阅读说明：本技术 个性化的洗熨设备 (Personalized laundry and ironing device ) 是由 陈昕 周华 高煜翔 朱欤 于 2018-11-14 设计创作，主要内容包括：洗熨设备使用机器学习模型和/或个性化设置以提供更好的处理。作为一个示例,洗熨设备具有在其中放置要处理的洗熨物品的腔室。传感器定位成感测腔室中的物品或当洗熨物品被装载到腔室中时感测该洗熨物品。机器学习模型使用来自这些传感器的数据来确定洗熨物品和/或其处理的各种属性,例如织物类型和/或物品的脏污程度,以及对处理过程进行相应控制。诸如个人对于物品处理的偏好或个人的敏感性和过敏史之类的个性化数据也可以用于个性化处理过程。(Laundry ironing devices use machine learning models and/or personalisation to provide better treatment. As one example, laundry ironing apparatuses have a chamber in which laundry items to be treated are placed. The sensor is positioned to sense an article in the chamber or to sense an laundry article when loaded into the chamber. The machine learning model uses data from these sensors to determine various attributes of the laundry article and/or its treatment, such as fabric type and/or degree of soiling of the article, and to control the treatment process accordingly. Personalized data such as an individual's preferences for item handling or an individual's sensitivity and allergy history may also be used to personalize the process.)

1. A system for generating settings for an laundry appliance that processes a load of laundry items, the system comprising:

a sensor group associated with the laundry apparatus, the sensor group including one or more sensors that capture sensor data of one or more laundry items in the load;

a machine learning model that receives the sensor data and determines a treatment attribute related to treatment of the load by the laundry appliance based on the sensor data; and

a controller to generate settings of the laundry appliance based on the treatment attributes determined by the machine learning model, and to control the laundry appliance to treat the load in accordance with the generated settings.

2. The system of claim 1, wherein the machine learning model further receives personalization data of one or more individuals associated with the laundry article, and determines the treatment attribute further based on the personalization data.

3. The system of claim 1, wherein the machine learning model further receives historical data associated with the laundry device and/or the laundry items, and determines the treatment attribute further based on the historical data.

4. The system of claim 1, wherein the sensor set includes a tactile surface sensor that senses a surface of one or more laundry articles by contact with the laundry articles, the machine learning model determining the treatment attribute based on the surface.

5. The system of claim 1, wherein the sensor set includes a camera that captures images of one or more laundry items, the machine learning model determining the treatment attribute based on the captured images.

6. The system of claim 1, wherein the processing attribute determined by the machine learning model comprises one of: fabric type, size of the laundry article, size of the load, and degree of soiling of the load.

7. The system of claim 1, wherein the machine learning model identifies one of the laundry items based on the sensor data, the controller generating the settings based on the identified laundry item.

8. The system of claim 7, wherein the settings of the laundry device are generated based in part on at least one of: instructions for processing the identified laundry article and prior processing of the identified laundry article by the laundry apparatus.

9. The system according to claim 7, wherein the settings of the laundry device are generated based in part on personalized preferences for processing the identified laundry items.

10. The system of claim 1, wherein the machine learning model is implemented remotely from the laundry device.

11. The system according to claim 1, wherein the controller further obtains personalization data of one or more individuals associated with the laundry article and generates settings of the laundry apparatus based on the personalization data.

12. The system of claim 11, wherein the individual associated with the laundry article is a user of the laundry article, the personalization data comprising one of: sensitivity or allergy history of the user, medical condition of the user, or laundry treatment preference of the user.

13. The system according to claim 11, wherein the personalization data is obtained from a profile of the individual accessible to the laundry device.

14. The system of claim 11, wherein the personalization data is obtained from a smartphone or other personal computing device operated by the individual.

15. The system of claim 11, wherein the personalization data is obtained from a third-party website.

16. The system according to claim 1, wherein the controller includes a second machine learning model that generates settings of the laundry ironing device.

17. The system according to claim 1, wherein the controller further obtains data from another laundry device that has previously processed the laundry items, and generates the settings further based on the data from the other laundry device.

18. The system of claim 1, wherein the treatment attributes are personalized for an individual associated with the laundry article.

19. The system of claim 1, wherein the settings are personalized for an individual associated with the laundry article.

20. A method for generating settings for an laundry appliance that processes a load of laundry articles, the method comprising:

capturing sensor data of one or more laundry items in the load by a sensor group associated with the laundry apparatus, the sensor group including one or more sensors;

receiving, by a machine learning model, the sensor data and determining, based on the sensor data, a treatment attribute related to treatment of the load by the laundry appliance;

generating, by a controller, settings of the laundry ironing device based on the treatment attributes determined by the machine learning model; and

controlling, by the controller, the laundry appliance to process the load according to the generated settings.

21. The method of claim 20, further comprising:

receiving, by the machine learning model, personalization data for one or more individuals associated with the laundry article; and

determining, by the machine learning model, the processing attribute based on the personalization data.

22. The method of claim 20, further comprising:

receiving, by the machine learning model, historical data associated with the laundry device and/or the laundry article; and

determining, by the machine learning model, the processing attribute based on the historical data.

23. The method of claim 20, further comprising:

the tactile surface sensor of the sensor set senses a surface of one or more laundry items by contact with the laundry items; and

determining, by the machine learning model, the treatment attribute from the surface.

24. The method of claim 20, wherein the set of sensors comprises a camera, and the method further comprises:

capturing, by the camera, images of one or more laundry items; and

determining, by the machine learning model, the processing attribute based on the captured image.

25. The method of claim 20, wherein the processing attribute determined by the machine learning model comprises one of: fabric type, size of the laundry article, size of the load, and degree of soiling of the load.

26. The method of claim 20, further comprising:

identifying, by the machine learning model, one of the laundry items based on the sensor data; and

generating, by the controller, the setting based on the identified laundry article.

27. The method according to claim 26, wherein the settings of the laundry device are generated based in part on at least one of: instructions for processing the identified laundry article and prior processing of the identified laundry article by the laundry apparatus.

28. The method according to claim 26, wherein the settings of the laundry apparatus are generated based in part on personalized preferences for processing the identified laundry items.

29. The method according to claim 20, wherein the machine learning model is implemented remotely from the laundry device.

30. The method of claim 20, further comprising:

obtaining, by the controller, personalization data for one or more individuals associated with the laundry article; and

generating settings of the laundry device based on the personalization data.

31. The method according to claim 30, wherein the individual associated with the laundry article is a user of the laundry article, the personalization data comprising one of: sensitivity or allergy history of the user, medical condition of the user, or laundry treatment preference of the user.

32. The method of claim 30, further comprising:

the personalization data is obtained from a profile of the individual to which the laundry device has access.

33. The method of claim 30, further comprising:

the personalization data is obtained from the personal operated smartphone or other personal computing device.

34. The method of claim 30, further comprising:

obtaining the personalization data from a third-party website.

35. The method according to claim 20, wherein the controller includes a second machine learning model that generates settings of the laundry ironing device.

36. The method of claim 20, further comprising:

obtaining, by the controller, data from another laundry device that has previously processed the laundry article; and

generating the setting based on data from the other laundry device.

37. The method according to claim 20, wherein the treatment attributes are personalized for an individual associated with the laundry article.

38. The method according to claim 20, wherein the settings are personalized for an individual associated with the laundry article.

39. An electronic device, comprising:

a processor;

a memory for storing instructions executable by the processor; and

the instructions, when executed by the processor, cause the processor to perform the method of any of claims 20-38.

40. A computer program comprising instructions for carrying out the method of providing a message to a user according to any one of claims 20-38, when said program is executed by a computer.

41. A computer readable medium readable by a computer, having a computer program recorded thereon, the computer program comprising instructions for performing the method of providing a message to a user according to any of claims 20-38.

Technical Field

The present disclosure relates generally to control of laundry and ironing apparatuses, such as washing machines and dryers.

Background

Washing machines and other types of laundry ironing apparatuses are designed to handle a variety of different types of articles under a variety of different conditions. Some items are very bulky, such as carpets, towels, and bedding. Other articles are small or delicate, such as older ancestral articles, silk, or lace. The type of fabric also affects the preferred settings of the laundry and ironing device. Thicker cotton articles may take a longer time to dry than nylon or other synthetic fibers. Some fabrics shrink more easily. Whether the laundry appliance is handling a full load or a partial load, how dirty the load is, affects the optimal settings.

The responsibility for selecting the optimum setting of the washing machine or dryer usually lies on the operator. This can be very tricky for an inexperienced operator and leads to poor results. In addition, prior art laundry ironing apparatuses typically have many settings that a casual operator may not know or how to use to maximize their benefits.

Thus, there is a need for a more intelligent laundry ironing device and a laundry ironing device allowing more personalized settings.

Disclosure of Invention

The present disclosure provides laundry ironing devices that use machine learning models to provide better automation and/or allow for greater personalization. As one example, laundry ironing apparatuses have a chamber in which laundry items to be treated are placed. The sensor (e.g., touch sensor, spectral sensor, etc.) is positioned to obtain information about the laundry article, for example, by sensing the article inside or within the chamber or by sensing the laundry article as it is loaded into the chamber. From this information, the machine learning model determines various attributes of the laundry article and/or treatment, such as the type of fabric or the degree of soiling of the laundry, and controls the treatment process accordingly. The machine learning model may be located in the laundry device or may be accessible over a network.

In another aspect, the laundering process is controlled based on user input, personal user preferences or other personalization data, for example, provided by or accessed from a personal smartphone. The laundry process may also be controlled based on temperature sensing and other sensor data, user usage history, historical performance data, and other factors.

Other aspects include components, devices, systems, improvements, methods, processes, applications, computer-readable media, and other technologies relating to any of the above aspects.

Drawings

Other advantages and features of embodiments of the present disclosure will become apparent from the following detailed description and the appended claims, taken in conjunction with the accompanying drawings, by way of example, in which:

fig. 1 is a sectional side view of a washing machine according to an embodiment.

Fig. 2A is a block diagram illustrating controlling a washing machine according to an embodiment.

Fig. 2B-2E provide some specific examples of controlling a washing machine according to embodiments.

Fig. 3 is a flow diagram illustrating the training and operation of a machine learning model according to an embodiment.

Fig. 4 is a block diagram of a residential environment including a laundry device according to an embodiment.

Detailed Description

The drawings and the following description relate to preferred embodiments by way of illustration only. It should be noted that from the following discussion, alternative embodiments of the structures and methods disclosed herein will be readily recognized as viable alternatives that may be employed without departing from the principles claimed.

Fig. 1 is a sectional side view of a washing machine 100 according to an embodiment. The washing machine 100 includes a washing chamber 110 having a door 120. In this example, the washing machine is open-top, although it may be open-front. A load of laundry articles 150 is placed in the chamber 110 for washing. Laundry articles may include clothing, bedding, carpets, towels, and the like. Other items may be present in the chamber, such as a drying rack in the case of the agitator or dryer shown in FIG. 1. The dimensions of the washing machine and the washing chamber 110 may vary: apartment, compact, regular size, home size, ultra large, commercial, industrial, etc. The magnitude of the load may also vary. The washing machine may be operated at full or partial load. In fig. 1, a state is shown in which the lid 120 of the laundry machine 100 is open when laundry articles 150 are loaded into the washing chamber 110.

The washing machine 100 includes a set of one or more sensors 130 for sensing a load. In this example, a spectral sensor 130A is located in the cover 120 that captures spectral information about the laundry items as they are loaded into the chamber. The field of view of the sensor is shown by the dashed line. The spectroscopic sensor and camera may also be placed in other locations suitable for capturing images of laundry items during loading.

The sensor set also includes a tactile surface sensor 130B. The tactile surface sensor senses the surface of the laundry article by contact with the laundry article. As one example, a tactile surface sensor records an impression (impression) of an item in contact with it. It has good resolution, typically on the order of microns, so that fine textures of the fabric can be resolved. In one method, a camera captures an image of the impression, which is then processed to determine the fabric type. In fig. 1, the tactile surface sensor 130B is located on the front flange (lip) of the washing machine. When laundry article 150D is loaded into the washing machine, it comes into contact with sensor 130B and is sensed by sensor 130B. An instruction may be given to the operator to load the laundry machine in such a way that the laundry article 150 is in contact with the tactile surface sensor 130B. For example, the operator may be instructed to press the laundry article against the tactile surface sensor 130B for proper operation.

The sensor suite includes cameras 130C, 130D positioned to acquire images of laundry items in the chamber 110. These cameras 130 may be used before washing begins (e.g., during loading). They may also be used during the washing process or at a specific stage of the washing process.

In this example, the camera 130 is not directly exposed to the wash environment in the chamber. The cover 110 includes a window and the spectral sensor 130A is located behind the window. If the cover 110 is transparent, it may be double-layered with the spectral sensor 130A located between the two panes of the window. Cameras 130C, 130D are also located behind the windows. The top camera 130C may be in a position that is not exposed to water, detergent, etc. In this manner, the camera 130 is isolated from the wash environment, thereby reducing possible damage.

If the cover 110 is transparent, the cover 110 may include an optical coating to reduce ambient light entering the wash chamber, thereby enabling the camera to capture a better quality image. The optical coating acts like a single mirror, preventing ambient light from entering the chamber while still allowing the operator to see into the chamber. The washing chamber may also include special illumination to provide internally controlled illumination for the camera. The camera may be color, monochrome, infrared, etc. They may have different resolutions depending on the task to be accomplished. For example, a camera used to identify a single garment has a higher resolution than a camera used only to sense whether the load is primarily colored or white.

The sensor group may include other types of sensors. Examples include temperature sensors, weight or volume sensors, pressure sensors, non-imaging optical or spectral sensors, water level sensors, pH sensors, and the like. These sensors may be directly exposed to the wash environment, directly sense the wash environment without being exposed thereto, or indirectly sense the wash environment.

For example, the water level sensor 130E may be a linear array of devices that are sensitive to submersion. The water level can be determined by observing which sensors are flooded and which sensors are not. A similar method may be used to sense volume. The level of laundry items in the chamber can be determined by observing which sensors in the linear array are covered by the laundry items. A pH sensor is another example of a device that may be directly exposed to a wash environment. Cameras and other optical sensors are examples of sensors that typically sense the wash environment directly, but are not exposed to the wash environment. Non-imaging optical sensors may be used to sense color. Certain types of temperature sensors may also fall under this category. For example, the weight of the total load may be sensed indirectly by a pressure sensor responsive to the total weight of the chamber, or by measuring the torque required to rotate the load and chamber at a rotational speed. In fig. 1, sensor 130G measures the torque produced by the bottom motor.

The sensor 130 need not be incorporated as part of the washing machine. For example, they may be implemented as an accessory for a washing machine. If the goal is to use more complex sensing to identify individual laundry items, a separate accessory with a combination of tactile surface sensors, cameras and other sensors in a controllable arrangement may be useful. As another example, the sensor 130 in the washing machine 100 may capture sensor data, which is then provided to the dryer for subsequent drying of the same laundry items. In such a scenario, some of the sensor data used by the dryer is not from the dryer's own sensors.

Fig. 2A is a block diagram illustrating control of an laundry appliance, such as the laundry machine 100. The control system 210 is generally divided into a machine learning model 220 and a controller 230. The controller 230 may (or may not) also include machine learning 232. The machine learning model 220 receives sensor data 250 captured by some or all of the sensors 130. From these inputs (which may be combined with other additional inputs such as personalization data 255 or historical data 257), the machine learning model 220 determines various attributes 260 related to the laundry ironing device processing load. The controller 230 generates settings 270 for the laundry appliance based on the process attributes 260 from the machine learning model 220.

Personalized settings 270 for an individual may also be generated taking into account the personalized data 255 and historical data 257 of one or more individuals associated with the laundry article. For example, some people may prefer softening, others may prefer faster or more efficient washing, and others may prefer automatic wrinkle removal or steaming. These personalized preferences may be provided directly by the individual, for example stored in an individual profile, or provided by the individual through a smartphone or other device. These personalized preferences may also be learned over time based on historical settings or the individual's feedback on previous processing results.

The individual is identified to determine how to personalize the process. An individual may be identified when the individual logs into the user account of his laundry device or a user account of a home network connected to the laundry device. Alternatively, the individual may be identified by facial recognition or other techniques.

The settings 270 may also be generated by the controller 230 directly using the sensor data 250. The controller 230 controls the laundry appliance to process the load according to the settings 270.

In general, machine learning model 220 is used for more complex relationships between sensor data 250, possible personalization data 255, and process attributes 260. One example is when the sensor data 250 is a captured image, the machine learning model 220 may be used to predict a fabric type, a fabric weight, a type of laundry item, a size of laundry item, a degree of soiling of laundry item, a color mix of a load, and/or identify a particular laundry item from the captured image. These are well suited to machine learning issues and are difficult to accomplish using more traditional techniques. Table I lists some examples of processing attributes. These may be attributes of individual laundry articles, or of the overall load.

Examples of Table I processing attributes

The machine learning model 220 may also use other data as inputs to predict these processing attributes. Surface information from the surface sensors, as well as more conventional sensor data such as color or weight, may be used as additional inputs to the machine learning model 220. Data from sources other than the sensor suite 130 may also be used as input to the machine learning model. Examples include the personalization data described below.

The controller 230 determines settings 270 of the laundry ironing device based on the processing properties and optionally also based on other data, such as personalization data 255 or historical data 257. The personalized data is data of one or more individuals associated with the laundry article. Typically, the individual is a user of the laundry article (e.g., a wearer of clothing) or an operator who uses the laundry apparatus to treat the laundry article. If the laundry article is a garment and the individual is a wearer of the garment, the personalized data may include a sensitivity or allergy history of the wearer, a medical condition of the wearer, or a treatment preference of the wearer for his or her garment, e.g., some people may prefer softening. In this way, laundry article treatment may be personalized to an individual. This information may be obtained from a user profile accessible to the laundry device. It may also be obtained from other sources such as third party websites.

Examples of historical data 257 include the past operating history of the appliance and the treatment history of each laundry item. For example, the washing machine may always be operated in a water saving mode, or a hot wash cycle is always performed for white and a warm wash cycle is always performed for color. Certain laundry articles may require special treatment, which may be determined from their previous treatment.

In any event, the controller 230 determines the appropriate settings 270 for the laundry apparatus. Examples of settings 270 include: temperature of the treatment performed by the laundry ironing device, duration of the treatment, load level of the treatment, mildness of the treatment, economic settings for the treatment, rotational speed of the treatment, amount of detergent used for the treatment and amount of water used for the treatment.

Laundry ironing devices can generally be operated in different treatment modes, which are generally referred to as different washing cycles or different drying cycles. The controller 230 may select an appropriate treatment mode based on the treatment attributes determined by the machine learning model. As another example, the process itself may have different stages. The controller 230 may select when to transition between the different phases based on the personalization data and the processing attributes determined by the machine learning model.

Some examples of different settings of the washing machine are listed below in table II.

TABLE II washing machine arrangement

Table III below lists some examples of different settings of the dryer.

TABLE III dryer set-up

Fig. 2B-2E provide some specific examples. Each of these examples enumerates the types of input data 250 used, including sensor data 252, personalization data 255, and historical data 257. These data are converted into attributes 260, possibly for individual laundry items 262 or for the overall load 265. The resulting settings 270 are also shown.

In fig. 2B, the surface sensors cooperate with a machine learning model to determine that most laundry items are cotton fabrics. The camera or spectral sensor detects that the load is mostly dark. The optical sensor determines that the wash chamber is only partially filled. Personal data 255 or historical data 257 is not used. Thus, the controller generates settings for a partial load of a dark cotton fabric article. A standard wash cycle is used with warm wash and rinse temperatures and high dehydration rates. Moderate levels of detergent and water were used, with no special options.

Fig. 2C is similar to fig. 2B except that the load is primarily light in color rather than dark. In addition, the machine learning model also detects stains on one of the items, which may be wine, grape juice, tomato paste, or blood. Thus, the wash cycle uses high temperatures, pre-soaks the load before the start of the conventional wash cycle, and turns on the stain treatment option.

In fig. 2D, the machine learning model detects the towel load from the captured image. Surface sensors indicate that these are heavy towels. Thus, the washing machine is set to a towel washing cycle. In addition, fabric softeners have been commonly used in the past to wash heavier towels, and therefore the fabric softener option has also been automatically selected.

In fig. 2E, a beach towel in which one towel is identified as dad, may be identified based on a unique color or pattern on the towel. However, dad was allergic to fabric softener and therefore did not select the fabric softener option. In this example, the machine learning model identifies a particular laundry item. In this case, the processing instructions for that particular item may be used to generate the settings. For example, the appropriate settings may be determined with reference to the manufacturer's instructions. Alternatively, the individual may provide specific instructions for important laundry items, either explicitly or implicitly, based on previous treatments of the laundry item or similar laundry items.

Fig. 3 is a flow diagram illustrating the training and operation of machine learning model 220 according to an embodiment. The process comprises two main stages: the machine learning model 220 and the reasoning (operation) of the machine learning model 220 are trained (310) (320). They will be described using an example in which a machine learning model learns the predicted fabric type from captured images.

A training module (not shown) performs training of the machine learning model 220 (310). In some embodiments, the machine learning model 220 is defined by an architecture with a certain number of layers and nodes, with bias and weighted connections (parameters) between nodes. During training (310), the training module determines parameter values (e.g., weights and biases) for the machine learning model 220 based on a set of training samples.

The training module receives (311) a training set for training. The training samples in the training set include images captured by the camera 130 for many different situations: different laundry items and fabric types, different colors and variations of the same fabric type, different load levels, different positions of laundry items in the chamber, different lighting conditions, etc. For supervised learning, the training set typically also includes labels for the images. The label includes the processing attributes to be trained: in this example of the fabric type.

In typical training 312, training samples are taken as inputs to machine learning model 220, and machine learning model 220 then produces outputs for particular process attributes. The training module uses the difference between the output of the machine learning model and the known good output to adjust the parameter values in the machine learning model 220. This operation is repeated for many different training samples to improve the performance of the machine learning model 220.

The training module also typically verifies (313) the trained machine learning model 220 based on additional verification samples. For example, the training module applies the machine learning model 220 to a set of validation samples to quantify the accuracy of the machine learning model 220. The set of verification samples includes the image and its known attributes. The output of the machine learning model 220 may be compared to known ground truth values. Common indicators applied in accuracy measurements include: precision (Precision) TP/(TP + FP), and Recall (Recall) TP/(TP + FN), where TP (true positive) is the number of true positive cases, FP (false positive) is the number of false positive cases, and FN (false negative) is the number of false negative cases. The precision is the proportion of the output (TP) correctly predicted to have the target property among the total output (TP + FP) predicted to have the target property by the machine learning model 220. The recall is the proportion of the total number of verification samples (TP + FN) that do have the target attribute that the machine learning model 220 correctly predicts as output (TP) having the target attribute. The F-score (F-score 2 precision recall/(precision + recall)) fuses "precision" and "recall" into one metric. Common indicators used in accuracy measurements also include Top-1 accuracy and Top-5 accuracy. With Top-1 accuracy, the trained model is accurate when the Top-1 prediction predicted by the trained model (i.e., the prediction with the highest probability) is correct. With Top-5 accuracy, the trained model is accurate when one of the Top-5 predictions (e.g., the five with the highest probability) is correct.

The training module may use other types of metrics to quantify the accuracy of the trained model. In one embodiment, the training module trains the machine learning model until a stopping condition occurs, such as a sufficiently accurate accuracy measurement of the model indicates or the number of training rounds that have been performed.

The training (310) of the machine learning model 220 may be performed offline as part of the product development of the laundry device. The trained model 220 is then installed on the laundry device sold to the consumer. The laundry device may execute the machine learning model using fewer computational resources than are required for training. In some cases, the machine learning model 220 is continuously trained (310) or updated. For example, the training module uses images captured by the camera 130 while actually washing to further train the machine learning model 220. Because the training (310) is computationally intensive, it may be cloud-based or on a separate home device with more computing power. Updates of the machine learning model 220 are distributed to the laundry devices.

In operation 320, the machine learning model 220 uses the image (321) captured by the camera 130 as an input (322) to the machine learning model 220. In one architecture, the machine learning model 220 calculates (323) probabilities of different possible outcomes, such as a probability that the fabric type is cotton, a probability that the fabric type is cotton blend, a probability that the fabric type is polyester, and so on. Based on the calculated probabilities, machine learning model 220 identifies (323) the most likely attributes. For example, the machine learning model 220 may identify that cotton is the most likely fabric type. Without an apparent winner, the machine learning model 220 may identify multiple attributes and require the user to verify. For example, it may report that both cotton and cotton blends are possible, and then the user confirms that the laundry item is cotton. The controller 230 then controls (324) the laundry ironing device based on the identified attribute.

In another aspect, the laundry device may be part of a home network. Fig. 4 is a block diagram of a residential environment including a laundry device according to an embodiment. The residential environment 400 is an environment designed for human occupancy. The residential environment 400 may be a residence, such as a house, apartment, private apartment, or dormitory. The residential environment 400 includes home appliances 410A-N, including laundry devices as described above. The residential environment 400 also includes a home device network 420 connecting home devices 410, and a household profile database 430 containing household preferences for home devices. The components in fig. 4 are shown as separate blocks, but they may be combined according to embodiments. For example, the household profile 430 may be part of the home device 410. Further, the residential environment 400 may include a hub for the network 420. The hub may also control the home devices 410. Network 420 may also provide access to external devices, such as cloud-based services.

The home device 410 is a home device that may be used by different people associated with the residential environment 400. Examples of other home devices 410 include: HVAC equipment (e.g., air conditioners, heaters, exhaust fans), lighting, motorized window treatments (e.g., door locks, motorized blinds, and curtains), motorized furniture or furnishings (e.g., standing desks, recliners), audio equipment (e.g., music players), video equipment (e.g., televisions, home theaters), environmental controls (e.g., air filters, air fresheners), kitchen equipment (e.g., rice cookers, coffee makers, refrigerators), bathroom equipment, and household robotic equipment (e.g., vacuum robots, robot caregivers). The home device 410 may include other types of devices that may be used in a home.

The household profile 430 typically includes information about different households such as name, identifiers used by the system, age, gender, and health information. The household profile 430 may also include settings and other preferences for the home device 410 selected by different households.

Network 420 provides a connection between the different components of residential environment 400 and enables these components to exchange data with one another. The term "network" is intended to be interpreted broadly. It may include formal networks with standard defined protocols, such as ethernet and wireless broadband technologies. In one embodiment, network 420 is a local area network whose network devices and interconnection devices are managed within residential environment 400. Network 420 may also combine different types of connections. It may comprise a combination of local area networks and/or wide area networks using wired and/or wireless links. Data exchanged between components may be represented using any suitable format. In some embodiments, all or some of the data and communications may be encrypted.

The above-described functionality may be physically implemented in a separate laundry device (one of the home devices 410), a central hub of a home network, a cloud-based service, or elsewhere accessible by the laundry device over the network 420.

Although the detailed description contains many specifics, these should not be construed as limiting the scope of the invention, but merely as providing illustrations of various examples of the invention. It should be understood that the scope of the present disclosure includes other embodiments not discussed in detail above. For example, although a washing machine is used as a primary example, other laundry devices may be used. These appliances include all kinds of washing machines, dryers and steamers. Various other modifications, changes, and variations apparent to those skilled in the art may be made in the arrangement, operation, and details of the methods and apparatus disclosed herein without departing from the spirit and scope as defined in the appended claims. Accordingly, the scope of the invention should be determined by the appended claims and their legal equivalents.

Alternative embodiments are implemented in computer hardware, firmware, software, and/or combinations thereof. The various embodiments may be implemented in the form of a computer program product tangibly embodied in a machine-readable storage device for execution by a programmable processor; the program of instructions may be executed by a programmable processor to perform functions by operating on input data and generating output. Advantageously, embodiments can be implemented in one or more computer programs that are executable on a programmable system including at least one programmable processor coupled to receive data and instructions from, and to transmit data and instructions to, a data storage system, at least one input device, and at least one output device. Each computer program may be implemented using a high level procedural or object oriented programming language, or in assembly or machine language if desired; in any case, the language may be a compiled or interpreted language. Suitable processors include, by way of example, both general and special purpose microprocessors. Generally, a processor will receive instructions and data from a read-only memory and/or a random access memory. Generally, a computer includes one or more mass storage devices for storing data files; such devices include magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and an optical disc. Storage devices suitable for tangibly embodying computer program instructions and data include all forms of non-volatile memory, including by way of example semiconductor memory devices, such as erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), and flash memory devices; magnetic disks, such as internal hard disks and removable disks; magneto-optical disks; and compact disc read only memory (CD-ROM) disks. Any of the foregoing may be supplemented by, or incorporated in, ASICs (application-specific integrated circuits) and other forms of hardware.