CN117056610A - Personalized recommendation method and system based on user tag - Google Patents
Personalized recommendation method and system based on user tag Download PDFInfo
- Publication number
- CN117056610A CN117056610A CN202311263226.6A CN202311263226A CN117056610A CN 117056610 A CN117056610 A CN 117056610A CN 202311263226 A CN202311263226 A CN 202311263226A CN 117056610 A CN117056610 A CN 117056610A
- Authority
- CN
- China
- Prior art keywords
- user
- information
- interest
- data
- tag
- 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
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000010801 machine learning Methods 0.000 claims abstract description 29
- 238000003058 natural language processing Methods 0.000 claims abstract description 24
- 238000005516 engineering process Methods 0.000 claims description 16
- 230000007246 mechanism Effects 0.000 claims description 14
- 238000012545 processing Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 238000002372 labelling Methods 0.000 abstract description 4
- 230000006399 behavior Effects 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000007635 classification algorithm Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000000586 desensitisation Methods 0.000 description 2
- 230000008451 emotion Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000011273 social behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
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
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/2866—Architectures; Arrangements
- H04L67/30—Profiles
- H04L67/306—User profiles
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
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)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a personalized recommendation method and a personalized recommendation system based on user labels, which are characterized in that user data are extracted based on natural language processing to obtain information of interest of a user, and the information of interest of the user is classified based on a machine learning model, so that characteristics can be automatically extracted from a large amount of data and user labels are generated, the complexity of manual labeling is reduced, in addition, the consistency and the accuracy of the user labels can be ensured, the interference of artificial subjective factors is avoided, the accuracy of generating the user labels is improved, meanwhile, content pushing is carried out for the user according to the user labels, personalized recommendation can be effectively realized, the accuracy of personalized recommendation is improved, and the condition of information overload is avoided.
Description
Technical Field
The invention relates to the technical field of personalized recommendation, in particular to a personalized recommendation method and a personalized recommendation system based on user tags.
Background
In recent years, with continuous updating of internet technology and computer technology, the internet brings huge information data volume, and meanwhile, the phenomenon of information overload is aggravated, although the selection range of information resources by users is expanded, how to quickly and effectively screen information useful for users from huge data, and improving the utilization efficiency of information becomes a great difficulty in the current generation of internet development, and many existing web application programs (such as portal websites and search engines) are essentially one method for helping users filter information, however, the methods only can meet the mainstream demands of users, the problem of individuation is not considered, the problem of information overload is not solved well, and individuation is recommended as an important information filtering means, so that the method is an effective method for solving the problem of information overload.
Disclosure of Invention
In view of this, the invention provides a personalized recommendation method and a personalized recommendation system based on user tags, which can solve the defect that information overload is caused by incapability of realizing personalized recommendation in the prior art.
The technical scheme of the invention is realized as follows:
a personalized recommendation method based on user tags specifically comprises the following steps:
collecting user data, extracting the user data based on natural language processing, and obtaining information of interest of a user;
classifying information interested by a user based on a machine learning model to obtain a user tag;
content pushing is carried out on the users according to the user labels, so that personalized recommendation is achieved.
As a further alternative of the personalized recommendation method based on user tags, the collecting user data and extracting the user data based on natural language processing to obtain information of interest to the user specifically includes:
preprocessing the user data to obtain corrected user data;
extracting the characteristics of the corrected user data to obtain user characteristics;
and analyzing the characteristics of the user according to a natural language processing technology to obtain information of interest to the user.
As a further alternative of the personalized recommendation method based on the user tag, the classifying the information interested by the user based on the machine learning model to obtain the user tag specifically includes:
constructing a machine learning model according to the historical user tag data;
inputting the information of interest of the user into the machine learning model for classification, and obtaining the user tag.
As a further alternative of the personalized recommendation method based on the user tag, the method further includes updating the user tag in real time, and specifically includes:
and analyzing the information of interest of the real-time user by adopting a real-time stream data processing technology, judging whether the information belongs to the new information of interest of the user, if so, updating the user tag, and otherwise, classifying the information of interest of the user.
As a further alternative of the personalized recommendation method based on the user tag, the method further includes privacy setting for the user tag, and specifically includes:
setting a privacy protection mechanism;
and encrypting the user tag according to the privacy protection mechanism.
A personalized recommendation system based on user tags, comprising:
the acquisition module is used for acquiring user data, extracting the user data based on natural language processing and obtaining information of interest of a user;
the classifying module is used for classifying the information interested by the user based on the machine learning model to obtain a user tag;
and the pushing module is used for pushing the content to the user according to the user tag, so that personalized recommendation is realized.
As a further alternative to the personalized recommendation system based on user tags, the collection module includes:
the preprocessing module is used for preprocessing the user data to obtain corrected user data;
the feature extraction module is used for extracting the features of the corrected user data to obtain user features;
and the natural language processing module is used for analyzing the characteristics of the user according to the natural language processing technology to obtain the information of interest of the user.
As a further alternative to the personalized recommendation system based on user tags, the categorizing module comprises:
the construction module is used for constructing a machine learning model according to the historical user tag data;
and the execution module is used for inputting the information of interest of the user into the machine learning model for classification to obtain the user tag.
As a further alternative scheme of the personalized recommendation system based on the user tag, the system further comprises a user tag updating module, wherein the user tag updating module is used for analyzing information of interest of a real-time user by adopting a real-time streaming data processing technology, judging whether the information belongs to the information of interest of the new user, if so, updating the user tag, otherwise, classifying the information of interest of the user.
As a further alternative to the personalized recommendation system based on user tags, the system further comprises a privacy setting module comprising:
the setting module is used for setting a privacy protection mechanism;
and the processing module is used for encrypting the user tag according to the privacy protection mechanism.
The beneficial effects of the invention are as follows: the user data is extracted based on natural language processing to obtain the information of interest of the user, the information of interest of the user is classified based on a machine learning model, the characteristics can be automatically extracted from a large amount of data and the user label is generated, so that the complexity of manual labeling is reduced, in addition, the consistency and the accuracy of the user label can be ensured, the interference of human subjective factors is avoided, the accuracy of generating the user label is improved, meanwhile, content pushing is carried out for the user according to the user label, personalized recommendation can be effectively realized, the accuracy of personalized recommendation is improved, and the condition of information overload is avoided.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a personalized recommendation method based on user tags according to the present invention;
fig. 2 is a schematic diagram of the composition of a personalized recommendation system based on user labels according to the present invention.
Detailed Description
The following description of the technical solutions in the embodiments of the present invention will be clear and complete, and it is obvious that the described embodiments are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-2, a personalized recommendation method based on user tags specifically includes:
collecting user data, extracting the user data based on natural language processing, and obtaining information of interest of a user;
classifying information interested by a user based on a machine learning model to obtain a user tag;
content pushing is carried out on the users according to the user labels, so that personalized recommendation is achieved.
In the embodiment, the user data is extracted based on natural language processing to obtain the information of interest of the user, and the information of interest of the user is classified based on a machine learning model, so that the characteristics can be automatically extracted from a large amount of data and the user label is generated, the complexity of manual labeling is reduced, in addition, the consistency and the accuracy of the user label can be ensured, the interference of artificial subjective factors is avoided, the accuracy of generating the user label is improved, meanwhile, content pushing is carried out for the user according to the user label, personalized recommendation can be effectively realized, the accuracy of personalized recommendation is improved, and the condition of information overload is avoided.
It should be noted that, the collected user data may be integrated into the database through various data sources, such as user registration information, purchase records, browsing history, social behavior, etc., and these data may help identify user features and behaviors, and provide basis for tag generation.
Preferably, the collecting the user data and extracting the user data based on natural language processing to obtain the information of interest of the user specifically includes:
preprocessing the user data to obtain corrected user data;
extracting the characteristics of the corrected user data to obtain user characteristics;
and analyzing the characteristics of the user according to a natural language processing technology to obtain information of interest to the user.
In this embodiment, before performing tag management, data preprocessing is generally required, which includes steps of data cleaning, deduplication, filling in missing values, data conversion, etc. to ensure accuracy and consistency of data, extracting useful features from the original data is a key step of generating tags, and features may be numerical, category, text, etc., at this stage, feature selection and dimension reduction may be required to reduce computational complexity and improve model performance, if the user data contains text information, such as comments, messages, etc., natural language processing techniques may be used for emotion analysis, topic extraction, etc., and information about user attitudes and interests is extracted therefrom for tag generation.
Preferably, the classifying the information of interest to the user based on the machine learning model to obtain the user tag specifically includes:
constructing a machine learning model according to the historical user tag data;
inputting the information of interest of the user into the machine learning model for classification, and obtaining the user tag.
In this embodiment, the machine learning model plays an important role in member tag management, and a classification algorithm, a clustering algorithm, a recommendation system, etc. may be used for tag generation and user grouping, and the machine learning model may learn patterns from historical data and then predict and classify according to new data.
Preferably, the method further comprises updating the user tag in real time, and specifically comprises the following steps:
and analyzing the information of interest of the real-time user by adopting a real-time stream data processing technology, judging whether the information belongs to the new information of interest of the user, if so, updating the user tag, and otherwise, classifying the information of interest of the user.
In this embodiment, the characteristics and behaviors of the user may change with time, but manual updating and maintenance of the tag requires constant human effort, the real-time tag is managed by a real-time streaming data processing technology, and the user tag may be updated in real time, which involves processing and analysis of streaming data to keep the user tag up-to-date, and the system automatically adds the relevant tag by establishing a real-time data stream, monitoring the behavior change of the user, and automatically updating the tag, for example, the user purchases a new product.
Preferably, the method further includes privacy setting for the user tag, specifically including:
setting a privacy protection mechanism;
and encrypting the user tag according to the privacy protection mechanism.
In the present embodiment, in some cases, the user may feel worry about the personal information thereof being used for tag management, and there is a privacy problem, and the personal information of the user may be ensured not to be abused by a privacy protection mechanism such as data desensitization, encryption, authority control, and the like.
A personalized recommendation system based on user tags, comprising:
the acquisition module is used for acquiring user data, extracting the user data based on natural language processing and obtaining information of interest of a user;
the classifying module is used for classifying the information interested by the user based on the machine learning model to obtain a user tag;
and the pushing module is used for pushing the content to the user according to the user tag, so that personalized recommendation is realized.
In the embodiment, the user data is extracted based on natural language processing to obtain the information of interest of the user, and the information of interest of the user is classified based on a machine learning model, so that the characteristics can be automatically extracted from a large amount of data and the user label is generated, the complexity of manual labeling is reduced, in addition, the consistency and the accuracy of the user label can be ensured, the interference of artificial subjective factors is avoided, the accuracy of generating the user label is improved, meanwhile, content pushing is carried out for the user according to the user label, personalized recommendation can be effectively realized, the accuracy of personalized recommendation is improved, and the condition of information overload is avoided.
It should be noted that, the collected user data may be integrated into the database through various data sources, such as user registration information, purchase records, browsing history, social behavior, etc., and these data may help identify user features and behaviors, and provide basis for tag generation.
Preferably, the acquisition module comprises:
the preprocessing module is used for preprocessing the user data to obtain corrected user data;
the feature extraction module is used for extracting the features of the corrected user data to obtain user features;
and the natural language processing module is used for analyzing the characteristics of the user according to the natural language processing technology to obtain the information of interest of the user.
In this embodiment, before performing tag management, data preprocessing is generally required, which includes steps of data cleaning, deduplication, filling in missing values, data conversion, etc. to ensure accuracy and consistency of data, extracting useful features from the original data is a key step of generating tags, and features may be numerical, category, text, etc., at this stage, feature selection and dimension reduction may be required to reduce computational complexity and improve model performance, if the user data contains text information, such as comments, messages, etc., natural language processing techniques may be used for emotion analysis, topic extraction, etc., and information about user attitudes and interests is extracted therefrom for tag generation.
Preferably, the classifying module includes:
the construction module is used for constructing a machine learning model according to the historical user tag data;
and the execution module is used for inputting the information of interest of the user into the machine learning model for classification to obtain the user tag.
In this embodiment, the machine learning model plays an important role in member tag management, and a classification algorithm, a clustering algorithm, a recommendation system, etc. may be used for tag generation and user grouping, and the machine learning model may learn patterns from historical data and then predict and classify according to new data.
Preferably, the system further comprises a user tag updating module, wherein the user tag updating module is used for analyzing information of interest of a real-time user by adopting a real-time streaming data processing technology, judging whether the information belongs to the information of interest of a new user, if yes, updating the user tag, and if not, classifying the information of interest of the user.
In this embodiment, the characteristics and behaviors of the user may change with time, but manual updating and maintenance of the tag requires constant human effort, the real-time tag is managed by a real-time streaming data processing technology, and the user tag may be updated in real time, which involves processing and analysis of streaming data to keep the user tag up-to-date, and the system automatically adds the relevant tag by establishing a real-time data stream, monitoring the behavior change of the user, and automatically updating the tag, for example, the user purchases a new product.
Preferably, the system further comprises a privacy setting module, the privacy setting module comprising:
the setting module is used for setting a privacy protection mechanism;
and the processing module is used for encrypting the user tag according to the privacy protection mechanism.
In the present embodiment, in some cases, the user may feel worry about the personal information thereof being used for tag management, and there is a privacy problem, and the personal information of the user may be ensured not to be abused by a privacy protection mechanism such as data desensitization, encryption, authority control, and the like.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (10)
1. The personalized recommendation method based on the user tag is characterized by comprising the following steps of:
collecting user data, extracting the user data based on natural language processing, and obtaining information of interest of a user;
classifying information interested by a user based on a machine learning model to obtain a user tag;
content pushing is carried out on the users according to the user labels, so that personalized recommendation is achieved.
2. The personalized recommendation method based on user tags according to claim 1, wherein the collecting user data and extracting the user data based on natural language processing to obtain information of interest to the user specifically comprises:
preprocessing the user data to obtain corrected user data;
extracting the characteristics of the corrected user data to obtain user characteristics;
and analyzing the characteristics of the user according to a natural language processing technology to obtain information of interest to the user.
3. The personalized recommendation method based on user tags according to claim 2, wherein the machine learning model is used for classifying information of interest to a user to obtain the user tags, and the method specifically comprises the following steps:
constructing a machine learning model according to the historical user tag data;
inputting the information of interest of the user into the machine learning model for classification, and obtaining the user tag.
4. The personalized recommendation method based on user tags according to claim 3, wherein the method further comprises updating the user tags in real time, and specifically comprises:
and analyzing the information of interest of the real-time user by adopting a real-time stream data processing technology, judging whether the information belongs to the new information of interest of the user, if so, updating the user tag, and otherwise, classifying the information of interest of the user.
5. The personalized recommendation method based on user tags according to claim 4, further comprising privacy setting of the user tags, specifically comprising:
setting a privacy protection mechanism;
and encrypting the user tag according to the privacy protection mechanism.
6. A personalized recommendation system based on user tags, comprising:
the acquisition module is used for acquiring user data, extracting the user data based on natural language processing and obtaining information of interest of a user;
the classifying module is used for classifying the information interested by the user based on the machine learning model to obtain a user tag;
and the pushing module is used for pushing the content to the user according to the user tag, so that personalized recommendation is realized.
7. The personalized recommendation system based on user tags according to claim 6, wherein the collection module comprises:
the preprocessing module is used for preprocessing the user data to obtain corrected user data;
the feature extraction module is used for extracting the features of the corrected user data to obtain user features;
and the natural language processing module is used for analyzing the characteristics of the user according to the natural language processing technology to obtain the information of interest of the user.
8. The personalized recommendation system based on user tags according to claim 7, wherein said categorization module comprises:
the construction module is used for constructing a machine learning model according to the historical user tag data;
and the execution module is used for inputting the information of interest of the user into the machine learning model for classification to obtain the user tag.
9. The personalized recommendation system according to claim 8, further comprising a user tag update module, wherein the user tag update module is configured to analyze information of interest to a real-time user by using a real-time streaming data processing technology, determine whether the information belongs to new information of interest to the user, if yes, update the user tag, otherwise, classify the information of interest to the user.
10. The personalized recommendation system based on user tags according to claim 9, further comprising a privacy settings module comprising:
the setting module is used for setting a privacy protection mechanism;
and the processing module is used for encrypting the user tag according to the privacy protection mechanism.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311263226.6A CN117056610A (en) | 2023-09-27 | 2023-09-27 | Personalized recommendation method and system based on user tag |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311263226.6A CN117056610A (en) | 2023-09-27 | 2023-09-27 | Personalized recommendation method and system based on user tag |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117056610A true CN117056610A (en) | 2023-11-14 |
Family
ID=88666572
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311263226.6A Pending CN117056610A (en) | 2023-09-27 | 2023-09-27 | Personalized recommendation method and system based on user tag |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117056610A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992531A (en) * | 2017-11-21 | 2018-05-04 | 吉浦斯信息咨询（深圳）有限公司 | News personalization intelligent recommendation method and system based on deep learning |
| CN111191122A (en) * | 2019-12-20 | 2020-05-22 | 重庆邮电大学 | Learning resource recommendation system based on user portrait |
-
2023
- 2023-09-27 CN CN202311263226.6A patent/CN117056610A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992531A (en) * | 2017-11-21 | 2018-05-04 | 吉浦斯信息咨询（深圳）有限公司 | News personalization intelligent recommendation method and system based on deep learning |
| CN111191122A (en) * | 2019-12-20 | 2020-05-22 | 重庆邮电大学 | Learning resource recommendation system based on user portrait |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111444236B (en) | Mobile terminal user portrait construction method and system based on big data | |
| CN109522562B (en) | Webpage knowledge extraction method based on text image fusion recognition | |
| US9069880B2 (en) | Prediction and isolation of patterns across datasets | |
| CN110705288A (en) | Big data-based public opinion analysis system | |
| CN105760524B (en) | A kind of multi-level more classification methods of Science News title | |
| CN106599160A (en) | Content rule base management system and encoding method thereof | |
| CN107368521B (en) | Knowledge recommendation method and system based on big data and deep learning | |
| CN106528777A (en) | Cross-screen user identification normalizing method and system | |
| CN116662577B (en) | Knowledge graph-based large language model training method and device | |
| CN111414520A (en) | Intelligent mining system for sensitive information in public opinion information | |
| US10467255B2 (en) | Methods and systems for analyzing reading logs and documents thereof | |
| CN113094512B (en) | Fault analysis system and method in industrial production and manufacturing | |
| Zhang | Application of data mining technology in digital library. | |
| CN113239208A (en) | Mark training model based on knowledge graph | |
| CN112328806A (en) | Data processing method, system, computer equipment and storage medium | |
| CN112016769B (en) | Method and device for managing relative person risk prediction and information recommendation | |
| CN113674846A (en) | Hospital intelligent service public opinion monitoring platform based on LSTM network | |
| CN112395513A (en) | Public opinion transmission power analysis method | |
| CN117009524A (en) | Internet big data analysis method and system based on public opinion emotion analysis | |
| CN117056610A (en) | Personalized recommendation method and system based on user tag | |
| CN116506498A (en) | Cloud computing-based data accurate pushing method | |
| CN112328812B (en) | Domain knowledge extraction method and system based on self-adjusting parameters and electronic equipment | |
| CN113626596B (en) | Subway design specification text analysis and corpus construction method based on deep learning | |
| CN115080636A (en) | Big data analysis system based on network service | |
| CN110390013A (en) | A kind of file classification method based on cluster with ANN fusion application |
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 |