Intelligent closestool self-adaptive control system

Abstract

The invention discloses an intelligent closestool adaptive control system, which relates to the technical field of intelligent closestools and comprises a pressure acquisition module, an impedance acquisition module, a user data acquisition module, a user identity matching module, a multispectral acquisition module, a dirt information analysis module, a flushing mode analysis module and an intelligent closestool decision module. The pressure acquisition module is used for acquiring user seating weight data when a user uses the closestool; the impedance acquisition module is used for acquiring user impedance data when a user sits on the closestool; the user data acquisition module is used for acquiring user identity recognition data; according to the intelligent closestool self-adaptive control system, the identity of the user is judged by collecting the gravity information and the impedance information when the user sits on the closestool, so that a personalized control strategy of the user is executed according to the identity of the user, and the possibility that the privacy of the user is invaded by video image monitoring required by face recognition is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent toilets, and in particular to an adaptive control system for an intelligent toilet. Background Art

[0002] Smart toilet technology integrates electronic sensing, automated control, and water-saving systems. Its core features include pressure / infrared sensors for automatic flushing, seat heating, and human body sensing. A built-in microcomputer chip regulates water temperature, pressure, and flushing mode, and supports variable frequency boosting to accommodate low-pressure environments. In recent years, the integration of the Internet of Things (IoT) and AI technologies has enabled some products to be remotely controlled via an app or to optimize water usage by learning user habits. Prior art publication CN119288031A discloses an adaptive smart toilet control system, comprising: a parameter setting module for setting operating parameters; an image acquisition module for acquiring a facial image of the current user; an identity recognition module for identifying the current user based on the facial image; a parameter matching module for matching corresponding operating parameters based on the user's identity identified by the identity recognition module; a sitting posture sensing module for identifying whether the current user is sitting on the seat; and a processor for controlling the adaptive smart toilet control system to perform relevant operations based on the operating parameters matched by the parameter matching module when the sitting posture sensing module detects that the current user is sitting on the seat. This existing technology can pre-set operating parameters for different users, automatically identify the user's identity before use, and automatically match the corresponding operating parameters according to the identified user identity, thereby greatly improving the user experience.

[0003] However, facial image recognition requires a high-definition camera to take a face photo. Installing a high-definition camera in the bathroom is likely to cause customers to worry about security and privacy issues. Without shooting with a camera, identity recognition cannot be achieved, and the toilet cannot be used to adaptively control the operation of the customer's identity, which has certain limitations. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent toilet adaptive control system to solve the above-mentioned deficiencies in the prior art.

[0005] To achieve the above-mentioned object, the present invention provides the following technical solutions: an intelligent toilet adaptive control system, comprising a pressure acquisition module, an impedance acquisition module, a user data acquisition module, a user identity matching module, a multi-spectral acquisition module, a waste information analysis module, a flushing mode analysis module, and an intelligent toilet decision module;

[0006] The pressure collection module is used to collect the user's seat weight data when the user uses the toilet;

[0007] The impedance acquisition module is used to collect user impedance data when the user sits on the toilet;

[0008] The user data collection module is used to collect user identification data;

[0009] The user identity matching module is used to perform user identity matching analysis based on the user seat weight data, user impedance data and user identity recognition data to generate user identity analysis data;

[0010] The multispectral acquisition module is used to collect multispectral data on the upper side of the inner wall of the toilet;

[0011] The dirt information analysis module is used to perform dirt information analysis based on the multispectral data and the dirt information multispectral feature data to generate dirt information analysis data;

[0012] The flushing pattern analysis module is used to perform flushing pattern category analysis processing based on multispectral data matching based on multispectral data, flushing pattern dirt information feature data and flushing pattern category data to generate flushing pattern category analysis data;

[0013] The smart toilet decision module is used to construct smart toilet feedback data and perform information feedback operations and smart toilet control operations based on the smart toilet feedback data.

[0014] Furthermore, the pressure collection module collects the user's seat weight data, including the following steps:

[0015] S11. Collect weight data of the user sitting on the smart toilet seat through a pressure sensor to generate user sitting weight data A, wherein the pressure sensor can be integrated on the smart toilet seat to detect the weight of the user sitting on the smart toilet seat.

[0016] Furthermore, the impedance acquisition module acquires user impedance data, including the following steps:

[0017] S21. The electrical impedance of the human body is measured by transmitting a low-voltage AC signal through multiple electrodes integrated on the seat of the smart toilet to generate user impedance data B. In one embodiment, the seat or contact surface of the smart toilet integrates multiple electrodes (such as 4-8), and the electrical impedance of different parts of the human body is measured by a low-voltage AC signal (the frequency is usually 20kHz-100kHz). For example, the electrodes on the feet and buttocks form a closed loop, and the body fat rate, water content and other parameters are analyzed by the impedance change when the current signal passes through the human tissue. A dedicated chip that supports 24-bit high-precision sampling is then used for signal amplification and filtering, and the impedance value is calculated in real time in combination with a 32-bit single-chip microcomputer; the difference in impedance characteristics of different users combined with the weight of the user's seat can be used for identity recognition.

[0018] Furthermore, the user data collection module collects user identification data, including the following steps:

[0019] S31. Collect user identity data C, wherein a network connection can be established between the mobile phone APP and the system, and the user identity data collected by the mobile phone APP is saved in the system;

[0020] S32. Collect user personalized control data D, select the collected user seat weight data A and user impedance data B as user reference seat weight data A0 and user reference impedance data B0, collect and combine the user reference seat weight data A0, user reference impedance data B0, user identity data C, and user personalized control data D to generate user identity recognition data E = (A0, B0, C, D). The user personalized control data D may include seat temperature, cleaning mode, etc.

[0021] Furthermore, the user identity matching module generates user identity analysis data, including the following steps:

[0022] S41. Based on the K-nearest neighbor algorithm, search for user identity recognition data E that matches the user seat weight data A and the user impedance data B to generate user identity analysis data E. fenxi .

[0023] Furthermore, the multispectral acquisition module acquires multispectral data, comprising the following steps:

[0024] S51, collect multispectral data of the upper side of the inner wall of the toilet through a multispectral sensor, and generate a multispectral data set F=(f1, ..., f w ,…,f υ ), w=1, 2, 3,…, υ, f w represents the multispectral data collected for the wth time, υ represents the maximum number of times multispectral data is collected, and f υ Represents the latest multispectral data; among them, multispectral sensors capture the reflection / transmission intensity of target objects at different wavelengths by emitting multiple narrow bands of light (such as visible light, near-infrared, mid-infrared, etc.), and based on the molecular structure of different substances (such as blood, organic matter, and microorganisms), they selectively absorb or reflect light of specific wavelengths, forming a unique spectral "fingerprint" to determine the component information in the sewage. For example, hemoglobin has a significant absorption peak in the near-infrared band (700-900nm) and can be used to detect occult blood in feces; glucose has characteristic absorption in the mid-infrared region (2.5-25μm) and can be used to detect whether the sugar content in urine is too high.

[0025] Furthermore, the dirt information analysis module generates dirt information analysis data, including the following steps:

[0026] S61, collecting multispectral characteristic data of dirt information, generating a multispectral characteristic data set of dirt information G=(g1, ..., g q ,…,g τ ), q=1, 2, 3,..., τ, g q represents the multispectral characteristic data of the qth category of pollution information, and τ represents the maximum number of categories of the multispectral characteristic data of pollution information; wherein the pollution information includes hemoglobin content, glucose content, etc.;

[0027] S62, based on K-nearest neighbor algorithm, search for the latest multispectral data f υ Matched dirt information multispectral feature data g q , generate the dirt information analysis data G fenxi .

[0028] Furthermore, the flushing pattern analysis module generates flushing pattern analysis data, including the following steps:

[0029] S71. Collect historical flushing pattern data for flushing away dirt and generate a flushing pattern data set r p represents the flushing mode data of the p-th flush, Indicates the maximum number of flush mode data;

[0030] S72, the flushing mode data r p The multispectral data f corresponding to the pollutants w Collect and combine to generate a multispectral data set of flushing patterns h′ p =(r p , f w ) represents the p-th flushing mode multispectral data;

[0031] S73, collect flushing mode category data, generate flushing mode category data set K = (k1, ..., k u ,…,k ψ ),u=1,2,3,…,ψ,k u represents the u-th flushing mode category data, ψ represents the maximum number of flushing mode categories;

[0032] S74, based on the double pointer algorithm, searching the flushing pattern multispectral data set H′ for the flushing pattern category k in the flushing pattern category data set K u Multispectral data h′ of the same flushing pattern p , generate the multispectral data set of flushing mode category K′=(k′1,…,k′ u ,…,k′ ψ ), k′ u represents the multispectral data of the u-th flushing mode category;

[0033] S75: Standardize the flushing mode category multispectral data set K′ and the multispectral data set F to generate a flushing mode category multispectral standardized data set K″=(k″1,…,k″ u ,…,k″ ψ ) and the multispectral normalized data set F′=(f1′,…,f′ w ,…,f υ ′);

[0034] S76, searching for the flushing mode multispectral standardized data set K″ that matches the latest multispectral standardized data f υ ′Matched flushing pattern category multispectral normalized data k″ u , generate flushing mode category analysis data F fenxi , including the following steps:

[0035] S761, initializing the algorithm parameters discovery probability P0 and maximum number of iterations T, and randomly generating N bird nests in the solution space of the flushing pattern multispectral standardized data set K″;

[0036] S762. Each bird's nest updates its position through the Levy flight mechanism. The formula for updating the nest position is as follows:

[0037]

[0038] Among them, x i represents the location of the i-th bird's nest, t represents the current number of iterations, κ is the step size control factor, η is the step size change harmonic factor, Levy(λ) represents the Levy random path, whose step size follows a heavy-tailed distribution and can be generated by the Mantegna algorithm;

[0039] S763, calculate the fitness value of each nest position. If the fitness value of the new nest position is less than that of the original nest position, update the nest position and update the nest position with the smallest fitness value among all nest positions as the optimal nest position x. best ;

[0040] S764. Generate a random number δ∈[0,1]. If δ>P0, update the current nest position to a random position to simulate the host's behavior of rebuilding the nest after discovering the presence of foreign eggs in the nest. The formula is as follows:

[0041]

[0042] Where α is the scaling factor, rand() represents the random perturbation vector;

[0043] S765: Determine whether the maximum number of iterations has been reached. If not, return to S762. If so, output the optimal nest position x. best Corresponding flushing mode category multispectral normalized data k″ u Corresponding flushing mode category data k u , generate flushing mode category analysis data F fenxi .

[0044] Furthermore, the smart toilet decision module constructs smart toilet feedback data and performs information feedback operations and smart toilet control operations based on the smart toilet feedback data, including the following steps:

[0045] S81, analyzing the user's seat weight data A and user identity data E fenxi , waste information analysis data G fenxi and flushing pattern category analysis data F fenxi Collect and combine to generate smart toilet feedback data L = (A, E fenxi , G fenxi , F fenxi );

[0046] S82, based on the user seat weight data A and user identity analysis data E in the smart toilet feedback data L. fenxi Carry out information feedback operation and according to the F in the L fenxi and E fenxi The user personalized control data D in the smart toilet is used to perform smart toilet control operations.

[0047] 1. Compared with the existing technology, the intelligent toilet adaptive control system provided by the present invention, by setting a pressure acquisition module, an impedance acquisition module, a user data acquisition module, a user identity matching module, a multi-spectral acquisition module, and a waste information analysis module, can determine the user's identity by collecting gravity information and impedance information when the user sits on the toilet, so as to implement a user personalized control strategy based on the user's identity, avoiding the possibility of video image monitoring that infringes on user privacy when using facial recognition.

[0048] 2. Compared with the existing technology, the present invention provides an adaptive control system for an intelligent toilet. By setting a flushing mode analysis module and an intelligent toilet decision module, the present invention can select a suitable flushing mode for flushing based on the relationship between the waste information collected by multi-spectral acquisition and the flushing mode with the least water consumption that can flush the waste clean. In this way, the intelligent toilet can adaptively select a flushing mode according to the different characteristics of the user's waste discharge information, thereby reducing the flushing volume while ensuring that the toilet is flushed cleanly, thereby saving water. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0050] Figure 1 A schematic diagram of the system structure provided by an embodiment of the present invention;

[0051] Figure 2 A diagram of the system implementation steps provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0053] Example embodiments will be described more fully hereinafter with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the scope of this disclosure to those skilled in the art.

[0054] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0055] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0056] The terms used herein are used only to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a," "an," and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements, and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof is not excluded.

[0057] The embodiments described herein may be described with reference to plan views and / or cross-sectional views, with the aid of idealized schematic diagrams of the present disclosure. Thus, the example illustrations may be modified based on manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings are schematic in nature, and the shapes of the regions shown in the drawings illustrate specific shapes of the regions of the elements, but are not intended to be limiting.

[0058] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless expressly defined as such herein.

[0059] See also Figure 1 , an intelligent toilet adaptive control system, including a pressure acquisition module, an impedance acquisition module, a user data acquisition module, a user identity matching module, a multi-spectral acquisition module, a waste information analysis module, a flushing mode analysis module, and an intelligent toilet decision module;

[0060] The pressure collection module is used to collect the user's seat weight data when the user uses the toilet;

[0061] The impedance acquisition module is used to collect user impedance data when the user sits on the toilet;

[0062] The user data collection module is used to collect user identification data;

[0063] The user identity matching module is used to perform user identity matching analysis based on the user's seat weight data, user impedance data and user identity recognition data to generate user identity analysis data;

[0064] The multispectral acquisition module is used to collect multispectral data from the upper side of the toilet inner wall;

[0065] The dirt information analysis module is used to perform dirt information analysis based on the multispectral data and the dirt information multispectral feature data to generate dirt information analysis data;

[0066] The flushing pattern analysis module is used to perform flushing pattern category analysis processing based on multispectral data matching based on multispectral data, flushing pattern dirt information feature data and flushing pattern category data, and generate flushing pattern category analysis data;

[0067] See also Figure 2 ,The smart toilet decision module is used to construct smart toilet feedback data, and ,perform information feedback operations and smart toilet control operations based on the ,smart toilet feedback data.

[0068] The system provided by the present invention realizes adaptive control of the smart toilet through the following steps:

[0069] S1. The pressure collection module collects the user's seat weight data, including the following steps:

[0070] S11. Collect weight data of the user sitting on the smart toilet seat through a pressure sensor to generate user sitting weight data A, wherein the pressure sensor can be integrated on the smart toilet seat to detect the weight of the user sitting on the smart toilet seat.

[0071] S2, the impedance acquisition module collects user impedance data, including the following steps:

[0072] S21. The electrical impedance of the human body is measured by transmitting a low-voltage AC signal through multiple electrodes integrated on the seat of the smart toilet to generate user impedance data B. In one embodiment, the seat or contact surface of the smart toilet integrates multiple electrodes (such as 4-8), and the electrical impedance of different parts of the human body is measured by a low-voltage AC signal (the frequency is usually 20kHz-100kHz). For example, the electrodes on the feet and buttocks form a closed loop, and the body fat rate, water content and other parameters are analyzed by the impedance change when the current signal passes through the human tissue. A dedicated chip that supports 24-bit high-precision sampling is then used for signal amplification and filtering, and the impedance value is calculated in real time in combination with a 32-bit single-chip microcomputer; the difference in impedance characteristics of different users combined with the weight of the user's seat can be used for identity recognition.

[0073] S3, the user data collection module collects user identification data, including the following steps:

[0074] S31. Collect user identity data C, wherein a network connection can be established between the mobile phone APP and the system, and the user identity data collected by the mobile phone APP is saved in the system;

[0075] S32. Collect user personalized control data D, select the collected user seat weight data A and user impedance data B as user reference seat weight data A0 and user reference impedance data B0, collect and combine the user reference seat weight data A0, user reference impedance data B0, user identity data C, and user personalized control data D to generate user identity recognition data E = (A0, B0, C, D). The user personalized control data D may include seat temperature, cleaning mode, etc.

[0076] S4. The user identity matching module generates user identity analysis data, including the following steps:

[0077] S41. Based on the K-nearest neighbor algorithm, search for user identity recognition data E that matches the user seat weight data A and the user impedance data B to generate user identity analysis data E. fenxi .

[0078] S5, the multispectral acquisition module collects multispectral data, including the following steps:

[0079] S51, collect multispectral data of the upper side of the inner wall of the toilet through a multispectral sensor, and generate a multispectral data set F=(f1, ..., f w ,…,f υ ), w=1, 2, 3,…, υ, f w represents the multispectral data collected for the wth time, υ represents the maximum number of times multispectral data is collected, and f υ Represents the latest multispectral data; among them, multispectral sensors capture the reflection / transmission intensity of target objects at different wavelengths by emitting multiple narrow bands of light (such as visible light, near-infrared, mid-infrared, etc.), and based on the molecular structure of different substances (such as blood, organic matter, and microorganisms), they selectively absorb or reflect light of specific wavelengths, forming a unique spectral "fingerprint" to determine the component information in the sewage. For example, hemoglobin has a significant absorption peak in the near-infrared band (700-900nm) and can be used to detect occult blood in feces; glucose has characteristic absorption in the mid-infrared region (2.5-25μm) and can be used to detect whether the sugar content in urine is too high.

[0080] S6. The dirt information analysis module generates dirt information analysis data, including the following steps:

[0081] S61, collecting multispectral characteristic data of dirt information, generating a multispectral characteristic data set of dirt information G=(g1, ..., g q ,…,g τ ), q=1, 2, 3,..., τ, g q represents the multispectral characteristic data of the qth category of pollution information, and τ represents the maximum number of categories of the multispectral characteristic data of pollution information; wherein the pollution information includes hemoglobin content, glucose content, etc.;

[0082] S62, based on K-nearest neighbor algorithm, search for the latest multispectral data f υ Matched dirt information multispectral feature data g q , generate pollution information analysis data G fenxi .

[0083] S7. The flushing pattern analysis module generates flushing pattern analysis data, including the following steps:

[0084] S71. Collect historical flushing pattern data for flushing away dirt and generate a flushing pattern data set r p represents the flushing mode data of the p-th flush, Indicates the maximum number of flushing mode data; among them, the historical flushing mode data for flushing away dirt selects the flushing mode with the minimum water consumption that can flush away dirt, so as to save water and reduce water resource waste;

[0085] S72, flushing water mode datap The multispectral data f corresponding to the pollutants w Collect and combine to generate a multispectral data set of flushing patterns h′ p =(r p , f w ) represents the p-th flushing mode multispectral data;

[0086] S73, collect flushing mode category data, generate flushing mode category data set K = (k1, ..., k u ,…,k ψ ),u=1,2,3,…,ψ,k u represents the u-th flushing mode category data, ψ represents the maximum number of flushing mode categories;

[0087] S74. Based on the double pointer algorithm, search for the flushing pattern multispectral data set H′ and the flushing pattern category data set K for the flushing pattern category k. u Multispectral data h′ of the same flushing pattern p , generate the multispectral data set of flushing mode category K′=(k′1,…,k′ u ,…,k′ ψ ), k′ u represents the multispectral data of the u-th flushing mode category;

[0088] S75, normalize the flushing mode category multispectral data set K′ and the multispectral data set F to generate a flushing mode category multispectral standardized data set K″=(k″1,…,k″ u ,…,k″ ψ ) and the multispectral normalized data set F′=(f1′,…,f′ w ,…,f υ ′);

[0089] S76, searching for the flushing mode multispectral standardized data set K″ that matches the latest multispectral standardized data f υ ′Matched flushing pattern category multispectral normalized data k″ u , generate flushing mode category analysis data F fenxi , including the following steps:

[0090] S761, initializing the algorithm parameters discovery probability P0 and maximum number of iterations T, and randomly generating N bird nests in the solution space of the flushing pattern multispectral standardized data set K″;

[0091] S762. Each bird's nest updates its position through the Levy flight mechanism. The formula for updating the nest position is as follows:

[0092]

[0093] Among them, x i represents the location of the i-th bird's nest, t represents the current number of iterations, κ is the step size control factor, η is the step size change harmonic factor, Levy(λ) represents the Levy random path, whose step size follows a heavy-tailed distribution and can be generated by the Mantegna algorithm;

[0094] S763, calculate the fitness value of each nest position. If the fitness value of the new nest position is less than that of the original nest position, update the nest position and update the nest position with the smallest fitness value among all nest positions as the optimal nest position x. best ;

[0095] S764. Generate a random number δ∈[0,1]. If δ>P0, update the current nest position to a random position to simulate the host's behavior of rebuilding the nest after discovering the presence of foreign eggs in the nest. The formula is as follows:

[0096]

[0097] Where α is the scaling factor, rand() represents the random perturbation vector;

[0098] S765: Determine whether the maximum number of iterations has been reached. If not, return to S762. If so, output the optimal nest position x. best Corresponding flushing mode category multispectral normalized data k″ u Corresponding flushing mode category data k u , generate flushing mode category analysis data F fenxi .

[0099] S8, the smart toilet decision module constructs smart toilet feedback data and performs information feedback operations and smart toilet control operations based on the smart toilet feedback data, including the following steps:

[0100] S81. Analyze user's seat weight data A and user identity data E. fenxi , waste information analysis data G fenxi and flushing pattern category analysis data F fenxi Collect and combine to generate smart toilet feedback data L = (A, E fenxi , G fenxi , F fenxi );

[0101] S82, based on the user seat weight data A and user identity analysis data E in the smart toilet feedback data L. fenxi Conduct information feedback and follow the L fenxi and E fenxiThe user personalized control data D in the smart toilet is used to perform smart toilet control operations.

[0102] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. An intelligent toilet adaptive control system, characterized by: It includes pressure acquisition module, impedance acquisition module, user data acquisition module, user identity matching module, multi-spectral acquisition module, waste information analysis module, flushing mode analysis module, and smart toilet decision module; The pressure collection module is used to collect the user's seat weight data when the user uses the toilet; The impedance acquisition module is used to collect user impedance data when the user sits on the toilet; The user data collection module is used to collect user identification data; The user identity matching module is used to perform user identity matching analysis based on the user seat weight data, user impedance data and user identity recognition data to generate user identity analysis data; The multispectral acquisition module is used to collect multispectral data on the upper side of the inner wall of the toilet; The dirt information analysis module is used to perform dirt information analysis based on the multispectral data and the dirt information multispectral feature data to generate dirt information analysis data; The flushing pattern analysis module is used to perform flushing pattern category analysis processing based on multispectral data matching based on multispectral data, flushing pattern dirt information feature data and flushing pattern category data to generate flushing pattern category analysis data; The smart toilet decision module is used to construct smart toilet feedback data and perform information feedback operations and smart toilet control operations based on the smart toilet feedback data.

2. The intelligent toilet adaptive control system according to claim 1, characterized in that: The pressure collection module collects the user's seat weight data, including the following steps: S11. The weight data of the user sitting on the smart toilet seat is collected through a pressure sensor to generate user sitting weight data A.

3. The intelligent toilet adaptive control system according to claim 2, characterized in that: The impedance acquisition module acquires user impedance data, comprising the following steps: S21. The user impedance data B is generated by transmitting a low-voltage AC signal by integrating multiple electrodes on the smart toilet seat to measure the human body's electrical impedance.

4. The intelligent toilet adaptive control system according to claim 3, characterized in that: The user data collection module collects user identification data, including the following steps: S31, collecting user identity data C; S32. Collect user personalized control data D, select the collected user seating weight data A and user impedance data B as user reference seating weight data A0 and user reference impedance data B0, collect and combine the user reference seating weight data A0, user reference impedance data B0, user identity data C and user personalized control data D, and generate user identity recognition data E = (A0, B0, C, D).

5. The intelligent toilet adaptive control system according to claim 4, characterized in that: The user identity matching module generates user identity analysis data, including the following steps: S41. Based on the K-nearest neighbor algorithm, search for user identity recognition data E that matches the user seat weight data A and the user impedance data B to generate user identity analysis data E. fenxi .

6. The intelligent toilet adaptive control system according to claim 5, characterized in that: The multispectral acquisition module acquires multispectral data, comprising the following steps: S51, collect multispectral data of the upper side of the inner wall of the toilet through a multispectral sensor, and generate a multispectral data set F=(f1, ..., f w ,…,f υ ), w=1, 2, 3,…, υ, f w represents the multispectral data collected for the wth time, υ represents the maximum number of times multispectral data is collected, and f υ Indicates the latest multispectral data.

7. The intelligent toilet adaptive control system according to claim 6, characterized in that: The dirt information analysis module generates dirt information analysis data, comprising the following steps: S61, collecting multispectral characteristic data of pollution information, generating a multispectral characteristic data set of pollution information G = (g1, ..., g q ,…,g τ ), q=1, 2, 3,..., τ, g q represents the multispectral feature data of the qth category of pollution information, and τ represents the maximum number of categories of the multispectral feature data of pollution information; S62, based on K-nearest neighbor algorithm, search for the latest multispectral data f υ Matched dirt information multispectral feature data g q , generate the dirt information analysis data G fenxi .

8. The intelligent toilet adaptive control system according to claim 7, characterized in that: The flushing pattern analysis module generates flushing pattern analysis data, including the following steps: S71. Collect historical flushing pattern data for flushing away dirt and generate a flushing pattern data set r p represents the flushing mode data of the p-th flush, Indicates the maximum number of flush mode data; S72, the flushing mode data r p The multispectral data f corresponding to the pollutants w Collect and combine to generate a multispectral data set of flushing patterns h′ p =(r p , f w ) represents the p-th flushing mode multispectral data; S73, collect flushing mode category data, generate flushing mode category data set K = (k1, ..., k u ,…,k ψ ),u=1,2,3,…,ψ,k u represents the u-th flushing mode category data, ψ represents the maximum number of flushing mode categories; S74, based on the double pointer algorithm, searching the flushing pattern multispectral data set H′ for the flushing pattern category k in the flushing pattern category data set K u Multispectral data h′ of the same flushing pattern p , generate the multispectral data set of flushing mode category K′=(k′1,…,k′ u ,…,k′ ψ ), k′ u represents the multispectral data of the u-th flushing mode category; S75: Standardize the flushing mode category multispectral data set K′ and the multispectral data set F to generate a flushing mode category multispectral standardized data set K″=(k″1,…,k″ u ,…,k″ ψ ) and the multispectral normalized data set F′=(f′1,…,f′ w ,…,f′ υ ); S76, searching for the latest multispectral standardized data f′ in the flushing mode multispectral standardized data set K″. υ Matched flushing pattern category multispectral normalized data k″ u , generate flushing mode category analysis data F fenxi , including the following steps: S761, initializing the algorithm parameters discovery probability P0 and maximum number of iterations T, and randomly generating N bird nests in the solution space of the flushing pattern multispectral standardized data set K″; S762. Each bird's nest updates its position through the Levy flight mechanism. The formula for updating the nest position is as follows: Among them, x i represents the location of the i-th bird's nest, t represents the current number of iterations, κ is the step size control factor, and Levy (λ) represents the Levy random path; S763, calculate the fitness value of each nest position. If the fitness value of the new nest position is less than that of the original nest position, update the nest position and update the nest position with the smallest fitness value among all nest positions as the optimal nest position x. best ; S764. Generate a random number δ∈[0,1]. If δ>P0, update the current nest position to a random position. The formula is as follows: Where α is the scaling factor, rand() represents the random perturbation vector; S765: Determine whether the maximum number of iterations has been reached. If not, return to S762. If so, output the optimal nest position x. best Corresponding flushing mode category multispectral normalized data k″ u Corresponding flushing mode category data k u , generate flushing mode category analysis data F fenxi .

9. The intelligent toilet adaptive control system according to claim 8, characterized in that: The smart toilet decision module constructs smart toilet feedback data and performs information feedback operations and smart toilet control operations based on the smart toilet feedback data, including the following steps: S81, analyzing the user's seat weight data A and user identity data E fenxi , waste information analysis data G fenxi and flushing pattern category analysis data F fenxi Collect and combine to generate smart toilet feedback data L = (A, E fenxi , G fenxi , F fenxi ); S82, based on the user seat weight data A and user identity analysis data E in the smart toilet feedback data L. fenxi Carry out information feedback operation and according to the F in the L fenxi and E fenxi The user personalized control data D in the smart toilet is used to perform smart toilet control operations.

Images