CN111339357A - Recommendation method and device based on live user behaviors - Google Patents
Recommendation method and device based on live user behaviors Download PDFInfo
- Publication number
- CN111339357A CN111339357A CN202010107564.0A CN202010107564A CN111339357A CN 111339357 A CN111339357 A CN 111339357A CN 202010107564 A CN202010107564 A CN 202010107564A CN 111339357 A CN111339357 A CN 111339357A
- Authority
- CN
- China
- Prior art keywords
- user
- live
- data
- program list
- live broadcast
- 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.)
- Pending
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
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/735—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24553—Query execution of query operations
- G06F16/24561—Intermediate data storage techniques for performance improvement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Library & Information Science (AREA)
- Computing Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention relates to a recommendation method and device based on live broadcast user behavior, which comprises the steps of utilizing flume to collect live broadcast viewing data watched by a user in time intervals, and storing the live broadcast viewing data by kafka; the Spark Streaming pulls the live broadcast audience data from the kafka based on a time interval and processes the received live broadcast audience data to generate a user tag result, and the user tag result is inserted into a mongodb table in a reverse order according to a weight value; filtering the metadata of the live-cast film and television to obtain user program data, and performing similar type retrieval on the user program data to obtain a candidate program list; generating a recommended program list according to the mongodb list and the candidate program list; the invention solves the bottleneck of the prior art, provides refined service for users and improves user experience.
Description
Technical Field
The invention belongs to the technical field of internet, and particularly relates to a recommendation method and device based on live user behaviors.
Background
Since the birth of television live broadcast, the television is accompanied by people all the time, and people enjoy high-definition visual watching experience on the television. However, the television is centered on the channel, and due to factors such as advertisements, the user passively receives the real-time content of the channel, lacks interaction, and cannot find the desired content. Tag portrayal is required to be carried out according to live broadcast behaviors of users, and real-time interest recommendation is carried out on the tags to the users subsequently.
The existing recommendation construction technology generates recommendations through basic information of past users, and the acquired information is insufficient and the real-time performance is not high. The recommendation accuracy and reliability are poor, and the real-time characteristics cannot be fully embodied. Therefore, a hysteresis of the recommendation update is caused, so that the user experience is low.
In the related art, there are many methods for generating live recommendations in the industry, for example:
constructing recommendations based on strom:
when the Storm is used for realizing the data flow model, the collected user data is continuously pulled from the log collection system and is subjected to flow type processing, the generated recommended data is stored and displayed, and the real-time performance is high. However, Storm has its own drawbacks, low throughput of data, and complex integration with other large data components.
Constructing a recommendation based on flink:
acquiring real-time live broadcast behavior data generated by the user viewing from a kafka message queue; and calculating the real-time behavior data by adopting a flink distributed operation system to obtain the real-time recommendation of the user. But as it is an emerging thing, aspects are still imperfect, and the stability of the program remains to be verified.
Disclosure of Invention
In view of the above, the present invention provides a recommendation method and apparatus based on live broadcast user behavior to solve the problem of hysteresis of recommendation update in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme: a recommendation method based on live user behavior comprises the following steps:
live broadcast viewing data watched by a user is collected by using a flash time-sharing mode, and the live broadcast viewing data is stored by kafka;
the Spark Streaming pulls the live broadcast audience data from the kafka based on a time interval and processes the received live broadcast audience data to generate a user tag result, and the user tag result is inserted into a mongodb table in a reverse order according to a weight value;
filtering the metadata of the live-cast film and television to obtain user program data, and performing similar type retrieval on the user program data to obtain a candidate program list;
and generating a recommended program list according to the mongodb list and the candidate program list.
Further, before the collecting live viewing data watched by a user in time segments by using flash, and storing and outputting the live viewing data by kafka, the method further comprises:
a user tag hierarchy is defined from the scene description.
Further, the user tag system includes:
the type of film and television, the watching point, the year of the plot, the emotion, the crowd, the age, the scene and the expression form.
Further, the user tag result is updated according to time intervals.
Further, the live broadcast audience data in the Spark Streaming adopts:
format of json string.
Further, filtering the live-broadcast movie metadata to obtain a candidate program list; the method comprises the following steps:
and filtering the live video metadata according to characters.
Further, the processing the received live viewing data to generate a user tag result includes:
labeling the live broadcast video data by combining a user label system and correspondingly configuring weight for each label to obtain a label result;
the labeling result comprises: user ID, user tag, tag weight value.
Further, the generating a recommended program list according to the mongodb list and the candidate program list includes:
sorting the candidate program list according to the label weight value in the mongodb table;
and generating a recommended program list according to the sequence of the candidate program list.
The embodiment of the application provides a recommendation device based on live user's action, includes:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring live broadcast viewing data watched by a user by using flash in a time-sharing mode, and kafka stores the live broadcast viewing data;
the first generation module is used for pulling the live broadcast audience data from the kafka based on a time interval by Spark Streaming, processing the received live broadcast audience data, generating a user tag result, and inserting the user tag result into a mongodb table in a reverse order according to a weight value;
the acquisition module is used for filtering the metadata of the live broadcast film and television, acquiring the data of a user program list, and performing similar type retrieval on the data of the user program list to acquire a candidate program list;
and the second generation module is used for generating a recommended program list according to the mongodb list and the candidate program list.
Further, the method also comprises the following steps:
and the definition module is used for defining a user tag system according to the scene description.
By adopting the technical scheme, the invention can achieve the following beneficial effects:
1, in the aspects of fault tolerance and data guarantee, Spark Streaming provides better support for fault-tolerant state calculation;
2, the throughput of real-time data is high;
3, Spark Streaming is a good feature as a one-stop solution, while providing offline, sql-like, Streaming computing. The Spark program calls rdd seamlessly inside. Thus, the same code for batch processing can be written, and independent code does not need to be written to process real-time streaming data and historical data;
4, in the aspect of cluster management integration, Spark Streaming can be operated on the own cluster, and can also be operated on both YARN and mess, and is a native adaptation YARN.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram illustrating steps of a recommendation method based on live user behavior according to the present invention;
fig. 2 is a schematic structural diagram of a recommendation device based on live user behavior according to 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.
A specific live user behavior-based recommendation method provided in the embodiment of the present application is described below with reference to the accompanying drawings.
As shown in fig. 1, a live user behavior-based recommendation method provided in an embodiment of the present application includes:
s101, live broadcast viewing data watched by a user is collected by using flume time-sharing, and the live broadcast viewing data is stored by kafka;
the flash system collects live broadcast viewing data watched by a user in real time in several time periods, and the kafka receives the live broadcast viewing data, stores the data according to topic and outputs the data to a Spark Streaming platform.
The flash is a distributed, reliable and highly available system for aggregating mass logs, supports various data senders to be customized in the system, is used for collecting data by monitoring the whole file directory or a certain specific file, and simultaneously provides the capability of writing data to various data receivers for forwarding the data. The ease of use of flash is that log files can be automatically collected by reading configuration files.
kafka belongs to middleware, and one obvious advantage is that all layers are decoupled, so that other components cannot be interfered when errors occur, therefore, data can be calculated in real time when a data source goes from flash to kafka, and multi-distribution of the data can be realized.
S102, pulling the live broadcast audience data from the kafka based on a time interval by Spark Streaming, processing the received live broadcast audience data to generate a user tag result, and inserting the user tag result into a mongodb table in a reverse order according to a weight value;
the Spark Streaming fetches the live broadcast viewing data from the kafka according to the time interval, monitors whether the live broadcast viewing data in the kafka is increased or not according to the time interval, and if the live broadcast viewing data in the kafka is increased, the Spark Streaming simultaneously increases the live broadcast viewing data, processes the collected live broadcast viewing data to generate a user tag result, and inserts the user tag result into the mongodb table according to the weighted value in a reverse order.
S103, filtering the metadata of the live-action film and television to obtain user program data, and performing similar type retrieval on the user program data to obtain a candidate program list;
and filtering all live broadcast movie metadata, forming user program data by the filtered live broadcast movie metadata, and performing similar type retrieval according to types in the user program data to obtain a candidate program list.
And S104, generating a recommended program list according to the mongodb list and the candidate program list.
And combining the mongodb list with the candidate program list, sorting the candidate program list according to the weight values in the mongodb list, ranking the candidate program list with high weight values in front, and recommending the candidate program list to the user.
The recommendation method based on the live user behavior has the working principle that: live broadcast viewing data watched by a user is collected by using a flash time-sharing mode, and the live broadcast viewing data is stored by kafka; the Spark Streaming pulls the live broadcast audience data from the kafka based on a time interval and processes the received live broadcast audience data to generate a user tag result, and the user tag result is inserted into a mongodb table in a reverse order according to a weight value; filtering the metadata of the live-cast film and television to obtain user program data, and performing similar type retrieval on the user program data to obtain a candidate program list; and generating a recommended program list according to the mongodb list and the candidate program list.
In some embodiments, live viewing data watched by a user is collected in time segments by using flume, and kafka stores the live viewing data and outputs the live viewing data; the method also comprises the following steps:
a user tag hierarchy is defined from the scene description.
Preferably, the user tag system includes:
the type of film and television, the watching point, the year of the plot, the emotion, the crowd, the age, the scene and the expression form.
A user tag system is defined according to a scene of a live broadcast picture watched by a user.
In some embodiments, the user tag results are updated at intervals.
Specifically, the user tag results are updated at intervals, so that the mongodb table is updated at intervals.
Preferably, in the present application, the live viewing data in the Spark Streaming adopts:
format of json string.
Preferably, the live-broadcast movie metadata is filtered to obtain a candidate program list; the method comprises the following steps:
and filtering the live video metadata according to characters.
Specifically, when filtering the metadata of the live-action movie, the filtering is performed according to characters, for example: the play is filtered in a way of having a director and actors, and if there are no director or actor characters in the play, the play is filtered out.
In some embodiments, the processing the received live viewing data to generate a user tagging result includes:
labeling the live broadcast video data by combining a user label system and correspondingly configuring weight for each label to obtain a label result;
the labeling result comprises: user ID, user tag, tag weight value.
Specifically, live broadcast viewing data with weight labels is obtained by labeling the live broadcast viewing data and configuring weights corresponding to each label, and the live broadcast viewing data with the weight labels is a label result.
In some embodiments, the generating a recommended program list from the mongodb list and the candidate program list includes:
sorting the candidate program list according to the label weight value in the mongodb table;
and generating a recommended program list according to the sequence of the candidate program list.
Specifically, the candidate program list is sorted according to the sorting of the label weight values, and the sorted candidate program list, i.e., the recommended program list, is recommended to the television of the user.
An embodiment of the present application provides a recommendation device based on live user behavior, as shown in fig. 2, including:
the system comprises an acquisition module 1, a storage module and a display module, wherein the acquisition module is used for acquiring live broadcast viewing data watched by a user by using flash in a time-sharing mode, and kafka stores the live broadcast viewing data;
the first generation module 2 is used for pulling the live broadcast audience data from the kafka based on a time interval by Spark Streaming, processing the received live broadcast audience data, generating a user tag result, and inserting the user tag result into a mongodb table according to a weighted value in a reverse order;
the acquisition module 3 is used for filtering the metadata of the live broadcast film and television, acquiring the data of a user program list, and performing similar type retrieval on the data of the user program list to acquire a candidate program list;
and the second generating module 4 is used for generating a recommended program list according to the mongodb list and the candidate program list.
The recommendation device based on the live broadcast user behavior has the working principle that the acquisition module 1 acquires live broadcast viewing data watched by a user by using flash time-sharing, and kafka stores the live broadcast viewing data; the first generation module 2 is used for pulling the live broadcast audience data from the kafka based on a time interval by spark streaming, processing the received live broadcast audience data, generating a user tag result, and inserting the user tag result into a mongodb table according to a weighted value in a reverse order; the acquisition module 3 filters the live-action movie metadata, acquires user program data, and performs similar type retrieval on the user program data to acquire a candidate program list; and the second generation module 4 generates a recommended program list according to the mongodb list and the candidate program list.
In some embodiments, embodiments provided herein further include:
and the definition module 5 is used for defining a user tag system according to the scene description.
In summary, the present invention provides a recommendation method and apparatus based on live broadcast user behavior, which has the beneficial effects that 1, in terms of fault tolerance and data assurance, Spark Streaming provides better support for fault-tolerant state calculation; 2, the throughput of real-time data is high; 3, Spark Streaming is a good feature as a one-stop solution, while providing offline, sql-like, Streaming computing. The Spark program calls rdd seamlessly inside. Thus, the same code for batch processing can be written, and independent code does not need to be written to process real-time streaming data and historical data; 4, in the aspect of cluster management integration, Spark Streaming can be operated on the own cluster, and can also be operated on both YARN and mess, and Spark Streaming is native adaptation YARN.
It can be understood that the method embodiment provided above corresponds to the recommendation method embodiment based on live user behavior, and corresponding specific contents may be referred to each other, and are not described herein again.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks for live user behavior-based recommendation.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks based on the live user behavior recommendation method.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
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. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (10)
1. A recommendation method based on live user behavior is characterized by comprising the following steps:
live broadcast viewing data watched by a user is collected by using a flash time-sharing mode, and the live broadcast viewing data is stored by kafka;
the Spark Streaming pulls the live broadcast audience data from the kafka based on a time interval and processes the received live broadcast audience data to generate a user tag result, and the user tag result is inserted into a mongodb table in a reverse order according to a weight value;
filtering the metadata of the live-cast film and television to obtain user program data, and performing similar type retrieval on the user program data to obtain a candidate program list;
and generating a recommended program list according to the mongodb list and the candidate program list.
2. The live user behavior-based recommendation method according to claim 1, wherein before said collecting live viewing data watched by a user in time segments by using flash, kafka storing said live viewing data and outputting it, further comprises:
a user tag hierarchy is defined from the scene description.
3. The live user behavior-based recommendation method according to claim 2, wherein the user tagging system comprises:
the type of film and television, the watching point, the year of the plot, the emotion, the crowd, the age, the scene and the expression form.
4. The live user behavior-based recommendation method of claim 1,
the user tag results are updated at time intervals.
5. The live user behavior-based recommendation method according to claim 1, wherein the live viewing data in SparkStreaming adopts:
format of json string.
6. The live user behavior-based recommendation method according to claim 5, wherein the live movie metadata is filtered to obtain a candidate program list; the method comprises the following steps:
and filtering the live video metadata according to characters.
7. The live user behavior-based recommendation method of claim 2, wherein the processing the received live viewing data to generate a user tagging result comprises:
labeling the live broadcast video data by combining a user label system and correspondingly configuring weight for each label to obtain a label result;
the labeling result comprises: user ID, user tag, tag weight value.
8. The live user behavior-based recommendation method according to claim 7, wherein said generating a recommended program list from said mongodb list and said candidate program list comprises:
sorting the candidate program list according to the label weight value in the mongodb table;
and generating a recommended program list according to the sequence of the candidate program list.
9. A recommendation device based on live user behavior, comprising:
the system comprises an acquisition module, a storage module and a display module, wherein the acquisition module is used for acquiring live broadcast viewing data watched by a user by using flash in a time-sharing mode, and kafka stores the live broadcast viewing data;
the first generation module is used for pulling the live broadcast audience data from the kafka based on a time interval by Spark Streaming, processing the received live broadcast audience data, generating a user tag result, and inserting the user tag result into a mongodb table in a reverse order according to a weight value;
the acquisition module is used for filtering the metadata of the live broadcast film and television, acquiring the data of a user program list, and performing similar type retrieval on the data of the user program list to acquire a candidate program list;
and the second generation module is used for generating a recommended program list according to the mongodb list and the candidate program list.
10. The live user behavior-based recommendation device of claim 9, further comprising:
and the definition module is used for defining a user tag system according to the scene description.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010107564.0A CN111339357A (en) | 2020-02-21 | 2020-02-21 | Recommendation method and device based on live user behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010107564.0A CN111339357A (en) | 2020-02-21 | 2020-02-21 | Recommendation method and device based on live user behaviors |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111339357A true CN111339357A (en) | 2020-06-26 |
Family
ID=71181729
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010107564.0A Pending CN111339357A (en) | 2020-02-21 | 2020-02-21 | Recommendation method and device based on live user behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111339357A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112015736A (en) * | 2020-08-21 | 2020-12-01 | 广州欢网科技有限责任公司 | Spark Mllib-based multifunctional recommendation method and device |
| CN114173200A (en) * | 2021-12-06 | 2022-03-11 | 南京辰和软件有限公司 | Video management pushing method and device based on private radio and television network |
| CN115734030A (en) * | 2022-12-14 | 2023-03-03 | 海看网络科技(山东)股份有限公司 | Method for accelerating mobile terminal to acquire live channel program list |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104394471A (en) * | 2014-11-19 | 2015-03-04 | 四川长虹电器股份有限公司 | Method for intelligently recommending favorite program to user |
| CN105142028A (en) * | 2015-07-29 | 2015-12-09 | 华中科技大学 | Television program content searching and recommending method oriented to integration of three networks |
| CN107608990A (en) * | 2016-07-12 | 2018-01-19 | 上海视畅信息科技有限公司 | A kind of live personalized recommendation method |
| CN110704677A (en) * | 2019-08-23 | 2020-01-17 | 优地网络有限公司 | Program recommendation method and device, readable storage medium and terminal equipment |
| CN110717093A (en) * | 2019-08-27 | 2020-01-21 | 广东工业大学 | Spark-based movie recommendation system and method |
-
2020
- 2020-02-21 CN CN202010107564.0A patent/CN111339357A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104394471A (en) * | 2014-11-19 | 2015-03-04 | 四川长虹电器股份有限公司 | Method for intelligently recommending favorite program to user |
| CN105142028A (en) * | 2015-07-29 | 2015-12-09 | 华中科技大学 | Television program content searching and recommending method oriented to integration of three networks |
| CN107608990A (en) * | 2016-07-12 | 2018-01-19 | 上海视畅信息科技有限公司 | A kind of live personalized recommendation method |
| CN110704677A (en) * | 2019-08-23 | 2020-01-17 | 优地网络有限公司 | Program recommendation method and device, readable storage medium and terminal equipment |
| CN110717093A (en) * | 2019-08-27 | 2020-01-21 | 广东工业大学 | Spark-based movie recommendation system and method |
Non-Patent Citations (1)
| Title |
|---|
| 郭栋: "《网络与新媒体概论》", 31 December 2018, 陕西师范大学出版社 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112015736A (en) * | 2020-08-21 | 2020-12-01 | 广州欢网科技有限责任公司 | Spark Mllib-based multifunctional recommendation method and device |
| CN112015736B (en) * | 2020-08-21 | 2024-04-05 | 广州欢网科技有限责任公司 | Multi-functional recommendation method and device based on Spark Mllib |
| CN114173200A (en) * | 2021-12-06 | 2022-03-11 | 南京辰和软件有限公司 | Video management pushing method and device based on private radio and television network |
| CN114173200B (en) * | 2021-12-06 | 2022-08-26 | 江苏省广电有线信息网络股份有限公司镇江分公司 | Video management pushing method and device based on private radio and television network |
| CN115734030A (en) * | 2022-12-14 | 2023-03-03 | 海看网络科技(山东)股份有限公司 | Method for accelerating mobile terminal to acquire live channel program list |
| CN115734030B (en) * | 2022-12-14 | 2024-01-26 | 海看网络科技(山东)股份有限公司 | Method for accelerating mobile terminal to acquire live channel program list |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6972260B2 (en) | Systems and methods for partitioning search indexes to improve media segment identification efficiency | |
| KR102068790B1 (en) | Estimating and displaying social interest in time-based media | |
| CN106792100B (en) | Video bullet screen display method and device | |
| US20170140398A1 (en) | Generating Audience Response Metrics and Ratings from Social Interest In Time-Based Media | |
| US11522938B2 (en) | Feature generation for online/offline machine learning | |
| CN111339357A (en) | Recommendation method and device based on live user behaviors | |
| CN106686419B (en) | Display method and display device of screen saver | |
| CN112989209B (en) | Content recommendation method, device and storage medium | |
| CN104065979A (en) | Method for dynamically displaying information related with video content and system thereof | |
| US9794638B2 (en) | Caption replacement service system and method for interactive service in video on demand | |
| US10798425B1 (en) | Personalized key object identification in a live video stream | |
| US20150100582A1 (en) | Association of topic labels with digital content | |
| CN107547922B (en) | Information processing method, device, system and computer readable storage medium | |
| CN111754268A (en) | OTT big data-based user label generation method, management system and storage medium | |
| CN111177489A (en) | Object data display method and system | |
| CN112015736B (en) | Multi-functional recommendation method and device based on Spark Mllib | |
| CN113111196B (en) | Multimedia resource recommendation method and related device | |
| CN112153478B (en) | Video processing method and video playing method | |
| KR20220132393A (en) | Method, Apparatus and System of managing contents in Multi-channel Network | |
| CN115278326A (en) | Video display method and device, computer readable medium and electronic equipment | |
| US10924790B1 (en) | Video stream modification | |
| CN114885203A (en) | Bullet screen reverse grabbing method and device, storage medium and terminal | |
| US20210120286A1 (en) | Methods and systems for dynamic media content | |
| CN117478729A (en) | Information stream processing method, system, device, electronic equipment and storage medium | |
| CN113778837A (en) | Page fault determination method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200626 |
|
| RJ01 | Rejection of invention patent application after publication |