Health drink recommendation system based on artificial intelligence

Abstract

The invention discloses a healthy drink recommendation system based on artificial intelligence, and relates to the technical field of health preservation and health, and the healthy drink recommendation system based on artificial intelligence comprises a central control module, a data acquisition module, a data processing module, a recommendation generation module and a user feedback module. According to the system, the body data, the beverage preference data and the environment data of the user are obtained through the data acquisition module, the extracted data are processed through the data processing module, the beverage features are matched with the user requirements through the recommendation generation module, the recommendation list is generated, the recommendation result is displayed through an interaction interface in the user feedback module, and the user experience is improved. According to the method, the user can conveniently select proper beverage supplies according to the body health condition of the user, the problems that in the prior art, functional component analysis in a beverage recommendation scene is insufficient, and drinking time and drinking frequency are not fully considered are solved, and the accuracy and adaptability of a recommendation result are enhanced.

Description

Technical Field

[0001] The present invention relates to the field of health and wellness technology, and in particular to an artificial intelligence-based healthy drink recommendation system. Background Art

[0002] With the widespread application of artificial intelligence technology in health management, healthy drink recommendation systems have gradually become an important tool for meeting users' personalized needs. However, existing healthy drink recommendation technologies still have certain shortcomings in data integration, personalized recommendation algorithms, and user experience optimization, which affect the accuracy and practicality of recommendations.

[0003] Patent publication number CN118315024B is an artificial intelligence-based special medical food recommendation system and method. This patent collects patients' medical records, health status, food preferences and treatment goal data, and uses semantic analysis and semantic alignment scores to determine whether special medical foods meet patients' potential needs, thereby providing personalized food recommendations.

[0004] However, this technical solution primarily focuses on the field of special medical foods, with limited coverage of health drink recommendation scenarios and a failure to fully consider the specific attributes of drinks (such as their functional ingredients, consumption frequency, and drinking time). Furthermore, this solution lacks the ability to integrate multi-dimensional data for drink recommendations, potentially impacting the accuracy and diversity of recommendations. Therefore, the present invention provides an AI-based health drink recommendation system to enhance the accuracy, practicality, and user experience of health drink recommendations, thereby better meeting users' personalized needs for healthy drinks. Summary of the Invention

[0005] The purpose of the present invention is to provide an artificial intelligence-based healthy drink recommendation system to solve the problems raised in the above background technology.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: An artificial intelligence-based healthy drink recommendation system, the artificial intelligence-based healthy drink recommendation system comprising: a central control module, a data acquisition module, a data processing module, a recommendation generation module and a user feedback module; The central control module is the center of the system and is connected to the data acquisition module, data processing module, recommendation generation module and user feedback module through the data bus to interact with data; The data acquisition module is connected to the central control module and is provided with a physiological data acquisition unit, a preference data acquisition unit and an environmental data acquisition unit for acquiring the user's physical data, beverage preference data and environmental data; The data processing module is connected to the output end of the data acquisition module and is internally provided with a data cleaning unit, a feature extraction unit, and a weight assignment unit for performing denoising on the raw data, extracting functional ingredients, drinking time distribution, and drinking frequency characteristics of the beverage from the cleaned data, and adjusting the weight value of each feature based on the user's historical behavior; The recommendation generation module is connected to the output end of the data processing module and is provided with a dynamic matching unit and a priority sorting unit for matching beverage characteristics with user needs through the dynamic matching unit and generating a recommendation list through the priority sorting unit; The user feedback module is connected to the recommendation generation module, and is provided with an interactive interface and a feedback recording unit. The interactive interface is used to display the recommendation results, and the feedback recording unit is used to collect the user's actual selection behavior.

[0007] A further improvement of the technical solution of the present invention is that: the central control module includes: a central processing unit, a memory, and a communication interface; The central processing unit is responsible for coordinating the data flow and logical operations among the data acquisition module, the data processing module, the recommendation generation module and the user feedback module; The memory is divided into a cache area and a long-term storage area, wherein the cache area is used to temporarily store real-time data, and the long-term storage area is used to save historical records, and uses artificial intelligence based on cloud computing to store the medicinal properties of various ingredients; The communication interface supports Wi-Fi, Bluetooth and Zigbee protocols to ensure data exchange between the central control module and other hardware devices.

[0008] A further improvement of the technical solution of the present invention is that the interior of the data acquisition module includes: Physiological data acquisition unit: used to obtain the user's physiological indicators through wearable devices, such as measuring heart rate through a heart rate monitor, measuring blood pressure through a blood pressure monitor, and measuring blood sugar level through a blood glucose meter; Preference data collection unit: used to record users' beverage consumption habits through mobile applications, including consumption time, drinking frequency and beverage types; Environmental data acquisition unit: used to obtain user environmental information such as temperature, humidity and air quality through sensors.

[0009] A further improvement of the technical solution of the present invention is that the data processing module includes: Data cleaning unit: The data cleaning unit includes an outlier detection unit and a data completion unit; Feature extraction unit: The feature extraction unit includes a functional component analysis unit, a time distribution analysis unit and a frequency analysis unit; Weight allocation unit: The weight allocation unit includes a historical behavior analysis unit and a dynamic adjustment unit.

[0010] A further improvement of the technical solution of the present invention is that: the outlier detection unit identifies and removes outliers in the data by using a statistical method, and the data completion unit fills in the missing data by using an interpolation algorithm; The functional component analysis unit labels the functional components of the beverage using a chemical component database, the time distribution analysis unit analyzes the user's drinking time pattern using a time series algorithm, and the frequency analysis unit determines the user's drinking frequency pattern using a clustering algorithm; The historical behavior analysis unit models the user's historical data through a machine learning model and calculates the initial weight value of each feature. The dynamic adjustment unit is used to update the weight value according to the user's real-time feedback data.

[0011] A further improvement of the technical solution of the present invention is that the recommendation generation module includes: Dynamic matching unit: Calculates the similarity between beverage features and user needs using the cosine similarity algorithm, and comprehensively evaluates the similarity results using a weighted scoring algorithm; Priority sorting unit: The drinks are divided into three categories of high priority, medium priority and low priority according to the matching evaluation results, and the high-priority drinks are further sorted using the bubble sort algorithm to generate the final recommendation list.

[0012] A further improvement of the technical solution of the present invention is that the user feedback module includes: Interactive interface: This interface presents functional ingredients, drinking recommendations, and nutritional value of beverages through a combination of graphics and text. It also allows users to manually adjust the priority and filter conditions of beverage recommendations. It also collects user satisfaction ratings on the recommended results in real time through buttons and sliders. Feedback recording unit: stores user feedback data through distributed database technology and analyzes user behavior patterns through association rule mining algorithms.

[0013] Due to the adoption of the above technical solution, the present invention has the following technical advancements compared to the prior art: 1. The present invention provides an artificial intelligence-based healthy drink recommendation system. The system obtains the user's physical data, drink preference data, and environmental data through a data acquisition module, and processes the extracted data using a data processing module. The recommendation generation module matches the drink characteristics with the user's needs and generates a recommendation list. The recommendation results are displayed using an interactive interface in a user feedback module, making it convenient for users to choose appropriate drinks and supplies based on their own physical health conditions. This solves the problems of insufficient functional ingredient analysis and insufficient consideration of drinking time and frequency in the existing technology in drink recommendation scenarios, thereby enhancing the accuracy and adaptability of the recommendation results.

[0014] 2. The present invention provides an artificial intelligence-based healthy drink recommendation system. The data cleaning unit uses statistical methods to identify and eliminate outliers in the data, and uses interpolation algorithms to fill in missing data to improve the quality and availability of the data. The weight allocation unit models the user's historical data through a machine learning model, calculates the initial weight value of each feature, and updates the weight value based on the user's real-time feedback data to improve the user experience and the practicality of the recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is the overall schematic diagram of the AI-based healthy drink recommendation system; Figure 2 This is a schematic diagram of the connections between the various modules within the AI-based healthy drink recommendation system. DETAILED DESCRIPTION

[0016] The present invention is described in further detail below in conjunction with the embodiments: Example 1 like Figure 1-2 As shown, the present invention provides an artificial intelligence-based healthy drink recommendation system, which includes: a central control module, a data acquisition module, a data processing module, a recommendation generation module and a user feedback module; The central control module is the center of the system and is connected to the data acquisition module, data processing module, recommendation generation module and user feedback module through the data bus for data interaction; The data acquisition module is connected to the central control module and is provided with a physiological data acquisition unit, a preference data acquisition unit and an environmental data acquisition unit for acquiring the user's physical data, beverage preference data and environmental data; The data processing module is connected to the output end of the data acquisition module and is internally equipped with a data cleaning unit, a feature extraction unit, and a weight assignment unit. It is used to denoise the raw data, extract the functional ingredients, drinking time distribution, and drinking frequency characteristics of the beverage from the cleaned data, and adjust the weight value of each feature based on the user's historical behavior; The recommendation generation module is connected to the output end of the data processing module and is provided with a dynamic matching unit and a priority sorting unit, for matching the characteristics of the beverages with the user's needs through the dynamic matching unit and generating a recommendation list through the priority sorting unit; The user feedback module is connected to the recommendation generation module, and is provided with an interactive interface and a feedback recording unit. The interactive interface is used to display the recommendation results, and the feedback recording unit is used to collect the user's actual selection behavior.

[0017] The central control module includes: central processing unit, memory, and communication interface; The central processing unit is responsible for coordinating the data flow and logical operations between the data acquisition module, data processing module, recommendation generation module and user feedback module; The memory is divided into a cache area and a long-term storage area. The cache area is used to temporarily store real-time data, and the long-term storage area is used to save historical records. It also uses artificial intelligence and cloud computing to store the medicinal properties of various ingredients. The communication interface supports Wi-Fi, Bluetooth and Zigbee protocols to ensure data exchange between the central control module and other hardware devices.

[0018] The central control module is responsible for coordinating the data flow and logical operations between various modules, and connecting with the data processing module using wireless communication protocols such as Bluetooth or Wi-Fi to ensure the real-time and stability of subsequent data transmission.

[0019] The data acquisition module includes: Physiological data acquisition unit: used to obtain the user's physiological indicators through wearable devices, such as measuring heart rate through a heart rate monitor, measuring blood pressure through a blood pressure monitor, and measuring blood sugar level through a blood glucose meter; Preference data collection unit: used to record users' beverage consumption habits through mobile applications, including consumption time, drinking frequency and beverage types; Environmental data acquisition unit: used to obtain user environmental information such as temperature, humidity and air quality through sensors.

[0020] The data acquisition module monitors the user's heart rate, blood pressure, blood sugar level and other physiological indicators in real time through wearable devices, and records the data in the form of timestamps. It obtains environmental parameters such as temperature, humidity and air quality through sensors arranged around the user, providing data support for subsequent beverage recommendations.

[0021] The data processing module includes: Data cleaning unit: The data cleaning unit includes an outlier detection unit and a data completion unit; The outlier detection unit uses statistical methods to identify and eliminate outliers in the data, and the data completion unit uses interpolation algorithms to fill in missing data.

[0022] Feature extraction unit: The feature extraction unit includes a functional component analysis unit, a time distribution analysis unit, and a frequency analysis unit; The functional component analysis unit labels the functional components of the beverage through the chemical component database, the time distribution analysis unit analyzes the user's drinking time pattern through the time series algorithm, and the frequency analysis unit determines the user's drinking frequency pattern through the clustering algorithm.

[0023] Weight allocation unit: The weight allocation unit includes a historical behavior analysis unit and a dynamic adjustment unit.

[0024] The historical behavior analysis unit models the user's historical data through a machine learning model and calculates the initial weight value of each feature. The dynamic adjustment unit is used to update the weight value based on the user's real-time feedback data.

[0025] The function of the data processing module is to denoise the data transmitted by the data acquisition module and use the linear interpolation algorithm to estimate the missing values ​​based on the previous and next data points, thereby improving the integrity and reliability of the data.

[0026] The recommendation generation module includes: Dynamic matching unit: Calculates the similarity between beverage features and user needs using the cosine similarity algorithm, and comprehensively evaluates the similarity results using a weighted scoring algorithm; Priority sorting unit: The drinks are divided into three categories of high priority, medium priority and low priority according to the matching evaluation results, and the high-priority drinks are further sorted using the bubble sort algorithm to generate the final recommendation list.

[0027] The recommendation generation module classifies drinks with matching scores higher than a certain threshold as high priority, and further sorts the high-priority drinks through a bubbling algorithm to generate a recommendation list.

[0028] The user feedback module includes: Interactive interface: This interface presents functional ingredients, drinking recommendations, and nutritional value of beverages through a combination of graphics and text. It also allows users to manually adjust the priority and filter conditions of beverage recommendations. It also collects user satisfaction ratings on the recommended results in real time through buttons and sliders. Feedback recording unit: stores user feedback data through distributed database technology and analyzes user behavior patterns through association rule mining algorithms.

[0029] The user feedback module graphically displays recommendation results and provides a variety of action options for users to choose from, such as a chart showing the content of the main ingredients in a drink and their health benefits. The user preference module allows users to manually adjust the priority and filter conditions of drink recommendations, for example, they can set it to only recommend low-sugar drinks or drinks within a specific time period. Users can express their opinions on the recommendations by clicking the "satisfied" or "unsatisfied" buttons.

[0030] The operation process of this system is as follows: First, the data acquisition module obtains the user's multi-dimensional data through the physiological data acquisition unit, the behavioral data acquisition unit and the environmental data acquisition unit, and passes the data to the data processing module. The data processing module denoises the original data through the data cleaning unit, and uses the feature extraction unit to extract key features such as functional ingredients, drinking time distribution and drinking frequency. The weight allocation unit adjusts the weight value of each feature according to the user's historical behavior and real-time feedback. Then the recommendation generation module matches the beverage characteristics with the user's needs through the dynamic matching unit, and uses the priority sorting unit to generate a recommendation list. Finally, the user feedback module uses the interactive interface to display the recommendation results, and collects the user's selection behavior through the feedback recording unit.

[0031] In summary, the effects of the present invention are: the user's physical data, beverage preference data and environmental data are obtained through the data acquisition module, and the extracted data is processed by the data processing module. The recommendation generation module matches the beverage characteristics with the user's needs and generates a recommendation list. The interactive interface in the user feedback module is used to display the recommendation results, which is convenient for users to choose suitable beverages and supplies according to their own physical health conditions. It solves the problems of insufficient functional ingredient analysis and insufficient consideration of drinking time and frequency in the existing technology in the beverage recommendation scenario, and enhances the accuracy and adaptability of the recommendation results.

[0032] The above generally describes the present invention in detail. However, it is obvious to those skilled in the art that modifications or improvements may be made based on the present invention. Therefore, modifications or improvements that do not depart from the spirit of the present invention are within the scope of protection of the present invention.

Claims

1. An artificial intelligence-based healthy drink recommendation system, characterized by: The AI-based healthy drink recommendation system includes: a central control module, a data acquisition module, a data processing module, a recommendation generation module, and a user feedback module; The central control module is the center of the system and is connected to the data acquisition module, data processing module, recommendation generation module and user feedback module through the data bus to interact with data; The data acquisition module is connected to the central control module and is provided with a physiological data acquisition unit, a preference data acquisition unit and an environmental data acquisition unit for acquiring the user's physical data, beverage preference data and environmental data; The data processing module is connected to the output end of the data acquisition module and is internally provided with a data cleaning unit, a feature extraction unit, and a weight assignment unit for performing denoising on the raw data, extracting functional ingredients, drinking time distribution, and drinking frequency characteristics of the beverage from the cleaned data, and adjusting the weight value of each feature based on the user's historical behavior; The recommendation generation module is connected to the output end of the data processing module and is provided with a dynamic matching unit and a priority sorting unit for matching beverage characteristics with user needs through the dynamic matching unit and generating a recommendation list through the priority sorting unit; The user feedback module is connected to the recommendation generation module, and is provided with an interactive interface and a feedback recording unit. The interactive interface is used to display the recommendation results, and the feedback recording unit is used to collect the user's actual selection behavior.

2. The artificial intelligence-based healthy drink recommendation system according to claim 1, characterized in that: The central control module includes: a central processing unit, a memory, and a communication interface; The central processing unit is responsible for coordinating the data flow and logical operations among the data acquisition module, the data processing module, the recommendation generation module and the user feedback module; The memory is divided into a cache area and a long-term storage area, wherein the cache area is used to temporarily store real-time data, and the long-term storage area is used to save historical records, and uses artificial intelligence based on cloud computing to store the medicinal properties of various ingredients; The communication interface supports Wi-Fi, Bluetooth and Zigbee protocols to ensure data exchange between the central control module and other hardware devices.

3. The artificial intelligence-based healthy drink recommendation system according to claim 1, characterized in that: The interior of the data acquisition module includes: Physiological data acquisition unit: used to obtain the user's physiological indicators through wearable devices, such as measuring heart rate through a heart rate monitor, measuring blood pressure through a blood pressure monitor, and measuring blood sugar level through a blood glucose meter; Preference data collection unit: used to record users' beverage consumption habits through mobile applications, including consumption time, drinking frequency and beverage types; Environmental data acquisition unit: used to obtain user environmental information such as temperature, humidity and air quality through sensors.

4. The artificial intelligence-based healthy drink recommendation system according to claim 1, characterized in that: The data processing module includes: Data cleaning unit: The data cleaning unit includes an outlier detection unit and a data completion unit; Feature extraction unit: The feature extraction unit includes a functional component analysis unit, a time distribution analysis unit and a frequency analysis unit; Weight allocation unit: The weight allocation unit includes a historical behavior analysis unit and a dynamic adjustment unit.

5. The artificial intelligence-based healthy drink recommendation system according to claim 4, characterized in that: The outlier detection unit identifies and removes outliers in the data using statistical methods, and the data completion unit fills in missing data using an interpolation algorithm; The functional component analysis unit labels the functional components of the beverage using a chemical component database, the time distribution analysis unit analyzes the user's drinking time pattern using a time series algorithm, and the frequency analysis unit determines the user's drinking frequency pattern using a clustering algorithm; The historical behavior analysis unit models the user's historical data through a machine learning model and calculates the initial weight value of each feature. The dynamic adjustment unit is used to update the weight value according to the user's real-time feedback data.

6. The artificial intelligence-based healthy drink recommendation system according to claim 1, characterized in that: The recommendation generation module includes: Dynamic matching unit: Calculates the similarity between beverage features and user needs using the cosine similarity algorithm, and comprehensively evaluates the similarity results using a weighted scoring algorithm; Priority sorting unit: The drinks are divided into three categories of high priority, medium priority and low priority according to the matching evaluation results, and the high-priority drinks are further sorted using the bubble sort algorithm to generate the final recommendation list.

7. The artificial intelligence-based healthy drink recommendation system according to claim 1, characterized in that: The user feedback module includes: Interactive interface: This interface presents functional ingredients, drinking recommendations, and nutritional value of beverages through a combination of graphics and text. It also allows users to manually adjust the priority and filter conditions of beverage recommendations. It also collects user satisfaction ratings on the recommended results in real time through buttons and sliders. Feedback recording unit: stores user feedback data through distributed database technology and analyzes user behavior patterns through association rule mining algorithms.

Images