Water boiling control method and system based on kettle body induction analysis

Abstract

The invention discloses a water boiling control method and system based on kettle body induction analysis. The method comprises the steps that first infrared data are obtained through an infrared sensor arranged in a first area of a water boiling kettle; according to the first infrared data, judging whether a user starting operation exists or not; when it is judged that the user starting operation exists, multiple pieces of second infrared data are obtained through an infrared sensor arranged in a second area of the water boiling kettle; the second area is closer to an equipment operation area corresponding to the water boiling kettle than the first area; and determining a water boiling instruction of the water boiling kettle according to the at least two pieces of second infrared data and a preset user action analysis algorithm. Therefore, accurate water boiling instruction identification based on multi-area infrared data and action analysis can be realized, and the intelligent operation accuracy and user experience of the water boiling kettle are improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a water boiling control method and system based on kettle body sensor analysis. Background Technology

[0002] With the popularization and development of smart kettles, companies are increasingly focusing on improving the ease of use and user experience through intelligent operation. Existing technologies typically collect infrared data from a single area of ​​the kettle or button trigger signals, using simple signal detection or fixed rules to determine the user's intention to control the boiling function. However, existing solutions lack comprehensive analysis of infrared data from multiple areas and dynamic recognition of user actions, making it difficult to accurately and proactively predict complex user intentions. The commonly used single trigger mechanism cannot adapt to diverse usage scenarios, resulting in insufficient accuracy in boiling command recognition, easily leading to misoperation or response delays, thus limiting the kettle's intelligence level and user experience. Therefore, existing technologies have shortcomings that urgently need to be addressed. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a water boiling control method and system based on kettle body sensing analysis, which can realize accurate water boiling command recognition based on multi-area infrared data and motion analysis, thereby improving the accuracy of intelligent operation of the kettle and the user experience.

[0004] To address the aforementioned technical problems, the first aspect of this invention discloses a water boiling control method based on kettle body sensor analysis, the method comprising:

[0005] First infrared data is acquired by an infrared sensor located in the first area of ​​the kettle.

[0006] Based on the first infrared data, determine whether a user-initiated operation has occurred;

[0007] When a user activation operation is detected, multiple second infrared data are acquired by an infrared sensor located in a second area of ​​the kettle; the second area is closer to the device operation area corresponding to the kettle than the first area.

[0008] The boiling water command of the kettle is determined based on at least two sets of second infrared data and a preset user action analysis algorithm.

[0009] As an optional implementation, in the first aspect of the present invention, both the first infrared data and the second infrared data include reflected light signals corresponding to multiple time points.

[0010] As an optional implementation, in the first aspect of the present invention, determining whether a user-initiated operation exists based on the first infrared data includes:

[0011] Based on the preset signal and distance recognition rules, the distance to the object corresponding to each reflected light signal is determined;

[0012] Sort the distances of all the objects from front to back according to the corresponding time points to obtain the first distance sequence;

[0013] Based on the multinomial fitting algorithm, the first distance sequence is fitted to obtain the first fitting coefficient of the object distance changing with time;

[0014] Based on the first fitting coefficient, determine whether a user-initiated operation exists.

[0015] As an optional implementation, in the first aspect of the present invention, determining the object distance corresponding to each reflected light signal according to a preset signal and distance recognition rule includes:

[0016] Determine the first device parameters of the infrared sensor located in the first area of ​​the kettle;

[0017] The distance prediction model corresponding to the first device parameter is determined from multiple preset prediction models; the distance prediction model is trained using a training dataset that includes multiple training reflected light signals corresponding to the first device parameter and corresponding user hand distance annotations.

[0018] Each of the reflected light signals is input into the distance prediction model to obtain the object distance corresponding to each reflected light signal.

[0019] As an optional implementation, in the first aspect of the present invention, determining whether a user-initiated operation exists based on the first fitting coefficient includes:

[0020] Calculate the average similarity between the first distance sequence and a preset set of reference distance sequences corresponding to multiple users that are known to belong to the proximity action, and obtain the sequence similarity of the first distance sequence.

[0021] Calculate the average similarity between the first fitting coefficient and the reference fitting coefficients of a preset set of multiple users that are known to belong to the proximity action, and obtain the coefficient similarity of the first distance sequence.

[0022] Calculate the weighted average of the sequence similarity and the coefficient similarity to obtain the judgment feature parameters;

[0023] Determine whether the judgment feature parameter is greater than a preset parameter threshold. If so, a user startup operation exists; otherwise, no user startup operation exists.

[0024] As an optional implementation, in the first aspect of the present invention, the step of determining whether a user-initiated operation exists based on the first infrared data is performed by a controller disposed in the kettle, and the step of determining the kettle's boiling command based on at least two sets of the second infrared data and a preset user action analysis algorithm is performed by a cloud server.

[0025] As an optional implementation, in the first aspect of the present invention, determining the boiling water command of the kettle based on at least two sets of second infrared data and a preset user action analysis algorithm includes:

[0026] Based on threshold filtering, at least two response infrared data with an average signal strength greater than a preset signal strength threshold are selected from all the second infrared data; the average signal strength is the average of the signal strength values ​​of all the reflected light signals corresponding to the second infrared data.

[0027] For each of the aforementioned response infrared data, all the reflected light signals corresponding to the response infrared data are sorted from early to late according to the corresponding time points to obtain the signal sequence corresponding to the response infrared data;

[0028] Based on the classifier algorithm and the signal sequence corresponding to each of the aforementioned response infrared data, the user's action type is predicted; the action type is pouring out water from the pot, adding water to the pot, pouring tea leaves into the pot, stopping heating, or starting heating.

[0029] Based on the action type and the preset correspondence between the type and the boiling command, the boiling command of the kettle is determined.

[0030] As an optional implementation, in the first aspect of the invention, predicting the user's action type based on a classifier algorithm and the signal sequence corresponding to each of the response infrared data includes:

[0031] Each of the signal sequences and the corresponding location of the infrared sensor are input into the trained user identification model to obtain the corresponding predicted user.

[0032] Determine the mode term among the predicted users corresponding to all the signal sequences to obtain the current predicted user;

[0033] The pre-trained action type prediction model corresponding to the current predicted user in the preset model database is determined; the action type prediction model is trained using a training dataset that includes multiple training infrared signal sequences and corresponding sensor location labels and user action labels.

[0034] All the signal sequences and the corresponding device locations of the infrared sensors are input into the action type prediction model to obtain the output user action type.

[0035] A second aspect of this invention discloses a water boiling control system based on kettle body sensor analysis, the system comprising:

[0036] The first acquisition module is used to acquire first infrared data through an infrared sensor set in the first area of ​​the kettle.

[0037] The judgment module is used to determine whether a user-initiated operation exists based on the first infrared data;

[0038] The second acquisition module is used to acquire multiple second infrared data through an infrared sensor set in a second area of ​​the kettle when a user start operation is detected; the second area is closer to the device operation area corresponding to the kettle than the first area.

[0039] The determining module is used to determine the boiling water command of the kettle based on at least two sets of the second infrared data and a preset user action analysis algorithm.

[0040] As an optional implementation, in a second aspect of the present invention, both the first infrared data and the second infrared data include reflected light signals corresponding to multiple time points.

[0041] As an optional implementation, in a second aspect of the present invention, the determining module determines, based on the first infrared data, whether there is a specific method for a user to initiate an operation, including:

[0042] Based on the preset signal and distance recognition rules, the distance to the object corresponding to each reflected light signal is determined;

[0043] Sort the distances of all the objects from front to back according to the corresponding time points to obtain the first distance sequence;

[0044] Based on the multinomial fitting algorithm, the first distance sequence is fitted to obtain the first fitting coefficient of the object distance changing with time;

[0045] Based on the first fitting coefficient, determine whether a user-initiated operation exists.

[0046] As an optional implementation, in a second aspect of the invention, the determining module determines the specific method by which it determines the distance to the object corresponding to each reflected light signal according to a preset signal and distance recognition rule, including:

[0047] Determine the first device parameters of the infrared sensor located in the first area of ​​the kettle;

[0048] The distance prediction model corresponding to the first device parameter is determined from multiple preset prediction models; the distance prediction model is trained using a training dataset that includes multiple training reflected light signals corresponding to the first device parameter and corresponding user hand distance annotations.

[0049] Each of the reflected light signals is input into the distance prediction model to obtain the object distance corresponding to each reflected light signal.

[0050] As an optional implementation, in a second aspect of the present invention, the determining module determines, based on the first fitting coefficient, whether there is a specific method for a user to initiate an operation, including:

[0051] Calculate the average similarity between the first distance sequence and a preset set of reference distance sequences corresponding to multiple users that are known to belong to the proximity action, and obtain the sequence similarity of the first distance sequence.

[0052] Calculate the average similarity between the first fitting coefficient and the reference fitting coefficients of a preset set of multiple users that are known to belong to the proximity action, and obtain the coefficient similarity of the first distance sequence.

[0053] Calculate the weighted average of the sequence similarity and the coefficient similarity to obtain the judgment feature parameters;

[0054] Determine whether the judgment feature parameter is greater than a preset parameter threshold. If so, a user startup operation exists; otherwise, no user startup operation exists.

[0055] As an optional implementation, in a second aspect of the invention, the step of determining whether a user-initiated operation exists based on the first infrared data is performed by a controller disposed in the kettle, and the step of determining the kettle's boiling command based on at least two sets of the second infrared data and a preset user action analysis algorithm is performed by a cloud server.

[0056] As an optional implementation, in a second aspect of the invention, the determining module determines the specific method of the kettle's boiling water instruction based on at least two sets of second infrared data and a preset user action analysis algorithm, including:

[0057] Based on threshold filtering, at least two response infrared data with an average signal strength greater than a preset signal strength threshold are selected from all the second infrared data; the average signal strength is the average of the signal strength values ​​of all the reflected light signals corresponding to the second infrared data.

[0058] For each of the aforementioned response infrared data, all the reflected light signals corresponding to the response infrared data are sorted from early to late according to the corresponding time points to obtain the signal sequence corresponding to the response infrared data;

[0059] Based on the classifier algorithm and the signal sequence corresponding to each of the aforementioned response infrared data, the user's action type is predicted; the action type is pouring out water from the pot, adding water to the pot, pouring tea leaves into the pot, stopping heating, or starting heating.

[0060] Based on the action type and the preset correspondence between the type and the boiling command, the boiling command of the kettle is determined.

[0061] As an optional implementation, in a second aspect of the invention, the specific method by which the determining module predicts the user's action type based on a classifier algorithm and the signal sequence corresponding to each of the response infrared data includes:

[0062] Each of the signal sequences and the corresponding location of the infrared sensor are input into the trained user identification model to obtain the corresponding predicted user.

[0063] Determine the mode term among the predicted users corresponding to all the signal sequences to obtain the current predicted user;

[0064] The pre-trained action type prediction model corresponding to the current predicted user in the preset model database is determined; the action type prediction model is trained using a training dataset that includes multiple training infrared signal sequences and corresponding sensor location labels and user action labels.

[0065] All the signal sequences and the corresponding device locations of the infrared sensors are input into the action type prediction model to obtain the output user action type.

[0066] A third aspect of this invention discloses another water boiling control system based on kettle body sensor analysis, the system comprising:

[0067] Memory containing executable program code;

[0068] A processor coupled to the memory;

[0069] The processor calls the executable program code stored in the memory to execute some or all of the steps in the water boiling control method based on kettle body induction analysis disclosed in the first aspect of the present invention.

[0070] The fourth aspect of the present invention discloses a computer storage medium storing computer instructions, which, when invoked, are used to execute some or all of the steps in the kettle-body induction analysis-based water boiling control method disclosed in the first aspect of the present invention.

[0071] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0072] This invention determines the user's start operation by acquiring infrared data from the first area of ​​the kettle, and after the start operation is confirmed, determines the boiling command by using infrared data from the second area, which is closer to the device's operating area than the first area, and a user action analysis algorithm. This enables accurate boiling command recognition based on multi-area infrared data and action analysis, improving the accuracy of the kettle's intelligent operation and the user experience. Attached Figure Description

[0073] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0074] Figure 1 This is a schematic flowchart of a water boiling control method based on kettle body induction analysis disclosed in an embodiment of the present invention.

[0075] Figure 2 This is a schematic diagram of a water boiling control system based on kettle body induction analysis disclosed in an embodiment of the present invention.

[0076] Figure 3 This is a schematic diagram of another water boiling control system based on kettle body induction analysis disclosed in an embodiment of the present invention. Detailed Implementation

[0077] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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.

[0078] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0079] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0080] This invention discloses a water boiling control method and system based on kettle body sensor analysis. It determines the user's start operation by acquiring infrared data from a first area of ​​the kettle, and after confirming the start operation, determines the water boiling command by using infrared data from a second area closer to the device's operating area than the first area and a user action analysis algorithm. This enables accurate water boiling command recognition based on multi-area infrared data and action analysis, improving the accuracy of intelligent kettle operation and user experience. Detailed explanations follow.

[0081] Example 1

[0082] Please see Figure 1 , Figure 1 This is a schematic flowchart of a water boiling control method based on kettle body induction analysis disclosed in an embodiment of the present invention. Figure 1 The described kettle-body sensor-based water boiling control method can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). For example... Figure 1 As shown, the water boiling control method based on kettle body sensor analysis may include the following operations:

[0083] 101. First infrared data is acquired by an infrared sensor located in the first area of ​​the kettle.

[0084] Optionally, the first infrared data may include reflected light signals, signal strength, timestamp data, and ambient light data, which are not limited in this invention.

[0085] Optionally, the first region can be the handle area, bottom area, side area, or other areas close to the user's contact point of the kettle; this invention does not limit this.

[0086] Optionally, the acquisition process of the first infrared data can be based on real-time acquisition, periodic sampling, triggered acquisition, or low-power acquisition, and the present invention does not limit it.

[0087] 102. Based on the first infrared data, determine whether there is a user-initiated operation.

[0088] Optionally, the user-initiated action can be a proximity action, a touch action, a specific gesture, or a button-triggered action; this invention does not impose any limitations.

[0089] Optionally, the user-initiated operation judgment process can be implemented based on signal processing, pattern recognition, machine learning models, or rule reasoning, and this invention does not limit it.

[0090] 103. When a user starts an operation, multiple second infrared data are acquired through an infrared sensor located in the second area of ​​the kettle.

[0091] Optionally, the second infrared data may include multiple sets of reflected light signals, signal intensity sequences, time series data, and multi-channel signal data, which are not limited in this invention.

[0092] Optionally, the second area can be the spout area of ​​the kettle, the control panel area, the lid area, or an area near the operating interface; the present invention does not limit this.

[0093] Optionally, the second zone is closer to the device operation area corresponding to the kettle than the first zone.

[0094] 104. Determine the kettle's boiling command based on at least two second infrared data and a preset user action analysis algorithm.

[0095] Optionally, the user action analysis algorithm can be a classification algorithm, a time series analysis algorithm, a neural network algorithm, or a rule matching algorithm; this invention does not impose any limitations.

[0096] Optionally, the water boiling command may include commands to start heating, stop heating, add water, pour out water, or keep warm; this invention does not limit this.

[0097] As can be seen, the above-described embodiments of the invention determine the user's start operation by acquiring infrared data from the first area of ​​the kettle, and after the start operation is confirmed, determine the boiling command by using infrared data from the second area, which is closer to the device's operating area than the first area, and the user's action analysis algorithm. This enables accurate boiling command recognition based on multi-area infrared data and action analysis, improving the accuracy of the kettle's intelligent operation and the user experience.

[0098] As an optional embodiment, in the above steps, both the first infrared data and the second infrared data include reflected light signals corresponding to multiple time points.

[0099] As can be seen, the contents of the first infrared data and the second infrared data are defined through the above optional embodiments to comprehensively characterize the signal characteristics of the user's actions captured by the infrared sensor, which helps to realize accurate water boiling command recognition based on multi-region infrared data and action analysis, thereby improving the accuracy of intelligent operation of the kettle and the user experience.

[0100] As an optional embodiment, the step of determining whether a user-initiated operation exists based on the first infrared data in the above steps includes:

[0101] Based on the preset signal and distance recognition rules, the distance to the object corresponding to each reflected light signal is determined;

[0102] Sort the distances of all objects from front to back according to the corresponding time points to obtain the first distance sequence;

[0103] Based on the multinomial fitting algorithm, the first distance sequence is fitted to obtain the first fitting coefficient of the object distance changing with time;

[0104] Based on the first fitting coefficient, determine whether a user-initiated operation exists.

[0105] Optionally, the identification rule can be a signal strength and distance mapping rule, a time difference analysis rule, a machine learning model, or a physical simulation model; this invention does not limit the specific rules.

[0106] Optionally, the process of determining the distance to the object can be optimized by considering sensor accuracy, environmental interference, or signal quality; this invention does not impose any limitations on this.

[0107] Optionally, the sorting can be time ascending order, time descending order, weight-based sorting, or timestamp-normalized sorting; this invention does not impose any limitations.

[0108] Optionally, the first distance sequence can be a continuous sequence, a discrete sequence, a time-weighted sequence, or a multidimensional sequence; the present invention does not impose any limitations on this.

[0109] Optionally, the polynomial fitting algorithm can be linear fitting, quadratic fitting, higher-order polynomial fitting, or spline fitting; this invention does not impose any limitations.

[0110] Optionally, the first fitting coefficient may include slope, intercept, curvature coefficient or weighting coefficient, which is not limited in this invention.

[0111] Optionally, the fitting process can be optimized by incorporating sequence length, data noise, or fitting error; this invention does not impose any limitations on this.

[0112] As can be seen, through the above optional embodiments, by determining the distance to the object based on the reflected light signal and generating a first distance sequence, and obtaining the fitting coefficient based on the polynomial fitting algorithm to determine the user's start operation, the accuracy of start operation detection is improved by distance sequence and fitting analysis on the basis of accurate water boiling command recognition, providing a reliable trigger basis for subsequent action recognition and reducing the risk of false triggering.

[0113] As an optional embodiment, the step above, determining the object distance corresponding to each reflected light signal according to a preset signal and distance recognition rule, includes:

[0114] Determine the first device parameters of the infrared sensor located in the first area of ​​the kettle;

[0115] Among multiple preset prediction models, the distance prediction model corresponding to the first device parameter is determined; optionally, the distance prediction model is trained using a training dataset that includes multiple training reflected light signals corresponding to the first device parameter and corresponding user hand distance annotations.

[0116] Each reflected light signal is input into the distance prediction model to obtain the distance to the object corresponding to each reflected light signal.

[0117] Optionally, the first device parameters may include sensor sensitivity, sampling frequency, installation location, signal range, or power consumption parameters, which are not limited in this invention.

[0118] Optionally, the determination of the first device parameter can be based on device configuration files, sensor calibration, system queries, or automatic detection, and this invention does not limit it.

[0119] Optionally, the distance prediction model can be a regression model, a neural network model, a support vector machine model, or a decision tree model; this invention does not impose any limitations.

[0120] Optionally, the training dataset may include historical signal data, analog signal data, labeled data, or multi-user data; this invention does not impose any limitations.

[0121] As can be seen, through the above optional embodiments, by selecting a distance prediction model based on the parameters of the infrared sensor device in the first region and determining the distance of the object reflecting the light signal, the accuracy of distance recognition is improved by using a model prediction adapted to the device parameters, based on the accurate start operation detection. This provides high-quality data support for the user's start operation judgment and reduces the risk of triggering errors caused by misjudgment of distance.

[0122] As an optional embodiment, the step of determining whether a user-initiated operation exists based on the first fitting coefficient in the above steps includes:

[0123] The average similarity between the first distance sequence and a preset set of reference distance sequences corresponding to multiple users that are known to belong to the proximity action is calculated to obtain the sequence similarity of the first distance sequence.

[0124] The coefficient similarity of the first fitting coefficient and the average similarity of the reference fitting coefficients of multiple users corresponding to known proximity actions is calculated to obtain the coefficient similarity of the first distance sequence.

[0125] Calculate the weighted average of sequence similarity and coefficient similarity to obtain the judgment feature parameters;

[0126] Determine whether the judgment feature parameter is greater than the preset parameter threshold. If it is, then there is a user startup operation; otherwise, there is no user startup operation.

[0127] Optionally, the similarity of the sequence can be cosine similarity, Jaccard coefficient, Euclidean distance or dynamic time warping distance, and the present invention does not limit it.

[0128] Optionally, the calculation of sequence similarity can be based on sequence comparison, statistical analysis, vector analysis or time series analysis, and this invention does not limit it.

[0129] Optionally, the similarity coefficient can be vector similarity, the inverse of the absolute difference, weighted similarity, or correlation coefficient; this invention does not impose any limitation.

[0130] Optionally, the calculation process can be based on coefficient comparison, statistical analysis, feature matching, or regression analysis, and this invention does not limit it.

[0131] Optionally, the weighted average can be calculated using fixed weights, dynamic weights, adaptive weights, or weights based on user behavior; this invention does not impose any limitations on this.

[0132] As can be seen, through the above optional embodiments, by calculating the weighted average of the similarity between the first distance sequence and the fitting coefficient and the reference sequence and coefficient as the judgment feature parameter to confirm the user's start operation, the accuracy and robustness of the start judgment are improved through multi-dimensional similarity analysis on the basis of accurate start operation detection, providing a reliable prerequisite for the recognition of boiling water command and reducing the risk of accidental triggering.

[0133] As an optional embodiment, in the above steps, the controller installed in the kettle performs the step of determining whether there is a user-initiated operation based on the first infrared data, and the cloud server receives the second infrared data and performs the step of determining the kettle's boiling command based on at least two second infrared data and a preset user action analysis algorithm.

[0134] Optionally, the controller can be an embedded microcontroller, a single-chip microcomputer, a dedicated chip, or a low-power processor; this invention does not limit the type of controller.

[0135] Optionally, the cloud server can be a single server, a distributed server, an edge computing node, or a cloud cluster; this invention does not limit the types of servers.

[0136] Optionally, the execution process can be optimized by combining local computing power, network latency, or data transmission efficiency, and this invention does not limit it.

[0137] As can be seen, through the above optional embodiments, the controller executes the start operation to determine the boiling water command, and the cloud server determines the boiling water command based on the second infrared data and motion analysis algorithm. Thus, based on accurate boiling water command recognition, the distributed processing optimizes the data processing efficiency and motion analysis computing power, improves the real-time performance and accuracy of command recognition, and reduces the risk of response delay caused by insufficient local processing power.

[0138] As an optional embodiment, the step described above, determining the kettle's boiling command based on at least two sets of second infrared data and a preset user action analysis algorithm, includes:

[0139] Based on threshold filtering, at least two response infrared data with an average signal strength greater than a preset signal strength threshold are selected from all second infrared data; optionally, the average signal strength is the average of the signal strength values ​​of all reflected light signals corresponding to the second infrared data;

[0140] For each response infrared data, all reflected light signals corresponding to the response infrared data are sorted from early to late according to the corresponding time points to obtain the signal sequence corresponding to the response infrared data;

[0141] Based on the classifier algorithm and the signal sequence corresponding to each response infrared data, the user's action type is predicted; optionally, the action type is pouring out water from the pot, adding water to the pot, pouring tea leaves into the pot, stopping heating or starting heating;

[0142] Based on the action type and the correspondence between the preset type and the boiling water instruction, the boiling water instruction of the kettle is determined.

[0143] Optionally, the signal strength threshold can be a fixed threshold, a dynamic threshold, a threshold adjusted based on sensor performance, or a threshold adjusted based on ambient light; the present invention does not limit this.

[0144] Optionally, the classifier algorithm can be a support vector machine, random forest, convolutional neural network, or deep learning classifier; this invention does not limit the specific classifier.

[0145] Optionally, the action type may include additional actions, such as stirring, cleaning, or heat preservation actions, which are not limited by this invention.

[0146] Optionally, the correspondence between the preset type and the boiling water instruction can be a mapping table, a rule base, a data-driven model, or a conditional logic table; this invention does not impose any limitations.

[0147] Optionally, the water boiling instruction can be a single instruction, a combination of instructions, a condition-triggered instruction, or a priority instruction; the present invention does not impose any limitations on this.

[0148] Optionally, the process of determining the boiling water instruction can be optimized by combining action priority, equipment status, or user preferences, and this invention does not limit it.

[0149] As can be seen, through the above optional embodiments, by filtering response infrared data with average signal strength exceeding the threshold and predicting user action types based on classifier algorithms and signal sequences, and combining the correspondence between type and instruction to determine the water boiling instruction, the accuracy of action type recognition is improved through signal filtering and action classification on the basis of accurate water boiling instruction recognition, providing a precise basis for intelligent water boiling operation and reducing the risk of action misjudgment.

[0150] As an optional embodiment, the step above, predicting the user's action type based on the classifier algorithm and the signal sequence corresponding to each response infrared data, includes:

[0151] Each signal sequence and the corresponding infrared sensor device location are input into the trained user identification model to obtain the corresponding predicted user.

[0152] Determine the mode term among the predicted users corresponding to all signal sequences to obtain the current predicted user;

[0153] Determine the pre-trained action type prediction model corresponding to the current user in the preset model database; optionally, the action type prediction model is trained using a training dataset that includes multiple training infrared signal sequences and corresponding sensor location labels and user action labels.

[0154] All signal sequences and the corresponding infrared sensor device locations are input into the action type prediction model to obtain the output user action type.

[0155] Optionally, the user identification model can be a classification model, clustering model, neural network model, or probability model, and this invention does not limit it.

[0156] Optionally, the user identification model can be trained using a training dataset that includes multiple training signal sequences and corresponding sensor location labels and user identity labels; this invention does not impose any limitations on this.

[0157] Optionally, the mode term can be determined based on frequency statistics, weighted voting, probability analysis, or pattern matching, and this invention does not limit it.

[0158] Optionally, the currently predicted user can be a registered user, a temporary user, a default user, or a guest user; this invention does not impose any limitations.

[0159] Optionally, the action type prediction model can be a convolutional neural network, a recurrent neural network, a Transformer model, or a hybrid model; this invention does not impose any limitations.

[0160] Optionally, the training dataset may include historical signal data, analog signal data, labeled data, or multi-user behavior data; this invention does not impose any limitations.

[0161] As can be seen, through the above optional embodiments, by inputting the signal sequence and sensor position into the user identification model to determine the current predicted user and selecting the corresponding action type prediction model to predict the action type, the personalization and accuracy of action type prediction are improved by optimizing the user-specific model on the basis of accurate water boiling instruction recognition. This provides a more accurate basis for user behavior for water boiling instruction generation and reduces the risk of action recognition error caused by user differences.

[0162] Example 2

[0163] Please see Figure 2 , Figure 2 This is a schematic diagram of a water boiling control system based on kettle body induction analysis disclosed in an embodiment of the present invention. Figure 2 The described kettle-body sensor-based water boiling control system can be applied to data processing systems / data processing equipment / data processing servers (including local processing servers or cloud processing servers). For example... Figure 2 As shown, the water boiling control system based on kettle body sensor analysis may include:

[0164] The first acquisition module 201 is used to acquire first infrared data through an infrared sensor set in the first area of ​​the kettle.

[0165] The judgment module 202 is used to determine whether a user-initiated operation exists based on the first infrared data.

[0166] The second acquisition module 203 is used to acquire multiple second infrared data through an infrared sensor set in the second area of ​​the kettle when it is determined that a user start operation has been detected.

[0167] Optionally, the second zone is closer to the device operation area corresponding to the kettle than the first zone.

[0168] The determining module 204 is used to determine the boiling water command of the kettle based on at least two second infrared data and a preset user action analysis algorithm.

[0169] As can be seen, the above-described embodiments of the invention determine the user's start operation by acquiring infrared data from the first area of ​​the kettle, and after the start operation is confirmed, determine the boiling command by using infrared data from the second area, which is closer to the device's operating area than the first area, and the user's action analysis algorithm. This enables accurate boiling command recognition based on multi-area infrared data and action analysis, improving the accuracy of the kettle's intelligent operation and the user experience.

[0170] As an optional embodiment, both the first infrared data and the second infrared data include reflected light signals corresponding to multiple time points.

[0171] As can be seen, the contents of the first infrared data and the second infrared data are defined through the above optional embodiments to comprehensively characterize the signal characteristics of the user's actions captured by the infrared sensor, which helps to realize accurate water boiling command recognition based on multi-region infrared data and action analysis, thereby improving the accuracy of intelligent operation of the kettle and the user experience.

[0172] As an optional embodiment, the determining module determines, based on the first infrared data, whether there is a specific method for a user-initiated operation, including:

[0173] Based on the preset signal and distance recognition rules, the distance to the object corresponding to each reflected light signal is determined;

[0174] Sort the distances of all objects from front to back according to the corresponding time points to obtain the first distance sequence;

[0175] Based on the multinomial fitting algorithm, the first distance sequence is fitted to obtain the first fitting coefficient of the object distance changing with time;

[0176] Based on the first fitting coefficient, determine whether a user-initiated operation exists.

[0177] As can be seen, through the above optional embodiments, by determining the distance to the object based on the reflected light signal and generating a first distance sequence, and obtaining the fitting coefficient based on the polynomial fitting algorithm to determine the user's start operation, the accuracy of start operation detection is improved by distance sequence and fitting analysis on the basis of accurate water boiling command recognition, providing a reliable trigger basis for subsequent action recognition and reducing the risk of false triggering.

[0178] As an optional embodiment, the determination module determines the specific method by which it determines the distance to the object corresponding to each reflected light signal according to a preset signal and distance recognition rule, including:

[0179] Determine the first device parameters of the infrared sensor located in the first area of ​​the kettle;

[0180] Among multiple preset prediction models, the distance prediction model corresponding to the first device parameter is determined; optionally, the distance prediction model is trained using a training dataset that includes multiple training reflected light signals corresponding to the first device parameter and corresponding user hand distance annotations.

[0181] Each reflected light signal is input into the distance prediction model to obtain the distance to the object corresponding to each reflected light signal.

[0182] As can be seen, through the above optional embodiments, by selecting a distance prediction model based on the parameters of the infrared sensor device in the first region and determining the distance of the object reflecting the light signal, the accuracy of distance recognition is improved by using a model prediction adapted to the device parameters, based on the accurate start operation detection. This provides high-quality data support for the user's start operation judgment and reduces the risk of triggering errors caused by misjudgment of distance.

[0183] As an optional embodiment, the determination module determines, based on the first fitting coefficient, whether there is a specific method for a user-initiated operation, including:

[0184] The average similarity between the first distance sequence and a preset set of reference distance sequences corresponding to multiple users that are known to belong to the proximity action is calculated to obtain the sequence similarity of the first distance sequence.

[0185] The coefficient similarity of the first fitting coefficient and the average similarity of the reference fitting coefficients of multiple users corresponding to known proximity actions is calculated to obtain the coefficient similarity of the first distance sequence.

[0186] Calculate the weighted average of sequence similarity and coefficient similarity to obtain the judgment feature parameters;

[0187] Determine whether the judgment feature parameter is greater than the preset parameter threshold. If it is, then there is a user startup operation; otherwise, there is no user startup operation.

[0188] As can be seen, through the above optional embodiments, by calculating the weighted average of the similarity between the first distance sequence and the fitting coefficient and the reference sequence and coefficient as the judgment feature parameter to confirm the user's start operation, the accuracy and robustness of the start judgment are improved through multi-dimensional similarity analysis on the basis of accurate start operation detection, providing a reliable prerequisite for the recognition of boiling water command and reducing the risk of accidental triggering.

[0189] As an optional embodiment, the controller installed in the kettle performs the step of determining whether there is a user-initiated operation based on the first infrared data, and the cloud server receives the second infrared data and performs the step of determining the kettle's boiling command based on at least two second infrared data and a preset user action analysis algorithm.

[0190] As can be seen, through the above optional embodiments, the controller executes the start operation to determine the boiling water command, and the cloud server determines the boiling water command based on the second infrared data and motion analysis algorithm. Thus, based on accurate boiling water command recognition, the distributed processing optimizes the data processing efficiency and motion analysis computing power, improves the real-time performance and accuracy of command recognition, and reduces the risk of response delay caused by insufficient local processing power.

[0191] As an optional embodiment, the determining module determines the specific method of the kettle's boiling water instruction based on at least two second infrared data sets and a preset user action analysis algorithm, including:

[0192] Based on threshold filtering, at least two response infrared data with an average signal strength greater than a preset signal strength threshold are selected from all second infrared data; optionally, the average signal strength is the average of the signal strength values ​​of all reflected light signals corresponding to the second infrared data;

[0193] For each response infrared data, all reflected light signals corresponding to the response infrared data are sorted from early to late according to the corresponding time points to obtain the signal sequence corresponding to the response infrared data;

[0194] Based on the classifier algorithm and the signal sequence corresponding to each response infrared data, the user's action type is predicted; optionally, the action type is pouring out water from the pot, adding water to the pot, pouring tea leaves into the pot, stopping heating or starting heating;

[0195] Based on the action type and the correspondence between the preset type and the boiling water instruction, the boiling water instruction of the kettle is determined.

[0196] As can be seen, through the above optional embodiments, by filtering response infrared data with average signal strength exceeding the threshold and predicting user action types based on classifier algorithms and signal sequences, and combining the correspondence between type and instruction to determine the water boiling instruction, the accuracy of action type recognition is improved through signal filtering and action classification on the basis of accurate water boiling instruction recognition, providing a precise basis for intelligent water boiling operation and reducing the risk of action misjudgment.

[0197] As an optional embodiment, the determining module predicts the user's action type based on the classifier algorithm and the signal sequence corresponding to each response infrared data in a specific way, including:

[0198] Each signal sequence and the corresponding infrared sensor device location are input into the trained user identification model to obtain the corresponding predicted user.

[0199] Determine the mode term among the predicted users corresponding to all signal sequences to obtain the current predicted user;

[0200] Determine the pre-trained action type prediction model corresponding to the current user in the preset model database; optionally, the action type prediction model is trained using a training dataset that includes multiple training infrared signal sequences and corresponding sensor location labels and user action labels.

[0201] All signal sequences and the corresponding infrared sensor device locations are input into the action type prediction model to obtain the output user action type.

[0202] As can be seen, through the above optional embodiments, by inputting the signal sequence and sensor position into the user identification model to determine the current predicted user and selecting the corresponding action type prediction model to predict the action type, the personalization and accuracy of action type prediction are improved by optimizing the user-specific model on the basis of accurate water boiling instruction recognition. This provides a more accurate basis for user behavior for water boiling instruction generation and reduces the risk of action recognition error caused by user differences.

[0203] Example 3

[0204] Please see Figure 3 , Figure 3 This is another water boiling control system based on kettle body induction analysis disclosed in the embodiments of the present invention. Figure 3 The described kettle-body sensor-based water boiling control system is applied in a data processing system / data processing equipment / data processing server (wherein, the server includes a local processing server or a cloud processing server). For example... Figure 3 As shown, the water boiling control system based on kettle body sensor analysis may include:

[0205] Memory 301 storing executable program code;

[0206] Processor 302 coupled to memory 301;

[0207] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the water boiling control method based on kettle body induction analysis described in Embodiment 1.

[0208] Example 4

[0209] This invention discloses a computer read storage medium that stores a computer program for electronic data exchange, wherein the computer program causes a computer to execute the steps of the water boiling control method based on kettle body induction analysis described in Embodiment 1.

[0210] Example 5

[0211] This invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to perform the steps of the boiling water control method based on kettle body induction analysis described in Embodiment 1.

[0212] The foregoing has described specific embodiments of this specification; other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims may be performed in a different order than those shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily have to follow the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0213] The systems, devices, modules, or units described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, a computer can be, for example, a personal computer, laptop computer, cellular phone, camera phone, smartphone, personal digital assistant, media player, navigation device, email device, game console, tablet computer, wearable device, or any combination of these devices.

[0214] For ease of description, the above devices are described in terms of function, divided into various units. Of course, in implementing this specification, the functions of each unit can be implemented in one or more software and / or hardware components.

[0215] Those skilled in the art will understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0216] This specification is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this specification. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0217] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0218] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0219] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0220] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0221] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0222] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0223] This specification can be described in the general context of computer-executable instructions that are executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform a specific task or implement a specific abstract data type. This specification can also be practiced in distributed computing environments, where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0224] The various embodiments in this specification are described in a progressive manner. Similar or identical parts between embodiments can be referred to interchangeably. Each embodiment focuses on describing the differences from other embodiments. In particular, the system embodiments are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions in the method embodiments.

[0225] Finally, it should be noted that the water boiling control method and system based on kettle body induction analysis disclosed in the embodiments of the present invention are merely preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A water boiling control method based on kettle body sensor analysis, characterized in that, The method includes: First infrared data is acquired by an infrared sensor located in the first area of ​​the kettle. Based on the first infrared data, determine whether a user-initiated operation has occurred; When a user activation operation is detected, multiple second infrared data are acquired by an infrared sensor located in a second area of ​​the kettle; the second area is closer to the device operation area corresponding to the kettle than the first area. The boiling water command of the kettle is determined based on at least two sets of second infrared data and a preset user action analysis algorithm.

2. The water boiling control method based on kettle body induction analysis according to claim 1, characterized in that, Both the first infrared data and the second infrared data include reflected light signals corresponding to multiple time points.

3. The water boiling control method based on kettle body induction analysis according to claim 2, characterized in that, The step of determining whether a user-initiated operation exists based on the first infrared data includes: Based on the preset signal and distance recognition rules, the distance to the object corresponding to each reflected light signal is determined; Sort the distances of all the objects from front to back according to the corresponding time points to obtain the first distance sequence; Based on the multinomial fitting algorithm, the first distance sequence is fitted to obtain the first fitting coefficient of the object distance changing with time; Based on the first fitting coefficient, determine whether a user-initiated operation exists.

4. The water boiling control method based on kettle body induction analysis according to claim 3, characterized in that, The step of determining the object distance corresponding to each reflected light signal according to a preset signal and distance recognition rule includes: Determine the first device parameters of the infrared sensor located in the first area of ​​the kettle; The distance prediction model corresponding to the first device parameter is determined from multiple preset prediction models; the distance prediction model is trained using a training dataset that includes multiple training reflected light signals corresponding to the first device parameter and corresponding user hand distance annotations. Each of the reflected light signals is input into the distance prediction model to obtain the object distance corresponding to each reflected light signal.

5. The water boiling control method based on kettle body induction analysis according to claim 3, characterized in that, The step of determining whether a user-initiated operation exists based on the first fitting coefficient includes: Calculate the average similarity between the first distance sequence and a preset set of reference distance sequences corresponding to multiple users that are known to belong to the proximity action, and obtain the sequence similarity of the first distance sequence. Calculate the average similarity between the first fitting coefficient and the reference fitting coefficients of a preset set of multiple users that are known to belong to the proximity action, and obtain the coefficient similarity of the first distance sequence. Calculate the weighted average of the sequence similarity and the coefficient similarity to obtain the judgment feature parameters; Determine whether the judgment feature parameter is greater than a preset parameter threshold. If so, a user startup operation exists; otherwise, no user startup operation exists.

6. The water boiling control method based on kettle body induction analysis according to claim 1, characterized in that, The controller installed in the kettle performs the step of determining whether a user has initiated an operation based on the first infrared data. The cloud server receives the second infrared data and performs the step of determining the kettle's boiling command based on at least two sets of the second infrared data and a preset user action analysis algorithm.

7. The water boiling control method based on kettle body induction analysis according to claim 1, characterized in that, The step of determining the kettle's boiling command based on at least two sets of second infrared data and a preset user action analysis algorithm includes: Based on threshold filtering, at least two response infrared data with an average signal strength greater than a preset signal strength threshold are selected from all the second infrared data; the average signal strength is the average of the signal strength values ​​of all the reflected light signals corresponding to the second infrared data. For each of the aforementioned response infrared data, all the reflected light signals corresponding to the response infrared data are sorted from early to late according to the corresponding time points to obtain the signal sequence corresponding to the response infrared data; Based on the classifier algorithm and the signal sequence corresponding to each of the aforementioned response infrared data, the user's action type is predicted; the action type is pouring out water from the pot, adding water to the pot, pouring tea leaves into the pot, stopping heating, or starting heating. Based on the action type and the preset correspondence between the type and the boiling command, the boiling command of the kettle is determined.

8. The water boiling control method based on kettle body induction analysis according to claim 7, characterized in that, The step of predicting the user's action type based on the classifier algorithm and the signal sequence corresponding to each of the response infrared data includes: Each of the signal sequences and the corresponding location of the infrared sensor are input into the trained user identification model to obtain the corresponding predicted user. Determine the mode term among the predicted users corresponding to all the signal sequences to obtain the current predicted user; The pre-trained action type prediction model corresponding to the current predicted user in the preset model database is determined; the action type prediction model is trained using a training dataset that includes multiple training infrared signal sequences and corresponding sensor location labels and user action labels. All the signal sequences and the corresponding device locations of the infrared sensors are input into the action type prediction model to obtain the output user action type.

9. A water boiling control system based on kettle body sensor analysis, characterized in that, The system includes: The first acquisition module is used to acquire first infrared data through an infrared sensor set in the first area of ​​the kettle. The judgment module is used to determine whether a user-initiated operation exists based on the first infrared data; The second acquisition module is used to acquire multiple second infrared data through an infrared sensor set in a second area of ​​the kettle when a user start operation is detected; the second area is closer to the device operation area corresponding to the kettle than the first area. The determining module is used to determine the boiling water command of the kettle based on at least two sets of the second infrared data and a preset user action analysis algorithm.

10. A water boiling control system based on kettle body sensor analysis, characterized in that, The system includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the water boiling control method based on kettle body induction analysis as described in any one of claims 1-8.

Images