Vehicle-mounted content information intelligent recommendation system based on Internet of Vehicles

Abstract

The invention relates to the technical field of vehicle-mounted content information recommendation, and discloses a vehicle-mounted content information intelligent recommendation system based on the Internet of Vehicles, which comprises a vehicle networking communication module, a user behavior analysis unit, a content database and an intelligent recommendation engine, the Internet of Vehicles communication module, the user behavior analysis unit and the content database are all in communication connection with the intelligent recommendation engine, the Internet of Vehicles communication module is responsible for real-time data transmission, the user behavior analysis unit accurately captures driving habits, and the content database stores mass information. According to the system, a recommendation algorithm is utilized, related contents are accurately pushed according to user interests and behavior characteristics, information overload is reduced, user experience is improved, the intelligent recommendation system not only optimizes information acquisition efficiency, but also shapes a user thinking model in unconsciousness and promotes diversified development of a knowledge system, and the intelligent recommendation system is suitable for popularization and application. The construction of an open and contained information ecological environment is assisted, and finally the double improvement of the user value and the platform value is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of in-vehicle content information recommendation, and specifically to an intelligent in-vehicle content information recommendation system based on the Internet of Vehicles. Background Art

[0002] With the development of the Internet, the use of vehicle networking can make vehicles more convenient during use. We spend more and more time on the road every day, and the acquisition of information during the driving life has begun to become an emerging topic for us. Due to the requirements for concentration and focus during driving, it is almost impossible for us to obtain corresponding information safely in the form of text or video products during driving, which also makes audio the only safe and effective way to obtain information during driving (technical requirements, accident cause analysis). In the current driving life, under the driving environment, the driver cannot carry out more effective interactions. Most of the time, the driver can only passively obtain information through in-vehicle radios and various mobile radios. The driver desires to be understood and obtain more effective interest guidance and demand satisfaction in the vast amount of information; at the same time, information content producers are also eager to understand customer needs and provide typed information content for customers, so as to achieve accurate push.

[0003] In view of this, the purpose of the present invention is to provide an intelligent in-vehicle content information recommendation system based on the Internet of Vehicles. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent in-vehicle content information recommendation system based on the Internet of Vehicles to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: An intelligent in-vehicle content information recommendation system based on the Internet of Vehicles, including an Internet of Vehicles communication module, a user behavior analysis unit, a content database, and an intelligent recommendation engine. The Internet of Vehicles communication module, the user behavior analysis unit, and the content database are all communicatively connected to the intelligent recommendation engine. The Internet of Vehicles communication module is responsible for real-time data transmission, the user behavior analysis unit accurately captures driving habits, the content database stores a vast amount of information, and the intelligent recommendation engine dynamically generates personalized recommendation content based on user preferences and behavior data to enhance the driving experience and optimize the information acquisition efficiency; The Internet of Vehicles communication module includes a GPS positioning module, a wireless network interface, and a data encryption unit. The GPS positioning module accurately tracks the vehicle position, the wireless network interface ensures high-speed data transmission, and the data encryption unit ensures information security. The three work together to provide stable and reliable data support for intelligent recommendation; The user behavior analysis unit includes a behavior collection module, a data analysis engine, and a user profile generator. The behavior collection module records driving behaviors in real time. The data analysis engine deeply mines behavior patterns. The user profile generator accurately depicts user characteristics, providing a precise basis for intelligent recommendations. The content database stores diverse content resources, covering information in multiple fields such as navigation, entertainment, and news, including a multimedia resource library, a real-time news library, and a user preference library. The multimedia resource library provides rich audio-visual content. The real-time news library updates instant information. The user preference library records personalized selections. The three complement each other to form a three-dimensional information matrix, providing comprehensive, dynamic, and precise data support for the intelligent recommendation system. The intelligent recommendation engine adopts an advanced algorithm model, which is based on deep learning and big data analysis. It dynamically adjusts the recommendation strategy, comprehensively analyzes user behavior data and preference information, and dynamically generates a personalized recommendation list, accurately pushing navigation routes, entertainment content, and real-time news that meet user needs. It effectively breaks the information cocoon, broadens the user's cognitive horizon, promotes comprehensive and objective thinking. At the same time, through thematic recommendations and hot topic guidance, the platform strengthens the attention to social issues and public affairs, increases the user's exposure frequency to diverse information, promotes the integration of cross-domain knowledge, stimulates the user's interest in exploring unknown fields, and cultivates the ability of in-depth thinking.

[0006] Preferably, the GPS positioning module includes a high-precision satellite receiver, a real-time dynamic monitoring chip, and a position correction algorithm. The high-precision satellite receiver accurately locks satellite signals. The real-time dynamic monitoring chip continuously updates position information. The position correction algorithm effectively eliminates errors, ensuring the accuracy and real-time nature of vehicle position data. Preferably, the wireless network interface includes a multi-band antenna, a signal amplifier, and a network protocol converter. The multi-band antenna enhances signal reception ability. The signal amplifier improves transmission stability. The network protocol converter ensures seamless data docking. The three work together to ensure efficient and stable data transmission.

[0007] Preferably, the data encryption unit includes a symmetric encryption chip, an asymmetric encryption module, and a key manager. The symmetric encryption chip quickly processes a large amount of data. The asymmetric encryption module enhances the security level. The key manager dynamically updates keys. The three jointly ensure the absolute security of data transmission.

[0008] Preferably, when decryption is required, the key manager generates a decryption key according to a preset algorithm. The symmetric encryption chip and the asymmetric encryption module work together to quickly and accurately decrypt data, ensuring the integrity and privacy of information during transmission, and providing a safe and reliable intelligent recommendation service for users. The decryption formula is: Dk = (Ek ⊕ Fk) / Gk Where Dk is the decryption key, Ek is the encryption key, Fk is the auxiliary key, and Gk is the verification factor. Through this formula, the system can efficiently complete data decryption and ensure that user privacy is not violated.

[0009] Preferably, when encryption is required, the key manager generates the encryption key according to the same algorithm. The symmetric encryption chip and the asymmetric encryption module cooperate to encrypt the data into ciphertext to ensure that the data is not tampered with or stolen during the transmission process. The encryption formula is: Ek = (Dk ⊕ Fk) * Gk Where Ek is the encryption key, Dk is the decryption key, Fk is the auxiliary key, and Gk is the verification factor. Through this formula, the system can efficiently complete data encryption and ensure the security and reliability of information during the transmission process, providing users with a seamless and efficient intelligent recommendation experience.

[0010] Preferably, the behavior acquisition module includes a sensor array, a data buffer, and a behavior recognition algorithm. The sensor array captures driving data omnidirectionally, the data buffer temporarily stores a large amount of information, and the behavior recognition algorithm efficiently analyzes the behavior pattern to ensure the real-time and accuracy of data processing; The parsing formula of the behavior recognition algorithm is: A = h(B) + β * k(C) where B represents sensor data, C represents environmental variables, β is a correction coefficient, h(B) extracts behavior features, k(C) reflects environmental influence factors. Through dynamic correction by β, the accuracy of behavior recognition is ensured, the robustness of the algorithm model is enhanced by comprehensively considering user behavior and environmental factors, behavior prediction in multiple scenarios is realized, the transparency and interpretability of the algorithm are enhanced, and the user's right to know is ensured.

[0011] Preferably, the data analysis engine integrates machine learning algorithms to deeply mine user behavior patterns. The user portrait generator accurately depicts user characteristics based on multi-dimensional data to achieve precise matching of personalized recommended content and improve the user experience; The data analysis engine integrates machine learning algorithms, and its algorithm formula is: Y = f(X) + α * g(Z) Where X represents user behavior data, Z represents the content feature vector, α is an adjustment parameter, f(X) reflects the user behavior pattern, g(Z) depicts the content attributes. Among them, f and g are respectively feature extraction and weight assignment functions. By dynamically adjusting the weight through α, precise matching of user behavior and content attributes is achieved, the flexibility and adaptability of the recommendation system are improved, the recommendation result is more in line with the actual needs of users, and user stickiness is enhanced.

[0012] The present invention provides an in-vehicle content information intelligent recommendation system based on the vehicle network. It has the following beneficial effects: (1) Through multi-dimensional data analysis, the present invention realizes personalized content recommendation and improves user satisfaction. At the same time, the system adopts symmetric and asymmetric encryption technologies to ensure data security. The behavior recognition algorithm accurately captures user habits and optimizes the recommendation strategy. The data analysis engine deeply mines user characteristics to achieve accurate docking of content and user needs, and improves the intelligence level of the recommendation system.

[0013] (2) The system of the present invention uses a recommendation algorithm to accurately push relevant content according to user interests and behavior characteristics, reducing information overload and improving the user experience. The intelligent recommendation system not only optimizes the information acquisition efficiency, but also subtly shapes the user's thinking mode, promotes the diversified development of the knowledge system, helps to build an open and inclusive information ecological environment, and ultimately realizes the double improvement of user value and platform value. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is the overall framework general schematic diagram of the present invention; Figure 2 It is the view of the networking communication module of the present invention; Figure 3 It is the view of the user behavior analysis unit of the present invention; Figure 4 It is the view of the content database of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

[0016] Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present invention and should not be construed as a limitation of the present invention.

[0017] A preferred embodiment of an in-vehicle content information intelligent recommendation system based on vehicle networking provided by the present invention is as Figures 1-4As shown: An intelligent in-vehicle content information recommendation system based on the Internet of Vehicles, including an Internet of Vehicles communication module, a user behavior analysis unit, a content database, and an intelligent recommendation engine. The Internet of Vehicles communication module, the user behavior analysis unit, and the content database are all communicatively connected to the intelligent recommendation engine. The Internet of Vehicles communication module is responsible for real-time data transmission. The user behavior analysis unit accurately captures driving habits. The content database stores a vast amount of information. The intelligent recommendation engine dynamically generates personalized recommendation content based on user preferences and behavior data, enhancing the driving experience and optimizing the information acquisition efficiency; The Internet of Vehicles communication module includes a GPS positioning module, a wireless network interface, and a data encryption unit. The GPS positioning module accurately tracks the vehicle's position. The wireless network interface ensures high-speed data transmission. The data encryption unit ensures information security. The three work together to provide stable and reliable data support for intelligent recommendations; The GPS positioning module includes a high-precision satellite receiver, a real-time dynamic monitoring chip, and a position correction algorithm. The high-precision satellite receiver accurately locks the satellite signal. The real-time dynamic monitoring chip continuously updates the position information. The position correction algorithm effectively eliminates errors, ensuring the accuracy and real-time nature of the vehicle position data; The wireless network interface includes a multi-band antenna, a signal amplifier, and a network protocol converter. The multi-band antenna enhances the signal reception ability. The signal amplifier improves the transmission stability. The network protocol converter ensures seamless data docking. The three work together to ensure efficient and stable data transmission; The data encryption unit includes a symmetric encryption chip, an asymmetric encryption module, and a key manager. The symmetric encryption chip quickly processes a large amount of data. The asymmetric encryption module enhances the security level. The key manager dynamically updates the key. The three jointly ensure the absolute security of data transmission; Further, when decryption is required, the key manager generates a decryption key according to a preset algorithm. The symmetric encryption chip and the asymmetric encryption module work together to quickly and accurately decrypt the data, ensuring the integrity and privacy of the information during transmission, and providing a secure and reliable intelligent recommendation service for users. The decryption formula is: Dk = (Ek ⊕ Fk) / Gk Where Dk is the decryption key, Ek is the encryption key, Fk is the auxiliary key, and Gk is the verification factor. Through this formula, the system can efficiently complete data decryption and ensure that user privacy is not violated; Further, when encryption is required, the key manager generates an encryption key according to the same algorithm. The symmetric encryption chip and the asymmetric encryption module work together to encrypt the data into ciphertext, ensuring that the data is not tampered with or stolen during transmission. The encryption formula is: Ek = (Dk ⊕ Fk) * Gk Where Ek is the encryption key, Dk is the decryption key, Fk is the auxiliary key, and Gk is the verification factor. Through this formula, the system can efficiently complete data encryption, ensuring the security and reliability of information during transmission, and providing users with a seamless and efficient intelligent recommendation experience; The user behavior analysis unit includes a behavior collection module, a data analysis engine, and a user portrait generator. The behavior collection module records driving behaviors in real time, the data analysis engine deeply mines behavior patterns, and the user portrait generator accurately depicts user characteristics, providing a precise basis for intelligent recommendations; The behavior collection module includes a sensor array, a data buffer, and a behavior recognition algorithm. The sensor array captures driving data comprehensively, the data buffer temporarily stores a large amount of information, and the behavior recognition algorithm efficiently analyzes behavior patterns, ensuring the real-time and accuracy of data processing; The parsing formula of the behavior recognition algorithm is: A = h(B) + β * k(C) Where B represents sensor data, C represents environmental variables, β is a calibration coefficient, h(B) extracts behavior characteristics, and k(C) reflects environmental influencing factors. Through dynamic calibration by β, the accuracy of behavior recognition is ensured. By comprehensively considering user behaviors and environmental factors, the robustness of the algorithm model is improved, behavior prediction in multiple scenarios is realized, the transparency and interpretability of the algorithm are enhanced, and the user's right to know is ensured; The data analysis engine integrates machine learning algorithms to deeply mine the laws of user behaviors. The user portrait generator accurately depicts user characteristics based on multi-dimensional data, realizing the precise matching of personalized recommended content and improving the user experience. The data analysis engine integrates machine learning algorithms, and its algorithm formula is: Y = f(X) + α * g(Z) Where X represents user behavior data, Z represents the content feature vector, α is an adjustment parameter, f(X) reflects the user behavior pattern, and g(Z) depicts the content attributes. Among them, f and g are respectively feature extraction and weight assignment functions. By dynamically adjusting the weight through α, the precise matching of user behaviors and content attributes is realized, the flexibility and adaptability of the recommendation system are improved, the recommendation results are more in line with the actual needs of users, and user stickiness is enhanced; The content database stores diverse content resources, covering information in multiple fields such as navigation, entertainment, and news, including a multimedia resource library, a real-time news library, and a user preference library. The multimedia resource library provides rich audio-visual content, the real-time news library updates instant information, and the user preference library records personalized selections. The three complement each other to form a three-dimensional information matrix, providing comprehensive, dynamic, and precise data support for the intelligent recommendation system; The intelligent recommendation engine adopts an advanced algorithm model, which is based on deep learning and big data analysis, dynamically adjusts the recommendation strategy, comprehensively analyzes user behavior data and preference information, dynamically generates a personalized recommendation list, and accurately pushes navigation paths, entertainment content, and real-time information that meet user needs, effectively breaking the information cocoon, broadening the user's cognitive horizon, promoting comprehensive and objective thinking. At the same time, through thematic recommendations and popular topic guidance, the platform strengthens the attention to social issues and public affairs, increases the frequency of users' exposure to diverse information, promotes the integration of cross-domain knowledge, stimulates users' interest in exploring unknown fields, and cultivates the ability of in-depth thinking.

[0018] In summary, the intelligent recommendation system not only optimizes the efficiency of information acquisition, but also subtly shapes the user's thinking mode, promotes the diversified development of the knowledge system, helps to build an open and inclusive information ecological environment, and ultimately realizes the double improvement of user value and platform value. Through algorithm iteration and data optimization, continuously improve the recommendation accuracy, deepen user insight, promote the accurate docking of information supply and demand, help users navigate efficiently in the information ocean, achieve cognitive upgrade and wisdom growth, build a harmonious information ecology, and empower the coordinated progress of individuals and society.

[0019] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device.

[0020] Finally, it should be noted that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An intelligent recommendation system for in-vehicle content information based on Internet of Vehicles, comprising an Internet of Vehicles communication module, a user behavior analysis unit, a content database and an intelligent recommendation engine, characterized in that: The Internet of Vehicles communication module, user behavior analysis unit, and content database are all connected to the intelligent recommendation engine. The Internet of Vehicles communication module is responsible for real-time data transmission, the user behavior analysis unit accurately captures driving habits, and the content database stores massive amounts of information. The intelligent recommendation engine dynamically generates personalized recommendation content based on user preferences and behavior data, thereby improving driving experience and optimizing information acquisition efficiency. The Internet of Vehicles communication module includes a GPS positioning module, a wireless network interface and a data encryption unit. The GPS positioning module accurately tracks the vehicle location, the wireless network interface ensures high-speed data transmission, and the data encryption unit ensures information security. The three work together to provide stable and reliable data support for intelligent recommendation. The user behavior analysis unit includes a behavior collection module, a data analysis engine and a user portrait generator. The behavior collection module records driving behavior in real time, the data analysis engine deeply mines behavior patterns, and the user portrait generator accurately depicts user characteristics, providing an accurate basis for intelligent recommendation. The content database stores diversified content resources, covering information in multiple fields such as navigation, entertainment, and information, including a multimedia resource library, a real-time information library, and a user preference library. The multimedia resource library provides rich audio-visual content, the real-time information library updates instant information, and the user preference library records personalized choices. The three complement each other to form a three-dimensional information matrix, providing comprehensive, dynamic, and accurate data support for the intelligent recommendation system; The intelligent recommendation engine adopts an advanced algorithm model based on deep learning and big data analysis, dynamically adjusts the recommendation strategy, comprehensively analyzes user behavior data and preference information, dynamically generates personalized recommendation lists, and accurately pushes navigation paths, entertainment content and real-time information that meet user needs, effectively breaking the information cocoon, broadening the user's cognitive horizons, and promoting comprehensive and objective thinking. At the same time, the platform strengthens the attention to social issues and public affairs through special recommendations and hot topic guidance, increases the frequency of users' exposure to diverse information, promotes the integration of cross-domain knowledge, stimulates users' interest in exploring unknown areas, and cultivates deep thinking ability.

2. The vehicle content information intelligent recommendation system based on the Internet of Vehicles according to claim 1 is characterized by: The GPS positioning module includes a high-precision satellite receiver, a real-time dynamic monitoring chip and a position correction algorithm. The high-precision satellite receiver accurately locks the satellite signal, the real-time dynamic monitoring chip continuously updates the position information, and the position correction algorithm effectively eliminates errors to ensure the accuracy and real-time nature of the vehicle position data.

3. The vehicle-mounted content information intelligent recommendation system based on the Internet of Vehicles according to claim 1, characterized in that: The wireless network interface includes a multi-band antenna, a signal amplifier and a network protocol converter. The multi-band antenna enhances the signal receiving capability, the signal amplifier improves the transmission stability, and the network protocol converter ensures seamless data connection. The three work together to ensure efficient and stable data transmission.

4. The vehicle-mounted content information intelligent recommendation system based on the Internet of Vehicles according to claim 1, characterized in that: The data encryption unit includes a symmetric encryption chip, an asymmetric encryption module and a key manager. The symmetric encryption chip quickly processes large amounts of data, the asymmetric encryption module enhances the security level, and the key manager dynamically updates the key. The three together ensure the absolute security of data transmission.

5. The vehicle-mounted content information intelligent recommendation system based on the Internet of Vehicles according to claim 4 is characterized in that: When decryption is required, the key manager generates a decryption key according to a preset algorithm. The symmetric encryption chip and the asymmetric encryption module work together to quickly and accurately decrypt data, ensuring the integrity and privacy of information during transmission, and providing users with safe and reliable intelligent recommendation services. The decryption formula is: Dk = (Ek ⊕ Fk) / Gk Where Dk is the decryption key, Ek is the encryption key, Fk is the auxiliary key, and Gk is the check factor. Through this formula, the system can efficiently complete data decryption and ensure that user privacy is not violated.

6. The vehicle-mounted content information intelligent recommendation system based on the Internet of Vehicles according to claim 4, characterized in that: When encryption is required, the key manager generates an encryption key based on the same algorithm. The symmetric encryption chip and the asymmetric encryption module work together to encrypt the data into ciphertext to ensure that the data is not tampered with or stolen during transmission. The encryption formula is: Ek = (Dk ⊕ Fk) * Gk Among them, Ek is the encryption key, Dk is the decryption key, Fk is the auxiliary key, and Gk is the check factor. Through this formula, the system can efficiently complete data encryption, ensure the security and reliability of information during transmission, and provide users with a seamless and efficient intelligent recommendation experience.

7. The vehicle-mounted content information intelligent recommendation system based on the Internet of Vehicles according to claim 1 is characterized by: The behavior acquisition module includes a sensor array, a data buffer and a behavior recognition algorithm. The sensor array captures driving data in all directions, the data buffer temporarily stores massive information, and the behavior recognition algorithm efficiently analyzes the behavior pattern to ensure the real-time and accuracy of data processing; The analytical formula of the behavior recognition algorithm is: A = h(B) + β * k(C) Among them, B represents sensor data, C represents environmental variables, β is the correction coefficient, h(B) extracts behavioral features, and k(C) reflects environmental influencing factors. Through β dynamic correction, the accuracy of behavior recognition is ensured, user behavior and environmental factors are comprehensively considered, the robustness of the algorithm model is improved, behavior prediction in multiple scenarios is achieved, the transparency and explainability of the algorithm are enhanced, and the user's right to know is ensured.

8. The vehicle-mounted content information intelligent recommendation system based on the Internet of Vehicles according to claim 1, characterized in that: The data analysis engine integrates machine learning algorithms to deeply explore user behavior patterns. The user portrait generator accurately describes user characteristics based on multi-dimensional data, achieves accurate matching of personalized recommendation content, and improves user experience. The data analysis engine integrates machine learning algorithms, and its algorithm formula is: Y = f(X) + α * g(Z) Where X represents user behavior data, Z represents content feature vector, α is adjustment parameter, f(X) reflects user behavior pattern, g(Z) describes content attribute, where f and g are feature extraction and weight assignment functions respectively. By dynamically adjusting weights through α, accurate matching of user behavior and content attributes can be achieved, thus improving the flexibility and adaptability of recommendation system, making recommendation results more in line with users’ actual needs and enhancing user stickiness.

Images