Control method for a laundry treatment apparatus

Abstract

The present application relates to the technical field of intelligent household appliances, and specifically provides a control method for a clothes processing device, aiming at solving the problem that the existing clothes processing device cannot start a voice module without sensing. To this end, the control method comprises the following steps: acquiring an image of a user through an image acquisition module; judging whether the user has clothes in hand according to the image; in the case that the user is determined to have clothes in hand, determining attribute information of the user according to the image; determining a first preset weight according to the attribute information; judging whether the existing weight of clothes in a clothes processing drum reaches the first preset weight; and selectively starting a voice module for voice prompting or a weighing module for clothes weighing according to the judgment result, so that the voice module can be started without any operation of the user, the purpose of starting the voice module without sensing is achieved, and the user experience is improved.

Description

Technical Field

[0001] This invention relates to the field of smart home appliance technology, specifically providing a control method for clothing processing equipment. Background Technology

[0002] Washing machines are common household laundry appliances. Based on washing methods, they can be broadly categorized into top-loading washing machines and front-loading washing machines. Taking front-loading washing machines as an example, to meet user needs, they are equipped with voice interaction functions, allowing for human-machine interaction via voice commands, making it more convenient for users to operate the washing machine.

[0003] However, existing drum washing machines require a wake-up keyword, such as "Xiaoyou," before activating the voice module. The drum washing machine can only activate the voice module after receiving the activation command, or the voice module's activation button can only be pressed or touched. It cannot be activated seamlessly, which affects the user experience.

[0004] Therefore, there is a need in the art for a new control method for garment processing equipment to solve the above problems. Summary of the Invention

[0005] The present invention aims to solve the above-mentioned technical problem, namely, to solve the problem that existing clothing processing equipment cannot seamlessly start the voice module.

[0006] This invention provides a control method for a clothing processing device, the clothing processing device including a clothing processing drum, an image acquisition module, a voice module, and a weighing module; the control method includes the following steps: acquiring an image of a user through the image acquisition module; determining whether the user has clothing in their hands based on the image; if the user has clothing in their hands, determining the user's attribute information based on the image; determining a first preset weight based on the attribute information; determining whether the existing weight of the clothing in the clothing processing drum has reached the first preset weight; and, based on the determination result, selectively activating the voice module to provide a voice prompt or activating the weighing module to weigh the clothing.

[0007] In the preferred embodiment of the above control method, the attribute information includes the user's age and identity; the step of "determining the user's attribute information based on the image" specifically includes: calling a preset model to analyze the image; determining the age and identity based on the analysis results; the step of "determining a first preset weight based on the attribute information" specifically includes: determining whether the user has used the clothing processing equipment based on the identity; if the user has not used the clothing processing equipment, determining the first preset weight based on the age and creating the user's ID account; and / or if the user has used the clothing processing equipment, obtaining the user's historical washing and care data based on the user's ID account; determining the first preset weight based on the age and the historical washing and care data.

[0008] In the preferred embodiment of the above control method, the step of "selectively activating the voice module to provide a voice reminder or activating the weighing module to weigh the clothes according to the judgment result" specifically includes: if the existing weight reaches the first preset weight, then the voice module is activated to provide a washing reminder.

[0009] In the preferred embodiment of the above control method, the step of "selectively activating the voice module to provide a voice reminder or activating the weighing module to weigh the clothing according to the judgment result" further includes: if the existing weight has not reached the first preset weight, then after a first preset time, activating the weighing module to weigh the clothing; obtaining the current weight of the clothing in the clothing processing tube and saving the current weight; determining whether the current weight has reached the second preset weight, wherein the second preset weight is greater than the first preset weight; and selectively activating the voice module to provide a voice reminder according to the judgment result.

[0010] In the preferred embodiment of the above control method, the step of "selectively activating the voice module to provide voice reminders based on the judgment result" specifically includes: if the current weight reaches the second preset weight, then the voice module is activated to provide an overweight reminder.

[0011] In the preferred embodiment of the above control method, the voice module has a pronunciation mode and a sound recognition mode; the step of "starting the voice module" specifically includes: controlling the voice module to enter the pronunciation mode.

[0012] In a preferred embodiment of the above control method, after "controlling the voice module to enter the pronunciation mode", or when it is determined that the current weight has not reached the second preset weight, the control method further includes: controlling the voice module to enter the sound recognition mode.

[0013] In a preferred embodiment of the above control method, the voice module further has an energy-saving mode; the control method further includes: within a second preset time period after the voice module enters the voice recognition mode, determining whether the voice module receives a valid control command; if the voice module does not receive the valid control command, controlling the voice module to exit the voice recognition mode and enter the energy-saving mode; and / or if the voice module receives the valid control command, causing the clothing processing device to operate according to the valid control command; wherein the valid control command includes at least a start washing command, a stop washing command, a power-on command, a power-off command, a standby command, and a sleep command.

[0014] In a preferred embodiment of the above control method, the clothing processing device further includes a human body detection module; before "acquiring the user's image through the image acquisition module", the control method further includes: detecting whether a user has entered a preset range through the human body detection module; if a user has entered the preset range, then activating the image acquisition module.

[0015] In a preferred embodiment of the above control method, the control method further includes: turning off the image acquisition module if the user has no clothing in their hands.

[0016] In a preferred embodiment of the control method of the present invention, an image of the user is acquired by an image acquisition module; based on the image, it is determined whether the user has clothes in their hands; if it is determined that the user has clothes in their hands, the user's attribute information is determined based on the image; a first preset weight is determined based on the attribute information; it is determined whether the existing weight of the clothes in the washing drum has reached the first preset weight; based on the determination result, a voice module is selectively activated to provide a voice reminder or a weighing module is activated to weigh the clothes.

[0017] Compared to existing technologies that require activation commands such as wake-up keywords to start the voice module, this invention determines whether the user has clothes in their hands based on an image, thus accurately judging the user's intention. If clothes are present, indicating an intention to add more, the system checks if the weight of the clothes in the tub reaches a first preset weight. Based on this, it selectively activates either the voice module to provide a voice prompt or the weighing module to weigh the clothes. This process requires no user intervention, achieving seamless voice module activation and improving user experience. Furthermore, the first preset weight is determined based on user attributes, making it more aligned with user needs and washing habits, and ensuring more accurate decision-making regarding voice module activation.

[0018] In addition, it can also seamlessly start the weighing module to obtain the weight of the clothes in the washing drum, and use this weight as the weight of the clothes for the next time to determine whether to start the voice module, thus better achieving the goal of seamlessly starting the voice module.

[0019] Furthermore, if the user has never used the washing machine before, indicating a new user with no stored information, the washing machine determines a first preset weight based on the user's age. This caters to the different washing weight needs of users of varying ages, and an ID account is created for the user to store their current and future washing data, providing a reference for future washes. If the user has used the washing machine before, indicating a returning user with stored historical washing data, the first preset weight is determined based on both the user's age and historical data. This approach considers not only the different washing weight needs of users of varying ages but also historical washing data, thus taking into account the user's washing habits and ensuring a better fit for their specific needs. Through these methods, the needs of users with different identities are met, further improving the user experience.

[0020] Furthermore, if the weight already reaches the first preset weight, it means there are already a lot of clothes in the washing drum and it can be washed. Adding more clothes may exceed the weight limit and affect the washing effect. At this time, the voice module is activated to remind the user to wash clothes, so as to prevent the user from adding more clothes. This achieves the purpose of activating the voice module without being noticed.

[0021] Furthermore, if the existing weight has not reached the first preset weight, it means that there are few clothes in the washing drum and more clothes can be added. Then, after the first preset time, that is, after the user puts the clothes into the washing drum, the weighing module is activated to weigh the clothes; the current weight of the clothes in the washing drum is obtained and saved; based on the current weight, the voice module is selectively activated to provide voice reminders, thereby better achieving the purpose of seamlessly activating the voice module.

[0022] Furthermore, if the current weight reaches the second preset weight, it means that there are too many clothes in the washing drum and it is overweight, which may affect the washing effect. At this time, the voice module will be activated to remind the user to take out some clothes, thus achieving the purpose of seamlessly activating the voice module.

[0023] Furthermore, after "controlling the voice module to enter the speech mode" or "obtaining the current weight of the clothes in the washing drum", the voice module can enter the voice recognition mode, allowing users to interact with the washing machine via voice, further improving the user experience. Attached Figure Description

[0024] The control method of the present invention will now be described with reference to the accompanying drawings and in conjunction with a washing machine, in which:

[0025] Figure 1 This is the flow chart of the control method of the present invention. Figure 1 ;

[0026] Figure 2 This is a flowchart of the control method for determining the first preset weight according to the present invention;

[0027] Figure 3 This is a flowchart of the control method for selectively activating the voice module or the weighing module according to the present invention;

[0028] Figure 4 This is a flowchart of the control method for selectively activating the voice module according to the present invention;

[0029] Figure 5 This is the flow chart of the control method of the present invention. Figure 2 ;

[0030] Figure 6 This is the flow chart of the control method of the present invention. Figure 3 ;

[0031] Figure 7 This invention describes the flow of a control method for determining whether a user has clothing in their hands. Figure 1 ;

[0032] Figure 8 This is a flowchart of the control method for calling a deep learning model to analyze images according to the present invention;

[0033] Figure 9 This invention describes the flow of a control method for determining whether a user has clothing in their hands. Figure 2 ;

[0034] Figure 10 This is a logic diagram of the control method of the present invention. Detailed Implementation

[0035] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention. For example, although this application is described in conjunction with a washing machine, the technical solution of the present invention is not limited thereto, and this control method can obviously also be applied to other clothing handling equipment such as dryers, garment care machines, and washer-dryer combos, without departing from the principles and scope of the present invention.

[0036] It should be noted that in the description of this invention, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0037] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the term "setup" should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral connection; it can refer to a mechanical connection or an electrical connection; it can refer to a direct connection or an indirect connection through an intermediate medium; it can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0038] Based on the technical problems mentioned in the background art, this invention provides a control method for a washing machine. The method aims to determine whether a user has clothes in their hands based on an image, thereby accurately determining the user's intention. If the method determines that the user has clothes in their hands, indicating an intention to add clothes to the washing drum, it then determines whether the existing weight of the clothes in the drum reaches a first preset weight. Based on the determination result, it selectively activates a voice module to provide a voice prompt or activates a weighing module to weigh the clothes. During this process, the voice module can be activated without any user intervention, achieving seamless activation and improving the user experience. Furthermore, the first preset weight is determined based on the user's attribute information, making it more aligned with the user's needs and washing habits, and enabling more accurate determination of whether to activate the voice module.

[0039] In addition, it can also seamlessly start the weighing module to obtain the weight of the clothes in the washing drum, and use this weight as the weight of the clothes for the next time to determine whether to start the voice module, thus better achieving the goal of seamlessly starting the voice module.

[0040] First, the washing machine of the present invention will be described.

[0041] The washing machine of the present invention includes a cabinet, a washing drum and a weighing module disposed within the cabinet, and an image acquisition module, a voice module, a human body detection module and a control module disposed on the cabinet. The washing drum includes an outer drum disposed within the cabinet and an inner drum rotatably disposed within the outer drum. The outer drum is used to hold washing water, and the inner drum is used to hold clothes.

[0042] The image acquisition module, voice module, weighing module, and human body detection module are all connected to the control module. The image acquisition module is used to acquire images of the user; the voice module is used to send voice prompts and interact with the user; the weighing module weighs the clothes inside the drum; the human body detection module detects whether there is a user within a preset range of the washing machine; the control module controls the image acquisition module to capture images of the user based on the detection results of the human body detection module, and controls the preset model to analyze the user's images. Based on the analysis results, it determines whether the user has clothes in their hands, and selectively activates the voice module to provide voice prompts or activates the weighing module to weigh the clothes based on the determination results.

[0043] Preferably, the image acquisition module can be, but is not limited to, a camera or a webcam.

[0044] Preferably, the voice module can be, but is not limited to, an SDK module, an NV020S module, a YQ5969 module, an NRK10B module, etc.

[0045] Preferably, the weighing module can be, but is not limited to, a weighing sensor, a weighing meter, etc.

[0046] Preferably, the human body detection module is an infrared sensor, which can accurately detect the user's location information. Of course, the human body detection module can also be a radar sensor or a laser sensor. Regardless of the sensor used to detect the user's location information, the specific detection method corresponding to any sensor should not constitute a limitation on this invention.

[0047] See next. Figure 1 and Figure 2 The control method of the present invention will be described below. Figure 1 This is the flow chart of the control method of the present invention. Figure 1 ; Figure 2 This is a flowchart of the control method for determining the first preset weight according to the present invention.

[0048] like Figure 1 As shown, the control method of the present invention includes the following steps:

[0049] S100: Acquire the user's image through the image acquisition module;

[0050] S200: Based on the image, determine whether the user has clothing in their hands;

[0051] S300: If it is determined that the user has clothing in their hand, determine the user's attribute information based on the image;

[0052] S400, Determine the first preset weight based on the attribute information;

[0053] S500: Determine whether the existing weight of the garment in the garment processing tube has reached the first preset weight;

[0054] S600: Based on the judgment result, selectively activate the voice module to provide voice reminders or activate the weighing module to weigh the clothing.

[0055] In step S100, the washing machine captures images of the user through image acquisition modules such as cameras and camcorders.

[0056] Furthermore, if it is determined that the user does not have any clothing, step S700 is executed;

[0057] S700, disable the image acquisition module.

[0058] If it is determined that the user has no clothes in their hands, it means that the user is not going to do laundry and may just be passing by the washing machine. In this case, the image acquisition module is turned off to save power.

[0059] If it is determined that the user has clothes in their hands, indicating that the user intends to add clothes to the washing drum, then step S300 is executed to determine the user's attribute information based on the image, wherein the user's attribute information includes the user's age and identity.

[0060] like Figure 2 As shown, the washing machine pre-stores a preset model and a database, the preset model including a classification model and an object detection model; step S300, "determining the user's attribute information based on the image," specifically includes:

[0061] S311. Call the preset model to analyze the image;

[0062] S312. Based on the analysis results, determine the age and identity.

[0063] Example 1: Identifying the user's age

[0064] In steps S311 and S312, a classification model is invoked to recognize the user's image, identify the user's age, and store the identified age in the ID account corresponding to the user. When the user washes clothes again, the user's age can be retrieved directly. The classification model can employ algorithms such as SENet, Keras, VGG, and AtoC to identify the user's age. Regardless of the algorithm used, the specific method for identifying the user's age using any particular algorithm should not constitute any limitation on this invention.

[0065] Preferably, the user's age is divided into multiple stages, such as infancy, adolescence, youth, adulthood, middle age, and old age. Of course, the division of age stages is not limited to the above-listed methods. Those skilled in the art can flexibly adjust and set them in practical applications. For example, age stages can be divided into minors, adults, and the elderly. Those skilled in the art can flexibly adjust and set the division of age stages according to the needs of activating the voice module.

[0066] Furthermore, the age range for the infant stage is 0-6 years; the age range for the adolescent stage is 6-12 years; the age range for the youth stage is 12-18 years; the age range for the young adult stage is 18-40 years; the age range for the middle-aged stage is 40-65 years; and the age range for the elderly stage is 65 years and above.

[0067] Example 2: Identifying the User's Identity

[0068] In steps S311 and S312, the object detection model is invoked to identify the user's image, thereby identifying the user in the image and the user's location within the image. The background of the user's image is then removed based on the location to obtain the main image. Further, a first vector matrix of the main image is extracted, and a second vector matrix of each historical user image is extracted from the database. The similarity between the first vector matrix and each second vector matrix is ​​calculated. The similarity is represented by cosine distance, but Euclidean distance can also be used. For example, the cosine distances between the first vector matrix and the three second vector matrices are 0.95, 0.6, and 0.3, respectively; or, the cosine distances between the first vector matrix and the three second vector matrices are 0.7, 0.4, and 0.1, respectively.

[0069] The first vector matrix and the second vector matrix are both n-dimensional vectors, such as 256-dimensional vectors, 512-dimensional vectors, etc. Those skilled in the art can flexibly adjust and set the dimensions of the first vector matrix and the second vector matrix according to the calculation requirements in practical applications.

[0070] Furthermore, the similarity is checked against a preset similarity. If the similarity is greater than the preset similarity (e.g., the preset cosine distance is 0.9), the calculated cosine distances of 0.95, 0.6, and 0.3 are compared with 0.9. Since 0.95 is greater than 0.8 and thus greater than the preset cosine distance, it indicates that the user has a very high similarity to one of the three historical users. Therefore, the user's clothing item is determined to be from an existing user. Alternatively, if the similarity is less than or equal to the preset similarity, the calculated cosine distances of 0.7, 0.4, and 0.1 are compared with 0.9. Since all are less than 0.9 and less than the preset cosine distance, it indicates that the user has a low similarity to the three historical users. This user and the three historical users being compared are not the same user. Therefore, the user's clothing item is determined to be from a new user.

[0071] Preferably, the object detection model can use the ResNet50 algorithm combined with triplet loss to identify the user's image and thus identify the user's identity. Of course, the object detection model can also use other algorithms such as Faster R-CNN, SPPNet, SSD, and YOLO to identify the user's image and thus identify the user's identity. Regardless of the algorithm used, the specific method for identifying the user's identity corresponding to any algorithm should not constitute any limitation on this invention.

[0072] It should be noted that the cosine distances and preset cosine distances listed above are merely illustrative and not restrictive. Those skilled in the art can calculate the cosine distance based on actual clothing images in practical applications, and flexibly adjust the preset cosine distance according to actual accuracy requirements.

[0073] Continue reading Figure 2 In step S400, the step of "determining the first preset weight based on attribute information" specifically includes:

[0074] S411. Based on the user's identity, determine whether the user has used the washing machine; if not, proceed to step S412; if yes, proceed to step S413.

[0075] S412. Determine the first preset weight based on age and create the user's ID account;

[0076] S413. Obtain the user's historical hair care data based on the user's ID account;

[0077] S414. Determine the first preset weight based on age and historical washing and care data.

[0078] In step S411, if it is determined in step S312 that the user is a new user, then the user has not used the washing machine; if it is determined in step S312 that the user is an old user, then the user has used the washing machine.

[0079] In step S412, if the user has never used the washing machine before, it means that the user is a new user and the washing machine has not stored any information about the user. Then, the first preset weight is determined according to the user's age to meet the needs of users of different ages for the weight of clothes to be washed. The user's ID account is created in order to store the user's washing data for this and future washing, and to provide data reference for the user's next washing of clothes.

[0080] Furthermore, the user's age stage is determined based on their age, and then a first preset weight is determined based on that age stage. Specifically, the first preset weight corresponds to 3kg for infants, 3.5kg for young adults, 4kg for middle-aged adults, 4.5kg for the elderly, and 5kg for teenagers and adolescents. It can be seen that the first preset weight for infants is less than that for young adults, which is less than that for middle-aged adults, which is less than that for the elderly, and which is less than that for teenagers and adolescents. Of course, the first preset weights for different age stages and the relationships between them are not limited to the relationships listed above and can be flexibly adjusted and set according to the user's actual usage needs.

[0081] For example, if the detected user is 28 years old and in their youth, the corresponding first preset weight is 3.5 kg.

[0082] In steps S413 and S414, if the user has used the washing machine before, it means that the user is an old user, the user's ID account has been created, and the washing machine stores historical washing data about the user. Then, the historical washing data of the user is obtained from the user's ID account, and the first preset weight is determined based on the user's age and historical washing data. This not only takes into account the needs of users of different ages for the weight of clothes to be washed, but also combines historical washing data, that is, it takes into account the user's washing habits, so that the determined first preset weight can better meet the user's needs.

[0083] The historical washing and care data includes historical washing programs, historical preset weights, historical water levels, historical water temperatures, historical washing cycles, and other washing and care data.

[0084] Furthermore, the user's age stage is determined based on their age, and then the first preset weight corresponding to that age is determined based on that age stage; the user's historical first preset weight is obtained based on their ID account, the two obtained first preset weights are compared, the maximum value is determined, and the maximum value is determined as the final first preset weight, thus satisfying the user's need to wash more clothes.

[0085] For example, if the detected user's age is 42 years old, which is in the middle age stage, then the corresponding first preset weight is 4kg; if the obtained historical preset weight is 4.2kg, then 4kg and 4.2kg are compared, and 4.2kg > 4kg, so 4.2kg is determined as the first preset weight.

[0086] It should be noted that in the above process, steps S300 and S700 are parallel and have no sequential order. They are only related to the judgment result of whether the user has clothes in their hands, and the corresponding steps are executed according to different judgment results. Steps S412 and S413 are parallel and have no sequential order. They are only related to the judgment result of whether the user has used the washing machine, and the corresponding steps are executed according to different judgment results.

[0087] The following reference Figure 3 and Figure 4 The present invention describes a control method for selectively activating the voice module or the weighing module. Wherein, Figure 3 This is a flowchart of the control method for selectively activating the voice module or the weighing module according to the present invention; Figure 4 This is a flowchart of the control method for selectively activating the voice module according to the present invention.

[0088] like Figure 3 As shown, step S600, "selectively activating the voice module to provide voice prompts or activating the weighing module to weigh the clothing based on the judgment result," specifically includes:

[0089] If the weight has already reached the first preset weight, then proceed to step S611;

[0090] If the existing weight has not reached the first preset weight, then proceed to step S612;

[0091] S611, Activate the voice module to provide washing reminders;

[0092] S612. After the first preset time, start the weighing module to weigh the clothing;

[0093] S613. Obtain the current weight of the garment inside the garment processing tube and save the current weight;

[0094] S614. Determine whether the current weight has reached the second preset weight, wherein the second preset weight is greater than the first preset weight;

[0095] S615. Based on the judgment result, selectively activate the voice module to provide voice reminders.

[0096] In step S611, if the existing weight has reached the first preset weight, for example, the first preset weight is 3.5kg and the detected existing weight is 3.6kg, which is slightly greater than the first preset weight, it means that there are already a lot of clothes in the washing drum and it can be washed. If more clothes are added, it may exceed the weight limit and thus affect the washing effect. At this time, the voice module is activated to remind the user to wash clothes, so as to prevent the user from adding more clothes and achieve the purpose of activating the voice module without being noticed.

[0097] Preferably, the voice module has a pronunciation mode and a sound recognition mode. When the voice module enters the pronunciation mode, it can issue a reminder. Those skilled in the art can flexibly set the content of the voice reminder according to the specific application scenario. When the voice module enters the sound recognition mode, it can collect ambient sounds, such as various commands issued by the user, such as commands to start washing, stop washing, power on, power off, standby, and hibernation.

[0098] Furthermore, the steps of "activating the voice module" specifically include: controlling the voice module to enter the speech mode, and further controlling the voice module to issue a "wash clothes" reminder, which can promptly remind the user to start washing clothes to prevent the user from adding more clothes and ensure the washing effect. Of course, the voice module can also send different prompts through different ringtones or other methods, and those skilled in the art can flexibly choose the specific reminder method.

[0099] In step S612, after a first preset time, such as 20s, 30s or 40s, the weighing module is started to weigh the clothes, so that the user has enough time to put the clothes in the inner drum, and the weighing module weighs the weight after the clothes are added.

[0100] In step S613, the current weight of the clothes in the garment processing tube is obtained and saved. This provides accurate data for determining whether to start the voice module in step S614, thereby achieving the goal of seamlessly starting the voice module more accurately.

[0101] like Figure 4 As shown, step S615, "selectively activating the voice module to provide voice reminders based on the judgment result," specifically includes:

[0102] If the current weight reaches the second preset weight, then proceed to step S621;

[0103] If the current weight has not reached the second preset weight, proceed to step S622;

[0104] S621. Activate the voice module to provide an overweight reminder;

[0105] S622, Do not start the voice module.

[0106] In step S621, if the current weight reaches the second preset weight, for example, if the first preset weight is 3.5kg, then the second preset weight is 4kg. If the detected current weight is 4.3kg, which is greater than the second preset weight, it means that there are too many clothes in the washing drum and it is overweight, which may affect the washing effect. At this time, the voice module is activated to remind the user to take out some clothes, thus better achieving the purpose of seamlessly activating the voice module.

[0107] Furthermore, the steps of "activating the voice module" specifically include: controlling the voice module to enter the speech mode, and further controlling the voice module to issue a "clothes are too heavy" reminder to remind the user to remove some of the clothes. Of course, the voice module can also send different prompts through different ringtones or other means, and those skilled in the art can flexibly choose the specific reminder method.

[0108] In step S622, if the current weight does not reach the second preset weight (for example, if the first preset weight is 3.5kg and the second preset weight is 4kg), and the detected current weight is 3.6kg, although greater than the first preset weight, it is less than the second preset weight. The current weight of the clothes is simply excessive and will not affect the washing effect, so there is no need to activate the voice model to provide a reminder. This current weight can be used to determine whether the existing weight of the clothes in the washing drum has reached the first preset weight when the user's hands are detected again. Then, based on the judgment result, it is further determined whether to activate the voice module, thereby better achieving seamless activation of the voice module.

[0109] Alternatively, if the detected current weight is 3.3kg, which is less than the second preset weight and less than the first preset weight, it means that the current weight of the clothes is small and will not affect the washing effect, so there is no need to activate the voice model to remind you.

[0110] It should be noted that in the above process, steps S611 and S612 are not sequential but parallel, and are only related to the judgment result of whether the existing weight has reached the first preset weight. The corresponding steps are executed according to different judgment results. Similarly, steps S621 and S622 are not sequential but parallel, and are only related to the judgment result of whether the current weight has reached the second preset weight. The corresponding steps are executed according to different judgment results.

[0111] The following reference Figure 5 The control method of the present invention is further described below. Figure 5 This is the flow chart of the control method of the present invention. Figure 2 .

[0112] The voice module also has an energy-saving mode; such as Figure 5 As shown, the control method also includes:

[0113] S811. After “controlling the voice module to enter the pronunciation mode”, or when it is determined that the current weight has not reached the second preset weight, control the voice module to enter the sound recognition mode.

[0114] S812. Within the second preset time period after the voice module enters the voice recognition mode, determine whether the voice module has received a valid control command; if not, proceed to step S813; if yes, proceed to step S814.

[0115] S813: Control the voice module to exit voice recognition mode and enter energy-saving mode;

[0116] S814. Make the washing machine operate according to effective control commands;

[0117] The effective control commands include at least the following: start washing command, stop washing command, power on command, power off command, standby command, and sleep command. It should be noted that the types of effective commands listed above are only specific to the command types; they do not limit the specific content of the commands that the voice module can receive. As long as the effective commands received by the voice module can control the washing machine to start washing, stop washing, power on, power off, standby, or sleep, it is acceptable.

[0118] In step S811, after “controlling the voice module to enter the voice mode”, a washing reminder or overload reminder is given. Then, the voice module is controlled to enter the voice recognition mode, and the user can give commands to the washing machine by voice, such as start washing command or stop washing command.

[0119] Alternatively, if the current weight is determined to be below the second preset weight, the voice module can be put into voice recognition mode, allowing the user to give commands to the washing machine via voice, such as the command to start washing.

[0120] In step S813, if the voice module does not receive a valid control command, for example, if the second preset time is 5 minutes and no valid control command is received within 5 minutes of the reservation module entering the voice recognition mode, it means that the user does not intend to wash clothes at this time, or the user has a hearing impairment and has not received the voice prompt information, or the user forgot to send the control command, etc. In any of the above situations, even if it continues to be in the voice recognition mode, it is unlikely to collect a valid control command. Therefore, the voice mode is controlled to exit the sound pickup mode and enter the energy saving mode.

[0121] Among them, the power consumption of the energy-saving mode is much lower than that of the voice module when it is running normally. The voice module is controlled to operate at low power, which effectively reduces power consumption even when the voice module is in sleep mode.

[0122] In step S814, if the voice module receives a valid control command, for example, if the second preset time is 5 minutes and a valid control command is received 1 minute after the reservation module enters the voice recognition mode, such as a start washing command, then the washing machine can be controlled to start executing the washing program.

[0123] It should be noted that steps S813 and S814 are not sequential but parallel, and are only related to the judgment result of whether a valid control command is received within the second preset time. The corresponding steps can be executed according to different judgment results.

[0124] The following reference Figure 6 The control method of the present invention is further described below. Figure 6 This is the flow chart of the control method of the present invention. Figure 3 .

[0125] like Figure 6 As shown, before step S100, the control method further includes:

[0126] S010. Detect whether a user has entered the preset range using the human body detection module; if yes, proceed to step S020; if no, proceed to step S030.

[0127] S020, Start the image acquisition module;

[0128] S030, Do not start the image acquisition module.

[0129] In step S010, the human body detection module can detect in real time whether a user has entered the preset range; or the human body detection module can detect whether a user has entered the preset range at preset time intervals.

[0130] The preset time interval can be 1 minute, 2 minutes, or 3 minutes, etc. The above preset time interval is only an example and not a limitation. In practical applications, those skilled in the art can flexibly adjust and set the preset time interval according to the frequency of users entering the washing machine placement position, etc. No matter how the preset time interval is adjusted and set, as long as it can accurately detect whether a user enters the preset range, it is acceptable.

[0131] The preset range can be the detection range of the detection module, such as 1.2m, 1.5m or 2.0m; the preset range can also be a range set by those skilled in the art based on experiments or experience, such as 1.0m, 1.3m or 1.6m. Those skilled in the art can flexibly adjust and set the preset range.

[0132] If a user enters the preset range, the user may be washing clothes and holding clothes to be washed. Of course, the user may also be passing by the washing machine. In order to determine the user's purpose, the image acquisition module is activated so that it can acquire the user's image and determine whether the user has clothes in their hands based on the image, thereby determining the user's purpose.

[0133] If no user enters the preset range, it means that no user wants to wash clothes. There is no need to determine the washing program based on the user's image. Therefore, the image acquisition module will not be started, and the system will continue to detect whether a user has entered the preset range until a user is detected. At this time, only the human body detection module is running, which further reduces energy consumption.

[0134] It should be noted that in the above process, steps S020 and S030 are not sequential but parallel, and are only related to the judgment result of whether a user has entered the preset range. The corresponding steps can be executed according to different judgment results.

[0135] The following reference Figures 7 to 9 The present invention describes a control method for determining whether a user has clothing in their hands. Figure 7 This invention describes the flow of a control method for determining whether a user has clothing in their hands. Figure 1 ; Figure 8 This is a flowchart of the control method for calling a deep learning model to analyze images according to the present invention; Figure 9 This invention describes the flow of a control method for determining whether a user has clothing in their hands. Figure 2 .

[0136] like Figure 7 As shown, a deep learning model is pre-stored on the washing machine; in step S200, the step of "determining whether the user has clothes in their hands based on the image" specifically includes:

[0137] S210. Use a deep learning model to analyze the image;

[0138] S220. Based on the analysis results, determine whether the user has any clothing in their hands.

[0139] The deep learning model can employ the shuffleNetV2 and FCOS algorithms to analyze images and determine whether a user has clothing in their hands. Of course, the deep learning model can also use other algorithms such as CNN, ResNet18, ResNet101, DeeplabV3+, ResNeXt, and HRNet to analyze images and determine whether a user has clothing in their hands. Regardless of the algorithm used by the deep learning model, the specific method for determining whether a user has clothing should not constitute any limitation on this invention.

[0140] like Figure 8 As shown, step S210, "calling a deep learning model to analyze the image," specifically includes:

[0141] S211. Extract multiple sub-images from the image according to a preset method;

[0142] S212. Input all sub-images into the deep learning model;

[0143] S213. The deep learning model calculates and obtains the feature values ​​of the image based on all sub-images.

[0144] One preset method could be to set different sliding boxes, extract the image from each sliding box, and use the extracted image as a sub-image. Alternatively, a preset method could be to divide the user's image into N parts based on its size, such as 5, 10, 15, or 20 parts, where N is a positive integer, and extract the image from each part, using the extracted image as a sub-image. Of course, preset methods are not limited to those listed above; any method that allows for the extraction of multiple sub-images from the image is acceptable.

[0145] like Figure 9 As shown, step S220, "determining whether the user has clothing based on the analysis results," specifically includes:

[0146] S221. Determine whether the feature value is greater than the preset value; if yes, proceed to step S222; if no, proceed to step S223.

[0147] S222, Determines that the user has clothing in their possession;

[0148] S223, Determines that the user does not have any clothing in their possession.

[0149] In step S222, if the feature value is greater than the preset value, for example, if the preset value is 0.5 and the feature value calculated in step S213 is 0.95, which is greater than the preset value, it means that the user has clothes in his / her hand, and it is determined that the user has clothes in his / her hand.

[0150] In step S223, if the feature value is less than or equal to the preset value, for example, if the preset value is 0.5 and the feature value calculated in step S213 is 0.05, which is less than the preset value, it means that the user has no clothes in his / her hands, and it is determined that the user has no clothes in his / her hands.

[0151] It should be noted that the preset values ​​listed above are merely illustrative and not restrictive. Those skilled in the art can flexibly adjust and set the preset values ​​according to the accuracy of determining whether the user has clothing in their hands. For example, the preset value can also be 0.7, 0.8, 0.9 or 1. No matter how the preset value is set, as long as it can accurately determine whether the user has clothing in their hands, it is acceptable.

[0152] It should also be noted that in the above process, steps S222 and S223 are not sequential but parallel, and are only related to the judgment result of whether the feature value is greater than the preset value. The corresponding steps can be executed according to different judgment results.

[0153] Furthermore, in the above process, classification models, object detection models, and deep learning models are used to analyze the images to determine the user's age, identity, and whether they are carrying clothing. In practical applications, only one or two models can be used to analyze the images to determine the user's age, identity, and whether they are carrying clothing. Those skilled in the art can flexibly adjust and set these models according to actual usage needs.

[0154] The following reference Figure 10 This paper describes one possible control flow of the present invention. Figure 10 This is a logic diagram of the control method of the present invention. Figure 10 Taking the human body detection module as an infrared sensor and the image acquisition module as a camera as an example, the control method of the present invention will be further described.

[0155] like Figure 10 As shown, a possible complete flow of the control method of the present invention is as follows:

[0156] S901, Turn on the infrared sensor;

[0157] S902. The infrared sensor detects whether a user has entered the preset range; if yes, proceed to step S903; if no, continue to proceed to step S902 until the infrared sensor detects that a user has entered the preset range.

[0158] S903: Start the camera and capture the user's image using the camera;

[0159] S904. Call the deep learning model to analyze the image;

[0160] S905. Based on the analysis results, determine whether the user has clothing in their hands; if not, proceed to step S906 and return to step S902 until the infrared sensor detects again that a user has entered the preset range and the user has clothing in their hands; if so, proceed to step S907.

[0161] S906. Turn off the camera;

[0162] S907. Call the preset model to analyze the image; the preset model includes a classification model and an object detection model;

[0163] S908. Based on the analysis results, determine age and identity;

[0164] S909. Based on the user's identity, determine whether the user has used the washing machine; if not, proceed to step S910; if yes, proceed to step S911.

[0165] S910. Determine the first preset weight m based on age. 01 ;

[0166] S911. Determine the first preset weight m based on age and the user's historical hair care data. 01 ;

[0167] After step S910 or step S911, step S912 is executed;

[0168] S912. Determine whether the existing weight m1 of the garment in the garment processing tube has reached m. 01 If yes, proceed to step S913; otherwise, proceed to step S914.

[0169] S913, Control the voice module to enter the voice mode to provide washing reminders;

[0170] S914. After 1 minute, start the weighing module to weigh the clothes, obtain the current weight m2 of the clothes in the garment processing tube, and save m2.

[0171] S915, Determine whether m2 has reached the second preset weight m 02 If yes, proceed to step S916; if no, proceed to step S917; where m 02 >m 01 ;

[0172] S916, Control the voice module to enter the pronunciation mode and provide overweight reminder;

[0173] After steps S913 and S916, step S917 is executed;

[0174] S917, Control the voice module to enter voice recognition mode;

[0175] S918. Within 5 minutes of the voice module entering the voice recognition mode, determine whether the voice module has received a valid control command; if not, proceed to step S919; if yes, proceed to step S920.

[0176] S919, Control the voice module to exit voice recognition mode and enter energy-saving mode;

[0177] S920, enables the washing machine to operate according to effective control commands.

[0178] It should be noted that the above embodiments are merely preferred embodiments of the present invention, used only to illustrate the principle of the method of the present invention, and are not intended to limit the scope of protection of the present invention. In practical applications, those skilled in the art can allocate the above functions to different steps as needed, that is, further decompose or combine the steps in the embodiments of the present invention. For example, the steps in the above embodiments can be combined into one step, or further divided into multiple sub-steps to complete all or part of the functions described above. The names of the steps involved in the embodiments of the present invention are merely for distinguishing the various steps and are not considered as limitations on the present invention.

[0179] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A control method for a garment processing device, characterized in that, The garment processing equipment includes a garment processing drum, an image acquisition module, a voice module, and a weighing module; The control method includes the following steps: The user's image is acquired through the image acquisition module; Based on the image, determine whether the user has clothing in their hands; If it is determined that the user has clothing in their hand, the user's attribute information is determined based on the image. Determine the first preset weight based on the attribute information; Determine whether the existing weight of the clothing in the garment processing tube has reached the first preset weight; Based on the judgment result, the voice module can be selectively activated to provide voice reminders, or the weighing module can be activated to weigh the clothing.

2. The control method according to claim 1, characterized in that, The attribute information includes the user's age and identity; The step of "determining the user's attribute information based on the image" specifically includes: The image is analyzed by calling a preset model; Based on the analysis results, the age and identity are determined; The step of "determining the first preset weight based on the attribute information" specifically includes: Based on the stated identity, determine whether the user has used the garment processing equipment before; If the user has not used the clothing processing equipment before, the first preset weight is determined based on the age, and an ID account for the user is created; and / or If the user has used the garment processing equipment, then the user's historical washing and care data will be obtained based on the user's ID account; The first preset weight is determined based on the age and the historical washing and care data.

3. The control method according to claim 1 or 2, characterized in that, The steps of "selectively activating the voice module to provide voice prompts or activating the weighing module to weigh the clothing based on the judgment result" specifically include: If the existing weight reaches the first preset weight, the voice module is activated to provide a washing reminder.

4. The control method according to claim 3, characterized in that, The step of "selectively activating the voice module to provide voice prompts or activating the weighing module to weigh the clothing based on the judgment result" further includes: If the existing weight does not reach the first preset weight, the weighing module will be activated to weigh the clothing after a first preset time. Obtain the current weight of the garment in the garment processing tube and save the current weight; Determine whether the current weight has reached a second preset weight, wherein the second preset weight is greater than the first preset weight; Based on the judgment result, the voice module is selectively activated to provide voice reminders.

5. The control method according to claim 4, characterized in that, The step of "selectively activating the voice module to provide voice reminders based on the judgment result" specifically includes: If the current weight reaches the second preset weight, the voice module is activated to provide an overweight reminder.

6. The control method according to claim 5, characterized in that, The voice module has a pronunciation mode and a sound recognition mode; The steps for "starting the voice module" specifically include: Control the voice module to enter the pronunciation mode.

7. The control method according to claim 6, characterized in that, After "controlling the voice module to enter the pronunciation mode", or when it is determined that the current weight has not reached the second preset weight, the control method further includes: Control the voice module to enter the voice recognition mode.

8. The control method according to claim 6, characterized in that, The voice module also has an energy-saving mode; the control method further includes: Within a second preset time period after the voice module enters the voice recognition mode, it is determined whether the voice module has received a valid control command; If the voice module does not receive the valid control command, then the voice module is controlled to exit the voice recognition mode and enter the energy-saving mode; and / or If the voice module receives the valid control command, it causes the clothing processing device to operate according to the valid control command; The effective control commands include at least the start washing command, stop washing command, power on command, power off command, standby command, and hibernation command.

9. The control method according to claim 1, characterized in that, The clothing processing equipment also includes a human body detection module; Before "acquiring the user's image through the image acquisition module", the control method further includes: The human detection module detects whether a user has entered the preset range. If a user enters the preset range, the image acquisition module is activated.

10. The control method according to claim 1 or 9, characterized in that, The control method further includes: If the user does not have any clothing, the image acquisition module will be turned off.

Images