CN115033798A - Activity recommendation method and system based on big data - Google Patents
Activity recommendation method and system based on big data Download PDFInfo
- Publication number
- CN115033798A CN115033798A CN202210777934.0A CN202210777934A CN115033798A CN 115033798 A CN115033798 A CN 115033798A CN 202210777934 A CN202210777934 A CN 202210777934A CN 115033798 A CN115033798 A CN 115033798A
- Authority
- CN
- China
- Prior art keywords
- activity
- recommendation
- data
- user
- information
- 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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/587—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- 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
- G06F16/787—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using geographical or spatial information, e.g. location
-
- 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
- G06F16/903—Querying
- G06F16/9035—Filtering based on additional data, e.g. user or group profiles
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention relates to the technical field of big data, and particularly discloses an activity recommendation method and system based on big data. According to the embodiment of the invention, a plurality of activity recommendation labels are generated by analyzing historical activity record data; performing big data activity search; carrying out data screening; performing image-text recommendation and video recommendation; and acquiring uninteresting recommendation pictures and texts or uninteresting recommendation videos marked by the user, and carrying out corresponding automatic marking. The method has the advantages that historical activity record data of a user can be analyzed, a plurality of activity recommendation labels are generated, data screening is carried out according to the activity recommendation labels, a plurality of activity recommendation pictures and texts and associated activity recommendation videos are created, picture and text recommendation and video recommendation are carried out, uninteresting marks of the user are obtained, and associated uninteresting marks are carried out, so that accurate recommendation of activity recommendation can be achieved, adaptability change of the activity recommendation can be carried out according to requirements of the user, and the activity recommendation can meet requirements of the user better.
Description
Technical Field
The invention belongs to the technical field of big data, and particularly relates to an activity recommendation method and system based on big data.
Background
Big data, or mass data, refers to the data that is too large to be captured, managed, processed, and organized in a reasonable time through mainstream software tools to help users make business decisions. The existing society is a society with high-speed development, developed technology and information circulation, people can communicate closely and conveniently, and big data is a product of the high-technology era.
Campaign recommendations, which are a form of advertising that recommends to users a campaign that may be of interest, are typically based on big data, making the subject of the campaign recommendations more accurate. The existing activity recommendation technology based on big data generally simply obtains age information of users by using the big data, classifies the users according to the age information, and recommends advertisements of different activities, and is too coarse to implement accurate activity recommendation and also unable to make adaptive changes according to the needs of the users.
Disclosure of Invention
The embodiment of the invention aims to provide an activity recommendation method and system based on big data, and aims to solve the problems in the background art.
In order to achieve the above purpose, the embodiments of the present invention provide the following technical solutions:
the activity recommendation method based on big data specifically comprises the following steps:
acquiring historical activity record data of a user, analyzing the historical activity record data, and generating a plurality of activity recommendation labels;
acquiring current position data of a user, and performing big data activity search according to the current position data to acquire activity search data;
screening the activity search data according to the plurality of activity recommendation labels to obtain a plurality of recommendation activities and corresponding activity information;
according to the activity information, creating activity recommendation pictures and texts and activity recommendation videos corresponding to the recommended activities, and recommending the pictures and texts and recommending the videos;
in the process of image-text recommendation and video recommendation, uninteresting recommendation images-texts or uninteresting recommendation videos marked by a user are obtained, and corresponding uninteresting recommendation videos or uninteresting recommendation images-texts are marked.
As a further limitation of the technical solution of the embodiment of the present invention, the acquiring historical activity record data of the user, analyzing the historical activity record data, and generating a plurality of activity recommendation labels specifically includes the following steps:
acquiring historical activity record data of a user;
extracting information from the historical activity record data to obtain a plurality of pieces of historical activity information and corresponding activity evaluation information;
marking a plurality of historical interest activity information from a plurality of the historical activity information according to a plurality of the activity evaluation information;
and analyzing the plurality of historical interest activity information to generate a plurality of activity recommendation labels.
As a further limitation of the technical solution of the embodiment of the present invention, the acquiring current location data of a user, and performing big data active search according to the current location data, the acquiring active search data specifically includes the following steps:
acquiring current position data of a user;
generating an activity recommendation range according to the current position data;
and according to the activity recommendation range, performing big data activity search to obtain activity search data.
As a further limitation of the technical solution of the embodiment of the present invention, the screening the activity search data according to the plurality of activity recommendation labels to obtain a plurality of recommended activities and corresponding activity information specifically includes the following steps:
screening the activity search data according to the plurality of activity recommendation labels to obtain a plurality of recommendation activities;
and analyzing the activity search data to obtain activity information corresponding to a plurality of recommended activities.
As a further limitation of the technical solution of the embodiment of the present invention, the creating activity recommendation graphics and videos corresponding to a plurality of recommended activities according to a plurality of the activity information, and performing graphics and video recommendation specifically includes the following steps:
creating activity recommendation pictures and texts corresponding to a plurality of recommended activities according to the plurality of activity information;
according to the plurality of pieces of activity information, creating activity recommendation videos corresponding to the plurality of recommendation activities;
establishing recommendation contact data between activity recommendation pictures and activity recommendation videos corresponding to a plurality of same recommendation activities;
and respectively carrying out image-text recommendation and video recommendation according to the plurality of activity recommendation images-texts and the plurality of activity recommendation videos.
As a further limitation of the technical solution of the embodiment of the present invention, in the process of image-text recommendation and video recommendation, uninteresting recommendation images-texts or uninteresting recommendation videos marked by a user are obtained, and marking corresponding uninteresting recommendation videos or uninteresting recommendation images-texts specifically includes the following steps:
in the process of image-text recommendation and video recommendation, uninteresting recommended images-texts or uninteresting recommended videos marked by a user are obtained;
and marking the corresponding uninteresting recommended video or uninteresting recommended graphics according to the recommended contact data.
The activity recommendation system based on big data comprises a recommendation label generation unit, a big data activity search unit, a search data screening unit, a graphic video recommendation unit and a user mark processing unit, wherein:
the recommendation label generation unit is used for acquiring historical activity record data of a user, analyzing the historical activity record data and generating a plurality of activity recommendation labels;
the big data activity searching unit is used for acquiring current position data of a user, performing big data activity searching according to the current position data and acquiring activity searching data;
the search data screening unit is used for screening the activity search data according to the activity recommendation labels to acquire a plurality of recommendation activities and corresponding activity information;
the image-text video recommending unit is used for creating activity recommendation images and texts and activity recommendation videos corresponding to a plurality of recommendation activities according to the plurality of activity information and performing image-text recommendation and video recommendation;
and the user mark processing unit is used for acquiring uninterested image-texts or uninterested videos marked by the user and marking the corresponding uninterested recommended videos or uninterested images-texts in the image-text recommendation and video recommendation processes.
As a further limitation of the technical solution of the embodiment of the present invention, the recommended label generating unit specifically includes:
the historical data acquisition module is used for acquiring historical activity record data of a user;
the data information extraction module is used for extracting information from the historical activity record data to obtain a plurality of historical activity information and corresponding activity evaluation information;
the activity information marking module is used for marking a plurality of historical interest activity information from a plurality of historical activity information according to a plurality of activity evaluation information;
and the activity information analysis module is used for analyzing the historical interest activity information to generate a plurality of activity recommendation labels.
As a further limitation of the technical solution of the embodiment of the present invention, the big data activity search unit specifically includes:
the position acquisition module is used for acquiring current position data of a user;
the position analysis module is used for generating an activity recommendation range according to the current position data;
and the activity searching module is used for searching big data activities according to the activity recommendation range and acquiring activity searching data.
As a further limitation of the technical solution of the embodiment of the present invention, the teletext video recommendation unit specifically includes:
the recommendation image-text creating module is used for creating activity recommendation image-texts corresponding to a plurality of recommendation activities according to the activity information;
the recommendation video creating module is used for creating activity recommendation videos corresponding to a plurality of recommendation activities according to the activity information;
the recommendation relation establishing module is used for establishing recommendation relation data between activity recommendation pictures and activity recommendation videos corresponding to a plurality of same recommendation activities;
and the image-text video recommending module is used for respectively recommending image-text and video according to the plurality of activity recommending images-text and the plurality of activity recommending videos.
Compared with the prior art, the invention has the beneficial effects that:
according to the embodiment of the invention, a plurality of activity recommendation labels are generated by analyzing historical activity record data of a user; performing big data activity search; carrying out data screening; performing image-text recommendation and video recommendation; and acquiring uninteresting recommendation pictures and texts or uninteresting recommendation videos marked by the user, and carrying out corresponding automatic marking. The method has the advantages that historical activity record data of a user can be analyzed, a plurality of activity recommendation labels are generated, data screening is carried out according to the activity recommendation labels, a plurality of activity recommendation pictures and texts and associated activity recommendation videos are created, picture and text recommendation and video recommendation are carried out, uninteresting marks of the user are obtained, and associated uninteresting marks are carried out, so that accurate recommendation of activity recommendation can be achieved, adaptability change of the activity recommendation can be carried out according to requirements of the user, and the activity recommendation can meet requirements of the user better.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 shows a flow chart of a method provided by an embodiment of the invention.
Fig. 2 shows a flowchart of historical activity record data analysis in the method provided by the embodiment of the invention.
Fig. 3 shows a flowchart of big data active search in the method provided by the embodiment of the present invention.
Fig. 4 shows a flowchart of active search data filtering in the method provided by the embodiment of the present invention.
Fig. 5 shows a flowchart of the teletext recommendation and the video recommendation in the method provided by the embodiment of the invention.
Fig. 6 shows a flow chart of uninteresting adaptation in a method provided by an embodiment of the invention.
Fig. 7 shows an application architecture diagram of a system provided by an embodiment of the invention.
Fig. 8 shows a block diagram of a structure of a recommended label generating unit in the system according to the embodiment of the present invention.
Fig. 9 shows a block diagram of a big data active search unit in the system according to an embodiment of the present invention.
Fig. 10 shows a block diagram of a teletext video recommendation unit in the system according to an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
It can be understood that, in the prior art, the activity recommendation technology based on big data generally simply obtains the age information of the user by using the big data, classifies the user according to the age information, and recommends advertisements of different activities, and this activity recommendation technology is too coarse to implement accurate activity recommendation, and cannot make adaptive changes according to the needs of the user.
In order to solve the above problems, in the embodiments of the present invention, a plurality of activity recommendation tags are generated by analyzing historical activity record data of a user; performing big data activity search; carrying out data screening; performing image-text recommendation and video recommendation; and acquiring uninteresting recommendation pictures and texts or uninteresting recommendation videos marked by the user, and carrying out corresponding automatic marking. The method has the advantages that historical activity record data of a user can be analyzed, a plurality of activity recommendation labels are generated, data screening is carried out according to the activity recommendation labels, a plurality of activity recommendation pictures and texts and associated activity recommendation videos are created, picture and text recommendation and video recommendation are carried out, uninteresting marks of the user are obtained, and associated uninteresting marks are carried out, so that accurate recommendation of activity recommendation can be achieved, adaptability change of the activity recommendation can be carried out according to requirements of the user, and the activity recommendation can meet requirements of the user better.
Fig. 1 shows a flow chart of a method provided by an embodiment of the invention.
Specifically, the activity recommendation method based on big data specifically comprises the following steps:
step S101, obtaining historical activity record data of a user, analyzing the historical activity record data, and generating a plurality of activity recommendation labels.
In the embodiment of the invention, a historical record data application is sent to a user, after the user agrees with the historical record data application, historical activity record data of the user recorded in a cloud database is obtained, historical activity information and activity evaluation information corresponding to a plurality of historical activities are obtained by analyzing and extracting the historical activity record data, an interest analysis result is generated by analyzing the activity evaluation information, whether the user is interested in the corresponding historical activities is judged according to the interest analysis result, the historical activity information corresponding to the historical activities which are interested by the plurality of users is marked as historical interest activity information, and a plurality of activity recommendation labels are generated by analyzing the historical interest activity information.
In particular, fig. 2 shows a flowchart of historical activity record data analysis in the method provided by the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the acquiring historical activity record data of a user, analyzing the historical activity record data, and generating a plurality of activity recommendation labels specifically includes the following steps:
in step S1011, historical activity record data of the user is acquired.
Step S1012, performing information extraction on the historical activity record data to obtain a plurality of pieces of historical activity information and corresponding activity evaluation information.
In step S1013, a plurality of pieces of historical interest activity information are marked from the plurality of pieces of historical activity information according to the plurality of pieces of activity evaluation information.
Further, the big data-based activity recommendation method further comprises the following steps:
step S102, current position data of a user are obtained, big data activity search is carried out according to the current position data, and activity search data are obtained.
In the embodiment of the invention, the user is positioned, the current position data of the user is obtained, the activity recommendation range is generated by taking the position corresponding to the current position data as the origin of coordinates according to the preset activity recommendation radius, the big data activity search is carried out in the activity recommendation range based on the big data technology, the activities held in the activity recommendation range within the preset time period are determined, and the activity search data is generated.
Specifically, fig. 3 shows a flowchart of big data activity search in the method provided by the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the acquiring current location data of a user, and performing big data active search according to the current location data, the acquiring active search data specifically includes the following steps:
step S1021, current position data of the user is acquired.
Step S1022, generating an activity recommendation range according to the current position data.
And S1023, performing big data activity search according to the activity recommendation range to acquire activity search data.
Further, the big data-based activity recommendation method further comprises the following steps:
step S103, screening the activity search data according to the plurality of activity recommendation labels, and acquiring a plurality of recommendation activities and corresponding activity information.
In the embodiment of the invention, the activity search data is subjected to activity screening on the basis of the plurality of activity recommendation labels to obtain a plurality of recommendation activities, and the activity information corresponding to the plurality of recommendation activities is obtained by performing activity analysis on the activity search data.
Specifically, fig. 4 shows a flowchart of active search data filtering in the method provided by the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the screening the activity search data according to the plurality of activity recommendation labels, and acquiring the plurality of recommended activities and corresponding activity information specifically includes the following steps:
and step S1031, screening the activity search data according to the plurality of activity recommendation labels, and obtaining a plurality of recommendation activities.
Step S1032, the activity search data is analyzed, and activity information corresponding to a plurality of recommended activities is obtained.
Further, the big data-based activity recommendation method further comprises the following steps:
and step S104, creating activity recommendation graphics and texts and activity recommendation videos corresponding to the plurality of recommended activities according to the plurality of activity information, and performing graphics and text recommendation and video recommendation.
In the embodiment of the invention, a preset recommendation image-text creating frame and a preset recommendation video creating frame are obtained, corresponding image-text information is divided and sorted in the recommendation image-text creating frame according to a plurality of activity information, activity recommendation images-text corresponding to a plurality of recommendation activities are created, corresponding video data are cut and sorted in the recommendation video creating frame according to the plurality of activity information, activity recommendation videos corresponding to the plurality of recommendation activities are created, recommendation connection data between the activity recommendation images-text corresponding to the plurality of same recommendation activities and the activity recommendation videos are created, and image-text recommendation and video recommendation are respectively performed in different recommendation scenes according to the plurality of activity recommendation images-text and the activity recommendation videos.
Specifically, fig. 5 shows a flowchart of the teletext recommendation and the video recommendation in the method provided by the embodiment of the invention.
In an embodiment of the present invention, the creating an activity recommendation image-text and an activity recommendation video corresponding to a plurality of recommended activities according to the plurality of activity information, and performing image-text recommendation and video recommendation specifically includes the following steps:
and step S1041, creating activity recommendation pictures and texts corresponding to a plurality of recommended activities according to the plurality of activity information.
Step S1042, creating an activity recommendation video corresponding to a plurality of recommended activities according to the plurality of activity information.
And step S1043, establishing recommendation contact data between the activity recommendation pictures and the activity recommendation videos corresponding to the multiple same recommendation activities.
And step S1044, respectively carrying out image-text recommendation and video recommendation according to the plurality of activity recommendation images and texts and the plurality of activity recommendation videos.
Further, the big data-based activity recommendation method further comprises the following steps:
and step S105, in the process of image-text recommendation and video recommendation, uninteresting recommendation images-texts or uninteresting recommendation videos marked by the user are obtained, and corresponding uninteresting recommendation videos or uninteresting recommendation images-texts are marked.
In the embodiment of the invention, in the process of image-text recommendation and video recommendation, when a user is not interested in browsed activity recommendation images-texts or activity recommendation videos, the corresponding activity recommendation images-texts or activity recommendation videos can be marked as uninteresting recommendation images-texts or uninteresting recommendation videos, the activity recommendation images-texts or uninteresting recommendation videos marked by the user are obtained, and then according to recommendation contact data, the activity recommendation videos connected with the uninteresting recommendation images-texts are marked as the uninteresting recommendation videos, or the activity recommendation images-texts connected with the uninteresting recommendation videos are marked as the uninteresting recommendation images-texts, so that the corresponding uninteresting recommendation images-texts and the uninteresting recommendation videos are not recommended.
Specifically, fig. 6 shows a flowchart of uninteresting adaptation in the method provided by the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the obtaining of uninteresting recommended pictures and texts or uninteresting recommended videos marked by a user in the picture and text recommendation and video recommendation processes specifically includes the following steps:
step S1051, in the process of image-text recommendation and video recommendation, uninteresting recommendation images-texts or uninteresting recommendation videos marked by the user are obtained.
And step 1052, marking the corresponding uninteresting recommended video or uninteresting recommended graphics and texts according to the recommended contact data.
Further, fig. 7 is a diagram illustrating an application architecture of the system according to the embodiment of the present invention.
In another preferred embodiment, the present invention provides a big data-based activity recommendation system, including:
the recommendation label generation unit 101 is configured to acquire historical activity record data of a user, analyze the historical activity record data, and generate a plurality of activity recommendation labels.
In the embodiment of the present invention, the recommendation tag generation unit 101 sends a history data application to a user, after the user agrees with the history data application, historical activity record data of the user recorded in the cloud database is obtained, historical activity information and activity evaluation information corresponding to a plurality of historical activities are obtained by analyzing and extracting the historical activity record data, then the recommendation tag generation unit 101 performs interest analysis on the activity evaluation information to generate an interest analysis result, determines whether the user is interested in the corresponding historical activity according to the interest analysis result, marks the historical activity information corresponding to the historical activity in which the user is interested as historical interest activity information, and performs tag analysis on the historical interest activity information to generate a plurality of activity recommendation tags.
Specifically, fig. 8 shows a block diagram of a structure of the recommended label generating unit 101 in the system according to the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the recommended label generating unit 101 specifically includes:
a historical data acquiring module 1011, configured to acquire historical activity record data of the user.
A data information extraction module 1012, configured to perform information extraction on the historical activity record data to obtain a plurality of historical activity information and corresponding activity evaluation information.
An activity information marking module 1013 configured to mark a plurality of historical interest activity information from a plurality of the historical activity information according to a plurality of the activity evaluation information.
And the activity information analysis module 1014 is configured to analyze a plurality of pieces of historical interest activity information to generate a plurality of activity recommendation tags.
Further, the big data based activity recommendation system further comprises:
the big data activity searching unit 102 is configured to obtain current location data of a user, perform big data activity search according to the current location data, and obtain activity search data.
In the embodiment of the present invention, the big data activity search unit 102 performs user positioning, acquires current position data of a user, generates an activity recommendation range by using a position corresponding to the current position data as an origin of coordinates according to a preset activity recommendation radius, performs big data activity search within the activity recommendation range based on a big data technology, determines activities held in the activity recommendation range within a preset time period, and generates activity search data.
Specifically, fig. 9 shows a block diagram of a structure of the big data activity search unit 102 in the system according to the embodiment of the present invention.
In an embodiment of the present invention, the big data activity searching unit 102 specifically includes:
a location obtaining module 1021, configured to obtain current location data of the user.
The location analysis module 1022 is configured to generate an activity recommendation range according to the current location data.
And the activity search module 1023 is used for searching big data activities according to the activity recommendation range to acquire activity search data.
Further, the big data based activity recommendation system further comprises:
and the search data screening unit 103 is configured to screen the activity search data according to the plurality of activity recommendation tags, and obtain a plurality of recommended activities and corresponding activity information.
In this embodiment of the present invention, the search data screening unit 103 performs activity screening on the activity search data based on the plurality of activity recommendation tags to obtain a plurality of recommended activities, and performs activity analysis on the activity search data to obtain activity information corresponding to the plurality of recommended activities.
And the image-text video recommending unit 104 is configured to create an activity recommendation image-text and an activity recommendation video corresponding to a plurality of recommended activities according to the plurality of activity information, and perform image-text recommendation and video recommendation.
In the embodiment of the present invention, the teletext video recommendation unit 104 obtains a preset teletext recommendation creation frame and a recommendation video creation frame, performs division and arrangement of corresponding teletext information in the teletext recommendation creation frame according to a plurality of activity information, creates activity recommendation teletext corresponding to a plurality of recommended activities, performs clipping and arrangement of corresponding video data in the recommendation video creation frame according to a plurality of activity information, creates activity recommendation videos corresponding to a plurality of recommended activities, establishes recommendation connection data between the activity recommendation teletext corresponding to a plurality of same recommended activities and the activity recommendation video, and performs teletext recommendation and video recommendation respectively in different recommendation scenes according to the plurality of activity recommendation teletext and activity recommendation videos.
Specifically, fig. 10 shows a block diagram of the structure of the teletext video recommendation unit 104 in the system according to the embodiment of the invention.
In a preferred embodiment provided by the present invention, the teletext video recommendation unit 104 specifically includes:
and a recommended graphics context creating module 1041, configured to create, according to the plurality of pieces of activity information, activity recommended graphics contexts corresponding to the plurality of recommended activities.
The recommended video creating module 1042 is configured to create an activity recommended video corresponding to a plurality of recommended activities according to the plurality of activity information.
And a recommendation relation establishing module 1043, configured to establish recommendation relation data between the activity recommendation graphics and the activity recommendation video corresponding to multiple identical recommendation activities.
And the image-text video recommending module 1044 is used for respectively recommending images and texts and recommending videos according to the plurality of activity recommending images and texts and the plurality of activity recommending videos.
Further, the big data based activity recommendation system further comprises:
and the user mark processing unit 105 is configured to obtain uninterested recommended pictures and texts or uninterested recommended videos marked by the user and mark corresponding uninterested recommended videos or uninterested recommended pictures and texts in the picture and text recommendation and video recommendation processes.
In the embodiment of the invention, in the process of image-text recommendation and video recommendation, when a user is uninteresting in browsed activity recommendation images-texts or activity recommendation videos, the corresponding activity recommendation images-texts or activity recommendation videos can be marked as uninteresting recommendation images-texts or uninteresting recommendation videos, and the user mark processing unit 105 marks the activity recommendation images-texts associated with the uninteresting recommendation images-texts as the uninteresting recommendation videos or marks the activity recommendation images-associated with the uninteresting recommendation videos as the uninteresting recommendation images-texts by obtaining the uninteresting recommendation images-texts or uninteresting recommendation videos marked by the user, according to recommendation contact data, so that the corresponding uninteresting recommendation images-texts and uninteresting recommendation videos are not recommended any more.
In summary, the embodiment of the present invention can analyze the historical activity record data of the user, generate a plurality of activity recommendation labels, perform data screening according to the plurality of activity recommendation labels, create a plurality of activity recommendation images and texts and associated activity recommendation videos, perform image and text recommendation and video recommendation, acquire the uninteresting marks of the user, and perform the associated uninteresting marks, thereby implementing accurate recommendation of activity recommendation, and changing the adaptability of activity recommendation according to the requirements of the user, so that the activity recommendation can meet the requirements of the user.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in sequence as indicated by the arrows, the steps are not necessarily performed in sequence as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a portion of the steps in various embodiments may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a non-volatile computer-readable storage medium, and can include the processes of the embodiments of the methods described above when the program is executed. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the embodiments described above may be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments described above are not described, but should be considered as being within the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. The activity recommendation method based on big data is characterized by specifically comprising the following steps of:
acquiring historical activity record data of a user, analyzing the historical activity record data, and generating a plurality of activity recommendation labels;
acquiring current position data of a user, and performing big data activity search according to the current position data to acquire activity search data;
screening the activity search data according to the plurality of activity recommendation labels to obtain a plurality of recommendation activities and corresponding activity information;
according to the plurality of pieces of activity information, activity recommendation graphics and activity recommendation videos corresponding to the plurality of recommended activities are created, and graphics recommendation and video recommendation are carried out;
in the process of image-text recommendation and video recommendation, uninteresting recommendation images-texts or uninteresting recommendation videos marked by a user are obtained, and corresponding uninteresting recommendation videos or uninteresting recommendation images-texts are marked.
2. The big data-based activity recommendation method according to claim 1, wherein the step of obtaining historical activity record data of the user, analyzing the historical activity record data, and generating a plurality of activity recommendation labels specifically comprises the steps of:
acquiring historical activity record data of a user;
extracting information from the historical activity record data to obtain a plurality of pieces of historical activity information and corresponding activity evaluation information;
marking a plurality of historical interest activity information from a plurality of the historical activity information according to a plurality of the activity evaluation information;
and analyzing the plurality of historical interest activity information to generate a plurality of activity recommendation labels.
3. The big data-based activity recommendation method according to claim 1, wherein the step of obtaining the current location data of the user and performing big data activity search according to the current location data specifically comprises the following steps:
acquiring current position data of a user;
generating an activity recommendation range according to the current position data;
and according to the activity recommendation range, performing big data activity search to obtain activity search data.
4. The big data-based activity recommendation method according to claim 1, wherein the step of filtering the activity search data according to the plurality of activity recommendation labels to obtain a plurality of recommended activities and corresponding activity information specifically comprises the steps of:
screening the activity search data according to the plurality of activity recommendation labels to obtain a plurality of recommendation activities;
and analyzing the activity search data to obtain activity information corresponding to a plurality of recommended activities.
5. The big data-based activity recommendation method according to claim 1, wherein the creating activity recommendation graphics and activity recommendation videos corresponding to a plurality of recommended activities according to the plurality of activity information, and performing the graphics and video recommendation specifically comprises the following steps:
creating activity recommendation pictures and texts corresponding to a plurality of recommended activities according to the plurality of activity information;
creating an activity recommendation video corresponding to a plurality of recommendation activities according to the plurality of activity information;
establishing recommendation contact data between activity recommendation pictures and activity recommendation videos corresponding to a plurality of same recommendation activities;
and respectively carrying out image-text recommendation and video recommendation according to the plurality of activity recommendation images-texts and the plurality of activity recommendation videos.
6. The big-data-based activity recommendation method according to claim 5, wherein during the teletext recommendation and video recommendation, uninteresting recommendation teletext or uninteresting recommendation video marked by the user is obtained, and marking the corresponding uninteresting recommendation video or uninteresting recommendation teletext specifically comprises the following steps:
in the process of image-text recommendation and video recommendation, uninteresting recommended images-texts or uninteresting recommended videos marked by a user are obtained;
and marking the corresponding uninteresting recommended video or uninteresting recommended graphics according to the recommended contact data.
7. The activity recommendation system based on big data is characterized by comprising a recommendation label generation unit, a big data activity search unit, a search data screening unit, a graphic video recommendation unit and a user mark processing unit, wherein:
the recommendation label generation unit is used for acquiring historical activity record data of a user, analyzing the historical activity record data and generating a plurality of activity recommendation labels;
the big data activity searching unit is used for acquiring current position data of a user, performing big data activity searching according to the current position data and acquiring activity searching data;
the search data screening unit is used for screening the activity search data according to the plurality of activity recommendation labels to acquire a plurality of recommendation activities and corresponding activity information;
the image-text video recommending unit is used for creating activity recommendation images and texts and activity recommendation videos corresponding to a plurality of recommendation activities according to the plurality of activity information and performing image-text recommendation and video recommendation;
and the user mark processing unit is used for acquiring uninterested image-texts or uninterested videos marked by the user and marking the corresponding uninterested recommended videos or uninterested images-texts in the image-text recommendation and video recommendation processes.
8. The big-data-based activity recommendation system according to claim 7, wherein the recommendation label generation unit specifically comprises:
the historical data acquisition module is used for acquiring historical activity record data of a user;
the data information extraction module is used for extracting information of the historical activity record data to obtain a plurality of pieces of historical activity information and corresponding activity evaluation information;
the activity information marking module is used for marking a plurality of historical interest activity information from a plurality of pieces of historical activity information according to a plurality of pieces of activity evaluation information;
and the activity information analysis module is used for analyzing the historical interest activity information to generate a plurality of activity recommendation labels.
9. The big-data-based activity recommendation system according to claim 7, wherein the big-data activity search unit specifically comprises:
the position acquisition module is used for acquiring current position data of a user;
the position analysis module is used for generating an activity recommendation range according to the current position data;
and the activity searching module is used for searching big data activities according to the activity recommendation range and acquiring activity searching data.
10. The big-data-based activity recommendation system according to claim 7, wherein the teletext video recommendation unit specifically comprises:
the recommendation image-text creating module is used for creating activity recommendation image-texts corresponding to a plurality of recommendation activities according to the activity information;
the recommendation video creating module is used for creating activity recommendation videos corresponding to a plurality of recommendation activities according to the activity information;
the recommendation relation establishing module is used for establishing recommendation relation data between activity recommendation pictures and activity recommendation videos corresponding to a plurality of same recommendation activities;
and the image-text video recommending module is used for respectively recommending image-text and video according to the plurality of activity recommending images-text and the plurality of activity recommending videos.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210777934.0A CN115033798A (en) | 2022-07-04 | 2022-07-04 | Activity recommendation method and system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210777934.0A CN115033798A (en) | 2022-07-04 | 2022-07-04 | Activity recommendation method and system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115033798A true CN115033798A (en) | 2022-09-09 |
Family
ID=83128085
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210777934.0A Pending CN115033798A (en) | 2022-07-04 | 2022-07-04 | Activity recommendation method and system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115033798A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110314040A1 (en) * | 2009-02-18 | 2011-12-22 | Yasuhide Mori | Method of recommending information, system thereof, and server |
| CN107248116A (en) * | 2017-06-07 | 2017-10-13 | 维沃移动通信有限公司 | A kind of activity recommendation method and mobile terminal |
| CN108460629A (en) * | 2018-02-10 | 2018-08-28 | 深圳壹账通智能科技有限公司 | User, which markets, recommends method, apparatus, terminal device and storage medium |
| CN109543111A (en) * | 2018-11-28 | 2019-03-29 | 广州虎牙信息科技有限公司 | Recommendation information screening technique, device, storage medium and server |
-
2022
- 2022-07-04 CN CN202210777934.0A patent/CN115033798A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110314040A1 (en) * | 2009-02-18 | 2011-12-22 | Yasuhide Mori | Method of recommending information, system thereof, and server |
| CN107248116A (en) * | 2017-06-07 | 2017-10-13 | 维沃移动通信有限公司 | A kind of activity recommendation method and mobile terminal |
| CN108460629A (en) * | 2018-02-10 | 2018-08-28 | 深圳壹账通智能科技有限公司 | User, which markets, recommends method, apparatus, terminal device and storage medium |
| CN109543111A (en) * | 2018-11-28 | 2019-03-29 | 广州虎牙信息科技有限公司 | Recommendation information screening technique, device, storage medium and server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108416003B (en) | Picture classification method and device, terminal and storage medium | |
| AU2017204338A1 (en) | Industry first method that uses users search query to show highly relevant poster frames for stock videos thereby resulting in great experience and more sales among users of stock video service | |
| CN109598171B (en) | Data processing method, device and system based on two-dimensional code | |
| US20150278248A1 (en) | Personal Information Management Service System | |
| CN109756760A (en) | Generation method, device and the server of video tab | |
| US11509836B1 (en) | Dynamically configured processing of a region of interest dependent upon published video data selected by a runtime configuration file | |
| CN107547922B (en) | Information processing method, device, system and computer readable storage medium | |
| CN112084812A (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN112291589A (en) | Video file structure detection method and device | |
| CN112925905B (en) | Method, device, electronic equipment and storage medium for extracting video subtitles | |
| CN111382281B (en) | Recommendation method, device, equipment and storage medium for content based on media object | |
| US20240040108A1 (en) | Method and system for preprocessing optimization of streaming video data | |
| CN108268488B (en) | Webpage main graph identification method and device | |
| CN112528832A (en) | Method and system for processing PDF-format relay protection fixed value list | |
| CN115033798A (en) | Activity recommendation method and system based on big data | |
| CN115357689B (en) | Data processing method, device and medium of distributed log and computer equipment | |
| CN114817585A (en) | Multimedia resource processing method and device, electronic equipment and storage medium | |
| KR102444172B1 (en) | Method and System for Intelligent Mining of Digital Image Big-Data | |
| CN106874684A (en) | A kind of image labeling system and method | |
| CN111382343B (en) | Label system generation method and device | |
| CN113869043A (en) | Content labeling method, device, equipment and storage medium | |
| CN115484474A (en) | Video clip processing method, device, electronic equipment and storage medium | |
| CN113762031A (en) | Image identification method, device, equipment and storage medium | |
| WO2020106355A1 (en) | Printing relevant content | |
| US20240037915A1 (en) | Method and system for preprocessing optimization of streaming video data using machine learning |
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 |