CN112831976A - Clothes material identification and washing scheme determination method, washing machine and server - Google Patents
Clothes material identification and washing scheme determination method, washing machine and server Download PDFInfo
- Publication number
- CN112831976A CN112831976A CN202110018227.9A CN202110018227A CN112831976A CN 112831976 A CN112831976 A CN 112831976A CN 202110018227 A CN202110018227 A CN 202110018227A CN 112831976 A CN112831976 A CN 112831976A
- Authority
- CN
- China
- Prior art keywords
- clothes
- washed
- infrared spectrum
- material type
- washing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
- D06F33/00—Control of operations performed in washing machines or washer-dryers
- D06F33/30—Control of washing machines characterised by the purpose or target of the control
- D06F33/32—Control of operational steps, e.g. optimisation or improvement of operational steps depending on the condition of the laundry
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
- D06F34/00—Details of control systems for washing machines, washer-dryers or laundry dryers
- D06F34/04—Signal transfer or data transmission arrangements
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
- D06F34/00—Details of control systems for washing machines, washer-dryers or laundry dryers
- D06F34/04—Signal transfer or data transmission arrangements
- D06F34/05—Signal transfer or data transmission arrangements for wireless communication between components, e.g. for remote monitoring or control
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
- D06F34/00—Details of control systems for washing machines, washer-dryers or laundry dryers
- D06F34/14—Arrangements for detecting or measuring specific parameters
- D06F34/18—Condition of the laundry, e.g. nature or weight
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
- D06F39/00—Details of washing machines not specific to a single type of machines covered by groups D06F9/00 - D06F27/00
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
- D06F2103/00—Parameters monitored or detected for the control of domestic laundry washing machines, washer-dryers or laundry dryers
- D06F2103/02—Characteristics of laundry or load
- D06F2103/06—Type or material
Abstract
The invention provides a clothes material identification and washing scheme determination method, a washing machine and a server. The method for identifying the material quality of the clothes comprises the following steps: acquiring infrared spectrum data of clothes to be washed; and analyzing the infrared spectrum data of the clothes to be washed by utilizing the trained clothes material recognition neural network model, and determining the clothes material type of the clothes to be washed according to the analysis result. The infrared spectrum data of the clothes to be washed can be automatically acquired, and the infrared spectrum data of the clothes to be washed are analyzed by utilizing a deep learning algorithm, so that the material type of the clothes to be washed is determined.
Description
Technical Field
The invention relates to the technical field of clothes washing, in particular to a clothes material identification and washing scheme determination method, a washing machine and a server.
Background
With the continuous development and progress of the society, the requirements of consumers on product comfort and experience are higher and higher, and the consumers hope that the washing machine can automatically identify the clothes material and automatically determine a reasonable washing scheme, so that the automatic washing of the washing machine is really realized.
At present, the automatic identification technology of clothes in the industry comprises the following steps: 1. image recognition method, 2, water absorption detection method, 3, label recognition method. The image recognition method can only analyze the surface condition of the material, and the material of the clothes cannot be accurately recognized for the same material with different colors or under the condition of weak light; the water absorption method is used for detecting the material quality of the clothes according to the comparative analysis of the weight of the material before water absorption and the weight after water absorption, and the detection result is very inaccurate; the tag identification method requires that each piece of clothing has a tag, but in reality, each piece of clothing does not have a tag, so that the method is very difficult to implement.
In view of the above, a method for identifying the type of clothes material and a washing machine based on automatic identification of clothes material are needed.
Disclosure of Invention
The invention mainly aims to provide a clothes material identification and washing scheme determination method, a washing machine and a server, so as to achieve the purpose of determining a corresponding washing scheme according to the clothes material and automatically washing.
In a first aspect, the present invention provides a method for identifying a material of a garment, comprising the steps of: acquiring infrared spectrum data of clothes to be washed; and analyzing the infrared spectrum data of the clothes to be washed by utilizing the trained clothes material recognition neural network model, and determining the clothes material type of the clothes to be washed according to the analysis result.
In one embodiment, the analyzing the infrared spectrum data of the clothes to be washed by using the trained clothes material recognition neural network model, and determining the clothes material type of the clothes to be washed according to the analysis result comprises: extracting the characteristics and numerical values of the infrared spectrum data of the clothes to be washed; and matching the characteristics of the infrared spectrum data of the clothes to be washed with the corresponding characteristics of the infrared spectrum data of the preset clothes material type, and determining the clothes material type of the clothes to be washed according to the matching result.
In one embodiment, matching the characteristics of the infrared spectrum data of the laundry to be washed with the corresponding characteristics of the infrared spectrum data of the preset laundry material type, and determining the laundry material type of the laundry according to the matching result includes: acquiring weights of corresponding characteristics of the infrared spectrum data of the preset clothes material type, which correspond to the characteristics of the infrared spectrum data of the clothes to be washed one by one, aiming at the infrared spectrum data of each preset clothes material type, weighting and summing numerical values of the characteristics of the infrared spectrum data of the clothes to be washed according to the weights, and taking the summed value as the matching degree of the clothes material type of the clothes to be washed and the preset clothes material type; and selecting the preset clothes material type corresponding to the maximum matching degree from the matching degrees of the clothes material type of the clothes to be washed and each preset clothes material type as the clothes material type of the clothes to be washed.
In one embodiment, the clothing material quality recognition neural network model is constructed by the following steps: acquiring a plurality of data samples for training a clothing material recognition neural network model, wherein each data sample comprises a clothing material type and infrared spectrum data of the clothing material type; and training the clothes material recognition neural network model by using the plurality of data samples to obtain the trained clothes material recognition neural network model.
In one embodiment, before analyzing the infrared spectrum data of the laundry to be washed by using the trained laundry material recognition neural network model, the method further comprises: the method comprises the following steps of preprocessing infrared spectrum data of clothes to be washed, wherein the preprocessing comprises data standardization processing, high-frequency noise filtering processing, differential derivation of signals and baseline correction processing, and the data standardization processing comprises mean value centralization processing, normalization processing and standard normal transformation processing.
In one embodiment, the method further comprises: sending inquiry information whether the determined clothes material type of the clothes to be washed is correct or not; and when the inquiry result is that the determined clothes material type of the clothes to be washed is wrong, acquiring the corrected clothes material type of the clothes to be washed.
In one embodiment, the method further comprises: and storing the infrared spectrum data of the clothes to be washed and the material type of the clothes in a correlation manner, so as to optimize and adjust the trained clothes material recognition neural network model.
In one embodiment, the infrared spectral data includes at least one of: near infrared spectral data and hyperspectral data.
In one embodiment, the clothing material quality recognition neural network model is a deep learning neural network model.
In a second aspect, the present invention provides a laundry washing course determining method, comprising the steps of: determining the clothes material type of the clothes to be washed by using the clothes material identification method; acquiring image data of clothes to be washed; determining the color and weave of the clothes to be washed according to the image data of the clothes to be washed by utilizing the trained image recognition neural network model; and determining a washing scheme aiming at the clothes to be washed based on the preset corresponding relation between the clothes material type, the preset color and the preset weave and the washing scheme according to the clothes material type, the preset color and the preset weave of the clothes to be washed.
In one embodiment, the image recognition neural network model is constructed by: obtaining a plurality of sample data sets for training an image recognition neural network model, wherein each sample data set comprises a plurality of sample subsets corresponding to a type of clothing material, and each sample subset comprises different colors corresponding to a cloth weave; and training the image recognition neural network model by using the plurality of sample data sets to obtain the trained image recognition neural network model.
In a third aspect, the present invention provides a washing machine comprising: the infrared spectrum sensor is used for acquiring infrared spectrum data of the clothes to be washed; the camera device is used for acquiring image data of the clothes to be washed; the communication device is used for sending the infrared spectrum data of the clothes to be washed acquired by the infrared spectrum sensor and the image data of the clothes to be washed acquired by the camera device to the server so that the server determines the washing scheme aiming at the clothes to be washed by using the clothes washing scheme determining method, and the communication device is also used for receiving the washing scheme aiming at the clothes to be washed returned by the server; the washing device is used for washing the clothes to be washed; the washing device comprises a controller and a memory, wherein program codes are stored in the memory, and when the program codes are executed by the controller, the controller controls the washing device to wash clothes to be washed according to a washing scheme which is received by the communication device and aims at the clothes to be washed.
In one embodiment, the communication device is further configured to receive a laundry material type of the laundry returned by the server; the washing machine further includes: and the display device is used for displaying the clothes material type of the clothes to be washed, which is received by the communication device and returned by the server.
In one embodiment, the communications apparatus is further configured to: receiving the clothes material type after the clothes material type of the clothes to be washed returned by the server is corrected; sending the corrected clothes material type to a server so that the server determines a new washing scheme aiming at the clothes to be washed according to the corrected clothes material type; receiving a new washing scheme for the clothes to be washed returned by the server; the controller is further used for controlling the washing device to wash the clothes to be washed according to the new washing scheme received by the communication device when the communication device receives the corrected clothes material type.
In one embodiment, the infrared spectral sensor comprises a near infrared spectral sensor and/or a hyperspectral sensor.
In one embodiment, the infrared spectrum sensor comprises an illumination device for illuminating the laundry.
In a fourth aspect, the present invention provides a server comprising a processor and a memory, said memory having stored therein program code which, when executed by said processor, implements the steps of a laundry material identification method as described above or the steps of a laundry washing program determination method as described above.
In one embodiment, the server is a local server or a cloud server.
In a fifth aspect, the present invention provides a laundry control system comprising: a washing machine as described above and a server as described above.
In a sixth aspect, the present invention provides a storage medium storing a computer program which, when executed by a processor, implements the steps of the laundry material identification method as described above or the steps of the laundry washing pattern determination method as described above.
The infrared spectrum data of the clothes to be washed can be automatically acquired, and the infrared spectrum data of the clothes to be washed are analyzed by utilizing a deep learning algorithm, so that the material type of the clothes to be washed is determined. And then, a washing scheme for the clothes to be washed is determined based on the determined type of the clothes material, so that automatic and reasonable washing is realized according to the material of the clothes to be washed. The material type and the washing scheme of the clothes to be washed do not need to be manually set by a user, so that the automatic washing of the clothes to be washed is really realized, and more precious time and energy are saved for the user.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention, in which:
FIG. 1 is a flowchart of a method for identifying a texture of a garment according to an exemplary embodiment of the present application;
fig. 2 is a flowchart of a laundry washing course determining method according to an exemplary embodiment of the present application;
FIG. 3 is a schematic illustration of an infrared spectrum according to an embodiment of the present application;
fig. 4 is a schematic diagram illustrating a connection relationship between an MCU in an intelligent acquisition module and each device according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a circuit connection relationship of an MCU according to an embodiment of the present application;
FIG. 6 is a schematic diagram of an overall structure of a system for washing laundry according to an embodiment of the present application;
fig. 7 is a flowchart illustrating a cloud server identifying a material type of a garment according to an embodiment of the present application.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
Example one
The present embodiment provides a method for identifying a clothing material, and fig. 1 is a flowchart of a method for identifying a clothing material according to an exemplary embodiment of the present application. As shown in fig. 1, the method comprises the steps of:
s100: and acquiring infrared spectrum data of the clothes to be washed.
Wherein the infrared spectral data at least comprises one of the following: near infrared spectral data and hyperspectral data.
S200: and analyzing the infrared spectrum data of the clothes to be washed by utilizing the trained clothes material recognition neural network model, and determining the clothes material type of the clothes to be washed according to the analysis result.
The clothing material identification neural network model is constructed by the following steps: acquiring a plurality of data samples for training a clothing material recognition neural network model, wherein each data sample comprises a clothing material type and infrared spectrum data of the clothing material type; and training the clothes material recognition neural network model by using the plurality of data samples to obtain the trained clothes material recognition neural network model. The clothing material identification neural network model is a deep learning neural network model.
The method comprises the following steps of analyzing infrared spectrum data of clothes to be washed by utilizing a trained clothes material recognition neural network model, and determining the clothes material type of the clothes to be washed according to an analysis result, wherein the method comprises the following steps: extracting the characteristics and numerical values of the infrared spectrum data of the clothes to be washed; and matching the characteristics of the infrared spectrum data of the clothes to be washed with the corresponding characteristics of the infrared spectrum data of the preset clothes material type, and determining the clothes material type of the clothes to be washed according to the matching result.
Specifically, the characteristics of the infrared spectrum data of the clothes to be washed are matched with the corresponding characteristics of the infrared spectrum data of the preset clothes material type, and the clothes material type of the clothes to be washed is determined according to the matching result, and the method comprises the following steps: acquiring weights of corresponding characteristics of the infrared spectrum data of the preset clothes material type, which correspond to the characteristics of the infrared spectrum data of the clothes to be washed one by one, aiming at the infrared spectrum data of each preset clothes material type, weighting and summing numerical values of the characteristics of the infrared spectrum data of the clothes to be washed according to the weights, and taking the summed value as the matching degree of the clothes material type of the clothes to be washed and the preset clothes material type; and selecting the preset clothes material type corresponding to the maximum matching degree from the matching degrees of the clothes material type of the clothes to be washed and each preset clothes material type as the clothes material type of the clothes to be washed.
Before analyzing the infrared spectrum data of the clothes to be washed by using the trained clothes material recognition neural network model, the method further comprises the following steps: the method comprises the following steps of preprocessing infrared spectrum data of clothes to be washed, wherein the preprocessing comprises data standardization processing, high-frequency noise filtering processing, differential derivation of signals and baseline correction processing, and the data standardization processing comprises mean value centralization processing, normalization processing and standard normal transformation processing.
The method further comprises the following steps: sending inquiry information whether the determined clothes material type of the clothes to be washed is correct or not; and when the inquiry result is that the determined clothes material type of the clothes to be washed is wrong, acquiring the corrected clothes material type of the clothes to be washed.
The method further comprises the following steps: and storing the infrared spectrum data of the clothes to be washed and the material type of the clothes in a correlation manner, so as to optimize and adjust the trained clothes material recognition neural network model.
According to the embodiment, infrared spectrum data of clothes to be washed are collected firstly, and the infrared spectrum data of the clothes to be washed are analyzed by utilizing a deep learning algorithm, so that the material type of the clothes to be washed is determined.
Example two
The present example provides a laundry scheme determining method, and fig. 2 is a flowchart of a laundry scheme determining method according to an exemplary embodiment of the present application. As shown in fig. 2, the method comprises the steps of:
s110: the clothes material type of the clothes to be washed is determined by the clothes material identification method.
S120: image data of laundry is acquired.
S130: and determining the color and weave of the clothes to be washed according to the image data of the clothes to be washed by utilizing the trained image recognition neural network model.
Wherein the image recognition neural network model is constructed by the following steps: obtaining a plurality of sample data sets for training an image recognition neural network model, wherein each sample data set comprises a plurality of sample subsets corresponding to a type of clothing material, and each sample subset comprises different colors corresponding to a cloth weave; and training the image recognition neural network model by using the plurality of sample data sets to obtain the trained image recognition neural network model.
S140: and determining a washing scheme aiming at the clothes to be washed based on the preset corresponding relation between the clothes material type, the preset color and the preset weave and the washing scheme according to the clothes material type, the preset color and the preset weave of the clothes to be washed.
According to the method and the device for determining the washing scheme of the clothes, on the basis of determining the material type of the clothes to be washed, the image data of the clothes to be washed are continuously collected, the color and the weave of the clothes to be washed are determined according to the image data of the clothes to be washed by using an image recognition method, so that the washing scheme of the clothes to be washed is determined, the purpose of automatically determining the washing scheme of the clothes to be washed is really achieved, and the intellectualization is achieved.
EXAMPLE III
The embodiment provides a washing machine including:
the infrared spectrum sensor is used for acquiring infrared spectrum data of the clothes to be washed;
the camera device is used for acquiring image data of the clothes to be washed;
the communication device is used for sending the infrared spectrum data of the clothes to be washed acquired by the infrared spectrum sensor and the image data of the clothes to be washed acquired by the camera device to the server so that the server determines the washing scheme aiming at the clothes to be washed by using the clothes washing scheme determining method, and the communication device is also used for receiving the washing scheme aiming at the clothes to be washed returned by the server;
the washing device is used for washing the clothes to be washed;
the washing device comprises a controller and a memory, wherein program codes are stored in the memory, and when the program codes are executed by the controller, the controller controls the washing device to wash clothes to be washed according to a washing scheme which is received by the communication device and aims at the clothes to be washed.
The communication device is also used for receiving the clothes material type of the clothes to be washed returned by the server; the washing machine further includes: and the display device is used for displaying the clothes material type of the clothes to be washed, which is received by the communication device and returned by the server.
The communication device is further configured to: receiving the clothes material type after the clothes material type of the clothes to be washed returned by the server is corrected; sending the corrected clothes material type to a server so that the server determines a new washing scheme aiming at the clothes to be washed according to the corrected clothes material type; receiving a new washing scheme for the clothes to be washed returned by the server; the controller is further used for controlling the washing device to wash the clothes to be washed according to the new washing scheme received by the communication device when the communication device receives the corrected clothes material type.
Wherein the infrared spectrum sensor comprises a near infrared spectrum sensor and/or a hyperspectral sensor. The infrared spectrum sensor comprises an illuminating device used for illuminating the clothes to be washed.
The washing machine of the embodiment can determine the clothes material type of the clothes to be washed according to the infrared spectrum data of the clothes to be washed, and can effectively avoid misjudgment caused by color difference when the image recognition method is used for recognizing the clothes material type. And moreover, the neural network model is identified based on the clothes material, so that more accurate judgment can be given to different material contents of clothes to be washed. The illumination device in the infrared spectrum sensor actively illuminates the clothes to be washed, so that the interference of external light rays when the infrared spectrum data of the clothes to be washed are collected is avoided.
Example four
The present embodiment provides a server comprising a processor and a memory, wherein the memory stores program code, and when the program code is executed by the processor, the steps of the laundry material identification method as described above or the steps of the laundry washing program determination method as described above are implemented. The server may include a communication means for receiving infrared spectrum data and image data of laundry to be washed.
In one example, the server may be a local server or a cloud server.
In one example, the server may include one or more processors (CPUs), input/output interfaces, network interfaces, and memory. The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or FLASH memory (FLASH RAM). Memory is an example of a computer-readable medium.
EXAMPLE five
The embodiment provides a washing machine which can automatically identify the type of the material of clothes and automatically wash the clothes to be washed according to a corresponding washing scheme. The washing machine can automatically identify the clothes material type of the clothes to be washed, and determine the most appropriate washing scheme according to the clothes material type. Meanwhile, misjudgment caused by color difference of the same clothes material type when the clothes material type is identified based on an image identification method can be effectively avoided. Moreover, the washing machine can also give more accurate judgment to the proportion of different material components of the clothes. The light source in the infrared spectrum sensor directly irradiates the clothes to be washed, so that the interference of external light is avoided.
The method and implementation process of the embodiment are as follows:
1. the near infrared spectrum data of the clothes to be washed are collected through a near infrared spectrum sensor embedded into the washing machine, a corresponding near infrared spectrum (shown in figure 3) is displayed on a display screen of the washing machine, and meanwhile, the infrared spectrum data of the clothes to be washed are uploaded to a data analysis platform. Meanwhile, the image data of the laundry is photographed by a camera embedded in the washing machine and uploaded to the data analysis platform.
2. The server side obtains near infrared spectrum data of the clothes to be washed from the data analysis platform, analyzes the near infrared spectrum data of the clothes to be washed by using a deep learning algorithm, obtains the material types of the clothes to be washed through steps of denoising, feature extraction, classification recognition and the like, and transmits the clothes to the washing machine through the data analysis platform.
In the present technical solution, the deep learning algorithm model (in this embodiment, the clothing material recognition neural network model) is established for predicting the composition or properties of an unknown sample. The method for establishing the correction model can comprise the following three methods: principal Component Regression (PCR), Partial Least Squares Regression (PISR), and Multiple Linear Regression (MIR).
The principal component analysis method is to reduce the dimension of data to eliminate the mutual overlapped information under the coexistence of numerous chemical information, and converts the original variables, uses a few new variables as the linear combination of the original variables, and simultaneously, the new variables should represent the data structure characteristics of the original variables as much as possible without losing information. Through principal component regression, noise can be removed, the problem of collinearity in the regression is solved, the information utilization is effectively improved, and the stability of the model is improved; the partial least squares method is similar to the principal component analysis, and the difference between the partial least squares method and the principal component analysis is that the factor in the variable Y is described, and the information contained in the variable X is also described, and the standard error of prediction Set (SEP) can be standardized by the RPD (Recognition of predicted Decision method) to increase the accuracy of the evaluation model. If the RPD is greater than 10, the accuracy and stability of the established model are very good, and the related parameters can be accurately predicted; if the RPD is between 5 and 10, the model can be used for quality control; if the RPD is between 2.5 and 5, the model can only carry out qualitative judgment on the content of the measured component in the sample, such as high, medium and low, and cannot be used for quantitative analysis; if the RPD is close to 1, it indicates that SEP is substantially equal to SD (Standard development), so the model cannot accurately and effectively predict the component content.
The near infrared spectrum sensor in the washing machine of this embodiment is not independent, but is included in an intelligent acquisition module, the intelligent acquisition module further includes a MCU (Microcontroller Unit), and fig. 5 is a schematic diagram of a circuit connection relationship of the MCU according to an embodiment of the present application. The MCU (as shown in fig. 4) is responsible for converting the infrared spectrum data of the laundry collected by the near infrared spectrum sensor into a digital signal, and uploading the infrared spectrum data collected by the infrared spectrum sensor to the server through the WiFi network based on a certain communication protocol. The server analyzes the infrared spectrum data of the clothes to be washed, then determines the material type of the clothes to be washed, and returns the material type of the clothes to the washing machine.
And meanwhile, the server determines the color and the weave of the clothes to be washed according to the image data of the clothes to be washed, further determines a washing scheme aiming at the clothes to be washed by combining the clothes material type of the clothes to be washed, and returns the washing scheme to the washing machine.
3. The washing machine acquires the identification result of the material type of the clothes and displays the identification result on a display screen. And meanwhile, the washing device is automatically set according to the washing scheme which is returned by the server and aims at the clothes to be washed, and the next step of instruction is waited.
The washing machine in the embodiment comprises the communication device and the display device, so that the washing machine is correspondingly provided with a data transmission function and a display function. The obtained result data is that the near infrared spectrum sensor scans clothes, the near infrared spectrum data is uploaded to the cloud server, the cloud server executes the process according to the process shown in the figure 7, and then the clothes material identification result is returned to the washing machine;
4. if the washing is determined, washing according to an automatically set washing scheme and uploading the data to a database of a data analysis platform; if the real material type of the clothes to be washed is found not to be consistent with the recognized material type, the real material type of the clothes to be washed can be manually input on the display screen. And re-determining a new washing scheme aiming at the real material type, washing the clothes to be washed according to the new washing scheme, and uploading the related data after the material type of the clothes is changed to a database of a data analysis platform for optimizing and adjusting the clothes material recognition neural network model.
For example, if the type of the clothes returned by the server is wool, the MCU of the washing machine will also perform washing according to a washing scheme corresponding to the wool, for example, for wool, the washing machine will automatically execute a washing program according to a gentle washing scheme. However, the server may have a phenomenon of wrong recognition, for example, recognizing dacron into acrylic, and at this time, manual intervention is required, for example, manually modifying the clothes material recognition result received by the washing machine, correcting the result, returning the result to the cloud server, and the cloud server may record correct and wrong results at the same time, and then perform optimization adjustment on the built-in clothes material recognition neural network model to improve the accuracy.
5. And the data stored in the database is used regularly to automatically retrain the clothes material recognition neural network model so as to achieve the aim of optimizing and perfecting the model.
The embodiment can solve the following technical problems:
1. the spectral analysis method applied to the washing machine collects clothes spectral data through the near infrared spectrum collecting sensor, and can avoid error identification when the image identification method identifies clothes of the same material and different colors.
2. The washing machine is provided with the light source for the near infrared spectrum acquisition sensor, so that the interference of external light rays can be avoided.
3. The near infrared spectrum acquisition sensor has low cost and does not need to be well labeled.
According to the technical scheme, the infrared spectrum data of the clothes to be washed can be automatically acquired, and the infrared spectrum data of the clothes to be washed are analyzed by utilizing a deep learning algorithm, so that the material type of the clothes to be washed is determined. And then, a washing scheme for the clothes to be washed is determined based on the determined type of the clothes material, so that automatic and reasonable washing is realized according to the material of the clothes to be washed. The material type and the washing scheme of the clothes to be washed do not need to be manually set by a user, so that the automatic washing of the clothes to be washed is really realized, and more precious time and energy are saved for the user.
EXAMPLE six
The present embodiment provides a laundry control system, including: a washing machine as described above and a server as described above. Fig. 6 is a schematic view of an overall structure of a system for washing laundry according to an embodiment of the present application.
EXAMPLE seven
The present embodiment provides a storage medium storing a computer program which, when executed by a processor, implements the steps of the laundry material identification method as described above or the steps of the laundry washing pattern determination method as described above.
Storage media, including permanent and non-permanent, removable and non-removable media, may implement the information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
It is noted that the terms used herein are merely for describing particular embodiments and are not intended to limit exemplary embodiments according to the present application, and when the terms "include" and/or "comprise" are used in this specification, they specify the presence of features, steps, operations, devices, components, and/or combinations thereof.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein.
It should be understood that the exemplary embodiments herein may be embodied in many different forms and should not be construed as limited to only the embodiments set forth herein. These embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of these exemplary embodiments to those skilled in the art, and should not be construed as limiting the present invention.
Claims (20)
1. A clothes material identification method is characterized by comprising the following steps:
acquiring infrared spectrum data of clothes to be washed;
and analyzing the infrared spectrum data of the clothes to be washed by utilizing the trained clothes material recognition neural network model, and determining the clothes material type of the clothes to be washed according to the analysis result.
2. The method for recognizing the texture of clothes according to claim 1, wherein the analyzing infrared spectrum data of the clothes to be washed by using the trained clothes texture recognition neural network model, and determining the texture type of the clothes to be washed according to the analysis result comprises:
extracting the characteristics and numerical values of the infrared spectrum data of the clothes to be washed;
and matching the characteristics of the infrared spectrum data of the clothes to be washed with the corresponding characteristics of the infrared spectrum data of the preset clothes material type, and determining the clothes material type of the clothes to be washed according to the matching result.
3. The clothing material identification method according to claim 2, wherein the step of matching the characteristics of the infrared spectrum data of the clothing to be washed with the corresponding characteristics of the infrared spectrum data of the preset clothing material type and determining the clothing material type of the clothing to be washed according to the matching result comprises the steps of:
acquiring weights of corresponding characteristics of the infrared spectrum data of the preset clothes material type, which correspond to the characteristics of the infrared spectrum data of the clothes to be washed one by one, aiming at the infrared spectrum data of each preset clothes material type, weighting and summing numerical values of the characteristics of the infrared spectrum data of the clothes to be washed according to the weights, and taking the summed value as the matching degree of the clothes material type of the clothes to be washed and the preset clothes material type;
and selecting the preset clothes material type corresponding to the maximum matching degree from the matching degrees of the clothes material type of the clothes to be washed and each preset clothes material type as the clothes material type of the clothes to be washed.
4. The method for recognizing the texture of clothes according to claim 1, wherein the neural network model for recognizing the texture of clothes is constructed by the following steps:
acquiring a plurality of data samples for training a clothing material recognition neural network model, wherein each data sample comprises a clothing material type and infrared spectrum data of the clothing material type;
and training the clothes material recognition neural network model by using the plurality of data samples to obtain the trained clothes material recognition neural network model.
5. The method of claim 1, wherein before analyzing the infrared spectrum data of the laundry using the trained neural network model for recognizing the texture of the laundry, the method further comprises:
the method comprises the following steps of preprocessing infrared spectrum data of clothes to be washed, wherein the preprocessing comprises data standardization processing, high-frequency noise filtering processing, differential derivation of signals and baseline correction processing, and the data standardization processing comprises mean value centralization processing, normalization processing and standard normal transformation processing.
6. The method for recognizing the texture of clothing according to claim 1, further comprising:
sending inquiry information whether the determined clothes material type of the clothes to be washed is correct or not;
and when the inquiry result is that the determined clothes material type of the clothes to be washed is wrong, acquiring the corrected clothes material type of the clothes to be washed.
7. The method for recognizing the texture of clothing according to claim 1, further comprising:
and storing the infrared spectrum data of the clothes to be washed and the material type of the clothes in a correlation manner, so as to optimize and adjust the trained clothes material recognition neural network model.
8. The method as claimed in claim 1, wherein the infrared spectrum data comprises at least one of the following: near infrared spectral data and hyperspectral data.
9. The method of claim 1, wherein the clothing material recognition neural network model is a deep learning neural network model.
10. A laundry washing course determining method, comprising the steps of:
determining a laundry material type of laundry using the laundry material identification method according to any one of claims 1 to 9;
acquiring image data of clothes to be washed;
determining the color and weave of the clothes to be washed according to the image data of the clothes to be washed by utilizing the trained image recognition neural network model;
and determining a washing scheme aiming at the clothes to be washed based on the preset corresponding relation between the clothes material type, the preset color and the preset weave and the washing scheme according to the clothes material type, the preset color and the preset weave of the clothes to be washed.
11. The laundry washing program determining method according to claim 10, wherein the image recognition neural network model is constructed by:
obtaining a plurality of sample data sets for training an image recognition neural network model, wherein each sample data set comprises a plurality of sample subsets corresponding to a type of clothing material, and each sample subset comprises different colors corresponding to a cloth weave;
and training the image recognition neural network model by using the plurality of sample data sets to obtain the trained image recognition neural network model.
12. A washing machine, characterized by comprising:
the infrared spectrum sensor is used for acquiring infrared spectrum data of the clothes to be washed;
the camera device is used for acquiring image data of the clothes to be washed;
communication means for transmitting infrared spectrum data of the laundry to be washed acquired by the infrared spectrum sensor and image data of the laundry to be washed acquired by the image pickup means to a server so that the server determines a washing course for the laundry to be washed using the laundry washing course determining method according to claim 10 or 11, the communication means being further configured to receive the washing course for the laundry to be washed returned by the server;
the washing device is used for washing the clothes to be washed;
the washing device comprises a controller and a memory, wherein program codes are stored in the memory, and when the program codes are executed by the controller, the controller controls the washing device to wash clothes to be washed according to a washing scheme which is received by the communication device and aims at the clothes to be washed.
13. The washing machine as claimed in claim 12, wherein the communication device is further configured to receive a laundry material type of the laundry returned from the server;
the washing machine further includes: and the display device is used for displaying the clothes material type of the clothes to be washed, which is received by the communication device and returned by the server.
14. A washing machine as claimed in claim 13 wherein the communication means is further adapted to: receiving the clothes material type after the clothes material type of the clothes to be washed returned by the server is corrected;
sending the corrected clothes material type to a server so that the server determines a new washing scheme aiming at the clothes to be washed according to the corrected clothes material type;
receiving a new washing scheme for the clothes to be washed returned by the server;
the controller is further used for controlling the washing device to wash the clothes to be washed according to the new washing scheme received by the communication device when the communication device receives the corrected clothes material type.
15. Laundry washing machine according to claim 12, characterized in that the infrared spectrum sensor comprises a near infrared spectrum sensor and/or a hyperspectral sensor.
16. A washing machine as claimed in claim 12 wherein the infrared spectroscopy sensor comprises illumination means for illuminating the laundry.
17. A server, characterized by comprising a processor and a memory, said memory having stored therein program code which, when executed by said processor, carries out the steps of the laundry material identification method according to any one of claims 1 to 9 or the steps of the laundry washing program determination method according to claim 10 or 11.
18. The server of claim 17, wherein the server is a local server or a cloud server.
19. A laundry washing control system, comprising: washing machine according to any of claims 12 to 16 and server according to any of claims 17 to 18.
20. A storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the steps of the laundry material identification method according to any one of claims 1 to 9 or the steps of the laundry washing program determination method according to claim 10 or 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110018227.9A CN112831976A (en) | 2021-01-07 | 2021-01-07 | Clothes material identification and washing scheme determination method, washing machine and server |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110018227.9A CN112831976A (en) | 2021-01-07 | 2021-01-07 | Clothes material identification and washing scheme determination method, washing machine and server |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112831976A true CN112831976A (en) | 2021-05-25 |
Family
ID=75927969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110018227.9A Pending CN112831976A (en) | 2021-01-07 | 2021-01-07 | Clothes material identification and washing scheme determination method, washing machine and server |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112831976A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114084085A (en) * | 2021-11-22 | 2022-02-25 | 奇瑞汽车股份有限公司 | Vehicle door mistaken clamping reminding system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106192289A (en) * | 2015-04-30 | 2016-12-07 | 青岛海尔洗衣机有限公司 | Control method for washing machine and washing machine |
| CN106637812A (en) * | 2017-01-22 | 2017-05-10 | 无锡小天鹅股份有限公司 | Washing machine control method and device, washing machine |
| CN106917223A (en) * | 2015-12-25 | 2017-07-04 | 青岛海尔滚筒洗衣机有限公司 | A kind of clothes washing control method, washing machine and system |
| US20200042822A1 (en) * | 2019-08-21 | 2020-02-06 | Lg Electronics Inc. | Fabric identifying method, apparatus, and system |
| CN111797930A (en) * | 2020-07-07 | 2020-10-20 | 四川长虹电器股份有限公司 | Fabric material near infrared spectrum identification and identification method based on twin network |
-
2021
- 2021-01-07 CN CN202110018227.9A patent/CN112831976A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106192289A (en) * | 2015-04-30 | 2016-12-07 | 青岛海尔洗衣机有限公司 | Control method for washing machine and washing machine |
| CN106917223A (en) * | 2015-12-25 | 2017-07-04 | 青岛海尔滚筒洗衣机有限公司 | A kind of clothes washing control method, washing machine and system |
| CN106637812A (en) * | 2017-01-22 | 2017-05-10 | 无锡小天鹅股份有限公司 | Washing machine control method and device, washing machine |
| US20200042822A1 (en) * | 2019-08-21 | 2020-02-06 | Lg Electronics Inc. | Fabric identifying method, apparatus, and system |
| CN111797930A (en) * | 2020-07-07 | 2020-10-20 | 四川长虹电器股份有限公司 | Fabric material near infrared spectrum identification and identification method based on twin network |
Non-Patent Citations (1)
| Title |
|---|
| 唐子惠: "《医学人工智能导论》", 上海世纪出版（集团）有限公司、上海科学技术出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114084085A (en) * | 2021-11-22 | 2022-02-25 | 奇瑞汽车股份有限公司 | Vehicle door mistaken clamping reminding system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6791972B2 (en) | Methods and Devices for Detecting Interferents in Samples | |
| JP6879366B2 (en) | Methods, devices and quality check modules for detecting hemolysis, jaundice, lipemia, or normality of a sample | |
| WO2017067023A1 (en) | Method for detecting body fluid based on special test paper | |
| CN110717368A (en) | Qualitative classification method for textiles | |
| JP2018511787A (en) | Model-based method and apparatus for classifying interfering factors in a sample | |
| US11120311B2 (en) | Adjusting machine settings through multi-pass training of object detection models | |
| CN107974799A (en) | A kind of method and washing machine of intelligent recognition washing clothing | |
| JP7078175B2 (en) | Inspection equipment and method | |
| CN110647894A (en) | Fault diagnosis method and system of electrical equipment, cloud server and storage medium | |
| CN112831976A (en) | Clothes material identification and washing scheme determination method, washing machine and server | |
| CN117152152B (en) | Production management system and method for detection kit | |
| CN116559111A (en) | Sorghum variety identification method based on hyperspectral imaging technology | |
| CN215163866U (en) | Washing machine | |
| KR20130086690A (en) | System for performing colorimetric analysis when running in a portable device and method of colorimetric analysis using the same | |
| CN109492701A (en) | A kind of congou tea withers appropriateness method of discrimination and system | |
| CN116481585B (en) | Product full detection system and method based on machine vision | |
| Portalés et al. | An image-based system to preliminary assess the quality of grape harvest batches on arrival at the winery | |
| CN113887543B (en) | Luggage counterfeit discrimination method based on hyperspectral characteristics and spectrum acquisition device | |
| CN113435444B (en) | Immunochromatography detection method, immunochromatography detection device, storage medium and computer equipment | |
| CN113533372B (en) | Paper defect detection method, system, device and computer storage medium | |
| CN113850762A (en) | Eye disease identification method, device, equipment and storage medium based on anterior segment image | |
| CN212846839U (en) | Fabric information matching system | |
| CN114667452A (en) | Method for determining the concentration of an analyte in a body fluid | |
| CN117309892B (en) | Defect detection method, device and system for blue film of battery and light source controller | |
| CN117523013B (en) | Color change characteristic analysis method and system for high-moisture-conductivity fabric |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |