Intelligent coffee robot taste detection system

Abstract

The invention discloses an intelligent coffee robot taste detection system, and relates to the technical field of artificial intelligence, and the system comprises a taste collection module which collects coffee taste preference data of a user; the taste analysis module is used for analyzing coffee taste data collected by the user and identifying taste characteristics preferred by the user; the formula optimization module is used for generating a personalized coffee formula based on the taste characteristics output by the taste analysis module; the coffee making module is used for making coffee according to the generated personalized coffee formula and adjusting taste parameters; and the taste adjustment feedback module is used for collecting user feedback after the user tastes the coffee and adjusting the coffee making formula according to the feedback information. Through personalized customization, intelligent adjustment and real-time data analysis, the taste requirement of the user is accurately met, the satisfaction degree of the user is improved, time and energy are saved, and meanwhile, the system optimizes making according to the physiological and environmental data of the user and provides coffee experience which is healthier and more suitable for individual requirements.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an intelligent coffee robot taste detection system. Background Art

[0002] With the advancement of science and technology, artificial intelligence technology has been widely used in various fields. Among them, the application of intelligent equipment has gradually penetrated into daily life, especially intelligent beverage making equipment. As one of the most popular beverages in the world, the market demand for coffee continues to increase, but traditional coffee making methods are still difficult to meet the personalized needs of different consumers. Although existing coffee machines can make coffee according to the set parameters, most devices lack the ability to accurately identify and adjust user taste preferences.

[0003] The emergence of the intelligent coffee robot flavor detection system aims to solve the problem that traditional coffee making equipment cannot be accurately adjusted according to the user's personalized taste needs. Through the collaborative work of multiple modules such as flavor collection, analysis, and optimization, the system can not only identify the user's taste preferences, but also make real-time adjustments based on user feedback to achieve personalized customization of each cup of coffee. Summary of the Invention

[0004] In order to solve the above technical problems, an intelligent coffee robot taste detection system is provided. This technical solution solves the above problems.

[0005] In order to achieve the above objects, the technical solution adopted by the present invention is: Intelligent coffee robot taste detection system, including: Taste collection module, used to collect users' coffee taste preference data; The taste analysis module is used to analyze the coffee taste data collected by the user and identify the taste characteristics preferred by the user; The recipe optimization module is used to generate personalized coffee recipes based on the taste characteristics output by the taste analysis module; A coffee making module is used to make coffee according to the generated personalized coffee recipe and adjust the taste parameters; The taste adjustment feedback module is used to collect user feedback after the user tastes the coffee and adjust the coffee making recipe based on the feedback information.

[0006] Preferably, the taste collection module specifically includes: Obtain the user's basic information, including age, gender, dietary habits, and allergy information, obtain the user's coffee taste preferences, and obtain the user's ratings for each taste dimension; Record users' past taste choices and preferences, form a historical data archive of taste preferences, regularly obtain changing trends in user tastes, and identify patterns in taste changes; Based on sensors, collect the heart rate changes of users when drinking coffee, infer their taste preferences, and collect the environmental data of users when drinking coffee, including the influence of external factors such as the temperature and humidity during coffee drinking on users' tastes; Generate a user taste portrait according to the feedback data and historical preferences of users, and record the preference patterns of users.

[0007] Preferably, the taste analysis module specifically includes: Feature extraction and classification unit: Extract key information from the taste data of users, including sweetness, acidity, bitterness, richness, and aftertaste taste characteristics, extract the preferences of users in each taste dimension through cluster analysis, form a high-dimensional taste feature vector, and label and classify the data of each user based on the preferences of users; Preference feature modeling unit: Establish a personalized taste preference model according to the historical taste data and preferences of users, and predict the trend changes of users' taste preferences through a time series analysis model; Taste analysis report generation: Generate a visual report of users' taste preferences, showing the scores, preferences, and change trends of users in different taste dimensions.

[0008] Preferably, the extraction of the preferences of users in each taste dimension through cluster analysis to form a high-dimensional taste feature vector specifically includes: Divide the user taste data into different clusters, identify the taste preferences of users, minimize the squared error within the clusters based on the cluster analysis algorithm, and cluster and extract the characteristics of each cluster of the user taste data through the cluster analysis algorithm to form a high-dimensional taste feature vector, where the squared error formula is: In the formula, is the number of clusters, is the th cluster, is the data point belonging to cluster , is the centroid of cluster , is the total squared error.

[0009] Preferably, the prediction of the trend changes of users' taste preferences through a time series analysis model specifically includes: Among them, the time series analysis model formula is: In the formula, is the predicted value of the time series at time , is the mean value of the data, is the weight coefficient of the observed value at time , is the observed value at time , is the observed value at time , is the weight coefficient of the observed value at time , is the observed value at time , is the weight coefficient of the observed value at time , is the prediction error at time , is the prediction error at time , is the prediction error at time , The random error at time , is 's weight coefficient, is 's weight coefficient, is 's weight coefficient.

[0010] Preferably, the formula optimization module specifically includes: User taste feature input unit: Receives user taste feature data from the taste analysis module, including the user's preferences for the taste dimensions of sweetness, acidity, bitterness, richness, and aftertaste. The input data also includes environmental factors, heart rate changes, and user feedback information; Taste feature matching unit: Uses a similarity matching algorithm to match the user's personalized taste features with existing coffee formulas to determine the most suitable coffee base formula, and based on the user's preferences, matches the best combination of coffee flavor features; Personalized formula generation: Automatically generates a personalized coffee formula according to the taste features and matching results, and determines each coffee element, including coffee bean variety, grind degree, extraction method, temperature, and proportion parameters, to meet the user's preferences.

[0011] Preferably, the formula optimization module further includes: Personalized adjustment unit: Automatically adjusts the parameters of the coffee formula according to the user's real-time feedback and environmental changes, so that each cup of coffee made meets the user's taste requirements; Data feedback storage unit: Records the process data of each generation of personalized coffee formulas, and optimizes the matching algorithm according to historical data to improve the accuracy of taste matching.

[0012] Preferably, the coffee making module specifically includes: Coffee bean selection unit: Automatically select and adjust the quantity, type, and grind degree of coffee beans according to the coffee bean types determined in the personalized recipe. Extraction control unit: Adjust the extraction time, temperature, and pressure parameters according to the generated personalized coffee recipe to achieve the best coffee taste. Automatic flavoring unit: Automatically add sugar and milk ingredients according to the user's taste requirements to adjust the overall taste of the coffee.

[0013] Preferably, the coffee making module further includes: Intelligent temperature control unit: Real-time monitor the temperature of the coffee liquid through a temperature sensor to make the coffee produced each time reach the required taste. Pressure control unit: Adjust the richness and taste layering of the coffee by controlling the pressure parameters during extraction.

[0014] Preferably, the taste adjustment feedback module specifically includes: Feedback collection unit: Collect the taste evaluations of users after drinking coffee, including feedback on sweetness, acidity, and richness, and quantify these feedbacks. Feedback analysis unit: Analyze the taste feedback of users, combine historical data and real-time environmental factors, and automatically adjust the coffee making parameters. Feedback storage and optimization unit: Compare the feedback information of users with historical data, regularly optimize the coffee recipe and production process to meet the user's taste requirements for a long time. <(

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention proposes to precisely meet the user's taste requirements through personalized customization, intelligent adjustment, and real-time data analysis, improve user satisfaction. The automated coffee making process saves time and effort and reduces waste. At the same time, the system optimizes production according to the user's physiological and environmental data to provide a healthier and more personalized coffee experience. Through the self-improvement of the continuous feedback mechanism, the system continuously optimizes the algorithm and taste matching to ensure that each cup of coffee meets the user's requirements and improves the long-term use experience. Brief Description of the Drawings

[0016] Figure 1 It is the system framework diagram of the present invention; Figure 2 It is the internal system framework diagram of the taste analysis module in the present invention. Detailed Embodiments

[0017] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations.

[0018] Referring to Figure 1 as shown, the intelligent coffee robot taste detection system includes: A taste collection module for collecting data on users' coffee taste preferences; A taste analysis module for analyzing the coffee taste data collected from users and identifying the taste characteristics preferred by users; A formula optimization module for generating personalized coffee formulas based on the taste characteristics output by the taste analysis module; A coffee making module for making coffee according to the generated personalized coffee formula and adjusting taste parameters; A taste adjustment feedback module for collecting user feedback after the user tastes the coffee and adjusting the coffee making formula according to the feedback information.

[0019] The taste collection module specifically includes: Obtain the user's basic information, including age, gender, eating habits, and allergy information, obtain the user's coffee taste preferences, and obtain the user's ratings for each taste dimension; Record the user's past taste selections and preferences to form a historical data file of taste preferences, regularly obtain the user's taste change trends, and identify the laws of taste changes; Based on sensors, collect the user's heart rate changes when drinking coffee, infer their taste tendencies, and collect the user's coffee drinking environment data, including the external factors such as the temperature and humidity when drinking coffee that affect the user's taste; Generate a user taste portrait according to the user's feedback data and historical preferences, and record the user's preference patterns; By integrating multi-dimensional data collection methods, it can not only accurately identify the user's taste preferences, but also infer the user's taste tendencies based on environmental changes and physiological states, realizing the construction of a comprehensive taste portrait model for users.

[0020] Referring to Figure 2 as shown, the taste analysis module specifically includes: A feature extraction and classification unit: extract key information from the user's taste data, including sweetness, acidity, bitterness, richness, and aftertaste taste characteristics, extract the user's preferences in each taste dimension through clustering analysis, form a high-dimensional taste feature vector, label the data of each user based on the user's preferences, and classify these labels; A preference feature modeling unit: establish a personalized taste preference model according to the user's historical taste data and preferences, and predict the trend changes of the user's taste preferences through a time series analysis model; Taste Analysis Report Generation: Generate a visual report of user taste preferences, showing the ratings, preferences, and trend changes of users in different taste dimensions; Use the clustering analysis method to extract high-dimensional features from taste data, generate user taste feature vectors through classification and labeling, and combine time series analysis to predict the trend changes of user taste preferences. It can understand and predict the preference changes of users in real time, and optimize the intelligent response ability of the system.

[0021] Extract the preferences of users in each taste dimension through the clustering analysis method to form high-dimensional taste feature vectors, specifically including: Divide the user taste data into different clusters, identify the taste preferences of users, minimize the squared error within the clusters based on the clustering analysis algorithm, and through the clustering analysis algorithm, cluster the user taste data and extract the features of each cluster to form high-dimensional taste feature vectors. Among them, the squared error formula is: In the formula, is the number of clusters, is the th cluster, is the data point belonging to cluster , is the centroid of cluster , is the total squared error; The clustering analysis algorithm can effectively identify different taste groups in the user taste data. By minimizing the squared error within the clusters, the taste characteristics of each user can be classified more accurately. This method can efficiently reduce the matching error in practical applications and enhance the personalized recommendation ability of the system.

[0022] Predict the trend changes of user taste preferences through the time series analysis model, specifically including: Among them, the time series analysis model formula is: In the formula, is the predicted value of the time series at time , is the mean of the data, is the weight coefficient of the observed value at time , is the observed value at time , is the observed value at time , is the weight coefficient of the observed value at time , is the observed value at time , At time is the weight coefficient of the observed value, is the prediction error at time ; is the prediction error at time ; is the prediction error at time ; The random error at time ; is 's weight coefficient, is 's weight coefficient, is 's weight coefficient; Dynamically predict the change trend of the user's taste through a time - series model, enabling the system to adapt to the user's taste changes and make adjustments in advance. This model can adjust the coffee recipe according to the user's long - term behavior and feedback, providing a better continuous personalized experience.

[0023] The recipe optimization module specifically includes: User taste feature input unit: Receive the user taste feature data from the taste analysis module, including the user's preferences for taste dimensions such as sweetness, acidity, bitterness, richness, and aftertaste. The input data also includes environmental factors, heart rate changes, and user feedback information; Taste feature matching unit: Use a similarity matching algorithm to match the user's personalized taste features with the existing coffee recipes, determine the most suitable coffee base recipe, and match the best combination of coffee flavor features based on the user's preferences; Personalized recipe generation: Automatically generate a personalized coffee recipe according to the taste features and matching results, determine each coffee element, including the type of coffee beans, grind size, extraction method, temperature, and proportion parameters, to meet the user's preferences; The recipe optimization module not only generates a personalized recipe based on the user's taste features, but also dynamically adjusts the recipe parameters in combination with real - time feedback and changes in environmental factors to ensure that each cup of coffee made can precisely meet the user's needs. This innovation makes the coffee making more adaptable and sustainable.

[0024] The recipe optimization module further includes: Personalized adjustment unit: Automatically adjust the parameters of the coffee recipe according to the user's real - time feedback and environmental changes, so that each cup of coffee made meets the user's taste requirements; Data feedback and storage unit: Record the process data of each generation of personalized coffee recipes, and optimize the matching algorithm according to historical data to improve the accuracy of taste matching.

[0025] The coffee making module specifically includes: Coffee bean selection unit: Automatically selects and adjusts the quantity, type, and grind degree of coffee beans according to the coffee bean types determined in the personalized recipe; Extraction control unit: Adjusts the extraction time, temperature, and pressure parameters according to the generated personalized coffee recipe to achieve the best taste of the coffee; Automatic flavoring unit: Automatically adds sugar and milk ingredients according to the user's taste requirements to adjust the overall taste of the coffee.

[0026] The coffee making module further includes: Intelligent temperature control unit: Real-time monitors the temperature of the coffee liquid through a temperature sensor to make the coffee produced each time reach the required taste; Pressure control unit: Adjusts the richness and taste layering of the coffee by controlling the pressure parameters during extraction.

[0027] The taste adjustment feedback module specifically includes: Feedback collection unit: Collects the user's taste evaluations after drinking coffee, including feedback on sweetness, acidity, and richness, and quantifies these feedbacks; Feedback analysis unit: Analyzes the user's taste feedback, combines historical data and real-time environmental factors, and automatically adjusts the coffee making parameters; Feedback storage and optimization unit: Compares the user's feedback information with historical data, regularly optimizes the coffee recipe and production process, and meets the user's taste requirements for a long time.

[0028] In summary, the advantages of the present invention are: This system collects information such as the user's basic information, past preferences, and environmental data through the taste collection module, generates a user taste profile, and adjusts the coffee recipe in combination with the user's real-time feedback, so that each cup of coffee can precisely meet personalized needs; The taste adjustment feedback module can immediately adjust the coffee making parameters according to the user's feedback, ensure that the taste of each coffee meets the user's requirements, and can automatically optimize the production process over time to enhance the user experience; Through the taste analysis module combined with clustering analysis and time series analysis methods, the system can continuously update the trend of the user's taste preferences and provide accurate data support for personalized recipes, enabling the system to predict and adapt to changes in the user's taste; The system can produce an ideal coffee taste by precisely controlling parameters such as coffee bean selection, extraction control, temperature control, and pressure regulation, greatly improving user satisfaction and meeting diverse consumer demands; Through an automated coffee-making and adjustment process, users no longer need to manually set complex parameters, saving time and effort. At the same time, personalized recipe optimization also improves production efficiency and reduces waste; The system collects users' physiological data and environmental data, comprehensively analyzes their impact on taste, and further optimizes coffee production, making the production process not only intelligent but also better adapted to the actual needs of each user; The system is equipped with a feedback storage and optimization unit. By continuously accumulating and analyzing user feedback, the algorithm is gradually optimized to improve the accuracy of taste matching, forming a virtuous cycle, and better satisfying the experience of each user.

[0029] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. Intelligent coffee robot taste detection system, characterized in that, It includes: A taste acquisition module for acquiring data on the coffee taste preferences of users; A taste analysis module for analyzing the coffee taste data collected by users and identifying the taste characteristics preferred by users; A recipe optimization module for generating personalized coffee recipes based on the taste characteristics output by the taste analysis module; A coffee making module for making coffee according to the generated personalized coffee recipe and adjusting the taste parameters; A taste adjustment feedback module for collecting user feedback after the user tastes the coffee and adjusting the coffee making recipe according to the feedback information.

2. The intelligent coffee machine taste detection system according to claim 1, characterized in that, The taste acquisition module specifically includes: Obtaining the basic information of users, including age, gender, eating habits and allergy information, obtaining the taste preferences of users for coffee, and obtaining the scores of users for each taste dimension; Recording the past taste choices and preferences of users to form a historical data archive of taste preferences, regularly obtaining the changing trends of users' tastes, and identifying the laws of taste changes; Based on sensors, collecting the heart rate changes of users when drinking coffee, inferring their taste tendencies, and collecting the environmental data when users drink coffee, including the influence of external factors such as the temperature and humidity when drinking coffee on the users' tastes; Generating a user taste portrait according to the feedback data and historical preferences of users and recording the preference patterns of users.

3. The intelligent coffee machine taste detection system according to claim 1, characterized in that, The taste analysis module specifically includes: A feature extraction and classification unit: extracting key information from the taste data of users, including sweetness, acidity, bitterness, richness and aftertaste taste characteristics, extracting the preferences of users in each taste dimension through the method of cluster analysis to form a high-dimensional taste feature vector, tagging the data of each user based on the preferences of users, and classifying these tags; A preference feature modeling unit: establishing a personalized taste preference model according to the historical taste data and preferences of users, and predicting the trend changes of users' taste preferences through a time series analysis model; Generating a taste analysis report: generating a visual report of users' taste preferences, showing the scores, preferences and changing trends of users in different taste dimensions.

4. The intelligent coffee machine taste detection system according to claim 3, wherein, The extracting the preferences of users in each taste dimension through the method of cluster analysis to form a high-dimensional taste feature vector specifically includes: Dividing the user taste data into different clusters, identifying the taste preferences of users, minimizing the squared error within the clusters based on the cluster analysis algorithm, clustering the user taste data through the cluster analysis algorithm and extracting the characteristics of each cluster to form a high-dimensional taste feature vector, where the squared error formula is: Wherein, is the number of clusters, is the th cluster, is a data point belonging to cluster , is the centroid of cluster , is the total squared error.

5. The intelligent coffee machine taste detection system according to claim 3, characterized in that, The predicting the trend changes of users' taste preferences through a time series analysis model specifically includes: Among them, the time series analysis model formula is: Wherein, is the predicted value of the time series at time , is the mean value of the data, is the weight coefficient of the observed value at time , is the observed value at time , is the observed value at time , is the weight coefficient of the observed value at time , is the observed value at time , is the weight coefficient of the observed value at time , is the prediction error at time , is the prediction error at time , is the prediction error at time , is the random error at time , is 's weight coefficient, is 's weight coefficient, is 's weight coefficient.

6. The intelligent coffee machine taste detection system according to claim 1, characterized in that The recipe optimization module specifically includes: A user taste feature input unit: receiving the user taste feature data from the taste analysis module, including the preferences of users in the taste dimensions of sweetness, acidity, bitterness, richness and aftertaste, and the input data also includes environmental factors, heart rate changes and user feedback information; Taste Feature Matching Unit: Uses a similarity matching algorithm to match the user's personalized taste features with existing coffee recipes, determines the most suitable coffee base recipe, and based on the user's preferences, matches the best combination of coffee flavor features; Personalized Recipe Generation: Automatically generates a personalized coffee recipe according to the taste features and matching results, determines each coffee element, including the type of coffee beans, grind size, extraction method, temperature, and ratio parameters, to meet the user's preferences.

7. The intelligent coffee machine taste detection system according to claim 6, wherein, The recipe optimization module further includes: Personalized Adjustment Unit: Automatically adjusts the parameters of the coffee recipe according to the user's real-time feedback and environmental changes, so that each cup of coffee made meets the user's taste requirements; Data Feedback and Storage Unit: Records the process data of each generation of personalized coffee recipes, and optimizes the matching algorithm according to historical data to improve the accuracy of taste matching.

8. The intelligent coffee machine taste detection system according to claim 1, characterized in that The coffee making module specifically includes: Coffee Bean Selection Unit: Automatically selects and adjusts the quantity, type, and grind size of coffee beans according to the type of coffee beans determined in the personalized recipe; Extraction Control Unit: Adjusts the extraction time, temperature, and pressure parameters according to the generated personalized coffee recipe to make the taste of the coffee reach the best state; Automatic Flavoring Unit: Automatically adds sugar and milk ingredients according to the user's taste requirements to adjust the overall taste of the coffee.

9. The intelligent coffee machine taste detection system according to claim 8, characterized in that, The coffee making module further includes: Intelligent Temperature Control Unit: Real-time monitors the temperature of the coffee liquid through a temperature sensor to make each cup of coffee reach the required taste; Pressure Control Unit: Adjusts the richness and taste layering of the coffee by controlling the pressure parameters during extraction.

10. The intelligent coffee machine flavor detection system according to claim 1, characterized in that, The taste adjustment feedback module specifically includes: Feedback Collection Unit: Collects the user's taste evaluation after drinking coffee, including feedback on sweetness, acidity, and richness, and quantifies this feedback; Feedback Analysis Unit: Analyzes the user's taste feedback, combines historical data and real-time environmental factors, and automatically adjusts the coffee making parameters; Feedback Storage and Optimization Unit: Compares the user's feedback information with historical data, and regularly optimizes the coffee recipe and production process to meet the user's taste requirements for a long time.

Images