Fault information processing method and system of intelligent capsule fresh extraction beverage machine

Abstract

The invention discloses a fault information processing method and system for an intelligent capsule fresh extraction beverage machine, and the method comprises the steps: collecting real-time data through a plurality of sensors disposed at all key parts of the intelligent capsule fresh extraction beverage machine, and carrying out the preprocessing of original sensor data; a polynomial time approximation algorithm of complete interval times is applied to carry out multi-dimensional fault feature analysis and matching, classification is carried out according to fault severity and user processability according to a fault diagnosis result, structured fault information is generated, and the fault information is output through a local display interface of equipment and a mobile terminal. And a top-down hierarchical differential private counting query mechanism is applied in the cloud server to process a fault diagnosis result, and a fault knowledge base is updated. According to the invention, accurate diagnosis, grading processing and multi-channel output of the fault of the intelligent capsule fresh extraction beverage machine are realized, the fault processing efficiency is improved, and the user experience is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent home appliance control and data processing, and in particular to a fault information processing method and system for an intelligent capsule fresh-brew beverage machine. Background Art

[0002] Smart capsule fresh-brew beverage machines are a product of the integration of modern home appliance technology with artificial intelligence and the Internet of Things, belonging to the field of smart home appliance control and data processing technology. These devices use specialized capsules to package ingredients, combined with precisely controlled water temperature, pressure, and extraction time, to provide users with a convenient, high-quality beverage-making experience.

[0003] Currently, common smart beverage dispensers on the market primarily utilize simple single-chip microcontroller control systems, coupled with basic sensors (such as temperature and water level) to implement core functions. For example, a certain brand of coffee capsule dispenser uses a thermistor to detect water temperature and a fixed program to control the heating element and water pump. Failures are indicated only by a flashing LED light or a simple error code.

[0004] While more advanced beverage dispensers incorporate a variety of sensors and microprocessors, enabling them to monitor a wider range of operating parameters, their fault handling mechanisms remain limited. These devices typically rely on a preset, fixed fault code mapping table for fault diagnosis, lacking the ability to comprehensively analyze data from multiple sensors, resulting in inaccurate fault location. Furthermore, the presentation of fault information is often limited to simple code displays or limited text descriptions, failing to fully utilize data processing technology to provide more intelligent fault analysis and resolution recommendations.

[0005] This traditional fault handling mechanism has obvious shortcomings: first, the fault information indication is not intuitive and clear enough, making it difficult for ordinary users to understand the specific cause of the fault; second, there is a lack of targeted fault-solving guidance, which makes it impossible for users to eliminate simple faults on their own; third, fault data is not effectively collected and analyzed, and after-sales maintenance efficiency is low; fourth, remote diagnosis and preventive maintenance cannot be achieved, which increases equipment maintenance costs. Summary of the Invention

[0006] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a fault information processing method and system for an intelligent capsule fresh-brew beverage machine, so as to realize accurate diagnosis, hierarchical processing and multi-channel output of faults, improve fault handling efficiency and improve user experience.

[0007] To achieve the above objectives, the present invention provides a method for processing fault information of an intelligent capsule fresh beverage machine, comprising: By deploying multiple sensors on key components of the smart capsule fresh beverage machine, real-time data of temperature, pressure, flow, current, voltage and vibration frequency are collected to obtain raw sensor data; Performing filtering and normalization preprocessing on the raw sensor data to obtain preprocessed sensor data; Based on the preprocessed sensor data, a polynomial time approximation algorithm of full interval degree is applied to perform multi-dimensional fault feature analysis and matching to obtain a fault diagnosis result; Based on the fault diagnosis results, the faults are graded according to their severity and user manageability, and structured fault information including fault description, cause analysis and solution is generated; Output the structured fault information through the local display interface of the device and the mobile terminal, and upload the fault diagnosis results to the cloud server; A top-down hierarchical differential private counting query mechanism is applied in the cloud server to process the fault diagnosis result and update the fault knowledge base.

[0008] Preferably, the raw sensor data is obtained by collecting real-time data of temperature, pressure, flow, current, voltage and vibration frequency through multiple sensors deployed in key components of the smart capsule fresh beverage machine, including: Based on the preset sampling time interval and sampling trigger conditions, the analog signal of each sensor is sampled regularly to obtain time series sampling data; Performing analog-to-digital conversion on the time series sampling data to obtain digital sensor data; Transmitting the digitized sensor data to a main control unit via an internal bus, and adding a timestamp to the received sensor data in the main control unit to obtain timestamp-marked sensor data; A data cache is established in the main control unit, and the sensor data marked with the timestamp is indexed according to the sensor type and the acquisition time to obtain a structured raw sensor data group.

[0009] Preferably, filtering and normalizing the raw sensor data to obtain preprocessed sensor data includes: Applying median filtering and Kalman filtering algorithms to the structured raw sensor data group to eliminate noise interference and obtain filtered data; Normalizing the filtered data to map different types of data to a unified interval to obtain standardized data; Based on the statistical analysis of historical operating data, the normal value range and fluctuation threshold of each sensor data are established to obtain the parameter benchmark data set; The standardized data is compared with the parameter reference data set, and abnormal data points are marked according to a preset deviation threshold to obtain pre-processed sensor data with abnormal marks.

[0010] Preferably, based on the preprocessed sensor data, a polynomial time approximation algorithm of full interval degree is applied to perform multi-dimensional fault feature analysis and matching to obtain a fault diagnosis result, including: Collect and organize historical fault cases, extract fault characteristic indicators and corresponding sensor data features, and obtain a fault characteristic mapping table; Based on the fault feature mapping table, a fault feature library including fault type, sensor data features and occurrence scenario is established to obtain fault feature reference data; Dividing the pre-processed sensor data with abnormality marks into intervals, calculating the data distribution density of each interval, and obtaining an interval frequency vector; Calculate similarity between the interval frequency vector and the fault feature reference data to obtain a fault type candidate set; Perform component association analysis on the fault type candidate set to determine the fault location and impact range, and obtain a fault diagnosis result.

[0011] Preferably, the pre-processed sensor data with abnormal markers is divided into intervals, and the data distribution density of each interval is calculated to obtain the interval frequency vector, including: Divide the value range of each sensor data into equal intervals, establish a numerical interval mapping table, and obtain an interval division scheme; Based on the interval division scheme, counting the data distribution frequency of each interval to generate the interval frequency vector; Calculate the similarity between the interval frequency vector and the fault feature reference data to obtain a fault type candidate set, including: Constructing a multi-layer neural network model, performing feature extraction on the interval frequency vector, and obtaining a fault feature representation; Calculating cosine similarity between the fault feature representation and a preset pattern in the fault feature reference data to obtain a similarity matrix; Based on the similarity matrix, screening fault types whose similarity exceeds a preset threshold to obtain preliminary fault types; Combining the initial fault judgment results of multiple sensors, a decision tree is constructed to determine the fault type and obtain a candidate set of fault types.

[0012] Preferably, based on the fault diagnosis results, faults are graded according to their severity and user manageability, and structured fault information including fault description, cause analysis, and solution is generated, including: Establish a fault assessment index system based on the degree of impact on equipment functions, safety risk level, and maintenance difficulty to obtain an assessment benchmark; Quantitatively scoring the fault diagnosis results based on the evaluation benchmark, classifying the fault levels, and obtaining a fault classification result; Extracting a description template corresponding to the fault classification result from a preset fault description template library, filling in fault parameters and impact range, and obtaining fault description content; Based on the statistical analysis of historical fault data, the probability distribution of different fault causes is calculated and the cause analysis content is generated; Select the corresponding treatment plan based on the fault classification results, and generate inspection, operation, and verification steps based on the equipment status to obtain the solution content; The fault description content, cause analysis content and solution content are integrated into a unified format to obtain structured fault information.

[0013] Preferably, outputting the structured fault information through the local display interface of the device and the mobile terminal, and uploading the fault diagnosis result to the cloud server, includes: Classifying the structured fault information into emergency warning information, fault prompt information, and maintenance suggestion information according to the fault level to obtain a hierarchical information set; Based on the hierarchical information set, configuring the basic information layout of the local display interface and the detailed information layout of the mobile terminal to obtain a display configuration solution; According to the display configuration scheme, the fault name, alarm level and basic processing prompts are output on the local display interface of the device, and the alarm level is output through the different colors and flashing frequencies of the LED indicator; The structured fault information is transmitted to the user's mobile terminal via the MQTT protocol, and the fault diagnosis process, cause analysis, and treatment plan are displayed in layers according to the importance of the information to obtain mobile terminal output information; The fault diagnosis results are encapsulated in JSON format and encrypted with AES, and uploaded to the cloud server via WiFi or Bluetooth communication.

[0014] Preferably, a top-down hierarchical differential private counting query mechanism is applied in the cloud server to process the fault diagnosis result and update the fault knowledge base, including: The cloud server receives and decrypts the fault diagnosis results uploaded by multiple devices, establishes a structured fault data table, and obtains original fault statistics; Performing hierarchical differential processing on the original fault statistical data, calculating the fault occurrence frequency while protecting user privacy, and obtaining fault type distribution statistics; Based on the distribution statistics of the fault types, combined with the equipment operation time and the operating environment parameters, the fault timing characteristics and environmental correlation are analyzed to obtain a fault mode analysis report; According to the fault mode analysis report, the feature weights and threshold parameters of the fault feature library are updated, the fault diagnosis rules are optimized, and an improved diagnosis model is obtained; Integrate user feedback and maintenance records, extract new fault features and solutions, update the fault knowledge base content, and obtain an iteratively optimized fault knowledge base.

[0015] Preferably, the original fault statistical data is subjected to hierarchical differential processing, and the fault frequency is calculated under the premise of protecting user privacy to obtain fault type distribution statistics, including: Establishing a multi-layer index for the raw fault statistics according to device model, usage time, geographical region, and ambient temperature to obtain a hierarchical data structure; In each layer of data index, fault records are grouped and counted, and Laplace noise is added according to the differential privacy budget to obtain the privatized counting results; Based on the privatized counting results, a sliding time window is used to calculate the time distribution characteristics of the fault occurrence frequency to obtain fault trend data; Performing hierarchical cluster analysis on the fault trend data to generate a fault frequency heat map and a time series trend map to obtain a visual statistical chart; Combining equipment operating parameters and environmental monitoring data, the causes of faults are identified through correlation analysis, and a statistical report on the distribution of fault types is obtained.

[0016] The present invention also provides a fault information processing device for an intelligent capsule fresh beverage machine, comprising: A data acquisition module is used to collect real-time data of temperature, pressure, flow, current, voltage and vibration frequency through multiple sensors deployed on key components of the smart capsule fresh beverage machine to obtain raw sensor data; A data preprocessing module, configured to perform filtering and normalization preprocessing on the raw sensor data to obtain preprocessed sensor data; A fault diagnosis module is used to perform multi-dimensional fault feature analysis and matching based on the pre-processed sensor data using a complete interval polynomial time approximation algorithm to obtain a fault diagnosis result; An information generation module is used to generate structured fault information including fault description, cause analysis and solution based on the fault diagnosis results, grading the fault according to its severity and user handleability; An information output module, configured to output the structured fault information via the device's local display interface and a mobile terminal, and upload the fault diagnosis results to a cloud server; The data processing module is used to apply a top-down hierarchical differential private counting query mechanism in the cloud server to process the fault diagnosis result and update the fault knowledge base.

[0017] The beneficial effects of the present invention are: The application of the full interval polynomial time approximation algorithm for multi-dimensional fault feature analysis enables rapid and accurate identification of complex fault modes, significantly improving the accuracy and efficiency of fault diagnosis. A top-down hierarchical differential private counting query mechanism is introduced for fault data processing. This ensures user data privacy while enabling efficient fault data statistical analysis and providing data support for continuous optimization of fault handling. A fault diagnosis system based on multi-sensor data fusion was constructed, which achieved accurate fault location and classification through comprehensive analysis of multi-dimensional parameters; A fault classification mechanism has been established to generate differentiated fault information and solutions based on fault severity and user manageability, improving the pertinence and efficiency of fault handling. A multi-channel fault information output method is designed to meet the needs of users for obtaining fault information in different scenarios, improving the user experience; A self-learning fault knowledge base update mechanism was created, and through analysis of user feedback and maintenance records, continuous optimization and iterative upgrades of fault handling were achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings required for use in the embodiments. The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without inventive effort.

[0019] Figure 1 A flow chart of a fault information processing method for an intelligent capsule fresh beverage machine provided by an embodiment of the present invention; Figure 2 A flowchart of multi-sensor real-time data acquisition provided by an embodiment of the present invention; Figure 3 A flowchart of data preprocessing and anomaly detection provided by an embodiment of the present invention; Figure 4 A flowchart of multi-dimensional fault diagnosis and location provided by an embodiment of the present invention; Figure 5 A flowchart of generating hierarchical fault information provided by an embodiment of the present invention; Figure 6 This is a structural diagram of a fault information processing system for an intelligent capsule fresh beverage machine provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the disclosure for which protection is sought, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0021] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0022] The term "and / or" herein simply describes an association relationship, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, and the existence of B alone. In addition, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0024] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0025] like Figure 1 As shown, the present invention provides a fault information processing method for an intelligent capsule fresh beverage machine, comprising the following steps: Step S1: By deploying multiple sensors on key components of the smart capsule fresh beverage machine, real-time data of temperature, pressure, flow, current, voltage and vibration frequency are collected to obtain raw sensor data.

[0026] In this embodiment, if Figure 2 As shown, step S1 specifically includes: Step S1.1: Based on the preset sampling time interval and sampling trigger condition, the analog signal of each sensor is sampled at regular intervals to obtain time series sampling data.

[0027] Different types of sensors are installed in key components of the smart capsule fresh beverage dispenser, including temperature, pressure, flow, current, voltage, and vibration sensors. Different sampling intervals are set for each sensor type, such as every 5 seconds for the temperature sensor, every 2 seconds for the pressure sensor, and every 1 second for the flow sensor. Sampling triggers are also set, such as when the device starts up, when its operating status changes, or when a user operates it. This allows for the acquisition of time-series sampling data from each sensor.

[0028] Step S1.2: performing analog-to-digital conversion on the time series sampling data to obtain digital sensor data.

[0029] The collected analog signal is converted into a digital signal using an ADC (analog-to-digital converter). For example, for a temperature sensor, a 0-5V analog voltage signal is converted into a digital value from 0-1023; for a pressure sensor, a 4-20mA current signal is converted into the corresponding digital value. This method achieves digital processing of sensor data.

[0030] Step S1.3: Transmitting the digitized sensor data to the main control unit via the internal bus, and adding a timestamp to the received sensor data in the main control unit to obtain timestamp-marked sensor data.

[0031] Digital sensor data is transmitted to the main control unit via internal bus protocols such as I²C and SPI. In the main control unit, a timestamp is added to each set of sensor data to record the precise time of data acquisition, facilitating subsequent timing analysis and data correlation.

[0032] Step S1.4: establishing a data cache in the main control unit, indexing the timestamp-marked sensor data according to sensor type and acquisition time, and obtaining a structured raw sensor data group.

[0033] A data cache area is established in the main control unit's memory to organize and manage received sensor data. An index structure is created based on sensor type (such as temperature, pressure, flow) and acquisition time, forming a structured raw sensor data set to facilitate subsequent data processing and analysis.

[0034] Step S2: performing filtering and normalization preprocessing on the raw sensor data to obtain preprocessed sensor data.

[0035] In this embodiment, if Figure 3 As shown, step S2 specifically includes: Step S2.1: applying median filtering and Kalman filtering algorithms to the structured raw sensor data set to eliminate noise interference and obtain filtered data.

[0036] A median filter algorithm is applied to raw sensor data to remove sudden noise and outliers. For example, for temperature sensor data, the median of five consecutive sampling points is used as the filtering result. For data that requires smoothing, such as pressure and flow data, a Kalman filter algorithm is applied. Based on historical data and the uncertainty of the current measurement, the filter parameters are dynamically adjusted to produce a smoother data curve.

[0037] Step S2.2: normalize the filtered data to map different types of data to a unified interval to obtain standardized data.

[0038] Normalize different types of sensor data and map them to the [0, 1] range. For example, for temperature data, you can use the formula (T - Tmin) / (Tmax - Tmin), where T is the current temperature, and Tmin and Tmax are the preset minimum and maximum temperatures, respectively. This unifies the scale of different sensor data, facilitating subsequent comprehensive analysis.

[0039] Step S2.3: Based on the statistical analysis of historical operating data, the normal value range and fluctuation threshold of each sensor data are established to obtain the parameter benchmark data set.

[0040] By analyzing historical data from normal equipment operation, we calculate the statistical characteristics of each sensor data, such as the mean, standard deviation, maximum, and minimum values. Based on these statistical characteristics, we establish a normal value range and fluctuation threshold for each sensor data. For example, the normal value range for a temperature sensor might be [85°C, 95°C], with a fluctuation threshold of ±2°C. These parameters constitute the parameter benchmark dataset, which serves as the basis for anomaly detection.

[0041] Step S2.4: Compare the standardized data with the parameter reference data set, mark abnormal data points according to a preset deviation threshold, and obtain pre-processed sensor data with abnormal marks.

[0042] The standardized sensor data is compared with a parameter baseline dataset to calculate the deviation. Any deviation exceeding a preset threshold is flagged as an abnormal data point. For example, if the standardized value of a temperature sensor deviates from the baseline by more than 0.1 (corresponding to an actual temperature of approximately ±5°C), this is flagged as a temperature anomaly. This generates preprocessed sensor data with anomaly markers, providing a foundation for subsequent fault diagnosis.

[0043] Step S3: Based on the pre-processed sensor data, a complete interval polynomial time approximation algorithm is applied to perform multi-dimensional fault feature analysis and matching to obtain a fault diagnosis result.

[0044] In this embodiment, if Figure 4 As shown, step S3 specifically includes: Step S3.1: Collect and organize historical fault cases, extract fault feature indicators and corresponding sensor data features, and obtain a fault feature mapping table.

[0045] Systematically collect information on various potential faults that may occur with the smart capsule fresh-brew beverage dispenser. This includes laboratory simulation testing, analysis of historical maintenance records, and expert experience. This allows for comprehensive identification of potential fault types, such as heating anomalies, water pump failure, communication interruptions, and capsule recognition errors. For each fault type, unique sensor data signature patterns are extracted. For example, a heating module failure may result in an abnormal temperature curve (such as slow heating or large temperature fluctuations) from the temperature sensor. A blocked water pump may also cause abnormal data from both the pressure and flow sensors. This method creates a fault signature mapping table, providing a reference for subsequent fault diagnosis.

[0046] Step S3.2: Based on the fault feature mapping table, a fault feature library including fault type, sensor data features and occurrence scenario is established to obtain fault feature reference data.

[0047] Based on the fault signature mapping table, a structured fault signature knowledge base is established, establishing a clear mapping relationship between each fault type and its corresponding sensor data feature pattern. This knowledge base includes information such as the fault type ID, fault name, involved sensor type, sensor data feature descriptions (such as value range, change trend, frequency characteristics), and typical fault occurrence scenarios. This knowledge base serves as the foundation for fault identification and provides a reference for subsequent fault diagnosis algorithms.

[0048] Step S3.3: Divide the pre-processed sensor data with abnormality marks into intervals, calculate the data distribution density of each interval, and obtain an interval frequency vector.

[0049] The pre-processed sensor data with abnormal markers is divided into intervals, and the data distribution density of each interval is calculated to obtain the interval frequency vector, which includes: Step S3.3.1: Divide the value range of each sensor data into equal intervals, establish a numerical interval mapping table, and obtain an interval division scheme.

[0050] Divide the data range of each sensor into intervals. For example, divide the temperature sensor's 0-100°C range into 10 intervals, each 10°C wide; divide the pressure sensor's 0-10 bar range into 5 intervals, each 2 bar wide. In this way, a numerical interval mapping table is established, which serves as the basis for interval count statistics.

[0051] Step S3.3.2: Based on the interval division scheme, count the data distribution frequency of each interval and generate the interval frequency vector.

[0052] Count the frequency of sensor data falling into each interval over a period of time (e.g., the last 10 minutes) to form an interval frequency vector. For example, the interval frequency vector for a temperature sensor might be [0,0,0,0,0,0,0,15,85,0], indicating that in the last 10 minutes, the temperature was between 70°C and 80°C 15% of the time and between 80°C and 90°C 85% of the time.

[0053] Step S3.4: Calculate the similarity between the interval frequency vector and the fault feature reference data to obtain a fault type candidate set.

[0054] The similarity between the interval frequency vector and the fault feature reference data is calculated to obtain the fault type candidate set, which includes: Step S3.4.1: Construct a multi-layer neural network model, perform feature extraction on the interval frequency vector, and obtain a fault feature representation.

[0055] Build a multi-layer neural network model to extract features from the interval frequency vector. This model can be a simple feedforward neural network consisting of an input layer, hidden layers, and an output layer. The input layer receives the interval frequency vector, and through nonlinear transformations in the hidden layers, the output layer generates a fault feature representation. This feature representation captures complex patterns in the interval frequency vector, facilitating subsequent similarity calculations.

[0056] In the fault diagnosis process for smart capsule fresh-brew beverage dispensers, building and training a multi-layer neural network model is crucial for extracting high-precision fault features. This model primarily converts interval frequency vectors into more expressive fault feature representations. The following details its construction and training process.

[0057] First, the model's basic architecture utilizes a three-layer feedforward neural network structure, consisting of an input layer, a hidden layer, and an output layer. The number of neurons in the input layer matches the dimension of the interval vector. For example, if each type of sensor data—temperature, pressure, flow, current, voltage, and vibration frequency—is divided into 10 intervals, the input layer dimension is 60 neurons. The hidden layer employs a two-layer structure, with the first hidden layer containing 128 neurons and the second hidden layer containing 64 neurons. The output layer dimension is 32, generating a 32-dimensional fault feature representation vector.

[0058] The choice of activation function is crucial to model performance. Using the ReLU (Rectified Linear Unit) activation function in the hidden layer, with the expression f(x) = max(0,x), helps address the vanishing gradient problem in deep network training and accelerates convergence. The output layer uses the tanh activation function, which constrains output values ​​to the range [-1, 1] to facilitate subsequent similarity calculations.

[0059] The model is trained using supervised learning, using labeled historical fault data as the training set. The training data includes a vector of the number of fault intervals as input, and the corresponding fault type as a label. To enhance the model's generalization capabilities, the training set includes fault cases under various operating conditions, such as varying ambient temperatures and usage frequencies. A typical training set consists of approximately 5,000 to 10,000 samples, covering 30 to 50 common fault types.

[0060] The optimizer chosen was Adam (Adaptive Moment Estimation), which combines the advantages of momentum and RMSProp and can adaptively adjust the learning rate. The initial learning rate was set to 0.001. The loss function used was cross-entropy loss, which is suitable for multi-classification problems. During training, a batch size of 64 and 100 epochs were used. An early stopping strategy was used, stopping training after 10 consecutive epochs without improvement in the validation set loss to prevent overfitting.

[0061] To further improve model performance, the following techniques are also used: Data augmentation: Gaussian noise (μ=0, σ=0.01) is added to the original interval frequency vector to simulate small fluctuations in sensor data and enhance model robustness.

[0062] Dropout regularization: A dropout layer is added between the two hidden layers with a dropout rate of 0.3 to reduce the risk of overfitting.

[0063] Batch Normalization: Adding a batch normalization layer after each hidden layer speeds up the training process and improves model stability.

[0064] After model training, its performance was evaluated on a test set, achieving a typical accuracy of 92%-95%. In practical applications, the model was able to convert raw interval frequency vectors into more discriminative feature representations. For example, the feature representation for a "water pump blockage" fault exhibited distinct activation patterns along specific dimensions, significantly different from the feature representation for a "heater failure," providing a reliable foundation for subsequent similarity calculations and fault diagnosis.

[0065] Step S3.4.2: Calculate the cosine similarity between the fault feature representation and the preset pattern in the fault feature reference data to obtain a similarity matrix.

[0066] The cosine similarity between the fault signature representation generated by the neural network and the preset patterns in the fault signature library is calculated. The formula for calculating cosine similarity is cos(θ)=A·B / (|A|·|B|), where A and B are the current and reference feature vectors, respectively. This method generates a similarity matrix between the current fault signature and various preset fault patterns.

[0067] Step S3.4.3: Based on the similarity matrix, the fault types whose similarity exceeds a preset threshold are screened to obtain preliminary fault types.

[0068] Set a similarity threshold (e.g., 0.8) and select fault types with similarities exceeding this threshold as preliminary fault types. For example, if the current feature has a similarity of 0.92 with the "water pump blocked" pattern and 0.75 with the "heater fault" pattern, then the preliminary fault is determined to be a "water pump blocked" fault.

[0069] Step S3.4.4: Combine the initial fault judgment results of multiple sensors to build a decision tree to determine the fault type and obtain a candidate set of fault types.

[0070] Based on the previous feature analysis results, a multi-level decision tree structure was designed to accurately classify fault types through a series of conditional judgments. Each node in the decision tree represents a judgment condition (such as "whether the temperature exceeds 85°C" or "whether the flow rate is less than 50 ml / min"). Each branch represents the result of the conditional judgment, and each leaf node corresponds to a fault type or the next level of decision.

[0071] When designing a decision tree, the optimal judgment sequence is determined based on prior knowledge of the fault and the correlation of sensor data. Typically, judgment begins with the most discriminatory features and progresses to more detailed features. For example, the system module experiencing an anomaly (such as the heating system or water pump system) is first determined, followed by the specific fault type. This multi-layered judgment logic can handle complex fault scenarios, including those with multiple abnormal parameters simultaneously.

[0072] Step S3.5: Perform component association analysis on the fault type candidate set to determine the fault location and impact range, and obtain a fault diagnosis result.

[0073] After determining the fault type, we further locate the specific location and impact of the fault. First, we build a topological relationship model between the various components of the equipment, describing the physical connections and functional dependencies between them. For example, there is a water flow transmission relationship between the water pump and the heater, and a temperature sensing relationship between the heater and the temperature sensor.

[0074] Based on this topological model, when a component anomaly is detected, the system analyzes the potential impact on upstream and downstream components and the potential propagation path of the fault. For example, if insufficient water flow is detected, possible fault points include a malfunctioning pump, a clogged pipe, or insufficient water in the water tank. By analyzing the temporal changes and interrelationships of data from each monitoring point, the scope of the fault can be further narrowed. This component correlation analysis not only accurately locates the fault but also assesses its impact, providing important insights for subsequent troubleshooting.

[0075] Step S4: Based on the fault diagnosis results, the faults are graded according to their severity and user processability, and structured fault information including fault description, cause analysis and solution is generated.

[0076] In this embodiment, if Figure 5 As shown, step S4 specifically includes: Step S4.1: Establish a fault assessment index system based on the degree of impact on equipment functions, safety risk level, and maintenance difficulty to obtain an assessment benchmark.

[0077] Establish a systematic fault classification standard to evaluate and classify faults from multiple perspectives. First, consider the degree of impact of the fault on the equipment's functionality. These faults are categorized into: minor faults that do not affect use (such as failure of certain non-essential indicator lights), general faults that partially affect functionality (such as unstable extraction temperature), severe faults that render key functions unusable (such as failure to heat), and dangerous faults that could pose safety risks (such as overpressure or electrical shorts).

[0078] Secondly, the fault's danger level is assessed from a safety risk perspective, including no safety risk, low risk (may affect beverage quality), medium risk (may cause equipment damage), and high risk (may cause personal injury or fire, etc.). Thirdly, from the perspective of user manageability, faults are categorized as simple faults that can be resolved by the user (such as water shortage or capsule not inserted), moderate faults that require basic maintenance (such as simple cleaning or resetting), and complex faults that require professional repair (such as internal component damage).

[0079] These classification dimensions combine to form a multi-dimensional fault classification matrix, assigning a comprehensive level to each fault to guide subsequent information generation and processing. For example, "Level A1 Fault" might represent a fault type that "affects primary functionality and poses a safety risk, but can be addressed by the user."

[0080] Step S4.2: Quantitatively score the fault diagnosis results based on the evaluation criteria, classify the fault levels, and obtain a fault classification result.

[0081] Quantify the fault diagnosis results and score them, such as functional impact (1-5 points), safety risk level (1-5 points), and repair difficulty (1-5 points). Based on the scoring results, the fault level is divided into: 1-3 points: Minor fault, the user can handle it by himself; 4-6 points: general failure, basic maintenance required; 7-9 points: serious fault, requiring professional repair; 10-15 points: Dangerous failure, you need to stop the machine immediately and contact professionals.

[0082] In this way, the fault classification results are obtained, which provide a basis for subsequent information generation.

[0083] Step S4.3: extracting a description template corresponding to the fault classification result from a preset fault description template library, filling in the fault parameters and impact range, and obtaining the fault description content.

[0084] Based on the identified fault type, corresponding templates are extracted from a pre-set fault description template library. These templates consist of three main components: the fault name (e.g., "water pump blocked," "heater overheat protection," etc.), the fault symptom (e.g., "no water flow during production," "abnormally extended preheating time," etc.), and the relevant technical parameters (e.g., "water flow rate less than 10 ml / min," "temperature exceeding 95°C for 30 seconds," etc.).

[0085] Specific parameter values ​​are entered into the template, such as "The current water temperature is 87°C, which is lower than the normal operating temperature of 92°C." Descriptive content of varying complexity can be generated for different user groups (such as ordinary users and professional maintenance personnel) to meet their information needs.

[0086] Step S4.4: Based on the statistical analysis of historical fault data, the probability distribution of different fault causes is calculated and the cause analysis content is generated.

[0087] The corresponding possible cause analysis is extracted from a pre-established fault cause knowledge base. This knowledge base is built based on historical fault data, expert experience, and theoretical analysis, and contains common causes and probability of occurrence for various faults. For example, for a "water pump malfunctioning" fault, possible causes include: a damaged pump motor (30%), a control circuit failure (25%), a clogged water pipe (35%), and a power supply problem (10%).

[0088] Based on the actual monitored data characteristics, various possible causes are ranked by probability, with the most likely causes presented to the user first. A detailed explanation is also provided for each possible cause to help the user understand the fault's mechanism. This probabilistic cause analysis provides more targeted guidance for users or maintenance personnel in troubleshooting, improving troubleshooting efficiency.

[0089] Step S4.5: Select the corresponding processing plan based on the fault classification result, generate inspection, operation and verification steps based on the equipment status, and obtain the solution content.

[0090] Based on the fault type, severity, and possible cause, corresponding solutions are generated for the user. For faults that can be resolved by the user (such as water shortage or incorrectly placed capsule), detailed step-by-step instructions are provided, including text instructions and possible graphic references. For example, for a "water tank shortage" fault, the solution might be: "1. Remove the water tank; 2. Fill the water tank with clean drinking water to the MAX mark; 3. Reinstall the water tank; 4. Press the retry button."

[0091] For faults requiring basic maintenance, simple maintenance instructions are provided, such as cleaning procedures and reset methods. For complex faults requiring professional repair, suggestions for contacting customer service or reporting a problem are provided, and temporary usage restrictions may be included to prevent further damage to the device. For faults that may pose a safety risk, safety precautions are emphasized, such as warnings such as "Disconnect the power supply immediately and do not attempt to repair the device yourself."

[0092] Step S4.6: Integrate the fault description content, cause analysis content, and solution content into a unified format to obtain structured fault information.

[0093] Combine the fault description, cause analysis, and solution generated in the previous steps to form a complete, structured fault information document. This structured content has a clear hierarchy, starting with the fault name and brief description, moving on to possible cause analysis and specific solution recommendations. Furthermore, the information content is formatted appropriately based on the characteristics of different output channels (such as device displays and mobile apps).

[0094] For example, due to limited display space, a local device display might only display a brief fault name and basic resolution steps. However, a mobile app can display complete fault information, including a detailed cause analysis, illustrated solution guidance, and even links to video tutorials. Furthermore, faults of varying severity can be distinguished using different visual styles (such as color coding and icons), enhancing the user's intuitive perception of fault severity.

[0095] Step S5: Output the structured fault information through the local display interface of the device and the mobile terminal, and upload the fault diagnosis result to the cloud server.

[0096] In this embodiment, step S5 specifically includes: Step S5.1: Divide the structured fault information into emergency warning information, fault prompt information and maintenance suggestion information according to the fault level to obtain a hierarchical information set.

[0097] According to the severity and urgency of the fault, structured fault information is divided into different levels: Emergency warning information: high-risk faults that require immediate user attention, such as excessive pressure, abnormal temperature, etc. Fault prompt information: Faults that affect normal use of the equipment but do not pose a safety risk, such as low water pump efficiency and capsule recognition errors; Maintenance recommendation information: Tips that do not affect current use but require regular maintenance, such as cleaning the water channel and replacing the filter element.

[0098] Through this hierarchical method, a hierarchical information set is formed, providing a basis for information output through different channels.

[0099] Step S5.2: Based on the hierarchical information set, the basic information layout of the local display interface and the detailed information layout of the mobile terminal are configured to obtain a display configuration solution.

[0100] Design the corresponding display layout according to different levels of fault information: For emergency warning information, a striking red background and warning icon are used on the local display interface, and push notifications are displayed on mobile terminals at the top. For fault prompt information, a yellow background and prompt icon are used on the local display interface and displayed in the fault list of the mobile terminal; Maintenance suggestion information is displayed in the information area of ​​the local display interface and on the maintenance suggestion page of the mobile terminal.

[0101] In this way, display configuration solutions for different devices are obtained to ensure effective communication of information.

[0102] Step S5.3: According to the display configuration scheme, the fault name, alarm level and basic processing prompts are output on the local display interface of the device, and the alarm level is output through different colors and flashing frequencies of the LED indicator.

[0103] The device's local display displays fault information based on the display configuration. For example, a "Water Pump Blockage" fault might display "Fault: Water Pump Blockage [Moderate]" and provide a brief action prompt: "Please check if the water pipe is blocked." Furthermore, different LED indicator states indicate different alarm levels, such as a rapidly flashing red light for an emergency alarm, a slowly flashing yellow light for a general fault, and a steady green light for normal operation.

[0104] Step S5.4: The structured fault information is transmitted to the user's mobile terminal via the MQTT protocol, and the fault diagnosis process, cause analysis, and treatment plan are displayed in layers according to the importance of the information to obtain mobile terminal output information.

[0105] The structured fault information is transmitted to the user's mobile terminal app via the MQTT (Message Queuing Telemetry Transport) protocol. In the app, the information is displayed in layers according to its importance: The home page displays the fault name, level and brief description; The details page displays the fault diagnosis process, possible cause analysis, and treatment solutions; Advanced information pages provide technical specifications, history, and links to related knowledge.

[0106] Through this layered display method, the needs of different users for information depth can be met and the user experience can be improved.

[0107] Step S5.5: Encapsulate the fault diagnosis result in JSON format and encrypt it with AES, and upload it to the cloud server via WiFi or Bluetooth communication.

[0108] The fault diagnosis results are converted into JSON format, containing information such as device ID, fault type, fault time, sensor data, and diagnostic results. The data is then encrypted using the AES algorithm to ensure secure data transmission. Finally, the encrypted data is uploaded to a cloud server via WiFi or Bluetooth for subsequent data analysis and knowledge base updates.

[0109] Step S6: Applying a top-down hierarchical differential private counting query mechanism in the cloud server to process the fault diagnosis result and update the fault knowledge base.

[0110] In this embodiment, step S6 specifically includes: Step S6.1: The cloud server receives and decrypts the fault diagnosis results uploaded by multiple devices, establishes a structured fault data table, and obtains original fault statistics.

[0111] The cloud server receives encrypted fault diagnosis data from multiple devices and decrypts it using the corresponding decryption key. The decrypted data is organized into a structured fault data table containing fields such as device ID, fault type, fault time, sensor data, and diagnostic results. This generates raw fault statistics, providing a foundation for subsequent analysis.

[0112] Step S6.2: Perform hierarchical differential processing on the original fault statistical data, calculate the frequency of fault occurrence while protecting user privacy, and obtain fault type distribution statistics.

[0113] Perform hierarchical differential processing on the original fault statistics, calculate the fault frequency while protecting user privacy, and obtain the fault type distribution statistics, including: Step S6.2.1: Create a multi-layer index for the original fault statistics according to device model, usage time, geographical area and ambient temperature to obtain a hierarchical data structure.

[0114] Raw fault statistics are hierarchically indexed according to multiple dimensions, including device model (e.g., Basic Edition, Advanced Edition), usage duration (e.g., 0-6 months, 6-12 months), geographic region (e.g., North China, East China), and ambient temperature (e.g., low temperature, normal temperature, high temperature). This multi-dimensional indexing creates a hierarchical data structure, facilitating subsequent hierarchical analysis.

[0115] Step S6.2.2: In each layer of data index, group and count the fault records, and add Laplace noise according to the differential privacy budget to obtain the privatized counting result.

[0116] At each data index level, fault records are grouped and counted by fault type. To protect user privacy, differential privacy techniques are applied to add random noise conforming to a Laplace distribution to the count results. The amount of noise is controlled by the differential privacy budget ε. A smaller ε value provides stronger privacy protection but reduces data accuracy. This approach produces privatized count results that protect individual user privacy while retaining statistical significance.

[0117] Step S6.2.3: Based on the privatized counting result, a sliding time window is used to calculate the time distribution characteristics of the fault occurrence frequency to obtain fault trend data.

[0118] Use a sliding time window (e.g., 30 days) to perform time series analysis on privatization count results and calculate the frequency of various fault types within different time periods. By comparing data from different time windows, we can identify trends in fault frequency, such as whether a particular fault type is showing an upward trend or seasonal fluctuations. This trend data provides important insights for fault prediction and preventive maintenance.

[0119] Step S6.2.4: Perform hierarchical cluster analysis on the fault trend data to generate a fault frequency heat map and a time series trend map to obtain a visual statistical chart.

[0120] Perform hierarchical cluster analysis on fault trend data to identify fault types and device groups with similar patterns. Based on the clustering results, generate a fault frequency heat map to visually display the frequency of various faults under different device types and usage environments. Simultaneously, generate a time series trend chart to show how fault frequency changes over time. These visual statistical charts provide intuitive support for fault analysis and decision-making.

[0121] Step S6.2.5: Combine the equipment operating parameters and environmental monitoring data to identify the fault causes through correlation analysis and obtain a statistical report on the distribution of fault types.

[0122] Fault data is correlated with equipment operating parameters (such as frequency of use and operating time) and environmental monitoring data (such as ambient temperature and humidity) to calculate correlation coefficients and identify possible fault causes. For example, analysis may reveal that "the incidence of heater overheat protection failures increases by 50% when the ambient temperature exceeds 30°C." These analysis results are compiled into a statistical report on the distribution of fault types, providing a basis for fault prevention and product improvement.

[0123] Step S6.3: Based on the fault type distribution statistics, combined with the equipment operation time and usage environment parameters, analyze the fault timing characteristics and environmental correlation to obtain a fault mode analysis report.

[0124] Based on the distribution statistics of fault types, we further analyze the timing characteristics and environmental relevance of faults. For example, we analyze whether a certain type of fault has a clear correlation with the length of equipment use (e.g., failure rates increase significantly after 12 months of use) or is related to specific environmental conditions (e.g., higher failure rates at high altitudes). This in-depth analysis yields a failure mode analysis report, revealing the underlying patterns and influencing factors of fault occurrence.

[0125] Step S6.4: Based on the fault mode analysis report, the feature weights and threshold parameters of the fault feature library are updated, the fault diagnosis rules are optimized, and an improved diagnosis model is obtained.

[0126] Based on the fault mode analysis report, the fault signature library is updated and optimized. Feature weights are adjusted to increase sensitivity to key features; threshold parameters are updated to improve fault diagnosis accuracy; and diagnostic rules are optimized to refine fault identification logic. For example, if analysis reveals that temperature sensor data is more critical for diagnosing a certain type of fault, its weight is increased. If the temperature threshold for a certain type of fault is found to require dynamic adjustment based on ambient temperature, the corresponding threshold calculation rules are updated. This continuous optimization results in an improved diagnostic model, enhancing the accuracy and efficiency of fault diagnosis.

[0127] Step S6.5: Integrate user feedback and maintenance records, extract new fault features and solutions, update the fault knowledge base content, and obtain an iteratively optimized fault knowledge base.

[0128] Collect and analyze user feedback on troubleshooting to understand their assessment of fault diagnosis accuracy and solution effectiveness. Also, integrate maintenance records from professional maintenance personnel, including information such as actual fault causes, solutions, and verification results. By analyzing this data, newly discovered fault characteristics and effective solutions are extracted and updated to the fault knowledge base. For example, if a new fault pattern is discovered, it is added to the fault characteristic library; if a more effective solution is found, the corresponding solution recommendations are updated. This continuous knowledge accumulation and optimization creates an iteratively optimized fault knowledge base, providing more comprehensive and accurate support for future fault diagnosis and resolution.

[0129] The following is a complete example process for handling fault information of the smart capsule fresh beverage machine: A user's smart capsule fresh-brew beverage machine experienced insufficient water flow during beverage preparation. At this point, the device's multi-sensor system immediately went into action. The flow sensor detected a water flow rate of only 15 ml / min, far below the normal value of 50 ml / min. The pressure sensor indicated the pump outlet pressure was 1.2 bar, 2.5 bar below the normal value. The current sensor detected the pump motor current at 0.8 A, 0.5 A above the normal value. The vibration sensor detected an abnormal, irregular vibration frequency. This raw sensor data was collected and transmitted to the main control unit via an internal bus. Timestamps were added to form structured raw sensor data sets.

[0130] The data preprocessing module processes this raw data. First, a median filter algorithm is applied to eliminate sudden noise in the vibration data. Then, a Kalman filter is used to smooth the flow and pressure data curves. Next, the different types of sensor data are normalized and mapped to the [0, 1] interval for comprehensive analysis. Comparing this normalized data with a pre-established parameter baseline dataset revealed that flow values ​​deviated from the normal range by 70%, pressure values ​​by 52%, and current values ​​by 60%. Therefore, these data points were marked as anomalies, generating preprocessed sensor data with anomaly labels.

[0131] The fault diagnosis module analyzes this preprocessed data. First, the abnormal data is segmented into intervals. For example, the flow rate data range of 0-100 ml / min is divided into 10 intervals. The interval frequency vector [0, 85, 15, 0, 0, 0, 0, 0, 0] is calculated, indicating that 85% of the time the flow rate is within the 0-10 ml / min range and 15% of the time it is within the 10-20 ml / min range. These interval frequency vectors are input into a pretrained neural network model consisting of an input layer (60 neurons), two hidden layers (128 and 64 neurons), and an output layer (32 neurons), generating a fault feature representation. The cosine similarity between this feature representation and patterns in the fault feature library was calculated, revealing a similarity of 0.93 with the "water pump blockage" pattern, significantly higher than other fault types. Further analysis using a decision tree confirmed the final diagnosis of "water pump inlet pipe blockage," with the fault located at the pump inlet and affecting the entire water flow system.

[0132] The information generation module performs a tiered analysis based on the fault diagnosis results. The fault's functional impact is assessed as 4 (moderate impact), safety risk as 1 (no safety risk), and repair difficulty as 2 (user-resolvable), for a total score of 7, classifying it as a "Class B fault." A corresponding template is extracted from the fault description template library, filled with specific parameters, and a fault description is generated: "Insufficient water flow detected. Current flow rate is 15 ml / min, lower than the normal value of 50 ml / min." Based on historical data analysis, a cause analysis is generated: "Possible causes: 1. Blockage of water pump inlet pipe (75%); 2. Water tank lacks water (15%); 3. Water pump failure (10%)." For the most likely cause, a solution is generated: "1. Turn off the power; 2. Remove the water tank; 3. Check and clean the water inlet filter at the bottom of the water tank; 4. Reinstall the water tank and ensure it is properly seated; 5. Restart the device." This information is then integrated into structured fault information.

[0133] The information output module classifies fault information as a fault prompt (Class B) and displays it with a yellow background. The device's local display displays "Fault: Insufficient Water Flow [Class B]" and a brief action prompt, "Please check the water tank inlet," while a yellow LED indicator flashes slowly. Detailed fault information is also transmitted to the user's mobile app via the MQTT protocol. The app displays the fault diagnosis process, three possible causes and their probabilities, and a detailed five-step solution with illustrated instructions. The fault diagnosis results are converted to JSON format and uploaded to the cloud server after encryption.

[0134] The cloud server receives and decrypts this fault data, adding it to a structured fault data table. It discovered that 27 devices of the same model had recently reported similar faults. Using layered differential processing to calculate the fault frequency, it was found that this fault occurred more frequently in devices between 3 and 6 months old and was positively correlated with water hardness. A fault frequency heat map was generated, showing that the fault incidence in hard water areas was 40% higher than in soft water areas. Based on this analysis, the fault signature database was updated, increasing the weight of water quality factors in fault diagnosis. A new preventive recommendation was also added to the knowledge base: "Users in hard water areas are advised to clean the water tank inlet filter once a month." This update will be applied to subsequent fault diagnosis to improve fault prevention and resolution efficiency.

[0135] like Figure 6 As shown, the present invention also provides a fault information processing system for an intelligent capsule fresh beverage machine, comprising: A data acquisition module is used to collect real-time data of temperature, pressure, flow, current, voltage and vibration frequency through multiple sensors deployed on key components of the smart capsule fresh beverage machine to obtain raw sensor data; A data preprocessing module, configured to perform filtering and normalization preprocessing on the raw sensor data to obtain preprocessed sensor data; A fault diagnosis module is used to perform multi-dimensional fault feature analysis and matching based on the pre-processed sensor data using a complete interval polynomial time approximation algorithm to obtain a fault diagnosis result; An information generation module is used to generate structured fault information including fault description, cause analysis and solution based on the fault diagnosis results, grading the fault according to its severity and user handleability; An information output module, configured to output the structured fault information via the device's local display interface and a mobile terminal, and upload the fault diagnosis results to a cloud server; The data processing module is used to apply a top-down hierarchical differential private counting query mechanism in the cloud server to process the fault diagnosis result and update the fault knowledge base.

[0136] The present invention realizes accurate diagnosis, hierarchical processing and multi-channel output of faults of smart capsule fresh-brew beverage machines through multi-sensor real-time data acquisition, data preprocessing and anomaly detection, multi-dimensional fault diagnosis and positioning, hierarchical fault information generation, multi-channel fault information output, fault data storage and analysis, as well as fault processing feedback and knowledge base update, thereby improving fault processing efficiency and user experience.

[0137] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

[0138] It should be noted that those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. If these changes and modifications fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these changes and modifications.

[0139] The present disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, executes the steps of the method for handling fault information of a smart capsule fresh-brew beverage machine described in the above method embodiment. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0140] In addition, an embodiment of the present disclosure also provides a computer program product, which stores a computer program. When the computer program is run by a processor, it executes the steps of the fault information processing method of any of the above-mentioned smart capsule fresh beverage machines disclosed in the present disclosure. For details, please refer to the above-mentioned method embodiments, which will not be repeated here.

[0141] The computer program product may be implemented in hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is embodied as a computer storage medium, which may be a volatile or non-volatile computer-readable storage medium. In another alternative embodiment, the computer program product is embodied as a software product, such as a software development kit (SDK).

[0142] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment and devices can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0143] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0144] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0145] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0146] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The scope of protection of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-mentioned embodiments within the technical scope disclosed in the present disclosure, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure should be based on the scope of protection of the claims.

Claims

1. A method for processing fault information of an intelligent capsule fresh beverage machine, characterized in that: include: By deploying multiple sensors on key components of the smart capsule fresh beverage machine, real-time data of temperature, pressure, flow, current, voltage and vibration frequency are collected to obtain raw sensor data; Performing filtering and normalization preprocessing on the raw sensor data to obtain preprocessed sensor data; Based on the preprocessed sensor data, a polynomial time approximation algorithm of full interval degree is applied to perform multi-dimensional fault feature analysis and matching to obtain a fault diagnosis result; Based on the fault diagnosis results, the faults are graded according to their severity and user manageability, and structured fault information including fault description, cause analysis and solution is generated; Output the structured fault information through the local display interface of the device and the mobile terminal, and upload the fault diagnosis results to the cloud server; A top-down hierarchical differential private counting query mechanism is applied in the cloud server to process the fault diagnosis result and update the fault knowledge base.

2. The method according to claim 1, characterized in that By deploying multiple sensors on key components of the smart capsule fresh beverage machine, real-time data on temperature, pressure, flow, current, voltage, and vibration frequency are collected to obtain raw sensor data, including: Based on the preset sampling time interval and sampling trigger conditions, the analog signal of each sensor is sampled regularly to obtain time series sampling data; Performing analog-to-digital conversion on the time series sampling data to obtain digital sensor data; Transmitting the digitized sensor data to a main control unit via an internal bus, and adding a timestamp to the received sensor data in the main control unit to obtain timestamp-marked sensor data; A data cache is established in the main control unit, and the sensor data marked with the timestamp is indexed according to the sensor type and the acquisition time to obtain a structured raw sensor data group.

3. The method according to claim 2, characterized in that The raw sensor data is filtered and normalized to obtain preprocessed sensor data, including: Applying median filtering and Kalman filtering algorithms to the structured raw sensor data group to eliminate noise interference and obtain filtered data; Normalizing the filtered data to map different types of data to a unified interval to obtain standardized data; Based on the statistical analysis of historical operating data, the normal value range and fluctuation threshold of each sensor data are established to obtain the parameter benchmark data set; The standardized data is compared with the parameter reference data set, and abnormal data points are marked according to a preset deviation threshold to obtain pre-processed sensor data with abnormal marks.

4. The method according to claim 3, characterized in that Based on the preprocessed sensor data, a complete interval degree polynomial time approximation algorithm is applied to perform multi-dimensional fault feature analysis and matching to obtain fault diagnosis results, including: Collect and organize historical fault cases, extract fault characteristic indicators and corresponding sensor data features, and obtain a fault characteristic mapping table; Based on the fault feature mapping table, a fault feature library including fault type, sensor data features and occurrence scenario is established to obtain fault feature reference data; Dividing the pre-processed sensor data with abnormality marks into intervals, calculating the data distribution density of each interval, and obtaining an interval frequency vector; Calculate similarity between the interval frequency vector and the fault feature reference data to obtain a fault type candidate set; Perform component association analysis on the fault type candidate set to determine the fault location and impact range, and obtain a fault diagnosis result.

5. The method according to claim 4, characterized in that The pre-processed sensor data with abnormal markers is divided into intervals, and the data distribution density of each interval is calculated to obtain an interval frequency vector, including: Divide the value range of each sensor data into equal intervals, establish a numerical interval mapping table, and obtain an interval division scheme; Based on the interval division scheme, counting the data distribution frequency of each interval to generate the interval frequency vector; Calculate the similarity between the interval frequency vector and the fault feature reference data to obtain a fault type candidate set, including: Constructing a multi-layer neural network model, performing feature extraction on the interval frequency vector, and obtaining a fault feature representation; Calculating cosine similarity between the fault feature representation and a preset pattern in the fault feature reference data to obtain a similarity matrix; Based on the similarity matrix, screening fault types whose similarity exceeds a preset threshold to obtain preliminary fault types; Combining the initial fault judgment results of multiple sensors, a decision tree is constructed to determine the fault type and obtain a candidate set of fault types.

6. The method according to claim 1, characterized in that Based on the fault diagnosis results, the faults are graded according to their severity and user manageability, and structured fault information is generated, including fault description, cause analysis, and solutions, including: Establish a fault assessment index system based on the degree of impact on equipment functions, safety risk level, and maintenance difficulty to obtain an assessment benchmark; Quantitatively scoring the fault diagnosis results based on the evaluation benchmark, classifying the fault levels, and obtaining a fault classification result; Extracting a description template corresponding to the fault classification result from a preset fault description template library, filling in fault parameters and impact range, and obtaining fault description content; Based on the statistical analysis of historical fault data, the probability distribution of different fault causes is calculated and the cause analysis content is generated; Select the corresponding treatment plan based on the fault classification results, and generate inspection, operation, and verification steps based on the equipment status to obtain the solution content; The fault description content, cause analysis content and solution content are integrated into a unified format to obtain structured fault information.

7. The method according to claim 1, characterized in that Outputting the structured fault information through the local display interface of the device and the mobile terminal, and uploading the fault diagnosis results to the cloud server, including: Classifying the structured fault information into emergency warning information, fault prompt information, and maintenance suggestion information according to the fault level to obtain a hierarchical information set; Based on the hierarchical information set, configuring the basic information layout of the local display interface and the detailed information layout of the mobile terminal to obtain a display configuration solution; According to the display configuration scheme, the fault name, alarm level and basic processing prompts are output on the local display interface of the device, and the alarm level is output through the different colors and flashing frequencies of the LED indicator; The structured fault information is transmitted to the user's mobile terminal via the MQTT protocol, and the fault diagnosis process, cause analysis, and treatment plan are displayed in layers according to the importance of the information to obtain mobile terminal output information; The fault diagnosis results are encapsulated in JSON format and encrypted with AES, and uploaded to the cloud server via WiFi or Bluetooth communication.

8. The method according to claim 1, characterized in that Applying a top-down hierarchical differential private counting query mechanism in the cloud server to process the fault diagnosis result and update the fault knowledge base includes: The cloud server receives and decrypts the fault diagnosis results uploaded by multiple devices, establishes a structured fault data table, and obtains original fault statistics; Performing hierarchical differential processing on the original fault statistical data, calculating the fault occurrence frequency while protecting user privacy, and obtaining fault type distribution statistics; Based on the distribution statistics of the fault types, combined with the equipment operation time and the operating environment parameters, the fault timing characteristics and environmental correlation are analyzed to obtain a fault mode analysis report; According to the fault mode analysis report, the feature weights and threshold parameters of the fault feature library are updated, the fault diagnosis rules are optimized, and an improved diagnosis model is obtained; Integrate user feedback and maintenance records, extract new fault features and solutions, update the fault knowledge base content, and obtain an iteratively optimized fault knowledge base.

9. The method according to claim 8, characterized in that Perform hierarchical differential processing on the original fault statistics, calculate the fault frequency while protecting user privacy, and obtain fault type distribution statistics, including: Establishing a multi-layer index for the raw fault statistics according to device model, usage time, geographical region, and ambient temperature to obtain a hierarchical data structure; In each layer of data index, fault records are grouped and counted, and Laplace noise is added according to the differential privacy budget to obtain the privatized counting results; Based on the privatized counting results, a sliding time window is used to calculate the time distribution characteristics of the fault occurrence frequency to obtain fault trend data; Performing hierarchical cluster analysis on the fault trend data to generate a fault frequency heat map and a time series trend map to obtain a visual statistical chart; Combining equipment operating parameters and environmental monitoring data, the causes of faults are identified through correlation analysis, and a statistical report on the distribution of fault types is obtained.

10. A fault information processing system for an intelligent capsule fresh beverage machine, characterized in that: include: A data acquisition module is used to collect real-time data of temperature, pressure, flow, current, voltage and vibration frequency through multiple sensors deployed on key components of the smart capsule fresh beverage machine to obtain raw sensor data; A data preprocessing module, configured to perform filtering and normalization preprocessing on the raw sensor data to obtain preprocessed sensor data; A fault diagnosis module is used to perform multi-dimensional fault feature analysis and matching based on the pre-processed sensor data using a complete interval polynomial time approximation algorithm to obtain a fault diagnosis result; An information generation module is used to generate structured fault information including fault description, cause analysis and solution based on the fault diagnosis results, grading the fault according to its severity and user handleability; An information output module, configured to output the structured fault information via the device's local display interface and a mobile terminal, and upload the fault diagnosis results to a cloud server; The data processing module is used to apply a top-down hierarchical differential private counting query mechanism in the cloud server to process the fault diagnosis result and update the fault knowledge base.

Images