CN114579916B - Big data based information recommendation method and system - Google Patents
Big data based information recommendation method and system Download PDFInfo
- Publication number
- CN114579916B CN114579916B CN202210487674.3A CN202210487674A CN114579916B CN 114579916 B CN114579916 B CN 114579916B CN 202210487674 A CN202210487674 A CN 202210487674A CN 114579916 B CN114579916 B CN 114579916B
- Authority
- CN
- China
- Prior art keywords
- information
- browsing
- screening
- data
- interest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the invention relates to the technical field of information recommendation, and particularly discloses an information recommendation method and system based on big data. According to the embodiment of the invention, activity analysis is carried out; carrying out browsing information statistics and screening on the active browsing data; performing label identification on the inactive browsing data; and recommending the plurality of interest recommendation information to the inactive users corresponding to the inactive browsing data. According to the method, liveness analysis can be carried out according to information browsing data of a plurality of users, browsing information statistics and screening are carried out on the active browsing data of the active users, tag identification is carried out, a tag information arrangement database is obtained, and then corresponding information with high browsing capacity of the active users can be recommended by matching with interest recommendation information from the tag information arrangement database through interest tags of the inactive users, so that the information recommended to the inactive users meets the interests of the users as far as possible, and the liveness of the inactive users is prevented from being lower and lower.
Description
Technical Field
The invention belongs to the technical field of information recommendation, and particularly relates to an information recommendation method and system based on big data.
Background
With the development of big data technology and various software technologies, information recommendation becomes more important, especially in news information software, the online time of a user can be increased only by recommending contents meeting the user interest, more active users are ensured, and the development of the software is further promoted.
The existing information recommendation method generally recommends related information according to the interest types selected by users, and although the information recommendation method can recommend some interesting contents to the users to a certain extent, most of the information cannot really arouse the interests of the users, especially for some users with low liveness, in the recommended information, if most of the contents cannot arouse the interests of the users, the liveness of the users may be reduced.
Disclosure of Invention
The embodiment of the invention aims to provide an information 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:
an information recommendation method based on big data specifically comprises the following steps:
acquiring information browsing data of a plurality of users based on a big data technology;
performing liveness analysis on the information browsing data, respectively marking the information browsing data as active browsing data and inactive browsing data according to an analysis result, and respectively marking corresponding users as active users and inactive users;
the method comprises the steps of counting and screening browsing information of a plurality of active browsing data, obtaining a plurality of screening information and corresponding browsing amount, carrying out label identification on the plurality of screening information to obtain a plurality of screening labels, and carrying out information arrangement and arrangement by integrating the plurality of screening information, the plurality of browsing amount and the plurality of screening labels to obtain a label information arrangement database;
performing label identification on the inactive browsing data to obtain a plurality of interest labels, and performing information matching in the label information arrangement database according to the interest labels to obtain a plurality of interest recommendation information and a recommendation sequence;
and recommending the plurality of interest recommendation information to the inactive users corresponding to the inactive browsing data according to the recommendation sequence.
As a further limitation of the technical solution of the embodiment of the present invention, the activity analysis of the plurality of information browsing data, and according to the analysis result, the marking of the plurality of information browsing data as active browsing data and inactive browsing data, and the marking of the corresponding users as active users and inactive users respectively specifically includes the following steps:
performing liveness analysis on the information browsing data to generate a plurality of liveness scores;
comparing a plurality of the liveness scores with a preset standard score;
marking the information browsing data with the liveness score larger than the standard score as active browsing data, and marking the corresponding user as an active user;
and marking the information browsing data with the liveness score not greater than the standard score as inactive browsing data, and marking the corresponding user as an inactive user.
As a further limitation of the technical solution of the embodiment of the present invention, the performing liveness analysis on the plurality of information browsing data and generating a plurality of liveness scores specifically includes the following steps:
performing registration duration analysis according to the information browsing data to obtain registration durations of a plurality of users;
carrying out browsing duration statistics according to the information browsing data to obtain a plurality of user browsing durations;
and integrating a plurality of user registration time lengths and corresponding user browsing time lengths to evaluate the activity degree, and generating a plurality of activity degree scores.
As a further limitation of the technical solution of the embodiment of the present invention, the counting and screening browsing information on a plurality of active browsing data, obtaining a plurality of screening information and corresponding browsing amount, performing tag identification on a plurality of screening information to obtain a plurality of screening tags, and performing information arrangement and sorting by integrating the plurality of screening information, the plurality of browsing amount, and the plurality of screening tags to obtain a tag information arrangement database specifically includes the following steps:
carrying out browsing information statistics and screening on the plurality of active browsing data to obtain a plurality of screening information and corresponding browsing amount;
performing label identification on the screening information to obtain a plurality of screening labels;
and arranging and sorting the information of the screening information and the corresponding screening labels according to the browsing amount to obtain a label information arrangement database.
As a further limitation of the technical solution of the embodiment of the present invention, the counting and screening browsing information of the plurality of active browsing data to obtain a plurality of screening information and corresponding browsing amount specifically includes the following steps:
counting the browsing amount of a plurality of browsing information in a plurality of active browsing data;
and removing browsing information with the browsing amount smaller than a preset standard amount, and acquiring a plurality of screening information and corresponding browsing amounts.
As a further limitation of the technical solution of the embodiment of the present invention, the tag identifying the inactive browsing data to obtain a plurality of interest tags, and performing information matching in the tag information arrangement database according to the plurality of interest tags to obtain a plurality of interest recommendation information and recommendation sequences specifically includes the following steps:
analyzing the inactive browsing data to acquire a plurality of interest information;
performing label identification on the interest information to obtain a plurality of interest labels;
and according to the interest labels, performing information matching in the label information arrangement database to obtain a plurality of interest recommendation information and recommendation sequences.
The information recommendation system based on big data comprises a browsing data acquisition unit, an active analysis processing unit, an active data processing unit, an interest information matching unit and an interest information recommendation unit, wherein:
the browsing data acquisition unit is used for acquiring information browsing data of a plurality of users based on a big data technology;
the active analysis processing unit is used for carrying out activity analysis on the information browsing data, marking the information browsing data as active browsing data and inactive browsing data respectively according to the analysis result, and marking corresponding users as active users and inactive users respectively;
the active data processing unit is used for counting and screening browsing information of the active browsing data, acquiring a plurality of screening information and corresponding browsing amount, performing label identification on the screening information to obtain a plurality of screening labels, and performing information arrangement and sorting by integrating the screening information, the browsing amount and the screening labels to obtain a label information arrangement database;
the interest information matching unit is used for carrying out label identification on the inactive browsing data to obtain a plurality of interest labels, and carrying out information matching in the label information arrangement database according to the interest labels to obtain a plurality of interest recommendation information and a recommendation sequence;
and the interest information recommending unit is used for recommending the interest recommendation information to the inactive users corresponding to the inactive browsing data according to the recommending sequence.
As a further limitation of the technical solution of the embodiment of the present invention, the activity analysis processing unit specifically includes:
the activity analysis module is used for carrying out activity analysis on the information browsing data to generate a plurality of activity scores;
the score comparison module is used for comparing a plurality of activity scores with a preset standard score;
the active data marking module is used for marking the information browsing data with the liveness score larger than the standard score as active browsing data and marking the corresponding user as an active user;
and the inactive data marking module is used for marking the information browsing data with the liveness score not greater than the standard score as inactive browsing data and marking the corresponding user as an inactive user.
As a further limitation of the technical solution of the embodiment of the present invention, the active data processing unit specifically includes:
the information counting and screening module is used for counting and screening browsing information of the active browsing data to obtain a plurality of screening information and corresponding browsing amount;
the screening label identification module is used for carrying out label identification on the screening information to obtain a plurality of screening labels;
and the information arrangement and arrangement module is used for carrying out information arrangement and arrangement on the screening information and the corresponding screening labels according to the browsing amount to obtain a label information arrangement database.
As a further limitation of the technical solution of the embodiment of the present invention, the interest information matching unit specifically includes:
the interest information acquisition module is used for analyzing the inactive browsing data to acquire a plurality of interest information;
the interest tag identification module is used for carrying out tag identification on the interest information to obtain a plurality of interest tags;
and the interest information matching module is used for performing information matching in the tag information arrangement database according to the plurality of interest tags to obtain a plurality of interest recommendation information and recommendation sequences.
Compared with the prior art, the invention has the beneficial effects that:
according to the embodiment of the invention, activity analysis is carried out; carrying out browsing information statistics and screening on the active browsing data; performing label identification on the inactive browsing data; and recommending the plurality of interest recommendation information to the inactive users corresponding to the inactive browsing data. According to the method, liveness analysis can be carried out according to information browsing data of a plurality of users, browsing information statistics and screening are carried out on the active browsing data of the active users, tag identification is carried out, a tag information arrangement database is obtained, and then corresponding information with high browsing capacity of the active users can be recommended by matching with interest recommendation information from the tag information arrangement database through interest tags of the inactive users, so that the information recommended to the inactive users meets the interests of the users as far as possible, and the liveness of the inactive users is prevented from being lower and lower.
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 is a flowchart illustrating an activity analysis flag in the method according to the embodiment of the present invention.
Fig. 3 is a flowchart illustrating the activity score generation in the method provided by the embodiment of the present invention.
Fig. 4 shows a flowchart of generating a tag information arrangement database in the method provided by the embodiment of the present invention.
Fig. 5 is a flowchart illustrating statistics and filtering of browsing information in the method according to the embodiment of the present invention.
Fig. 6 shows a flowchart of interest tag information matching in the method provided by the embodiment of the present 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 an active analysis processing unit in the system according to an embodiment of the present invention.
Fig. 9 shows a block diagram of an active data processing unit in the system according to the embodiment of the present invention.
Fig. 10 shows a block diagram of a structure of an interest information matching unit in the system provided by the 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, information recommendation methods generally recommend related information according to the interest types selected by the user, and although such information recommendation methods can recommend some interesting contents to the user to some extent, most of the information cannot really arouse the interest of the user, especially for some users with low liveness, in the recommended information, if a large number of contents cannot arouse the interest of the user, the liveness of the user may be lower and lower.
In order to solve the above problems, the embodiment of the present invention performs liveness analysis; carrying out browsing information statistics and screening on the active browsing data; performing label identification on the inactive browsing data; and recommending the plurality of interest recommendation information to the inactive users corresponding to the inactive browsing data. According to the method, liveness analysis can be carried out according to information browsing data of a plurality of users, browsing information statistics and screening are carried out on the active browsing data of the active users, tag identification is carried out, a tag information arrangement database is obtained, and then corresponding information with high browsing capacity of the active users can be recommended by matching with interest recommendation information from the tag information arrangement database through interest tags of the inactive users, so that the information recommended to the inactive users meets the interests of the users as far as possible, and the liveness of the inactive users is prevented from being lower and lower.
Fig. 1 shows a flow chart of a method provided by an embodiment of the invention.
Specifically, the method for recommending information based on big data specifically comprises the following steps:
step S101, based on big data technology, information browsing data of a plurality of users are obtained.
In the embodiment of the invention, browsing data access requests are sent to a plurality of users, and after the plurality of users approve the browsing data access requests, information browsing data of the plurality of users are accessed and obtained based on a big data technology.
It is to be understood that the information browsing data is recorded data of news information browsed by the user, and records the news information browsed by the user after registration and browsing time.
Step S102, performing liveness analysis on the plurality of information browsing data, respectively marking the plurality of information browsing data as active browsing data and inactive browsing data according to the analysis result, and respectively marking corresponding users as active users and inactive users.
In the embodiment of the invention, registration time length analysis is carried out on a plurality of information browsing data to obtain a plurality of user registration time lengths, browsing time length statistics is carried out on the plurality of information browsing data to obtain a plurality of user browsing time lengths, the user browsing time length of each user is divided by the user registration time length to obtain an active proportion value, activity evaluation is carried out according to the active proportion value to generate activity scores corresponding to each user, the plurality of activity scores are compared with a preset standard score, the information browsing data with the activity scores larger than the standard score are marked as active browsing data, and the users corresponding to the active browsing data are marked as active users; and marking the information browsing data with the liveness score not greater than the standard score as inactive browsing data, and marking the corresponding user as an inactive user.
It will be appreciated that active users have more frequent information browsing records after registration, while inactive users have fewer information browsing records after registration.
Specifically, fig. 2 shows a flowchart of activity analysis tagging in the method provided by the embodiment of the present invention.
In a preferred embodiment of the present invention, the activity analyzing the information browsing data, respectively marking the information browsing data as active browsing data and inactive browsing data according to an analysis result, and respectively marking corresponding users as active users and inactive users specifically includes the following steps:
step S1021, performing liveness analysis on the information browsing data to generate a plurality of liveness scores.
Specifically, fig. 3 shows a flowchart of generating an activity score in the method provided by the embodiment of the present invention.
In an embodiment of the present invention, the activity analysis of the information browsing data to generate a plurality of activity scores includes:
step S10211, according to the information browsing data, performing registration duration analysis to obtain a plurality of user registration durations.
Step S10212, browsing duration statistics is carried out according to the information browsing data to obtain browsing durations of a plurality of users.
Step S10213, integrating a plurality of user registration time lengths and corresponding user browsing time lengths to evaluate the activity degree, and generating a plurality of activity degree scores.
Further, the activity analysis of the plurality of information browsing data, the marking of the plurality of information browsing data as active browsing data and inactive browsing data, and the marking of the corresponding users as active users and inactive users, respectively, further includes the following steps:
step S1022, comparing the plurality of activity scores with a preset standard score.
And step S1023, marking the information browsing data with the liveness score larger than the standard score as active browsing data, and marking the corresponding user as an active user.
Step S1024, marking the information browsing data with the liveness score not larger than the standard score as inactive browsing data, and marking the corresponding user as an inactive user.
Further, the big data-based information recommendation method further comprises the following steps:
step S103, counting and screening browsing information of the plurality of active browsing data, obtaining a plurality of screening information and corresponding browsing amount, performing tag identification on the plurality of screening information to obtain a plurality of screening tags, and performing information arrangement and sorting by integrating the plurality of screening information, the plurality of browsing amount, and the plurality of screening tags to obtain a tag information arrangement database.
In the embodiment of the invention, the browsing amount of the same browsing information in a plurality of active browsing data is counted, the browsing information of which the browsing amount is smaller than a preset standard amount is removed, the reserved browsing information is marked as screening information, so that a plurality of screening information and corresponding browsing amount are obtained, a plurality of screening labels corresponding to different screening information are obtained by performing label identification on the plurality of screening information, the screening labels and the browsing amount corresponding to each screening information are sorted, and the screening labels and the browsing amount are arranged according to the browsing amount to generate a label information arrangement database.
Specifically, fig. 4 shows a flowchart of generating a tag information arrangement database in the method provided by the embodiment of the present invention.
In a preferred embodiment of the present invention, the counting and screening browsing information on a plurality of active browsing data, obtaining a plurality of screening information and corresponding browsing amount, performing tag identification on a plurality of screening information, obtaining a plurality of screening tags, and performing information arrangement and sorting by integrating the plurality of screening information, the plurality of browsing amount, and the plurality of screening tags, to obtain a tag information arrangement database specifically includes the following steps:
and step S1031, carrying out browsing information statistics and screening on the plurality of active browsing data, and acquiring a plurality of screening information and corresponding browsing amount.
Specifically, fig. 5 shows a flowchart of browsing information statistics and screening in the method provided by the embodiment of the present invention.
In a preferred embodiment of the present invention, the counting and screening browsing information of the plurality of active browsing data to obtain a plurality of screening information and corresponding browsing amount specifically includes the following steps:
step S10311, counting browsing amounts of a plurality of browsing information in a plurality of active browsing data.
And step S10312, removing the browsing information with the browsing amount smaller than the preset standard amount, and acquiring a plurality of screening information and corresponding browsing amounts.
Further, the counting and screening of browsing information on the multiple active browsing data to obtain multiple screening information and corresponding browsing volume, performing label identification on the multiple screening information to obtain multiple screening labels, and performing information arrangement and sorting by integrating the multiple screening information, the multiple browsing volume, and the multiple screening labels to obtain a label information arrangement database further includes the following steps:
step S1032, performing label identification on the plurality of screening information to obtain a plurality of screening labels.
Step S1033, according to the plurality of browsing volumes, performing information arrangement and sorting on the plurality of screening information and the corresponding screening labels to obtain a label information arrangement database.
Further, the big data-based information recommendation method further comprises the following steps:
and step S104, performing label identification on the inactive browsing data to obtain a plurality of interest labels, and performing information matching in the label information arrangement database according to the plurality of interest labels to obtain a plurality of interest recommendation information and a recommendation sequence.
In the embodiment of the invention, the inactive browsing data corresponding to each inactive user is analyzed, interest information identification is carried out according to information browsing duration, information praise, information collection, information forwarding and the like to obtain a plurality of interest information, tag identification is carried out on the plurality of interest information to obtain a plurality of interest tags, information matching is carried out in a tag information arrangement database through the plurality of interest tags to obtain screening information with the same screening tags as the interest tags, the screening information is marked as interest recommendation information, recommendation sequencing is carried out according to the browsing quantity of the plurality of interest recommendation information, and a recommendation sequence is generated.
It can be understood that the interest labels of each inactive user are different, the generated interest recommendation information is different, and the recommendation sequence is also different.
Specifically, fig. 6 shows a flowchart of interest tag information matching in the method provided by the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the tag identifying the inactive browsing data to obtain a plurality of interest tags, and performing information matching in the tag information arrangement database according to the plurality of interest tags to obtain a plurality of interest recommendation information and recommendation sequences specifically includes the following steps:
step S1041, analyzing the inactive browsing data to obtain a plurality of interest information.
Step S1042, performing tag identification on the plurality of interest information to obtain a plurality of interest tags.
And step S1043, performing information matching in the tag information arrangement database according to the plurality of interest tags to obtain a plurality of interest recommendation information and recommendation sequences.
Further, the big data-based information recommendation method further comprises the following steps:
step S105, recommending the interest recommendation information to the inactive users corresponding to the inactive browsing data according to the recommendation sequence.
In the embodiment of the invention, when the inactive user browses the information again, the plurality of interest recommendation information are recommended to the inactive user in sequence according to the recommendation sequence, if the inactive user pauses or closes the information browsing, the information recommendation is continued at the last paused or closed interest recommendation information according to the recommendation sequence after the next browsing is started.
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 information recommendation system, including:
a browsing data obtaining unit 101, configured to obtain information browsing data of multiple users based on big data technology.
In the embodiment of the present invention, the browsing data acquisition unit 101 sends browsing data access requests to a plurality of users, and after the plurality of users approve the browsing data access requests, information browsing data of the plurality of users is accessed and acquired based on a big data technology.
And the active analysis processing unit 102 is configured to perform activity analysis on the multiple pieces of information browsing data, mark the multiple pieces of information browsing data as active browsing data and inactive browsing data according to an analysis result, and mark corresponding users as active users and inactive users respectively.
In the embodiment of the present invention, the activity analysis processing unit 102 performs registration duration analysis on a plurality of information browsing data to obtain a plurality of user registration durations, performs browsing duration statistics on a plurality of information browsing data to obtain a plurality of user browsing durations, divides the user browsing duration of each user by the user registration duration to obtain an activity ratio value, performs activity evaluation according to the activity ratio value to generate an activity score corresponding to each user, compares the activity scores with a preset standard score, marks information browsing data with an activity score larger than the standard score as active browsing data, and marks the user corresponding to the active browsing data as an active user; and marking the information browsing data with the liveness score not greater than the standard score as inactive browsing data, and marking the corresponding user as an inactive user.
Specifically, fig. 8 shows a block diagram of the active analysis processing unit 102 in the system according to the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the activity analysis processing unit 102 specifically includes:
and an activity analysis module 1021, configured to perform activity analysis on the multiple information browsing data to generate multiple activity scores.
A score comparing module 1022, configured to compare the plurality of liveness scores with a preset standard score.
And an active data marking module 1023, configured to mark the information browsing data with the liveness score greater than the standard score as active browsing data, and mark the corresponding user as an active user.
And an inactive data tagging module 1024, configured to tag the information browsing data with the liveness score not greater than the standard score as inactive browsing data, and tag a corresponding user as an inactive user.
Further, the big data-based information recommendation system further includes:
and the active data processing unit 103 is configured to count and filter browsing information of the plurality of active browsing data, obtain a plurality of filtering information and corresponding browsing amount, perform tag identification on the plurality of filtering information to obtain a plurality of filtering tags, and perform information arrangement and sorting by integrating the plurality of filtering information, the plurality of browsing amount, and the plurality of filtering tags to obtain a tag information arrangement database.
In the embodiment of the present invention, the active data processing unit 103 counts the browsing amount of the same browsing information in the multiple active browsing data, removes browsing information whose browsing amount is smaller than a preset standard amount, marks the remaining browsing information as screening information, thereby obtaining multiple screening information and corresponding browsing amount, obtains multiple screening labels corresponding to different screening information by performing label identification on the multiple screening information, arranges the screening labels and browsing amount corresponding to each screening information, and generates a label information arrangement database according to the size of the browsing amount.
Specifically, fig. 9 shows a block diagram of the active data processing unit 103 in the system according to the embodiment of the present invention.
In a preferred embodiment provided by the present invention, the active data processing unit 103 specifically includes:
and an information statistics and screening module 1031, configured to perform browsing information statistics and screening on the multiple active browsing data, and obtain multiple screening information and corresponding browsing volumes.
The screening tag identification module 1032 is configured to perform tag identification on the plurality of screening information to obtain a plurality of screening tags.
And an information arrangement and sorting module 1033, configured to perform information arrangement and sorting on the multiple pieces of screening information and the corresponding screening tags according to the multiple browsing volumes, so as to obtain a tag information arrangement database.
Further, the big data-based information recommendation system further includes:
an interest information matching unit 104, configured to perform tag identification on the inactive browsing data to obtain a plurality of interest tags, and perform information matching in the tag information arrangement database according to the plurality of interest tags to obtain a plurality of interest recommendation information and a recommendation order.
In the embodiment of the present invention, the interest information matching unit 104 analyzes the inactive browsing data corresponding to each inactive user, performs interest information identification according to information browsing duration, information approval, information collection, information forwarding, and the like to obtain a plurality of interest information, performs tag identification on the plurality of interest information to obtain a plurality of interest tags, performs information matching in a tag information arrangement database through the plurality of interest tags to obtain screening information in which the plurality of screening tags are the same as the interest tags, marks the screening information as interest recommendation information, performs recommendation sorting according to the browsing amount of the plurality of interest recommendation information, and generates a recommendation sequence.
Specifically, fig. 10 shows a block diagram of the structure of the interest information matching unit 104 in the system provided by the embodiment of the present invention.
In an embodiment of the present invention, the interest information matching unit 104 specifically includes:
an interest information obtaining module 1041, configured to analyze the inactive browsing data, and obtain a plurality of interest information.
The interest tag identifying module 1042 is configured to perform tag identification on the multiple pieces of interest information to obtain multiple interest tags.
An interest information matching module 1043, configured to perform information matching in the tag information arrangement database according to the multiple interest tags, so as to obtain multiple interest recommendation information and recommendation sequences.
Further, the big data-based information recommendation system further includes:
an interest information recommending unit 105, configured to recommend, according to the recommendation order, the multiple pieces of interest recommendation information to the inactive user corresponding to the inactive browsing data.
In the embodiment of the present invention, when the inactive user browses information again, the interest information recommending unit 105 recommends a plurality of interest recommendation information to the inactive user in sequence according to the recommendation order, and if the inactive user suspends or closes information browsing, information recommendation is continued at the interest recommendation information that was suspended or closed last time according to the recommendation order after the next browsing is started.
In summary, the embodiments of the present invention can perform liveness analysis according to the information browsing data of multiple users, perform browsing information statistics and screening on the active browsing data of the active users, perform tag identification to obtain a tag information arrangement database, and then perform recommendation by matching the interest recommendation information in the tag information arrangement database through the interest tags of the inactive users, so that corresponding information with a high browsing volume of the active users can be recommended according to the interests of the inactive users, so that the information recommended to the inactive users meets the interests of the users as much as possible, and the liveness of the inactive users is prevented from becoming lower.
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 performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. 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. An information recommendation method based on big data is characterized by specifically comprising the following steps:
acquiring information browsing data of a plurality of users based on a big data technology;
performing liveness analysis on the information browsing data, respectively marking the information browsing data as active browsing data and inactive browsing data according to an analysis result, and respectively marking corresponding users as active users and inactive users;
the method comprises the steps of counting and screening browsing information of a plurality of active browsing data, obtaining a plurality of screening information and corresponding browsing amount, carrying out label identification on the plurality of screening information to obtain a plurality of screening labels, and carrying out information arrangement and arrangement by integrating the plurality of screening information, the plurality of browsing amount and the plurality of screening labels to obtain a label information arrangement database;
performing label identification on the inactive browsing data to obtain a plurality of interest labels, and performing information matching in the label information arrangement database according to the interest labels to obtain a plurality of interest recommendation information and a recommendation sequence;
recommending the interest recommendation information to the inactive users corresponding to the inactive browsing data according to the recommendation sequence;
and when the inactive user browses the information again, sequentially recommending a plurality of interest recommendation information to the inactive user according to a recommendation sequence, and if the inactive user pauses or closes the information browsing, continuing to recommend the information at the last paused or closed interest recommendation information according to the recommendation sequence after the next browsing is started.
2. The big data-based information recommendation method according to claim 1, wherein the activity analysis of the plurality of information browsing data, the marking of the plurality of information browsing data as active browsing data and inactive browsing data respectively according to the analysis result, and the marking of the corresponding users as active users and inactive users respectively comprises the following steps:
performing liveness analysis on the information browsing data to generate a plurality of liveness scores;
comparing a plurality of the liveness scores with a preset standard score;
marking the information browsing data with the liveness score larger than the standard score as active browsing data, and marking the corresponding user as an active user;
and marking the information browsing data with the liveness score not greater than the standard score as inactive browsing data, and marking the corresponding user as an inactive user.
3. The big data-based information recommendation method according to claim 2, wherein the activity analysis is performed on the plurality of information browsing data, and the generating of the plurality of activity scores specifically comprises the following steps:
analyzing registration duration according to the information browsing data to obtain registration durations of a plurality of users;
carrying out browsing duration statistics according to the information browsing data to obtain a plurality of user browsing durations;
and integrating a plurality of user registration time lengths and corresponding user browsing time lengths to evaluate the activity degree, and generating a plurality of activity degree scores.
4. The big data-based information recommendation method according to claim 1, wherein the step of performing browsing information statistics and screening on the plurality of active browsing data to obtain a plurality of screening information and corresponding browsing amount, performing tag identification on the plurality of screening information to obtain a plurality of screening tags, and performing information arrangement and sorting by integrating the plurality of screening information, the plurality of browsing amount, and the plurality of screening tags to obtain a tag information arrangement database specifically includes the steps of:
carrying out browsing information statistics and screening on the plurality of active browsing data to obtain a plurality of screening information and corresponding browsing amount;
performing label identification on the screening information to obtain a plurality of screening labels;
and arranging and sorting the information of the screening information and the corresponding screening labels according to the browsing amount to obtain a label information arrangement database.
5. The big data-based information recommendation method according to claim 4, wherein the step of performing browsing information statistics and screening on the plurality of active browsing data to obtain a plurality of screening information and corresponding browsing volumes specifically comprises the steps of:
counting the browsing amount of a plurality of browsing information in a plurality of active browsing data;
and removing browsing information with the browsing amount smaller than a preset standard amount, and acquiring a plurality of screening information and corresponding browsing amounts.
6. The big data-based information recommendation method according to claim 1, wherein the tag identification of the inactive browsing data to obtain a plurality of interest tags, and the information matching in the tag information arrangement database according to the plurality of interest tags to obtain a plurality of interest recommendation information and recommendation sequence specifically comprises the following steps:
analyzing the inactive browsing data to acquire a plurality of interest information;
performing label identification on the interest information to obtain a plurality of interest labels;
and according to the interest labels, performing information matching in the label information arrangement database to obtain a plurality of interest recommendation information and recommendation sequences.
7. The big data-based information recommendation system is characterized by comprising a browsing data acquisition unit, an active analysis processing unit, an active data processing unit, an interest information matching unit and an interest information recommendation unit, wherein:
the browsing data acquisition unit is used for acquiring information browsing data of a plurality of users based on a big data technology;
the active analysis processing unit is used for carrying out activity analysis on the information browsing data, marking the information browsing data as active browsing data and inactive browsing data respectively according to the analysis result, and marking corresponding users as active users and inactive users respectively;
the active data processing unit is used for counting and screening browsing information of the active browsing data, acquiring a plurality of screening information and corresponding browsing amount, performing label identification on the screening information to obtain a plurality of screening labels, and performing information arrangement and sorting by integrating the screening information, the browsing amount and the screening labels to obtain a label information arrangement database;
the interest information matching unit is used for carrying out label identification on the inactive browsing data to obtain a plurality of interest labels, and carrying out information matching in the label information arrangement database according to the interest labels to obtain a plurality of interest recommendation information and a recommendation sequence;
and the interest information recommending unit is used for recommending the interest recommendation information to the inactive users corresponding to the inactive browsing data according to the recommending sequence.
8. The big-data-based information recommendation system according to claim 7, wherein the activity analysis processing unit specifically comprises:
the activity analysis module is used for carrying out activity analysis on the information browsing data to generate a plurality of activity scores;
the score comparison module is used for comparing a plurality of activity scores with a preset standard score;
the active data marking module is used for marking the information browsing data with the liveness score larger than the standard score as active browsing data and marking the corresponding user as an active user;
and the inactive data marking module is used for marking the information browsing data with the liveness score not greater than the standard score as inactive browsing data and marking the corresponding user as an inactive user.
9. The big-data-based information recommendation system according to claim 7, wherein the active data processing unit specifically comprises:
the information counting and screening module is used for counting and screening browsing information of the active browsing data to obtain a plurality of screening information and corresponding browsing amount;
the screening label identification module is used for carrying out label identification on the screening information to obtain a plurality of screening labels;
and the information arrangement and arrangement module is used for carrying out information arrangement and arrangement on the screening information and the corresponding screening labels according to the browsing amount to obtain a label information arrangement database.
10. The big-data-based information recommendation system according to claim 7, wherein the interest information matching unit specifically comprises:
the interest information acquisition module is used for analyzing the inactive browsing data to acquire a plurality of interest information;
the interest tag identification module is used for carrying out tag identification on the interest information to obtain a plurality of interest tags;
and the interest information matching module is used for performing information matching in the tag information arrangement database according to the plurality of interest tags to obtain a plurality of interest recommendation information and recommendation sequences.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210487674.3A CN114579916B (en) | 2022-05-06 | 2022-05-06 | Big data based information recommendation method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210487674.3A CN114579916B (en) | 2022-05-06 | 2022-05-06 | Big data based information recommendation method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114579916A CN114579916A (en) | 2022-06-03 |
| CN114579916B true CN114579916B (en) | 2022-07-29 |
Family
ID=81768965
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210487674.3A Active CN114579916B (en) | 2022-05-06 | 2022-05-06 | Big data based information recommendation method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114579916B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014071529A (en) * | 2012-09-27 | 2014-04-21 | Dainippon Printing Co Ltd | Information processor, information processing method and information processing program |
| WO2017128433A1 (en) * | 2016-01-31 | 2017-08-03 | 胡明祥 | Information pushing method during recommendation update, and pushing system |
| 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 |
| CN111159578A (en) * | 2019-12-31 | 2020-05-15 | 第四范式（北京）技术有限公司 | Method and system for recommending object |
| CN112733023A (en) * | 2020-12-30 | 2021-04-30 | 平安科技（深圳）有限公司 | Information pushing method and device, electronic equipment and computer readable storage medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160203523A1 (en) * | 2014-02-21 | 2016-07-14 | Lithium Technologies, Inc. | Domain generic large scale topic expertise and interest mining across multiple online social networks |
| CN113378071A (en) * | 2021-08-16 | 2021-09-10 | 武汉卓尔数字传媒科技有限公司 | Advertisement recommendation method and device, electronic equipment and storage medium |
-
2022
- 2022-05-06 CN CN202210487674.3A patent/CN114579916B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2014071529A (en) * | 2012-09-27 | 2014-04-21 | Dainippon Printing Co Ltd | Information processor, information processing method and information processing program |
| WO2017128433A1 (en) * | 2016-01-31 | 2017-08-03 | 胡明祥 | Information pushing method during recommendation update, and pushing system |
| 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 |
| CN111159578A (en) * | 2019-12-31 | 2020-05-15 | 第四范式（北京）技术有限公司 | Method and system for recommending object |
| CN112733023A (en) * | 2020-12-30 | 2021-04-30 | 平安科技（深圳）有限公司 | Information pushing method and device, electronic equipment and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114579916A (en) | 2022-06-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CA3177209A1 (en) | Data cleaning method | |
| CN109376237B (en) | Client stability prediction method, device, computer equipment and storage medium | |
| CN107797894B (en) | APP user behavior analysis method and device | |
| CN107592346B (en) | User classification method based on user behavior analysis | |
| CN110674144A (en) | User portrait generation method and device, computer equipment and storage medium | |
| CN111831629A (en) | Data processing method and device | |
| CN111210356B (en) | Medical insurance data analysis method and device, computer equipment and storage medium | |
| CN107832333A (en) | Method and system based on distributed treatment and DPI data structure user network data fingerprint | |
| CN109086938B (en) | Product SKU identification method and device and computer readable storage medium | |
| CN114579916B (en) | Big data based information recommendation method and system | |
| CN115357689B (en) | Data processing method, device and medium of distributed log and computer equipment | |
| CN116662327A (en) | Data fusion cleaning method for database | |
| CN114463673B (en) | Material recommendation method, device, equipment and storage medium | |
| CN116243869A (en) | Data processing method and device and electronic equipment | |
| CN113076473B (en) | User data processing method, device, computer equipment and storage medium | |
| CN114782780A (en) | Data set construction method and device and electronic equipment | |
| CN110442780B (en) | Vehicle owner portrait generation method and device based on intelligent park and computer equipment | |
| CN109739817B (en) | Method and system for storing data file in big data storage system | |
| CN113901265A (en) | Video tag extraction method and device, computer equipment and storage medium | |
| CN112199388A (en) | Strange call identification method and device, electronic equipment and storage medium | |
| CN111428037A (en) | Method for analyzing matching performance of behavior policy | |
| CN115033798A (en) | Activity recommendation method and system based on big data | |
| CN116225338B (en) | Data processing method and device based on time sequence information and storage information | |
| CN114217876A (en) | Efficient customer data processing system and method | |
| CN114884843B (en) | Flow monitoring system based on network audiovisual new media |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |