Water purifier cleaning control method, device and equipment and storage medium
By collecting and processing the water level data of the water purifier, the cleaning time of the water purifier is dynamically determined, which solves the problem of unreasonable cleaning frequency in the prior art, and realizes a water purifier cleaning solution that is more suitable for users' water use habits.
Patent Information
- Application Number
- CN202411881977.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-19
- Publication Date
- 2025-04-01
AI Technical Summary
The existing water purifier cleaning methods are based on fixed time intervals, resulting in unreasonable cleaning frequency and inability to adapt to the water use habits of different users, which may lead to bacterial growth or waste of resources.
By collecting the water level sampling value of the water purifier, using the Kalman filtering algorithm for smoothing and interpolation processing, the water consumption state is determined, and the pre-trained prediction model is used to predict the future water consumption state, and the cleaning time of the water purifier is dynamically determined.
It realizes dynamically adjusting the cleaning time of the water purifier according to the user's water use habits, ensuring the cleaning frequency of the water purifier is reasonable, and avoiding bacterial growth and resource waste.
Smart Images
Figure CN119739060A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of Internet of Things, and in particular to a water purifier cleaning control method, device, equipment and storage medium. Background Art
[0002] With the improvement of people's living standards and the enhancement of health awareness, water purifiers used to provide healthy drinking water have been widely used in users' lives as a household appliance. In order to ensure that the water purifier can provide uncontaminated purified water, it is necessary to clean the water purifier every once in a while during its use. If the water purifier is not cleaned for a long time, bacteria will grow inside the water purifier, affecting the water quality, thus posing a potential threat to the health of users.
[0003] At present, the cleaning of water purifiers is mostly triggered based on fixed time intervals. However, different users have different water usage habits, resulting in different usage frequencies of water purifiers, which in turn causes different actual cleaning intervals for water purifiers. If the water purifier is cleaned at fixed time intervals, the cleaning frequency of the water purifier will be unreasonable. For example: For users with high frequency of use, bacteria may have begun to breed inside the water purifier, but the cleaning time has not yet arrived. If the water purifier is not cleaned in time, it will affect the user's health. Another example: For users with low frequency of use, fixed time intervals seem to be too frequent for cleaning, which wastes resources and affects the user experience. Summary of the invention
[0004] The present application provides a water purifier cleaning control method, device, equipment and storage medium to solve the problem of unreasonable cleaning frequency of the water purifier caused by cleaning the water purifier at fixed time intervals.
[0005] In view of the above technical problems, the technical solution of this application is solved by the following embodiments:
[0006] An embodiment of the present application provides a water purifier cleaning control method, comprising: collecting a water level sampling value of the water purifier once at a preset sampling interval and calibrating each of the collected water level sampling values to obtain a plurality of water level calibration values with consecutive sampling times; determining the water consumption state corresponding to each of the sampling times according to the plurality of water level calibration values with consecutive sampling times; using a pre-trained prediction model to determine the water consumption state corresponding to each of the sampling times in a future time period according to the water consumption state corresponding to each of the sampling times; determining the cleaning time of the water purifier in the future time period according to the water consumption state corresponding to each of the sampling times in the future time period, and controlling the water purifier to perform a cleaning operation when the cleaning time arrives.
[0007] Among them, the calibration of each water level sampling value collected includes: for each water level sampling value collected, using a preset Kalman filtering algorithm, smoothing the water level sampling value to obtain a water level smoothed value; according to the sampling time corresponding to each water level smoothed value, performing interpolation processing on each water level smoothed value to obtain multiple water level calibration values with continuous sampling time.
[0008] Among them, for each water level sampling value collected, a preset Kalman filtering algorithm is used to smooth the water level sampling value to obtain a water level smoothing value, including: initializing a state transfer matrix, an observation matrix, a state transfer matrix variance, an observation matrix variance and a covariance; obtaining a preset sampling error; and, in order of sampling time from first to last, performing the following processing on each water level sampling value in sequence: predicting the water level prediction value corresponding to the next sampling time according to the state transfer matrix, the water level sampling value and the sampling error; predicting the water level prediction value corresponding to the next sampling time according to the state transfer matrix, the water level sampling value and the sampling error; and The covariance is updated by using the state transfer matrix, the covariance, and the state transfer matrix variance; the Kalman filter gain is determined by using the updated covariance, the observation matrix, and the observation matrix variance; the water level smoothing value corresponding to the water level sampling value is determined according to the Kalman filter gain, the water level sampling value, and the water level prediction value; and, according to the Kalman filter gain, the observation matrix and the updated covariance, the updated covariance is updated; and, according to the water level smoothing value, the state transfer matrix variance and the observation matrix variance and covariance are updated.
[0009] Among them, according to the sampling time corresponding to each of the water level smoothing values, interpolation processing is performed on each of the water level smoothing values to obtain a plurality of water level calibration values with continuous sampling time, including: identifying the sampling time of the missing data point according to the sampling time corresponding to each of the water level smoothing values; among each of the water level smoothing values, determining the water level smoothing value corresponding to the sampling time of the missing data point according to the water level smoothing value corresponding to the previous sampling time and the water level smoothing value corresponding to the next sampling time of the sampling time of the missing data point, to obtain a plurality of water level calibration values with continuous sampling time.
[0010] Among them, the water consumption state corresponding to each sampling time is determined based on multiple continuous water level calibration values at the sampling time, including: for each sampling time, taking the sampling time as a reference, determining the difference between the water level calibration value corresponding to the sampling time and the water level calibration value before a preset time length; if the absolute value of the difference is greater than a preset water consumption threshold, determining that the water consumption state corresponding to the sampling time is the first state; otherwise, determining that the water consumption state corresponding to the sampling time is the second state.
[0011] Wherein, determining the cleaning time of the water purifier in the future time period according to the water consumption status corresponding to each sampling time in the future time period includes: determining the peak water consumption period in the future time period according to the water consumption status corresponding to each sampling time in the future time period; wherein the peak water consumption period is a plurality of continuous sampling times whose number is greater than a preset number threshold and whose water consumption status is all in the first state; determining a discrete time period whose time length is greater than the cleaning time length of the water purifier in each discrete time period after excluding the peak water consumption time period in the future time period, and using the determined start time of the discrete time period as the cleaning time.
[0012] Among them, the determining of a discrete time period whose time length is greater than the cleaning time length of the water purifier includes: determining a discrete time period before the peak water consumption period among each of the discrete time periods; or determining a discrete time period before the peak water consumption period and in which the water consumption state corresponding to each sampling time is the second state.
[0013] The embodiment of the present application also provides a water purifier cleaning control device, including: a data processing module, which is used to collect the water level sampling value of the water purifier once at a preset sampling interval and calibrate each of the collected water level sampling values to obtain a plurality of water level calibration values with continuous sampling time; a first determination module, which is used to determine the water consumption state corresponding to each of the sampling times according to the plurality of water level calibration values with continuous sampling time; a second determination module, which is used to determine the water consumption state corresponding to each of the sampling times in a future time period according to the water consumption state corresponding to each of the sampling times using a pre-trained prediction model; and a cleaning control module, which is used to determine the cleaning time of the water purifier in the future time period according to the water consumption state corresponding to each of the sampling times in the future time period, and control the water purifier to perform a cleaning operation when the cleaning time arrives.
[0014] An embodiment of the present application also provides a water purifier cleaning control device, comprising: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; at least one memory connected to the at least one bus, wherein the processor is configured to: execute the water purifier cleaning control program stored in the memory to implement any of the water purifier cleaning control methods described above.
[0015] An embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. The computer-executable instructions are executed to implement any of the water purifier cleaning control methods described above.
[0016] The above-mentioned technical scheme provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application can collect the water level sampling value of the water purifier once at a preset sampling interval and calibrate each of the collected water level sampling values to obtain a plurality of water level calibration values with continuous sampling time; determine the water consumption state corresponding to each of the sampling times according to the plurality of water level calibration values with continuous sampling time; utilize a pre-trained prediction model to determine the water consumption state corresponding to each of the sampling times in a future time period according to the water consumption state corresponding to each of the sampling times; determine the cleaning time of the water purifier in the future time period according to the water consumption state corresponding to each of the sampling times in the future time period, and control the water purifier to perform a cleaning operation when the cleaning time arrives. The embodiment of the present application does not use a fixed time interval to clean the water purifier, but detects the water level change of the water purifier and determines the cleaning time of the water purifier according to the water consumption status of the user at each sampling time. In other words, the cleaning time of the water purifier is not fixed, but is determined according to the water consumption status of the user at each sampling time, so that the cleaning of the water purifier is more in line with the actual situation of the water purifier itself, and the cleaning frequency is more reasonable. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0019] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.
[0020] Figure 1 This is a flow chart of a water purifier cleaning control method according to an embodiment of the present application;
[0021] Figure 2 is a flow chart of the steps of smoothing processing according to an embodiment of the present application;
[0022] Figure 3 This is a structural diagram of a water purifier cleaning control device according to an embodiment of the present application;
[0023] Figure 4 It is a structural diagram of a water purifier cleaning control device according to an embodiment of the present application. DETAILED DESCRIPTION
[0024] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0025] The disclosure below provides many different embodiments or examples to realize the different structures of the present application. In order to simplify the disclosure of the present application, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.
[0026] The present application embodiment provides a water purifier cleaning control method. Figure 1 Shown is a flow chart of a water purifier cleaning control method according to an embodiment of the present application.
[0027] Step S110, collecting a water level sampling value of the water purifier once at a preset sampling interval and calibrating each of the collected water level sampling values to obtain a plurality of water level calibration values with continuous sampling time.
[0028] The sampling interval refers to the time interval between two consecutive water level sampling values of the water purifier. The sampling interval can be an empirical value or a value obtained through experiments. For example, if the sampling interval is 1 second, it means that a water level sampling value is collected every 1 second.
[0029] The water level sampling value refers to the original water level value. Further, the water level sensor can be used to collect the water level collection value of the water purifier.
[0030] The water level calibration value refers to the calibrated water level value. Furthermore, since the water level sampling value may be noisy or missing, the calibration of each collected water level sampling value is used to compensate for the noise or missing problem of each water level sampling value, so that there is a water level value at each sampling time, there is no missing data point, and the water level value corresponding to each sampling time is smoothed to avoid the noise of the water level value affecting the subsequent judgment.
[0031] Step S120, determining the water consumption state corresponding to each of the sampling times according to a plurality of continuous water level calibration values at the sampling times.
[0032] The water consumption status is used to indicate whether the water consumption within a preset time length with the sampling time as the end point exceeds a preset water consumption threshold.
[0033] The duration can measure the amount of water used in a period of time. Generally speaking, when a user uses water, it does not happen at just one moment, but for a period of time. For example, the duration can be 1 minute.
[0034] The water consumption threshold may be an empirical value or a value obtained through experiments.
[0035] The types of water consumption states include: a first state and a second state. The first state refers to the water consumption within the preset time length being greater than the water consumption threshold. The second state refers to the water consumption within the preset time length being less than or equal to the water consumption threshold.
[0036] Step S130, using the pre-trained prediction model, according to the water consumption status corresponding to each of the sampling times, determine the water consumption status corresponding to each of the sampling times in the future time period.
[0037] The prediction model refers to a model that, after training, can predict the water consumption status corresponding to each sampling time in a future time period based on the water consumption status corresponding to each sampling time in a historical time period.
[0038] The historical time period refers to the time period during which the water level sampling values of the water purifier are collected in the embodiment of the present application. For example, the historical time period is from 0:00 to 24:00 today.
[0039] The future time period refers to the time period that has not yet arrived. The length of the historical time period is equal to the length of the future time period. For example, the future time period is from 0:00 to 24:00 tomorrow.
[0040] Step S140, determining the cleaning time of the water purifier in the future time period according to the water consumption status corresponding to each sampling time in the future time period, and controlling the water purifier to perform a cleaning operation when the cleaning time arrives.
[0041] According to the water consumption status corresponding to each sampling time in the future time period, the time period in which the water consumption is less than the preset idle water consumption threshold is determined, and the start time of the time period is determined as the cleaning time of the water purifier in the future time period.
[0042] In the embodiment of the present application, the water level sampling value of the water purifier is collected once at every preset sampling interval and each of the collected water level sampling values is calibrated to obtain a plurality of water level calibration values with continuous sampling time; the water consumption state corresponding to each of the sampling times is determined according to the plurality of water level calibration values with continuous sampling time; the water consumption state corresponding to each of the sampling times in the future time period is determined according to the water consumption state corresponding to each of the sampling times by using the pre-trained prediction model; the cleaning time of the water purifier in the future time period is determined according to the water consumption state corresponding to each of the sampling times in the future time period, and the water purifier is controlled to perform the cleaning operation when the cleaning time arrives. The embodiment of the present application does not use a fixed time interval to clean the water purifier, but detects the water level change of the water purifier, and determines the cleaning time of the water purifier according to the water consumption state of the user at each sampling time, that is, the cleaning time of the water purifier is not fixed, but is determined according to the water consumption state of the user at each sampling time, so that the cleaning of the water purifier is more in line with the actual situation of the water purifier itself, and the cleaning frequency is more reasonable.
[0043] In order to make the embodiment of the present application easier to understand, the water purifier cleaning control method of the embodiment of the present application will be further described below.
[0044] In an embodiment of the present application, a water level sensor may be built into the water purifier, and the water level sampling value of the water purifier may be collected once every preset sampling interval using the water level sensor.
[0045] In an embodiment of the present application, in order to avoid the problem of noise and anomalies in the water level sampling values detected by the water level sensor and to avoid the problem of missing water level sampling values, the collected water level sampling values can be calibrated to obtain multiple water level calibration values with continuous sampling time.
[0046] In order to avoid the problem of noise and anomalies in the water level sampling values, the water level sampling values collected each time may be smoothed using a preset Kalman filter algorithm to obtain water level smoothed values.
[0047] Furthermore, the state transfer matrix, observation matrix, state transfer matrix variance, observation matrix variance and covariance are initialized; a preset sampling error is obtained; and, using the state transfer matrix, observation matrix, state transfer matrix variance, observation matrix variance, covariance and sampling error, smoothing is performed on each of the water level sampling values in order from sampling time to obtain a water level smoothing value corresponding to the water level sampling value.
[0048] The state transfer matrix is used to represent the theoretical relationship between the current water level sampling value and the next water level sampling value.
[0049] The observation matrix is used to represent the true relationship between the current water level sampling value and the next water level sampling value. Since the water level sampling values at two adjacent sampling times will not change significantly, the state transfer matrix and the observation matrix of the embodiment of the present application can be set to 1.
[0050] The state transition matrix variance represents the overall variance of the water level prediction values.
[0051] The observation matrix variance represents the overall variance of the water level sampling values.
[0052] Covariance is used to control the water level smoothing value to lean towards the water level sampling value or the water level theoretical value. Among them, if the covariance is large, the water level smoothing value is more inclined to the water level sampling value, and if the covariance is small, the water level prediction value is more inclined to the water level theoretical value (that is, in theory the water level will not change significantly). The embodiment of the present application involves a water purifier scenario. The theoretical data is not as accurate as the actual data and has a high uncertainty, so the Kalman filter uses a larger covariance. For example: the initial value of the covariance is 1, and it is continuously updated iteratively in the future.
[0053] Sampling error refers to the change in value caused by water level jitter or water usage within each sampling interval.
[0054] According to the sampling time from the earliest to the latest, perform the following for each water level sampling value: Figure 2 Steps shown. Figure 2 FIG. 4 is a flow chart of smoothing steps according to an embodiment of the present application.
[0055] Step S210: predicting a water level prediction value corresponding to a next sampling time according to the state transfer matrix, the water level sampling value and the sampling error.
[0056] For example, the following formula can be used to predict the water level prediction value corresponding to the next sampling time:
[0057] X i+1 =A×x i -D; where X i+1 is the water level prediction value corresponding to the next sampling time, that is, the i+1th water level prediction value; A is the preset state transfer matrix; x i is the water level sampling value corresponding to the current sampling time, that is, the i-th water level sampling value; D is the preset sampling error.
[0058] Step S220: updating the covariance according to the state transfer matrix, the covariance, and the state transfer matrix variance.
[0059] For example, the covariance can be updated using the following formula:
[0060] P ′=A×A×P+Q; where P ′ is the updated covariance; A is the state transfer matrix; P is the current covariance; Q is the state transfer matrix variance.
[0061] State transfer matrix variance Among them, X i is the predicted value of the i-th water level; μ1 is the distance from X1 to X i The population mean of ; n is the number of water level prediction values. The first water level prediction value is the first water level sampling value, and starting from the second water level prediction value, the water level prediction value is X i+1 =A×x i -D.
[0062] Step S230, determining the Kalman filter gain using the updated covariance, the observation matrix, and the observation matrix variance.
[0063] For example, the Kalman filter gain can be determined using the following formula:
[0064] G=P ′ ×H / (P′×H×H+R);
[0065] Where G is the Kalman filter gain; P ′ is the updated covariance; H is the preset measurement matrix; R is the measurement matrix variance.
[0066] Observation matrix variance Among them, x i is the i-th water level sampling value; μ2 is from x to x i The total mean of ; n is the number of water level sampling values. The number of water level prediction values is consistent with the number of water level sampling values.
[0067] Step S240, determining the water level smoothing value corresponding to the water level sampling value according to the Kalman filter gain, the water level sampling value and the water level prediction value.
[0068] For example, the following formula can be used to determine the water level smoothing value corresponding to the water level sampling value:
[0069] X_filter i =X i +(x i -X i )×G; where X_filter i is the i-th water level smoothing value; X i is the predicted value of the i+1th water level; x i is the i-th water level sampling value; G is the Kalman filter gain.
[0070] Step S250, updating the updated covariance according to the Kalman filter gain, the observation matrix and the updated covariance; and updating the state transfer matrix variance and the observation matrix variance and covariance according to the water level smoothing value.
[0071] For example: Use the following formula to update the covariance again:
[0072] P″=(1-G×H)×P′; where P″ is the covariance after being updated again, that is, P when the water level smoothing value is calculated next time; G is the Kalman filter gain; H is the observation matrix; P′ is the updated covariance.
[0073] By performing Kalman filtering on the water level sampling values, the noise and outliers in the water level sampling values can be removed to obtain a smooth water level value.
[0074] In order to avoid the problem that the water level sensor fails and the water level sampling values cannot be collected at some sampling times, interpolation processing can be performed on each water level smoothing value according to the sampling time corresponding to each water level smoothing value to obtain multiple water level calibration values with continuous sampling time.
[0075] Specifically, the sampling time of the missing data point can be identified according to the sampling time corresponding to each of the water level smoothing values; among the water level smoothing values, the water level smoothing value corresponding to the sampling time before the sampling time of the missing data point and the water level smoothing value corresponding to the sampling time after the sampling time are determined to obtain a plurality of water level calibration values with continuous sampling times.
[0076] Continuous sampling time means that the time difference between two adjacent sampling times is the sampling interval.
[0077] The sampling time of a missing data point refers to the time difference between two adjacent sampling times that is greater than the sampling interval, and there is a sampling time of a missing data point between the two adjacent sampling times. The sampling time of a missing data point is the missing sampling time.
[0078] The sampling times corresponding to the water level smoothing values can be sorted in order from the earliest sampling time to the latest sampling time to obtain a sampling time series; the missing sampling time can be identified in the sampling time series according to the sampling interval; the previous sampling time and the next sampling time of the missing sampling time in the sampling time series are determined; the average values of the water level smoothing value corresponding to the previous sampling time and the water level smoothing value corresponding to the next sampling time are calculated; the average value is used as the water level smoothing value corresponding to the missing sampling time; the water level smoothing value corresponding to the missing sampling time is added to the various water level smoothing values obtained by smoothing to supplement the water level smoothing values corresponding to the missing sampling time in the various water level smoothing values obtained by smoothing. After supplementation, the calibration of each water level sampling value is completed, and each water level smoothing value can be used as a water level calibration value, thereby obtaining a plurality of water level calibration values with continuous sampling times, so that each water level calibration value has continuity and integrity.
[0079] In the embodiment of the present application, after obtaining a plurality of water level calibration values at consecutive sampling times, the water consumption status corresponding to each sampling time can be determined.
[0080] Specifically, for each sampling time, the difference between the water level calibration value corresponding to the sampling time and the water level calibration value before a preset time length can be determined based on the sampling time; if the difference is greater than the preset water consumption threshold, the water consumption state corresponding to the sampling time is determined to be the first state; otherwise, the water consumption state corresponding to the sampling time is determined to be the second state.
[0081] The difference represents the amount of water used over a preset length of time.
[0082] The first state indicates that the water consumption within the preset time length is greater than the water consumption threshold. The water consumption state corresponding to the sampling time is the first state, which means that the user has obvious water consumption behavior.
[0083] The second state indicates that the water consumption within the preset time length is less than or equal to the water consumption threshold. The water consumption state corresponding to the sampling time is the second state, which means that even if the user has water consumption behavior, the water consumption is small and can be ignored.
[0084] For example: the preset time length is 1 minute, and the current sampling time is 10 o'clock, then the difference between the water level calibration value corresponding to 10 o'clock and the water level calibration value corresponding to 9:59 is calculated, and the absolute value of the difference is compared with the water consumption. If the absolute value of the difference is greater than the water consumption threshold, the water consumption state corresponding to 10 o'clock is determined to be the first state; otherwise, the water consumption state corresponding to 10 o'clock is determined to be the second state.
[0085] Further, the first state can be represented by a first preset value, and the second state can be represented by a second preset value. For example, the first preset value is 1, and the second preset value is 0.
[0086] In an embodiment of the present application, when determining the water consumption status corresponding to each of the sampling times, the water consumption status corresponding to each of the sampling times can be input into a pre-trained prediction model, and the water consumption status corresponding to each of the sampling times in the future time period output by the prediction model can be obtained.
[0087] After the prediction model is trained, it can be used to predict the water consumption status corresponding to each sampling time in the future time period based on the water consumption status corresponding to each sampling time in the historical time period.
[0088] Furthermore, the prediction model may be a neural network model. When training the prediction model, the following steps may be performed:
[0089] Data preparation: Segment the processed water level data to construct training data sets and test data sets. The water level data includes each sampling time and the water level sampling value corresponding to each sampling time. For example, it can be segmented by day, with the water level data of the first 10 days as the training data set and the water level data of the last 10 days as the test data set. In the water level data of the first 10 days and the water level data of the last 10 days, the water level data of the first day can be used as a training sample, and the water level data of the last day can be used as the true value.
[0090] Model construction: Select a suitable neural network structure and build a neural network model.
[0091] Model training: Use the training data set to train the prediction model, and use the cross-validation method to evaluate the model performance to prevent overfitting.
[0092] Model optimization: Adjust the structure and parameters of the prediction model according to the training results to improve the prediction accuracy of the prediction model.
[0093] Performance optimization: After the prediction model is trained, the performance of the prediction model is evaluated using the test data set. For example, the performance of the prediction model is evaluated by accuracy, recall, and F1 score.
[0094] In an embodiment of the present application, after determining the water consumption status corresponding to each of the sampling times in the future time period, the cleaning time of the water purifier in the future time period can be determined according to the water consumption status corresponding to each of the sampling times in the future time period.
[0095] Specifically, according to the water consumption status corresponding to each sampling time in the future time period, the peak water consumption period in the future time period is determined; wherein the peak water consumption period is a plurality of continuous sampling times whose number is greater than a preset number threshold and whose water consumption status is all in the first state; in each discrete time period after excluding the peak water consumption time period in the future time period, a discrete time period with a time length greater than the cleaning time of the water purifier is determined, and the start time of the determined discrete time period is used as the cleaning time.
[0096] The peak water consumption period is a plurality of consecutive sampling times whose number is greater than a preset number threshold and whose water consumption status is all in the first state. That is to say, there are multiple consecutive sampling times in the peak water consumption period, the number of sampling times is greater than the number threshold and the water consumption status corresponding to each sampling time is all in the first state.
[0097] Discrete time periods refer to the discontinuous time periods remaining in the future time periods excluding the peak water consumption period. For example, during a day, 11:00 to 12:00 is the peak water consumption period, so before 11:00 is a discrete time period, and after 12:00 is another discrete time period.
[0098] Furthermore, when determining the water consumption state, the judgment standard is based on the sampling time, and the difference between the water level calibration value corresponding to the sampling time and the water level calibration value before the preset time length is determined; if the absolute value of the difference is greater than the water consumption threshold, the water consumption state corresponding to the sampling time is determined to be the first state. Therefore, if the number of sampling times in the peak water consumption period is greater than the quantity threshold and the water consumption state corresponding to each sampling time is the first state, it means that the water consumption frequency in the peak water consumption period is high and the water consumption is large.
[0099] Further, a discrete time period having a time length greater than the cleaning time of the water purifier is determined, including: among each of the discrete time periods, determining a discrete time period before the peak water usage period; or determining a discrete time period before the peak water usage period and in which the water consumption state corresponding to each sampling time is the second state.
[0100] Each sampling time in the selected discrete time period only includes part of the sampling time corresponding to the second state or all the sampling time corresponds to the second state. Performing water purifier cleaning in such a discrete time period will not affect the user's normal use of the water purifier, or will have little impact on the user's water use, and can ensure that the water purifier has been cleaned before the user uses a large amount of water.
[0101] In the embodiment of the present application, the water purifier is controlled to perform a cleaning operation when the cleaning time arrives. For example, a cleaning instruction is sent to the water purifier, and after receiving the cleaning instruction, the water purifier starts a cleaning program to rinse the water storage cavity and detect whether the filter element needs to be replaced, so as to ensure the safety of the water quality in the water storage cavity.
[0102] The executor of the embodiment of the present application may be a server or a control host in the environment where the water purifier is located. The embodiment of the present application can collect the water level information of the water purifier, use Kalman filtering for data preprocessing, and avoid the problems of excessive cleaning and untimely cleaning; interpolate the water level information of the water purifier, and then judge whether the user uses the water purifier through the water level information. Finally, through the neural network, the subsequent user usage is predicted, and finally the cavity cleaning is turned on before the user uses it to achieve water quality optimization. The embodiment of the present application can not only intelligently control the cleaning mode of the water purifier, improve the user experience and water quality safety, and reduce the risk of bacterial growth; the embodiment of the present application can optimize the cleaning frequency, reduce unnecessary waste of water and electricity resources, and improve the use efficiency of the water purifier. In addition to saving resources, it can also enhance user satisfaction and has significant technical advantages and application value.
[0103] The present application also provides a water purifier cleaning control device. Figure 3 , which is a structural diagram of a water purifier cleaning control device according to an embodiment of the present application.
[0104] The water purifier cleaning control device comprises:
[0105] The data processing module 310 is used to collect the water level sampling value of the water purifier once at a preset sampling interval and calibrate each of the collected water level sampling values to obtain a plurality of water level calibration values with continuous sampling time.
[0106] The first determination module 320 is used to determine the water consumption state corresponding to each sampling time according to a plurality of continuous water level calibration values at the sampling time.
[0107] The second determination module 330 is used to determine the water consumption state corresponding to each of the sampling times in a future time period according to the water consumption state corresponding to each of the sampling times by using a pre-trained prediction model.
[0108] The cleaning control module 340 is used to determine the cleaning time of the water purifier in the future time period according to the water consumption status corresponding to each sampling time in the future time period, and control the water purifier to perform a cleaning operation when the cleaning time arrives.
[0109] The functions of the device described in the embodiment of the present application have been described in the above method embodiment. Therefore, for any details not provided in the description of this embodiment, please refer to the relevant descriptions in the above embodiment and will not be repeated here.
[0110] The present application also provides a water purifier cleaning control device, such as Figure 4 Shown is a structural diagram of a water purifier cleaning control device according to an embodiment of the present application.
[0111] The water purifier cleaning control device includes: a processor 410, a communication interface 420, a memory 430 and a communication bus 440. The processor 410, the communication interface 420, and the memory 430 communicate with each other through the communication bus 440.
[0112] The memory 430 is used to store computer programs.
[0113] In one embodiment of the present application, the processor 410, when executing the program stored in the memory 430, implements the water purifier cleaning control method provided by any of the aforementioned method embodiments, including: collecting a water level sampling value of the water purifier once at a preset sampling interval and calibrating each of the collected water level sampling values to obtain a plurality of water level calibration values with continuous sampling time; determining the water consumption state corresponding to each of the sampling times according to the plurality of water level calibration values with continuous sampling time; using a pre-trained prediction model to determine the water consumption state corresponding to each of the sampling times in a future time period according to the water consumption state corresponding to each of the sampling times; determining the cleaning time of the water purifier in the future time period according to the water consumption state corresponding to each of the sampling times in the future, and controlling the water purifier to perform a cleaning operation when the cleaning time arrives.
[0114] Among them, the calibration of each water level sampling value collected includes: for each water level sampling value collected, using a preset Kalman filtering algorithm, smoothing the water level sampling value to obtain a water level smoothed value; according to the sampling time corresponding to each water level smoothed value, performing interpolation processing on each water level smoothed value to obtain multiple water level calibration values with continuous sampling time.
[0115] Among them, for each water level sampling value collected, a preset Kalman filtering algorithm is used to smooth the water level sampling value to obtain a water level smoothing value, including: initializing a state transfer matrix, an observation matrix, a state transfer matrix variance, an observation matrix variance and a covariance; obtaining a preset sampling error; and, in order of sampling time from first to last, performing the following processing on each water level sampling value in sequence: predicting the water level prediction value corresponding to the next sampling time according to the state transfer matrix, the water level sampling value and the sampling error; predicting the water level prediction value corresponding to the next sampling time according to the state transfer matrix, the water level sampling value and the sampling error; and The covariance is updated by using the state transfer matrix, the covariance, and the state transfer matrix variance; the Kalman filter gain is determined by using the updated covariance, the observation matrix, and the observation matrix variance; the water level smoothing value corresponding to the water level sampling value is determined according to the Kalman filter gain, the water level sampling value, and the water level prediction value; and, according to the Kalman filter gain, the observation matrix and the updated covariance, the updated covariance is updated; and, according to the water level smoothing value, the state transfer matrix variance and the observation matrix variance and covariance are updated.
[0116] Among them, according to the sampling time corresponding to each of the water level smoothing values, interpolation processing is performed on each of the water level smoothing values to obtain a plurality of water level calibration values with continuous sampling time, including: identifying the sampling time of the missing data point according to the sampling time corresponding to each of the water level smoothing values; among each of the water level smoothing values, determining the water level smoothing value corresponding to the sampling time of the missing data point according to the water level smoothing value corresponding to the previous sampling time and the water level smoothing value corresponding to the next sampling time of the sampling time of the missing data point, to obtain a plurality of water level calibration values with continuous sampling time.
[0117] Among them, the water consumption state corresponding to each sampling time is determined based on multiple continuous water level calibration values at the sampling time, including: for each sampling time, taking the sampling time as a reference, determining the difference between the water level calibration value corresponding to the sampling time and the water level calibration value before a preset time length; if the absolute value of the difference is greater than a preset water consumption threshold, determining that the water consumption state corresponding to the sampling time is the first state; otherwise, determining that the water consumption state corresponding to the sampling time is the second state.
[0118] Wherein, determining the cleaning time of the water purifier in the future time period according to the water consumption status corresponding to each sampling time in the future time period includes: determining the peak water consumption period in the future time period according to the water consumption status corresponding to each sampling time in the future time period; wherein the peak water consumption period is a plurality of continuous sampling times whose number is greater than a preset number threshold and whose water consumption status is all in the first state; determining a discrete time period whose time length is greater than the cleaning time length of the water purifier in each discrete time period after excluding the peak water consumption time period in the future time period, and using the determined start time of the discrete time period as the cleaning time.
[0119] Among them, the determining of a discrete time period whose time length is greater than the cleaning time length of the water purifier includes: determining a discrete time period before the peak water consumption period among each of the discrete time periods; or determining a discrete time period before the peak water consumption period and in which the water consumption state corresponding to each sampling time is the second state.
[0120] The present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of the water purifier cleaning control method provided in any of the above method embodiments are implemented. Since the water purifier cleaning control method has been described in detail above, for any details not fully described in the description of this embodiment, please refer to the relevant descriptions in the above embodiments, and no further description will be given here.
[0121] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0122] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0123] It should be understood that the terms used in the text are only for the purpose of describing specific example embodiments, and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used in the text may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.
[0124] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.
Claims
1. A water purifier cleaning control method, characterized in that: include: At every preset sampling interval, a water level sampling value of the water purifier is collected and each of the collected water level sampling values is calibrated to obtain a plurality of water level calibration values with continuous sampling time; Determine the water consumption state corresponding to each of the sampling times according to a plurality of continuous water level calibration values at the sampling times; Using a pre-trained prediction model, according to the water consumption status corresponding to each of the sampling times, determine the water consumption status corresponding to each of the sampling times in a future time period; The cleaning time of the water purifier in the future time period is determined according to the water consumption status corresponding to each sampling time in the future time period, and the water purifier is controlled to perform a cleaning operation when the cleaning time arrives.
2. The method according to claim 1, characterized in that The water level sampling values collected by the calibration include: For each collected water level sampling value, a preset Kalman filter algorithm is used to smooth the water level sampling value to obtain a water level smoothing value; According to the sampling times corresponding to the water level smoothing values, interpolation processing is performed on the water level smoothing values to obtain a plurality of water level calibration values with continuous sampling times.
3. The method according to claim 2, characterized in that The water level sampling value collected each time is smoothed by using a preset Kalman filter algorithm to obtain a water level smoothing value, including: Initialize the state transfer matrix, the observation matrix, the state transfer matrix variance, the observation matrix variance and the covariance; obtain the preset sampling error; and perform the following processing for each of the water level sampling values in order of sampling time from first to last: Predicting a water level prediction value corresponding to a next sampling time according to the state transfer matrix, the water level sampling value and the sampling error; Update the covariance according to the state transfer matrix, the covariance, and the state transfer matrix variance; Determine a Kalman filter gain using the updated covariance, the observation matrix, and the observation matrix variance; Determining the water level smoothing value corresponding to the water level sampling value according to the Kalman filter gain, the water level sampling value and the water level prediction value; and The updated covariance is updated according to the Kalman filter gain, the observation matrix and the updated covariance; and the state transfer matrix variance and the observation matrix variance and covariance are updated according to the water level smoothing value.
4. The method according to claim 2, characterized in that: The interpolation process is performed on each of the water level smoothing values according to the sampling time corresponding to each of the water level smoothing values to obtain a plurality of water level calibration values with continuous sampling time, including: Identify the sampling time of the missing data point according to the sampling time corresponding to each of the water level smoothing values; Among the water level smoothing values, the water level smoothing value corresponding to the sampling time of the missing data point is determined based on the water level smoothing value corresponding to the previous sampling time and the water level smoothing value corresponding to the next sampling time of the missing data point, so as to obtain multiple water level calibration values with continuous sampling times.
5. The method according to claim 1, characterized in that The step of determining the water consumption state corresponding to each of the sampling times according to the plurality of continuous water level calibration values at the sampling times comprises: For each of the sampling times, taking the sampling time as a reference, determining the difference between the water level calibration value corresponding to the sampling time and the water level calibration value before a preset time length; If the absolute value of the difference is greater than the preset water consumption threshold, the water consumption state corresponding to the sampling time is determined to be the first state; otherwise, the water consumption state corresponding to the sampling time is determined to be the second state.
6. The method according to claim 1, characterized in that The step of determining the cleaning time of the water purifier in the future time period according to the water consumption states corresponding to the sampling times in the future time period includes: Determine a peak water consumption period in the future time period according to the water consumption status corresponding to each sampling time in the future time period; wherein the peak water consumption period is a plurality of consecutive sampling times whose number is greater than a preset number threshold and whose water consumption status is all in the first state; In each discrete time period after excluding the peak water usage period in the future time period, a discrete time period having a time length greater than the cleaning time of the water purifier is determined, and the start time of the determined discrete time period is used as the cleaning time.
7. The method according to claim 6, characterized in that The determining of a discrete time period whose length is greater than the cleaning time of the water purifier comprises: In each of the discrete time periods, a discrete time period before the peak water usage period is determined; or, a discrete time period before the peak water usage period and in which the water usage state corresponding to each sampling time is the second state is determined.
8. A water purifier cleaning control device, characterized in that: include: A data processing module, used to collect a water level sampling value of the water purifier once at a preset sampling interval and calibrate each of the collected water level sampling values to obtain a plurality of water level calibration values with continuous sampling time; A first determination module is used to determine the water consumption state corresponding to each sampling time according to a plurality of continuous water level calibration values at the sampling time; A second determination module is used to determine the water consumption state corresponding to each of the sampling times in a future time period according to the water consumption state corresponding to each of the sampling times using a pre-trained prediction model; The cleaning control module is used to determine the cleaning time of the water purifier in the future time period according to the water consumption status corresponding to each sampling time in the future time period, and control the water purifier to perform a cleaning operation when the cleaning time arrives.
9. A water purifier cleaning control device, characterized in that: include: at least one communication interface; at least one bus connected to the at least one communication interface; at least one processor connected to the at least one bus; At least one memory connected to the at least one bus, wherein the processor is configured to: execute a water purifier cleaning control program stored in the memory to implement the water purifier cleaning control method according to any one of claims 1-7.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are executed to implement the water purifier cleaning control method according to any one of claims 1 to 7.