Intelligent kettle water volume display method and system based on weighing data

Abstract

The invention provides an intelligent kettle water volume display method and system based on weighing data, and relates to the technical field of intelligent kettles.The intelligent kettle water volume display method comprises the steps that firstly, a use portrait is determined according to use habit data such as the operation mode, the operation frequency and the mode continuing relation of an intelligent kettle; the method comprises the following steps: acquiring a detection sequence of impurity information such as conductivity and a light detection value of the first intelligent kettle, then obtaining a change relationship between the impurity amount in water and sensing data such as conductivity and the light detection value through big data fitting, thereby obtaining a predicted value of the impurity amount, and finally, obtaining a prediction result of the impurity amount. And correcting the detection value of the water quantity in the intelligent kettle according to the predicted value of the impurity quantity so as to obtain a water quantity display value. According to the technical scheme, the impurity quantity can be predicted by integrating multiple types of sensing data, and a relatively accurate water volume display value of the intelligent kettle can be obtained by combining big data analysis.

Description

Technical Field

[0001] The present invention belongs to the field of big data, and particularly relates to an intelligent kettle water volume display method and system based on weighing data. Background Art

[0002] Currently, intelligent small household appliances have increasingly appeared in daily life, but the accuracy of operation and display of various small household appliances still needs to be improved. With the development of big data and artificial intelligence technologies, various sensing data obtained from the Internet of Things can be processed by big data to obtain higher operation and display accuracy. Summary of the Invention

[0003] The purpose of the present invention is to provide an intelligent kettle water volume display method and system based on weighing data to solve the technical problem of low display accuracy of the water volume of intelligent kettles in the prior art.

[0004] The present application proposes an intelligent kettle water volume display method based on weighing data, which is implemented based on a remote intelligent analysis system. The remote intelligent analysis system includes a big data operation node and a plurality of distributed intelligent kettle nodes. Each of the distributed intelligent kettle nodes corresponds to a first intelligent kettle. The method includes: S1: Obtain a first usage profile according to the first historical usage data of the first intelligent kettle; the first historical usage data refers to the usage data of the first intelligent kettle within a first historical time interval; S2: Obtain a first impurity information detection sequence of the first intelligent kettle at a first preset time interval; the first impurity information detection sequence includes the conductivity and light detection values of the first intelligent kettle; S3: Obtain a target impurity amount according to the first impurity information detection sequence and the first usage profile; the target impurity amount refers to the predicted value of the amount of impurities in water; S4: Obtain a first water volume display value according to the first water volume detection value and the target impurity amount.

[0005] Preferably, the S1 includes the following sub-steps: S11: Obtain the first operation mode information of the first intelligent kettle within the first historical time interval; S12: Extract a plurality of first consecutive operation modes according to the first operation mode information, and obtain first mode association information; S13: Upload the first operation mode information and the first mode association information to the big data operation node to obtain the first usage profile.

[0006] Preferably, the S12 includes the following sub-steps: S121: Obtain a plurality of first operation modes and a plurality of first usage time intervals from the first operation mode information; S122: Establish a plurality of first mapping relationships according to the plurality of first operation modes and the plurality of first usage time intervals; S123: Obtain a plurality of target operation modes from the plurality of first operation modes, and obtain corresponding first subsequent operation modes for each of the target operation modes.

[0007] Preferably, the S2 includes the following sub-steps: S21: Obtain the first conductivity and the first light detection value of the first intelligent kettle at a plurality of first time points; S22: Obtain the first impurity information detection sequence according to the plurality of first conductivities and the first light detection values.

[0008] Preferably, the S3 includes the following sub-steps: S31: Train to obtain a second impurity mass growth model according to the plurality of first conductivities and the plurality of first light detection values; S32: Obtain the first impurity mass of the first intelligent kettle according to the first conductivity, the first light detection value at the first time point, and the second impurity mass growth model; S33: Obtain a first similar intelligent kettle according to the first usage portrait, and then obtain the second impurity mass of the first similar intelligent kettle; S34: Obtain the target impurity mass according to the first impurity mass and the second impurity mass.

[0009] Preferably, the relationship between the conductivity, the light detection value and the impurity in the second impurity mass growth model is as follows: For the relationship between the conductivity and the impurity: G(D)=G 0 -f(D, PH); wherein, G(D) represents the conductivity when the impurity mass in water is D, G 0 is the initial conductivity, D is the impurity mass in water, and f is a function representing the comprehensive influence of the impurity mass and the PH value on the conductivity; For the relationship between the light detection value and the impurity: R(D)=R max -(R max -R 0 ) / 1+(D / D 0 )n; wherein, R 0 is the initial reflectance when there is no impurity in water, R(D) represents the reflectance varying with the impurity mass D in water, R maxDenotes the maximum reflectivity when the impurity content reaches the saturation state, D 0 Is the characteristic thickness of the impurity content, indicating that at this thickness, the reflectivity reaches half of the maximum value, and n is the shape parameter.

[0010] 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.

[0011] An intelligent kettle water volume display method and system based on weighing data proposed in this application relate to the technical field of intelligent kettles. First, according to usage habit data such as the operation mode, operation frequency, and mode connection relationship of the intelligent kettle, a usage portrait is determined. Then, at a first preset time interval, an impurity information detection sequence such as the conductivity and light detection value of the first intelligent kettle is obtained. Then, through big data fitting, the variation relationship between the impurity content in water and sensing data such as conductivity and light detection value is obtained, so as to obtain the predicted value of the impurity content. Finally, the detected value of the water volume in the intelligent kettle is corrected through the predicted value of the impurity content to obtain the water volume display value. Through the technical solution of the present invention, multiple types of sensing data can be comprehensively used to predict the impurity content, and combined with big data analysis to obtain a relatively accurate water volume display value of the intelligent kettle. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, without creative efforts, other implementation drawings can also be obtained according to the provided drawings.

[0013] Figure 1 Is the system architecture diagram of the remote intelligent analysis system in the present invention.

[0014] Figure 2 Is the execution flowchart of an intelligent kettle water volume display method based on weighing data in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0016] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. The illustrative embodiments and descriptions are only used to explain the present invention, but not to limit the present invention.

[0017] A method and system for displaying the water volume of an intelligent kettle based on weighing data of the present invention will be described in detail below.

[0018] This embodiment proposes a method for displaying the water volume of an intelligent kettle based on weighing data.

[0019] The method for displaying the water volume of the intelligent kettle based on weighing data is implemented based on a remote intelligent analysis system. The remote intelligent analysis system includes a big data operation node and multiple distributed intelligent kettle nodes, and the specific architecture is as Figure 1 shown.

[0020] Among them, the big data operation node establishes a remote communication connection with multiple distributed intelligent kettle nodes. Each distributed intelligent kettle node uploads usage data to the big data operation node at a preset time interval. The big data operation node performs operations based on the received usage data, and thus distributes the water volume display adjustment value of each distributed intelligent kettle node to the corresponding intelligent kettle node.

[0021] Each distributed intelligent kettle node has a one-to-one correspondence with an intelligent kettle. In each intelligent kettle, a data processing module and an information communication module are included. The data processing module is used to collect and analyze the operation data of the user on the intelligent kettle, and the information communication module is used to upload the collected and analyzed data to the big data operation node.

[0022] Among them, in each intelligent kettle, multiple sensors are further included for obtaining usage data during the operation of the intelligent kettle. The sensors specifically include a conductivity sensor, an optical sensor, and a temperature sensor. Among them, the conductivity sensor is arranged in the heating part of the intelligent kettle, the optical sensor is arranged in the lid part of the intelligent kettle, and the temperature sensor is arranged in the heating part of the intelligent kettle.

[0023] The flow of the method for displaying the water volume of the intelligent kettle based on weighing data is as Figure 2 shown, and specifically includes the following steps: S1: Obtain a first usage profile according to the first historical usage data of the first intelligent kettle.

[0024] The first historical usage data refers to the usage data of the first intelligent kettle within the first historical time interval.

[0025] The S1 includes the following sub-steps: S11: Obtain the first operation mode information of the first intelligent kettle within the first historical time interval.

[0026] The operation mode refers to the functional modes supported by the first intelligent kettle, including tea brewing, boiling water, stewing, keeping warm, etc. The first operation mode information includes the operation modes used by the first intelligent kettle within the first historical time interval and the total number of times, and includes the time intervals for using each operation mode. For example, if the first intelligent kettle has used the boiling water mode 10 times, the tea brewing mode 15 times, the stewing mode 10 times, and the keeping warm mode 20 times in 30 days, the specific form of the first operation mode information may include the above information.

[0027] 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.

[0028] S12: According to the first operation mode information, extract multiple first consecutive operation modes and obtain the first mode association information.

[0029] Generally, the impurities that may accumulate in the kettle mainly include scale and tea stains, etc. The amount of impurity accumulation will directly affect the water volume measurement value and the accuracy of the water volume display of the intelligent kettle. The formation of the above impurities is caused by various reasons, including but not limited to the mineral components in the water, the components in the tea, and the water temperature, etc. Among them, the water temperature is the most important factor causing impurity deposition. If the kettle is placed to cool naturally after brewing tea, the accumulation amount of tea stains will be significantly less than that when the kettle is placed in the keeping warm mode. And the water temperature information is directly affected by the consecutive operation modes. Therefore, in this step, multiple first consecutive operation modes need to be extracted from the first operation mode information, so as to analyze the association relationship between multiple first consecutive operation modes.

[0030] S12 includes the following sub-steps: S121: Obtain multiple first operation modes and multiple first usage time intervals from the first operation mode information.

[0031] Among them, the multiple first operation modes are each operation mode used by the first intelligent kettle within the first historical time interval, and the multiple first usage time intervals are the start and end time points corresponding to each operation mode. Each first operation mode has a one-to-one correspondence with a first usage time interval.

[0032] S122: Establish multiple first mapping relationships according to the multiple first operation modes and the multiple first usage time intervals.

[0033] Since each of the first operation modes has a one-to-one correspondence with a first usage time interval, a first mapping relationship can be set between a first operation mode and the corresponding first usage time interval, and thus multiple such first mapping relationships can be obtained.

[0034] S123: Obtain multiple target operation modes from the multiple first operation modes, and for each target operation mode, obtain the corresponding first successive operation mode.

[0035] Among them, the multiple first operation modes include various operation modes such as tea brewing, water boiling, stewing, and heat preservation. Since scale is more likely to form on the water temperature if the heat preservation mode is selected after the tea brewing or stewing mode, it is necessary to determine whether the mode that keeps the water temperature high still exists after the tea brewing or stewing mode.

[0036] Specifically, in this step, the operation modes other than water boiling are determined as the target operation modes, and the operation mode whose first usage time interval is after the target operation mode is determined as the first successive operation mode.

[0037] S124: Determine the first mode association information according to the target operation mode and the first successive operation mode whose first usage time intervals satisfy a preset relationship.

[0038] In this step, for each target operation mode and the corresponding first successive operation mode, it is judged whether the first usage time intervals of the two are less than a preset time interval. If so, the setting of the first successive operation mode will increase the deposition amount of tea scale. Therefore, the first mode association information determined thereby can be used to characterize the amount of tea scale deposition to a certain extent.

[0039] S13: Upload the first operation mode information and the first mode association information to the big data operation node to obtain the first usage portrait.

[0040] In this step, the first operation mode information and the first mode association information are uploaded to the big data operation node through the information communication module of the intelligent kettle. Furthermore, the big data operation node can form several tags for characterizing the usage situation of the first intelligent kettle according to the received information, and thus obtain the first usage portrait according to multiple tags.

[0041] Since the big data operation node has established communication connections with multiple distributed intelligent kettle nodes, based on the first usage portrait, the usage situation data and impurity generation data of multiple distributed intelligent kettle nodes can be matched, and thus can be used for the correction and display of the water volume in the intelligent kettle.

[0042] S2: Obtain the first impurity information detection sequence of the first intelligent kettle at a first preset time interval.

[0043] In this step, based on the conductivity sensor and optical sensor set in the first intelligent kettle, relevant data that may affect impurity formation is obtained, such as conductivity, light transmission in the kettle, etc. This is because the accumulation of impurities such as water scale and tea scale in the water will affect the conductivity in the kettle, the light transmission in the kettle, etc.

[0044] The S2 includes the following sub-steps: S21: Obtain the first conductivity and the first light detection value of the first intelligent kettle at a first time point.

[0045] Among them, conductivity is used to detect the mineral content in the kettle. Usually, the higher the mineral content deposited in the kettle and distributed in the water, the higher the conductivity. Therefore, the first conductivity can be obtained by using the conductivity sensor set at the bottom of the intelligent kettle.

[0046] Among them, the light detection value is used to detect the light transmission in the kettle. Usually, the more impurities such as tea scale deposited on the bottom and side walls of the kettle, the worse the light transmission, that is, the lower the light detection value. Therefore, the first light detection value can be obtained by using the optical sensor set at the bottom of the intelligent kettle.

[0047] S22: Obtain the first impurity information detection sequence according to the first conductivity and the first light detection value at multiple time points.

[0048] Among them, multiple time points are determined at intervals of the first preset time interval. The first impurity information detection sequence includes the change of the first conductivity and the first light detection value over time, and the formation trend of impurities in the first intelligent kettle can be determined based on this.

[0049] S3: Obtain the target impurity amount according to the first impurity information detection sequence and the first usage profile.

[0050] In this step, the target impurity amount in the intelligent kettle at a preset time point is mainly obtained according to the change trends of the conductivity and light detection value in the first impurity information detection sequence.

[0051] The S3 includes the following sub-steps: S31: Train to obtain a second impurity amount growth model according to multiple first conductivities and multiple first light detection values.

[0052] The second impurity amount growth model is trained by non-linear fitting, and the main goal of training is to determine the relevant coefficients in the non-linear fitting formula.

[0053] The relationship between conductivity and impurities is as follows: G(D)=G 0 -f(D, PH) where G(D) represents the conductivity when the impurity content in water is D, and G 0 is the initial conductivity, D is the impurity content in water, and f is a function representing the combined influence of factors such as impurity content and PH value on conductivity.

[0054] The relationship between the light detection value and impurities is as follows: R(D)=R max -(R max -R 0 ) / 1+(D / D 0 ) n where R 0 is the initial reflectivity when there are no impurities in water, R(D) represents the reflectivity varying with the impurity content D in water, and R max represents the maximum reflectivity when the impurity content reaches the saturation state, D 0 is the characteristic thickness of the impurity content, indicating that the reflectivity reaches half of the maximum value at this thickness, and n is the shape parameter that determines the steepness of the change curve and reflects the speed of the reflectivity change during the impurity accumulation process.

[0055] In the second impurity content growth model, it is mainly used to determine the relationship f between the above-mentioned conductivity and impurities, and n in the relationship between the light detection value and impurities, based on multiple first conductivities and multiple first light detection values at multiple time points.

[0056] Specifically, in the second impurity content growth model, the input parameters include G(D), PH, R(D), R max , R 0 , G 0 , D 0 , and the output parameters include the impurity content in water determined by the conductivity and the light detection value respectively at the current time point T.

[0057] S32: Obtain the first impurity content of the first intelligent kettle according to the first conductivity, the first light detection value at the first time point, and the second impurity content growth model.

[0058] In this step, the first conductivity and the first light detection value obtained in real time at the first time point are used to obtain the first impurity content of the first intelligent kettle. The first impurity content respectively includes the impurity content determined by the first conductivity and the first light detection value.

[0059] Among them, the first time point refers to the cumulative usage duration of the first intelligent kettle.

[0060] S33: Obtain the first similar intelligent kettle according to the first usage portrait, and then obtain the second impurity amount of the first similar user.

[0061] In this step, according to the first usage portrait of the first intelligent kettle, perform similarity matching with the usage portraits of other intelligent kettles in the big data operation node, so as to take the intelligent kettle with the highest similarity as the first similar intelligent kettle.

[0062] Obtain the impurity amount of the first similar intelligent kettle at the first time point as the second impurity amount.

[0063] S34: Obtain the target impurity amount according to the first impurity amount and the second impurity amount.

[0064] The target impurity amount is obtained by comprehensively calculating the first impurity amount and the second impurity amount, and the specific calculation method is not limited herein.

[0065] Preferably, the first impurity amount and the second impurity amount can be weighted and averaged. For example, compared with the impurities that have a greater impact on the conductivity and the impurities that have a greater impact on the light detection value, the degree of influence on the water volume detection value is different. Therefore, different weight values can be assigned to different types of impurity amounts accordingly.

[0066] S4: Obtain the first water volume display value according to the first water volume detection value and the target impurity amount.

[0067] The first water volume detection value refers to the water volume detection value directly obtained through the weight sensor of the first intelligent kettle. There is usually a preset relationship among the first water volume detection value, the target impurity amount, and the first water volume display value. Therefore, the change relationship among the three can be established in advance, so as to obtain the first water volume display value for water volume display.

[0068] Preferably, the change relationship among the first water volume detection value, the target impurity amount, and the first water volume display value can be established by training a convolutional neural network model. Specifically, the historical data of existing intelligent kettles can be used as sample data for training.

[0069] This application also proposes an intelligent kettle water volume display system based on weighing data for executing the above-mentioned intelligent kettle water volume display method based on weighing data.

[0070] An intelligent kettle water volume display method and system based on weighing data proposed in this application relate to the technical field of intelligent kettles. First, according to usage habit data such as the operation mode, operation frequency, and mode connection relationship of the intelligent kettle, a usage portrait is determined. Then, at a first preset time interval, an impurity information detection sequence such as the conductivity and light detection value of the first intelligent kettle is obtained. Then, through big data fitting, the change relationship between the amount of impurities in water and sensing data such as conductivity and light detection value is obtained, so as to obtain the predicted value of the amount of impurities. Finally, the detected value of the water volume in the intelligent kettle is corrected by the predicted value of the amount of impurities to obtain the water volume display value. Through the technical solution of the present invention, multiple types of sensing data can be comprehensively used to predict the amount of impurities, and combined with big data analysis to obtain a relatively accurate water volume display value of the intelligent kettle.

[0071] The above are only the preferred embodiments of the present invention. Therefore, all equivalent changes or modifications made according to the structure, characteristics, and principles described in the scope of this invention patent application are included in the scope of this invention patent application.

Claims

1. A method for displaying water volume in an intelligent kettle based on weighing data, implemented based on a remote intelligent analysis system, wherein the remote intelligent analysis system includes a big data computing 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 includes: S1: acquiring a first usage profile according to first historical usage data of a first smart kettle; the first historical usage data refers to usage data of the first smart kettle within a first historical time interval; S2: acquiring 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 usage profile; the target impurity amount refers to a predicted value of the impurity amount in water; S4: Obtaining a first water volume display value according to the first water volume detection value and the target impurity volume.

2. The method for displaying water volume of an intelligent kettle based on weighing data according to claim 1, characterized in that: The S1 comprises the following sub-steps: S11: Acquire first operation mode information of the first smart kettle in a first historical time interval; S12: extracting a plurality of first successive operation modes according to the first operation mode information, and acquiring first mode association information; S13: Upload the first operation mode information and the first mode association information to the big data computing node to obtain the first usage portrait.

3. The method for displaying water volume of an intelligent kettle based on weighing data according to claim 2, characterized in that: The S12 comprises the following sub-steps: S121: Acquire multiple first operation modes and multiple first usage time intervals from the first operation mode information; S122: establishing a plurality of first mapping relationships according to a plurality of the first operation modes and a plurality of the first usage time intervals; S123: Acquire multiple target operation modes from the multiple first operation modes, and acquire a corresponding first subsequent operation mode for each of the target operation modes.

4. The method for displaying water volume of an intelligent kettle based on weighing data according to claim 3, characterized in that: The S2 comprises the following sub-steps: S21: Acquire a first conductivity and a first light detection value 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 the first conductivities and the first light detection values.

5. The method for displaying water volume of an intelligent kettle based on weighing data according to claim 4, characterized in that: The S3 comprises the following sub-steps: S31: training and obtaining a second impurity amount growth model according to the plurality of the first conductivities and the 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 and the second impurity amount growth model at the first time point; S33: Obtain a first similar smart kettle according to the first usage portrait, and then obtain a second impurity amount of the first similar smart kettle; S34: Obtain the target impurity amount according to the first impurity amount and the second impurity amount.

6. The method for displaying water volume of an intelligent kettle based on weighing data according to claim 5, characterized in that: The relationship between the conductivity and light detection value and the impurities in the second impurity mass growth model is as follows: The relationship between conductivity and impurities is as follows: G(D)=G0-f(D, PH); Where G(D) represents the conductivity when the amount of impurities in water is D, G0 is the initial conductivity, D is the amount of impurities in water, and f is a function that represents the combined effect of impurities and pH value on conductivity; The relationship between light detection value and impurities is as follows: R(D)=R max -(R max -R0) / 1+(D / D0) n ; Among them, R0 is the initial reflectivity when there is no impurity in the water, R(D) represents the reflectivity that changes with the amount of impurities D in the water, and R max It represents the maximum reflectivity when the impurity mass reaches saturation state, D0 is the characteristic thickness of the impurity mass, which means that the reflectivity reaches half of the maximum value at this thickness, and n is the shape parameter.

7. A smart kettle water volume display system based on weighing data, used to implement a smart kettle water volume display method based on weighing data as described in any one of claims 1 to 6.

Images