Water quality monitoring method of water dispenser, water quality monitoring device and storage medium

Abstract

The invention relates to the water quality detection technology, and discloses a water quality monitoring method and device for a water dispenser and a storage medium, and the method comprises the steps that based on a data acquisition module, water quality parameters of the water dispenser are acquired, and the water quality parameters comprise conductivity, spectral data and current temperature; the data acquisition module is arranged at a water inlet and / or a water outlet of the water dispenser; performing temperature compensation on the conductivity according to the current temperature, and calculating the TDS concentration according to the conductivity after temperature compensation; and extracting a feature vector corresponding to the spectral data, inputting the feature vector into a linear regression model, and predicting the content of microorganisms, and performing weighted summation based on the TDS concentration and the microbial content to obtain a comprehensive water quality index corresponding to the water dispenser. The invention further discloses the water dispenser. The invention aims to accurately reflect the water quality condition of the water dispenser.

Description

Technical Field

[0001] The present application relates to the technical field of water quality detection, and in particular to a water quality monitoring method for a water dispenser, a water quality monitoring device, a water dispenser, and a computer-readable storage medium. Background Art

[0002] As people pay more and more attention to healthy living, drinking water safety has become the focus of public attention. As a common drinking water device in homes and offices, the importance of water quality monitoring technology is self-evident.

[0003] In existing water quality monitoring technologies, water quality is usually assessed by detecting certain specific indicators in the water. These single indicators can only reflect the characteristics of a certain aspect of water quality, and cannot fully assess the overall condition of water quality. In addition, existing water quality monitoring technologies often ignore the impact of temperature on water quality parameters. In fact, changes in temperature will affect parameters such as conductivity and dissolved oxygen in water, thereby affecting the accuracy of water quality monitoring.

[0004] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0005] The main purpose of the present application is to provide a water quality monitoring method for a water dispenser, a water quality monitoring device, a water dispenser and a computer-readable storage medium, aiming to accurately reflect the water quality status of the water dispenser.

[0006] To achieve the above objectives, the present application provides a method for monitoring water quality of a water dispenser, comprising the following steps: Based on the data acquisition module, water quality parameters of the water dispenser are collected, wherein the water quality parameters include conductivity, spectral data and current temperature; the data acquisition module is arranged at the water inlet and / or the water outlet of the water dispenser; Conducting temperature compensation on the conductivity according to the current temperature and calculating the TDS (Total Dissolved Solids) concentration based on the temperature-compensated conductivity; and extracting the eigenvector corresponding to the spectral data and inputting the eigenvector into a linear regression model to predict the microbial content; Based on the weighted sum of TDS concentration and microbial content, the comprehensive water quality index corresponding to the water dispenser is obtained.

[0007] Optionally, before the step of extracting the feature vector corresponding to the spectral data and inputting the feature vector into a linear regression model to predict the microbial content, the step further includes: The spectral data were denoised and normalized.

[0008] Optionally, before the step of extracting the feature vector corresponding to the spectral data and inputting the feature vector into a linear regression model to predict the microbial content, the step further includes: Based on the training data set, a linear regression model is constructed; The training data set includes microbial contents corresponding to feature vectors of multiple samples.

[0009] Optionally, before the step of performing weighted summation based on TDS concentration and microbial content to obtain a comprehensive water quality index corresponding to the water dispenser, the step further includes: The TDS concentration and microbial content were standardized.

[0010] Optionally, after the step of performing weighted summation based on TDS concentration and microbial content to obtain a comprehensive water quality index corresponding to the water dispenser, the step further includes: Check whether the comprehensive water quality index meets the preset standards; If not, an alarm will be issued.

[0011] Optionally, after the step of performing weighted summation based on TDS concentration and microbial content to obtain a comprehensive water quality index corresponding to the water dispenser, the step further includes: The output displays the water quality parameters, TDS concentration, microbial content and comprehensive water quality index corresponding to the water dispenser.

[0012] Optionally, after the step of performing weighted summation based on TDS concentration and microbial content to obtain a comprehensive water quality index corresponding to the water dispenser, the step further includes: The water quality parameters, TDS concentration, microbial content and comprehensive water quality index corresponding to the water dispenser are uploaded to the cloud platform so that the cloud platform can generate a water quality report corresponding to the water dispenser.

[0013] To achieve the above-mentioned purpose, the present application also provides a water quality monitoring device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the computer program is executed by the processor, the steps of the water quality monitoring method for the water dispenser as mentioned above are implemented.

[0014] To achieve the above objectives, the present application also provides a water dispenser, comprising the water quality monitoring device as described above.

[0015] To achieve the above objectives, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the water quality monitoring method for the water dispenser are implemented as described above.

[0016] The water quality monitoring method, water quality monitoring device, water dispenser and computer-readable storage medium provided in the present application can provide multi-dimensional water quality parameters by simultaneously monitoring conductivity, spectral data and current temperature through a data acquisition module, and use the current temperature to compensate for conductivity to ensure that the calculation of TDS concentration is more accurate, while achieving accurate prediction of microbial content. The comprehensive water quality index obtained on this basis can accurately reflect the water quality status of the water dispenser, which not only improves the accuracy and reliability of water quality assessment, but also enhances the user's confidence in drinking water safety and provides users with an experience of using a water dispenser. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the steps of a method for monitoring water quality of a water dispenser in one embodiment of the present application; Figure 2 Schematic diagram of the internal structure of a water quality monitoring device according to an embodiment of the present application.

[0018] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0019] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0020] In addition, if the descriptions of "first", "second", etc. are involved in this application, they are only used for descriptive purposes (such as for distinguishing the same or similar features), and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0021] Reference Figure 1 In one embodiment, the water quality monitoring method of the water dispenser includes: Step S10: Based on the data acquisition module, water quality parameters of the water dispenser are collected, wherein the water quality parameters include conductivity, spectral data and current temperature; the data acquisition module is arranged at the water inlet and / or the water outlet of the water dispenser; Step S20, temperature compensation is performed on the conductivity according to the current temperature, and the TDS concentration is calculated according to the conductivity after temperature compensation; and, a feature vector corresponding to the spectral data is extracted, and the feature vector is input into a linear regression model to predict the microbial content; Step S30: Perform weighted summation based on TDS concentration and microbial content to obtain a comprehensive water quality index corresponding to the water dispenser.

[0022] In this embodiment, the execution terminal of the embodiment may be a water quality monitoring device, or may be other equipment or devices (such as a control device) that controls the water quality monitoring device.

[0023] As shown in step S10, the data acquisition module includes a conductivity sensor, a temperature sensor and a spectrum sensor.

[0024] Conductivity sensor (such as TDS sensor): used to measure the conductivity of water to determine the concentration of dissolved ions in water. When the conductivity sensor is powered on, it will generate a small alternating current, and the conductivity of the water sample can be used to obtain information about the ion concentration in the water.

[0025] Temperature sensor: used to monitor the temperature of water in real time. You can use NTC (Negative Temperature Coefficient) thermistor or digital temperature sensor (such as DS18B20). The temperature sensor obtains the current water temperature and updates the reading regularly to ensure synchronization with the conductivity measurement time.

[0026] Spectral sensors: For example, UV-Vis spectroscopic sensors can detect spectral features in water to identify pollutants and microorganisms. Spectral sensors obtain the spectrum of water samples by emitting and receiving light of specific wavelengths.

[0027] Optionally, the data acquisition module is arranged at the water inlet and / or the water outlet of the water dispenser. The water quality parameters detected at the water inlet can be used to generate the comprehensive water quality index of the water source of the water dispenser; the water quality parameters detected at the water outlet can be used to generate the comprehensive water quality index of the water supplied by the water dispenser.

[0028] The implementation of step S10 can collect the water quality parameters of the water dispenser in real time and accurately through precise sensors and effective data processing. This link is the basis of the entire water quality monitoring process and lays a data foundation for subsequent temperature compensation, TDS concentration calculation and microbial prediction.

[0029] As described in step S20, the real-time conductivity and current temperature are obtained from the data acquisition module. The conductivity is adjusted using a preset temperature compensation formula to eliminate the influence of temperature changes on the conductivity measurement results. The temperature compensation formula is as follows: ; Among them, E1 is the conductivity before temperature compensation, E2 is the conductivity after temperature compensation, T1 is the current temperature, T2 is the preset standard temperature (indicating the conventional water temperature value, which can be selected as 25°C), and α is the temperature compensation coefficient (this is a constant related to the type and characteristics of water (such as the compensation coefficients of different water quality conditions will be different accordingly, such as tap water and bottled drinking water), which can be set after obtaining the optimal value through experimental tests (such as performing linear regression analysis on the data to obtain the relationship between conductivity and temperature, and then extracting the slope from the regression equation. This slope is the temperature compensation coefficient)).

[0030] Calculate TDS concentration based on temperature-compensated conductivity: TDS=K×E2; Where K is the conversion factor, and the typical value is usually between 0.5 and 0.7, depending on the chemical composition of the water. For example, for drinking water, K≈0.5~0.65; for seawater, K≈0.75~0.9.

[0031] In the water quality monitoring method of drinking fountains, extracting feature vectors from spectral data and predicting microbial content using a linear regression model is a key step. The following is a description of one of the optional solutions for this process, including the steps of spectral data processing, feature extraction, model training and prediction: (1) Preprocessing of raw spectral data Spectral data usually contains light intensity information at multiple wavelengths, forming a spectral signal. Before extracting feature vectors, the spectral data needs to be preprocessed to improve the accuracy of subsequent analysis. Optional preprocessing steps include: Use filters (such as Savitzky-Golay filters, moving average filters, etc.) to reduce the impact of noise; Calibrate the spectral data and compare it with the spectral data of the standard sample to eliminate the systematic errors caused by equipment differences or environmental changes; The spectral data are normalized (such as min-max normalization or z-score normalization) to keep the characteristic data within a reasonable range and avoid deviations caused by different spectral intensity ranges.

[0032] (2) Feature extraction Raw data features: spectral intensity, the spectral intensity value at a specific wavelength (such as 450 nm, 550 nm, 600 nm, etc.) can be directly used.

[0033] Statistical features: Using statistical features such as mean, variance, peak value, peak width, etc. can help capture the distribution characteristics of spectral data.

[0034] Peak and trough detection: Use algorithms to detect peaks and troughs in the spectrum and extract the wavelength positions of high and low intensities and their corresponding intensities as features.

[0035] PCA (principal components analysis): reduce the dimension of spectral data and extract the main components through PCA, which can reduce the number of features and thus improve the computational efficiency and effect of the model.

[0036] Other quantitative analyses: Chemometric methods (such as PLS / GLM) were used to further extract and select important features for correlation analysis with microbial content.

[0037] (3) Feature vector construction Combine the above extracted features into a feature vector. Assume that n features are extracted from each spectrum to form a feature vector: [f1,f2,f3,…,f n ].

[0038] (4) Calling the linear regression model Model selection: Choose a tool suitable for linear regression analysis (such as the scikit-learn library in Python or the lm function in R).

[0039] Prediction of microbial content: The feature vector is input into the trained linear regression model for prediction, and the predicted microbial content can be obtained through the predicted value output by the model.

[0040] As described in step S30, the comprehensive water quality index (WQI) combines the TDS concentration and the microbial content: WQI=W1×TDS+W2×MC; Among them, W1 is the weight corresponding to TDS concentration, W2 is the weight corresponding to microbial content, MC is the microbial content, and W1+W2=1.

[0041] Optionally, weights may be chosen based on the following criteria: According to water safety standards, microbial content often has a greater impact on water quality (W2>W1 can be set); Refer to relevant drinking water standards and water quality monitoring specifications, for example, set W1=0.6 and W2=0.4.

[0042] In one embodiment, the data acquisition module simultaneously monitors conductivity, spectral data and current temperature, can provide multi-dimensional water quality parameters, and use the current temperature to compensate for conductivity, ensuring that the calculation of TDS concentration is more accurate, while achieving accurate prediction of microbial content. The comprehensive water quality index obtained on this basis can accurately reflect the water quality of the water dispenser, which not only improves the accuracy and reliability of water quality assessment, but also enhances users' confidence in drinking water safety and provides users with a better experience in using water dispensers.

[0043] In one embodiment, based on the above embodiment, before the step of extracting the feature vector corresponding to the spectral data and inputting the feature vector into the linear regression model to predict the microbial content, the step further includes: The spectral data were denoised and normalized.

[0044] In this embodiment, the data collected by the spectral sensor is used to extract features through preprocessing (such as denoising and normalization).

[0045] For example, the collected original spectral data x is: 0.2, 0.3, 0.5, 0.7, 0.8, 0.9, 0.85, 0.7, 0.4, 0.2.

[0046] Use the sliding average filter formula with window width k=1: ; Calculate the denoised spectral data: ; ; ; ; ; ; ; ; The denoised spectral data y are: 0.333, 0.5, 0.666, 0.8, 0.85, 0.816, 0.65, 0.433.

[0047] Furthermore, the denoised spectral data is normalized. Assuming that the minimum value of the spectral data is 0.2 and the maximum value is 0.9, the minimum-maximum normalization formula is used: ; Calculate the normalized spectral data: ; ; ; ; ; ; ; ; Normalized spectral data They are: 0.19, 0.428, 0.666, 0.857, 0.928, 0.88, 0.642, and 0.333.

[0048] Afterwards, features are extracted from the normalized spectral data: Peak position: The fifth data point, corresponding to a specific wavelength value; Peak intensity: 0.928; Half-peak width: Assume the half-peak width is 0.4; Feature vector [f1,f2,f3]=[5,0.928,0.4].

[0049] Through denoising and normalization processing, the quality of spectral data can be effectively improved, laying a solid foundation for subsequent feature extraction and microbial content prediction.

[0050] In one embodiment, based on the above embodiment, before the step of extracting the feature vector corresponding to the spectral data and inputting the feature vector into the linear regression model to predict the microbial content, the step further includes: Based on the training data set, a linear regression model is constructed; The training data set includes microbial contents corresponding to feature vectors of multiple samples.

[0051] In this embodiment, during the data preparation process, it is assumed that there is the following training data set: each row represents a feature vector [f1, f2, f3] of a sample and the corresponding microbial content MC; It is assumed that there is a linear relationship between the microbial content MC and the feature vector [f1, f2, f3]; Then you can have the following training data set including multiple samples: ; Assume that there is a linear relationship between the microbial content MC and the feature vector [f1,f2,f3]: .

[0052] Choose the least squares method as the loss function: ; Use the normal equation to solve for the parameters ω and b. The normal equation formula is: ; Among them, X is a matrix containing the features of all training samples, and Y is a vector containing the labels of all training samples.

[0053] ; ; The bias term b is considered as a column of constant terms 1 in the feature matrix X.

[0054] First, calculate and : ; = ; Next, calculate : ; Finally, calculate the parameters get: ; Therefore, the parameters of the linear regression model are: ω=[17.5,150,-82.5], b=-30.

[0055] Input the feature vector [5, 0.928, 0.4] into the linear regression model to predict the microbial content: MC=17.5×5+150×0.928-82.5×0.4-30=163.7.

[0056] Through the above steps, the constructed linear regression model can effectively estimate the microbial content and provide support for further water quality monitoring and management.

[0057] In one embodiment, based on the above embodiment, before the step of performing weighted summation based on TDS concentration and microbial content to obtain the comprehensive water quality index corresponding to the water dispenser, the step further includes: The TDS concentration and microbial content were standardized.

[0058] In this embodiment, before executing step S30, the TDS concentration and the microbial content may be standardized to ensure that they are on the same scale. This can usually be standardized using the following formula: TDS concentration standardization: ; Microbiological Standardization: ; Among them, TDS min 、TDS max are the minimum and maximum TDS concentrations observed during monitoring; MC min , MC max They are the minimum and maximum values ​​of microbial content observed during monitoring.

[0059] The normalized values ​​are then used to update the TDS concentration and microbial content (MC) values.

[0060] Through standardization, the data of TDS concentration and microbial content are unified, making the subsequent weighted summation more reasonable, and the comprehensive water quality index provides a quantitative basis for water quality monitoring and management.

[0061] For example: The data acquisition module collects conductivity, current temperature and spectrum data at the water inlet and outlet. For example, the inlet water conductivity is 500 μS / cm, the outlet water conductivity is 50 μS / cm, and the temperature is 30°C.

[0062] After temperature compensation of the electrokinetic efficiency, the calculated TDS concentration is: 335 ppm for the inlet water and 33.5 ppm for the outlet water.

[0063] The pre-trained linear regression model was used to predict the microbial content, assuming the inlet was 163.7 and the effluent was 10. TDS concentration and microbial content were normalized, assuming the reference range was 10-500 ppm and 0-500, respectively.

[0064] Standardized TDS concentration and microbial content of influent: ; ; Standardized TDS concentration and microbial content of effluent: ; ; At this time, if W1=0.6 and W2=0.4 are set, the comprehensive water quality index of the inlet water is calculated as: ; The comprehensive water quality index of the effluent is calculated as: .

[0065] In this way, the comprehensive water quality index corresponding to the water inlet and outlet of the water dispenser can be calculated respectively.

[0066] In one embodiment, based on the above embodiment, after the step of performing weighted summation based on TDS concentration and microbial content to obtain the comprehensive water quality index corresponding to the water dispenser, the step further includes: Check whether the comprehensive water quality index meets the preset standards; If not, an alarm will be issued.

[0067] In this embodiment, the preset standard of the comprehensive water quality index is set according to the relevant water quality standards and actual needs. For example: Safety standard: A comprehensive water quality index below or less than a certain threshold (such as 0.04) indicates that the water quality is safe.

[0068] Danger standard: When the comprehensive water quality index is higher than a certain threshold (such as 0.04), it means that there is a risk in water quality.

[0069] The calculated comprehensive water quality index is compared with the preset standard. If the comprehensive water quality index is less than or equal to the preset standard, no alarm is required.

[0070] If the comprehensive water quality index is greater than the preset standard, an alarm will be triggered. The alarm mechanism can include the following methods: Visual warning: A red warning sign or text prompt is displayed on the display screen of the water dispenser.

[0071] Audible alarm: The alarm sounds through the built-in speaker.

[0072] Remote alarm: Send alarm information to the administrator's mobile phone or computer through the network, or upload the alarm information to the cloud platform simultaneously, so that users can understand the water quality status in time through remote monitoring.

[0073] The alarm prompt may include the following information: display the current comprehensive water quality index value, the reason for non-compliance with the standard, and recommended measures (providing possible solutions, such as replacing the filter element, performing water quality treatment, etc.).

[0074] Through the above steps, the water quality monitoring method of the water dispenser can not only calculate the comprehensive water quality index, but also detect in real time whether the index meets the preset standard, and issue an alarm in time when it does not meet the standard. This helps to ensure drinking water safety, take timely measures, and protect the health of users.

[0075] In one embodiment, based on the above embodiment, after the step of performing weighted summation based on TDS concentration and microbial content to obtain the comprehensive water quality index corresponding to the water dispenser, the step further includes: The output displays the water quality parameters, TDS concentration, microbial content and comprehensive water quality index corresponding to the water dispenser.

[0076] In this embodiment, in order to enable users to clearly understand the water quality information, a standard output format can be set, which usually includes the following contents: Conductivity, spectral data, current temperature, TDS concentration, microbial content, comprehensive water quality index.

[0077] The water quality information can be output to a display screen of the water dispenser (ie, the water dispenser can have a data display module), or displayed on a user-associated terminal device, so that the user can check the water quality at any time.

[0078] In one embodiment, based on the above embodiment, after the step of performing weighted summation based on TDS concentration and microbial content to obtain the comprehensive water quality index corresponding to the water dispenser, the step further includes: The water quality parameters, TDS concentration, microbial content and comprehensive water quality index corresponding to the water dispenser are uploaded to the cloud platform so that the cloud platform can generate a water quality report corresponding to the water dispenser.

[0079] In this embodiment, the water dispenser may be provided with a network communication module (such as a WiFi module), through which the water quality parameters, TDS concentration, microbial content and comprehensive water quality index corresponding to the water dispenser may be uploaded to the cloud platform.

[0080] After receiving the data, the cloud platform performs data storage and preliminary analysis to identify outliers or patterns.

[0081] Optionally, the cloud platform can perform big data analysis based on the above data to generate water quality reports and historical data comparisons.

[0082] The cloud platform can clean the collected data, remove duplicates and outliers, and ensure data quality. It can also analyze the trends of historical water quality data to identify the patterns of water quality changes over time, such as seasonal changes. It can then compare current water quality parameters with historical data to generate comparison charts to help users understand water quality changes.

[0083] Furthermore, based on the analysis results, a water quality report including trend charts, abnormal prompts and comparative analysis is automatically generated and provided to users and managers.

[0084] Optionally, the generated water quality report can be automatically sent to users and relevant managers via email or application notification.

[0085] Through the above steps, the water quality monitoring data of the water dispenser can be effectively uploaded to the cloud platform, and then a detailed water quality report can be generated. This will help users understand the changes in water quality in real time and ensure the safety of drinking water.

[0086] In some optional embodiments, the cloud platform can also introduce machine learning models to analyze historical data in order to generate more accurate water quality reports.

[0087] First, ensure that there is sufficient historical water quality data, including parameters such as conductivity, spectral data, temperature, etc., which will be used to train the machine learning model. Then integrate the data collected at different time points to form a unified data set.

[0088] Remove outliers and missing values ​​to ensure the quality of training data. Process raw data into features that can be understood by machine learning models, such as standardization, normalization, category encoding, etc.

[0089] If the goal is to identify whether the water quality meets the standard (classification problem), you can choose classification models such as logistic regression, support vector machine (SVM), random forest or XGBoost; if the goal is to predict specific values ​​(such as TDS concentration or microbial content), you can choose regression models such as linear regression, decision tree, random forest or neural network.

[0090] The dataset is divided into training set and test set for model training and evaluation.

[0091] Optionally, use Grid Search or Random Search to find the best hyperparameters for the model. Evaluate the performance of the model on different subsets through cross-validation and select the optimal parameter combination.

[0092] Optionally, use tools such as SHAP (SHapley Additive exPlanations) to interpret the model prediction results and understand the contribution of each feature to water quality prediction. Verify the performance of the model through the test set to ensure its accuracy in practical applications.

[0093] Then, the real-time data of the water dispenser is input into the trained model to predict the water quality, and the prediction results are pushed to users and relevant managers in real time.

[0094] Among them, a detailed water quality report is generated based on the real-time prediction results, which may include the following: Real-time water quality parameter values; Predicted values ​​of TDS concentration and microbial content; Comprehensive water quality index and its assessment; Analysis of water quality change trends; Advice and warnings to predict future water quality.

[0095] Optionally, deploy the trained model on a cloud platform to ensure that it can run stably and process real-time data from the water dispenser.

[0096] Optionally, the data collection module, data upload mechanism, model prediction and report generation module are integrated to form a complete system.

[0097] Optionally, update and retrain the model periodically as new data accumulates to ensure the accuracy of its predictions.

[0098] By introducing machine learning models to analyze and predict historical data, the accuracy and intelligence of the water quality monitoring system of water dispensers can be significantly improved. This not only helps users understand water quality changes in real time, but also predicts future trends and provides more comprehensive water quality assurance.

[0099] In addition, a water quality monitoring device is also provided in the embodiment of the present application. The internal structure of the water quality monitoring device can be as follows: Figure 2 As shown, it includes a processor, a memory, a communication interface and an input interface connected by a system bus. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database is used to store data called by the computer program. The communication interface is used to communicate data with an external terminal. The input interface is used to receive a signal input by an external device. When the computer program is executed by the processor, a water quality monitoring method for a water dispenser as described in the above embodiment is implemented.

[0100] Those skilled in the art will understand that Figure 2 The structure shown in the figure is only a block diagram of a part of the structure related to the present application scheme, and does not constitute a limitation on the water quality monitoring device to which the present application scheme is applied. For example, in some optional embodiments, the water quality monitoring device may also include an output interface (not shown in the figure), and the output interface is also connected to the system bus and is used to output corresponding signals to the peripheral device.

[0101] In addition, the present application further proposes a water drinking machine, which includes a water quality monitoring device. The specific structure of the water quality monitoring device refers to the above-mentioned embodiments. Since the present water drinking machine adopts all the technical solutions of all the above-mentioned embodiments, it has at least all the technical effects brought by the technical solutions of the above-mentioned embodiments, which will not be described one by one here.

[0102] In addition, the present application also proposes a computer-readable storage medium, the computer-readable storage medium includes a computer program, and when the computer program is executed by a processor, the steps of the water quality monitoring method of the water dispenser as described in the above embodiment are implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0103] In summary, the water quality monitoring method, water quality monitoring device, water dispenser and computer-readable storage medium provided in the embodiments of the present application can provide multi-dimensional water quality parameters by simultaneously monitoring conductivity, spectral data and current temperature through the data acquisition module, and use the current temperature to compensate for conductivity to ensure that the calculation of TDS concentration is more accurate and realize accurate prediction of microbial content. The comprehensive water quality index obtained on this basis can accurately reflect the water quality status of the water dispenser, which not only improves the accuracy and reliability of water quality assessment, but also enhances the user's confidence in drinking water safety and provides users with an experience of using a water dispenser.

[0104] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0105] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0106] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A method for monitoring water quality of a water dispenser, characterized in that: include: Based on the data acquisition module, water quality parameters of the water dispenser are collected, wherein the water quality parameters include conductivity, spectral data and current temperature; The data acquisition module is arranged at the water inlet and / or the water outlet of the water dispenser; Conducting temperature compensation on the conductivity according to the current temperature and calculating the TDS concentration according to the temperature-compensated conductivity; and extracting the characteristic vector corresponding to the spectral data and inputting the characteristic vector into a linear regression model to predict the microbial content; Based on the weighted sum of TDS concentration and microbial content, the comprehensive water quality index corresponding to the water dispenser is obtained.

2. The water quality monitoring method of a water dispenser as claimed in claim 1, characterized in that: Before the step of extracting the characteristic vector corresponding to the spectral data and inputting the characteristic vector into the linear regression model to predict the microbial content, the method further includes: The spectral data were denoised and normalized.

3. The water quality monitoring method of a water dispenser according to claim 1, characterized in that: Before the step of extracting the characteristic vector corresponding to the spectral data and inputting the characteristic vector into the linear regression model to predict the microbial content, the method further includes: Based on the training data set, a linear regression model is constructed; The training data set includes microbial contents corresponding to feature vectors of multiple samples.

4. The water quality monitoring method of a water dispenser according to claim 1, characterized in that: Before the step of performing weighted summation based on TDS concentration and microbial content to obtain a comprehensive water quality index corresponding to the water dispenser, the method further includes: The TDS concentration and microbial content were standardized.

5. The water quality monitoring method of a water dispenser according to any one of claims 1 to 4, characterized in that: After the step of performing weighted summation based on TDS concentration and microbial content to obtain a comprehensive water quality index corresponding to the water dispenser, the method further includes: Check whether the comprehensive water quality index meets the preset standards; If not, an alarm will be issued.

6. The water quality monitoring method of a water dispenser according to any one of claims 1 to 4, characterized in that: After the step of performing weighted summation based on TDS concentration and microbial content to obtain a comprehensive water quality index corresponding to the water dispenser, the method further includes: The output displays the water quality parameters, TDS concentration, microbial content and comprehensive water quality index corresponding to the water dispenser.

7. The water quality monitoring method of a water dispenser according to any one of claims 1 to 4, characterized in that: After the step of performing weighted summation based on TDS concentration and microbial content to obtain a comprehensive water quality index corresponding to the water dispenser, the method further includes: The water quality parameters, TDS concentration, microbial content and comprehensive water quality index corresponding to the water dispenser are uploaded to the cloud platform so that the cloud platform can generate a water quality report corresponding to the water dispenser.

8. A water quality monitoring device, characterized in that: The water quality monitoring device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the computer program is executed by the processor, the steps of the water quality monitoring method for a drinking fountain as described in any one of claims 1 to 7 are implemented.

9. A water dispenser, characterized in that: Comprising the water quality monitoring device as described in claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the water quality monitoring method for a water dispenser according to any one of claims 1 to 7 are implemented.

Images