Flushing control method and system, intelligent closestool, medium and product

Abstract

The invention discloses a flushing control method and system, an intelligent closestool, a medium and a product. The method comprises the following steps: inputting pre-acquired human body excrement parameters corresponding to a user sitting on the intelligent closestool into a target prediction model to obtain an initial flushing mode; determining an actual prediction confidence value according to the initial flushing mode and a predetermined identification result non-conflict value; determining a target flushing mode of the intelligent closestool according to the actual prediction confidence value and the initial flushing mode; and executing the flushing operation by adopting the target flushing amount associated with the target flushing mode. The technical problem that the flushing amount of the intelligent closestool cannot be dynamically controlled by adapting to the habit change of a user in real time when the closestool is flushed by adopting a fixed water amount in the prior art is solved, so that the flushing amount of the intelligent closestool is dynamically controlled according to the habit of the user in real time in a self-adaptive manner, that is, water is supplied as required, and the user experience is improved. The flushing cleanliness is guaranteed, waste of water resources is avoided, and meanwhile the use experience and the equipment adaptability are improved.

Description

Technical Field

[0001] This invention relates to the field of smart bathroom technology, and in particular to a flushing control method, system, smart toilet, medium, and product. Background Technology

[0002] As people's living standards continue to improve, the functions of smart homes are also constantly being enhanced. When toilets in bathrooms are flushed, they generally output a fixed amount of water, which cannot dynamically and adaptively adjust the flushing volume to adapt to users' habits in real time. Summary of the Invention

[0003] This invention provides a flushing control method, system, smart toilet, medium, and product to solve the technical problem in the prior art of dynamically controlling the flushing volume of smart toilets in real time to adapt to changes in user habits.

[0004] According to one aspect of the present invention, a flushing control method is provided, comprising:

[0005] The pre-acquired parameters of human excrement corresponding to the user sitting on the smart toilet are input into the target prediction model to obtain the initial flushing mode.

[0006] The actual prediction confidence value is determined based on the initial flushing pattern and the pre-determined non-conflict value of the identification result;

[0007] The target flushing mode of the smart toilet is determined based on the actual predicted confidence value and the initial flushing mode.

[0008] The flushing operation is performed using a target flushing volume associated with the target flushing mode.

[0009] According to another aspect of the present invention, a flushing control device is provided, comprising:

[0010] The pattern prediction module is used to input the pre-acquired human excrement parameters corresponding to the user sitting on the smart toilet into the target prediction model to obtain the initial flushing pattern.

[0011] The confidence value determination module is used to determine the actual predicted confidence value based on the initial flushing pattern and the pre-determined non-conflict value of the identification result;

[0012] The mode determination module is used to determine the target flushing mode of the smart toilet based on the actual predicted confidence value and the initial flushing mode.

[0013] A flushing control module is used to perform a flushing operation with a target flushing volume associated with the target flushing mode.

[0014] According to another aspect of the present invention, a flushing control system is provided, comprising: a smart toilet and a cloud server; wherein the smart toilet establishes a communication connection with the cloud server;

[0015] The cloud server is used to send a pre-created target prediction model to the smart toilet;

[0016] The smart toilet is used to input the pre-acquired human excrement parameters corresponding to the user sitting on the smart toilet into the target prediction model to obtain an initial flushing mode, and to determine the actual prediction confidence value based on the initial flushing mode and the pre-determined non-conflict value of the recognition result, and to determine the target flushing mode of the smart toilet based on the actual prediction confidence value and the initial flushing mode, and to perform the flushing operation using the target flushing volume associated with the target flushing mode.

[0017] According to another aspect of the present invention, a smart toilet is provided, the smart toilet comprising: a communication module, at least one main controller; and

[0018] A memory that is communicatively connected to the at least one main controller;

[0019] The communication module is used to establish a communication connection with the cloud server.

[0020] The memory stores a computer program that can be executed by the at least one main controller, which enables the at least one main controller to perform the flushing control method according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a main controller to execute and implement the flushing control method according to any embodiment of the present invention.

[0022] According to another aspect of the present invention, a computer program product is provided, the computer program product comprising a computer program that, when executed by a main controller, implements the flushing control method described in any embodiment of the present invention.

[0023] The technical solution of this invention obtains the human excrement parameters corresponding to the user sitting on the smart toilet, inputs these parameters into the target prediction model to obtain the initial flushing mode, determines the actual prediction confidence value based on the initial flushing mode and a pre-determined non-conflict value of the recognition result, and determines the target flushing mode of the smart toilet based on the actual prediction confidence value and the initial flushing mode. The flushing operation is then performed according to the target flushing volume corresponding to the target flushing mode. This solves the technical problem in the prior art where a fixed water volume is used for toilet flushing, making it impossible to dynamically control the flushing volume of the smart toilet in real time to adapt to changes in user habits. Therefore, it achieves real-time adaptive dynamic control of the flushing volume of the smart toilet according to user habits, realizing on-demand water supply, ensuring flushing cleanliness, avoiding water waste, and improving user experience and device compatibility.

[0024] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a flowchart of a flushing control method provided in an embodiment of the present invention;

[0027] Figure 2 This is a flowchart of another flushing control method provided in an embodiment of the present invention;

[0028] Figure 3 This is a flowchart of another flushing control method provided in an embodiment of the present invention;

[0029] Figure 4 This is a flowchart of another flushing control method provided in an embodiment of the present invention;

[0030] Figure 5 This is a schematic diagram of the structure of a flushing control device provided in an embodiment of the present invention;

[0031] Figure 6 This is a schematic diagram of a flushing control system provided in an embodiment of the present invention;

[0032] Figure 7 This is a structural block diagram of a smart toilet provided in an embodiment of the present invention. Detailed Implementation

[0033] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0035] In one embodiment, Figure 1 This is a flowchart of a flushing control method provided in an embodiment of the present invention. This embodiment is applicable to situations where the flushing volume of a smart toilet needs to be dynamically controlled. The method can be executed by a flushing control device, which can be implemented in hardware and / or software and can be configured in the smart toilet. Figure 1 As shown, the method includes:

[0036] S110. Input the pre-acquired human excrement parameters corresponding to the user sitting on the smart toilet into the target prediction model to obtain the initial flushing mode.

[0037] In one example, a pressure sensor can be configured on the toilet seat of the smart toilet to detect in real time whether a user is sitting on the smart toilet. If a change in pressure value is detected, it indicates that a user is sitting on the smart toilet.

[0038] In one example, the target prediction model refers to a pre-created model used to predict the flushing patterns of a smart toilet. This target prediction model can be an embedded machine learning model. This model can be trained on a cloud server. A communication connection is established between the cloud server and the smart toilet. For example, the cloud server can remotely push the pre-trained and created target prediction model to the smart toilet via Over-The-Air (OTA) technology, or remotely push a retrained target prediction model to the smart toilet to configure or update the target prediction model configured in the smart toilet. Before the smart toilet leaves the factory, the model can be trained with a large amount of test data to obtain a target prediction model with high prediction accuracy, and the trained target prediction model is then embedded into the smart toilet as the device.

[0039] In one example, human excrement parameters refer to relevant indicator data used in a smart toilet to describe and analyze the characteristics of human excrement. In one example, when a user is detected sitting on the smart toilet, an optical sensor and a pressure sensor located at the bottom can be activated to collect human excrement parameters in real time. In one example, human excrement parameters may include, but are not limited to, at least one of the following: excrement impact force; excrement shape; excrement drop height; impact force fluctuation duration; and excrement density. Specifically, excrement impact force refers to the magnitude of the impact force generated when human excrement falls onto the toilet bowl. A pressure sensor can be installed at the bottom of the smart toilet to detect the excrement impact force. Excrement shape characterizes whether human excrement is formed; for example, if the excrement is formed, it is solid; if it is not formed, it is liquid. Impact force fluctuation duration refers to the duration of the impact force fluctuation each time human excrement falls into the water. Excrement density quantifies the density or thinness of human excrement and can be the mass per unit volume of human excrement. In actual operation, users may have multiple defecation behaviors during defecation. In order to ensure the accuracy of the maximum flush volume, the peak value of the impact force of multiple excrement falling corresponding to multiple defecation behaviors, as well as the shape of multiple excrement and the duration of multiple impact force fluctuations, can be input into the target prediction model to obtain the initial flushing mode.

[0040] In one example, the initial flushing mode refers to the preset flushing method used by the smart toilet when initiating the flushing process. In this example, each initial flushing mode includes a flush volume and a mode percentage. The flush volume of each initial flushing mode is different, and the sum of the mode percentages corresponding to all initial flushing modes is 1. For example, suppose the target prediction model outputs three different initial flushing modes: Mode 1, Mode 2, and Mode 3; Mode 1 corresponds to a flush volume of 1 liter (L) and a mode percentage of 0.12; Mode 2 corresponds to a flush volume of 1.3L and a mode percentage of 0.75; and Mode 3 corresponds to a flush volume of 1.5L and a mode percentage of 0.13.

[0041] In one example, a smart toilet, as a device, can input pre-collected data on the impact force of falling excrement, the shape of the excrement, and the duration of the impact force fluctuation into a target prediction model. The target prediction model can then perform inference and output the corresponding initial flushing mode.

[0042] S120. Determine the actual prediction confidence value based on the initial flushing pattern and the pre-determined non-conflict value of the identification result.

[0043] In one example, the non-collision value of the identification result is used to characterize the degree of conflict between the shape of the excrement identified by the optical sensor and the volume of the excrement corresponding to the impact force of the excrement falling, as identified by the pressure sensor. Generally, the non-collision value of the identification result can be represented as a percentage, and the maximum value of the non-collision value of the identification result is 100%. It can be understood that the degree of conflict between the shape of the excrement identified by the optical sensor and the volume of the excrement corresponding to the impact force of the excrement falling, as identified by the pressure sensor, is inversely proportional to the non-collision value of the identification result. That is, the greater the degree of conflict between the shape of the excrement identified by the optical sensor and the volume of the excrement corresponding to the impact force of the excrement falling, as identified by the pressure sensor, the smaller the corresponding non-collision value of the identification result. For example, assuming the degree of conflict between the shape of the excrement identified by the optical sensor and the volume of the excrement corresponding to the impact force of the excrement falling identified by the pressure sensor is severe, the non-conflict value of the identification result is 70%; assuming the degree of conflict between the shape of the excrement identified by the optical sensor and the volume of the excrement corresponding to the impact force of the excrement falling identified by the pressure sensor is moderate, the non-conflict value of the identification result is 80%; assuming the degree of conflict between the shape of the excrement identified by the optical sensor and the volume of the excrement corresponding to the impact force of the excrement falling identified by the pressure sensor is no conflict, the non-conflict value of the identification result is 100%.

[0044] In one example, the actual prediction confidence value is used to characterize the credibility of the initial flushing patterns output by the target prediction model. The actual prediction confidence value can be the product of the maximum pattern percentage corresponding to the multiple initial flushing patterns output by the target prediction model and the non-conflict value of the identification result. For example, assuming the non-conflict value of the identification result is 80%, and the initial flushing patterns output by the target prediction model include pattern 1, pattern 2, and pattern 3, and the pattern percentages corresponding to pattern 1, pattern 2, and pattern 3 are 0.12, 0.75, and 0.13 respectively; then the maximum pattern percentage corresponding to the multiple initial flushing patterns is 0.75, and the actual prediction confidence value is the product of 0.75 and 80%, i.e., the actual prediction confidence value is 0.6.

[0045] S130. Determine the target flushing mode of the smart toilet based on the actual predicted confidence value and the initial flushing mode.

[0046] In one example, the target flushing mode refers to the final flushing mode adjusted by the smart toilet based on the initial flushing mode after further detection and analysis, in order to achieve a better flushing effect or meet specific needs. In another example, when the actual prediction confidence value is greater than the preset prediction confidence threshold, it indicates that the initial flushing mode corresponding to the maximum mode proportion output by the target prediction model is reliable. This can also be understood as the flushing volume corresponding to the initial flushing mode with the maximum mode proportion being sufficient to handle the amount of human excrement. In other words, the flushing volume corresponding to the initial flushing mode with the maximum mode proportion can effectively flush away human excrement. In this case, the initial flushing mode can be directly used as the target flushing mode for the smart toilet.

[0047] In one example, if the actual prediction confidence value is less than the preset prediction confidence threshold, the initial flushing mode corresponding to the maximum mode proportion output by the target prediction model is unreliable. In this case, the mode can be incremented by one based on the initial flushing mode corresponding to the maximum mode proportion, that is, the next mode corresponding to the initial flushing mode can be used as the target flushing mode of the smart toilet. For example, suppose the initial flushing mode corresponding to the maximum mode proportion output by the target prediction model is mode 2, the mode proportion is 0.75, and the non-conflict value of the recognition result is 80%, and the preset prediction confidence threshold is 0.7. Then the actual prediction confidence value is equal to the product of the mode proportion (0.75) and the non-conflict value of the recognition result (80%), which is 0.6. In addition, the actual prediction confidence value corresponding to mode 2 is less than the preset prediction confidence threshold of 0.7. It can also be understood that the flushing volume corresponding to the initial flushing mode corresponding to the maximum mode proportion (i.e. mode 2) cannot meet the amount of human excrement. That is, the flushing volume corresponding to the initial flushing mode corresponding to the maximum mode proportion (i.e. mode 2) cannot clean the human excrement. At this time, the next mode corresponding to mode 2 (i.e. mode 3) can be used as the target flushing mode of the smart toilet.

[0048] S140, Perform the flushing operation using the target flushing volume associated with the target flushing mode.

[0049] It's important to note that each target flushing mode is associated with a target flush volume. After the smart toilet determines the target flushing mode, it can directly use the target flush volume corresponding to that mode to perform the flushing operation. For example, assuming the target flushing mode is mode 3, the smart toilet will directly use a target flush volume of 1.5L to perform the flushing operation. It's also worth noting that the flushing operation can be performed using the target flush volume associated with the target flushing mode after detecting that the user has left the toilet seat, thus avoiding water splashing onto the user and effectively improving the user experience.

[0050] The technical solution of this embodiment obtains the human excrement parameters corresponding to the user sitting on the smart toilet, inputs these parameters into the target prediction model to obtain the initial flushing mode, determines the actual prediction confidence value based on the initial flushing mode and a pre-determined non-conflict value of the recognition result, and determines the target flushing mode of the smart toilet based on the actual prediction confidence value and the initial flushing mode. The flushing operation is then performed according to the target flushing volume corresponding to the target flushing mode. This solves the technical problem in the prior art where a fixed water volume is used for toilet flushing, making it impossible to dynamically control the flushing volume of the smart toilet in real time to adapt to changes in user habits. Therefore, it achieves real-time adaptive dynamic control of the flushing volume of the smart toilet according to user habits, realizing on-demand water supply, ensuring flushing cleanliness, avoiding water waste, and improving user experience and device compatibility.

[0051] In one embodiment, Figure 2 This is a flowchart of another flushing control method provided by an embodiment of the present invention. This embodiment elaborates on the process of determining the non-conflicting value of the identification result based on the above embodiment. Figure 2 As shown, the method includes:

[0052] S210. Input the pre-acquired human excrement parameters corresponding to the user sitting on the smart toilet into the target prediction model to obtain the initial flushing mode.

[0053] S220 uses a pressure sensor in a smart toilet to obtain the impact force of human excrement falling.

[0054] In one example, a pressure sensor can be installed at the bottom of the smart toilet. When a user is detected sitting on the smart toilet, the pressure sensor can be activated to detect the impact force of human excrement falling in real time.

[0055] S230. Determine the volume of excrement based on the impact force of the excrement falling, the height of the excrement falling, the duration of the impact force fluctuation, and the density of the excrement.

[0056] In one example, the height of excrement falling refers to the relative distance between the human excrement from the discharge point and the water surface inside the toilet. In actual operation, the relative distance between the toilet seat and the water surface inside the toilet can be used to represent this.

[0057] In practice, the mass of excrement can be calculated based on the impact force of the falling excrement, the height of the falling excrement, and the duration of the impact force fluctuation. The volume of excrement is then calculated using the ratio between its mass and density. For example, the formula for calculating the mass of excrement can be: The formula for calculating excrement volume can be: ;in, For the quality of excrement; The impact force of falling excrement; The height from which excrement falls; The duration of the impact force fluctuation; This refers to the density of excrement. Generally, the density of human excrement, in the case of feces, can be 1.05 to 1.3 grams per cubic centimeter.

[0058] S240. Determine the degree of excrement recognition conflict based on the volume of excrement and the shape of excrement identified by the optical sensor in the smart toilet.

[0059] In one example, an optical sensor can be built into the smart toilet to analyze at least one of the following: color, texture, shape, and viscosity of human excrement, in order to determine the excrement shape corresponding to the human excrement.

[0060] In practice, when human excrement is feces, the density of the excrement is greater than... This can be understood as 50ml corresponding to at least 50g. If the excrement falls from a height of 40cm and the impact force fluctuation lasts for 0.1s, then using the above formula for calculating the excrement mass, the impact force should be greater than 1.3N. However, in reality, the pressure sensor detects an impact force of less than 1.3N. This means that the volume of excrement determined by the impact force, fall height, impact force fluctuation duration, and excrement density is less than 50ml. In this case, it can be understood that the excrement shape estimated by the pressure sensor is liquid, not solid; while the shape of the excrement identified by the optical sensor in the smart toilet is solid. Therefore, the excrement identification conflict level can be determined to be severe.

[0061] Similarly, if the shape of the excrement identified as liquid by the optical sensor in the smart toilet is actually greater than 200ml, but the volume of the excrement is determined by the impact force of the excrement falling, the height of the excrement falling, the duration of the impact force fluctuation, and the density of the excrement detected by the pressure sensor, it can be understood that the shape of the excrement estimated by the pressure sensor is solid. In this case, the degree of excrement identification conflict can be determined as moderate conflict.

[0062] In one example, if the optical sensor built into the smart toilet becomes dirty, the degree of excrement recognition conflict is directly determined to be a severe conflict. At this time, a large flush can be used to flush the toilet, and a voice alarm can be issued through the smart toilet's built-in voice playback module, or an alarm can be displayed on the smart toilet's built-in display screen to remind the user that the optical sensor is dirty.

[0063] In one example, if the pressure sensor fails to detect the impact of falling excrement within a certain period (e.g., 0.5 seconds) after the optical signal is triggered by the built-in optical sensor of the smart toilet, it is considered that the built-in timer of the smart toilet has timed out. The excrement recognition conflict is directly judged as a severe conflict. At this time, a large flushing volume can be used to flush the toilet, and a voice alarm can be issued through the built-in voice playback module of the smart toilet, or an alarm can be displayed on the built-in display screen of the smart toilet to remind the user that the optical sensor is dirty.

[0064] It should be noted that if the pressure sensor fails to detect the impact force of the falling excrement within a certain period after the optical signal is triggered, or if the optical sensor is damaged, a large volume of water will be used for flushing without performing the actual calculation of the predicted confidence value or related subsequent processes.

[0065] S250. Determine the non-conflict value of the identification result based on the degree of conflict in the excrement identification.

[0066] In one example, a mapping relationship between the degree of excrement identification conflict and the non-conflict value of the identification result can be pre-configured. After determining the degree of excrement identification conflict, the non-conflict value of the identification result corresponding to the degree of excrement identification conflict can be found based on the mapping relationship between the two.

[0067] For example, suppose that when the excrement identification conflict level is severe, the corresponding non-conflict value is 70%; when the excrement identification conflict level is moderate, the corresponding non-conflict value is 80%; and when the excrement identification conflict level is mild, the corresponding non-conflict value is 90%.

[0068] S260. Determine the actual prediction confidence value based on the initial flushing pattern and the pre-determined non-conflict value of the identification result.

[0069] S270. Determine the target flushing mode of the smart toilet based on the actual predicted confidence value and the initial flushing mode.

[0070] S280, Perform the flushing operation using the target flushing volume associated with the target flushing mode.

[0071] The technical solution of this embodiment, based on the above embodiments, uses a pressure sensor in the smart toilet to obtain the impact force of human excrement falling, and determines the volume of excrement based on the impact force, the height of the excrement falling, the duration of the impact force fluctuation, and the density of the excrement. It then determines the degree of conflict between the excrement volume and the shape of the excrement identified by the optical sensor in the smart toilet, and determines a non-conflict value based on the degree of conflict. This allows for the judgment of the accuracy of both optical and pressure sensor identification, effectively ensuring the accuracy of the target flushing mode and achieving on-demand water supply.

[0072] In one embodiment, Figure 3 This is a flowchart of another flushing control method provided by an embodiment of the present invention. This embodiment, based on the above embodiments, elaborates on the process of determining the actual predicted confidence value and the target flushing mode. Figure 3 As shown, the method includes:

[0073] S310. Input the pre-acquired human excrement parameters corresponding to the user sitting on the smart toilet into the target prediction model to obtain the initial flushing mode.

[0074] S320: Obtain the mode percentage corresponding to the initial flushing mode.

[0075] In one example, each initial flushing mode is configured with a mode percentage, and the sum of the mode percentages corresponding to all initial flushing modes is 1. In this embodiment, after outputting the initial flushing modes through the target prediction model, the mode percentage and flushing volume corresponding to each initial flushing mode can be obtained.

[0076] S330. The product of the pattern proportion and the predetermined non-conflict value of the identification result is used as the actual prediction confidence value.

[0077] In this embodiment, the product of the maximum pattern percentage associated with all initial flushing patterns and the pre-determined non-conflict value of the identification result can be used as the actual prediction confidence value.

[0078] S340. Determine the comparison result between the actual prediction confidence value and the preset prediction confidence threshold.

[0079] In one example, the preset prediction confidence threshold refers to a pre-configured threshold value used to characterize whether the initial flushing pattern corresponding to the largest pattern proportion is reliable. For example, the preset prediction confidence threshold can be 70%. This can be understood as follows: if the actual confidence level is less than the preset prediction confidence threshold, the initial flushing pattern corresponding to the largest pattern proportion is considered unreliable; if the actual confidence level is greater than the preset prediction confidence threshold, the initial flushing pattern corresponding to the largest pattern proportion is considered reliable.

[0080] S350. If the actual prediction confidence value is less than the preset prediction confidence threshold, then the next mode corresponding to the initial flushing mode will be used as the target flushing mode of the smart toilet.

[0081] In one example, if the actual confidence level associated with the initial flushing mode corresponding to the maximum mode percentage is less than the preset predicted confidence level threshold, it indicates that the initial flushing mode corresponding to the maximum mode percentage is unreliable. This can also be understood as the flushing volume associated with the initial flushing mode corresponding to the maximum mode percentage being insufficient to meet the flushing needs of the smart toilet. In this case, the next mode associated with the initial flushing mode corresponding to the maximum mode percentage can be used as the target flushing mode of the smart toilet, i.e., the flushing volume is increased to meet the flushing needs of the smart toilet.

[0082] S360. If the actual prediction confidence value is greater than the preset prediction confidence threshold, the initial flushing mode will be directly used as the target flushing mode of the smart toilet.

[0083] In one example, if the actual prediction confidence value associated with the initial flushing mode corresponding to the maximum mode percentage is greater than the preset prediction confidence threshold, it indicates that the initial flushing mode corresponding to the maximum mode percentage is reliable. It can also be understood that the flushing volume associated with the initial flushing mode corresponding to the maximum mode percentage can meet the flushing needs of the smart toilet. In this case, the initial flushing mode corresponding to the maximum mode percentage can be directly used as the target flushing mode of the smart toilet. That is, the flushing volume cannot be increased to meet the flushing needs of the smart toilet.

[0084] S370, Perform the flushing operation using a target flushing volume associated with the target flushing mode.

[0085] The technical solution of this embodiment, based on the above embodiment, compares the actual predicted confidence value associated with the initial flushing mode corresponding to the maximum mode proportion with a preset predicted confidence threshold. If the actual predicted confidence value is less than the preset predicted confidence threshold, the next mode corresponding to the initial flushing mode is taken as the target flushing mode of the smart toilet; if the actual predicted confidence value is greater than the preset predicted confidence threshold, the initial flushing mode is directly taken as the target flushing mode of the smart toilet, so as to effectively ensure that the determined target flushing mode meets the flushing needs of the smart toilet as much as possible.

[0086] In one embodiment, after performing a flushing operation using a target flushing volume associated with a target flushing mode, the flushing control method further includes: if the actual prediction confidence value is less than a preset prediction confidence threshold, reporting the human excrement parameters to a cloud server so that the cloud server can retrain the target prediction model to obtain a new target prediction model. In one example, if the actual prediction confidence value associated with the initial flushing mode corresponding to the maximum mode proportion is less than the preset prediction confidence threshold, it indicates that the initial flushing mode output by the target prediction model cannot meet the flushing needs of the smart toilet, that is, the prediction accuracy of the initial flushing mode output by the target prediction model is low. At this time, the main controller in the smart toilet can report the human excrement parameters to the cloud server with which a communication connection has been established through the communication module so that the cloud server can retrain the target prediction model to obtain a new target prediction model, and distribute the new target prediction model to the associated smart toilet within a specified time so that the main controller of the smart toilet can update the built-in target prediction model with the new target prediction model. This achieves the effect of continuous learning of the target prediction model built into the smart toilet, effectively ensuring the prediction accuracy of the target prediction model.

[0087] In one embodiment, after performing a flushing operation using a target flushing volume associated with a target flushing mode, the flushing control method further includes: obtaining the actual flushing result of the smart toilet; if the actual flushing result is detected as not being clean, performing a second flushing operation according to the target flushing volume associated with the target flushing mode, and reporting the human excrement parameters to a cloud server so that the cloud server can retrain the target prediction model to obtain a new target prediction model.

[0088] In one example, after the smart toilet performs a flushing operation using a target flush volume associated with a target flushing mode, the actual flushing result can be obtained. If the actual flushing result is not clean, the toilet can be flushed again using external means (such as a remote control or a button on the smart toilet). In this case, a second flushing operation is performed using the target flush volume associated with the target flushing mode, and then it is judged again whether it is clean. If it is clean, the human excrement parameters are reported to the cloud server so that the cloud server can retrain the target prediction model to obtain a new target prediction model. If it is still not clean, a second flushing operation is performed using a larger flush volume, and the human excrement parameters are reported to the cloud server so that the cloud server can retrain the target prediction model to obtain a new target prediction model. Then, the cloud server can send the new target prediction model to the associated smart toilet within a specified time, so that the main controller of the smart toilet can update the built-in target prediction model with the new target prediction model. This achieves the effect of continuous learning of the target prediction model built into the smart toilet, effectively ensuring the prediction accuracy of the target prediction model.

[0089] The maximum flush volume can be the maximum flush volume associated with all initial flush modes, or it can be a pre-configured flush volume; there is no limitation on this.

[0090] In one embodiment, Figure 4 This is a flowchart of another flushing control method provided by an embodiment of the present invention. This embodiment is a preferred embodiment, and the flushing control process is described. In this embodiment, the smart toilet has a built-in pressure sensor, an optical sensor, and a timer, and it is assumed that the preset prediction confidence threshold is 70%. Figure 4 As shown, the flushing control process in this embodiment includes the following steps:

[0091] S410 uses a pressure sensor to collect the impact force of falling excrement in real time.

[0092] S420 uses an optical sensor to collect the shape of excrement in real time.

[0093] S430 uses a timer to collect the duration of impact force fluctuations in real time.

[0094] S440. Input the impact force of the falling excrement, the shape of the excrement, and the duration of the impact force fluctuation into the target prediction model to obtain the initial flushing mode.

[0095] S450. Determine the actual prediction confidence value based on the maximum pattern percentage among all initial flushing patterns and the non-conflict value of the identification result.

[0096] S460. Is the actual prediction confidence level greater than or equal to 70%? If yes, proceed to S470; otherwise, proceed to S4100.

[0097] S470, Obtain the flush volume corresponding to the initial flush mode associated with the maximum mode percentage.

[0098] S480, flush according to the flush volume corresponding to the initial flush mode associated with the maximum mode proportion.

[0099] S490: Is it rinsed clean? If yes, then end; if not, proceed to S4130.

[0100] S4100: Obtain the next mode associated with the initial flushing mode corresponding to the maximum mode percentage.

[0101] S4110, Use the flushing volume corresponding to the next mode for rinsing.

[0102] S4120: Is it rinsed clean? If yes, proceed to S1460; otherwise, proceed to S4130.

[0103] S4130, use the same flushing mode as the initial flush for a second flush.

[0104] S4140: Is it rinsed clean? If yes, proceed to S1460; otherwise, proceed to S4150.

[0105] S4150 uses a large volume of water for rinsing.

[0106] S1460. The impact force of the falling excrement, the shape of the excrement, and the duration of the impact force fluctuation are reported to the cloud server to retrain the target prediction model and obtain a new target prediction model.

[0107] S4170: Within the time specified by the user, the new target prediction model is sent to the smart toilet.

[0108] The technical solution of this embodiment, by training a model on a cloud server based on a large amount of training data to obtain a target prediction model, effectively overcomes the hardware resource limitations of smart toilets as devices. This enables more efficient, accurate, and iterative model development, improves the accuracy of the target prediction model, and reduces the equipment cost and maintenance difficulty of smart toilets as devices. Simultaneously, by inputting the human excrement parameters into the target prediction model, an initial flushing mode is obtained. Based on the initial flushing mode and a pre-determined non-conflict value of the recognition result, the actual prediction confidence value is determined. Then, based on the actual prediction confidence value and the initial flushing mode, the target flushing mode of the smart toilet is determined, and the flushing operation is performed according to the target flushing volume corresponding to the target flushing mode. This solves the technical problem in existing technologies that use a fixed water volume for toilet flushing, making it impossible to dynamically control the flushing volume of smart toilets in real time to adapt to changes in user habits. Therefore, it achieves real-time adaptive dynamic control of the flushing volume of the smart toilet according to user habits, realizing on-demand water supply, ensuring flushing cleanliness, avoiding water waste, and improving user experience and device adaptability.

[0109] In one embodiment, Figure 5 This is a schematic diagram of a flushing control device provided in an embodiment of the present invention. Figure 5 As shown, the device includes: a pattern prediction module 510, a confidence value determination module 520, a pattern determination module 530, and a flushing control module 540.

[0110] The pattern prediction module 510 is used to input the pre-acquired human excrement parameters corresponding to the user sitting on the smart toilet into the target prediction model to obtain the initial flushing pattern.

[0111] The confidence value determination module 520 is used to determine the actual predicted confidence value based on the initial flushing pattern and the pre-determined non-conflict value of the identification result;

[0112] The mode determination module 530 is used to determine the target flushing mode of the smart toilet based on the actual predicted confidence value and the initial flushing mode.

[0113] The flushing control module 540 is used to perform a flushing operation with a target flushing volume associated with a target flushing mode.

[0114] In one embodiment, the parameters of human excrement include at least one of the following: the impact force of excrement falling; the shape of excrement; the height of excrement falling; the duration of the impact force fluctuation; and the density of excrement.

[0115] In one embodiment, before determining the actual predicted confidence value based on the initial flushing pattern and a pre-determined non-conflict value of the identification result, the flushing control device further includes:

[0116] The impact force acquisition module is used to acquire the impact force of human excrement falling from the toilet using a pressure sensor in the smart toilet.

[0117] The volume determination module is used to determine the volume of excrement based on the impact force of the excrement falling, the height of the excrement falling, the duration of the impact force fluctuation, and the density of the excrement.

[0118] The conflict level determination module is used to determine the degree of conflict between excrement recognition and the shape of excrement identified by the optical sensor in the smart toilet based on the volume of excrement and the shape of excrement identified by the optical sensor in the smart toilet.

[0119] The non-conflict value determination module is used to determine the non-conflict value of the identification result based on the degree of conflict in the excrement identification.

[0120] In one embodiment, the confidence value determination module 520 includes:

[0121] The mode percentage acquisition unit is used to acquire the mode percentage corresponding to the initial flushing mode.

[0122] The confidence value determination unit is used to take the product between the pattern proportion and the pre-determined non-conflict value of the recognition result as the actual predicted confidence value.

[0123] In one embodiment, the pattern determination module 530 includes:

[0124] The comparison result determination unit is used to determine the comparison result between the actual prediction confidence value and the preset prediction confidence threshold;

[0125] The mode determination unit is used to determine the next mode corresponding to the initial flushing mode as the target flushing mode of the smart toilet if the actual prediction confidence value is less than the preset prediction confidence threshold.

[0126] The mode determination unit is also used to directly use the initial flushing mode as the target flushing mode of the smart toilet if the actual prediction confidence value is greater than the preset prediction confidence threshold.

[0127] In one embodiment, after performing a flushing operation with a target flush volume associated with a target flushing pattern, the flushing control device further includes:

[0128] The reporting module is used to report human excrement parameters to the cloud server if the actual prediction confidence value is less than the preset prediction confidence threshold, so that the cloud server can retrain the target prediction model and obtain a new target prediction model.

[0129] In one embodiment, after performing a flushing operation with a target flush volume associated with a target flushing pattern, the flushing control device further includes:

[0130] The flushing result acquisition module is used to acquire the actual flushing results of the smart toilet;

[0131] The reporting module is also used to perform a second flushing operation according to the target flushing volume associated with the target flushing mode if the actual flushing result is detected as not being clean. The module also reports the human excrement parameters to the cloud server so that the cloud server can retrain the target prediction model to obtain a new target prediction model.

[0132] The flushing control device provided in the embodiments of the present invention can execute the flushing control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method.

[0133] In one embodiment, Figure 6 This is a schematic diagram of a flushing control system provided in an embodiment of the present invention. Figure 6 As shown, the system includes: a smart toilet 610 and a cloud server 620; wherein, the smart toilet 610 establishes a communication connection with the cloud server 620;

[0134] The cloud server 620 is used to send the pre-created target prediction model to the smart toilet 610;

[0135] The smart toilet 610 is used to input the pre-acquired human excrement parameters corresponding to the user sitting on the smart toilet 610 into the target prediction model to obtain the initial flushing mode. Based on the initial flushing mode and the pre-determined non-conflict value of the recognition result, the actual prediction confidence value is determined. Based on the actual prediction confidence value and the initial flushing mode, the target flushing mode of the smart toilet is determined, and the flushing operation is performed using the target flushing volume associated with the target flushing mode.

[0136] In one embodiment, Figure 7 This is a structural block diagram of a smart toilet provided in an embodiment of the present invention, such as... Figure 7 The diagram illustrates a schematic of a smart toilet 10 that can be used to implement embodiments of the present invention. The electronics integrated into the smart toilet are intended to represent various forms of digital computers, such as laptops, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. The electronics can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0137] like Figure 7As shown, the smart toilet 10 includes at least one main controller 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one main controller 11. The memory stores computer programs executable by the at least one main controller. The main controller 11 can perform various appropriate actions and processes based on the computer programs stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The main controller 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0138] Multiple components in the smart toilet 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, optical disk, etc.; and a communication unit 19, such as a network card, modem, wireless transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks. The smart toilet 10 also includes: an optical sensor 20 and a pressure sensor 21; wherein the pressure sensor 21 in the smart toilet acquires the impact force of human excrement falling; and the optical sensor 20 in the smart toilet acquires the shape of human excrement.

[0139] The main controller 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the main controller 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. The main controller 11 performs the various methods and processes described above, such as flush control methods.

[0140] In some embodiments, the flush control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by main controller 11, one or more steps of the flush control method described above may be performed. Alternatively, in other embodiments, main controller 11 may be configured to perform the flush control method by any other suitable means (e.g., by means of firmware).

[0141] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0142] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to the main controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the main controller, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on the machine, partially on the machine, as a standalone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0143] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0144] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0145] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0146] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0147] This invention also provides a computer program product, including a computer program that, when executed by a main controller, can implement the flushing control method provided in any embodiment of this application.

[0148] In the implementation of the computer program product, computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0149] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0150] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A flushing control method, characterized in that, include: The pre-acquired parameters of human excrement corresponding to the user sitting on the smart toilet are input into the target prediction model to obtain the initial flushing mode. The actual prediction confidence value is determined based on the initial flushing pattern and the pre-determined non-conflict value of the identification result; The target flushing mode of the smart toilet is determined based on the actual predicted confidence value and the initial flushing mode. The flushing operation is performed using a target flushing volume associated with the target flushing mode.

2. The method according to claim 1, characterized in that, The parameters of human excrement include at least one of the following: impact force of excrement falling; shape of excrement; height of excrement falling; duration of impact force fluctuation; and density of excrement.

3. The method according to claim 1, characterized in that, Before determining the actual predicted confidence value based on the initial flushing pattern and the pre-determined non-conflict value of the identification result, the method further includes: The pressure sensor in the smart toilet is used to obtain the impact force of human excrement falling; The volume of excrement is determined based on the impact force of the excrement falling, the height of the excrement falling, the duration of the impact force fluctuation, and the density of the excrement. The degree of conflict in excrement recognition is determined based on the volume of the excrement and the shape of the excrement identified by the optical sensor in the smart toilet. The non-conflict value of the identification result is determined based on the degree of conflict in the excrement identification.

4. The method according to claim 1, characterized in that, The step of determining the actual predicted confidence value based on the initial flushing pattern and the pre-determined non-conflict value of the identification result includes: Obtain the mode percentage corresponding to the initial flushing mode; The product of the pattern proportion and the predetermined non-conflict value of the identification result is used as the actual prediction confidence value.

5. The method according to claim 1, characterized in that, Determining the target flushing mode of the smart toilet based on the actual predicted confidence value and the initial flushing mode includes: Determine the comparison result between the actual prediction confidence value and the preset prediction confidence threshold; If the actual prediction confidence value is less than the preset prediction confidence threshold, then the next mode corresponding to the initial flushing mode will be used as the target flushing mode of the smart toilet. If the actual prediction confidence value is greater than the preset prediction confidence threshold, then the initial flushing mode will be directly used as the target flushing mode of the smart toilet.

6. The method according to claim 1, characterized in that, After performing the flushing operation with a target flush volume associated with the target flushing mode, the method further includes: If the actual prediction confidence value is less than the preset prediction confidence threshold, the human excrement parameters are reported to the cloud server so that the cloud server can retrain the target prediction model to obtain a new target prediction model.

7. The method according to claim 1, characterized in that, After performing the flushing operation with a target flush volume associated with the target flushing mode, the method further includes: Obtain the actual flushing results of the smart toilet; If the actual flushing result is detected as not being clean, a second flushing operation is performed according to the target flushing volume associated with the target flushing mode, and the human excrement parameters are reported to the cloud server so that the cloud server can retrain the target prediction model to obtain a new target prediction model.

8. A flushing control system, characterized in that, include: A smart toilet and a cloud server; wherein the smart toilet establishes a communication connection with the cloud server; The cloud server is used to send a pre-created target prediction model to the smart toilet; The smart toilet is used to input the pre-acquired human excrement parameters corresponding to the user sitting on the smart toilet into the target prediction model to obtain an initial flushing mode, and to determine the actual prediction confidence value based on the initial flushing mode and the pre-determined non-conflict value of the recognition result, and to determine the target flushing mode of the smart toilet based on the actual prediction confidence value and the initial flushing mode, and to perform the flushing operation using the target flushing volume associated with the target flushing mode.

9. A smart toilet, characterized in that, The smart toilet includes: a communication module, at least one main controller; and A memory that is communicatively connected to the at least one main controller; The communication module is used to establish a communication connection with the cloud server. The memory stores a computer program that can be executed by the at least one main controller, the computer program being executed by the at least one main controller to enable the at least one main controller to perform the flushing control method according to any one of claims 1-7.

10. The smart toilet according to claim 9, characterized in that, Also includes: Optical sensors and pressure sensors; The pressure sensor in the smart toilet is used to obtain the impact force of human excrement falling; The shape of human excrement is obtained using an optical sensor in the smart toilet.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause the main controller to execute the flushing control method according to any one of claims 1-7.

12. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by the main controller, implements the flushing control method according to any one of claims 1-7.

Images