CN106202393B - Media information pushing method and device - Google Patents
Media information pushing method and device Download PDFInfo
- Publication number
- CN106202393B CN106202393B CN201610538477.4A CN201610538477A CN106202393B CN 106202393 B CN106202393 B CN 106202393B CN 201610538477 A CN201610538477 A CN 201610538477A CN 106202393 B CN106202393 B CN 106202393B
- Authority
- CN
- China
- Prior art keywords
- media information
- information
- user
- media
- piece
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Abstract
The embodiment of the invention discloses a method and a device for pushing media information, wherein the method for pushing the media information can comprise the following steps: receiving an information push request sent by a client, and acquiring the characteristic information of a user according to a user identifier contained in the information push request; comparing the attribute of each media information with the characteristic information of the user to calculate a first matching value of each media information, and determining the media information of which the first matching value is greater than a preset value as the media information to be analyzed; comparing the historical interaction data of each piece of media information to be analyzed with the characteristic information of the user to calculate a second matching value of each piece of media information to be analyzed, and determining the media information with the highest sum of the first matching value and the second matching value as the media information to be pushed; and pushing the media information to be pushed to the client. The media information pushing method and the media information pushing device can improve the accuracy of information pushing and the effectiveness of information popularization.
Description
Technical Field
The present invention relates to the field of internet technologies, and in particular, to a method and an apparatus for pushing media information.
Background
The network video has been used by most netizens with the characteristics of high definition, watching on demand, watching while stopping and the like, and is not only applied to leisure and entertainment at ordinary times, but also widely applied in work. Meanwhile, in the process of playing network videos, more and more information push services including online advertisement push and the like are provided.
Taking push advertisements as an example, the current methods for pushing advertisements mainly include the following two methods: the first is a basic advertisement delivery method, that is, when an advertisement needs to be played, a server pushes advertisement information to a network video played by a client according to a pre-arranged fixed play list. The other is that the server embeds the pushed advertisement content in the network video of the client after simply analyzing the content label played by the video.
However, the media information push method of the prior art has at least the following disadvantages: the advertisement delivery in the network video does not deliver the advertisement information which is interested by the user according to the preference of the user, so that the excessive disturbance to the user can be caused, sometimes even the dislike of some user groups is caused, and the precision of media information pushing is influenced. In addition, the method can also cause some adverse effects on the network video, such as directly causing the reduction of the user quantity, thereby also greatly reducing the overall advertisement promotion effect.
Disclosure of Invention
The invention provides a media information pushing method and a media information pushing device, which can improve the accuracy of media information pushing and the effectiveness of information popularization.
The technical scheme is as follows:
the invention provides a media information pushing method, which comprises the following steps:
in the process of playing a video by a client, receiving an information push request sent by the client, and acquiring feature information of a user from an attribute library corresponding to the user according to a user identifier contained in the information push request, wherein the feature information of the user is obtained by monitoring and analyzing the video content currently played by the client based on login information of the user, and comprises personal information, interest information and historical consumption data;
comparing the characteristics of each media information with the characteristics of the user with the same type one by one, wherein the number of the compared characteristics is set according to the requirement;
according to the matching degree of the characteristics of each piece of media information and the characteristic information of the user, obtaining a matching score corresponding to the characteristics from a lookup table;
adding the matching scores of all the compared features according to the weights, and dividing the sum by the weights of all the compared features to obtain a first matching value of each piece of media information, wherein the weights of all the features of each piece of media information are set according to the importance of each feature or a sample training mode, and the media information of which the first matching value is greater than a preset value is determined as the media information to be analyzed;
comparing the historical interaction data of each piece of media information to be analyzed with the characteristics of the users with the same type one by one, wherein the number of the compared characteristics is set according to the requirement;
acquiring a matching score corresponding to the characteristic in a query table according to the matching degree of the historical interaction data of each piece of media information to be analyzed and the characteristic information of the user;
adding the matching scores of all the compared features according to the weights, and dividing the sum by the weights of all the compared features to obtain a second matching value of each piece of media information to be analyzed, wherein the weight of each feature in the historical interaction data of each piece of media information to be analyzed is set according to the importance of each feature or a sample training mode, and the media information with the highest sum of the first matching value and the second matching value is determined as the media information to be pushed;
embedding the media information to be pushed into the video played by the client for playing;
if the user clicks the pushed media information, the feature information of the user is stored as the interactive data of the pushed media information;
analyzing all interaction data of the media information to generate new historical interaction data, wherein the new historical interaction data is at least used for comparing with feature information of other users except the user.
The invention also provides a media information pushing device, which comprises:
the request receiving and information obtaining module is used for receiving an information pushing request sent by a client in the process of playing a video by the client, and obtaining the characteristic information of a user from an attribute library corresponding to the user according to a user identifier contained in the information pushing request, wherein the characteristic information of the user is obtained by monitoring and analyzing the video content currently played by the client based on the login information of the user, and comprises personal information, interest information and historical consumption data;
the first calculation and confirmation module is used for comparing the characteristics of each piece of media information with the characteristics of the user in the same type one by one, the number of the compared characteristics is set according to needs, the matching scores corresponding to the characteristics are obtained in a query table according to the matching degree of the characteristics of each piece of media information and the characteristics of the user, the matching scores of all the compared characteristics are added according to weights and divided by the sum of the weights of all the compared characteristics to obtain a first matching value of each piece of media information, wherein the weights of all the characteristics of each piece of media information are set according to the importance of each characteristic or a sample training mode, and the media information of which the first matching value is greater than a preset value is confirmed as the piece of media information to be analyzed;
a second calculation and confirmation module for comparing the historical interaction data of each media information to be analyzed with the characteristics of the users with the same type one by one, and the number of the compared characteristics is set according to the requirement, according to the matching degree of the historical interaction data of each piece of media information to be analyzed and the characteristic information of the user, obtaining the matching scores corresponding to the features from a look-up table, adding the matching scores of all the compared features according to the weight, and dividing the sum by the weights of all the compared features to obtain a second matching value of each media information to be analyzed, the weight of each feature in the historical interaction data of each piece of media information to be analyzed is set according to the importance of each feature or a sample training mode, and the media information with the highest sum of the first matching value and the second matching value is determined as the media information to be pushed;
the pushing module is used for embedding the media information to be pushed into the video played by the client for playing;
the interactive data acquisition module is used for storing the characteristic information of the user as the interactive data of the pushed media information if the user clicks the pushed media information;
and the historical interaction data generation module is used for analyzing all interaction data of the media information to generate new historical interaction data, wherein the new historical interaction data is at least used for comparing with the characteristic information of other users except the user.
In the embodiment of the invention, the media information approximately conforming to the characteristics of the user is preliminarily screened out by comparing the characteristic information of the user with the attributes of the media information, and then the historical interactive data of the part of the media information is compared with the characteristic information of the user, so that the media information conforming to the characteristics of the user is finally and accurately obtained, thereby realizing the accurate pushing of the media information, effectively improving the accuracy of the pushing of the media information and the effectiveness of information popularization, leading the information popularization to be more targeted and effectively improving the video experience of the user.
The foregoing description is only an overview of the technical solutions of the present invention, and in order to make the technical means of the present invention more clearly understood, the technical solutions of the present invention can be implemented according to the content of the description, and in order to make the above-mentioned and other features and advantages of the present invention more clearly understood, the following preferred embodiments are described in detail with reference to the accompanying drawings.
Drawings
Fig. 1 is a flowchart illustrating a media information pushing method according to a first embodiment of the present invention.
Fig. 2 is a flowchart illustrating step 12 of a media information pushing method according to a first embodiment of the present invention.
Fig. 3 is a flowchart illustrating step 13 of a media information pushing method according to a first embodiment of the present invention.
Fig. 4 is a flowchart illustrating a media information pushing method according to a second embodiment of the present invention.
Fig. 5 is a flowchart illustrating a media information pushing method according to a third embodiment of the present invention.
Fig. 6 is a schematic structural diagram of a media information pushing apparatus according to a fourth embodiment of the present invention.
Fig. 7 is a schematic structural diagram of a first calculation and confirmation module according to a fourth embodiment of the present invention.
Fig. 8 is a schematic structural diagram of a second calculation and confirmation module according to a fourth embodiment of the present invention.
Fig. 9 is a schematic structural diagram of a media information pushing apparatus according to a fifth embodiment of the present invention.
Fig. 10 is a schematic structural diagram of a media information pushing apparatus according to a sixth embodiment of the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention adopted to achieve the predetermined objects, the following detailed description of the embodiments, structures, features and effects of the media information pushing method and device according to the present invention will be made with reference to the accompanying drawings and preferred embodiments.
The foregoing and other technical and scientific aspects, features and advantages of the present invention will be apparent from the following detailed description of preferred embodiments, which is to be read in connection with the accompanying drawings. While the present invention has been described in connection with the preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but is intended to cover various modifications, equivalent arrangements, and specific embodiments thereof.
First embodiment
Fig. 1 is a flowchart illustrating a media information pushing method according to a first embodiment of the present invention. The embodiment of the invention is applied to the following scenes: when a user opens a certain video at a network video client or watches the certain video, namely the network video is being played, the network video server pushes media information (such as advertisements) to the client according to the acquired user characteristic information, if the pushed media information is the media information which is more interesting to the user, the user can click the media information, and if the user is satisfied with commodities in the media information, the user can select to purchase the commodities, so that the accuracy of information pushing and the effectiveness of information popularization can be improved.
Based on the application scenario, referring to fig. 1, the media information pushing method of the present embodiment may include the following steps 11 to 14.
The client may be, for example, a video client or an audio client, and the information push request is used to indicate a need for acquiring media information to the server, where the user identifier is, for example, an ID generated when a user registers an account, or an ID allocated by the server when the client is installed.
The characteristic information of the user may include personal information and interest information of the user. The personal information may be personal information registered in a user interaction platform provided by the third-party software, such as basic information of the user, such as age, sex, academic history, location, place of birth, hobby and the like, and may also be personal basic information contained in a social account when the user logs in a network video website with the social account, such as a QQ or a micro signal. Further, the type of the personal information obtained by the server may be set as desired, for example, at least the age, sex and school calendar of the user may be obtained. The interest information may be interest information of the user obtained by monitoring and analyzing video content currently played by the client, the interest information may be a tag corresponding to the video content, such as an automobile, sports, beauty, real estate, travel, digital, music, animation, games, sports, friends making, reading, military affairs, finance, literature, food, and the like, and the server stores the tag of the video content each time the user plays the video.
The characteristic information can jointly construct an attribute library corresponding to each user, and the server acquires the corresponding characteristic information from the attribute library according to the user identification contained in the information pushing request.
And step 12, comparing the attributes of the media information with the characteristic information of the user to calculate a first matching value of the media information, and determining the media information of which the first matching value is greater than a preset value as the media information to be analyzed.
The media information is data which is pre-made and stored in the server, the attribute of the media information is, for example, the age, sex, school calendar, location, place of birth, interest and the like of a promotion object of the media information, the age and the school calendar can be intervals, for example, 20-40 years old, primary school-subject, and the interest can include at least one of automobile, sports, beauty, real estate, travel, digital, music, cartoon, game, sports, dating, book reading, military affairs, finance, literature and food.
Referring to fig. 2, in an embodiment of the present invention, step 12 may specifically include:
and step 21, comparing the attributes of the media information with the same characteristics of the characteristic information of the user one by one.
The same feature refers to a feature that the attribute of the media information is the same as the type in the feature information of the user, for example, between the age of the user and the age of the media information promotion object, between the gender of the user and the gender of the media information promotion object, between the academic calendar of the user and the academic calendar of the media information promotion object, and between the interest information of the user and the interest of the media information promotion object. Further, the number and types of features to be compared can be set according to the needs, for example, 4 features are set, and the 4 features are set as age, gender, academic history and interests.
And step 22, acquiring a matching score corresponding to the characteristics according to the matching degree of the comparison.
The matching degree refers to the degree of coincidence between the characteristic information of the user and each attribute of the media information, and a query table of the matching degree and the matching score can be stored in the server, so that query can be performed according to the matching degree to obtain the corresponding matching score. For example, the age of the media information popularization object is 20-30 years, if the age of the user is within the interval range, the obtained matching score is 1, otherwise, the obtained matching score is 0; the gender of the media information popularization object is male, if the gender of the user is male, the obtained matching score is 1, otherwise, the obtained matching score is 0; the interest of the media information popularization object is automobile, sports, beauty and real estate, the interest information of the user is automobile, sports and music, and the obtained matching score is 0.6. By analogy, the matching score of each attribute in the media information can be obtained.
And step 23, adding the matching score weights of all the compared features to obtain a first matching value of each piece of media information.
The weights of the attributes in the media information may be set in advance according to the importance of each attribute or a sample training mode, and the weights of the attributes may be equal or different.
In one embodiment, the formula for calculating the first matching value may be:
wherein S is1Is the first matching value of a piece of media information, λ i is the weight of the ith attribute in the media information, m is the number of the attributes in the media information, Wi is the mediaAnd matching score of the ith attribute in the volume information, wherein n is the sum of weights of all attributes in the media information, and i, n and m are integers greater than 1.
For example, if the age of a media information popularization object is 20-30 years old, the gender is male, the interest is automobile, sports, beauty treatment and real estate, the age of a user is 25, the gender is male, the interest information is automobile, sports and music, wherein the weights of the age, the gender and the interest are 0.2, 0.4 and 0.4 respectively, and the media information popularization object is obtained according to the formula
Calculating to obtain the first matching value S of the piece of media information1＝(0.2*1+0.4*1+0.4*0.6)/(0.2+0.4+0.4)＝0.84。
And step 24, confirming the media information with the first matching value larger than the preset value as the media information to be analyzed.
The preset value may be a preset fixed value, or a value corresponding to the media information that can obtain N top ranked (N > 1) names and is obtained automatically by the server sorting the calculation results of the first matching value.
The media data to be analyzed is preliminarily screened media information approximately conforming to the characteristics of the user, and the media information is filtered according to the characteristic information (such as personal information and interest information) of the user, so that the media information conforming to the characteristics of the user can be obtained to a certain extent.
And step 13, comparing the historical interaction data of each piece of media information to be analyzed with the characteristic information of the user to calculate a second matching value of each piece of media information to be analyzed, and determining the media information with the highest sum of the first matching value and the second matching value as the media information to be pushed.
The historical interactive data may be obtained, for example, in such a manner that if the user clicks the pushed media information, the feature information of the user is stored as the interactive data of the pushed media information, and all the interactive data of the piece of media information are analyzed to generate the historical interactive data of the piece of media information, such as age group distribution, gender ratio, interest tag distribution, and the like of the interactive crowd of the media information.
Referring to fig. 3, in an embodiment of the present invention, step 13 may specifically include:
and step 31, comparing the historical interaction data of each piece of media information to be analyzed with the same characteristics of the characteristic information of the user one by one.
The same feature refers to a feature of the same type in the historical interaction data and the feature information of the user, such as between the age of the user and the age group distribution in the historical interaction data of the media information, between the gender of the user and the gender ratio in the historical interaction data of the media information, and between the interest information of the user and the interest label distribution in the historical interaction data of the media information. Further, the number and type of features to be compared can be set according to the needs, for example, 3 features, where the 3 features are set as age, gender and interest.
And step 32, acquiring a matching score corresponding to the characteristic according to the matching degree of the comparison.
The matching degree refers to the degree of coincidence between the characteristic information of the user and the historical interaction data of the media information, and a query table of the matching degree and the matching score can be stored in the server, so that the server can perform query according to the matching degree to obtain the corresponding matching score. For example, the age in the media information historical interaction data is 20 to 60 years, wherein the number of users in the age range of 30 to 40 years is large, if the age of the user is in the range of 30 to 40 years, the obtained matching score is 1, if the age of the user is not in the range of 20 to 60 years, the obtained matching score is 0, and if the age of the user is in the range of 20 to 30 years or 40 to 60 years, the obtained matching score is 0.5, for example; the sex ratio in the media information historical interaction data is 60% for male and 40% for female, if the sex of the user is male, the obtained matching score is 0.6, otherwise, the obtained matching score is 0.4; the interest labels in the media information historical interactive data are distributed to automobiles, sports, beauty and real estate, and the interest information of the user is the automobiles, the sports and the music, so that the obtained matching score is 0.6. By analogy, the matching score corresponding to each feature in the historical interaction data can be obtained.
And step 33, adding the matching score weights of all the compared features to obtain a second matching value of each piece of media information to be analyzed.
The weights of the features in the media information historical interactive data can be set in advance according to the importance of each feature or a sample training mode, and the weights of the features can be equal or different.
In one embodiment, the formula for calculating the second matching value may be:
wherein S is2The second matching value of a piece of media information is obtained, λ j is the weight of the jth feature in the media information history interactive data, m is the number of features in the media information history interactive data, Wj is the matching score of the jth feature in the media information history interactive data, n is the sum of the weights of all features in the media information history interactive data, and j, n and m are integers greater than 1.
For example, the age group distribution in one piece of media information history interactive data is 20 to 60 years old, wherein the number of users in 30 to 40 years old is large, the gender ratio in the media information history interactive data is 60% for male and 40% for female, the interest tag distribution in the media information history interactive data is automobile, sports, beauty and real estate, the age of the user is 35 years old, the gender of the user is male, the interest information of the user is automobile, sports and music, wherein the weights of the age group distribution, the gender ratio and the interest tag distribution are 0.4, 0.4 and 0.2 respectively, and the weights are calculated according to a formula
Calculating to obtain a second matching value S of the piece of media information2＝(0.4*1+0.4*0.6+0.2*0.6)/(0.2+0.4+0.4)＝0.76。
And step 34, determining the media information with the highest sum of the first matching value and the second matching value as the media information to be pushed.
The sum of the first matching value and the second matching value may be calculated by adding weights, and the weights of the first matching value and the second matching value may be equal to or different from each other. It is understood that there is only one or more possibilities for the highest summed media information, and in one embodiment, if there is one highest summed media information, the media information is pushed directly, and if there are more highest summed media information, the media information can be pushed separately in a time period.
In this case, historical interactive data of the comprehensive media information is further analyzed to finally determine the delivered media information, so that the accuracy of pushing the media information can be improved, the information pushing is more targeted, and the video experience of a user is effectively improved.
And step 14, pushing the media information to be pushed to the client.
In this embodiment, the media information to be pushed is embedded into the video played by the client for playing, so as to facilitate the user to watch.
In summary, according to the media information pushing method provided by the embodiment of the present invention, the attribute of the user characteristic information is compared with the attribute of the media information, so as to preliminarily screen the media information approximately conforming to the user characteristic, and then the historical interaction data of the part of the media information is compared with the characteristic information of the user, so as to finally and accurately obtain the media information conforming to the user characteristic, thereby implementing accurate pushing of the media information, effectively improving the accuracy of media information pushing and the effectiveness of information popularization, enabling information popularization to be more targeted, and effectively improving the video experience of the user.
Second embodiment
Fig. 4 is a flowchart illustrating a media information pushing method according to a second embodiment of the present invention. Referring to fig. 4, the main difference between the second embodiment and the first embodiment is that, before step 11, the method further includes:
and step 41, acquiring and storing the personal information contained in the login account of the user.
The personal information is characteristic information of the user, the personal information may be personal information registered in a user interaction platform provided by the user based on third-party software, such as basic information of the user, such as age, sex, academic calendar, location, place of birth, hobby and the like, and may also be personal basic information contained in a social account when the user logs in a network video website with the social account, such as a QQ or a micro signal and the like. And the server acquires the personal information of the user and detects and updates regularly when the user logs in the client. Further, the type of the personal information obtained by the server may be set as desired, for example, at least the age, sex and school calendar of the user may be obtained.
And 42, monitoring the video content currently played by the client and analyzing the attribute of the video content to obtain and store the interest information of the user.
The interest information is characteristic information of the user, when the user plays a video at the client, the server monitors and analyzes the video content currently played at the client to obtain interest information of the user, the interest information can be labels corresponding to the video content, such as an automobile, sports, beauty, real estate, travel, digital codes, music, animation, games, sports, friends making, book reading, military, finance, literature, food and the like, and the labels of the video content can be stored and updated by the server when the user plays the video each time.
It is understood that the feature information of the user may further include historical consumption data, and the historical consumption data may be obtained, for example, in such a manner that, if it is detected that the user performs a payment operation related to the pushed media information, the payment data and the attribute of the media information are stored as consumption data of the user in a corresponding manner, and all consumption data of the user are analyzed to form historical consumption data, which may be, for example, a corresponding relationship between a consumption amount and an interest tag, and a corresponding relationship between a payment number and an interest tag.
In summary, according to the media information pushing method provided by the embodiment of the present invention, the media information approximately conforming to the user characteristics is preliminarily screened by comparing the characteristic information of the user with the attributes of the media information, and then the historical interaction data of the part of the media information is compared with the characteristic information of the user, so as to finally and accurately obtain the media information conforming to the user characteristics, thereby implementing accurate pushing of the media information, effectively improving the accuracy of media information pushing and the effectiveness of information promotion, making information promotion more targeted, and effectively improving the video experience of the user.
Third embodiment
Fig. 5 is a flowchart illustrating a media information pushing method according to a third embodiment of the present invention. Referring to fig. 5, the main difference between the third embodiment and the first embodiment is that step 14 further includes:
After the media information is pushed to the client, the user can see the media information in a playing interface of the video and click the media information to check according to needs, and at the moment, if the user clicks the pushed media information, the characteristic information of the user is stored as the interactive data of the pushed media information.
The same piece of media information can be pushed to different users, so that one piece of media information can have interaction information corresponding to different users, and historical interaction data of the piece of media information, such as age group distribution, gender ratio and interest tag distribution of interaction crowd of the piece of media information, can be generated by analyzing all interaction data of the piece of media information.
In summary, according to the media information pushing method provided by the embodiment of the present invention, the interactive data of the pushed media information is obtained and analyzed to obtain the historical interactive data, so that the historical interactive data of the media information can be further analyzed after the initial screening to determine the media information to be finally delivered, thereby further improving the accuracy of media information pushing, making the information pushing more targeted, and effectively improving the video experience of the user.
The following are embodiments of the apparatus of the present invention, details of which are not described in detail in the embodiments of the apparatus, and reference may be made to the corresponding embodiments of the method described above.
Fourth embodiment
Fig. 6 is a schematic structural diagram of a media information pushing apparatus according to a fourth embodiment of the present invention. The media information pushing device can be arranged on a server. Referring to fig. 6, the media information pushing apparatus includes a request receiving and information obtaining module 61, a first calculating and confirming module 62, a second calculating and confirming module 63, and a pushing module 64.
The request receiving and information obtaining module 61 is configured to receive an information push request sent by a client, and obtain feature information of a user according to a user identifier included in the information push request.
The first calculating and confirming module 62 is configured to compare the attribute of each piece of media information with the feature information of the user to calculate a first matching value of each piece of media information, and confirm the piece of media information of which the first matching value is greater than a preset value as the piece of media information to be analyzed. Referring to fig. 7, in the present embodiment, the first calculating and confirming module 62 includes a comparing unit 71, a score obtaining unit 72, a first matching value generating unit 73 and a confirming unit 74, where the comparing unit 71 is configured to compare attributes of each piece of media information with features of the user, the score obtaining unit 72 is configured to obtain matching scores corresponding to the features according to matching degrees of the comparison, the first matching value generating unit 73 adds matching score weights of all the compared features to obtain a first matching value of each piece of media information, and the confirming unit 74 is configured to confirm the piece of media information of which the first matching value is greater than a preset value as the piece of media information to be analyzed.
And a second calculating and confirming module 63, which is configured to compare the historical interaction data of each piece of media information to be analyzed with the feature information of the user to calculate a second matching value of each piece of media information to be analyzed, and confirm the media information with the highest sum of the first matching value and the second matching value as the piece of media information to be pushed. Referring to fig. 8, in this embodiment, the second calculating and confirming module 63 includes a comparing unit 81, a score obtaining unit 82, a second matching value generating unit 83 and a confirming unit 84, where the comparing unit 81 is configured to compare the same features between the historical interaction data of each piece of media information to be analyzed and the feature information of the user one by one, the score obtaining unit 82 is configured to obtain matching scores corresponding to the features according to matching degrees of the comparison, the second matching value generating unit 83 is configured to add the matching score weights of all the compared features to obtain a second matching value of each piece of media information to be analyzed, and the confirming unit 84 confirms the media information with the highest sum of the first matching value and the second matching value as the piece of media information to be pushed.
For a detailed process of implementing each function by each functional module of the media information pushing apparatus in this embodiment, please refer to the detailed description about fig. 1-3 in the first embodiment, which is not described herein again.
In summary, the media information pushing device provided in the embodiment of the present invention primarily screens media information approximately conforming to the user characteristics by comparing the characteristic information of the user with the attributes of the media information, and then compares the historical interaction data of the part of media information with the characteristic information of the user, so as to finally and accurately obtain the media information conforming to the user characteristics, thereby implementing accurate pushing of the media information, effectively improving the accuracy of media information pushing and the effectiveness of information popularization, making information popularization more targeted, and effectively improving the video experience of the user.
Fifth embodiment
Fig. 9 is a schematic structural diagram of a media information pushing apparatus according to a fifth embodiment of the present invention. Referring to fig. 9, the main difference between the fifth embodiment and the fourth embodiment is that the media information pushing device may further include a personal information obtaining module 91 and an interest information obtaining module 92.
And the personal information obtaining module 91 is configured to obtain and store the personal information included in the login account of the user. And the interest information obtaining module 92 is configured to monitor the video content currently played by the client and analyze the attribute of the video content, so as to obtain and store the interest information of the user.
Further, the media information pushing device may further include a consumption data generation module, where the consumption data generation module is configured to, if it is monitored that the user performs a payment operation related to the pushed media information, store payment data and an attribute of the media information as consumption data of the user correspondingly.
For a detailed process of implementing each function by each functional module of the media information pushing apparatus in this embodiment, please refer to the detailed description about fig. 4 in the second embodiment, which is not described herein again.
In summary, the media information pushing device provided in the embodiment of the present invention primarily screens media information that approximately conforms to the user characteristics by comparing the characteristic information of the user with the attributes of the media information, and then compares the historical interaction data of the part of media information with the characteristic information of the user, so as to finally and accurately obtain the media information that conforms to the user characteristics, thereby implementing accurate pushing of the media information, effectively improving the accuracy of media information pushing and the effectiveness of information promotion, making information promotion more targeted, and effectively improving the video experience of the user.
Sixth embodiment
Fig. 10 is a schematic structural diagram of a media information pushing apparatus according to a sixth embodiment of the present invention. Referring to fig. 10, the main difference between the sixth embodiment and the fourth embodiment is that the media information pushing device may further include an interactive data obtaining module 101 and a historical interactive data generating module 102.
An interactive data obtaining module 101, configured to store the feature information of the user as interactive data of the pushed media information if the user clicks the pushed media information. A historical interaction data generation module 102, configured to analyze all interaction data of the media information to generate historical interaction data of the media information.
For a detailed process of implementing each function by each functional module of the media information pushing apparatus in this embodiment, please refer to the detailed description about fig. 5 in the third embodiment, which is not described herein again.
In summary, the media information pushing device provided in the embodiment of the present invention obtains the interactive data of the pushed media information and analyzes the interactive data to obtain the historical interactive data, so that the historical interactive data of the media information can be further analyzed after the initial screening to determine the media information to be finally delivered, thereby further improving the accuracy of pushing the media information, making the information pushing more targeted, and effectively improving the video experience of the user.
Although the present invention has been described with reference to a preferred embodiment, it should be understood that various changes, substitutions and alterations can be made herein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (9)
1. A method for pushing media information, comprising:
in the process of playing a video by a client, receiving an information push request sent by the client, and acquiring feature information of a user from an attribute library corresponding to the user according to a user identifier contained in the information push request, wherein the feature information of the user is obtained by monitoring and analyzing the video content currently played by the client based on login information of the user, and comprises personal information, interest information and historical consumption data;
comparing the characteristics of each media information with the characteristics of the user with the same type one by one, wherein the number of the compared characteristics is set according to the requirement;
according to the matching degree of the characteristics of each piece of media information and the characteristic information of the user, obtaining a matching score corresponding to the characteristics from a lookup table;
adding the matching scores of all the compared features according to the weights, and dividing the sum by the weights of all the compared features to obtain a first matching value of each piece of media information, wherein the weights of all the features of each piece of media information are set according to the importance of each feature or a sample training mode, and the media information of which the first matching value is greater than a preset value is determined as the media information to be analyzed;
comparing the historical interaction data of each piece of media information to be analyzed with the characteristics of the users with the same type one by one, wherein the number of the compared characteristics is set according to the requirement;
acquiring a matching score corresponding to the characteristic in a query table according to the matching degree of the historical interaction data of each piece of media information to be analyzed and the characteristic information of the user;
adding the matching scores of all the compared features according to the weights, and dividing the sum by the weights of all the compared features to obtain a second matching value of each piece of media information to be analyzed, wherein the weight of each feature in the historical interaction data of each piece of media information to be analyzed is set according to the importance of each feature or a sample training mode, and the media information with the highest sum of the first matching value and the second matching value is determined as the media information to be pushed;
embedding the media information to be pushed into the video played by the client for playing;
if the user clicks the pushed media information, the feature information of the user is stored as the interactive data of the pushed media information;
analyzing all interaction data of the media information to generate new historical interaction data, wherein the new historical interaction data is at least used for comparing with feature information of other users except the user.
2. The media information pushing method according to claim 1, further comprising:
acquiring and storing personal information contained in the login account of the user;
and monitoring the video content currently played by the client and analyzing the attribute of the video content to obtain and store the interest information of the user.
3. The method according to claim 2, wherein the personal information includes at least an age and a gender of the user.
4. The media information pushing method according to claim 2, wherein the attribute of the video content is a tag of the video content.
5. The method of claim 1, wherein the historical interaction data of the media information comprises age distribution, gender ratio and interest tag distribution of the interactive crowd of the media information.
6. The method for pushing media information according to claim 1, further comprising, after the step of pushing the media information to be pushed to the client:
and if the payment operation related to the pushed media information is detected to be executed by the user, correspondingly storing payment data and the attribute of the media information as consumption data of the user.
7. A media information pushing apparatus, comprising:
the request receiving and information obtaining module is used for receiving an information pushing request sent by a client in the process of playing a video by the client, and obtaining the characteristic information of a user from an attribute library corresponding to the user according to a user identifier contained in the information pushing request, wherein the characteristic information of the user is obtained by monitoring and analyzing the video content currently played by the client based on the login information of the user, and comprises personal information, interest information and historical consumption data;
the first calculation and confirmation module is used for comparing the characteristics of each piece of media information with the characteristics of the user in the same type one by one, the number of the compared characteristics is set according to needs, the matching scores corresponding to the characteristics are obtained in a query table according to the matching degree of the characteristics of each piece of media information and the characteristics of the user, the matching scores of all the compared characteristics are added according to weights and divided by the sum of the weights of all the compared characteristics to obtain a first matching value of each piece of media information, wherein the weights of all the characteristics of each piece of media information are set according to the importance of each characteristic or a sample training mode, and the media information of which the first matching value is greater than a preset value is confirmed as the piece of media information to be analyzed;
a second calculation and confirmation module for comparing the historical interaction data of each media information to be analyzed with the characteristics of the users with the same type one by one, and the number of the compared characteristics is set according to the requirement, according to the matching degree of the historical interaction data of each piece of media information to be analyzed and the characteristic information of the user, obtaining the matching scores corresponding to the features from a look-up table, adding the matching scores of all the compared features according to the weight, and dividing the sum by the weights of all the compared features to obtain a second matching value of each media information to be analyzed, the weight of each feature in the historical interaction data of each piece of media information to be analyzed is set according to the importance of each feature or a sample training mode, and the media information with the highest sum of the first matching value and the second matching value is determined as the media information to be pushed;
the pushing module is used for embedding the media information to be pushed into the video played by the client for playing;
the interactive data acquisition module is used for storing the characteristic information of the user as the interactive data of the pushed media information if the user clicks the pushed media information;
and the historical interaction data generation module is used for analyzing all interaction data of the media information to generate new historical interaction data, wherein the new historical interaction data is at least used for comparing with the characteristic information of other users except the user.
8. The media information pushing apparatus according to claim 7, wherein the media information pushing apparatus further comprises:
the personal information acquisition module is used for acquiring and storing personal information contained in the login account of the user;
and the interest information acquisition module is used for monitoring the video content currently played by the client and analyzing the attribute of the video content to obtain and store the interest information of the user.
9. The media information pushing apparatus according to claim 7, further comprising:
and the consumption data generation module is used for correspondingly storing the payment data and the attribute of the media information as the consumption data of the user if the payment operation related to the pushed media information executed by the user is monitored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610538477.4A CN106202393B (en) | 2016-07-08 | 2016-07-08 | Media information pushing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610538477.4A CN106202393B (en) | 2016-07-08 | 2016-07-08 | Media information pushing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106202393A CN106202393A (en) | 2016-12-07 |
| CN106202393B true CN106202393B (en) | 2021-03-19 |
Family
ID=57474048
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610538477.4A Active CN106202393B (en) | 2016-07-08 | 2016-07-08 | Media information pushing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106202393B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108259529A (en) * | 2016-12-28 | 2018-07-06 | 深圳市优朋普乐传媒发展有限公司 | A kind of acquisition methods and device of page sharing information |
| CN107566896B (en) * | 2017-08-17 | 2022-02-11 | 上海擎感智能科技有限公司 | Multimedia information recommendation method and device, storage medium and terminal |
| CN108255992A (en) * | 2017-12-29 | 2018-07-06 | 广州贝睿信息科技有限公司 | It is a kind of paint originally can be readability assessment recommend method |
| CN111309923B (en) * | 2020-01-22 | 2023-01-03 | 腾讯科技（深圳）有限公司 | Object vector determination method, model training method, device, equipment and storage medium |
| CN111723237B (en) * | 2020-06-12 | 2023-06-02 | 腾讯科技（深圳）有限公司 | Media content access control method |
| CN112417302B (en) * | 2020-12-08 | 2021-06-04 | 六晟信息科技(杭州)有限公司 | Big data-based information content intelligent analysis recommendation processing system |
| CN116501972B (en) * | 2023-05-06 | 2024-01-05 | 广州市巨应信息科技有限公司 | Content pushing method and AI intelligent pushing system based on big data online service |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150066685A1 (en) * | 2013-09-03 | 2015-03-05 | muse IQ, LLC | System and method for digital content discovery, recommendations and purchasing |
| CN104572688A (en) * | 2013-10-17 | 2015-04-29 | 腾讯科技（深圳）有限公司 | Information push method and device |
| CN104753929A (en) * | 2015-03-17 | 2015-07-01 | 三星电子（中国）研发中心 | Content pushing method, server, terminal and system |
| CN105005576B (en) * | 2015-03-27 | 2018-03-09 | 合一信息技术（北京）有限公司 | A kind of video website similar users search system and method |
| CN105681830A (en) * | 2016-02-06 | 2016-06-15 | 优住（北京）科技股份公司 | Advertisement playing system and playing platform based on interest points of user |
-
2016
- 2016-07-08 CN CN201610538477.4A patent/CN106202393B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106202393A (en) | 2016-12-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106202393B (en) | Media information pushing method and device | |
| CN107832437B (en) | Audio/video pushing method, device, equipment and storage medium | |
| CA2858992C (en) | Video recommendation based on video co-occurrence statistics | |
| CN107590689B (en) | Advertisement data recommendation method and system | |
| JP2018198079A (en) | System and method for directing content to user of social networking engine | |
| US20120130805A1 (en) | Selecting media advertisements for presentation based on their predicted playtimes | |
| US20140244400A1 (en) | Systems and methods for social advertisement syndication | |
| CN107808295B (en) | Multimedia data delivery method and device | |
| US8725559B1 (en) | Attribute based advertisement categorization | |
| US20090037967A1 (en) | Video upload system | |
| TW201520936A (en) | User engagement-based contextually-dependent automated pricing for non-guaranteed delivery | |
| EP2743874A1 (en) | Targeting objects to users based on search results in an online system | |
| CN105608125B (en) | Information processing method and server | |
| US20140122504A1 (en) | Systems and Methods for Collection and Automatic Analysis of Opinions on Various Types of Media | |
| US20160036939A1 (en) | Selecting Content for Simultaneous Viewing by Multiple Users | |
| US20150142584A1 (en) | Ranking content based on member propensities | |
| WO2010127150A2 (en) | Targeting advertisements to videos predicted to develop a large audience | |
| US20220414716A1 (en) | Managing metadata enrichment of digital asset portfolios | |
| WO2016125166A1 (en) | Systems and methods for analyzing video and making recommendations | |
| US11308135B2 (en) | Data prioritization through relationship analysis mapping | |
| US20150227970A1 (en) | System and method for providing movie file embedded with advertisement movie | |
| JP2015060467A (en) | Service provision device, service provision method, and service provision program | |
| CN114630194B (en) | Bullet screen jump linking method, system, equipment and computer readable storage medium | |
| US20230351442A1 (en) | System and method for determining a targeted creative from multi-dimensional testing | |
| CN116228320B (en) | Live advertisement putting effect analysis system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |