system can not only provide personalized services for users, but also can establish close relations with the users to enable the users to generate dependence on the recommendation, and the recommendation system is widely applied to a plurality of fields, wherein the most typical field with good development and application prospects is the electronic commerce field. Meanwhile, the research popularity of the academic community on the recommendation system is high all the time, and an independent subject is gradually formed.
However, in the prior art, the recommendation system cannot perform push monitoring, which results in wrong resources being pushed, and meanwhile, for users who cannot acquire favorites, video content information cannot be pushed reasonably and accurately, thereby greatly reducing the working efficiency.
Disclosure of Invention
The invention aims to provide a video content recommendation system based on social media.
The purpose of the invention can be realized by the following technical scheme:
a video content recommendation system based on social media comprises a registration login unit, a database, a data acquisition unit, a collaborative filtering unit, an analysis unit, a monitoring unit and a cloud recommendation platform;
the analysis unit is used for analyzing video content information and ranking the video content, the video content information comprises comment data, use data and number of people data, the comment data are expressed as the ratio of the number of good comments to the number of bad comments of the video content, the use data are expressed as the number of times of secondary use of the video content, the number of people data are expressed as the sum of the total number of browsing people and the number of secondary use people of the video content, the video content is marked as o, o =1, 2, and the ranking process is specifically as follows:
SS 1: acquiring the ratio of the good comment quantity to the bad comment quantity of the video content, and marking the ratio of the good comment quantity to the bad comment quantity of the video content as Bo;
SS 2: acquiring the secondary usage times of the video content, and marking the secondary usage times of the video content as Co;
SS 3: acquiring the sum of the total number of browsing people and the number of secondary users of the video content, and marking the sum of the total number of browsing people and the number of secondary users of the video content as Ro;
SS 4: by the formula
Acquiring an analysis coefficient Po of video content, wherein a1, a2 and a3 are all preset proportionality coefficients, and a1 is greater than a2 is greater than a3 is greater than 0;
SS 5: comparing the analysis coefficient Po of the video content with an analysis coefficient threshold of the video content:
if the analysis coefficient Po of the video content is larger than or equal to the analysis coefficient threshold of the video content, judging that the analysis coefficient of the video content is high, marking the analysis coefficient as hot video content, and then sending the video content analysis coefficient and the name of the corresponding hot video content to a cloud recommendation platform;
if the analysis coefficient Po of the video content is larger than or equal to the analysis coefficient threshold of the video content, judging that the analysis coefficient of the video content is low, marking the video content as cold video content, and sending the cold video content to a cloud recommendation platform;
the cloud recommendation platform sends the cold door video content to the database for storage after receiving the cold door video content, sets storage time k, obtains an analysis coefficient of the cold door video content in the k time, marks the analysis coefficient as deleted video content if the analysis coefficient is still less than an analysis coefficient threshold value, and deletes the deleted video content in the database; after receiving the popular video content, the cloud recommendation platform corresponds the popular video content to the analysis coefficients one by one, sorts the popular video content according to the sequence of the analysis coefficients from large to small, marks the popular video content as a popular video content ranking list, pushes the popular video content ranking list to a mobile phone terminal of a user stored in the data, and sets the updating time of the popular video content ranking list.
Further, the registration login unit is used for the user and the administrator to submit user information and administrator information through the mobile phone terminal for registration, and send the user information and the administrator information which are successfully registered to the database for storage, wherein the user information comprises the name, the age, the occupation and the mobile phone number of the real name authentication of the user, and the administrator information comprises the name, the age, the time of enrollment and the mobile phone number of the real name authentication of the administrator.
Further, the data acquisition unit is configured to acquire and analyze video content historical data of a user, where the video content is represented by videos and documents in various fields, the historical data of the user includes browsing data, duration magnitude data, and frequency data, the browsing data is represented by a sum of times that the user browses videos and times that the user browses documents in one month, the duration magnitude data is represented by a sum of times that the user browses videos and times that the user browses documents in one month, the frequency data is represented by a sum of frequencies that the user browses videos and frequencies that the user browses documents in one month, and the user is marked as i, i =1, 2,.. once.
Step one, acquiring the sum of the number of times of browsing videos and the number of times of browsing documents of a user in one month, and marking the sum of the number of times of browsing videos and the number of times of browsing documents of the user in one month as Ci;
step two, acquiring the sum of the video browsing time length of the user and the document browsing time length in one month, and marking the sum of the video browsing time length of the user and the document browsing time length in one month as Si;
step three, acquiring the sum of the frequency of the video browsed by the user and the frequency of the document browsed by the user in one month, and marking the sum of the frequency of the video browsed by the user and the frequency of the document browsed by the user in one month as Pi;
step four, passing through a formula
Acquiring a history coefficient Xi of a user, wherein s1, s2 and s3 are all preset proportional coefficients, s1 is larger than s2 is larger than s3 is larger than 0, and beta is an error correction factor and is 2.3012563;
step five, comparing the history coefficient Xi of the user with a history coefficient threshold value:
if the historical coefficient Xi of the user is larger than or equal to the historical coefficient threshold value, judging that the user has high interest degree in the video content, generating an interest signal and sending the interest signal and the corresponding video content to the cloud recommendation platform;
and if the historical coefficient Xi of the user is less than the historical coefficient threshold value, judging that the user has low interest degree in the video content, generating a non-interest signal and sending the non-interest signal and the corresponding user name to the cloud recommendation platform.
Further, after receiving the interest signal and the corresponding video content, the cloud recommendation platform marks the corresponding video content as a recommendation resource and sends the recommendation resource to a mobile phone terminal of a user; after receiving a non-interest signal and a corresponding user name, the cloud recommendation platform marks the user as a non-browsing user and sends the non-browsing user to the collaborative filtering unit if the historical coefficient Xi of the user is less than the lowest limit value of the historical coefficient;
the collaborative filtering unit is used for analyzing the users who do not browse and reasonably distributing proper video content, and the specific reasonable distribution process is as follows:
s1, obtaining login addresses of users who do not browse through the Internet, marking the login address with the highest login frequency as a common login address, then obtaining surrounding login users by taking the common login address as a center, and marking the surrounding login users as preselected users;
s2, obtaining the contact times and contact frequency of the pre-selected user and the mobile phone terminal of the user who does not browse, marking the contact times and contact frequency of the pre-selected user and the mobile phone terminal of the user who does not browse as LC and LP respectively, and marking the contact times and contact frequency as LC and LP correspondingly through formulas
Acquiring a familiarity coefficient SX of a preselected user, wherein c1 and c2 are both preset proportionality coefficients;
s3: the familiarity coefficient SX is compared to a familiarity coefficient threshold: if the familiarity coefficient SX is larger than or equal to the familiarity coefficient threshold, judging that the preselected user is frequently contacted with the user who does not browse, and marking the preselected user as a selected user; if the familiarity coefficient SX is less than the familiarity coefficient threshold value, judging that the preselected user is not frequently contacted with the user who does not browse, and marking the preselected user as an irrelevant user;
s4: and acquiring the familiarity coefficient of the selected user and the non-browsing user within one month, if the familiarity coefficient is more than or equal to the familiarity coefficient threshold, acquiring the video content with high interest degree of the selected user within one month, marking the video content as screened video content, and then sending the screened video content to the mobile phone terminal of the non-browsing user.
Further, the monitoring unit is configured to analyze video content information and monitor pushing of a recommended video, where the video content information includes complaint data, query data, and duration data, the complaint data indicates the number of complaints of a user on the recommended video, the query data indicates the number of queries of the user on the recommended video, the duration data indicates browsing duration of the user on the recommended video, the recommended video is marked as G, G =1, 2, and u is a non-zero positive integer, and a specific analysis and monitoring process is as follows:
r1: obtaining the number of complaints of the user on the recommended video, and marking the number of complaints of the user on the recommended video as TG;
r2: acquiring the query times of a user on a recommended video, and marking the query times of the user on the recommended video as CG;
r3: acquiring the browsing time of a user on a recommended video, and marking the browsing time of the user on the recommended video as LG;
r4: by the formula
Acquiring a monitoring coefficient GG, wherein v1, v2 and v3 are all preset proportionality coefficients, v1 is greater than v2 and is greater than v3 and is greater than 0, and alpha is an error correction factor and is 1.36521542;
r5: comparing the monitoring coefficient GG to a monitoring coefficient threshold:
if the monitoring coefficient GG is larger than or equal to the monitoring coefficient threshold value, judging that the recommended resources are normal, generating a normal cloud recommendation platform signal and sending the normal cloud recommendation platform signal to a mobile phone terminal of an administrator;
and if the monitoring coefficient GG is smaller than the monitoring coefficient threshold value, judging that the recommended resources are abnormal, generating a cloud recommendation platform abnormal signal and sending the cloud recommendation platform abnormal signal to a mobile phone terminal of an administrator.
Compared with the prior art, the invention has the beneficial effects that:
1. in the invention, the video content information is analyzed by an analysis unit, and the video content is ranked: the method comprises the steps of obtaining video content information, obtaining an analysis coefficient Po of video content through a formula, marking the analysis coefficient Po of the video content as cold video content if the analysis coefficient Po of the video content is larger than or equal to an analysis coefficient threshold of the video content, and sending the cold video content to a cloud recommendation platform; after receiving the popular video content, the cloud recommendation platform corresponds the popular video content and the analysis coefficients one by one, sorts the popular video content according to the sequence of the analysis coefficients from large to small, marks the popular video content as a popular video content ranking list, pushes the popular video content ranking list to a mobile phone terminal of a user stored in data, and sets updating time of the popular video content ranking list; through resource analysis, appropriate video content is pushed for the user, so that the searching time of the user is reduced, and the working efficiency of the platform is improved;
2. in the invention, the non-browsing user is analyzed through the collaborative filtering unit, proper video content is reasonably distributed, the login address of the non-browsing user is obtained through the Internet, and the login address is used for displaying the video contentThe login address with the highest login frequency is marked as a common login address, then the common login address is used as the center, the surrounding login users are obtained, and the login users are marked as preselected users; acquiring contact times and contact frequency of a preselected user and a mobile phone terminal of a non-browsing user through a formula
Acquiring a familiarity coefficient SX of a preselected user, and comparing the familiarity coefficient SX with a familiarity coefficient threshold value: if the familiarity coefficient SX is larger than or equal to the familiarity coefficient threshold, judging that the preselected user is frequently contacted with the user who does not browse, and marking the preselected user as a selected user; if the familiarity coefficient SX is less than the familiarity coefficient threshold, the preselected user is marked as an irrelevant user, the familiarity coefficient between the selected user and the non-browsing user within one month is obtained, if the familiarity coefficient is more than or equal to the familiarity coefficient threshold, the video content with high interest degree within one month of the selected user is obtained and marked as screened video content, and then the screened video content is sent to the mobile phone terminal of the non-browsing user; the method and the device analyze the surrounding users of the users who do not browse, recommend the users who do not browse through the interested resources of the surrounding users, avoid pushing useless resources, improve the working efficiency and improve the use quality of the users.
Drawings
In order to facilitate understanding for those skilled in the art, the present invention will be further described with reference to the accompanying drawings.
Fig. 1 is a schematic block diagram of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, a video content recommendation system based on social media includes a registration login unit, a database, a data acquisition unit, a collaborative filtering unit, an analysis unit, a monitoring unit, and a cloud recommendation platform;
the registration login unit is used for submitting user information and administrator information for registration through a mobile phone terminal by a user and an administrator, and sending the user information and the administrator information which are successfully registered to the database for storage, wherein the user information comprises the name, the age, the occupation and the mobile phone number of real name authentication of the user, and the administrator information comprises the name, the age, the time of entry and the mobile phone number of real name authentication of the administrator;
the data acquisition unit is used for acquiring and analyzing video content historical data of a user, the video content is represented as videos and documents in various fields, the historical data of the user comprises browsing data, duration magnitude data and frequency data, the browsing data is represented as the sum of the times of the user browsing videos and the times of browsing the documents in one month, the duration magnitude data is represented as the sum of the duration of the user browsing videos and the duration of the document browsing in one month, the frequency data is represented as the sum of the frequencies of the user browsing videos and the frequencies of the browsing documents in one month, the user is marked as i, i =1, 2,.
Step one, acquiring the sum of the number of times of browsing videos and the number of times of browsing documents of a user in one month, and marking the sum of the number of times of browsing videos and the number of times of browsing documents of the user in one month as Ci;
step two, acquiring the sum of the video browsing time length of the user and the document browsing time length in one month, and marking the sum of the video browsing time length of the user and the document browsing time length in one month as Si;
step three, acquiring the sum of the frequency of the video browsed by the user and the frequency of the document browsed by the user in one month, and marking the sum of the frequency of the video browsed by the user and the frequency of the document browsed by the user in one month as Pi;
step four, passing through a formula
Acquiring historical coefficients Xi of the user, wherein s1, s2 and s3 are all presetThe proportionality coefficient is s1 & gt s2 & gt s3 & gt 0, beta is an error correction factor, and the value is 2.3012563;
step five, comparing the history coefficient Xi of the user with a history coefficient threshold value:
if the historical coefficient Xi of the user is larger than or equal to the historical coefficient threshold value, judging that the user has high interest degree in the video content, generating an interest signal and sending the interest signal and the corresponding video content to the cloud recommendation platform;
if the historical coefficient Xi of the user is smaller than the historical coefficient threshold value, judging that the user has low interest degree in the video content, generating a non-interest signal and sending the non-interest signal and the corresponding user name to the cloud recommendation platform;
after receiving the interest signal and the corresponding video content, the cloud recommendation platform marks the corresponding video content as a recommendation resource and sends the recommendation resource to a mobile phone terminal of a user; after receiving a non-interest signal and a corresponding user name, the cloud recommendation platform marks the user as a non-browsing user and sends the non-browsing user to the collaborative filtering unit if the historical coefficient Xi of the user is less than the lowest limit value of the historical coefficient;
the collaborative filtering unit is used for analyzing the users who do not browse and reasonably distributing proper video content, and the specific reasonable distribution process is as follows:
s1, obtaining login addresses of users who do not browse through the Internet, marking the login address with the highest login frequency as a common login address, then obtaining surrounding login users by taking the common login address as a center, and marking the surrounding login users as preselected users;
s2, obtaining the contact times and contact frequency of the pre-selected user and the mobile phone terminal of the user who does not browse, marking the contact times and contact frequency of the pre-selected user and the mobile phone terminal of the user who does not browse as LC and LP respectively, and marking the contact times and contact frequency as LC and LP correspondingly through formulas
Acquiring a familiarity coefficient SX of a preselected user, wherein c1 and c2 are both preset proportionality coefficients;
s3: the familiarity coefficient SX is compared to a familiarity coefficient threshold: if the familiarity coefficient SX is larger than or equal to the familiarity coefficient threshold, judging that the preselected user is frequently contacted with the user who does not browse, and marking the preselected user as a selected user; if the familiarity coefficient SX is less than the familiarity coefficient threshold value, judging that the preselected user is not frequently contacted with the user who does not browse, and marking the preselected user as an irrelevant user;
s4: acquiring the familiarity coefficient of the selected user and the non-browsing user within one month, if the familiarity coefficient is larger than or equal to the familiarity coefficient threshold, acquiring the video content with high interest level of the selected user within one month, marking the video content as screened video content, and then sending the screened video content to the mobile phone terminal of the non-browsing user;
the analysis unit is used for analyzing video content information and ranking the video content, the video content information comprises comment data, use data and number of people data, the comment data is represented as the ratio of the number of good comments to the number of bad comments of the video content, the use data is represented as the number of times of secondary use of the video content, the number of people data is represented as the sum of the total number of browsing people and the number of secondary use people of the video content, the video content is marked as o, o =1, 2, the.
SS 1: acquiring the ratio of the good comment quantity to the bad comment quantity of the video content, and marking the ratio of the good comment quantity to the bad comment quantity of the video content as Bo;
SS 2: acquiring the secondary usage times of the video content, and marking the secondary usage times of the video content as Co;
SS 3: acquiring the sum of the total number of browsing people and the number of secondary users of the video content, and marking the sum of the total number of browsing people and the number of secondary users of the video content as Ro;
SS 4: by the formula
Acquiring an analysis coefficient Po of video content, wherein a1, a2 and a3 are all preset proportionality coefficients, and a1 is greater than a2 is greater than a3 is greater than 0;
SS 5: comparing the analysis coefficient Po of the video content with an analysis coefficient threshold of the video content:
if the analysis coefficient Po of the video content is larger than or equal to the analysis coefficient threshold of the video content, judging that the analysis coefficient of the video content is high, marking the analysis coefficient as hot video content, and then sending the video content analysis coefficient and the name of the corresponding hot video content to a cloud recommendation platform;
if the analysis coefficient Po of the video content is larger than or equal to the analysis coefficient threshold of the video content, judging that the analysis coefficient of the video content is low, marking the video content as cold video content, and sending the cold video content to a cloud recommendation platform;
after receiving the cold door video content, the cloud recommendation platform sends the cold door video content to the database for storage, sets storage time k, obtains an analysis coefficient of the cold door video content in the k time, marks the analysis coefficient as deleted video content if the analysis coefficient is still less than an analysis coefficient threshold value, and deletes the deleted video content in the database; after receiving the popular video content, the cloud recommendation platform corresponds the popular video content and the analysis coefficients one by one, sorts the popular video content according to the sequence of the analysis coefficients from large to small, marks the popular video content as a popular video content ranking list, pushes the popular video content ranking list to a mobile phone terminal of a user stored in data, and sets updating time of the popular video content ranking list;
the monitoring unit is used for analyzing video content information and monitoring pushing of recommended videos, the video content information comprises complaint data, query data and duration data, the complaint data is represented as complaint times of a user on the recommended videos, the query data is represented as query times of the user on the recommended videos, the duration data is represented as browsing duration of the user on the recommended videos, the recommended videos are marked as G, G =1, 2, a.
R1: obtaining the number of complaints of the user on the recommended video, and marking the number of complaints of the user on the recommended video as TG;
r2: acquiring the query times of a user on a recommended video, and marking the query times of the user on the recommended video as CG;
r3: acquiring the browsing time of a user on a recommended video, and marking the browsing time of the user on the recommended video as LG;
r4: by the formula
Acquiring a monitoring coefficient GG, wherein v1, v2 and v3 are all preset proportionality coefficients, v1 is greater than v2 and is greater than v3 and is greater than 0, and alpha is an error correction factor and is 1.36521542;
r5: comparing the monitoring coefficient GG to a monitoring coefficient threshold:
if the monitoring coefficient GG is larger than or equal to the monitoring coefficient threshold value, judging that the recommended resources are normal, generating a normal cloud recommendation platform signal and sending the normal cloud recommendation platform signal to a mobile phone terminal of an administrator;
if the monitoring coefficient GG is smaller than the monitoring coefficient threshold value, judging that the recommended resources are abnormal, generating a cloud recommendation platform abnormal signal and sending the cloud recommendation platform abnormal signal to a mobile phone terminal of an administrator;
the branch management unit is used for carrying out classification management on historical use data of a user, the historical use data comprises the date of historical use video content and the field of the video content, the date of the historical use video content is compared, the interval duration of the historical use video content is obtained, the historical use video content is sequenced according to the sequence of the interval duration from small to large, the video content with the shortest interval duration is marked as frequent video content, the field to which the frequent video content belongs is obtained, and the video content with the top three times of hot door ranking in the field is pushed to the mobile phone terminal of the user.
The working principle of the invention is as follows:
a video content recommendation system based on social media analyzes video content information through an analysis unit and ranks the video content when in work: the method comprises the steps of obtaining the ratio of the number of good comments to the number of bad comments of video content, the number of times of secondary use of the video content and the sum of the total number of browsing people and the number of secondary users of the video content, obtaining an analysis coefficient Po of the video content through a formula, judging that the analysis coefficient Po of the video content is high if the analysis coefficient Po of the video content is larger than or equal to the analysis coefficient threshold value of the video content, marking the analysis coefficient Po as hot video content, and then sending the video content analysis coefficient and the name of the corresponding hot video content to a cloud recommendation platform; if the analysis coefficient Po of the video content is larger than or equal to the analysis coefficient threshold of the video content, judging that the analysis coefficient of the video content is low, marking the video content as cold video content, and sending the cold video content to a cloud recommendation platform;
after receiving the cold door video content, the cloud recommendation platform sends the cold door video content to the database for storage, sets storage time k, obtains an analysis coefficient of the cold door video content in the k time, marks the analysis coefficient as deleted video content if the analysis coefficient is still less than an analysis coefficient threshold value, and deletes the deleted video content in the database; after receiving the popular video content, the cloud recommendation platform corresponds the popular video content to the analysis coefficients one by one, sorts the popular video content according to the sequence of the analysis coefficients from large to small, marks the popular video content as a popular video content ranking list, pushes the popular video content ranking list to a mobile phone terminal of a user stored in the data, and sets the updating time of the popular video content ranking list.
The above formulas are all calculated by taking the numerical value of the dimension, the formula is a formula which obtains the latest real situation by acquiring a large amount of data and performing software simulation, and the preset parameters in the formula are set by the technical personnel in the field according to the actual situation.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (5)
1. A video content recommendation system based on social media is characterized by comprising a registration login unit, a database, a data acquisition unit, a collaborative filtering unit, an analysis unit, a monitoring unit and a cloud recommendation platform;
the analysis unit is used for analyzing video content information and ranking the video content, the video content information comprises comment data, use data and number of people data, the comment data are expressed as the ratio of the number of good comments to the number of bad comments of the video content, the use data are expressed as the number of times of secondary use of the video content, the number of people data are expressed as the sum of the total number of browsing people and the number of secondary use people of the video content, the video content is marked as o, o =1, 2, and the ranking process is specifically as follows:
SS 1: acquiring the ratio of the good comment quantity to the bad comment quantity of the video content, and marking the ratio of the good comment quantity to the bad comment quantity of the video content as Bo;
SS 2: acquiring the secondary usage times of the video content, and marking the secondary usage times of the video content as Co;
SS 3: acquiring the sum of the total number of browsing people and the number of secondary users of the video content, and marking the sum of the total number of browsing people and the number of secondary users of the video content as Ro;
SS 4: by the formula
Acquiring an analysis coefficient Po of video content, wherein a1, a2 and a3 are all preset proportionality coefficients, and a1 is greater than a2 is greater than a3 is greater than 0;
SS 5: comparing the analysis coefficient Po of the video content with an analysis coefficient threshold of the video content:
if the analysis coefficient Po of the video content is larger than or equal to the analysis coefficient threshold of the video content, judging that the analysis coefficient of the video content is high, marking the analysis coefficient as hot video content, and then sending the video content analysis coefficient and the name of the corresponding hot video content to a cloud recommendation platform;
if the analysis coefficient Po of the video content is larger than or equal to the analysis coefficient threshold of the video content, judging that the analysis coefficient of the video content is low, marking the video content as cold video content, and sending the cold video content to a cloud recommendation platform;
the cloud recommendation platform sends the cold door video content to the database for storage after receiving the cold door video content, sets storage time k, obtains an analysis coefficient of the cold door video content in the k time, marks the analysis coefficient as deleted video content if the analysis coefficient is still less than an analysis coefficient threshold value, and deletes the deleted video content in the database; after receiving the popular video content, the cloud recommendation platform corresponds the popular video content to the analysis coefficients one by one, sorts the popular video content according to the sequence of the analysis coefficients from large to small, marks the popular video content as a popular video content ranking list, pushes the popular video content ranking list to a mobile phone terminal of a user stored in the data, and sets the updating time of the popular video content ranking list.
2. The social media-based video content recommendation system according to claim 1, wherein the registration login unit is configured to enable the user and the administrator to submit user information and administrator information through the mobile phone terminal for registration, and send the user information and the administrator information that are successfully registered to the database for storage, the user information includes a mobile phone number for authenticating the name, the age, the occupation, and the real name of the user, and the administrator information includes a mobile phone number for authenticating the real name of the administrator, the age, the time of enrollment, and the real name of the administrator.
3. The social media-based video content recommendation system according to claim 1, wherein the data acquisition unit is configured to acquire and analyze video content history data of a user, the video content is represented by videos and documents in various fields, the history data of the user includes browsing data, duration magnitude data, and frequency data, the browsing data is represented by a sum of a number of times that the user browses videos and a number of times that the user browses documents in a month, the duration magnitude data is represented by a sum of a duration that the user browses videos and a duration that the user browses documents in a month, the frequency data is represented by a sum of a frequency that the user browses videos and a frequency that the user browses documents in a month, and the user is marked as i, i =1, 2,...., n, n is a non-zero positive integer, and the acquisition and analysis processes are as follows:
step one, acquiring the sum of the number of times of browsing videos and the number of times of browsing documents of a user in one month, and marking the sum of the number of times of browsing videos and the number of times of browsing documents of the user in one month as Ci;
step two, acquiring the sum of the video browsing time length of the user and the document browsing time length in one month, and marking the sum of the video browsing time length of the user and the document browsing time length in one month as Si;
step three, acquiring the sum of the frequency of the video browsed by the user and the frequency of the document browsed by the user in one month, and marking the sum of the frequency of the video browsed by the user and the frequency of the document browsed by the user in one month as Pi;
step four, passing through a formula
Acquiring a history coefficient Xi of a user, wherein s1, s2 and s3 are all preset proportional coefficients, s1 is larger than s2 is larger than s3 is larger than 0, and beta is an error correction factor and is 2.3012563;
step five, comparing the history coefficient Xi of the user with a history coefficient threshold value:
if the historical coefficient Xi of the user is larger than or equal to the historical coefficient threshold value, judging that the user has high interest degree in the video content, generating an interest signal and sending the interest signal and the corresponding video content to the cloud recommendation platform;
and if the historical coefficient Xi of the user is less than the historical coefficient threshold value, judging that the user has low interest degree in the video content, generating a non-interest signal and sending the non-interest signal and the corresponding user name to the cloud recommendation platform.
4. The social media-based video content recommendation system according to claim 3, wherein after receiving the interest signal and the corresponding video content, the cloud recommendation platform marks the corresponding video content as a recommendation resource and sends the recommendation resource to a mobile phone terminal of a user; after receiving a non-interest signal and a corresponding user name, the cloud recommendation platform marks the user as a non-browsing user and sends the non-browsing user to the collaborative filtering unit if the historical coefficient Xi of the user is less than the lowest limit value of the historical coefficient;
the collaborative filtering unit is used for analyzing the users who do not browse and reasonably distributing proper video content, and the specific reasonable distribution process is as follows:
s1, obtaining login addresses of users who do not browse through the Internet, marking the login address with the highest login frequency as a common login address, then obtaining surrounding login users by taking the common login address as a center, and marking the surrounding login users as preselected users;
s2, obtaining the contact times and contact frequency of the pre-selected user and the mobile phone terminal of the user who does not browse, marking the contact times and contact frequency of the pre-selected user and the mobile phone terminal of the user who does not browse as LC and LP respectively, and marking the contact times and contact frequency as LC and LP correspondingly through formulas
Acquiring a familiarity coefficient SX of a preselected user, wherein c1 and c2 are both preset proportionality coefficients;
s3: the familiarity coefficient SX is compared to a familiarity coefficient threshold: if the familiarity coefficient SX is larger than or equal to the familiarity coefficient threshold, judging that the preselected user is frequently contacted with the user who does not browse, and marking the preselected user as a selected user; if the familiarity coefficient SX is less than the familiarity coefficient threshold value, judging that the preselected user is not frequently contacted with the user who does not browse, and marking the preselected user as an irrelevant user;
s4: and acquiring the familiarity coefficient of the selected user and the non-browsing user within one month, if the familiarity coefficient is more than or equal to the familiarity coefficient threshold, acquiring the video content with high interest degree of the selected user within one month, marking the video content as screened video content, and then sending the screened video content to the mobile phone terminal of the non-browsing user.
5. The social media-based video content recommendation system according to claim 1, wherein the monitoring unit is configured to analyze video content information and monitor pushing of recommended videos, the video content information includes complaint data, query data, and duration data, the complaint data indicates the number of complaints of the user on the recommended videos, the query data indicates the number of queries of the user on the recommended videos, the duration data indicates the duration of browsing of the recommended videos by the user, the recommended videos are marked as G, G =1, 2, ·.. the.
R1: obtaining the number of complaints of the user on the recommended video, and marking the number of complaints of the user on the recommended video as TG;
r2: acquiring the query times of a user on a recommended video, and marking the query times of the user on the recommended video as CG;
r3: acquiring the browsing time of a user on a recommended video, and marking the browsing time of the user on the recommended video as LG;
r4: by the formula
Acquiring a monitoring coefficient GG, wherein v1, v2 and v3 are all preset proportionality coefficients, v1 is greater than v2 and is greater than v3 and is greater than 0, and alpha is an error correction factor and is 1.36521542;
r5: comparing the monitoring coefficient GG to a monitoring coefficient threshold:
if the monitoring coefficient GG is larger than or equal to the monitoring coefficient threshold value, judging that the recommended resources are normal, generating a normal cloud recommendation platform signal and sending the normal cloud recommendation platform signal to a mobile phone terminal of an administrator;
and if the monitoring coefficient GG is smaller than the monitoring coefficient threshold value, judging that the recommended resources are abnormal, generating a cloud recommendation platform abnormal signal and sending the cloud recommendation platform abnormal signal to a mobile phone terminal of an administrator.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011432029.9A CN112511865B (en) | 2020-12-10 | 2020-12-10 | Video content recommendation system based on social media |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011432029.9A CN112511865B (en) | 2020-12-10 | 2020-12-10 | Video content recommendation system based on social media |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112511865A true CN112511865A (en) | 2021-03-16 |
| CN112511865B CN112511865B (en) | 2022-05-03 |
Family
ID=74970331
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011432029.9A Active CN112511865B (en) | 2020-12-10 | 2020-12-10 | Video content recommendation system based on social media |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112511865B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010797A (en) * | 2021-04-15 | 2021-06-22 | 王美珍 | Smart city data sharing method and system based on cloud platform |
| CN113115107A (en) * | 2021-04-15 | 2021-07-13 | 深圳鸿祥源科技有限公司 | Handheld video acquisition terminal system based on 5G network |
| CN113238826A (en) * | 2021-05-14 | 2021-08-10 | 深圳掌酷软件有限公司 | Dynamic change system for AOD screen display |
| CN113703334A (en) * | 2021-09-22 | 2021-11-26 | 深圳市欧瑞博科技股份有限公司 | Intelligent scene updating method and device |
| CN117009557A (en) * | 2023-08-08 | 2023-11-07 | 苏州瑞山传媒有限公司 | Multimedia system data processing method and processing device |
| CN117931958A (en) * | 2024-03-21 | 2024-04-26 | 山东山科世鑫科技有限公司 | Data warehouse management system and method based on artificial intelligence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103686240A (en) * | 2013-12-16 | 2014-03-26 | 深圳创维数字技术股份有限公司 | Program recommending method and system |
| CN107748759A (en) * | 2017-09-21 | 2018-03-02 | 广州华多网络科技有限公司 | Video pushing method and its equipment |
| CN107888950A (en) * | 2017-11-09 | 2018-04-06 | 福州瑞芯微电子股份有限公司 | A kind of method and system for recommending video |
| CN109101563A (en) * | 2018-07-13 | 2018-12-28 | 东软集团股份有限公司 | A kind of object recommendation method, apparatus, medium and equipment |
| CN110472145A (en) * | 2019-07-25 | 2019-11-19 | 维沃移动通信有限公司 | A kind of content recommendation method and electronic equipment |
| CN111741336A (en) * | 2020-07-20 | 2020-10-02 | 杭州翔毅科技有限公司 | Video content recommendation method, device, equipment and storage medium |
-
2020
- 2020-12-10 CN CN202011432029.9A patent/CN112511865B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103686240A (en) * | 2013-12-16 | 2014-03-26 | 深圳创维数字技术股份有限公司 | Program recommending method and system |
| CN107748759A (en) * | 2017-09-21 | 2018-03-02 | 广州华多网络科技有限公司 | Video pushing method and its equipment |
| CN107888950A (en) * | 2017-11-09 | 2018-04-06 | 福州瑞芯微电子股份有限公司 | A kind of method and system for recommending video |
| CN109101563A (en) * | 2018-07-13 | 2018-12-28 | 东软集团股份有限公司 | A kind of object recommendation method, apparatus, medium and equipment |
| CN110472145A (en) * | 2019-07-25 | 2019-11-19 | 维沃移动通信有限公司 | A kind of content recommendation method and electronic equipment |
| CN111741336A (en) * | 2020-07-20 | 2020-10-02 | 杭州翔毅科技有限公司 | Video content recommendation method, device, equipment and storage medium |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010797A (en) * | 2021-04-15 | 2021-06-22 | 王美珍 | Smart city data sharing method and system based on cloud platform |
| CN113115107A (en) * | 2021-04-15 | 2021-07-13 | 深圳鸿祥源科技有限公司 | Handheld video acquisition terminal system based on 5G network |
| CN113238826A (en) * | 2021-05-14 | 2021-08-10 | 深圳掌酷软件有限公司 | Dynamic change system for AOD screen display |
| CN113703334A (en) * | 2021-09-22 | 2021-11-26 | 深圳市欧瑞博科技股份有限公司 | Intelligent scene updating method and device |
| CN117009557A (en) * | 2023-08-08 | 2023-11-07 | 苏州瑞山传媒有限公司 | Multimedia system data processing method and processing device |
| CN117931958A (en) * | 2024-03-21 | 2024-04-26 | 山东山科世鑫科技有限公司 | Data warehouse management system and method based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112511865B (en) | 2022-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112511865B (en) | Video content recommendation system based on social media | |
| Skoutas et al. | Ranking and clustering web services using multicriteria dominance relationships | |
| US8250096B2 (en) | Access to trusted user-generated content using social networks | |
| CN102622417B (en) | The method and apparatus that information record is ranked up | |
| US20080059453A1 (en) | System and method for enhancing the result of a query | |
| US20070233672A1 (en) | Personalizing search results from search engines | |
| US20080313215A1 (en) | System and method for the generation and storage of contextually anchored links and for navigation within information systems based on such links | |
| CN112348602B (en) | Automatic advertisement putting management system based on big data | |
| WO2013169178A2 (en) | Social media profiling | |
| CN103729359A (en) | Method and system for recommending search terms | |
| CN111654518B (en) | Content pushing method and device, electronic equipment and computer readable storage medium | |
| CN103812906B (en) | Website recommendation method and device and communication system | |
| CN101661490B (en) | Search engine, client thereof and method for searching page | |
| CN104615741A (en) | Cloud computing based cold start item recommending method and device | |
| CN105787066A (en) | Digital content distribution system based on total analysis | |
| CN109033286A (en) | Data statistical approach and device | |
| CN106407362A (en) | Keyword information retrieval method and device | |
| Wang et al. | CMBPR: category-aided Multi-Channel Bayesian personalized ranking for short video recommendation | |
| KR20170114321A (en) | Personalized news contents filtering system and method using the Keyword analysis | |
| CN102957721B (en) | Device and method for classifying users based on identification information | |
| CN103514237A (en) | Method and system for obtaining personalized features of user and file | |
| JP2002063303A (en) | On-line marketing system using grading information | |
| US7890515B2 (en) | Article distribution system and article distribution method used in this system | |
| CN102495867B (en) | Online social network webpage searching method and webpage searching system | |
| CN105159899A (en) | Searching method and searching device |
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 |