Intelligent bathtub temperature control system
By acquiring users' historical preferences and environmental data, and using deep learning technology for intelligent bathtub temperature control, the problem of traditional bathtub temperature control systems being unable to accurately control water temperature has been solved, achieving personalized automated water temperature adjustment and improving the system's automation level.
Patent Information
- Application Number
- CN202411099296.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-12
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-08-12
AI Technical Summary
Traditional bathtub temperature control systems cannot accurately control water temperature, cannot automatically adjust the water temperature according to personal preferences or different usage scenarios, lack a personalized experience, and are complicated to operate.
By acquiring users' historical preference data and environmental condition data, and employing deep learning-based semantic analysis and data processing techniques, semantic encoding and temporal feature extraction and association are performed to intelligently recommend water temperature values suitable for the current environmental conditions.
It enables intelligent recommendation of water temperature suitable for the current environmental conditions based on user preferences, ensuring that users enjoy a comfortable bathing experience under different conditions, reducing manual intervention and improving the level of system automation.
Smart Images

Figure CN118939022A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of intelligent control, and more specifically, to an intelligent bathtub temperature control system. Background Art
[0002] As living standards improve, consumers have higher and higher requirements for the quality of home life, including bathing experience. People hope to enjoy a comfortable water temperature when bathing, and avoid the bathing experience being affected by too high or too low water temperature. Therefore, controlling the water temperature in the bathtub can ensure that the water temperature meets personal preferences and provide a more comfortable bathing experience.
[0003] However, the traditional bathtub temperature control system may not be able to accurately control the water temperature, which is prone to over-temperature or over-temperature. It also cannot automatically adjust the water temperature according to personal preferences or different usage scenarios, lacking a personalized experience. Secondly, the traditional bathtub water temperature also requires users to manually adjust the water temperature, which cannot be automatically controlled, increasing the complexity of the operation.
[0004] Therefore, an optimized intelligent counting system for skipping rope is expected. Summary of the invention
[0005] In order to solve the above technical problems, the present application is proposed. An embodiment of the present application provides an intelligent bathtub temperature control system, which obtains user historical preference data and collects environmental condition data at multiple predetermined time points within a predetermined time period, wherein the environmental condition data includes water temperature, room temperature and humidity, and uses semantic analysis and data processing technology based on deep learning to semantically encode the user historical preference data and the environmental condition data, respectively, and extract and associate temporal features, so as to intelligently obtain the recommended water temperature value at the current time point based on the fusion representation features between the semantic features of the user preference data and the temporal association features of the environmental condition data. In this way, the system can intelligently recommend a water temperature suitable for the current environmental conditions based on the user's historical preferences, ensuring that the user can enjoy a comfortable bathing experience under different environmental conditions. At the same time, the system can collect environmental data in real time and respond quickly, reduce manual intervention, and improve the level of system automation.
[0006] According to one aspect of the present application, there is provided an intelligent bathtub temperature control system, comprising: A user historical preference data acquisition module, used to acquire user historical preference data; An environmental condition data collection module, used to collect environmental condition data at multiple predetermined time points within a predetermined time period, wherein the environmental condition data includes water temperature, room temperature and humidity; An environmental condition data regularization time series capture module is used to regularize the environmental condition data at multiple predetermined time points within the predetermined time period to obtain a sequence of environmental condition data time series input vectors and then input the sequence into an environmental condition parameter time series capture model to obtain a sequence of environmental condition data time series feature vectors; A parameter time series association module, used for inputting the sequence of the environmental condition data time series feature vector into an environmental condition parameter time series association extractor to obtain an environmental condition parameter time series association feature vector; A user history preference data semantic encoding module, used for inputting the user history preference data into a user preference semantic feature extractor to obtain a user history preference data semantic encoding feature vector; A user preference environmental condition feature fusion module, used to fuse the environmental condition parameter time series association feature vector and the user historical preference data semantic encoding feature vector to obtain a user preference-environmental condition representation vector; The water temperature value recommendation module is used to obtain the recommended water temperature value at the current time point based on the user preference-environmental condition characterization vector, and control the output of the heating element based on the recommended water temperature value.
[0007] Compared with the prior art, the present application provides a smart bathtub temperature control system, which obtains user historical preference data and collects environmental condition data at multiple predetermined time points within a predetermined time period, wherein the environmental condition data includes water temperature, room temperature and humidity, and uses semantic analysis and data processing technology based on deep learning to semantically encode the user historical preference data and the environmental condition data, respectively, and extract and associate temporal features, so as to intelligently obtain the recommended water temperature value at the current time point based on the fusion representation features between the semantic features of the user preference data and the temporal association features of the environmental condition data. In this way, the system can intelligently recommend a water temperature suitable for the current environmental conditions based on the user's historical preferences, ensuring that the user can enjoy a comfortable bathing experience under different environmental conditions. At the same time, the system can collect environmental data in real time and respond quickly, reduce manual intervention, and improve the level of system automation. BRIEF DESCRIPTION OF THE DRAWINGS
[0008] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.
[0009] Figure 1 4 is a block diagram of a smart bathtub temperature control system according to an embodiment of the present application.
[0010] Figure 2 Schematic diagram of the architecture of a smart bathtub temperature control system according to an embodiment of the present application.
[0011] Figure 3 It is a block diagram of the environmental condition data regularization timing capture module in the smart bathtub temperature control system according to an embodiment of the present application.
[0012] Figure 4 4 is a block diagram of a user preference environmental condition feature fusion module in a smart bathtub temperature control system according to an embodiment of the present application.
[0013] Figure 5 This is a block diagram of a water temperature value recommendation module in a smart bathtub temperature control system according to an embodiment of the present application. DETAILED DESCRIPTION
[0014] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, but rather these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.
[0015] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.
[0016] It should be noted that the terms "first\second\third" involved in the embodiments of the present application are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that the specific order or sequence of "first\second\third" can be interchanged where permitted. It should be understood that the objects distinguished by "first\second\third" can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.
[0017] As shown in this disclosure, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.
[0018] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.
[0019] As living standards improve, consumers have higher and higher requirements for the quality of home life, including bathing experience. People hope to enjoy a comfortable water temperature when bathing, and avoid the bathing experience being affected by too high or too low water temperature. Therefore, controlling the water temperature in the bathtub can ensure that the water temperature meets personal preferences and provide a more comfortable bathing experience.
[0020] However, the traditional bathtub temperature control system may not be able to accurately control the water temperature, which is prone to over-temperature or over-temperature. It also cannot automatically adjust the water temperature according to personal preferences or different usage scenarios, lacking a personalized experience. Secondly, the traditional bathtub water temperature also requires users to manually adjust the water temperature, which cannot be automatically controlled, increasing the complexity of the operation.
[0021] Therefore, a smart bathtub temperature control system is desired, which obtains the user's historical preference data and collects environmental condition data at multiple predetermined time points within a predetermined time period, wherein the environmental condition data includes water temperature, room temperature and humidity, and uses semantic analysis and data processing technology based on deep learning to perform semantic encoding and temporal feature extraction and association on the user's historical preference data and the environmental condition data, respectively, so as to intelligently obtain the recommended water temperature value at the current time point based on the fusion representation features between the semantic features of the user preference data and the temporal association features of the environmental condition data. In this way, the system can intelligently recommend a water temperature suitable for the current environmental conditions based on the user's historical preferences, ensuring that the user can enjoy a comfortable bathing experience under different environmental conditions. At the same time, the system can collect environmental data in real time and respond quickly, reduce manual intervention, and improve the level of system automation.
[0022] Figure 1 4 is a block diagram of a smart bathtub temperature control system according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of the architecture of the smart bathtub temperature control system according to an embodiment of the present application. Figure 1 and Figure 2As shown, the smart bathtub temperature control system 100 according to the embodiment of the present application includes: a user history preference data acquisition module 110, which is used to acquire user history preference data; an environmental condition data acquisition module 120, which is used to collect environmental condition data at multiple predetermined time points within a predetermined time period, wherein the environmental condition data includes water temperature, room temperature and humidity; an environmental condition data regularization time series capture module 130, which is used to regularize the environmental condition data at multiple predetermined time points within the predetermined time period to obtain a sequence of environmental condition data time series input vectors and then input the sequence into the environmental condition parameter time series capture model to obtain a sequence of environmental condition data time series feature vectors; a parameter time series association module 140, which is used to associate the environmental condition data time series The sequence of feature vectors is input into the environmental condition parameter time series association extractor to obtain the environmental condition parameter time series association feature vector; the user history preference data semantic encoding module 150 is used to input the user history preference data into the user preference semantic feature extractor to obtain the user history preference data semantic encoding feature vector; the user preference environmental condition feature fusion module 160 is used to fuse the environmental condition parameter time series association feature vector and the user history preference data semantic encoding feature vector to obtain the user preference-environmental condition representation vector; the water temperature value recommendation module 170 is used to obtain the recommended water temperature value at the current time point based on the user preference-environmental condition representation vector, and control the output of the heating element based on the recommended water temperature value.
[0023] In an embodiment of the present application, the user historical preference data acquisition module 110 is used to acquire user historical preference data. It should be understood that the user historical preference data refers to the record of preferences and choices shown by the user when using a smart bathtub or other similar devices in the past. Specifically, the user historical preference data may include the user's favorite water temperature range, the time period of the day when the user usually uses the bathtub, the user's preferences under different room temperature and humidity conditions, etc. Based on this, in order to be able to recommend the water temperature in the future to meet the user's preferences at a specific time point, so as to adjust it in advance, in the technical solution of the present application, the user's historical preference data is acquired. In this way, by collecting and analyzing the user's historical preference data, the smart bathtub temperature control system can better meet the needs of users and provide a more comfortable, energy-saving and safe bathing experience.
[0024] In the embodiment of the present application, the environmental condition data acquisition module 120 is used to collect environmental condition data at multiple predetermined time points within a predetermined time period, wherein the environmental condition data includes water temperature, room temperature and humidity. Accordingly, it is considered that the environmental condition data refers to the measured values of various environmental factors that affect people's daily life and specific activities (such as bathing). Specifically, the water temperature is the temperature of the water in the bathtub, which is one of the key factors determining the comfort of bathing. The room temperature is the air temperature in the bathroom, which affects people's perception of water temperature and the overall bathing experience. The humidity is the moisture content in the air, and high humidity may make people feel stuffy and affect the bathing experience. Therefore, in order for the system to provide a bathing experience that is more in line with user expectations, the water temperature can be intelligently adjusted according to environmental conditions and user preferences to ensure that users can enjoy suitable water temperatures under different conditions. In the technical solution of the present application, environmental condition data at multiple predetermined time points within a predetermined time period are collected, wherein the environmental condition data includes water temperature, room temperature and humidity. That is, using environmental condition data, the system can make more accurate temperature control decisions based on a data-driven method, so that the system can become more intelligent and better understand user needs, thereby providing a more comfortable, energy-saving and safe bathing experience.
[0025] In an embodiment of the present application, the environmental condition data regularization timing capture module 130 is used to regularize the environmental condition data at multiple predetermined time points within the predetermined time period to obtain a sequence of environmental condition data timing input vectors, and then input the sequence into the environmental condition parameter timing capture model to obtain a sequence of environmental condition data timing feature vectors. Figure 3 is a block diagram of an environmental condition data regularization timing capture module in a smart bathtub temperature control system according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 3 As shown, the environmental condition data regularization and timing capture module 130 includes: a parameter sample time dimension arrangement unit 131, which is used to regularize the environmental condition data of multiple predetermined time points within the predetermined time period according to the parameter sample dimension and the time dimension to obtain a sequence of the environmental condition data timing input vector; an environmental parameter timing feature extraction unit 132, which is used to input the sequence of the environmental condition data timing input vector into an environmental condition parameter timing capture model based on a deep neural network to obtain a sequence of the environmental condition data timing feature vector.
[0026] Specifically, the parameter sample time dimension arrangement unit 131 is used to perform data regularization on the environmental condition data at multiple predetermined time points within the predetermined time period according to the parameter sample dimension and the time dimension to obtain a sequence of the environmental condition data time series input vector. It should be understood that, considering that each environmental condition parameter in the environmental condition data at multiple predetermined time points within the predetermined time period is constantly changing with the passage of time, that is, each environmental condition parameter has time series feature information on the time dimension, and there is a mutual correlation relationship between the various environmental condition parameters on the time dimension. Based on this, in the technical solution of the present application, the environmental condition data at multiple predetermined time points within the predetermined time period are data regularized according to the parameter sample dimension and the time dimension to obtain a sequence of the environmental condition data time series input vector. That is, the environmental condition data at multiple predetermined time points are data regularized according to the time dimension, which can more accurately and meticulously identify the changing trend and fluctuation pattern of environmental conditions over time. Regularizing the environmental condition data at the multiple predetermined time points according to the parameter sample dimension can better capture the interdependence between the various environmental condition parameters in the time dimension, and provide more accurate input for subsequent time series feature analysis and processing.
[0027] Specifically, the environmental parameter time series feature extraction unit 132 is used to input the sequence of the environmental condition data time series input vector into the environmental condition parameter time series capture model based on the deep neural network to obtain the sequence of the environmental condition data time series feature vector. In particular, here, the environmental condition parameter time series capture model based on the deep neural network is an environmental condition parameter time series capture model based on a one-dimensional convolutional network. Accordingly, considering that each environmental condition data time series input vector in the sequence of the environmental condition data time series input vector has certain local temporal feature information in the local time scale, such as periodic changes and fluctuations in a short period of time, etc. 1D CNN can automatically capture the temporal features within the local time span from the sequence data, such as trends, periodicity and seasonal changes. Therefore, in the technical solution of the present application, the sequence of the environmental condition data time series input vector is input into the environmental condition parameter time series capture model based on the one-dimensional convolutional network to obtain the sequence of the environmental condition data time series feature vector, so that the environmental parameter temporal feature information within the local time segment can be captured and mined from the environmental condition data time series input vector, thereby obtaining the sequence of environmental condition data time series feature vectors.
[0028] In an embodiment of the present application, the parameter timing association module 140 is used to input the sequence of the environmental condition data timing feature vector into the environmental condition parameter timing association extractor to obtain the environmental condition parameter timing association feature vector. Specifically, in an embodiment of the present application, the parameter timing association module is used to: input the sequence of the environmental condition data timing feature vector into the environmental condition parameter timing association extractor based on the converter to obtain the environmental condition parameter timing association feature vector. It should be understood that, considering that there is overall timing feature information about the environmental conditions between the sequences of the environmental condition data timing feature vectors, that is, there is mutual correlation and dependency in the time dimension between the sequences of the environmental condition data timing feature vectors. And the degree of mutual correlation between different environmental condition timing feature vectors is different, and considering that the converter model can capture long-distance dependencies through the self-attention mechanism, it is suitable for environmental condition data with long-term correlation, and the self-attention mechanism allows the model to dynamically adjust the attention weights of different parts of the sequence. Based on this, in order to more clearly understand and consider the mutual correlation of the sequence of the environmental condition data time series feature vector, in the technical solution of the present application, the sequence of the environmental condition data time series feature vector is input into the environmental condition parameter time series association extractor based on the converter to obtain the environmental condition parameter time series association feature vector. That is, through the attention mechanism, the converter can integrate the context information in the sequence, improve the semantic expression ability of the feature, and obtain a more feature-rich environmental condition parameter time series association feature vector, providing a more accurate and comprehensive environmental condition parameter time series association feature for the intelligent bathtub temperature control system.
[0029] In an embodiment of the present application, the user historical preference data semantic encoding module 150 is used to input the user historical preference data into a user preference semantic feature extractor to obtain a semantic encoding feature vector of the user historical preference data. Specifically, in an embodiment of the present application, the user historical preference data semantic encoding module is used to: input the user historical preference data into a user preference semantic feature extractor based on a Bi-LSTM model to obtain a semantic encoding feature vector of the user historical preference data. Accordingly, considering that the user historical preference data contains the preference data and habits of the user in using the bathtub in the past, and there is a contextual semantic association relationship between these individual data. Therefore, in the technical solution of the present application, the user historical preference data is input into a user preference semantic feature extractor based on a Bi-LSTM model to obtain a semantic encoding feature vector of the user historical preference data. It should be understood that the Bi-LSTM model can handle the time dependency in the data and can more accurately capture the changing trend of user preferences over time, which helps to understand the long-term and short-term preference changes of users and provides support for subsequent water temperature control.
[0030] In the embodiment of the present application, the user preference environmental condition feature fusion module 160 is used to fuse the environmental condition parameter temporal association feature vector and the user historical preference data semantic encoding feature vector to obtain a user preference-environmental condition representation vector. Figure 4 is a block diagram of a user preference environment condition feature fusion module in a smart bathtub temperature control system according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 4 As shown, the user preference environmental condition feature fusion module 160 includes: a user historical preference metric perception optimization unit 161, which is used to perform viewpoint metric perception optimization based on inverse error detection on the semantic encoding feature vector of the user historical preference data based on the environmental condition parameter time series association feature vector to obtain an optimized user historical preference data semantic encoding feature vector; an optimized user historical preference-environmental condition parameter feature fusion unit 162, which is used to perform feature fusion on the environmental condition parameter time series association feature vector and the optimized user historical preference data semantic encoding feature vector to obtain the user preference-environmental condition representation vector.
[0031] Specifically, the user historical preference metric perception optimization unit 161 is used to perform viewpoint metric perception optimization based on inverse error detection on the semantic encoding feature vector of the user historical preference data based on the time series association feature vector of the environmental condition parameter to obtain an optimized semantic encoding feature vector of the user historical preference data. In particular, in the technical solution of the present application, considering that in the above technical solution, the user historical preference data is usually static, discrete personal preference information, while the environmental condition parameter is dynamic, continuous time series data. This difference in data types may lead to inconsistencies in feature extraction and processing between the two. The environmental condition parameters are subjected to time series feature extraction through a one-dimensional convolutional network and a converter, emphasizing the time dependency and dynamic changes of the data. The user historical preference data is subjected to semantic feature extraction through a Bi-LSTM model, focusing mainly on the semantic content and preference tendency of the data. The two have different methods and emphases when processing time series data and static data. The time series association feature vector of the environmental condition parameter is extracted through a time series capture model and a time series association extractor, which are specially designed to capture long-term dependencies in time series data. The semantic encoding feature vector of user historical preference data is extracted through the Bi-LSTM model, focusing on understanding user preferences and behavior patterns. There are differences in the methods and purposes of feature extraction between the two. When fusing the environmental condition parameter temporal association feature vector and the user historical preference data semantic encoding feature vector, if the fusion strategy is not sophisticated or not well considered, it may lead to the lack of a posteriori-priori causal relationship between the two. In order to solve this problem, in the technical solution of the present application, based on the environmental condition parameter temporal association feature vector, the user historical preference data semantic encoding feature vector is optimized based on the viewpoint metric perception of inverse error detection to obtain the optimized user historical preference data semantic encoding feature vector.
[0032] More specifically, in an embodiment of the present application, the user history preference metric perception optimization unit is used to: calculate the position difference between the semantic encoding feature vector of the user history preference data and the temporal association feature vector of the environmental condition parameter to obtain a first viewpoint metric representation vector; calculate the position point multiplication between the semantic encoding feature vector of the user history preference data and the temporal association feature vector of the environmental condition parameter to obtain a second viewpoint metric representation vector; calculate the position sum between the semantic encoding feature vector of the user history preference data and the temporal association feature vector of the environmental condition parameter to obtain a third viewpoint metric representation vector; calculate the first viewpoint metric representation vector. The first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector are obtained by calculating the gradient amplitude of each position in the metric representation vector, the second viewpoint metric representation vector and the third viewpoint metric representation vector to obtain the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector; the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector are input into the backward machine learning reverse multi-viewpoint perception optimization module to obtain the reverse multi-viewpoint perception optimization representation vector; the position-wise point multiplication between the reverse multi-viewpoint perception optimization representation vector and the user historical preference data semantic encoding feature vector is calculated to obtain the optimized user historical preference data semantic encoding feature vector.
[0033] In the embodiment of the present application, specifically, the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector are input into the backward machine learning reverse multi-view perception optimization module, and are processed by the following perception optimization formula to obtain the reverse multi-view perception optimization representation vector; wherein the perception optimization formula is: ;in, , and The first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector are represented by The eigenvalues at the positions, are three eigenvalues of corresponding positions in the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector The mean of is the standard deviation of three eigenvalues at corresponding positions in the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector, represents the maximum value of three eigenvalues at corresponding positions in the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector, represents the linear rectification function, represents the normalized exponential function, represents the reverse multi-view perception optimization representation vector The feature value at each position.
[0034] Specifically, in the technical solution of the present application, based on the time-series correlation feature vector of the environmental condition parameter, the semantic coding feature vector of the user's historical preference data is optimized based on the reverse error detection viewpoint metric perception, and the process includes first calculating the position difference, point multiplication and sum between the semantic coding feature vector of the user's historical preference data and the time-series correlation feature vector of the environmental condition parameter through multi-view analysis (Multi-View Analysis) to obtain three viewpoint metric representation vectors, and quantify the relationship between features from different angles. Then, the gradient amplitude of each position in these viewpoint metric representation vectors is calculated through reverse error perception (Backward Error Perception) to identify key change points to provide a basis for feature optimization.
[0035] Then, the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector are input into the backward machine learning reverse multi-viewpoint perception optimization module, wherein the backward machine learning reverse multi-viewpoint perception optimization module captures the significant comprehensive ability factor of the feature importance perception (Feature Importance Perception) of the feature sub-dimension distribution of the corresponding position in the first to third viewpoint metric perception vectors by adopting a squeeze-incentive mechanism composed of -functions. Then, the position point multiplication between the reverse multi-viewpoint perception optimization representation vector and the user historical preference data semantic encoding feature vector is calculated to perform backward optimization perception (Backward Optimization Perception) on the user historical preference data semantic encoding feature vector to adjust the user historical preference data semantic encoding feature vector so as to better associate it with the environmental condition parameter time series association feature vector, thereby enhancing the causal relationship between the user historical preference data semantic encoding feature vector and the environmental condition parameter time series association feature vector.
[0036] Specifically, the optimized user historical preference-environmental condition parameter feature fusion unit 162 is used to perform feature fusion on the environmental condition parameter time series association feature vector and the optimized user historical preference data semantic coding feature vector to obtain the user preference-environmental condition representation vector. It should be understood that considering that the environmental condition parameter time series association feature vector expresses the change trend and pattern of environmental conditions (such as water temperature, room temperature and humidity) over time, it captures the time dependency between environmental condition parameters, for example, temperature changes at different time points in a day or in different seasons. The optimized user historical preference data semantic coding feature vector expresses the semantic information of the user's past behavior patterns and selection habits after feature optimization. Therefore, in order to provide more comprehensive user and environmental information and increase the system's understanding and prediction capabilities, combining user preferences and environmental condition data can improve the accuracy of system prediction and recommendation. In the technical solution of the present application, the environmental condition parameter time series association feature vector and the optimized user historical preference data semantic coding feature vector are feature fused to obtain the user preference-environmental condition representation vector. In this way, the smart bathtub temperature control system can comprehensively consider the user's historical preferences and real-time environmental conditions to provide a more intelligent and personalized temperature control solution, thereby enhancing the user experience and improving the effectiveness of the system.
[0037] In the embodiment of the present application, the water temperature value recommendation module 170 is used to obtain the recommended water temperature value at the current time point based on the user preference-environmental condition characterization vector, and control the output of the heating element based on the recommended water temperature value. Figure 5 is a block diagram of a water temperature value recommendation module in a smart bathtub temperature control system according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 5 As shown, the water temperature value recommendation module 170 includes: a water temperature decoding value unit 171, which is used to input the user preference-environmental condition characterization vector into a decoder-based water temperature recommender to obtain the water temperature value recommended at the current time point; a heating element control unit 172, which is used to automatically control the output of the heating element based on the water temperature value recommended at the current time point. That is, the user preference-environmental condition characterization vector is decoded to intelligently obtain the water temperature value recommended at the current time point. In this way, the system can intelligently recommend a water temperature suitable for the current environmental conditions based on the user's historical preferences, ensuring that the user can enjoy a comfortable bathing experience under different environmental conditions. At the same time, the system can collect environmental data in real time and respond quickly, reduce manual intervention, and improve the level of system automation.
[0038] In summary, the intelligent bathtub temperature control system 100 based on the embodiment of the present application is explained, which obtains the user's historical preference data and collects the environmental condition data at multiple predetermined time points within a predetermined time period, wherein the environmental condition data includes water temperature, room temperature and humidity, and uses semantic analysis and data processing technology based on deep learning to semantically encode the user's historical preference data and the environmental condition data, respectively, and extract and associate temporal features, so as to intelligently obtain the recommended water temperature value at the current time point based on the fusion representation features between the semantic features of the user preference data and the temporal association features of the environmental condition data. In this way, the system can intelligently recommend a water temperature suitable for the current environmental conditions based on the user's historical preferences, ensuring that the user can enjoy a comfortable bathing experience under different environmental conditions. At the same time, the system can collect environmental data in real time and respond quickly, reduce manual intervention, and improve the level of system automation.
[0039] As described above, the smart bathtub temperature control system 100 according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with a smart bathtub temperature control algorithm. In a possible implementation, the smart bathtub temperature control system 100 according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the smart bathtub temperature control system 100 can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the smart bathtub temperature control system 100 can also be one of the many hardware modules of the wireless terminal.
[0040] Alternatively, in another example, the smart bathtub temperature control system 100 and the wireless terminal may also be separate devices, and the smart bathtub temperature control system 100 may be connected to the wireless terminal via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.
[0041] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0042] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0043] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0044] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.
[0045] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit of the technical solution of the present invention.
Claims
1. An intelligent bathtub temperature control system, characterized in that: include: A user historical preference data acquisition module, used to acquire user historical preference data; An environmental condition data collection module, used to collect environmental condition data at multiple predetermined time points within a predetermined time period, wherein the environmental condition data includes water temperature, room temperature and humidity; An environmental condition data regularization time series capture module is used to regularize the environmental condition data at multiple predetermined time points within the predetermined time period to obtain a sequence of environmental condition data time series input vectors and then input the sequence into an environmental condition parameter time series capture model to obtain a sequence of environmental condition data time series feature vectors; A parameter time series association module, used for inputting the sequence of the environmental condition data time series feature vector into an environmental condition parameter time series association extractor to obtain an environmental condition parameter time series association feature vector; A user history preference data semantic encoding module, used for inputting the user history preference data into a user preference semantic feature extractor to obtain a user history preference data semantic encoding feature vector; A user preference environmental condition feature fusion module, used to fuse the environmental condition parameter time series association feature vector and the user historical preference data semantic encoding feature vector to obtain a user preference-environmental condition representation vector; The water temperature value recommendation module is used to obtain the recommended water temperature value at the current time point based on the user preference-environmental condition characterization vector, and control the output of the heating element based on the recommended water temperature value.
2. The intelligent bathtub temperature control system according to claim 1, characterized in that: The environmental condition data regularization time series capture module includes: A parameter sample time dimension arrangement unit, used for regularizing the environmental condition data at a plurality of predetermined time points within the predetermined time period according to the parameter sample dimension and the time dimension to obtain a sequence of the environmental condition data time series input vectors; The environmental parameter time series feature extraction unit is used to input the sequence of the environmental condition data time series input vectors into the environmental condition parameter time series capture model based on the deep neural network to obtain the sequence of the environmental condition data time series feature vectors.
3. The intelligent bathtub temperature control system according to claim 2, characterized in that: The environmental condition parameter time series capture model based on a deep neural network is an environmental condition parameter time series capture model based on a one-dimensional convolutional network.
4. The intelligent bathtub temperature control system according to claim 3, characterized in that: The parameter timing association module is used to: The sequence of the environmental condition data time series feature vectors is input into a converter-based environmental condition parameter time series association extractor to obtain the environmental condition parameter time series association feature vectors.
5. The intelligent bathtub temperature control system according to claim 4, characterized in that: The user historical preference data semantic encoding module is used to: The user historical preference data is input into a user preference semantic feature extractor based on a Bi-LSTM model to obtain a semantic encoding feature vector of the user historical preference data.
6. The intelligent bathtub temperature control system according to claim 5, characterized in that: The user preference environment condition feature fusion module includes: A user history preference metric perception optimization unit, configured to perform viewpoint metric perception optimization based on inverse error detection on the user history preference data semantic encoding feature vector based on the environmental condition parameter time series association feature vector to obtain an optimized user history preference data semantic encoding feature vector; The optimized user historical preference-environmental condition parameter feature fusion unit is used to perform feature fusion on the environmental condition parameter time series association feature vector and the optimized user historical preference data semantic coding feature vector to obtain the user preference-environmental condition representation vector.
7. The intelligent bathtub temperature control system according to claim 6, characterized in that: The user history preference metric perception optimization unit is used to: Calculating the position difference between the semantic encoding feature vector of the user historical preference data and the temporal association feature vector of the environmental condition parameter to obtain a first viewpoint metric representation vector; Calculate the position point multiplication between the semantic encoding feature vector of the user historical preference data and the temporal association feature vector of the environmental condition parameter to obtain a second viewpoint metric representation vector; Calculating the positional sum of the semantic encoding feature vector of the user historical preference data and the temporal association feature vector of the environmental condition parameter to obtain a third viewpoint metric representation vector; Calculating the gradient magnitude of each position in the first viewpoint metric representation vector, the second viewpoint metric representation vector, and the third viewpoint metric representation vector to obtain a first viewpoint metric perception vector, a second viewpoint metric perception vector, and a third viewpoint metric perception vector; Inputting the first viewpoint metric perception vector, the second viewpoint metric perception vector and the third viewpoint metric perception vector into a backward machine learning inverse multi-view perception optimization module to obtain a reverse multi-view perception optimization representation vector; The optimized semantic encoding feature vector of user historical preference data is obtained by calculating the position point multiplication between the reverse multi-view perception optimization representation vector and the semantic encoding feature vector of user historical preference data.
8. The intelligent bathtub temperature control system according to claim 7, characterized in that: The water temperature value recommendation module includes: A water temperature decoding value unit, used to input the user preference-environmental condition characterization vector into a decoder-based water temperature recommender to obtain a water temperature value recommended at a current time point; A heating element control unit is used to automatically control the output of the heating element based on the water temperature value recommended at the current time point.
Citation Information
Patent Citations
Three-dimension model observation view point generation method based on framework
CN102332176A
Smart water heater temperature adjustment method and device and water heater
CN104482656A
Rotary kiln sintering temperature prediction method based on hybrid deep neural network
CN111950191A
Intelligent shower control method and device, intelligent equipment and storage medium
CN114253190A
Water temperature adjusting method and device for water heater
CN114623603A
Cited By
Remote medical system and method based on 5G technology
CN119338743A
Health monitoring management system and method based on intelligent bathtub
CN120432115A
Warehousing temperature and humidity intelligent regulation and control method and system based on deep learning
CN120686931A
