Intelligent information recommendation method and system based on big data

Abstract

The invention discloses an intelligent information recommendation method and system based on big data, and belongs to the technical field of big data and information recommendation. According to the method, screening and recommendation can be carried out according to the interest points expressed by the user, time and energy needed by the user in the information searching and screening process are greatly saved, potential interests of the user can be deeply mined, some content which may not be actively concerned by the user but actually highly conforms to the interest preference of the user is presented for the user, and the user experience is improved. Therefore, the information acquisition channel of the user is effectively broadened, the visual field of the user is enriched, meanwhile, by applying an advanced algorithm and model, the system can accurately capture and understand personalized demands and interests of the user, customized recommendation services are provided for the user, and the personalized recommendation mode not only improves the user experience, but also improves the user experience. Viscosity and satisfaction of the user to the platform are enhanced, the platform is helped to establish a good brand image, and attention and reliability of more users are attracted.

Description

Technical Field

[0001] The present invention belongs to the technical field of big data and information recommendation, and specifically relates to an intelligent information recommendation method and system based on big data. Background Art

[0002] With the rapid development of the Internet and e-commerce, the amount of information on the Internet has increased exponentially. This surge in information has provided users with abundant choices, but it has also brought about the problem of information overload, making it difficult for users to quickly and accurately find the content they are interested in from the massive amount of information. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent information recommendation method and system based on big data to solve the problems raised in the above background technology.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an intelligent information recommendation method and system based on big data, the system comprising a data acquisition module, a data preprocessing module, a feature extraction module, a recommendation calculation module, an evaluation and optimization module, a user interface module, and a feedback processing module. The data acquisition module is responsible for collecting user behavior data, user attribute data, product attribute data, and user evaluation data as the basis for subsequent analysis and recommendation. The data preprocessing module is used to clean, merge, and annotate the collected data to eliminate duplicate data, process missing values, and outliers, so as to ensure the quality and accuracy of the data.

[0005] As a further preferred embodiment of the present technical solution: the feature extraction module extracts key information and user preference features from the preprocessed data, and the feature extraction module is further subdivided into a time series analysis submodule, an association rule mining submodule and a text content analysis submodule; the recommendation calculation module selects a suitable recommendation algorithm for personalized recommendation based on the features extracted by the feature extraction module, and generates a personalized information recommendation list.

[0006] As a further preferred embodiment of the present technical solution: the evaluation and optimization module evaluates and optimizes the recommendation results generated by the recommendation calculation module to improve the accuracy of the recommendation and user satisfaction, and the user interface module presents a personalized information recommendation list to the user and updates the recommendation results in real time.

[0007] As a further preferred embodiment of the present technical solution: the feedback processing module is responsible for collecting and analyzing user feedback and adjusting the recommendation strategy accordingly; the data acquisition module also includes an interface for acquiring data from multiple data sources to ensure the comprehensiveness and diversity of the data; the data preprocessing module also includes a data anonymization processing function to protect user privacy.

[0008] As a further preferred embodiment of the present technical solution: the time series analysis submodule in the feature extraction module is used to analyze the changing trend of user behavior data over time, the association rule mining submodule is used to discover the correlation between user behavior and product attributes, and the text content analysis submodule is used to analyze the text content in the user evaluation data to extract user preferences.

[0009] As a further preferred embodiment of the present technical solution: the recommendation calculation module adopts a variety of recommendation algorithms, including but not limited to content-based recommendation, collaborative filtering recommendation and deep learning recommendation, to generate a personalized information recommendation list according to user preferences and historical behavior data.

[0010] As a further preferred embodiment of the present technical solution: the user interface module provides an interactive interface, allowing the user to provide feedback based on the recommendation results, and updates the recommendation list in real time to reflect changes in user preferences.

[0011] As a further preferred embodiment of the present technical solution: wherein the feedback processing module automatically adjusts the recommendation strategy according to the user feedback, including adjusting the recommendation algorithm, updating the user portrait and replacing the recommendation model.

[0012] As a further preferred embodiment of the present technical solution: the method comprises the following steps:

[0013] Step 1: Collect user behavior and preference data to form an initial data set:

[0014] Step 2: Preprocess the initial data set, including data cleaning, deduplication, merging, and anonymization, to ensure data quality and protect user privacy;

[0015] Step 3: Use the feature extraction module to extract key information and user preference features from the preprocessed data;

[0016] Step 4: Use the recommendation calculation module to take the preprocessed data set and feature extraction results as input, and generate a personalized information recommendation list by combining the prediction results, user historical behavior data and real-time data;

[0017] Step 5: Use the evaluation and optimization module to evaluate and optimize the recommendation results;

[0018] Step 6: Display the personalized information recommendation list to the user through the user interface, and continuously optimize the recommendation algorithm based on user feedback;

[0019] Step 7: Collect and analyze user feedback through the feedback processing module, and adjust the recommendation strategy based on the feedback.

[0020] As a further preferred embodiment of the present technical solution: the method also includes the steps of continuously optimizing the recommendation algorithm and updating the user portrait according to user feedback, so as to improve the flexibility and applicability of the system.

[0021] Compared with the prior art, the beneficial effects of the present invention are: the present invention can filter and recommend according to the interests expressed by users, greatly saving the time and energy required by users in the process of searching and filtering information, and can also deeply explore the potential interests of users, and present some content to users that they may not have actively paid attention to but are actually highly in line with their interest preferences, thereby effectively broadening the users' information acquisition channels and enriching their horizons. At the same time, through the use of advanced algorithms and models, the system can accurately capture and understand the users' personalized needs and interests, and provide them with customized recommendation services. The personalized recommendation method not only improves the user experience and enhances the users' stickiness and satisfaction with the platform, but also helps the platform to establish a good brand image and attract more users' attention and trust. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is an overall schematic diagram of an intelligent information recommendation method and system based on big data of the present invention;

[0023] Figure 2 The present invention is a flowchart of an intelligent information recommendation method and system based on big data. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Example

[0026] See also Figure 1-Figure 2 As shown, the present invention provides a technical solution: an intelligent information recommendation method and system based on big data, the system includes a data acquisition module, a data preprocessing module, a feature extraction module, a recommendation calculation module, an evaluation and optimization module, a user interface module, and a feedback processing module. The data acquisition module is responsible for collecting user behavior data, user attribute data, product attribute data, and user evaluation data as a basis for subsequent analysis and recommendation. The data preprocessing module is used to clean, merge, and annotate the collected data to eliminate duplicate data, process missing values ​​and outliers, and ensure the quality and accuracy of the data.

[0027] In this embodiment, specifically: the feature extraction module extracts key information and user preference features from the preprocessed data, the feature extraction module is further subdivided into a time series analysis submodule, an association rule mining submodule and a text content analysis submodule, and the recommendation calculation module selects a suitable recommendation algorithm for personalized recommendation based on the features extracted by the feature extraction module to generate a personalized information recommendation list.

[0028] In this embodiment, specifically: the evaluation and optimization module evaluates and optimizes the recommendation results generated by the recommendation calculation module to improve the accuracy of the recommendation and user satisfaction, and the user interface module presents a personalized information recommendation list to the user and updates the recommendation results in real time.

[0029] In this embodiment, specifically: the feedback processing module is responsible for collecting and analyzing user feedback and adjusting the recommendation strategy accordingly. The data acquisition module also includes an interface for obtaining data from multiple data sources to ensure the comprehensiveness and diversity of the data. The data preprocessing module also includes a data anonymization processing function to protect user privacy.

[0030] In this embodiment, specifically: the time series analysis submodule in the feature extraction module is used to analyze the changing trend of user behavior data over time, the association rule mining submodule is used to discover the correlation between user behavior and product attributes, and the text content analysis submodule is used to analyze the text content in the user evaluation data to extract user preferences.

[0031] In this embodiment, specifically: the recommendation calculation module adopts a variety of recommendation algorithms, including but not limited to content-based recommendation, collaborative filtering recommendation and deep learning recommendation, to generate a personalized information recommendation list based on user preferences and historical behavior data.

[0032] In this embodiment, specifically: the user interface module provides an interactive interface, allowing the user to provide feedback based on the recommendation results, and updates the recommendation list in real time to reflect changes in user preferences.

[0033] In this embodiment, specifically: the feedback processing module automatically adjusts the recommendation strategy according to user feedback, including adjusting the recommendation algorithm, updating the user portrait, and replacing the recommendation model.

[0034] In this embodiment, specifically: the method comprises the following steps:

[0035] Step 1: Collect user behavior and preference data to form an initial data set.

[0036] Step 2: Perform preprocessing on the initial data set, including data cleaning, deduplication, merging, and anonymization to ensure data quality and protect user privacy.

[0037] Step 3: Use the feature extraction module to extract key information and user preference features from the preprocessed data.

[0038] Step 4: Use the recommendation calculation module, take the preprocessed data set and feature extraction results as input, and generate a personalized information recommendation list by combining the prediction results, user historical behavior data and real-time data.

[0039] Step 5: Use the evaluation and optimization module to evaluate and optimize the recommendation results.

[0040] Step 6: Display the personalized information recommendation list to the user through the user interface, and continuously optimize the recommendation algorithm based on user feedback.

[0041] Step 7: Collect and analyze user feedback through the feedback processing module, and adjust the recommendation strategy based on the feedback.

[0042] In this embodiment, specifically: the method also includes the steps of continuously optimizing the recommendation algorithm and updating the user portrait according to user feedback, so as to improve the flexibility and applicability of the system.

[0043] Working principle or structural principle: First, the data collection module is responsible for collecting recommendation-related data from various data sources. Then the data processing module pre-processes the collected data, including cleaning, deduplication, merging and anonymization. Secondly, the data analysis module extracts and analyzes the features of the pre-processed data to obtain the similarities between users and the degree of user preference for the product. After that, the recommendation calculation module uses the recommendation algorithm to further process the data analysis results and generate a personalized information recommendation list. Finally, the evaluation and optimization module evaluates and optimizes the recommendation results to improve the recommendation effect. The user display module displays the recommendation results to the user in a user-friendly manner and collects user feedback on the recommendation results through the user interface.

[0044] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method and system for intelligent information recommendation based on big data, characterized in that: The system includes a data acquisition module, a data preprocessing module, a feature extraction module, a recommendation calculation module, an evaluation and optimization module, a user interface module, and a feedback processing module. The data acquisition module is responsible for collecting user behavior data, user attribute data, product attribute data, and user evaluation data as a basis for subsequent analysis and recommendation. The data preprocessing module is used to clean, merge, and annotate the collected data to eliminate duplicate data, process missing values, and outliers, so as to ensure the quality and accuracy of the data.

2. According to claim 1, a method and system for intelligent information recommendation based on big data, characterized in that: The feature extraction module extracts key information and user preference features from the preprocessed data. The feature extraction module is further subdivided into a time series analysis submodule, an association rule mining submodule and a text content analysis submodule. The recommendation calculation module selects a suitable recommendation algorithm for personalized recommendation based on the features extracted by the feature extraction module to generate a personalized information recommendation list.

3. The method and system for intelligent information recommendation based on big data according to claim 1, characterized in that: The evaluation and optimization module evaluates and optimizes the recommendation results generated by the recommendation calculation module to improve the accuracy of the recommendation and user satisfaction. The user interface module presents a personalized information recommendation list to the user and updates the recommendation results in real time.

4. The method and system for intelligent information recommendation based on big data according to claim 1, characterized in that: The feedback processing module is responsible for collecting and analyzing user feedback and adjusting the recommendation strategy accordingly. The data acquisition module also includes an interface for obtaining data from multiple data sources to ensure the comprehensiveness and diversity of the data. The data preprocessing module also includes a data anonymization processing function to protect user privacy.

5. The method and system for intelligent information recommendation based on big data according to claim 1, characterized in that: The time series analysis submodule in the feature extraction module is used to analyze the changing trend of user behavior data over time, the association rule mining submodule is used to discover the association relationship between user behavior and product attributes, and the text content analysis submodule is used to analyze the text content in the user evaluation data to extract user preferences.

6. The method and system for intelligent information recommendation based on big data according to claim 1, characterized in that: The recommendation calculation module adopts a variety of recommendation algorithms, including but not limited to content-based recommendation, collaborative filtering recommendation and deep learning recommendation, to generate a personalized information recommendation list based on user preferences and historical behavior data.

7. The method and system for intelligent information recommendation based on big data according to claim 1, characterized in that: The user interface module provides an interactive interface that allows users to provide feedback based on the recommendation results and updates the recommendation list in real time to reflect changes in user preferences.

8. The method and system for intelligent information recommendation based on big data according to claim 1, characterized in that: The feedback processing module automatically adjusts the recommendation strategy based on user feedback, including adjusting the recommendation algorithm, updating user portraits, and replacing the recommendation model.

9. The method and system for intelligent information recommendation based on big data according to claim 1, characterized in that: The method comprises the following steps: Step 1: Collect user behavior and preference data to form an initial data set. Step 2: Perform preprocessing on the initial data set, including data cleaning, deduplication, merging, and anonymization to ensure data quality and protect user privacy. Step 3: Use the feature extraction module to extract key information and user preference features from the preprocessed data. Step 4: Use the recommendation calculation module, take the preprocessed data set and feature extraction results as input, and generate a personalized information recommendation list by combining the prediction results, user historical behavior data and real-time data. Step 5: Use the evaluation and optimization module to evaluate and optimize the recommendation results. Step 6: Display the personalized information recommendation list to the user through the user interface, and continuously optimize the recommendation algorithm based on user feedback. Step 7: Collect and analyze user feedback through the feedback processing module, and adjust the recommendation strategy based on the feedback.

10. The method and system for intelligent information recommendation based on big data according to claim 1, characterized in that: The method also includes the steps of continuously optimizing the recommendation algorithm and updating the user portrait based on user feedback.

Images