Model training method and device, clothes processing method and device, equipment and storage medium
By obtaining data of clothing fabric and processing solutions, simulation and model training, the automatic processing solution output of clothing processing equipment is realized, solving the poor processing effect and experience problems caused by improper user choice, and improving the clothing processing effect and user satisfaction.
Patent Information
- Application Number
- CN202310651106.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-06-02
- Publication Date
- 2024-12-03
AI Technical Summary
The lack of professional knowledge of traditional clothing processing equipment users, which leads to inappropriate selection of clothing treatment agents and procedures, resulting in poor processing effects and possible damage to clothing, and poor user experience.
By obtaining the data of the fabric and sample processing schemes of various clothing, traversing the scheme using simulation method, obtaining the optimal processing scheme of each fabric, and obtaining the target clothing processing model based on the initial model training, which is used to automatically output the processing of the clothes to be processed. plan.
The automatic output target processing solution based on clothing fabrics is realized, avoiding users' independent selection of treatment agents and programs, improving processing effect and user experience, and reducing model training costs and efficiency.
Smart Images

Figure CN119066477A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of smart home appliances, and in particular to a model training method, a clothing processing method, a device, a equipment and a storage medium. Background Art
[0002] In modern life, the pace of life is getting faster and faster, and clothing processing equipment is widely used.
[0003] When using a conventional clothes treating device, a user is required to add clothes to be treated into the clothes treating device, add clothes treating agent, and select a program from the complicated programs of the clothes treating device to treat the clothes.
[0004] However, since users do not have professional knowledge of clothing treatment, the clothing treatment agents added by users and the programs they choose are not necessarily suitable for the current clothing to be treated, which leads to poor clothing treatment effects. More seriously, it may cause damage to the clothing during the clothing treatment process, resulting in a poor user experience. Summary of the invention
[0005] The present invention provides a model training method, a clothing processing method, a device, an equipment and a storage medium to solve the technical problems of poor clothing processing effect and poor user experience in the clothing processing process in the related art.
[0006] According to one aspect of the present invention, a model training method is provided, comprising:
[0007] Acquire sample data; wherein the sample data includes: fabrics of various clothes and sample treatment solutions, and the sample treatment solutions include information of clothing treatment agents;
[0008] For each type of clothing fabric, the sample processing solutions are traversed by simulation to obtain the optimal processing solution corresponding to each type of fabric;
[0009] According to the fabrics of the various clothes and the corresponding optimal treatment solutions, the initial clothes treatment model is trained to obtain a target clothes treatment model; wherein the target clothes treatment model is used to output a target treatment solution according to the fabrics of the clothes to be treated, and the target treatment solution includes: information on a target clothes treatment agent for treating the clothes to be treated.
[0010] According to another aspect of the present invention, there is provided a method for treating clothes, comprising:
[0011] Acquire the fabric of the clothes to be processed according to the clothes to be processed and a pre-trained clothes fabric recognition model;
[0012] According to the fabric of the clothes to be processed and the pre-trained target clothes processing model, a target processing scheme corresponding to the clothes to be processed is obtained; wherein the target processing scheme includes: information of a target clothes processing agent for processing the clothes to be processed, and the target clothes processing model is a target clothes processing model obtained by the model training method according to any embodiment of the present invention;
[0013] The laundry to be processed is processed according to the target processing scheme.
[0014] According to another aspect of the present invention, a model training device is provided, the device comprising:
[0015] A first acquisition module is used to acquire sample data; wherein the sample data includes: fabrics of various clothes and sample treatment solutions, and the sample treatment solution includes information of clothing treatment agents;
[0016] The second acquisition module is used to traverse the sample processing solutions for each type of clothing fabric through simulation to obtain the optimal processing solution corresponding to each type of fabric;
[0017] A training module is used to train an initial clothing treatment model according to the fabrics of the various clothes and the corresponding optimal treatment solutions to obtain a target clothing treatment model; wherein the target clothing treatment model is used to output a target treatment solution according to the fabrics of the clothes to be treated, and the target treatment solution includes: information on a target clothing treatment agent for treating the clothes to be treated.
[0018] According to another aspect of the present invention, there is provided a laundry processing device, the device comprising:
[0019] A fourth acquisition module, used for acquiring the fabric of the clothes to be processed according to the clothes to be processed and a pre-trained clothing fabric recognition model;
[0020] a fifth acquisition module, configured to acquire a target treatment scheme corresponding to the clothes to be treated according to the fabric of the clothes to be treated and the pre-trained target clothes treatment model; wherein the target treatment scheme includes: information of a target clothes treatment agent for treating the clothes to be treated, and the target clothes treatment model is a target clothes treatment model obtained by the model training method described in any embodiment of the present invention;
[0021] A processing module is used to process the clothes to be processed according to the target processing scheme.
[0022] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:
[0023] at least one processor; and
[0024] a memory communicatively connected to the at least one processor; wherein,
[0025] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the model training method described in any embodiment of the present invention, or execute the clothing processing method described in any embodiment of the present invention.
[0026] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the model training method described in any embodiment of the present invention when executed, or to execute the clothing processing method described in any embodiment of the present invention.
[0027] The technical solution of the embodiment of the present invention includes: obtaining sample data, wherein the sample data includes: fabrics of various clothes and sample treatment schemes, and the sample treatment schemes include information of clothing treatment agents; for each type of clothing fabric, traversing the sample treatment schemes through simulation to obtain the optimal treatment scheme corresponding to each type of clothing fabric; training the initial clothing treatment model according to the fabrics of various clothes and the corresponding optimal treatment schemes to obtain a target clothing treatment model, wherein the target clothing treatment model is used to output the target treatment scheme according to the fabrics of the clothes to be treated, and the target treatment scheme includes: information of the target clothing treatment agent for treating the clothes to be treated. It has the following technical effects: on the one hand, the target clothing treatment model provided by this embodiment can realize the automatic output of the target treatment scheme based on the fabrics of the clothes to be treated, wherein the target treatment scheme includes information of the target clothing treatment agent for treating the clothes to be treated, thereby avoiding the user from independently determining the information of the clothing treatment agent and selecting the clothing treatment program during the clothing treatment process, and the treatment effect of the target clothing treatment model is better, and at the same time, it will not cause damage to the clothes, thereby improving the clothing treatment effect and user experience; on the other hand, during the model training process, the optimal treatment scheme corresponding to each type of fabric can be obtained through simulation, thereby reducing the cost of model training and improving the efficiency of model training.
[0028] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0030] Figure 1 A flowchart of a model training method provided according to Embodiment 1 of the present invention;
[0031] Figure 2 A flowchart of a model training method provided according to Embodiment 2 of the present invention;
[0032] Figure 3 This is a flow chart of a method for treating clothes provided according to Embodiment 3 of the present invention;
[0033] Figure 4 A schematic diagram of a clothes processing device provided by an embodiment of the present invention;
[0034] Figure 5 A schematic diagram of the structure of a model training device provided according to an embodiment of the present invention;
[0035] Figure 6 A schematic structural diagram of a clothes processing device provided according to an embodiment of the present invention;
[0036] Figure 7 It is a structural schematic diagram of an electronic device for implementing the model training method of an embodiment of the present invention. DETAILED DESCRIPTION
[0037] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0038] It should be noted that the terms "initial" and "target" in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the term "comprising" and any variation thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0039] Figure 1 This is a flow chart of a model training method provided according to the first embodiment of the present invention. This embodiment can be applied to the case where a target clothing treatment model is obtained through model training, so that a target treatment plan for the clothing to be treated can be automatically output through the target clothing treatment model. The method can be executed by a model training device, which can be implemented in the form of hardware and / or software, and the model training device can be configured in an electronic device. The electronic device can be a computer device or a server, etc. Figure 1 As shown, the method comprises the following steps:
[0040] Step 101: Obtain sample data.
[0041] The sample data includes: fabrics of various clothes and sample treatment solutions, and the sample treatment solutions include information of clothing treatment agents.
[0042] The fabrics of the clothes in this embodiment may include polyester, spandex, nylon, viscose, cotton, etc. Of course, the fabrics of the clothes may also be classified according to other classification methods, for example, according to fiber classification, according to raw material classification, according to weaving method classification or according to weaving principle classification, etc. This embodiment is not limited to this, as long as the fabric of the clothes can be determined.
[0043] The sample processing scheme in this embodiment includes information about clothing treatment agents. The clothing treatment in this embodiment refers to the processing processes of washing, drying, ironing, and disinfecting clothing. In the scenario of washing clothing, the clothing treatment agent refers to detergent. In the scenario of drying or ironing clothing, the clothing treatment agent refers to chemical reagents that may be used in the drying process or ironing process. In the scenario of disinfecting clothing, the clothing treatment agent refers to clothing disinfectant.
[0044] Optionally, the information of the laundry treatment agent in this embodiment may include the ingredients of the laundry treatment agent and the ratio of each ingredient. The ingredients of the laundry treatment agent in this embodiment may include: surfactants, builders and additives. Surfactants may include: anionic surfactants, nonionic surfactants, zwitterionic surfactants and cationic surfactants. Builders may include: sodium carbonate, sodium silicate and sodium tripolyphosphate. Additives may include: fluorescent whitening agents, corrosion inhibitors, antistatic agents, colorants, spices and bactericides.
[0045] Optionally, the information of the laundry treatment agent in this embodiment may further include the appearance of the laundry treatment agent, for example, various forms such as powder, block, paste, slurry and liquid.
[0046] In this embodiment, before step 101, the treatment effects of various clothing treatment agents may be obtained; thereafter, various sample treatment plans are generated according to the treatment effects of various clothing treatment agents. That is, according to the treatment effects of various clothing treatment agents, the components of various clothing treatment agents and the proportions of the components in a clothing treatment process are determined.
[0047] Optionally, the treatment effect of the clothes treatment agent includes: subjective effect and objective effect. In the process of generating each sample treatment scheme according to the treatment effects of various clothes treatment agents, each sample treatment scheme can be generated according to the subjective effect and objective effect corresponding to each clothes treatment agent.
[0048] The subjective effect of the clothing treatment agent in this embodiment can be obtained from the manufacturer of the clothing treatment agent, or through the promotional slogan of the manufacturer of the clothing treatment agent. The objective effect of the clothing treatment agent can be obtained through various experimental data. In the process of generating each sample treatment scheme according to the subjective effect and objective effect corresponding to each clothing treatment agent, the matching form and ratio of the clothing treatment agent can be determined according to the description of the subjective effect and the objective effect, thereby forming each sample treatment scheme.
[0049] Furthermore, the sample processing scheme in this embodiment also includes at least one of the following information: the type of clothing processing device, the temperature of the processing medium, the processing mode, and the processing time corresponding to each processing mode.
[0050] In the scenario of drying clothes, the types of clothes treating apparatus in this embodiment may include: exhaust type, condensation type and heat pump type. In the scenario of drying clothes, the treatment medium refers to air.
[0051] In the scenario of washing clothes, the type of the clothes processing device in this embodiment refers to a pulsator type or a drum type. In the scenario of washing clothes, the processing medium refers to water. In the scenario of washing clothes, the processing mode may include: washing, rinsing, dehydration and other processes. The processing time corresponding to each processing mode may include the washing time, the rinsing time and the dehydration time.
[0052] In step 101, multiple sample processing solutions may be obtained.
[0053] Step 102: For each type of clothing fabric, sample processing solutions are traversed through simulation to obtain the optimal processing solution corresponding to each type of fabric.
[0054] The simulation method in this embodiment refers to the method of using fluid simulation software for simulation. During the simulation process, the real clothing processing process can be simulated, and the processing degree corresponding to this simulation can be output. In the scene of clothing washing, the processing degree corresponding to the simulation can be measured by the washing ratio or cleanliness.
[0055] In one implementation, the sample treatment plan includes information about the clothing treatment agent. In step 102, for each type of clothing fabric, the components and proportions of each clothing treatment agent are traversed by simulation to obtain multiple treatment degrees for each type of fabric; the components and proportions of the clothing treatment agent corresponding to the optimal treatment degree are determined as the optimal treatment plan corresponding to the fabric.
[0056] In another implementation, in addition to the information of the clothing treatment agent, the sample treatment scheme also includes at least one of the type of clothing treatment device, the temperature of the treatment medium, the treatment mode, and the treatment time corresponding to each treatment mode. In step 102, for each type of clothing fabric, the information of each clothing treatment agent and the type of clothing treatment device, the temperature of the treatment medium, the treatment mode, and the treatment time corresponding to each treatment mode are traversed by simulation to obtain multiple treatment degrees for each fabric; the sample treatment scheme corresponding to the optimal treatment degree is determined as the optimal treatment scheme corresponding to the fabric. It can be understood that the obtained optimal treatment scheme includes the information of the clothing treatment agent and at least one of the type of clothing treatment device, the temperature of the treatment medium, the treatment mode, and the treatment time corresponding to each treatment mode.
[0057] It should be noted that traversing the information of each clothing treatment agent and traversing at least one of the type of clothing treatment device, the temperature of the treatment medium, the treatment mode and the treatment time corresponding to each treatment mode refers to various possible combinations of traversing the information of each clothing treatment agent and traversing at least one of the type of clothing treatment device, the temperature of the treatment medium, the treatment mode and the treatment time corresponding to each treatment mode.
[0058] Step 103: According to the fabrics of various clothes and the corresponding optimal processing solutions, the initial clothing processing model is trained to obtain the target clothing processing model.
[0059] The target clothing treatment model is used to output a target treatment solution according to the fabric of the clothing to be treated. The target treatment solution includes: information of a target clothing treatment agent for treating the clothing to be treated.
[0060] After obtaining the fabrics of various clothes and the corresponding optimal treatment solutions, the initial clothing treatment model can be trained. The initial clothing treatment model in this embodiment can be a model using a machine learning algorithm, a model using a deep learning algorithm, or a model using natural language processing (Natural Language Processing, NLP). Exemplarily, the initial clothing treatment model in this embodiment can be a ChatGenerative Pre-trained Transformer (ChatGPT) based model.
[0061] The model training process in this embodiment may include the following steps: inputting fabrics of various clothes into the initial clothing processing model to obtain the processing solution output by the initial clothing processing model; for each fabric, comparing the processing solution output by the initial clothing processing model with the optimal processing solution corresponding to the fabric to obtain a loss function; if the loss function does not meet the training end condition, updating the parameters of the initial clothing processing model using a stochastic gradient descent algorithm according to the loss function to obtain an updated initial clothing processing model, and returning to execute the step of "inputting fabrics of various clothes into the initial clothing processing model to obtain the processing solution output by the initial clothing processing model"; if the loss function meets the training end condition, determining the updated initial clothing processing model corresponding to the loss function that meets the training end condition as the target clothing processing model.
[0062] The target clothing processing model obtained based on the model training method provided in this embodiment is used to output a target processing solution according to the fabric of the clothing to be processed.
[0063] In an implementation in which the sample treatment scheme includes information of a laundry treatment agent, it can be understood that the target treatment scheme includes information of a target laundry treatment agent for treating the laundry to be treated.
[0064] In an implementation method in which the sample processing scheme includes both information on the clothing treatment agent and at least one of the type of clothing treatment device, the temperature of the treatment medium, the treatment mode, and the treatment time corresponding to each treatment mode, the target processing scheme includes information on the target clothing treatment agent for treating the clothing to be treated, and at least one of the type of clothing treatment device for treating the clothing to be treated, the temperature of the treatment medium for treating the clothing to be treated, the treatment mode for treating the clothing to be treated, and the treatment time corresponding to each treatment mode.
[0065] The above process is illustrated below with a specific example. Assume that the sample data is as shown in the following table. Each sample treatment scheme may include information about a clothing treatment agent. It can be understood that for the same fabric, the information about the clothing treatment agent is different in different sample treatment schemes. Afterwards, step 102 is executed to obtain the optimal treatment scheme corresponding to each fabric. For example, assuming that the optimal treatment scheme for fabric 1 is sample treatment scheme 11, the optimal treatment scheme for fabric 2 is sample treatment scheme 22, the optimal treatment scheme for fabric 3 is sample treatment scheme 33, the optimal treatment scheme for fabric 4 is sample treatment scheme 42, and the optimal treatment scheme for fabric 5 is sample treatment scheme 51. Afterwards, step 103 is executed to train the initial clothing treatment model according to the fabrics of various clothes and the corresponding optimal treatment schemes to obtain the target clothing treatment model.
[0066] Table 1 Sample data
[0067]
[0068] Therefore, the target clothing treatment model obtained by the model training method provided by this embodiment can realize the automatic output of the target treatment plan based on the fabric of the clothing to be treated, wherein the target treatment plan includes information about the target clothing treatment agent for treating the clothing to be treated, thereby avoiding the user from independently determining the information about the clothing treatment agent and selecting the clothing treatment program during the clothing treatment process. Since the target clothing treatment model in this embodiment is trained based on the fabrics of various clothing and the corresponding optimal treatment plans, the treatment effect of the target clothing treatment model is better, and at the same time, it will not cause damage to the clothing, thereby improving the clothing treatment effect and user experience. It can be understood that when the target clothing treatment model is used to output the target treatment plan based on the fabric of the clothing to be treated, the fabric of the clothing to be treated may be different from the fabric in Table 1.
[0069] The model training method provided in this embodiment includes: obtaining sample data, wherein the sample data includes: fabrics of various clothes and sample treatment schemes, and the sample treatment schemes include information of clothing treatment agents; for each type of clothing fabric, traversing the sample treatment schemes through simulation to obtain the optimal treatment scheme corresponding to each type of clothing fabric; training the initial clothing treatment model according to the fabrics of various clothes and the corresponding optimal treatment schemes to obtain a target clothing treatment model, wherein the target clothing treatment model is used to output the target treatment scheme according to the fabrics of the clothes to be treated, and the target treatment scheme includes: information of the target clothing treatment agent for treating the clothes to be treated. It has the following technical effects: on the one hand, the target clothing treatment model provided in this embodiment can realize the automatic output of the target treatment scheme based on the fabrics of the clothes to be treated, wherein the target treatment scheme includes information of the target clothing treatment agent for treating the clothes to be treated, thereby avoiding the user from independently determining the information of the clothing treatment agent and selecting the clothing treatment program during the clothing treatment process, and the treatment effect of the target clothing treatment model is better, and at the same time, it will not cause damage to the clothes, thereby improving the clothing treatment effect and user experience; on the other hand, during the model training process, the optimal treatment scheme corresponding to each type of fabric can be obtained through simulation, thereby reducing the cost of model training and improving the efficiency of model training.
[0070] Figure 2 Flow chart of a model training method provided according to Embodiment 2 of the present invention. Figure 1 Based on the illustrated embodiment and various optional implementation schemes, a detailed description is given of how to update the target clothing treatment model. Figure 2 As shown, the model training method provided in this embodiment includes the following steps:
[0071] Step 201: Obtain sample data.
[0072] The sample data includes: fabrics of various clothes and sample treatment solutions, and the sample treatment solutions include information of clothing treatment agents.
[0073] Step 202: for each type of clothing fabric, sample processing solutions are traversed through simulation to obtain the optimal processing solution corresponding to each type of fabric.
[0074] Step 203: According to the fabrics of various clothes and the corresponding optimal processing solutions, the initial clothing processing model is trained to obtain the target clothing processing model.
[0075] The target clothing treatment model is used to output a target treatment solution according to the fabric of the clothing to be treated, and the target treatment solution includes: information of a target clothing treatment agent for treating the clothing to be treated.
[0076] The implementation process and technical principle of step 201 and step 101, step 202 and step 102, and step 203 and step 103 are similar, and will not be repeated here.
[0077] Step 204: When it is determined that the sample processing scheme is updated, the target clothing processing model is used as a new initial clothing processing model, and the process returns to step 202 for execution.
[0078] In this embodiment, when it is determined that the sample processing scheme is updated, the target clothing processing model can be used as a new initial clothing processing model, and the process returns to step 202 to train the target clothing model again.
[0079] The sample processing solution update in this embodiment refers to the update of any information included in the sample processing solution.
[0080] In an implementation in which the sample treatment regimen includes information of a laundry treatment agent, if any one of the ingredients of the laundry treatment agent and the proportions of the ingredients is updated, it is determined that the sample treatment regimen is updated.
[0081] In an implementation method in which the sample processing scheme includes, in addition to information on the clothing treatment agent, at least one of the type of clothing treatment device, the temperature of the treatment medium, the processing mode, and the processing time corresponding to each processing mode, if any one of the ingredients of the clothing treatment agent and the ratio of each ingredient is updated, or if at least one of the type of clothing treatment device, the temperature of the treatment medium, the processing mode, and the processing time corresponding to each processing mode is updated, it is determined that the sample processing scheme is updated.
[0082] It can be understood that the target clothing processing model obtained by the model training method provided in this embodiment can be trained and updated according to the update of the sample processing scheme, so that the processing performance of the target clothing processing model is better.
[0083] The model training method provided in this embodiment, when determining that the sample processing scheme is updated, uses the target clothing processing model as a new initial clothing processing model, returns to execute the step of "for each type of clothing fabric, traversing the sample processing scheme in a simulation manner, and obtaining the optimal processing scheme corresponding to each fabric", and re-trains the target clothing processing model. The target clothing processing model can be trained and updated according to the update of the sample processing scheme, thereby improving the processing performance of the target clothing processing model.
[0084] Figure 3 This is a flowchart of a method for treating clothes provided according to Embodiment 3 of the present invention. The method for treating clothes provided in this embodiment provides a method for treating clothes using Figure 1 and Figure 2The process of performing clothing treatment using the target clothing treatment model obtained by the model training method provided in the illustrated embodiment is described in detail. This embodiment is applicable to the case where a target treatment scheme for treating clothing to be treated is automatically output through a target clothing treatment model. The method can be executed by a clothing treatment device, which can be implemented in the form of hardware and / or software, and the clothing treatment can be configured in an electronic device. The electronic device can be a washing machine, a dryer, a clothing disinfector, etc. Figure 3 As shown, the method comprises the following steps:
[0085] Step 301: Acquire the fabric of the clothes to be processed according to the clothes to be processed and a pre-trained clothing fabric recognition model.
[0086] Step 302: Obtain a target processing solution corresponding to the clothes to be processed according to the fabric of the clothes to be processed and a pre-trained target clothes processing model.
[0087] The target treatment scheme includes: information about the target laundry treatment agent for treating the laundry to be treated. The target laundry treatment model is as follows: Figure 1 or Figure 2 The target clothing processing model obtained by the model training method provided by any embodiment and various optional implementations.
[0088] Optionally, the information of the target laundry treatment agent includes: ingredients of the laundry treatment agent and ratios of the ingredients.
[0089] The clothes processing device in this embodiment includes two models: one model is a pre-trained clothes fabric recognition model, and the other model is a pre-trained clothes fabric recognition model. Figure 1 or Figure 2 The target clothing processing model obtained by the model training method provided by any embodiment and various optional implementations.
[0090] The clothing fabric recognition model in this embodiment may be a model using a machine learning algorithm, a model using a deep learning algorithm, or a model using NLP. For example, the clothing fabric recognition model in this embodiment may be ChatGPT.
[0091] Optionally, the implementation process of step 301 may include the following steps: obtaining photos of the clothes to be processed and the spectral data of the clothes to be processed; inputting the photos of the clothes to be processed and the spectral data of the clothes to be processed into the clothes fabric recognition model to obtain the fabric of the clothes to be processed. It can be understood that based on this implementation method, the clothes processing device may include a visual sensor for obtaining photos of the clothes to be processed, and may also include a spectrometer for obtaining the spectral data of the clothes to be processed. Optionally, the spectrometer in this embodiment may be a red light spectrometer, an infrared light spectrometer, an ultraviolet light spectrometer, etc. By identifying the fabric of the clothes to be processed based on the photos of the clothes to be processed and the spectral data of the clothes to be processed, the fabric recognition is achieved by combining the two properties of the clothes to be processed, the accuracy of the fabric recognition of the clothes is improved, and then the performance of the clothes processing is improved.
[0092] The training process of the clothing fabric recognition model in this embodiment may be: inputting photos and spectral data of various clothing into the initial clothing fabric recognition model to obtain the recognition result of the clothing fabric output by the initial clothing fabric recognition model; for each clothing, comparing the recognition result output by the initial clothing fabric recognition model with the fabric actually corresponding to the clothing to obtain a loss function; if the loss function does not meet the training end condition, updating the parameters of the initial clothing fabric recognition model using a stochastic gradient descent algorithm according to the loss function to obtain an updated initial clothing fabric recognition model, and returning to execute the step of "inputting photos and spectral data of various clothing into the initial clothing fabric recognition model to obtain the recognition result of the clothing fabric output by the initial clothing fabric recognition model"; if the loss function meets the training end condition, determining the updated initial clothing fabric recognition model corresponding to the loss function that meets the training end condition as the clothing fabric recognition model.
[0093] The training process of the target clothing treatment model in this embodiment is similar to Figure 1 or Figure 2 The illustrated embodiment and various optional implementation schemes are similar and will not be described in detail here.
[0094] Step 303: Process the laundry to be processed according to the target processing solution.
[0095] After the target laundry treatment model outputs a target treatment plan for the laundry to be treated, the laundry to be treated can be treated according to the target treatment plan.
[0096] In one implementation, the clothing treatment device automatically executes step 303 after determining the target treatment solution.
[0097] In another implementation, after determining the target treatment plan, the clothing treatment device may wait for a preset time period, and if no instruction from the user not to treat the clothing according to the target treatment plan is received within the preset time period, step 303 is executed.
[0098] It can be understood that in the above two implementations, the clothes treating device can prepare the target clothes treating agent according to the information of the target clothes treating agent.
[0099] In another implementation, assuming that the clothing treatment device cannot prepare the target clothing treatment agent according to the information of the target clothing treatment agent, after executing step 302, step 303 can be executed after determining that the target clothing treatment agent added by the user is obtained.
[0100] Optionally, the target processing scheme in this embodiment also includes at least one of the following information: the type of clothing processing device for processing the clothes to be processed, the temperature of the processing medium for processing the clothes to be processed, the processing mode for processing the clothes to be processed, and the processing time corresponding to each processing mode.
[0101] In the scenario of washing clothes, the type of the clothes processing device in this embodiment refers to a pulsator type or a drum type. In the scenario of washing clothes, the processing medium refers to water. In the scenario of washing clothes, the processing mode may include: washing, rinsing, dehydration and other processes. The processing time corresponding to each processing mode may include the washing time, the rinsing time and the dehydration time.
[0102] The above process is described below with a specific example. Figure 4 Schematic diagram of a clothes processing device provided by an embodiment of the present invention. Figure 4 As shown, it is assumed that the clothing processing device 40 is a washing machine. The clothing fabric recognition model 401 and the target clothing processing model 402 are pre-stored in the washing machine. The washing machine also includes a visual sensor 403 and a spectrometer 404. The visual sensor 403 and the spectrometer 404 are both connected to the clothing fabric recognition model 401. The clothing fabric recognition model 401 is connected to the target clothing processing model 402. The target clothing processing model 402 can be connected to the main control board of the washing machine. Alternatively, the clothing fabric recognition model 401 and the target clothing processing model 402 are both stored in the main control board.
[0103] When the user uses the clothes treatment device 40 to wash clothes, the user only needs to put the clothes to be treated into the clothes treatment device 40. After the main control board of the clothes treatment device 40 detects that the user puts in the clothes to be treated, it can trigger the visual sensor 403 to obtain the photo of the clothes to be treated and trigger the spectrometer 404 to obtain the spectral data of the clothes to be treated.
[0104] The visual sensor 403 inputs the photo of the clothes to be processed into the clothes fabric recognition model 401, and the spectrometer 404 inputs the spectral data of the clothes to be processed into the clothes fabric recognition model 401. The clothes fabric recognition model 401 outputs the fabric of the clothes to be processed to the target clothes processing model 402 according to the photo of the clothes to be processed and the spectral data of the clothes to be processed.
[0105] The target clothing treatment model 402 outputs a target treatment scheme corresponding to the clothing to be treated according to the fabric of the clothing to be treated. Afterwards, the main control board can wash the clothing to be treated according to the target treatment scheme corresponding to the clothing to be treated.
[0106] Exemplarily, one possible implementation of the target treatment scheme is: the ratio of ingredient A in the detergent is 50% (weight ratio or volume ratio), the ratio of ingredient B in the detergent is 50%, the clothes are washed in a drum type, the water temperature is 40 degrees, the washing time is 20 minutes, the rinsing time is 10 minutes, and the dehydration time is 10 minutes.
[0107] It can be seen that in the process of clothing treatment using the clothing treatment method provided in this embodiment, the target treatment plan can be automatically output, wherein the target treatment plan includes information of the target clothing treatment agent, thereby avoiding the user from independently determining the information of the clothing treatment agent and selecting the clothing treatment program during the clothing treatment process. The clothing treatment method has a better treatment effect on the clothes and will not cause damage to the clothes, thereby improving the clothing treatment effect and user experience.
[0108] Optionally, based on Figure 2 As described in the illustrated embodiments and various optional implementations, the target laundry processing model can be updated. In one implementation, the model training device can send the updated target laundry processing model to the laundry processing device after updating the target laundry processing model. In another implementation, the laundry processing device can request the updated target laundry processing model from the model training device at a preset frequency, for example, once a week or 10 days.
[0109] In this embodiment, after the clothing processing device has processed the clothing according to the target processing scheme, the fabric of the clothing to be processed and the corresponding target processing scheme can be sent to the model training device, so that the model training device can train and update the target clothing processing model according to the information fed back by the clothing processing device, thereby realizing continuous updating of the target clothing processing model training and improving the processing performance of the target clothing processing model.
[0110] In the scenario where the clothing processing device cannot be connected to the model training device due to network problems, the clothing processing device can first store the fabric of the clothing to be processed and the corresponding target processing solution. After the network is restored to normal, the fabric of the clothing to be processed and the corresponding target processing solution are sent to the model training device.
[0111] The clothing treatment method provided in this embodiment includes: obtaining the fabric of the clothing to be treated according to the clothing to be treated and a pre-trained clothing fabric recognition model, obtaining the target treatment scheme corresponding to the clothing to be treated according to the fabric of the clothing to be treated and a pre-trained target clothing treatment model, and treating the clothing to be treated according to the target treatment scheme. It has the following technical effects: on the one hand, the fabric of the clothing to be treated can be identified according to the pre-trained clothing fabric recognition model using big data technology, with a high accuracy rate, thereby improving the performance of subsequent clothing treatment; on the other hand, the target treatment scheme can be automatically output, wherein the target treatment scheme includes information of the target clothing treatment agent, thereby avoiding the user from independently determining the information of the clothing treatment agent and selecting the clothing treatment program during the clothing treatment process. The clothing treatment method has a better treatment effect on the clothing, and at the same time, it will not cause damage to the clothing, thereby improving the clothing treatment effect and user experience.
[0112] Figure 5 Schematic diagram of a model training device according to an embodiment of the present invention. Figure 5 As shown, the device includes the following modules: a first acquisition module 51 , a second acquisition module 52 and a training module 53 .
[0113] The first acquisition module 51 is used to acquire sample data.
[0114] The sample data includes: fabrics of various clothes and sample treatment solutions, and the sample treatment solutions include information of clothing treatment agents.
[0115] The second acquisition module 52 is used to traverse the sample processing solutions for each type of clothing fabric through simulation to obtain the optimal processing solution corresponding to each type of fabric.
[0116] The training module 53 is used to train the initial clothing processing model according to the fabrics of various clothes and the corresponding optimal processing solutions to obtain the target clothing processing model.
[0117] The target clothing treatment model is used to output a target treatment solution according to the fabric of the clothing to be treated, and the target treatment solution includes: information of a target clothing treatment agent for treating the clothing to be treated.
[0118] In one embodiment, the information of the clothing treatment agent includes: the composition of the clothing treatment agent and the ratio of each component. The second acquisition module 52 is specifically used to: for each type of clothing fabric, traverse the composition and the ratio of each component of each clothing treatment agent through simulation to obtain multiple treatment degrees of each fabric; determine the composition and the ratio of the composition of the clothing treatment agent corresponding to the optimal treatment degree as the optimal treatment solution corresponding to the fabric.
[0119] In one embodiment, the model training device provided in this embodiment also includes: a third acquisition module, used to obtain the treatment effects of various clothing treatment agents; a generation module, used to generate various sample treatment plans according to the treatment effects of various clothing treatment agents.
[0120] In one embodiment, the treatment effect of the clothes treatment agent includes: a subjective effect and an objective effect. The generation module is specifically used to: generate each sample treatment plan according to the subjective effect and the objective effect corresponding to each clothes treatment agent.
[0121] In one embodiment, the sample processing scheme further includes at least one of the following information: the type of the laundry processing device, the temperature of the processing medium, the processing mode, and the processing time corresponding to each processing mode.
[0122] In one embodiment, the device further comprises: an updating module, which is used to use the target clothing treatment model as a new initial clothing treatment model and return to execute the steps executed by the second acquisition module 52 when it is determined that the sample treatment scheme is updated.
[0123] The model training device provided in the embodiment of the present invention can execute the model training method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0124] Figure 6 Schematic diagram of the structure of a clothes processing device provided according to an embodiment of the present invention. Figure 6 As shown, the clothes processing device provided in this embodiment includes the following modules: a fourth acquisition module 61 , a fifth acquisition module 62 and a processing module 63 .
[0125] The fourth acquisition module 61 is used to acquire the fabric of the clothes to be processed according to the clothes to be processed and a pre-trained clothing fabric recognition model.
[0126] The fifth acquisition module 62 is used to acquire a target processing solution corresponding to the clothes to be processed according to the fabric of the clothes to be processed and a pre-trained target clothes processing model.
[0127] The target treatment scheme includes: information about the target laundry treatment agent for treating the laundry to be treated. The target laundry treatment model is as follows: Figure 1 or Figure 2The target clothing processing model obtained by the model training method provided by any embodiment and various optional implementations.
[0128] The processing module 63 is used to process the laundry to be processed according to the target processing scheme.
[0129] In one embodiment, the fourth acquisition module 61 is specifically used to: acquire photos of the clothes to be processed and spectral data of the clothes to be processed; input the photos of the clothes to be processed and the spectral data of the clothes to be processed into a clothes fabric recognition model to obtain the fabric of the clothes to be processed.
[0130] In one embodiment, the target treatment plan also includes at least one of the following information: the type of clothing treatment device for treating the clothes to be treated, the temperature of the treatment medium for treating the clothes to be treated, the treatment mode for treating the clothes to be treated, and the treatment time corresponding to each treatment mode.
[0131] The clothes processing device provided in the embodiment of the present invention can execute the clothes processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.
[0132] Figure 7 It is a structural diagram of an electronic device for implementing the model training method of an embodiment of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent washing machines, dryers, clothing disinfection machines, clothing dry cleaning machines, and other possible clothing processing equipment. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The electronic device may also represent household appliances, such as washing machines, etc. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.
[0133] like Figure 7As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.
[0134] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, a key, a touch screen, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0135] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a model training method, or a clothing processing method.
[0136] In some embodiments, the model training method may be implemented as a computer program or computer instructions, which are tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the model training method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the model training method, or, execute the clothing treatment method, in any other appropriate manner (e.g., by means of firmware).
[0137] 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 chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.
[0138] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.
[0139] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0140] To provide interaction with a user, the systems and techniques described herein may 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 a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0141] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server) or a computing system that includes middleware components (e.g., an application server) or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein) or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.
[0142] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.
[0143] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.
[0144] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims
1. A model training method, characterized in that: include: Acquire sample data; wherein the sample data includes: fabrics of various clothes and sample treatment solutions, and the sample treatment solutions include information of clothing treatment agents; For each type of clothing fabric, the sample processing solutions are traversed by simulation to obtain the optimal processing solution corresponding to each type of fabric; According to the fabrics of the various clothes and the corresponding optimal treatment solutions, the initial clothes treatment model is trained to obtain a target clothes treatment model; wherein the target clothes treatment model is used to output a target treatment solution according to the fabrics of the clothes to be treated, and the target treatment solution includes: information on a target clothes treatment agent for treating the clothes to be treated.
2. The method according to claim 1, characterized in that The information of the laundry treatment agent includes: the ingredients of the laundry treatment agent and the proportions of the ingredients; For each type of clothing fabric, the sample processing solutions are traversed by simulation to obtain the optimal processing solution corresponding to each type of fabric, including: For each type of clothing fabric, the components and proportions of each clothing treatment agent are traversed through simulation to obtain multiple treatment levels of each fabric; The composition and ingredient ratio of the clothing treatment agent corresponding to the optimal treatment degree are determined as the optimal treatment solution corresponding to the fabric.
3. The method according to claim 1, characterized in that Before obtaining the sample data, the method further includes: Obtain the treatment effects of various clothing treatment agents; The sample treatment plans are generated according to the treatment effects of various clothing treatment agents.
4. The method according to claim 3, characterized in that The treatment effects of the laundry treatment agent include: subjective effects and objective effects; The generating of each sample treatment scheme according to the treatment effects of various laundry treatment agents comprises: Each of the sample treatment plans is generated according to the subjective effect and the objective effect corresponding to each of the clothing treatment agents.
5. The method according to claim 1, characterized in that The sample processing scheme further includes at least one of the following information: the type of the laundry processing device, the temperature of the processing medium, the processing mode, and the processing time corresponding to each processing mode.
6. The method according to claim 5, characterized in that After the initial clothing processing model is trained according to the various clothing fabrics and the corresponding optimal processing solutions to obtain the target clothing processing model, the method further includes: When it is determined that the sample processing scheme is updated, the target clothing processing model is used as a new initial clothing processing model, and the step of "for each type of clothing fabric, traversing the sample processing scheme through simulation to obtain the optimal processing scheme corresponding to each type of fabric" is returned to be executed.
7. A method for treating clothing, characterized in that: include: Acquire the fabric of the clothes to be processed according to the clothes to be processed and a pre-trained clothes fabric recognition model; According to the fabric of the clothes to be processed and the pre-trained target clothes processing model, a target processing scheme corresponding to the clothes to be processed is obtained; wherein the target processing scheme includes: information of a target clothes processing agent for processing the clothes to be processed, and the target clothes processing model is a target clothes processing model obtained by the model training method according to any one of claims 1 to 6; The laundry to be processed is processed according to the target processing scheme.
8. The method according to claim 7, characterized in that The method of obtaining the fabric of the clothes to be processed according to the clothes to be processed and the pre-trained clothes fabric recognition model comprises: Acquiring photos of the clothes to be processed and spectral data of the clothes to be processed; The photo of the clothes to be processed and the spectrum data of the clothes to be processed are input into the clothes fabric recognition model to obtain the fabric of the clothes to be processed.
9. The method according to claim 7 or 8, characterized in that: The target treatment plan also includes at least one of the following information: the type of clothing treatment device for treating the clothing to be treated, the temperature of the treatment medium for treating the clothing to be treated, the treatment mode for treating the clothing to be treated, and the treatment time corresponding to each treatment mode.
10. A model training device, characterized in that: include: A first acquisition module is used to acquire sample data; wherein the sample data includes: fabrics of various clothes and sample treatment solutions, and the sample treatment solution includes information of clothing treatment agents; The second acquisition module is used to traverse the sample processing solutions for each type of clothing fabric through simulation to obtain the optimal processing solution corresponding to each type of fabric; A training module is used to train an initial clothing treatment model according to the fabrics of the various clothes and the corresponding optimal treatment solutions to obtain a target clothing treatment model; wherein the target clothing treatment model is used to output a target treatment solution according to the fabrics of the clothes to be treated, and the target treatment solution includes: information on a target clothing treatment agent for treating the clothes to be treated.
11. A clothes processing device, characterized in that: include: A fourth acquisition module, used for acquiring the fabric of the clothes to be processed according to the clothes to be processed and a pre-trained clothing fabric recognition model; a fifth acquisition module, configured to acquire a target treatment scheme corresponding to the clothes to be treated according to the fabric of the clothes to be treated and the pre-trained target clothes treatment model; wherein the target treatment scheme includes: information of a target clothes treatment agent for treating the clothes to be treated, and the target clothes treatment model is a target clothes treatment model obtained by the model training method according to any one of claims 1 to 6; A processing module is used to process the clothes to be processed according to the target processing scheme.
12. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the model training method described in any one of claims 1 to 6, or execute the clothing processing method described in any one of claims 7 to 9.
13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the model training method described in any one of claims 1 to 6, or to implement the clothing processing method described in any one of claims 7 to 9 when executed.
Citation Information
Patent Citations
Model training method, clothes washing method, system, device and medium
CN111598141A
Clothes matching method and device and clothes matching system
CN114255332A
Clothes stain treatment system and clothes stain treatment method
CN114687123A
Clothes processing method and device, electronic equipment and storage medium
CN115787271A
Method, system and equipment for guiding user to process clothes and storage medium
CN116152536A
