Coffee machine multi-language cloud formula interaction control method and system

Abstract

The invention relates to the technical field of coffee machines, in particular to a coffee machine multi-language cloud formula interaction control method and system, and the method comprises the steps: obtaining a target language text resource and target coffee formula data from a cloud server according to the voice of a user; after generating a target language user interface based on the target language text resource, displaying target coffee formula data through the target language user interface; when a coffee parameter adjustment operation of the target coffee formula data is received, generating new coffee formula data according to the coffee parameter adjustment operation; and after the new coffee formula data is uploaded to the cloud server for user behavior analysis, other coffee formula data on the cloud server are adjusted according to the user behavior analysis result, so that global optimization and dynamic adaptation of the formula are realized, the requirement of frequent manual adjustment of a user is reduced, and the user experience is improved. On the whole, through voice driving, cloud processing and intelligent optimization, the operation convenience and personalized experience are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of coffee machine technology, specifically to a multilingual cloud recipe interactive control method and system for coffee machines. Background Technology

[0002] Currently, as a common device in modern life, coffee machines have gradually expanded their function from basic beverage preparation to providing personalized and intelligent user experiences. Especially with the advancement of Internet of Things (IoT) technology, smart coffee machines can achieve more convenient operation and a wider range of recipes through semantic interaction and cloud support.

[0003] Existing coffee machine semantic adjustment and recipe output solutions typically rely on a locally stored fixed recipe library and a preset multilingual interface. After the user inputs commands via voice or touchscreen, the device calls up the recipe data in the local database and displays it on the interface. At the same time, the user can make limited adjustments to parameters such as concentration and temperature. The adjusted recipe can be saved locally.

[0004] However, as mentioned above, the language switching and recipe adjustment of existing coffee machines rely entirely on manual operation by the user, which results in insufficient ease of operation and adjustment. Summary of the Invention

[0005] To address the technical problem that existing coffee machines rely entirely on manual operation for language switching and recipe adjustment, resulting in insufficient ease of use, this application provides a multilingual cloud recipe interactive control method and system for coffee machines.

[0006] The technical solution adopted in this application for a multilingual cloud recipe interactive control method and system for a coffee machine is as follows: A multilingual cloud recipe interactive control method for a coffee machine includes: Retrieve target language text resources and target coffee recipe data from the cloud server based on the user's voice; After generating a target language user interface based on the target language text resources, the target coffee recipe data is displayed through the target language user interface; When the coffee parameters are adjusted upon receiving the target coffee recipe data, new coffee recipe data is generated based on the coffee parameter adjustment operation. After uploading new coffee recipe data to a cloud server for user behavior analysis, other coffee recipe data on the cloud server are adjusted based on the results of the user behavior analysis.

[0007] Furthermore, the steps of obtaining target language text resources and target coffee recipe data from the cloud server based on the user's voice include: After obtaining language identifiers from the collected user voice, the corresponding target language text resources are retrieved from the cloud server based on the language identifiers. The coffee recipe code is determined based on the target language text resources, and the target coffee recipe data corresponding to the coffee recipe code is extracted from the cloud server.

[0008] Furthermore, the steps for generating a target language user interface based on target language text resources include: The target language text resources are parsed and processed to extract the set of interface elements and the standard encoding mapping table; Semantic analysis is performed on the set of UI elements to generate UI element dependencies. Based on these dependencies, layout optimization is performed to generate the UI layout. Text matching is performed based on a standard encoding mapping table. After obtaining the current language text description set, font rendering is performed on the current language text description set to generate a glyph library and typesetting rules. The interface layout, font library, and typesetting rules are integrated to obtain the target language user interface.

[0009] Furthermore, the steps for displaying the target coffee recipe data through the target language user interface include: After extracting recipe parameters and display attributes from the target coffee recipe data, the recipe parameters are mapped to visual elements, and the display attributes are rendered to obtain the interface rendering scheme. The display layout is generated by compositing based on visual elements and interface rendering schemes. Then, the display layout is sent to the target language user interface for display operations.

[0010] Furthermore, when receiving coffee parameter adjustment operations based on target coffee recipe data, the steps for generating new coffee recipe data based on these adjustments include: Based on the coffee parameter adjustment operation, after obtaining the parameter modification instruction set, the parameter modification instruction set is parsed and processed to obtain the valid parameter modification value; Based on the effective parameter modification value, locate the corresponding formula parameter item and generate a parameter update instruction; Create new coffee recipe data based on the parameter update instructions.

[0011] Furthermore, the steps for uploading new coffee recipe data to a cloud server for user behavior analysis include: Parameters are extracted from the new coffee recipe data to obtain a user parameter preference dataset; By combining user parameter preference datasets with historical user behavior data and identifying user group preference features based on collaborative filtering, a group preference dataset is obtained. A user taste prediction model is obtained by training and learning based on a group preference dataset.

[0012] Furthermore, the steps for adjusting other coffee recipe data on the cloud server based on user behavior analysis results include: Formula adjustment parameters are generated based on a user taste prediction model, and the effect of the prediction adjustment is verified through simulation. After generating adjustment instructions based on the adjustment results, the parameters of other coffee recipe data on the cloud server are modified to form a new version of coffee recipe data.

[0013] This application also provides a multilingual cloud recipe interactive control system for coffee machines, including: The data acquisition module is used to acquire target language text resources and target coffee recipe data from the cloud server based on the user's voice. The data display module is used to generate a target language user interface based on the target language text resources, and then display the target coffee recipe data through the target language user interface. The data adjustment module is used to generate new coffee recipe data based on the coffee parameter adjustment operation when the target coffee recipe data is received. The data adjustment module is also used to upload new coffee recipe data to the cloud server for user behavior analysis, and then adjust other coffee recipe data on the cloud server based on the results of the user behavior analysis.

[0014] Beneficial effects achieved: This application provides a multilingual cloud recipe interactive control method for a coffee machine, characterized by comprising: acquiring target language text resources and target coffee recipe data from a cloud server based on user voice; generating a target language user interface based on the target language text resources and displaying the target coffee recipe data through the target language user interface; generating new coffee recipe data based on the coffee parameter adjustment operation received from the target coffee recipe data; uploading the new coffee recipe data to the cloud server for user behavior analysis, and adjusting other coffee recipe data on the cloud server based on the user behavior analysis results.

[0015] In this application, an automated and dynamic operation process is achieved through voice interaction, cloud collaboration, and intelligent learning mechanisms: First, target language text resources and coffee recipe data are directly obtained through user voice, avoiding the tedious steps of manually switching languages ​​and improving the convenience of language settings; second, the target language user interface is dynamically generated and recipe data is displayed based on the cloud server, ensuring the visibility of the interface and recipes; third, when the user adjusts parameters, the system automatically generates new coffee recipe data and uploads it to the cloud for user behavior analysis, enabling the system to continuously learn user preferences based on actual usage data; finally, based on the analysis results, other recipe data in the cloud is automatically adjusted, achieving global optimization and dynamic adaptation of recipes, thereby reducing the need for frequent manual adjustments by users. Overall, voice-driven, cloud-processed, and intelligent optimization significantly improve the convenience and personalized experience of operation. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the overall process of a multilingual cloud recipe interactive control method for a coffee machine according to this application; Figure 2 A schematic diagram of the settings display interface for a coffee machine; Figure 3 A schematic diagram of the interface for adjusting coffee parameters for a specific coffee recipe. Figure 4 This is a schematic diagram of a module of a multilingual cloud recipe interactive control system for a coffee machine according to this application.

[0017] Explanation of icon numbers: 10. Data acquisition module; 20. Data display module; 30. Data adjustment module. Detailed Implementation

[0018] The following is in conjunction with the appendix Figures 1-4 This application will be described in further detail.

[0019] In the description of this application, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0020] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances.

[0021] This application discloses a multilingual cloud recipe interactive control method and system for coffee machines.

[0022] Please refer to Figure 1 The coffee machine multilingual cloud recipe interactive control method proposed in this embodiment includes steps S10~S40: Step S10: Obtain target language text resources and target coffee recipe data from the cloud server based on the user's voice.

[0023] This step utilizes user voice to automatically identify language features and, based on the corresponding language and cultural preferences, provides accurate coffee recipe recommendations. Specifically, through the multilingual processing capabilities of the cloud server, it first analyzes the language information in the user's voice. Then, it automatically matches the target language text resources corresponding to the identified language with the coffee recipe features commonly preferred by the target audience of that language. For example, it identifies Italian speakers as needing espresso-based coffee recipes, while Japanese speakers would prefer milder flavors. This identifies popular coffee recipes that align with the cultural habits of that language as the target coffee recipe data. This breaks through the limitations of traditional manual selection, allowing the coffee machine to proactively provide language text and coffee recipe selections that match the user's cultural background without requiring manual settings. This significantly reduces operational complexity and enhances the user experience through a language-driven approach.

[0024] Step S20: After generating a target language user interface based on the target language text resources, display the target coffee recipe data through the target language user interface.

[0025] Based on the acquired target language text resources, a user interface conforming to the language's habits is automatically constructed. This avoids the burden of pre-installing multiple firmware sets for different language markets or manually switching languages. It achieves real-time binding and dynamic rendering of language resources and interface elements. By parsing the encoding mapping relationship in the target language text resources, the parameters in the target coffee recipe data are associated and integrated with the corresponding language text resources, namely the description text, unit format, and layout logic of the target language text resources. This generates a grammatically correct, visually standardized target language user interface that conforms to local usage habits, thereby improving the consistency and intuitiveness of the user experience. Users see not only translated text but also a complete interactive solution deeply adapted to the target language's cultural habits, including right-to-left text layout, support for Arabic and compound characters, simplified / traditional Chinese switching, and localized parameter expressions, such as automatic conversion between ounces and milliliters. At the same time, a standardized process ensures real-time synchronization between the target language user interface and the target coffee recipe data, ensuring that any adjustment to recipe parameters is immediately reflected in the current language environment.

[0026] Step S30: When receiving the coffee parameter adjustment operation of the target coffee recipe data, generate new coffee recipe data according to the coffee parameter adjustment operation.

[0027] Based on user adjustments to coffee parameters on the target language user interface, the system dynamically captures these adjustments and generates new coffee recipe data. This transforms user preferences into standardized, reusable digital recipes. It not only records parameter changes but also maintains the correlation between the new recipe and multilingual text resources through coded mapping, ensuring that the adjusted coffee recipe data remains adaptable to display and operation needs in different language environments. This creates an intelligent feedback loop between the user and the coffee machine, allowing users to customize recipes through an intuitive interface without needing to understand complex technical parameters. The system continuously accumulates this adjustment data to provide structured input for subsequent cloud-based behavioral analysis. Ultimately, this achieves real-time generation and saving of personalized recipes and provides a data foundation for optimizing other recipes in the cloud, significantly improving recipe applicability and user satisfaction.

[0028] Step S40: After uploading the new coffee recipe data to the cloud server for user behavior analysis, adjust other coffee recipe data on the cloud server based on the user behavior analysis results.

[0029] By uploading user-adjusted coffee recipe data to a cloud server for user behavior analysis, valuable preference patterns and usage trends are extracted from individual operations. The cloud server's computing power is then used to perform cluster analysis on the uploaded coffee recipe data, identifying common preferences or unusual adjustment behaviors regarding parameters such as concentration, sweetness, and temperature. Based on these analysis results, other coffee recipe data stored on the cloud server is intelligently adjusted—for example, by optimizing default parameter settings, recommending similar recipes, or correcting the applicability of existing recipes. This builds a self-learning and evolving recipe ecosystem, where each user's adjustment contributes to the improvement of the overall recipe library. This not only enhances the overall quality of recipes and user satisfaction but also reduces the need for subsequent manual adjustments through data-driven dynamic adjustments, enabling coffee machines to provide more precise and user-responsive intelligent services.

[0030] It should be noted that, referring to Figure 2 and Figure 3 As shown, Figure 2 and Figure 3 This is the display interface of the coffee machine proposed in this embodiment, wherein, Figure 2 This is the settings display interface for the coffee machine, which includes wireless connectivity (i.e.,...). Figure 2 Wifi), connectivity (i.e. Figure 2 Link in the middle), rinsing (i.e. Figure 2 Rinse in the middle), timed hibernation (i.e. Figure 2 Timer in the middle), support (i.e. Figure 2 Support in the middle), descaling (i.e. Figure 2 In Descale), timer (i.e. Figure 2 The Counter and volume switch (i.e.) Figure 2 On in the text), brightness (i.e. Figure 2 Display), download (i.e. Figure 2 Updates), language (i.e. Figure 2 Language), brewing unit (i.e. Figure 2 Brewing Unit and milk storage unit (i.e.) Figure 2 If the user does not support the language automatically switched by the coffee machine (e.g., Milk Tank), they can access the language switching interface through the settings display to switch the language. The main interface button (i.e., ...) is located on the main interface. Figure 2 The HOME option in the menu allows you to return to the main coffee menu.

[0031] Figure 3 This is an interface for adjusting coffee parameters for a specific coffee recipe. The interface displays a bar indicating the weight of the ground coffee beans (i.e.,...). Figure 3Grounds (in grams), coffee temperature adjustment bar (i.e.) Figure 3 Temperature (in °C), coffee concentration adjustment bar (i.e.) Figure 3 The coffee intensity (in ml) and the milk foam adjustment bar (i.e.) Figure 3 Foam (unit: s) and milk adjustment bar (i.e. Figure 3 Milk (in seconds), the save button on the interface (i.e. Figure 3 The "Save" button in the interface allows you to save the adjusted coffee parameters, while the "Delete" button on the screen (i.e., ...) allows you to save the settings. Figure 3 The "Cancel" option in the settings can be used to delete the adjusted coffee parameters.

[0032] In one feasible implementation, the specific steps for acquiring target language text resources and target coffee recipe data include S11~S12: Step S11: After obtaining the language identifier based on the collected user voice, retrieve the corresponding target language text resources from the cloud server based on the language identifier.

[0033] First, the user's voice is captured by the microphone array built into the coffee machine. After noise reduction and enhancement preprocessing, the language recognition algorithm in the speech recognition service of the cloud server is used. For example, a classifier based on Mel-frequency cepstral coefficient feature extraction combined with Gaussian mixture model or deep neural network is used to analyze the speech spectrum features of the user's voice, identify the language features contained in the user's voice, and generate corresponding language identifiers, such as zh-CN (Simplified Chinese) and en-US (American English). Then, the cloud server quickly retrieves the corresponding target language text resources (including interface text, prompts, parameter descriptions, etc., translated content) from the distributed resource database based on the language identifier, and securely sends the target language text resources to the coffee machine through dynamic compression and encrypted transmission technology.

[0034] In this step, users can trigger the coffee machine to automatically complete the entire process from language recognition to language text resource loading simply by using natural voice commands. There is no need to manually switch languages ​​or download update packages. This allows the coffee machine to immediately provide an interactive interface that matches the current user's language habits when it is first turned on or when a user changes. At the same time, the dynamic loading mechanism of the cloud server ensures that the text resources are always up-to-date. This eliminates the storage space waste caused by the need for pre-installed multi-language firmware in traditional devices and avoids the operational barriers caused by manually setting the language.

[0035] Step S12: Determine the coffee recipe code based on the target language text resources, and extract the target coffee recipe data corresponding to the coffee recipe code from the cloud server.

[0036] After obtaining the target language text resource package, the coffee machine parses the standard encoding index table contained therein. It should be noted that the standard encoding index table is stored in key-value pair format, where the key is the multilingual unified recipe element code and the value is the text description in the corresponding language. Next, based on the user-defined language identifier, the corresponding recipe code set is matched in the standard coding index table. For example, Americano corresponds to BEV_001, and concentration parameters correspond to PARAM_STRENGTH. These recipe codes adopt an internationally standardized format to ensure the uniqueness and traceability of cross-language recipes. At this time, the coffee machine sends these recipe codes to the recipe database on the cloud server through an encrypted API (Application Programming Interface). The recipe database uses a distributed architecture to store the preferred recipe data of different groups of people. For example, it stores a set of recipe codes with lower caffeine concentration for East Asian people and a set of recipe codes with higher concentration for European people. The recipe parameter set corresponding to the recipe code is quickly located through a hash index algorithm, such as numerical data such as water temperature, grind size, and extraction time. Finally, the cloud server integrates the matched recipe parameter set into the target coffee recipe data, compresses and encrypts it, and returns it to the coffee machine. The coffee machine decrypts and verifies the data before loading it into memory for the brewing system to use.

[0037] This step establishes an intelligent recipe recommendation system guided by ethnic preferences. By mapping language identifiers to dietary habits, the coffee machine automatically provides users with a baseline recipe that matches the general taste preferences of that group. This avoids the tedious manual adjustments required by users and significantly improves first-drink satisfaction through data-driven personalized initial settings. At the same time, the standardized coding mechanism ensures the version uniformity and maintainability of global recipe data, laying a precise data foundation for subsequent personalized adjustments.

[0038] In one feasible implementation, the specific steps for generating the target language user interface include S21~S23: Step S21: Parse the target language text resources and extract the set of interface elements and the standard encoding mapping table.

[0039] The parsing engine, such as an XML or JSON-based parser, deconstructs the structure of the target language text resource, identifies and extracts the set of interface elements, including the definitions and attributes of UI components such as buttons, labels, and input boxes, and a standard encoding mapping table, which is stored in key-value pairs.

[0040] During the parsing process, the parsing engine verifies the format integrity of the target language text resources and uses regular expressions or DOM parsing methods to match element tags and encoding entries to ensure accurate data extraction. This builds a dynamic and adaptable multilingual interface foundation. By extracting the set of interface elements, the coffee machine can quickly assemble UI components, while the standard encoding mapping table ensures the precise association between text descriptions and functional codes. This supports real-time rendering and consistent display of the coffee machine's interface in multilingual environments, eliminating the need for multiple pre-installed firmware sets and significantly improving development efficiency and user experience flexibility.

[0041] Step S22: Perform semantic analysis processing based on the set of interface elements to generate interface element dependencies, and then perform layout optimization processing based on the interface element dependencies to generate the interface layout; and perform text matching processing based on the standard encoding mapping table to obtain the current language text description set, and then perform font rendering processing on the current language text description set to generate a character library and typesetting rules.

[0042] Semantic analysis is performed on the set of interface elements. Natural language processing techniques, such as dependency parsing or graph neural networks, are used to parse the logical relationships between interface elements. For example, the functional dependencies or grouping relationships between buttons and input boxes are identified to generate a dependency graph of interface elements. Then, layout optimization is performed based on this dependency relationship. Rule-based layout algorithms, such as constraint solving or responsive design principles, are used to adjust the position, size and spacing of elements to ensure that the layout conforms to visual logic and generate the interface layout.

[0043] Simultaneously, text matching is performed based on a standard encoding mapping table. Hash lookup or index retrieval is used to quickly match the current language text description set corresponding to the encoding. Then, font rendering is performed on the current language text description set. Font engines, such as FreeType or HarfBuzz, are used to parse character shapes, ligatures, and typographic characteristics to generate a glyph library adapted to the current language, including character bitmaps and measurement information, and typographic rules such as line spacing, alignment, and text direction. This enables the construction of a highly adaptive and cross-language consistent user interface, ensuring that text display meets language-specific rendering requirements. This improves the smoothness of the user experience and the professionalism of the interface, reduces the need for manual adjustments, and supports rapid multilingual deployment.

[0044] Step S23: The interface layout, font library and typesetting rules are integrated to obtain the target language user interface.

[0045] First, the interface layout generated by the layout engine, including control coordinates, hierarchical relationships, and dynamic constraints, the glyph library generated by the font rendering engine, including character vector data, anti-aliasing information, and cached bitmaps, and the typography rules, including line spacing, alignment, text flow, and line wrapping strategies, are loaded into the shared memory space. Then, based on the visual tree synthesis algorithm, such as using depth-first traversal and Z-order (Z-axis) sorting, the abstract layout description is converted into specific drawing instructions. The glyph library is precisely matched with the text area in the layout through texture mapping technology. At the same time, the typography rules are dynamically adjusted to adjust the text rendering position through real-time calculation, such as handling special needs such as Arabic text layout from right to left or Chinese vertical text layout.

[0046] The compositing process uses a GPU (Graphics Processing Unit) to accelerate the rendering pipeline, handles geometric transformations through vertex shaders and texture sampling through fragment shaders, and finally generates a target language user interface with multilingual visual features.

[0047] The goal is to build a truly dynamic multilingual interface generation system. By integrating layouts, fonts, and rules in real time at runtime, coffee machines can generate corresponding display effects according to any language requirements without pre-compiling multiple sets of interface resources. At the same time, it ensures a high degree of consistency between the interface's functional logic and visual presentation. This significantly reduces the storage overhead and maintenance costs of multilingual products and ensures that interactive experiences that conform to local cultural habits can be provided in different language environments.

[0048] In one feasible implementation, the specific steps for displaying the target coffee recipe data include S24-S25: Step S24: After extracting the recipe parameters and display attributes from the target coffee recipe data, the recipe parameters are mapped to visual elements, and the display attributes are rendered to obtain the interface rendering scheme.

[0049] Extract recipe parameters, such as concentration, temperature, and water volume, and display attributes, such as color coding, icon identification, and font style, from the target coffee recipe data. The extraction process is based on a structured parsing engine, such as a JSON or XML parser, to identify data fields and separate functional parameters from visual attributes.

[0050] By using preset mapping rules—for example, mapping temperature values ​​to the scale position of a dynamic thermometer graphic, concentration parameters to the intensity indicator of a color gradient bar, and water volume parameters to the fill ratio of a progress bar—recipe parameters are mapped to visual elements, ensuring that each parameter has a corresponding graphical representation. Simultaneously, element hues are adjusted according to the extracted color scheme, corresponding image resources are loaded based on icon identifiers, and text rendering attributes are set according to font styles. This configures the rendering of display attributes, generating a complete interface rendering scheme, including element position, size, color, and animation effects. This enables the construction of a highly dynamic and personalized user interface, transforming abstract recipe data into intuitive visual elements. A unified rendering configuration ensures consistency across different languages ​​and devices, allowing users to quickly understand recipe content through a graphical interface without interpreting complex parameters, significantly improving operational convenience and the intuitiveness of the interactive experience.

[0051] Step S25: Based on the visual elements and interface rendering scheme, a composite processing is performed to generate a display layout. After that, the display layout is sent to the target language user interface for display operation.

[0052] The interface compositing engine integrates visual elements and interface rendering schemes, employing constraint-based layout algorithms, such as the Cassowary constraint solver, to calculate the optimal position and size of visual elements. This ensures the layout conforms to the reading habits and visual flow logic of the target language. After generating the display layout, OpenGL (Open Graphics Library) converts the display layout into drawing instructions, which are then sent to the rendering module of the target language user interface via message queues or network protocols. Finally, the display operation is executed on the interface, achieving a highly adaptive and cross-language consistent interactive interface. This allows the coffee machine to convert recipe parameters and display attributes into intuitive visual representations in real time, ensuring that the interface layout perfectly matches the language characteristics.

[0053] In one feasible implementation, the specific steps for generating new coffee recipe data include S31~S33: Step S31: Based on the coffee parameter adjustment operation, after obtaining the parameter modification instruction set, the parameter modification instruction set is parsed and processed to obtain the valid parameter modification value.

[0054] Based on coffee parameter adjustment operations, such as users modifying the concentration value via an interface slider or adjusting the temperature via a button, the system captures the original operation data. An event listening module collects operation signals and packages them into a parameter modification instruction set. This instruction set is then parsed using a rule-based parsing algorithm, such as the Drools rule engine or a custom syntax parser, to perform lexical analysis, syntax verification, and semantic checks on each instruction in the instruction set. This filters out out-of-bounds values, conflicting operations, or incorrectly formatted instructions. Simultaneously, strings or analog signals are converted into standardized numerical formats. Finally, valid parameter modification values ​​that conform to the coffee machine's constraints and safety ranges are extracted. For example, a high concentration input by the user is mapped to a specific concentration value of 85%, and this value is verified to be within the valid range of 60% to 90%.

[0055] In this step, the automated parsing and verification mechanism eliminates ambiguity and errors in user operations, ensuring that only compliant and safe parameter modification values ​​are processed in subsequent processes. This prevents system anomalies or coffee making failures caused by invalid input, and ensures the consistency of recipe parameters across different languages ​​and equipment environments through standardized data conversion. Ultimately, this significantly improves the accuracy of parameter adjustments and the stability of coffee machine operation, providing users with a smooth and reliable interactive experience.

[0056] Step S32: Locate the corresponding formula parameter item based on the effective parameter modification value and generate a parameter update instruction.

[0057] Based on the valid parameter modification values, a standard coding mapping table is used for rapid lookup and matching. The corresponding recipe parameter item is located through a hash index algorithm. For example, the concentration parameter item may be related to the calculation rules of coffee powder amount and water amount, ensuring that each valid parameter modification value can be accurately mapped to the corresponding recipe parameter item. Then, a parameter update instruction is generated based on the location result. The parameter update instruction adopts the JSON or XML protocol and includes parameter identifier, new value, timestamp and version information, realizing the construction of a high-precision parameter synchronization system. User input is converted into standardized instructions that can be executed by the machine in real time, avoiding parameter mismatch or update conflict, and ensuring the accuracy and consistency of recipe adjustment.

[0058] Step S33: Create new coffee recipe data according to the parameter update instruction.

[0059] The recipe copy is created based on the parameter update instruction to ensure the security of the original data. Then, the parameter items that need to be modified are located (e.g., the storage path of the concentration parameter in the recipe data structure). The new value in the parameter update instruction is replaced in the corresponding position of the copy. At the same time, the rationality and security of the recipe copy are verified by the constraint verification module (e.g., checking the parameter range, logical relationship and type consistency based on predefined rules). Finally, serialization technology, such as Protocol Buffers or Message Packets, is used to encapsulate the modified recipe copy into new coffee recipe data.

[0060] The goal is to build a precise and reliable personalized recipe system that can quickly respond to user adjustment needs. While ensuring the integrity of the recipe structure and the correctness of the parameter logic, it can dynamically generate new coffee recipe data that is fully adapted to the user's taste preferences. This not only meets the user's real-time personalized customization needs for coffee flavor, but also provides a data foundation for subsequent recipe optimization, forming an interactive cycle between user needs and recipe evolution.

[0061] In one feasible implementation, the specific steps for performing user behavior analysis on new coffee recipe data and adjusting other coffee recipe data include S41~S45: Step S41: Extract parameters from the new coffee recipe data to obtain a user parameter preference dataset.

[0062] Based on regular expressions or XML / JSON parsers, new coffee recipe data is identified and its parameters are extracted, including numerical data such as concentration, temperature, sweetness, and water volume. Data cleaning removes outliers and invalid inputs to ensure accuracy and consistency. These parameters are then organized by user identifier and timestamp to generate a user parameter preference dataset. This dataset is stored in tabular format, containing parameter type, value, adjustment frequency, and related contextual information, providing standardized input for subsequent analysis. This enables the construction of a high-precision user preference database, automatically capturing and quantifying user taste preferences from each recipe adjustment. This forms a traceable and analyzable data foundation, supporting personalized recommendations, group trend analysis, and recipe optimization decisions, ultimately improving the adaptability of coffee recipes and user satisfaction.

[0063] Step S42: Combine the user parameter preference dataset with historical user behavior data, and identify user group preference features based on collaborative filtering to obtain a group preference dataset.

[0064] The user parameter preference dataset is integrated with historical user behavior data, such as past recipe selection, adjustment frequency, and drinking habits. Then, a user-based collaborative filtering method is used to calculate the preference similarity between the various user parameter preference datasets stored on the cloud server through cosine similarity or Pearson correlation coefficient. Similar user parameter preference datasets are clustered into groups, and common preference features, such as average concentration values ​​and common parameter combinations, are extracted from these groups to obtain the group preference dataset.

[0065] In the specific implementation of the algorithm, a user-parameter matrix is ​​first constructed, then K-means clustering or hierarchical clustering is used to group users, and finally the parameter values ​​within the group are aggregated to obtain the group preference dataset, thereby realizing the construction of a high-precision group taste profile. It can automatically discover potential preference patterns from massive user behavior, providing a data-driven decision-making basis for recipe optimization and personalized recommendations, thus significantly improving the adaptability of coffee recipes and user satisfaction.

[0066] Step S43: Train the model based on the group preference dataset to obtain the user taste prediction model.

[0067] First, the group preference dataset is preprocessed, including data cleaning, feature selection, and standardization. Then, the model is trained using neural networks, random forests, or gradient boosting trees. During training, the model learns relevant features from the group preference dataset, such as the preference patterns of different user groups for parameters like coffee concentration, sweetness, and temperature. Finally, the model parameters are iteratively optimized to generate a predictive model that can accurately predict user tastes.

[0068] Step S44: Generate recipe adjustment parameters based on the user taste prediction model, and verify the predicted adjustment effect through simulation.

[0069] The user taste prediction model is deployed to the parameter generation engine. This model receives historical user preference data and current environmental context, such as time and season, as input. Through forward propagation of a neural network, it calculates and outputs suggested adjustment values ​​for core parameters such as concentration, sweetness, and temperature, forming formula adjustment parameters. These parameters are then fed into a simulation verification module. This module constructs a virtual coffee-making environment based on historical data, simulates the coffee extraction process using digital twin technology, and calculates the theoretical taste, aroma, and balance indices of the adjusted formula using heat conduction equations or fluid dynamics models, as well as sensory quality predictors based on support vector machines (SVM) or random forests. Simultaneously, it compares the results with historical successful case data to verify the effect, generating an adjustment effect that includes expected taste scores and adjustment confidence levels.

[0070] Step S45: After generating adjustment instructions based on the adjustment effect, modify the parameters of other coffee recipe data on the cloud server to form a new version of coffee recipe data.

[0071] After generating adjustment instructions based on relevant metrics such as concentration, sweetness, and temperature, these instructions are sent to the cloud server via a secure API interface. The cloud server then modifies parameters in other coffee recipe data based on these instructions. Specifically, it locates and modifies matching recipe parameters using database query languages ​​or NoSQL document update operations. For example, new concentration values ​​derived from group preference analysis are applied to all similar recipes. A transaction processing mechanism ensures the atomicity and consistency of data operations. After modification, a new version identifier (e.g., an incrementing version number or timestamp) is generated for the updated recipe data and stored in the cloud database, forming traceable new version coffee recipe data. This enables the construction of efficient and reliable global recipe optimization capabilities, automatically promoting improved solutions to the entire recipe library based on adjustment effects. This ensures all recipes maintain up-to-date and consistent high-quality standards, while version control supports flexible rollback and auditing, significantly improving the adaptability of the recipe library, user satisfaction, and system maintenance efficiency.

[0072] This application also provides a multilingual cloud recipe interactive control system for a coffee machine, see reference. Figure 4 As shown, it includes: Data acquisition module 10 is used to acquire target language text resources and target coffee recipe data from the cloud server based on the user's voice. The data display module 20 is used to generate a target language user interface based on the target language text resources, and then display the target coffee recipe data through the target language user interface. The data adjustment module 30 is used to generate new coffee recipe data based on the coffee parameter adjustment operation when the target coffee recipe data is received. The data adjustment module 30 is also used to upload new coffee recipe data to the cloud server for user behavior analysis, and then adjust other coffee recipe data on the cloud server based on the results of the user behavior analysis.

[0073] Optionally, the data acquisition module 10 is also used for: After obtaining language identifiers from the collected user voice, the corresponding target language text resources are retrieved from the cloud server based on the language identifiers. The coffee recipe code is determined based on the target language text resources, and the target coffee recipe data corresponding to the coffee recipe code is extracted from the cloud server.

[0074] Optionally, the data display module 20 is also used for: The target language text resources are parsed and processed to extract the set of interface elements and the standard encoding mapping table; Semantic analysis is performed on the set of UI elements to generate UI element dependencies. Based on these dependencies, layout optimization is performed to generate the UI layout. Text matching is performed based on a standard encoding mapping table. After obtaining the current language text description set, font rendering is performed on the current language text description set to generate a glyph library and typesetting rules. The interface layout, font library, and typesetting rules are integrated to obtain the target language user interface.

[0075] Optionally, the data display module 20 is also used for: After extracting recipe parameters and display attributes from the target coffee recipe data, the recipe parameters are mapped to visual elements, and the display attributes are rendered to obtain the interface rendering scheme. The display layout is generated by compositing based on visual elements and interface rendering schemes. Then, the display layout is sent to the target language user interface for display operations.

[0076] Optionally, the data adjustment module 30 is also used for: Based on the coffee parameter adjustment operation, after obtaining the parameter modification instruction set, the parameter modification instruction set is parsed and processed to obtain the valid parameter modification value; Based on the effective parameter modification value, locate the corresponding formula parameter item and generate a parameter update instruction; Create new coffee recipe data based on the parameter update instructions.

[0077] Optionally, the data adjustment module 30 is also used for: Parameters are extracted from the new coffee recipe data to obtain a user parameter preference dataset; By combining user parameter preference datasets with historical user behavior data and identifying user group preference features based on collaborative filtering, a group preference dataset is obtained. A user taste prediction model is obtained by training and learning based on a group preference dataset.

[0078] Optionally, the data adjustment module 30 is also used for: Formula adjustment parameters are generated based on a user taste prediction model, and the effect of the prediction adjustment is verified through simulation. After generating adjustment instructions based on the adjustment results, the parameters of other coffee recipe data on the cloud server are modified to form a new version of coffee recipe data.

[0079] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A multilingual cloud recipe interactive control method for a coffee machine, characterized in that, include: Retrieve target language text resources and target coffee recipe data from the cloud server based on the user's voice; After generating a target language user interface based on the target language text resources, the target coffee recipe data is displayed through the target language user interface; When a coffee parameter adjustment operation is received from the target coffee recipe data, new coffee recipe data is generated based on the coffee parameter adjustment operation. After the new coffee recipe data is uploaded to the cloud server for user behavior analysis, other coffee recipe data on the cloud server are adjusted based on the user behavior analysis results.

2. The coffee machine multilingual cloud recipe interactive control method according to claim 1, characterized in that, The steps of obtaining target language text resources and target coffee recipe data from the cloud server based on user voice include: After obtaining the language identifier based on the collected user voice, the corresponding target language text resources are obtained from the cloud server based on the language identifier. The coffee recipe code is determined based on the target language text resource, and the target coffee recipe data corresponding to the coffee recipe code is extracted from the cloud server.

3. The coffee machine multilingual cloud recipe interactive control method according to claim 1, characterized in that, The step of generating a target language user interface based on the target language text resources includes: The target language text resources are parsed to extract the set of interface elements and the standard encoding mapping table; Based on the set of interface elements, semantic analysis is performed to generate interface element dependencies. Then, layout optimization is performed based on these dependencies to generate the interface layout. Based on the standard encoding mapping table, text matching processing is performed to obtain the current language text description set. Then, font rendering processing is performed on the current language text description set to generate a character library and typesetting rules. The interface layout, the font library, and the typesetting rules are integrated to obtain the target language user interface.

4. The coffee machine multilingual cloud recipe interactive control method according to claim 1, characterized in that, The step of displaying the target coffee recipe data through the target language user interface includes: After extracting recipe parameters and display attributes from the target coffee recipe data, the recipe parameters are mapped to visual elements, and the display attributes are rendered to obtain an interface rendering scheme. Based on the visualization elements and the interface rendering scheme, a composite processing is performed to generate a display layout. The display layout is then sent to the target language user interface for display operations.

5. The coffee machine multilingual cloud recipe interactive control method according to claim 1, characterized in that, The step of generating new coffee recipe data based on the coffee parameter adjustment operation when the target coffee recipe data is received includes: Based on the coffee parameter adjustment operation, after obtaining the parameter modification instruction set, the parameter modification instruction set is parsed and processed to obtain the effective parameter modification value; Based on the effective parameter modification value, locate the corresponding formula parameter item and generate a parameter update instruction; Based on the parameter update instructions, the new coffee recipe data is created.

6. The coffee machine multilingual cloud recipe interactive control method according to claim 1, characterized in that, The step of uploading the new coffee recipe data to the cloud server for user behavior analysis includes: Parameters are extracted from the new coffee recipe data to obtain a user parameter preference dataset; By combining the user parameter preference dataset with historical user behavior data and identifying user group preference features based on collaborative filtering, a group preference dataset is obtained. The user taste prediction model is obtained by training and learning based on the aforementioned group preference dataset.

7. The coffee machine multilingual cloud recipe interactive control method according to claim 6, characterized in that, The user taste prediction model is the result of the user behavior analysis, and the step of adjusting other coffee recipe data on the cloud server based on the user behavior analysis result includes: Based on the user taste prediction model, formula adjustment parameters are generated, and the predicted adjustment effect is verified through simulation. After generating adjustment instructions based on the adjustment effect, the parameters of other coffee recipe data on the cloud server are modified to form a new version of coffee recipe data.

8. A multilingual cloud-based interactive control system for coffee machines, characterized in that, include: The data acquisition module is used to acquire target language text resources and target coffee recipe data from the cloud server based on the user's voice. The data display module is used to generate a target language user interface based on the target language text resources, and then display the target coffee recipe data through the target language user interface. The data adjustment module is used to generate new coffee recipe data based on the coffee parameter adjustment operation when the target coffee recipe data is received. The data adjustment module is also used to upload the new coffee recipe data to the cloud server for user behavior analysis, and then adjust other coffee recipe data on the cloud server based on the user behavior analysis results.

Images