A method and system for displaying water volume in an intelligent kettle based on weighing data

Abstract

The application provides an intelligent kettle water quantity display method and system based on weighing data, and relates to the technical field of intelligent kettles. First, usage habit data such as an operation mode, an operation frequency and a mode connection relationship of the intelligent kettle are used to determine a usage portrait. Then, a first preset time interval is used to obtain an impurity information detection sequence of conductivity, light detection values and the like of the first intelligent kettle. Then, a change relationship between impurity quantity and sensing data such as conductivity and light detection values is obtained through big data fitting, so that a predicted value of the impurity quantity is obtained. Finally, the predicted value of the impurity quantity is used to correct a detection value of water quantity in the intelligent kettle, so that a water quantity display value is obtained. Through the technical scheme, the impurity quantity can be predicted by comprehensively using multiple types of sensing data, and a more accurate water quantity display value of the intelligent kettle can be obtained through big data analysis.

Description

Technical Field

[0001] This invention belongs to the field of big data, and in particular relates to a method and system for displaying the water volume of an intelligent kettle based on weighing data. Background Technology

[0002] Currently, smart home appliances are increasingly appearing in daily life, but the accuracy of their operation and display still needs improvement. With the development of big data and artificial intelligence technologies, it is possible to process various sensor data acquired through the Internet of Things (IoT) to achieve greater operational and display accuracy. Summary of the Invention

[0003] The purpose of this invention is to provide a method and system for displaying the water volume of an intelligent kettle based on weighing data, so as to solve the technical problem of low accuracy in the water volume display of existing intelligent kettles.

[0004] This application proposes a method for displaying the water volume of a smart kettle based on weighing data, implemented using a remote intelligent analysis system. The remote intelligent analysis system includes a big data processing node and multiple distributed smart kettle nodes, wherein each distributed smart kettle node corresponds to a first smart kettle. The method includes:

[0005] S1: Obtain a first usage profile based on the first historical usage data of the first smart kettle; the first historical usage data refers to the usage data of the first smart kettle within a first historical time interval.

[0006] S2: At a first preset time interval, acquire a first impurity information detection sequence of the first smart kettle; the first impurity information detection sequence includes the conductivity and light detection value of the first smart kettle;

[0007] S3: Based on the first impurity information detection sequence and the first usage profile, obtain the target impurity quantity; the target impurity quantity refers to the predicted value of the amount of impurities in the water;

[0008] S4: Obtain the first water volume display value based on the first water volume detection value and the target impurity quantity.

[0009] Preferably, step S1 includes the following sub-steps:

[0010] S11: Obtain the first operation mode information of the first smart kettle within the first historical time interval;

[0011] S12: Based on the first operation mode information, extract multiple first successive operation modes and obtain first mode association information;

[0012] S13: Upload the first operation mode information and the first mode association information to the big data computing node to obtain the first usage profile.

[0013] Preferably, step S12 includes the following sub-steps:

[0014] S121: Obtain multiple first operation modes and multiple first usage time intervals from the first operation mode information;

[0015] S122: Establish multiple first mapping relationships based on multiple first operation modes and multiple first usage time intervals;

[0016] S123: Obtain multiple target operation modes from multiple first operation modes, and obtain a corresponding first successive operation mode for each target operation mode.

[0017] Preferably, step S2 includes the following sub-steps:

[0018] S21: Obtain the first conductivity and first light detection value of the first smart kettle at multiple first time points;

[0019] S22: Obtain the first impurity information detection sequence based on multiple first conductivity values ​​and first light detection values.

[0020] Preferably, step S3 includes the following sub-steps:

[0021] S31: Based on multiple first conductivity values ​​and multiple first light detection values, a first impurity growth model is trained to obtain the first impurity mass growth model;

[0022] S32: Based on the first conductivity, the first light detection value, and the first impurity mass growth model at the first time point, obtain the first impurity mass of the first smart kettle;

[0023] S33: Obtain a first similar smart kettle based on the first usage profile, and then obtain the second impurity mass of the first similar smart kettle;

[0024] S34: Obtain the target impurity level based on the first impurity level and the second impurity level.

[0025] Preferably, the relationship between conductivity and light detection value and impurities in the first impurity mass growth model is as follows:

[0026] The relationship between conductivity and impurities is as follows:

[0027] G(D) = G0 - f(D, PH);

[0028] Where G(D) represents the conductivity when the amount of impurities in the water is D, G0 is the initial conductivity, D is the amount of impurities in the water, and f is a function representing the combined effect of the amount of impurities and pH value on the conductivity;

[0029] The relationship between the light detection value and impurities is as follows:

[0030] R(D)=R max -(R max -R0) / (1+(D / D0) n );

[0031] Where R0 is the initial reflectance of the water when there are no impurities, and R(D) represents the reflectance as a function of the amount of impurities D in the water. max The maximum reflectivity is represented when the impurity mass reaches saturation. D0 is the characteristic thickness of the impurity mass, indicating that the reflectivity reaches half of the maximum value at this thickness. n is the shape parameter.

[0032] This application also proposes an intelligent kettle water volume display system based on weighing data, which is used to implement the above-mentioned intelligent kettle water volume display method based on weighing data.

[0033] This application proposes a method and system for displaying water level in a smart kettle based on weighing data, relating to the field of smart kettle technology. First, a user profile is determined based on usage habit data such as the smart kettle's operation mode, operation frequency, and mode sequence. Then, at a first preset time interval, a sequence of impurity information, including conductivity and light detection values, is acquired from the smart kettle. Next, through big data fitting, the relationship between the amount of impurities in the water and the changes in sensor data such as conductivity and light detection values ​​is obtained, thereby obtaining a predicted value for the amount of impurities. Finally, the predicted value of the amount of impurities is used to correct the detected value of the water level in the smart kettle to obtain the displayed water level value. Through the technical solution of this invention, multiple types of sensor data can be integrated to predict the amount of impurities, and combined with big data analysis to obtain a relatively accurate displayed water level value for the smart kettle. Attached Figure Description

[0034] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0035] Figure 1 This is a system architecture diagram of the remote intelligent analysis system in this invention.

[0036] Figure 2This is an execution flowchart of a smart kettle water volume display method based on weighing data according to the present invention. Detailed Implementation

[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0038] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. The illustrative embodiments and descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0039] The following is a detailed description of a smart kettle water volume display method and system based on weighing data according to the present invention.

[0040] This embodiment proposes a method for displaying the water volume of an intelligent kettle based on weighing data.

[0041] The intelligent kettle water volume display method based on weighing data is implemented using a remote intelligent analysis system. This remote intelligent analysis system includes a big data processing node and multiple distributed intelligent kettle nodes, with the specific architecture as follows: Figure 1 As shown.

[0042] The big data processing node establishes a remote communication connection with multiple distributed smart kettle nodes. Each distributed smart kettle node uploads usage data to the big data processing node at preset time intervals. The big data processing node performs calculations based on the received usage data, thereby distributing the water level adjustment value displayed by each distributed smart kettle node to the corresponding smart kettle node.

[0043] Each of the distributed value smart kettle nodes has a one-to-one correspondence with a smart kettle. Each smart kettle includes a data processing module and an information communication module. The data processing module is used to collect and analyze user operation data of the smart kettle, and the information communication module is used to upload the collected and analyzed data to the big data processing node.

[0044] Each smart kettle also includes multiple sensors for acquiring usage data during operation. These sensors specifically include a conductivity sensor, an optical sensor, and a temperature sensor. The conductivity sensor is located in the heating element of the smart kettle, the optical sensor is located in the lid, and the temperature sensor is located in the heating element.

[0045] The process of the smart kettle water volume display method based on weighing data is as follows: Figure 2 As shown, the specific steps include the following:

[0046] S1: Obtain the first user profile based on the first historical usage data of the first smart kettle.

[0047] The first historical usage data refers to the usage data of the first smart kettle within the first historical time interval.

[0048] S1 includes the following sub-steps:

[0049] S11: Obtain the first operating mode information of the first smart kettle within the first historical time interval.

[0050] The operating mode refers to the functional modes supported by the first smart kettle, including tea brewing, water boiling, stewing, and heat preservation. The first operating mode information includes the operating modes used by the first smart kettle within the first historical time interval and the total number of times, including the time interval for each operating mode. For example, if the first smart kettle used the water boiling mode 10 times, the tea brewing mode 15 times, the stewing mode 10 times, and the heat preservation mode 20 times in 30 days, then the specific form of the first operating mode information may include the above information.

[0051] The first historical time interval is preferably 15 days or more. The longer the first historical time interval, the more accurate the water volume display value.

[0052] S12: Based on the first operation mode information, extract multiple first successive operation modes and obtain the first mode association information.

[0053] Typically, impurities that accumulate in a kettle mainly include limescale and tea stains. The amount of these impurities directly affects the accuracy of the smart kettle's water level measurement and display. The formation of these impurities is caused by various factors, including but not limited to the mineral composition of the water, the components of the tea leaves, and water temperature. Water temperature is the most significant factor contributing to impurity deposition. If the kettle is allowed to cool naturally after brewing tea, the amount of tea stains accumulated will be significantly less than if the kettle is kept warm. Since water temperature information is directly affected by the continuous operation mode, this step requires extracting multiple first consecutive operation modes from the first operation mode information to analyze the correlation between these multiple first consecutive operation modes.

[0054] S12 includes the following sub-steps:

[0055] S121: Obtain multiple first operation modes and multiple first usage time intervals from the first operation mode information.

[0056] The multiple first operating modes refer to each operating mode used by the first smart kettle within the first historical time interval, and the multiple first usage time intervals are the start and end times corresponding to each operating mode. Each first operating mode has a one-to-one correspondence with a first usage time interval.

[0057] S122: Establish multiple first mapping relationships based on multiple first operation modes and multiple first usage time intervals.

[0058] Since each of the first operation modes has a one-to-one correspondence with a first usage time interval, a first operation mode and its corresponding first usage time interval can be set as a first mapping relationship, thereby obtaining multiple first mapping relationships.

[0059] S123: Obtain multiple target operation modes from multiple first operation modes, and obtain a corresponding first successive operation mode for each target operation mode.

[0060] Among them, the first operation modes include multiple operation modes such as tea brewing, water boiling, stewing, and heat preservation. Since the heat preservation mode is more likely to form scale after the tea brewing or stewing mode, it is necessary to determine whether the mode that keeps the water temperature high is still selected after the tea brewing or stewing mode.

[0061] Specifically, in this step, the operating mode other than boiling water is determined as the target operating mode, and the operating mode after the target operating mode during the first usage time interval is determined as the first continuous operating mode.

[0062] S124: Determine the first mode association information based on the target operation mode that satisfies the preset relationship in the first usage time interval and the first successive operation mode.

[0063] In this step, for each target operating mode and its corresponding first successive operating mode, it is determined whether the first usage time interval between the two is less than a preset time interval. If so, setting the first successive operating mode will increase the amount of tea stains deposited. Therefore, the first mode association information determined in this way can be used to characterize the amount of tea stains deposited to a certain extent.

[0064] S13: Upload the first operation mode information and the first mode association information to the big data computing node to obtain the first usage profile.

[0065] In this step, the first operation mode information and the first mode association information are uploaded to the big data processing node through the information communication module of the smart kettle. Then, the big data processing node can generate several tags characterizing the usage of the first smart kettle based on the received information, thereby obtaining the first usage profile based on multiple tags.

[0066] Since the big data computing node establishes communication connections with multiple distributed smart kettle nodes, based on the first usage profile, the usage data and impurity generation data of multiple distributed smart kettle nodes can be matched, which can then be used for the correction and display of water volume in the smart kettle.

[0067] S2: At a first preset time interval, acquire the first impurity information detection sequence of the first smart kettle.

[0068] In this step, based on the conductivity sensor and optical sensor installed in the first smart kettle, relevant data that may affect the formation of impurities are acquired, such as conductivity and light transmittance inside the kettle. This is because the accumulation of impurities such as limescale and tea stains in the water can affect the conductivity and light transmittance inside the kettle.

[0069] S2 includes the following sub-steps:

[0070] S21: Obtain the first conductivity and the first light detection value of the first smart kettle at the first time point.

[0071] The conductivity is used to detect the mineral content in the kettle. Generally, the higher the mineral content deposited in the kettle and distributed in the water, the higher the conductivity will be. Therefore, the conductivity sensor located at the bottom of the smart kettle can be used to obtain the first conductivity.

[0072] The light detection value is used to detect the light transmittance inside the kettle. Generally, the more tea stains and other impurities deposited on the bottom and sides of the kettle, the worse the light transmittance, and thus the lower the light detection value. Therefore, an optical sensor located at the bottom of the smart kettle can be used to obtain the first light detection value.

[0073] S22: Obtain the first impurity information detection sequence based on the first conductivity and the first light detection value at multiple time points.

[0074] The multiple time points are determined with the first preset time interval as the interval. The first impurity information detection sequence includes the changes in the first conductivity and the first light detection value over time, which can be used to determine the formation trend of impurities in the first smart kettle.

[0075] S3: Obtain the target impurity quantity based on the first impurity information detection sequence and the first usage profile.

[0076] In this step, the target impurity quantity in the smart kettle at a preset time point is obtained mainly based on the changing trends of conductivity and light detection values ​​in the first impurity information detection sequence.

[0077] S3 includes the following sub-steps:

[0078] S31: A first impurity growth model is trained based on multiple first conductivity values ​​and multiple first light ray detection values.

[0079] The first impurity growth model is obtained through nonlinear fitting, and the main goal of the training is to determine the correlation coefficient in the nonlinear fitting formula.

[0080] The relationship between conductivity and impurities is as follows:

[0081] G(D) = G0 - f(D, PH)

[0082] Where G(D) represents the conductivity when the amount of impurities in the water is D, G0 is the initial conductivity, D is the amount of impurities in the water, and f is a function representing the combined influence of impurities and factors such as pH value on the conductivity.

[0083] The relationship between the light detection value and impurities is as follows:

[0084] R(D)=R max -(R max -R0) / (1+(D / D0) n )

[0085] Where R0 is the initial reflectance of the water when there are no impurities, and R(D) represents the reflectance as a function of the amount of impurities D in the water. max The maximum reflectivity is represented when the impurity mass reaches saturation. D0 is the characteristic thickness of the impurity mass, indicating that the reflectivity reaches half of the maximum value at this thickness. n is a shape parameter that determines the steepness of the curve and reflects the rate of reflectivity change during impurity accumulation.

[0086] In the first impurity growth model, it is mainly used to determine the relationship f between the conductivity and the impurities, and n in the relationship between the light detection value and the impurities, based on multiple first conductivity values ​​and multiple first light detection values ​​at multiple time points.

[0087] Specifically, in the first impurity growth model, the input parameters include G(D), PH, R(D), and R0. maxR0, G0, D0, the output parameters include the amount of impurities in the water determined by conductivity and light detection values ​​at the current time point T.

[0088] S32: Based on the first conductivity, the first light detection value, and the first impurity mass growth model at the first time point, obtain the first impurity mass of the first smart kettle.

[0089] In this step, the first impurity mass of the first smart kettle is obtained by using the first conductivity and the first light detection value acquired in real time at the first time point. The first impurity mass includes the impurity mass determined by the first conductivity and the first light detection value.

[0090] The first point in time refers to the cumulative usage time of the first smart kettle.

[0091] S33: Obtain a first similar smart kettle based on the first usage profile, and then obtain the second impurity quality of the first similar user.

[0092] In this step, based on the first usage profile of the first smart kettle, a similarity match is performed with the usage profiles of other smart kettles in the big data processing node, so that the smart kettle with the highest similarity is selected as the first similar smart kettle.

[0093] The amount of impurities in the first similar smart kettle at the first time point is obtained as the second amount of impurities.

[0094] S34: Obtain the target impurity level based on the first impurity level and the second impurity level.

[0095] The target impurity mass is obtained by combining the first impurity mass and the second impurity mass; the specific calculation method is not limited here.

[0096] Preferably, the first impurity mass and the second impurity mass can be obtained by weighted average. For example, impurities that have a greater impact on conductivity have a different degree of influence on water volume detection than impurities that have a greater impact on light detection values. Therefore, different weight values ​​can be assigned to different types of impurities.

[0097] S4: Obtain the first water volume display value based on the first water volume detection value and the target impurity quantity.

[0098] The first water volume detection value refers to the water volume detection value directly obtained through the weight sensor of the first smart kettle. There is usually a preset relationship between the first water volume detection value, the target impurity quantity, and the first water volume display value. Therefore, the relationship between the three can be established in advance to obtain the first water volume display value used for water volume display.

[0099] Preferably, a convolutional neural network model can be trained to establish the relationship between the first water volume detection value, the target impurity quantity, and the first water volume display value. Specifically, historical data from existing smart kettles can be used as sample data for training.

[0100] This application also proposes an intelligent kettle water volume display system based on weighing data, used to execute the aforementioned intelligent kettle water volume display method based on weighing data.

[0101] This application proposes a method and system for displaying water level in a smart kettle based on weighing data, relating to the field of smart kettle technology. First, a user profile is determined based on usage habit data such as the smart kettle's operation mode, operation frequency, and mode sequence. Then, at a first preset time interval, a sequence of impurity information, including conductivity and light detection values, is acquired from the smart kettle. Next, through big data fitting, the relationship between the amount of impurities in the water and the changes in sensor data such as conductivity and light detection values ​​is obtained, thereby obtaining a predicted value for the amount of impurities. Finally, the predicted value of the amount of impurities is used to correct the detected value of the water level in the smart kettle to obtain the displayed water level value. Through the technical solution of this invention, multiple types of sensor data can be integrated to predict the amount of impurities, and combined with big data analysis to obtain a relatively accurate displayed water level value for the smart kettle.

[0102] The above description is only a preferred embodiment of the present invention. Therefore, all equivalent changes or modifications made to the structure, features and principles described in the claims of this patent application are included in the scope of this patent application.

Claims

1. A smart kettle water volume display method based on weighing data, realized based on a remote intelligent analysis system, the remote intelligent analysis system comprising a big data operation node and a plurality of distributed intelligent kettle nodes, wherein each of the distributed intelligent kettle nodes corresponds to a first intelligent kettle, characterized in that, The method comprises: S1: obtaining a first use portrait according to first historical use data of a first smart kettle; the first historical use data refers to use data of the first smart kettle in a first historical time interval; S2: obtaining a first impurity information detection sequence of the first smart kettle at a first preset time interval; the first impurity information detection sequence includes conductivity and light detection values of the first smart kettle; S3: obtaining a target impurity amount according to the first impurity information detection sequence and the first use portrait; the target impurity amount refers to a predicted value of the impurity amount in water; S4: obtaining a first water amount display value according to a first water amount detection value and the target impurity amount; The S3 comprises the following sub-steps: S31: training a first impurity amount growth model according to a plurality of the first conductivity and a plurality of the first light detection values; S32: obtaining a first impurity amount of the first smart kettle according to the first conductivity, the first light detection value at a first time point, and the first impurity amount growth model; S33: obtaining a second impurity amount of a first similar smart kettle according to the first use portrait; S34: obtaining the target impurity amount according to the first impurity amount and the second impurity amount; The first water amount detection value refers to a water amount detection value directly obtained by a weight sensor of the first smart kettle.

2. The intelligent water bottle water quantity display method based on weighing data according to claim 1, characterized in that, The S1 comprises the following sub-steps: S11: obtaining first operation mode information of the first smart kettle in the first historical time interval; S12: extracting a plurality of first consecutive operation modes according to the first operation mode information to obtain first mode association information; S13: uploading the first operation mode information and the first mode association information to the big data operation node to obtain the first use portrait.

3. The intelligent water bottle water level display method based on weighing data according to claim 2, characterized in that, The S12 comprises the following sub-steps: S121: obtaining a plurality of first operation modes and a plurality of first use time intervals from the first operation mode information; S122: establishing a plurality of first mapping relationships according to the plurality of first operation modes and the plurality of first use time intervals; S123: obtaining a plurality of target operation modes from the plurality of first operation modes, and obtaining a corresponding first consecutive operation mode for each target operation mode.

4. The intelligent water bottle water volume display method based on weighing data according to claim 3, characterized in that, The S2 comprises the following sub-steps: S21: obtaining first conductivity and first light detection values of the first smart kettle at a plurality of first time points; S22: obtaining the first impurity information detection sequence according to the plurality of first conductivity and the first light detection values.

5. The intelligent water bottle water level display method based on weighing data according to claim 4, characterized in that, The relationship between conductivity and light detection value and impurity in the first impurity amount growth model is as follows: The relationship between conductivity and impurity is as follows: G(D) = G0-f(D, PH); Wherein, G(D) represents the conductivity when the impurity amount in water is D, G0 is the initial conductivity, D is the impurity amount in water, f is a function, and represents the comprehensive influence of the impurity amount and PH value on the conductivity; The relationship between light detection value and impurity is as follows: R(D) = R max - (R max - R0) / (1 + (D / D0) n ) ; where R0 is the initial reflectivity in the absence of impurities in the water, R(D) represents the reflectivity as a function of the impurity concentration D in the water, R max represents the maximum reflectivity when the impurity concentration reaches a saturation state, D0 is a characteristic thickness of the impurity concentration, represents the thickness at which the reflectivity reaches half of its maximum value, and n is a shape parameter.

6. A smart kettle water level display system based on weighing data, for implementing the smart kettle water level display method based on weighing data according to any one of claims 1-5.

Images