Internet service method based on big data
By introducing reinforcement learning, deep learning and other technologies into the Internet service system, data collection and recommendation strategies are optimized, and the problems of low data processing efficiency and poor personalized recommendation effects in the existing technology are solved, and efficient and intelligent Internet services are achieved. Significantly improves user experience and system performance.
Patent Information
- Application Number
- CN202410929365.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-11
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing Internet service methods based on big data have problems such as low data processing efficiency and poor personalized recommendation effects, and cannot fully utilize the advantages of big data.
A system including data acquisition, data processing, personalized recommendation and feedback optimization modules was designed, and the dynamically optimized data collection was achieved using reinforcement learning, deep learning, federated learning, generative adversarial networks, natural language processing and sentiment analysis technologies. Strategy, intelligent data cleaning and storage, multi-source data fusion, cross-platform analysis of privacy protection, real-time optimization of personalized recommendations and automated feedback analysis.
It significantly improves the overall performance and user experience of the system, overcomes difficulties such as data redundancy, inaccurate positioning, privacy leakage, single recommendation and slow feedback response, and improves data collection efficiency and recommendation accuracy and diversity.
Smart Images

Figure CN119066053A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of Internet services, and in particular to an Internet service method based on big data. Background Art
[0002] With the rapid development and popularization of Internet technology, the generation and collection of massive data has become the norm. These data cover many aspects of information such as user behavior, preferences, and location. How to efficiently use these data to provide users with personalized and intelligent services has become an important research direction in the field of Internet services. At present, although there are many service methods based on big data, most of them have problems such as low data processing efficiency and poor personalized recommendation effect, and cannot give full play to the advantages of big data. Therefore, it is very necessary to design an efficient and intelligent Internet service method based on big data. Summary of the invention
[0003] The purpose of the present invention is to provide an Internet service method based on big data to solve the problems raised in the above background technology.
[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a big data-based Internet service method, including a big data-based Internet service system, the big data-based Internet service system including a data acquisition module, a data processing module, a personalized recommendation module and a feedback optimization module, the data acquisition module is used to collect user behavior data, location data and preference data, the data processing module is used to clean, store and analyze the collected data, the personalized recommendation module is used to generate personalized service recommendations based on the analysis results, the feedback optimization module is used to optimize the recommendation algorithm based on user feedback, and the data acquisition module, the data processing module, the personalized recommendation module and the feedback optimization module are connected through a network.
[0005] According to the above technical solution, the data collection module includes a user behavior collection unit, a location data collection unit and a preference data collection unit. The user behavior collection unit is used to collect the user's behavior data in the process of using Internet services, the location data collection unit is used to collect the user's geographic location data, and the preference data collection unit is used to collect the user's interest preference data.
[0006] According to the above technical solution, the data processing module includes a data cleaning unit, a data storage unit and a data analysis unit. The data cleaning unit is used to deduplicate, complete and standardize the collected data, the data storage unit is used to classify and store the cleaned data, and the data analysis unit is used to perform multi-dimensional analysis on the stored data to generate a user portrait.
[0007] According to the above technical solution, the personalized recommendation module includes a recommendation algorithm unit and a recommendation generation unit. The recommendation algorithm unit is used to design a recommendation algorithm based on user portraits and big data analysis results, and the recommendation generation unit is used to generate personalized service recommendations based on the recommendation algorithm.
[0008] According to the above technical solution, the feedback optimization module includes a user feedback collection unit and an algorithm optimization unit. The user feedback collection unit is used to collect user feedback on the recommendation service, and the algorithm optimization unit is used to optimize the recommendation algorithm according to the user feedback.
[0009] According to the above technical solution, the method comprises the following steps: Step S1: Collecting user behavior data, location data and preference data through a data collection module; Step S2: Clean, store and analyze the collected data through the data processing module to generate a user portrait; Step S3: Generate personalized service recommendations based on user portraits and big data analysis results through a personalized recommendation module; Step S4: Optimize the recommendation algorithm based on user feedback through the feedback optimization module to continuously improve the recommendation effect.
[0010] According to the above technical solution, step S1 further includes: Behavioral data collection: Use reinforcement learning algorithms to optimize data collection strategies, adjust data collection frequency and content in real time based on user behavior, and improve the efficiency and accuracy of data collection; Location data collection: Combine multi-source location data for fusion and use Bayesian estimation methods to improve the accuracy and robustness of location data; Preference data collection: Use deep learning models to automatically extract user preference features from historical behavior data, reducing the burden of active input from users.
[0011] According to the above technical solution, step S2 further includes: Introducing anomaly detection algorithms based on graph neural networks to automatically identify and process abnormal data and improve the intelligence level of data cleaning; Adopt distributed file system combined with blockchain technology to ensure the security and non-tamperability of data storage; Combined with federated learning technology, cross-platform data analysis can be performed without sharing the original data to protect user privacy.
[0012] According to the above technical solution, step S3 further includes: Introducing recommendation strategy optimization based on reinforcement learning, adjusting the recommendation model in real time through user feedback, and improving the accuracy and real-time performance of recommendations; Generate personalized recommendation lists using generative adversarial networks (GANs) to improve the diversity and novelty of recommendation results.
[0013] According to the above technical solution, step S4 further includes: Combine natural language processing (NLP) and sentiment analysis technology to automatically analyze the sentiment tendency of user feedback and improve the intelligence level of feedback analysis; Apply deep reinforcement learning algorithms to dynamically adjust the parameters of the recommendation algorithm based on feedback results and continuously optimize the recommendation effect.
[0014] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention overcomes the difficulties of data redundancy, inaccurate positioning, privacy leakage, single recommendation and slow feedback response in the prior art through dynamically optimized data collection strategies, intelligent data cleaning and storage, multi-source data fusion, cross-platform analysis with privacy protection, real-time optimized personalized recommendations, and automated feedback analysis and recommendation algorithm optimization, thereby significantly improving the overall performance of the system and user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0015] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION
[0016] 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.
[0017] See also Figure 1The present invention provides a technical solution: a big data-based Internet service method, including a big data-based Internet service system, the big data-based Internet service system includes a data collection module, a data processing module, a personalized recommendation module and a feedback optimization module, the data collection module is used to collect user behavior data, location data and preference data, the data processing module is used to clean, store and analyze the collected data, the personalized recommendation module is used to generate personalized service recommendations according to the analysis results, the feedback optimization module is used to optimize the recommendation algorithm according to user feedback, and the data collection module, the data processing module, the personalized recommendation module and the feedback optimization module are connected through a network; the present invention realizes intelligent, precise and efficient data collection, processing, analysis and recommendation by introducing reinforcement learning, deep learning, federated learning, generative adversarial network, natural language processing, sentiment analysis and AutoML technology. At the same time, through dynamically optimized data collection strategies, intelligent data cleaning and storage, multi-source data fusion, privacy-protected cross-platform analysis, real-time optimized personalized recommendations, and automated feedback analysis and recommendation algorithm optimization, the difficulties of data redundancy, inaccurate positioning, privacy leakage, single recommendation and slow feedback response in the prior art are overcome, and the overall performance and user experience of the system are significantly improved.
[0018] The data collection module includes a user behavior collection unit, a location data collection unit and a preference data collection unit. The user behavior collection unit is used to collect the user's behavior data when using Internet services, the location data collection unit is used to collect the user's geographic location data, and the preference data collection unit is used to collect the user's interest preference data.
[0019] The data processing module includes a data cleaning unit, a data storage unit and a data analysis unit. The data cleaning unit is used to deduplicate, complete and standardize the collected data, the data storage unit is used to classify and store the cleaned data, and the data analysis unit is used to perform multi-dimensional analysis on the stored data to generate user portraits.
[0020] The personalized recommendation module includes a recommendation algorithm unit and a recommendation generation unit. The recommendation algorithm unit is used to design a recommendation algorithm based on user portraits and big data analysis results, and the recommendation generation unit is used to generate personalized service recommendations based on the recommendation algorithm.
[0021] The feedback optimization module includes a user feedback collection unit and an algorithm optimization unit. The user feedback collection unit is used to collect user feedback on the recommendation service, and the algorithm optimization unit is used to optimize the recommendation algorithm according to the user feedback.
[0022] The method comprises the following steps: Step S1: Collecting user behavior data, location data and preference data through a data collection module; Step S2: Clean, store and analyze the collected data through the data processing module to generate a user portrait; Step S3: Generate personalized service recommendations based on user portraits and big data analysis results through a personalized recommendation module; Step S4: Optimize the recommendation algorithm based on user feedback through the feedback optimization module to continuously improve the recommendation effect.
[0023] Step S1 further comprises: Behavioral data collection: Use reinforcement learning algorithms to optimize data collection strategies, adjust data collection frequency and content in real time according to user behavior, and improve the efficiency and accuracy of data collection; including page browsing records, click records, operation timestamps, etc., introduce reinforcement learning algorithms, and adjust collection strategies adaptively to reduce redundant data collection, while improving the accuracy of user behavior data; Location data collection: Combine multi-source location data for fusion, and use Bayesian estimation to improve the accuracy and robustness of location data; including latitude and longitude coordinates, location update time, IP address, etc.; through multi-source data fusion and Bayesian estimation, improve the accuracy and reliability of location data and overcome the limitations of a single data source; Preference data collection: Use deep learning models to automatically extract user preference features from historical behavior data, reducing the burden of active user input; including interest tags, preferred product categories, preferred content types, etc.; apply deep learning models to achieve automated preference data extraction, improve user experience, and reduce human intervention.
[0024] Step S2 further comprises: Introduce anomaly detection algorithms based on graph neural networks to automatically identify and process abnormal data and improve the intelligence level of data cleaning; use graph neural networks to achieve intelligent anomaly detection and improve the accuracy and efficiency of data cleaning; Adopt distributed file system combined with blockchain technology to ensure the security and immutability of data storage; introduce blockchain technology into data storage to ensure the security and integrity of data and prevent data tampering; Combined with federated learning technology, cross-platform data analysis can be carried out without sharing the original data to protect user privacy; using federated learning technology, cross-platform data analysis can be achieved to protect user privacy while improving the comprehensiveness and accuracy of the analysis.
[0025] Step S3 further comprises: Introduce recommendation strategy optimization based on reinforcement learning, adjust the recommendation model in real time through user feedback, and improve the accuracy and real-time performance of recommendations; apply reinforcement learning to optimize the recommendation strategy, make adaptive adjustments based on user feedback, and achieve dynamic optimization of personalized recommendations; Generate personalized recommendation lists using generative adversarial networks (GANs) to improve the diversity and novelty of recommendation results; Generate recommendation lists using generative adversarial networks to improve the diversity and novelty of recommendation results and avoid the uniformity of recommendations.
[0026] Step S4 further comprises: Combine natural language processing (NLP) and sentiment analysis technology to automatically analyze the sentiment tendency of user feedback and improve the intelligence level of feedback analysis; through NLP and sentiment analysis technology, realize intelligent analysis of user feedback and quickly extract effective information; Apply deep reinforcement learning algorithms to dynamically adjust the parameters of the recommendation algorithm based on feedback results and continuously optimize the recommendation effect; realize the dynamic optimization of the recommendation algorithm.
[0027] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
[0028] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.
Claims
1. An Internet service method based on big data, characterized in that: The method includes an Internet service system based on big data, which includes a data collection module, a data processing module, a personalized recommendation module and a feedback optimization module. The data collection module is used to collect user behavior data, location data and preference data, the data processing module is used to clean, store and analyze the collected data, the personalized recommendation module is used to generate personalized service recommendations based on analysis results, and the feedback optimization module is used to optimize the recommendation algorithm based on user feedback. The data collection module, data processing module, personalized recommendation module and feedback optimization module are connected through a network.
2. The Internet service method based on big data according to claim 1, characterized in that: The data collection module includes a user behavior collection unit, a location data collection unit and a preference data collection unit. The user behavior collection unit is used to collect the user's behavior data in the process of using Internet services, the location data collection unit is used to collect the user's geographic location data, and the preference data collection unit is used to collect the user's interest preference data.
3. The Internet service method based on big data according to claim 2, characterized in that: The data processing module includes a data cleaning unit, a data storage unit and a data analysis unit. The data cleaning unit is used to deduplicate, complete and standardize the collected data, the data storage unit is used to classify and store the cleaned data, and the data analysis unit is used to perform multi-dimensional analysis on the stored data to generate a user portrait.
4. The Internet service method based on big data according to claim 3 is characterized in that: The personalized recommendation module includes a recommendation algorithm unit and a recommendation generation unit. The recommendation algorithm unit is used to design a recommendation algorithm based on user portraits and big data analysis results, and the recommendation generation unit is used to generate personalized service recommendations based on the recommendation algorithm.
5. The Internet service method based on big data according to claim 4, characterized in that: The feedback optimization module includes a user feedback collection unit and an algorithm optimization unit. The user feedback collection unit is used to collect user feedback on the recommendation service, and the algorithm optimization unit is used to optimize the recommendation algorithm according to the user feedback.
6. The Internet service method based on big data according to claim 5, characterized in that: The method comprises the following steps: Step S1: Collecting user behavior data, location data and preference data through a data collection module; Step S2: Clean, store and analyze the collected data through the data processing module to generate a user portrait; Step S3: Generate personalized service recommendations based on user portraits and big data analysis results through a personalized recommendation module; Step S4: Optimize the recommendation algorithm based on user feedback through the feedback optimization module to continuously improve the recommendation effect.
7. The big data-based Internet service method according to claim 6, characterized in that: The step S1 further comprises: Behavioral data collection: Use reinforcement learning algorithms to optimize data collection strategies, adjust data collection frequency and content in real time based on user behavior, and improve the efficiency and accuracy of data collection; Location data collection: Combine multi-source location data for fusion and use Bayesian estimation methods to improve the accuracy and robustness of location data; Preference data collection: Use deep learning models to automatically extract user preference features from historical behavior data, reducing the burden of active input from users.
8. The Internet service method based on big data according to claim 7, characterized in that: The step S2 further comprises: Introducing anomaly detection algorithms based on graph neural networks to automatically identify and process abnormal data and improve the intelligence level of data cleaning; Adopt distributed file system combined with blockchain technology to ensure the security and non-tamperability of data storage; Combined with federated learning technology, cross-platform data analysis can be performed without sharing the original data to protect user privacy.
9. The Internet service method based on big data according to claim 8, characterized in that: The step S3 further comprises: Introducing recommendation strategy optimization based on reinforcement learning, adjusting the recommendation model in real time through user feedback, and improving the accuracy and real-time performance of recommendations; Generate personalized recommendation lists using generative adversarial networks to improve the diversity and novelty of recommendation results.
10. The Internet service method based on big data according to claim 9, characterized in that: The step S4 further comprises: Combine natural language processing and sentiment analysis technology to automatically analyze the sentiment tendency of user feedback and improve the intelligence level of feedback analysis; Apply deep reinforcement learning algorithms to dynamically adjust the parameters of the recommendation algorithm based on feedback results and continuously optimize the recommendation effect.
