CN110602531B - System for recommending advertisements to smart television - Google Patents
System for recommending advertisements to smart television Download PDFInfo
- Publication number
- CN110602531B CN110602531B CN201910805866.2A CN201910805866A CN110602531B CN 110602531 B CN110602531 B CN 110602531B CN 201910805866 A CN201910805866 A CN 201910805866A CN 110602531 B CN110602531 B CN 110602531B
- Authority
- CN
- China
- Prior art keywords
- advertisement
- data
- advertisements
- information
- service
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0251—Targeted advertisements
- G06Q30/0255—Targeted advertisements based on user history
-
- 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
-
- 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
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
-
- 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
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
- H04N21/25891—Management of end-user data being end-user preferences
-
- 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
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26208—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists the scheduling operation being performed under constraints
- H04N21/26241—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists the scheduling operation being performed under constraints involving the time of distribution, e.g. the best time of the day for inserting an advertisement or airing a children program
-
- 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/81—Monomedia components thereof
- H04N21/812—Monomedia components thereof involving advertisement data
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Graphics (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a system for recommending advertisements to a smart television, which is characterized in that user portrait data generated by a big data technology is combined with label information pre-printed in advertisement information, an artificial intelligence technology-a personalized recommendation algorithm based on the user portrait data is used for calculating matched advertisements, recommended advertisements in a near period of time are filtered by a filtering algorithm and are sorted according to weight values, a recommendation result set is finally obtained, the advertisements which are sorted first in the result set are selected and recommended to a smart television terminal, and the method is used for accurately releasing the advertisements.
Description
Technical Field
The invention relates to the technical field of intelligent televisions, in particular to a system for recommending advertisements to an intelligent television.
Background
Along with the popularization of the smart television, more and more advertisers are willing to put advertisements on the smart television, and the advertisement putting at the television terminal is either too wide in range and low in cost performance, or limited by audience rating and low in user acceptance rate, or the advertisement conversion rate is low because the television live broadcast advertisement has fixed time and the user changes channels when playing the advertisement;
the existing accurate advertisement putting method mainly has 3 categories: :
the method has the advantages that the method carries out word segmentation processing on basic information of live television programs and advertisements, then carries out one-to-many matching by using an algorithm, and carries out recommendation on advertisements according to the live television programs, and has the defects that the correlation quantity of advertisement contents and the live television program contents is not large or the advertisement contents and the live television program contents are correlated in time and are also fuzzy, the delivery precision is not enough, the correlation relation between the advertisements and the live television programs needs to be maintained, and meanwhile, the method is in conflict with the benefits of large advertisers;
the method comprises the steps of associating advertisements with videos, and when a user plays the videos, inquiring the advertisements associated with the videos by using the obtained video information to accurately push the advertisements, wherein the defects that the advertisement content and the video program content can be associated in a small amount or are associated in time and are also fuzzy, the delivery precision is insufficient, and the association relationship between the advertisements and the video programs needs to be maintained;
the method comprises the steps of associating advertisements with advertisements, using the viewing history of a user, analyzing favorite scores of the advertisements in the history, and recommending similar advertisements, wherein the defects that although the advertisements which the user probably likes are obtained, the advertisements are recommended like e-commerce recommendation, the advertisements are all the same type of advertisements within a period of time, and the user feels dislike easily;
in order to facilitate advertisers to put advertisements to television users, avoid the cost problem caused by large-scale putting and improve the putting efficiency and the receiving rate of the advertisements, the invention provides a system for recommending the advertisements to a smart television.
Disclosure of Invention
Aiming at the problems, the invention provides a system for recommending advertisements to a smart television, which uses a more precise method for advertisement delivery, through the user portrait data generated by the big data technology and the label information pre-printed in the advertisement information, the matched advertisement is calculated by using the artificial intelligence technology-the personalized recommendation algorithm based on the user portrait data, the recommended advertisement in the near period is filtered by the filtering algorithm and sorted according to the weight value, finally, a recommendation result set is obtained, the advertisement with the first order in the result set is selected and recommended to the intelligent television terminal, the method is used for accurately delivering the advertisement, to the operation personnel, only need maintain the label of advertisement, reduced operation work load greatly, to advertisement release merchant, greatly promoted the input accuracy of advertisement, the acceptance rate promotes the input price/performance ratio of advertisement. According to the invention, the advertisement can be accurately delivered to the intelligent television terminals of the corresponding user group and displayed to the users only by marking the advertisement with the label within the specified range.
The invention realizes the purpose through the following technical scheme:
a system for recommending advertisements for smart televisions, comprising:
an advertising management platform; after the advertisement management platform detects the change of the advertisement information, calling a data cache center component to update the advertisement information in the cache: it includes the following modules:
the advertisement information storage service is used for editing and storing advertisement video url address information, introduction information and labels;
the advertisement information inquiry service displays the basic information of the advertisement, and the upper and lower line states, the purchase and delivery times and the delivered times are displayed;
an advertisement information deletion service;
an advertisement information modification service;
the advertisement examination service is used for watching the advertisement content by an administrator and examining the validity of the advertisement;
the advertisement online and offline service is used for editing advertisement putting times and controlling whether the advertisement is put or not;
a data cache center; the data cache center comprises 5 components, and updates data regularly every day, and can also call the updated data manually:
the portrait data caching component caches the terminal mac and corresponding portrait data by using a key-value data format, and provides a service for inquiring portrait information through a mac address to the outside;
the advertisement data caching component caches the advertisement information by using a key-value data format and provides a service of inquiring the advertisement information by using the id;
the tag-advertisement matching information caching component caches tag-advertisement matching information by using a key-value data format, provides a service for querying the associated advertisement through a tag, modifies the associated advertisement through the tag, and rejects the service of the advertisement under the tag according to the tag and the advertisement id;
the advertisement booking delivery times caching component is used for caching advertisement booking delivery times data by using a key-value data format and providing query service;
the advertisement delivery times cache component caches the advertisement delivery times by using a key-value data format, provides the advertisement delivery times for external calling, operates in a thread safety mode every time, acquires the advertisement delivery times through an advertisement id, defaults to 0 if the advertisement delivery times are not acquired, adds the advertisement delivery times into a cache, acquires the reserved delivery times in an advertisement preset delivery times cache component through the advertisement id, subtracts the delivery times added with 1 from the reserved delivery times, feeds back a success code if the advertisement delivery times are greater than or equal to 0, feeds back an execution failure code if the advertisement delivery times are less than 0 or less than 0, stores the delivery times into a database, calls a region-advertisement matching information cache component to remove the service of the advertisement in the region according to the region and the advertisement id to remove the advertisement, and self-removes the delivery times cache after the advertisement delivery times are successful;
the method comprises the steps that a cache component for advertisements released by a user caches the advertisements released by the user by using a key-value data format for algorithm query, the cache can set expiration time, cache data of mac are refreshed after the expiration time is up, and the component provides service for querying the released advertisements and service for updating data according to the mac;
a personalized recommendation algorithm platform; the personalized recommendation algorithm platform comprises two sub-platforms, which are respectively as follows:
recommending a cloud platform: for receiving requests and feeding back advertisement data, comprising:
receiving an advertisement recommendation request, and verifying the validity of parameters in the request;
taking a mac address request recommendation algorithm platform to obtain a recommendation result;
calling an advertisement putting time cache component to update the put times;
if the success code is obtained, inquiring specific advertisement information through the inquiry advertisement information cache component, assembling the specific advertisement information into data available for the terminal according to a data protocol with the terminal, feeding the data back to the terminal, calling the released advertisement cache component of the user at the same time, and adding the advertisement id into the released advertisement data of the user;
if the failure code is acquired, re-executing the request from the step II;
a recommendation algorithm platform: based on artificial intelligence technology, using a technology based on a deep learning algorithm-personalized recommendation algorithm to aim at a single mac to produce recommendation results, and processing logic, wherein the processing logic comprises the following steps:
after receiving a request with a mac address;
loading the user portrait of the user in a portrait data cache component according to the mac address;
loading all advertisement candidate set information from the tag-advertisement matching information cache component;
loading the information of the mac delivered advertisement from the user delivered advertisement cache component;
based on a deep learning recommendation algorithm, analyzing user portrait labels by using a user portrait of the mac address, performing weight sorting on the labels to obtain a plurality of labels with higher weights, then obtaining advertisement data corresponding to the labels by using the labels, filtering output data by using the advertisements delivered by the mac, filtering the delivered advertisements, sorting the advertisement data according to the label weight algorithm, obtaining advertisement id ranked first after sorting, and feeding the advertisement id to a recommendation cloud platform;
a data warehouse; the data warehouse is used for storing data of the system.
Further, the system requests and displays the method at the television terminal as follows:
after the television terminal is started and accessed to a network, an advertisement recommending service request is immediately carried out, and recommended advertisements are obtained and displayed and can be used for displaying fixed advertisement positions;
in the time period from the time when the television terminal is started to access the network to the time when the television terminal is turned off, requesting an advertisement recommendation service at random time to obtain recommended advertisements, wherein the recommended advertisements can be used for showing the television starting advertisements;
when the television terminal enters the screen saver, the television terminal requests an advertisement recommendation service, and the television terminal can be used for displaying screen saver advertisements.
The invention has the beneficial effects that:
according to the method and the device, the advertisement content can be accurately recommended according to the preference of the user, and each user can receive the advertisement content matched with the relevant information, so that the advertisement putting precision is increased, the receiving rate and the conversion rate of the advertisement are improved, the rate of regional advertisements at the television terminal is reduced, and the cost performance of advertisement putting is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the embodiments or the drawings needed to be practical in the prior art description, and obviously, the drawings in the following description are only some embodiments of the embodiments, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a main flow diagram of the present invention.
Fig. 2 is a logic diagram of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the examples given herein without any inventive step, are within the scope of the present invention.
The scheme of the invention is established on the basis of relatively complete big data acquisition, portrait data needs to contain family favorite labels (science fiction, comedy, speech and the like), family member gender and age distribution labels (male, female, old, middle, green and the like), family consumption grade labels (low, middle and high), family member personalized group labels (lovely baby, precious mother, scientific and technological home and the like) and weight ratio data of the labels, and the labels are obtained by calculation of big data correlation technology and a customized user portrait prediction algorithm model algorithm;
in any embodiment, as shown in fig. 1-2, a system for recommending advertisements to a smart tv of the present invention includes:
an advertising management platform; after the advertisement management platform detects the change of the advertisement information, calling a data cache center component to update the advertisement information in the cache: it includes the following modules:
the advertisement information storage service is mainly used for editing and storing advertisement video url address information, brief introduction information and labels (the label set data is from a picture label set, such as a delicate male label on a high-end shaver advertisement and the like);
the advertisement information inquiry service displays the basic information of the advertisement, and the upper and lower line states, the purchase and delivery times and the delivered times are displayed;
an advertisement information deletion service;
an advertisement information modification service;
the advertisement examination service is used for watching the advertisement content by an administrator and examining the validity of the advertisement;
the advertisement online and offline service is used for editing advertisement putting times and controlling whether the advertisement is put or not;
a data cache center; the data cache center comprises 5 components, and updates data regularly every day, and can also call the updated data manually:
a portrait data caching component, which caches the terminal mac and corresponding portrait data, such as ("mac": user portrait ") in a key-value data format, and provides a service for inquiring portrait information through a mac address to the outside;
the advertisement data caching component caches advertisement information (such as ' advertisement id ': advertisement url ') by using a key-value data format and provides a service for inquiring the advertisement information by the id;
a tag-advertisement matching information caching component for caching tag-advertisement matching information (advertisement candidate set) (such as '0-3 years': 1,3,5,11 (advertisement id array)) by using a key-value data format, providing a service for inquiring the associated advertisement by the tag, modifying the service of the associated advertisement by the tag, and rejecting the service of the advertisement under the tag according to the tag and the advertisement id;
the advertisement booking delivery time caching component caches advertisement booking delivery time data (purchase times-delivered times, if the purchase times are less than or equal to 0, the advertisement booking delivery times are not cached) (such as advertisement id: 10000) by using a key-value data format, and provides query service;
the advertisement delivery times cache component caches the delivered times of the advertisement (such as 'advertisement id': 3000) by using a key-value data format, provides the advertisement to external calling, operates in a thread safety mode each time the advertisement is called, acquires the delivered times of the advertisement by the advertisement id, if the advertisement is not obtained, defaulting to 0, adding the advertisement into the cache, obtaining the number of the reserved impressions in the advertisement preset impression cache component through the advertisement id, subtracting the number of the impressions added by 1 from the number of the reserved impressions, if the number of released times is greater than or equal to 0, feeding back a success code, if the number of released times is less than 0, feeding back an execution failure code, if the number of released times is equal to or less than 0, storing the released times in a database, calling a service of a region-advertisement matching information cache component for rejecting the advertisement in the region according to the region and the advertisement id to reject the advertisement, and after the service is successful, self-rejecting the released times for caching;
a user delivered advertisement caching component, which caches the advertisements delivered by the user (such as: mac: [1,2,3,4,5] advertisement id) in a key-value data format for algorithm query, the cache can set an expiration time, after the expiration time, the cache data of the mac is refreshed, the component provides the delivered advertisement service and the updated data service according to the mac query (the mac and id are transmitted, and the id is added to the delivered advertisement array of the mac);
a personalized recommendation algorithm platform; the personalized recommendation algorithm platform comprises two sub-platforms, which are respectively as follows:
recommending a cloud platform: for receiving requests and feeding back advertisement data, comprising:
receiving an advertisement recommendation request, and verifying the validity of parameters in the request;
taking a mac address request recommendation algorithm platform to obtain a recommendation result (a result set is an advertisement id);
calling an advertisement putting time cache component to update the put times;
if the success code is obtained, inquiring specific advertisement information through the inquiry advertisement information cache component, assembling the specific advertisement information into data available for the terminal according to a data protocol with the terminal, feeding the data back to the terminal, calling the released advertisement cache component of the user at the same time, and adding the advertisement id into the released advertisement data of the user;
if the failure code is acquired, re-executing the request from the step II;
a recommendation algorithm platform: based on artificial intelligence technology, using a technology based on a deep learning algorithm-personalized recommendation algorithm to aim at a single mac to produce recommendation results, and processing logic, wherein the processing logic comprises the following steps:
after receiving a request with a mac address;
loading the user portrait of the user in a portrait data cache component according to the mac address;
loading all advertisement candidate set information from the tag-advertisement matching information cache component;
loading the information of the mac delivered advertisement from the user delivered advertisement cache component;
based on a deep learning recommendation algorithm, using a user portrait of the mac address, analyzing user portrait labels, performing weight sorting on the labels, obtaining a plurality of labels with higher weights, then using the labels to obtain advertisement data corresponding to the labels, using the macs to put advertisements to filter produced data, filtering the put advertisements, then sorting the advertisement data according to a label weight algorithm (the advertisement label and user label matching algorithm is higher in matching degree, higher in score and higher in ranking), obtaining a first-ranked advertisement id after sorting, and feeding the first-ranked advertisement id back to a recommendation cloud platform;
a data warehouse; the data warehouse is used for storing data of the system.
The system requests and displays the method at the television terminal as follows:
after the television terminal is started and accessed to a network, an advertisement recommending service request is immediately carried out, and recommended advertisements are obtained and displayed and can be used for displaying fixed advertisement positions;
in the time period from the time when the television terminal is started to access the network to the time when the television terminal is turned off, requesting an advertisement recommendation service at random time to obtain recommended advertisements, wherein the recommended advertisements can be used for showing the television starting advertisements;
when the television terminal enters the screen saver, the television terminal requests an advertisement recommendation service, and the television terminal can be used for displaying screen saver advertisements.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. The various features described in the foregoing detailed description may be combined in any suitable manner without contradiction, and various combinations that are possible in the present invention will not be further described in order to avoid unnecessary repetition. Any combination of the different embodiments of the present invention is also possible, and the same should be considered as the disclosure of the present invention as long as it does not depart from the gist of the present invention.
Claims (2)
1. A system for recommending advertisements for smart televisions, comprising:
an advertising management platform; after the advertisement management platform detects the change of the advertisement information, calling a data cache center component to update the advertisement information in the cache: it includes the following modules:
the advertisement information storage service module is used for editing and storing advertisement video url address information, introduction information and labels;
the advertisement information inquiry service module is used for displaying the basic information of the advertisement, the upper and lower line states, the purchase and delivery times and the delivered times;
the advertisement information deleting service module;
an advertisement information modification service module;
the advertisement examination service module is used for watching the advertisement content by an administrator and examining the validity of the advertisement;
the advertisement online and offline service module is used for editing advertisement putting times and controlling whether the advertisement is put or not;
a data cache center; the data cache center comprises 7 components, and updates data regularly every day or manually:
the portrait data caching component caches the terminal mac and corresponding portrait data by using a key-value data format, and provides a service for inquiring portrait information through a mac address to the outside;
the advertisement data caching component caches the advertisement information by using a key-value data format and provides a service of inquiring the advertisement information by using the id;
the tag-advertisement matching information caching component caches tag-advertisement matching information by using a key-value data format, provides a service for querying the associated advertisement through a tag, modifies the associated advertisement through the tag, and rejects the service of the advertisement under the tag according to the tag and the advertisement id;
the advertisement booking delivery times caching component is used for caching advertisement booking delivery times data by using a key-value data format and providing query service;
the advertisement delivery times cache component is used for caching the advertisement delivery times by using a key-value data format, providing the advertisement delivery times for external calling, calling each time, operating in a thread safety mode, obtaining the advertisement delivery times through an advertisement id, if the advertisement delivery times are not obtained, defaulting to 0, adding the advertisement delivery times into the cache, obtaining the reserved delivery times through the advertisement id, subtracting the delivery times added with 1 from the reserved delivery times, if the advertisement delivery times are more than or equal to 0, feeding back a success code, if the advertisement delivery times are less than 0, storing the delivery times into a database, rejecting the advertisement service of the advertisement in the region according to the region and the advertisement id, and rejecting the delivery times cache after the advertisement delivery times are successfully rejected;
the method comprises the steps that a cache component for advertisements released by a user caches the advertisements released by the user by using a key-value data format for algorithm query, the cache can set expiration time, cache data of mac are refreshed after the expiration time is up, and the component provides service for querying the released advertisements and service for updating data according to the mac;
a personalized recommendation algorithm platform; the personalized recommendation algorithm platform comprises two sub-platforms, which are respectively as follows:
recommending a cloud platform: for receiving requests and feeding back advertisement data, comprising:
receiving an advertisement recommendation request, and verifying the validity of parameters in the request;
requesting a recommendation algorithm platform to obtain a recommendation result according to the mac address;
calling an advertisement putting time cache component to update the put times;
if the success code is obtained, inquiring specific advertisement information through the inquiry advertisement information cache component, assembling the specific advertisement information into data available for the terminal according to a data protocol with the terminal, feeding the data back to the terminal, calling the released advertisement cache component of the user at the same time, and adding the advertisement id into the released advertisement data of the user;
if the failure code is acquired, the request is executed again;
a recommendation algorithm platform: based on artificial intelligence technology, carrying out technical processing on a single mac by using a deep learning algorithm-personalized recommendation algorithm, and outputting a recommendation result, wherein the processing logic comprises the following steps:
after receiving a request with a mac address;
loading the user portrait of the user in a portrait data cache component according to the mac address;
loading all advertisement candidate set information from the tag-advertisement matching information cache component;
loading the information of the mac delivered advertisement from the user delivered advertisement cache component;
based on a deep learning recommendation algorithm, analyzing user portrait labels by using a user portrait of the mac address, performing weight sorting on the labels to obtain a plurality of labels with higher weights, then obtaining advertisement data corresponding to the labels by using the labels, filtering output data by using the advertisements delivered by the mac, filtering the delivered advertisements, sorting the advertisement data according to the label weight algorithm, obtaining advertisement id ranked first after sorting, and feeding the advertisement id to a recommendation cloud platform;
a data warehouse; the data warehouse is used for storing data of the system.
2. The system for recommending advertisements to a smart television as recited in claim 1, wherein the television terminal requests and presents methods are as follows:
after the television terminal is started and accessed to a network, an advertisement recommending service request is immediately carried out, and recommended advertisements are obtained and displayed and can be used for displaying fixed advertisement positions;
in the time period from the time when the television terminal is started to access the network to the time when the television terminal is turned off, requesting an advertisement recommendation service at random time to obtain recommended advertisements, wherein the recommended advertisements can be used for showing the television starting advertisements;
when the television terminal enters the screen saver, the television terminal requests an advertisement recommendation service, and the television terminal can be used for displaying screen saver advertisements.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910805866.2A CN110602531B (en) | 2019-08-28 | 2019-08-28 | System for recommending advertisements to smart television |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910805866.2A CN110602531B (en) | 2019-08-28 | 2019-08-28 | System for recommending advertisements to smart television |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110602531A CN110602531A (en) | 2019-12-20 |
CN110602531B true CN110602531B (en) | 2021-06-22 |
Family
ID=68856405
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910805866.2A Active CN110602531B (en) | 2019-08-28 | 2019-08-28 | System for recommending advertisements to smart television |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110602531B (en) |
Families Citing this family (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111275496B (en) * | 2020-02-24 | 2023-05-30 | 北京头条易科技有限公司 | Self-media advertisement intelligent recommendation method |
CN111626774A (en) * | 2020-05-21 | 2020-09-04 | 广州欢网科技有限责任公司 | Advertisement delivery system, method and readable storage medium |
CN112765208A (en) * | 2021-01-12 | 2021-05-07 | 云南电网有限责任公司电力科学研究院 | Scheduling method, system, equipment and storage medium for power transmission line maintenance task |
CN112818220A (en) * | 2021-01-26 | 2021-05-18 | 广州欢网科技有限责任公司 | Advertisement recommendation method and device and computer equipment |
CN112884399B (en) * | 2021-01-28 | 2023-07-25 | 重庆允丰科技有限公司 | Online marketing method, server and system for industrial products based on warehouse front-end processor |
CN113450134B (en) * | 2021-02-03 | 2024-03-19 | 北京新氧科技有限公司 | Advertisement putting method, device, equipment and storage medium |
CN114638646A (en) * | 2022-03-25 | 2022-06-17 | 广州华多网络科技有限公司 | Advertisement putting recommendation method and device, equipment, medium and product thereof |
CN114663168A (en) * | 2022-05-20 | 2022-06-24 | 广东省广告集团股份有限公司 | Information flow-based advertisement targeted delivery management method and system |
CN115511524B (en) * | 2022-09-26 | 2023-09-26 | 陕西励爱互联网科技有限公司 | Advertisement pushing method, system and cloud platform |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106131616A (en) * | 2016-07-25 | 2016-11-16 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device throwing in advertisement |
CN106658069A (en) * | 2016-12-16 | 2017-05-10 | 华扬联众数字技术股份有限公司 | Method and device for advertisement putting |
CN106803190A (en) * | 2017-01-03 | 2017-06-06 | 北京掌阔移动传媒科技有限公司 | A kind of ad personalization supplying system and method |
CN107256501A (en) * | 2017-07-14 | 2017-10-17 | 环球智达科技(北京)有限公司 | A kind of advertisement placement method |
US10136191B1 (en) * | 2016-12-12 | 2018-11-20 | Google Llc | Methods, systems, and media for recommending media content based on attribute grouped viewing sessions |
CN109451423A (en) * | 2018-11-14 | 2019-03-08 | 重庆雾都科技有限公司 | A kind of intelligent box of accurate marketing |
CN109447714A (en) * | 2018-11-06 | 2019-03-08 | 北京极睿科技有限责任公司 | Advertisement recommended method, device, equipment, system and server |
CN109840782A (en) * | 2017-11-24 | 2019-06-04 | 腾讯科技(深圳)有限公司 | Clicking rate prediction technique, device, server and storage medium |
CN109978630A (en) * | 2019-04-02 | 2019-07-05 | 安徽筋斗云机器人科技股份有限公司 | A kind of Precision Marketing Method and system for establishing user's portrait based on big data |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080250450A1 (en) * | 2007-04-06 | 2008-10-09 | Adisn, Inc. | Systems and methods for targeted advertising |
US10104411B2 (en) * | 2014-08-04 | 2018-10-16 | Adap.Tv, Inc. | Systems and methods for sell-side TV ad optimization |
CN108205766A (en) * | 2016-12-19 | 2018-06-26 | 阿里巴巴集团控股有限公司 | Information-pushing method, apparatus and system |
US11308523B2 (en) * | 2017-03-13 | 2022-04-19 | Adobe Inc. | Validating a target audience using a combination of classification algorithms |
CN110147882B (en) * | 2018-09-03 | 2023-02-10 | 腾讯科技(深圳)有限公司 | Neural network model training method, crowd diffusion method, device and equipment |
-
2019
- 2019-08-28 CN CN201910805866.2A patent/CN110602531B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106131616A (en) * | 2016-07-25 | 2016-11-16 | 无锡天脉聚源传媒科技有限公司 | A kind of method and device throwing in advertisement |
US10136191B1 (en) * | 2016-12-12 | 2018-11-20 | Google Llc | Methods, systems, and media for recommending media content based on attribute grouped viewing sessions |
CN106658069A (en) * | 2016-12-16 | 2017-05-10 | 华扬联众数字技术股份有限公司 | Method and device for advertisement putting |
CN106803190A (en) * | 2017-01-03 | 2017-06-06 | 北京掌阔移动传媒科技有限公司 | A kind of ad personalization supplying system and method |
CN107256501A (en) * | 2017-07-14 | 2017-10-17 | 环球智达科技(北京)有限公司 | A kind of advertisement placement method |
CN109840782A (en) * | 2017-11-24 | 2019-06-04 | 腾讯科技(深圳)有限公司 | Clicking rate prediction technique, device, server and storage medium |
CN109447714A (en) * | 2018-11-06 | 2019-03-08 | 北京极睿科技有限责任公司 | Advertisement recommended method, device, equipment, system and server |
CN109451423A (en) * | 2018-11-14 | 2019-03-08 | 重庆雾都科技有限公司 | A kind of intelligent box of accurate marketing |
CN109978630A (en) * | 2019-04-02 | 2019-07-05 | 安徽筋斗云机器人科技股份有限公司 | A kind of Precision Marketing Method and system for establishing user's portrait based on big data |
Non-Patent Citations (1)
Title |
---|
面向智能终端的广告投放系统与实现;郭小芬;《中国优秀硕士学位论文全文数据库》;20181116;I138-88 * |
Also Published As
Publication number | Publication date |
---|---|
CN110602531A (en) | 2019-12-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110602531B (en) | System for recommending advertisements to smart television | |
US11200596B2 (en) | System and method for segmenting and targeting audience members | |
CN110430471B (en) | Television recommendation method and system based on instantaneous calculation | |
US9361373B1 (en) | Content aggregation and presentation | |
CN108900923B (en) | Method and device for recommending live broadcast template | |
CN106028071A (en) | Video recommendation method and system | |
CN111062735A (en) | Advertisement putting method, device, system, terminal and computer readable storage medium | |
CN110602533B (en) | Intelligent television advertisement recommendation system and method for time-sharing and crowd-sharing | |
CN109429103B (en) | Method and device for recommending information, computer readable storage medium and terminal equipment | |
CN103458275A (en) | Real-time interaction digital television information recommendation system and method | |
CN102323951B (en) | Internet advertisement publishing method and system | |
US20160308800A1 (en) | Method and system for account recommendation | |
CN110717093A (en) | Spark-based movie recommendation system and method | |
CN113170221A (en) | Display method, device, terminal, server and storage medium of live broadcast interface | |
US20220239980A1 (en) | System And Method For Recommending A Content Service To A Content Consumer | |
CN112396461A (en) | Vehicle-mounted video advertisement management system based on big data | |
CN112115354A (en) | Information processing method, information processing apparatus, server, and storage medium | |
CN112150186A (en) | Advertisement putting method, client device, server and system | |
CN111078998A (en) | Information retrieval method, information retrieval device, storage medium and server | |
CN106603351B (en) | Television advertisement pushing method and system based on user behaviors | |
CN113553509B (en) | Content recommendation method and device, electronic equipment and storage medium | |
CN115119021A (en) | Data processing method and device, electronic equipment and storage medium | |
CN112104910B (en) | Video searching method, device and system | |
CN107992548B (en) | Information processing method, system, medium, and computing device | |
CN114461893A (en) | Information recommendation method, related device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |