KR102555484B1 - Washing machine and cloud server performing freeze preventing function using artificial intelligence - Google Patents

Abstract

The present invention relates to a washing machine and a cloud server that perform a freezing prevention function using artificial intelligence. The washing machine and the cloud server according to the present invention include a control unit that performs a freeze prevention cycle by driving the washing unit to prevent freezing when the freezing probability is higher than a predetermined reference value. In this case, when the freezing probability is higher than a predetermined reference value, the controller generates a freezing warning message and transmits it to the pre-stored user terminal. Through this, the user can grasp the possibility of freezing in advance.

Description

Washing machine and cloud server that performs freeze protection using artificial intelligence

The present invention relates to a washing machine and a cloud server that perform an anti-freezing function.

In general, a washing machine includes a tub in which wash water is contained, and a drum rotatably provided in the tub to accommodate clothes and the like (hereinafter, referred to as 'wash cloth'). Washing machines wash laundry by rotating a drum.

The washing machine includes a water supply device for supplying water into the tub and a drainage device for draining wash water after washing, rinsing, and spin-drying.

However, when washing water is frozen in an environment where the external temperature drops below freezing, the water supply device or drainage device does not operate normally. In particular, when residual water existing in the drainage device or the drain hole of the tub is frozen, the water in the washing machine is not drained to the outside.

In order to solve this problem, a conventional washing machine has an anti-freezing function. For example, a phenomenon in which residual water remaining inside the tub is frozen can be prevented through an operation of rotating the tub left and right at regular intervals.

However, in order to execute the anti-freeze function in a conventional washing machine, the user had to set the anti-freeze function directly through a button. That is, in the conventional washing machine, the user has to predict the occurrence of a freezing phenomenon and set an anti-freeze function in advance, which is inconvenient.

An object of the present invention is to provide a washing machine and a cloud server that determines a freezing probability based on internal or external temperature information or information on a cold season and transmits a message about the freezing probability to a user terminal.

In addition, an object of the present invention is to provide a washing machine and a cloud server that allow a user to remotely drive an anti-freeze cycle of a washing machine when there is user approval.

Another object of the present invention is to provide a washing machine and a cloud server for calculating a freezing probability through machine learning using the temperature measured in the washing machine or the temperature of the external environment as a learning factor.

The objects of the present invention are not limited to the above-mentioned objects, and other objects and advantages of the present invention not mentioned above can be understood by the following description and will be more clearly understood by the examples of the present invention. It will also be readily apparent that the objects and advantages of the present invention may be realized by means of the instrumentalities and combinations indicated in the claims.

The washing machine and the cloud server according to the present invention include a control unit that performs a freeze prevention cycle by driving the washing unit to prevent freezing when the freezing probability is higher than a predetermined reference value. At this time, the control unit generates a freeze warning message and transmits it to the pre-stored user terminal. Through this, the user can grasp the freezing occurrence probability in advance.

In addition, the washing machine and the cloud server according to the present invention include a control unit that determines whether the washing machine is in a remote controllable state when the freezing probability is higher than a predetermined reference value. At this time, the remote controllable state indicates that there is no change in the state of the door after the door installed in the washing unit is closed by the user. In the remote controllable state, the control unit transmits a message about performing an anti-freezing operation to the user terminal. Subsequently, when there is an agreement response to the message from the user terminal, the control unit performs a freeze prevention cycle. Through this, the user can remotely drive the freeze prevention cycle of the washing machine.

In addition, the washing machine and the cloud server according to the present invention include a parameter generating unit for calculating one or more parameters based on the temperature measured by the sensor unit, receiving the parameter as a learning factor and calculating the freezing probability of the washing unit as an output thereof. Includes a learning unit that outputs. Also, the learning unit may additionally receive a parameter for external temperature. Accordingly, the learning unit may calculate the freezing probability through machine learning.

The washing machine and the cloud server according to the present invention determine a freezing probability based on internal or external temperature information of the washing machine or information on cold weather, and provide the information to the user. Accordingly, the washing machine may perform a freeze protection cycle by actively determining a freezing probability even without a user command. Therefore, the present invention can eliminate the inconvenience of having to directly execute the freezing prevention function by the user.

In addition, the washing machine and the cloud server according to the present invention may inform the user of the possibility of freezing in advance. In addition, the present invention supports a function of remotely driving an anti-freezing cycle when there is a user's permission. Accordingly, the user can remotely control the washing machine to perform an anti-freezing operation. Through this, the user's convenience of operation of the washing machine may be improved. In addition, freezing of the washing machine can be prevented in advance.

In addition, the washing machine and the cloud server according to the present invention may provide highly accurate freezing probability information to the user through machine learning learned in various scenarios in which the washing machine is frozen. Through this, the user's reliability of the product may be improved. In addition, brand awareness of the product may be improved.

The effects of the present invention are not limited to the above-mentioned effects, and those skilled in the art can easily derive various effects of the present invention from the configuration of the present invention.

1 is a perspective view showing a washing machine according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating the washing machine of FIG. 1 .
3 is a diagram illustrating a connection relationship between a washing machine and other electronic devices according to another embodiment of the present invention.
4 is a block diagram illustrating a relationship between a home appliance and a cloud server according to another embodiment of the present invention.
5 is a diagram showing the configuration of a learning unit according to some embodiments of the present invention.
6 is a flowchart illustrating an operating method of a washing machine according to an embodiment of the present invention.
FIG. 7 is a diagram for explaining a method of determining a freezing probability in step S150 of FIG. 6 .
FIG. 8 is a diagram for explaining a method of operating a freeze prevention cycle in step S190 of FIG. 6 .

Advantages and features of the present invention, and methods of achieving them, will become clear with reference to the detailed description of the following embodiments taken in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in various different forms, only these embodiments make the disclosure of the present invention complete, and common knowledge in the art to which the present invention belongs. It is provided to fully inform the holder of the scope of the invention, and the present invention is only defined by the scope of the claims. Like reference numbers designate like elements throughout the specification.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used in a meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

In addition, in implementing the present invention, components may be subdivided for convenience of explanation, but these components may be implemented in one device or module, or one component may be implemented in a plurality of devices or modules. It may be implemented by dividing into .

Hereinafter, with reference to FIGS. 1 to 8 , a washing machine and a cloud server performing an anti-freezing function according to an embodiment of the present invention will be described.

1 is a perspective view showing a washing machine according to an embodiment of the present invention.

First, referring to FIG. 1 , the washing machine 100 may include a plurality of washing units. Specifically, the washing machine 100 may include a first washing unit 150A and a second washing unit 150B.

The first washing unit 150A and the second washing unit 150B may be disposed adjacent to each other. For example, the first washing unit 150A and the second washing unit 150B may be arranged vertically.

The first washing unit 150A and the second washing unit 150B may be coupled and separated from each other. The first washing unit 150A and the second washing unit 150B may have respective housings. At this time, each housing may be formed to be coupled and separated from each other.

Also, the first washing unit 150A and the second washing unit 150B may be disposed within one housing. In this case, the first washing unit 150A and the second washing unit 150B may be fixed in the housing and not separated.

The first washing unit 150A and the second washing unit 150B may each be configured in a front load or top load method.

Here, the front load method has a form in which laundry is put into the washing tub from the front side. Accordingly, in the front-loading method, the washing tub in which laundry is processed substantially rotates about a horizontal axis.

On the other hand, the top-load method has a form in which laundry is put into the washing tub from the top surface. Accordingly, in the top-loading method, the washing tub in which laundry is processed substantially rotates around a vertical axis.

1 illustrates an embodiment in which the first washing unit 150A is configured in a front-loading manner and the second washing unit 150B is configured in a top-loading manner. However, the present invention is not limited thereto, and the first washing unit 150A and the second washing unit 150B may be modified and implemented in various ways.

The first washing unit 150A may include a first washing tub 151A, a first door 153A, and a first interface unit 170A. The first door 153A is installed in the inlet of the first washing tub 151A. The first interface unit 170A includes various buttons capable of controlling the operation of the first washing unit 150A.

Similarly, the second washing unit 150B may include a second washing tub 151B, a second door 153B, and a second interface unit 170B. The second door 153B is installed in the inlet of the second washing tub 151B. The second interface unit 170B includes various buttons capable of controlling the operation of the second washing unit 150B.

That is, the first washing unit 150A and the second washing unit 150B may include separate washing tubs 151A and 151B, doors 153A and 153B, and interface units 170A and 170B, respectively. Accordingly, the first washing unit 150A and the second washing unit 150B may operate independently of each other.

For reference, unlike what is shown in the drawings, the washing machine 100 may include only one washing unit 150 . In this case, the washing unit 150 may include only one washing tub 151, one door 153, and one interface unit 170, respectively.

Hereinafter, for convenience of description, an example in which the washing machine 100 includes only one washing unit 150 will be described.

At this time, the user may manipulate the washing machine 100 to perform the freezing prevention function through the interface unit 170 . At this time, the anti-freezing function refers to an operation of discharging residual water remaining inside the washing tub 151 by rotating the washing tub 151 left and right at regular intervals. As residual water remaining inside is discharged, freezing of the washing unit 150 may be prevented.

However, conventionally, when the external temperature is low and the possibility of freezing is high, the user has to directly set the freezing prevention function, which is inconvenient.

In order to solve this conventional problem, the present invention determines the freezing probability based on the temperature inside the washing machine 100 or the temperature of the external environment. Subsequently, when the freezing probability is equal to or greater than a predetermined reference value, the washing machine 100 transmits a freezing warning message to the user terminal. In addition, when the washing machine 100 is in a remote controllable state, the washing machine 100 transmits a message about performing an anti-freezing operation to the user terminal. Subsequently, when there is a response to the user's consent, the washing machine 100 may perform a freezing prevention function.

Hereinafter, the configuration of the washing machine 100 performing the above-described operation will be described in detail.

FIG. 2 is a block diagram illustrating the washing machine of FIG. 1 .

Referring to FIG. 2 , a washing machine 100 according to an embodiment of the present invention includes a sensor unit 110, a parameter generator 120, a learning unit 130, a control unit 140, a washing unit 150, a communication unit ( 160), an interface unit 170, and a memory unit 180.

The sensor unit 110 includes one or more sensors capable of measuring the temperature of the washing machine 100 . For example, freezing of the washing machine 100 may mainly occur in the washing unit 150 where residual water exists. Accordingly, the sensor unit 110 may be installed at a location capable of measuring the temperature of the washing unit 150 .

Various types of sensors capable of measuring temperature may be used as the sensor unit 110 . For example, a contact temperature sensor or a non-contact temperature sensor may be used as the sensor unit 110 . Here, the contact temperature sensor may include a thermocouple, a metal temperature measuring resistor, a thermistor, an IC temperature sensor, a magnetic temperature sensor, and the like. The non-contact temperature sensor may include a thermopile or a pyroelectric temperature sensor.

Additionally, the sensor unit 110 may further include a water level sensor capable of measuring a change in water level in the washing unit 150 .

The parameter generating unit 120 may generate parameters based on temperature information measured by the sensor unit 110 . The parameter generator 120 may generate a plurality of parameters after accumulating and storing the values sensed by the sensor unit 110 (ie, internal temperature information) in the memory unit 180 .

Also, the parameter generating unit 120 may generate parameters based on external temperature information received from an external server or a separate device. Similarly, the parameter generating unit 120 may generate a plurality of parameters after accumulating and storing the received external temperature information in the memory unit 180 .

That is, the parameter generator 120 may generate a plurality of parameters based on the internal temperature of the washing machine 100 and the external temperature of the external environment.

The parameter generated by the parameter generator 120 may be provided to the learner 130 as a learning factor.

The learning unit 130 receives the parameter received from the parameter generator 120 as a learning factor, and outputs the freezing probability of the washing unit 150 as an output thereof.

Specifically, the learning unit 130 may receive parameters (learning factors) generated by the parameter generator 120 as input. Next, the learning unit 130 may calculate the freezing probability of the washing unit 150 by applying the input parameters to the deep learning structure inside the learning unit 130 . At this time, the learning unit 130 may estimate the freezing probability using a predetermined learning algorithm input in advance.

The freezing probability may be determined based on output information of the learning unit 130 that calculates the current state based on machine learning. A detailed description of the learning unit 130 will be described later with reference to FIG. 5 .

The controller 140 may perform overall control of components included in the washing machine 100 .

The control unit 140 receives the freezing probability from the learning unit 130 . Subsequently, the controller 140 may determine whether the freezing probability is greater than or equal to a predetermined reference value.

Subsequently, when the freezing probability is equal to or greater than a predetermined reference value, the controller 140 may generate a message for a freezing warning and transmit the message to the user terminal 300 through the communication unit 160 .

Subsequently, the controller 140 may determine whether the washing machine 100 is in a remote controllable state. Here, the remote controllable state means that there is no state change of the door 153 of the washing unit 150 after the door 153 is closed. That is, the remote controllable state means that the door 153 remains closed after the user closes the door 153 .

If the door 153 is not opened again after the user closes the door 153 of the washing unit 150, the probability that a child or pet enters the washing unit 150 is low. Therefore, since the probability of a safety accident occurring when the door 153 is maintained in a closed state is low, the control unit 140 allows remote control.

Subsequently, when the washing machine 100 is in a remote controllable state, the control unit 140 may generate a message about performing an anti-freeze operation and transmit the message to the user terminal 300 through the communication unit 160 . Here, the message regarding the execution of the freeze protection operation includes content requesting the user to confirm whether or not to perform the freeze protection operation.

Subsequently, when there is a response to the user agreement from the user terminal 300, the controller 140 may perform a freeze protection cycle.

In the freeze protection cycle, the control unit 140 determines whether the temperature measured by the sensor unit 110 is lower than the freezing limit temperature or whether the water level change during water supply or spin-drying of the washing unit 150 is out of the normal reference range. .

Next, when the temperature measured by the sensor unit 110 is lower than the freezing limit temperature or when the water level change during water supply or spin-drying of the washing unit 150 is out of the normal standard range, the control unit 140 sends a message about the occurrence of freezing. It may be displayed on the interface unit 170 or transmitted to the user terminal 300 .

On the other hand, when the temperature measured by the sensor unit 110 is higher than the freezing limit temperature and the water level change during water supply or spin-drying of the washing unit 150 is within the normal reference range, the control unit 140 controls the An anti-freezing operation of rotating the tub left and right may be performed.

Additionally, the operation of the controller 140 described above may be performed in an active standby state. Here, the active standby state means a state in which only minimum power is provided so that the washing machine 100 can receive external temperature information from an external device. In addition, the active standby state means a state in which only minimum power is provided to detect the internal temperature of the washing unit 150 .

In this case, when the received external temperature or the detected internal temperature is smaller than the reference temperature, the controller 140 may control the learning unit 130 to calculate the freezing probability.

The operation of the washing unit 150 may be controlled by the control unit 140 . The washing unit 150 may operate the washing tub 151 left and right at regular intervals to perform a freezing prevention function of preventing residual water remaining inside the washing tub 151 from being frozen.

The communication unit 160 includes one or more communication modules. Through this, the communication unit 160 can perform wireless communication with other electronic devices to exchange various signals. For example, the communication unit 160 may exchange data with separate servers or user terminals using a wireless Internet network. In addition, the communication unit 160 may receive information about cold weather from a server that provides weather information or safety information among various servers constituting the external service 400 . The information on the cold season may include information such as when the cold season occurred, whether it lasted or not, and the temperature. In addition, the information on the cold weather may include information on the number or rate of freezing of the washing machine in the region where the washing machine is disposed. Of course, in addition to this, various pieces of information affecting the freezing of the washing machine may be included in the information on the cold season.

In addition, the controller 140 may generate a freezing warning message and transmit it to the pre-stored user terminal 300 or increase a freezing probability by using the information on the cold season. By increasing the probability of freezing, the washing machine 100 may operate in response to an increase in the possibility of freezing.

The interface unit 170 may include a plurality of manipulation buttons and a display. Using a plurality of control buttons, the user can set a washing course or washing option. The display may display information corresponding to the user's command input, a processing result corresponding to the user's command input, an operating course, an operating state, an error state, and the like. Also, the interface unit 170 may be configured in a form in which a touch pad and a touch screen are combined.

The memory unit 180 stores various types of information necessary for the operation of the washing machine, and may include a volatile or non-volatile recording medium. The memory unit 180 may store periodic temperature measurement data used for parameter calculation in the form of a database.

For example, the memory unit 180 may store the internal temperature of the washing unit 150 measured by the sensor unit 110 at regular intervals. Also, the memory unit 180 may store the external temperature received from the external device at regular intervals. Information on internal and external temperatures may be stored in the form of a database.

The learning unit 130 may perform machine learning on parameters input as learning factors. The memory unit 180 may store data used for machine learning, result data, and the like.

To explain in more detail, deep learning technology, a type of machine learning, learns by going down to a deep level in multiple stages based on data.

Deep learning represents a set of machine learning algorithms that extract core data from a plurality of data while stepping up.

The deep learning architecture may include artificial neural networks (ANNs). For example, the deep learning structure may include a deep neural network (DNN) such as a convolutional neural network (CNN), a recurrent neural network (RNN), and a deep belief network (DBN).

The learning unit 130 may use various well-known deep learning structures. For example, the learning unit 130 may use a structure such as a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), or a Deep Belief Network (DBN).

Specifically, CNN (Convolutional Neural Network) extracts the basic features of an object when a person recognizes an object, and then performs complex calculations in the brain to recognize the object based on the result. It is a simulated model.

RNN (Recurrent Neural Network) is widely used in natural language processing, etc., and is an effective structure for processing time-series data that changes over time.

DBN (Deep Belief Network) is a deep learning structure composed of multiple layers of RBM (Restricted Boltzman Machine), a deep learning technique. When a certain number of layers is obtained by repeating RBM (Restricted Boltzman Machine) learning, a DBN (Deep Belief Network) having a corresponding number of layers may be configured.

Meanwhile, learning of the artificial neural network of the learning unit 130 may be performed by adjusting the weight of a connection line between nodes (and adjusting a bias value if necessary) so that a desired output is produced for a given input.

In addition, the artificial neural network may continuously update a weight value by learning. In addition, a method such as back propagation may be used to learn the artificial neural network.

On the other hand, the memory unit 180 may be loaded with an artificial neural network previously learned through machine learning.

That is, the washing machine 100 according to an embodiment of the present invention may perform a situation determination operation based on machine learning using received temperature information as input data. In this case, both unsupervised learning and supervised learning may be used as machine learning methods of the artificial neural network. In addition, the learning unit 130 may control to update the artificial neural network structure of the freezing probability calculation after learning according to settings.

Additionally, in another embodiment of the present invention, the operation of the learning unit 130 may be implemented in a separate cloud server 200. A system in which a machine learning operation is performed internally, such as the washing machine 100 according to an embodiment of the present invention described above, is referred to as an internal learning-based system.

On the other hand, a system in which machine learning operations are performed in an external server (eg, the cloud server 200) is referred to as an external learning-based system.

Hereinafter, the washing machine 101 and the cloud server 200 constituting the external learning-based system will be reviewed with reference to FIGS. 3 and 4 .

3 is a diagram illustrating a connection relationship between a washing machine and other electronic devices according to another embodiment of the present invention. 4 is a block diagram illustrating a relationship between a home appliance and a cloud server according to another embodiment of the present invention. Here, the contents overlapping with the above contents are omitted and described.

3 and 4, among the components of the washing machine 101 constituting the external learning-based system, a sensor unit 110, a parameter generator 120, a control unit 140, a washing unit 150, a communication unit ( 160), the interface unit 170, and the memory unit 180 may operate substantially the same as the respective components of the washing machine 100 described with reference to FIG. 2 above. Here, descriptions of overlapping components of the washing machine 101 will be omitted.

The parameter generating unit 120 may generate one or more parameters based on temperature information measured by the sensor unit 110 . The parameter generating unit 120 may store internal temperature information sensed by the sensor unit 110 in the memory unit 180 at regular intervals, and then generate a plurality of parameters based on this.

Also, the parameter generator 120 may receive external temperature information received from the external service 400 . In this case, the external service 400 may be a weather server, an external temperature measuring device, a weather information providing module, and the like. In addition, the external service 400 may also provide information on cold weather. For example, the information about the cold season may include information such as when the cold season occurred, whether it lasted or not, and the temperature. In addition, the information on the cold season may include information on the number or rate of washing machine freezing occurring in a specific region. Information on cold weather may be provided to the washing machines 100 or 101 or provided to the cloud server 200 to increase accuracy in calculating the possibility of freezing.

In this case, the parameter generator 120 may generate one or more parameters based on the received external temperature information. Similarly, the parameter generating unit 120 may store the received external temperature information in the memory unit 180 at regular intervals and then generate a plurality of parameters based on this.

That is, the parameter generator 120 may generate a plurality of parameters based on the internal temperature of the washing machine 100 and the external temperature of the external environment.

Next, the controller 140 transmits the generated parameters to the cloud server 200 through the communication unit 160 .

The cloud server 200 includes a communication unit 210 , a server control unit 220 and a learning unit 230 .

The communication unit 210 is wirelessly connected to the communication unit 160 of the washing machine 100 to exchange data.

The server controller 220 transfers the parameters received through the communication unit 210 to the learning unit 230 .

The learning unit 230 receives the received parameter as a learning factor (ie, an input factor). Subsequently, the learning unit 130 may output the freezing probability of the washing unit 150 as an output factor.

At this time, the learning unit 230 may generate links or biases or weights of each link disposed in the hidden layer and each input/output factor in a learning process, and store updated information from the outside. there is. In this case, the learning unit 230 may be stored in the cloud server 200 in a different version.

In summary, the cloud server 200 may receive a learning factor (ie, parameter) from the washing machine 101 and calculate an output factor corresponding thereto. In addition, the learning unit 230 may be updated by continuously inputting learning factors provided by the washing machine 101 to the learning unit 230 . The learning unit 230 may estimate the load level using a predetermined learning algorithm.

Subsequently, the freezing probability output from the learning unit 230 may be composed of a normal state probability and a frozen state probability.

When the freezing state probability is greater than the steady state probability, the server controller 220 may determine that the current washing machine 100 is highly likely to be frozen. In addition, when the frozen state probability is greater than the reference value, the server controller 220 may determine that the current washing machine 100 is highly likely to be frozen.

Subsequently, when it is determined that the possibility of freezing is high, the server controller 220 may transmit a freezing warning message to the user terminal 300 .

In addition, the server controller 220 may determine whether the washing machine 100 is in the aforementioned remote controllable state.

Subsequently, when the washing machine 100 is in a remote controllable state, the server controller 220 may generate a message regarding performing an anti-freezing operation and transmit the message to the user terminal 300 .

Subsequently, when there is a response to the user consent from the user terminal 300, the server controller 220 may control the washing machine 100 to perform an anti-freezing cycle.

Here, operation control for the freeze protection cycle may be performed by the controller 140 of the washing machine 101 .

In addition, the communication unit 210 of the cloud server 200 may also receive information about cold weather from a server providing weather information or safety information among various servers constituting the external service 400 . The information about the cold season is as described above. Also, the server control unit 220 may increase the freezing probability by using the information on the cold season. The cloud server 200 provides the result of increasing the freezing probability to the washing machines 100 and 101, so that the washing machines 100 and 101 may operate in response to an increase in the possibility of freezing.

Hereinafter, the configuration of the learning units 130 and 230 according to some embodiments of the present invention described above will be described.

5 is a diagram showing the configuration of a learning unit according to some embodiments of the present invention.

Referring to FIG. 5, the learning units 130 and 230 have an input layer (input) having N parameters as input nodes, an output layer (Output) having a freezing probability as an output node, and between the input layer and the output layer. It includes M hidden layers to be arranged.

Here, a weight may be set to an edge connecting nodes of each layer. The presence or absence of these weights or edges can be added, removed, or updated in the learning process. Therefore, through the learning process, weights of nodes and edges disposed between k input nodes and i output nodes may be updated.

As shown in FIG. 5, i output nodes may be arranged to output values such as 1/0 or probability for each mode. For example, as described above, the output node may be composed of a steady state probability and a frozen state probability (ie, two).

Before the learning units 130 and 230 perform learning, all nodes and edges may be set to initial values. However, when cumulative information is input, the weights of nodes and edges are changed, and in this process, the parameters input as learning factors (i.e., the cumulative value of internal temperature or external temperature) and the value assigned to the output node (i.e., , freezing probability) can be made.

Additionally, when using the cloud server 200, the learning unit 230 may receive and process a large number of parameters. Accordingly, the learning unit 230 may perform learning based on a large amount of data.

In summary, the weights of the nodes and edges between the input node and the output node constituting the learning units 130 and 230 of FIG. 5 may be updated by the learning process of the learning units 130 and 230 . The freezing probability output from the learning units 130 and 230 may be used to determine the freezing possibility of the washing machine 100 .

Hereinafter, a method of operating a washing machine performing an anti-freeze function according to some embodiments of the present invention will be described in detail.

However, hereinafter, for convenience of description, the washing machine 100 according to an embodiment of the present invention described above, which operates based on an internal learning-based system, will be described as an example.

6 is a flowchart illustrating an operating method of a washing machine according to an embodiment of the present invention. FIG. 7 is a diagram for explaining a method of determining a freezing probability in step S150 of FIG. 6 . FIG. 8 is a diagram for explaining a method of operating a freeze prevention cycle in step S190 of FIG. 6 .

Referring to FIG. 6 , in the operating method of the washing machine according to the embodiment of the present invention, the control unit 140 determines whether the washing machine 100 is currently in an active standby state (S110).

Here, the active standby state means a state in which only minimum power is provided to sense the internal temperature of the washing unit 150 . Also, the active standby state means a state in which only minimum power is provided so that the washing machine 100 can receive external temperature information from an external device.

For reference, in another embodiment of the present invention, step S110 may be omitted.

Subsequently, the sensor unit 110 measures the temperature of the tub provided in the washing unit 150 (S120). The temperature measured by the sensor unit 110 may be transmitted to the controller 140 .

Next, the controller 140 compares the received temperature of the tub with the reference temperature (S130).

Next, when the temperature of the tub is lower than the reference temperature, the controller 140 receives temperature information from the sensor unit 110 at predetermined intervals (S140). At this time, the temperature information received from the sensor unit 110 may represent the internal temperature of the washing machine 100 . Temperature information received by the sensor unit 110 may be accumulated and stored in the memory unit 180 .

Also, the controller 140 may receive external temperature information from an external device. Similarly, information on the external temperature may be accumulated and stored in the memory unit 180 .

Here, the predetermined period means a predetermined period. For example, the predetermined period may be 1 hour, 2 hours, or 30 minutes. The predetermined cycle may be previously set in the washing machine 100 in the manufacturing process and may be changed by the user.

Subsequently, the learning unit 130 calculates a freezing probability based on the internal temperature or external temperature stored in the memory unit 180 (S150). In this case, the parameter generator 120 may generate a plurality of parameters based on the internal temperature of the washing machine 100 and the external temperature of the external environment. A plurality of parameters generated by the parameter generator 120 may be input to the learning unit 130 .

The learning unit 130 may receive the parameter received from the parameter generator 120 as a learning factor and output the freezing probability of the washing unit 150 as an output thereof.

Referring to FIG. 7 , the parameter generating unit 120 may calculate a first parameter based on the internal temperature of the washing machine 100 measured by the sensor unit 110 . For example, the first parameter may include first to Nth tub temperatures (Tub. Temp1 to N). At this time, the first tub temperature (Tub. Temp1) represents the current internal temperature of the washing machine 100, and the second to Nth tub temperatures (Tub. Temp2 to N) represent the internal temperature of the washing machine 100 prior to a predetermined cycle. can indicate

Also, the parameter generator 120 may calculate the second parameter based on the external temperature received from the external device through the communication unit 160 . For example, the second parameter may include first to Nth external temperatures (Ex. Temp1 to N). At this time, the first external temperature (Ex. Temp1) represents the current internal temperature of the washing machine 100, and the second to Nth tub temperatures (Tub. Temp2 to N) represent the internal temperature of the washing machine 100 prior to a predetermined cycle. can indicate

The learning unit 130 may input the aforementioned first and second parameters to an input node. For example, five of each of the aforementioned first and second parameters may be input.

At this time, the learning unit 130 has an input layer (input) with 10 parameters as input nodes, an output layer (Output) with freezing probabilities as two output nodes, and three layers disposed between the input layer and the output layer. A hidden layer may be included. However, this is only one example, and the number of each input node and output node and the number of hidden layers may be variously modified and implemented.

Subsequently, the freezing probability output from the learning unit 130 may be composed of a normal state probability and a frozen state probability.

When the freezing state probability is greater than the steady state probability, the server controller 220 may determine that the current washing machine 100 is highly likely to be frozen. In addition, when the frozen state probability is greater than the reference value, the server controller 220 may determine that the current washing machine 100 is highly likely to be frozen. Hereinafter, for convenience of explanation, the comparison of the frozen state probability and the reference value by the control unit 140 will be described as an example.

Subsequently, the control unit 140 compares the frozen state probability (ie, freezing probability) with a predetermined reference value (S160).

Subsequently, when the frozen state probability (ie, frozen probability) is greater than the reference value, the controller 140 generates a frozen warning message and transmits it to the user terminal 300 (S170). Here, the freezing warning message may include information "It is highly likely that the washing machine is currently frozen." However, this is just one example, and the freeze warning message may be variously modified and implemented.

Next, the controller 140 determines whether the washing machine 100 is in a remote controllable state (S180). Here, the remote controllable state means that there is no state change of the door 153 of the washing unit 150 after the door 153 is closed. That is, the remote controllable state means that the door 153 remains closed after the user closes the door 153 .

If the door 153 is not opened again after the user closes the door 153 of the washing unit 150, the probability that a child or pet enters the washing unit 150 is low. Therefore, since the probability of a safety accident occurring when the door 153 is maintained in a closed state is low, the control unit 140 may allow remote control.

Subsequently, when the washing machine 100 is in the above-described remote controllable state, a message regarding performing an anti-freezing operation may be transmitted to the user terminal 300 (S182). Here, the message regarding the execution of the anti-freezing operation may include information "Do you want to perform the anti-freezing operation? Select consent or rejection". The user may select Agree or Deny for performing the freezing prevention operation through the user terminal 300 .

Subsequently, the control unit 140 may receive a user agreement response (S184). In this case, the controller 140 may perform a freezing prevention cycle (S190).

Hereinafter, the freezing prevention cycle will be described in detail with reference to FIG. 8 .

Referring to FIG. 8 , in the freeze protection cycle, the tub temperature of the washing unit 150 and the freezing limit temperature are first compared (S210). Here, the freezing limit temperature may be set to a temperature lower than the reference value for determining the possibility of freezing. For example, the reference value for determining the possibility of freezing may be set to '0 degree' and the freezing limit temperature may be set to '-15 degree'. However, these reference values and freezing limit temperatures may be variously changed and implemented.

Subsequently, when the tub temperature is higher than the freezing limit temperature, the controller 140 controls the washing unit 150 to supply water (S220). Subsequently, the control unit 140 may receive a water level change in relation to the water supply operation from the sensor unit 110 .

Next, the control unit 140 determines whether the water level change for the water supply operation is within the normal reference range (S230). Here, the normal reference range may be expressed as a water level change amount for a predetermined time.

Subsequently, when the change in water level for the water supply operation is within the normal standard range, the controller 140 controls the washing unit 150 to perform a draining operation (S240). Subsequently, the control unit 140 may receive a water level change in relation to the drainage operation from the sensor unit 110 .

Subsequently, the control unit 140 determines whether the water level change for the drainage operation is within the normal reference range (S250). Similarly, the normal reference range can be expressed as a change in water level over a predetermined period of time.

Subsequently, when the change in water level for the draining operation is within the normal reference range, the controller 140 stops the draining operation (S260).

Subsequently, the controller 140 performs a freezing prevention operation (S270). Here, the freezing prevention operation means an operation of repeatedly rotating the tub included in the washing unit 150 left and right. Through the anti-freeze operation, residual water inside the washing unit 150 may be discharged to the outside of the washing unit 150 .

For reference, steps S210 to S260 represent conditions for determining whether or not to freeze, and step S270 represents a control operation for substantially preventing the washing unit 150 from freezing.

Meanwhile, in step S210 described above, if the tub temperature is lower than the freezing limit temperature, the controller 140 may display a message about the occurrence of freezing on the interface unit 170 (S280). In addition, the controller 140 may transmit a message about the occurrence of freezing to the user terminal 300 (S290).

In addition, in the above-described step S230 or step S250, when the change in water level due to the water supplying or draining operation is out of the normal reference range, the controller 140 may display a message about the occurrence of freezing on the interface unit 170 ( S280). In addition, the controller 140 may transmit a message about the occurrence of freezing to the user terminal 300 (S290).

For reference, in an embodiment of the present invention, steps S280 and S290 may be selectively performed.

In summary, the present invention can determine the freezing probability based on the temperature information of the inside or outside of the washing machine and provide the information to the user. Accordingly, the washing machine may perform a freeze protection cycle by actively determining a freezing probability even without a user command.

In addition, if there is a user's permission, the present invention supports a function of remotely driving the freeze protection cycle. Accordingly, the user can remotely control the washing machine to perform an anti-freezing operation. Through this, the user's convenience of operation of the washing machine may be improved. In addition, freezing of the washing machine can be prevented in advance.

In addition, the present invention can provide highly accurate freezing probability information to the user through machine learning learned in various scenarios in which the washing machine is frozen. Through this, the user's reliability of the product may be improved. In addition, brand awareness of the product may be improved.

Although the above has been described based on the embodiments of the present invention, various changes or modifications may be made at the level of those skilled in the art. Accordingly, it will be understood that such changes and modifications are included within the scope of the present invention as long as they do not depart from the scope of the present invention.

100: washing machine 110: sensor unit
120: parameter generation unit 130: learning unit
140: control unit 150: washing unit
160: communication unit 170: interface unit
180: memory unit 200: cloud server
210: communication unit 220: server control unit
230: learning unit 300: user terminal

Claims (18)

a washing unit to wash laundry;
a sensor unit to measure the temperature of the washing unit;
a parameter generating unit calculating one or more parameters based on the temperature measured by the sensor unit;
a learning unit that receives the parameter as a learning factor and outputs a freezing probability of the washing unit as an output thereof; and
When the freezing probability is higher than a predetermined reference value, comprising a control unit for performing a freeze prevention cycle for preventing freezing by driving the washing unit
washing machine.
According to claim 1,
The learning unit,
An input layer having the parameter as an input node;
An output layer having the freezing probability as an output node;
Including one or more hidden layers disposed between the input layer and the output layer;
Weights of nodes and edges between the input node and the output node are updated by the learning process of the learning unit.
washing machine.
According to claim 1,
Further comprising a communication unit for receiving information about the external temperature,
The parameter generator,
Calculating a plurality of parameters based on the external temperature received from the communication unit and the temperature of the washing unit measured by the sensor unit
washing machine.
According to claim 1,
Further comprising a communication unit for receiving information on the cold season,
The control unit
Using the information on the cold weather, generating a freezing warning message and transmitting it to a pre-stored user terminal or increasing the freezing probability,
washing machine.
According to claim 1,
The control unit,
When the freezing probability is higher than a predetermined reference value, generating a freezing warning message and transmitting it to a pre-stored user terminal
washing machine.
According to claim 1,
The control unit,
When the freezing probability is higher than a predetermined reference value, determining whether the washing machine is in a remote controllable state,
The remote controllable state,
Indicates that the closed state of the door is maintained after the door installed in the washing unit is closed by the user
washing machine.
According to claim 6,
The control unit,
When the washing machine is in the remote controllable state, a message about performing an anti-freeze operation is transmitted to a user terminal;
If there is an agreement response to the message from the user terminal, performing the freeze prevention cycle
washing machine.
According to claim 7,
Further comprising an interface unit for displaying a state of the washing machine,
In the freeze protection cycle, the control unit,
When the temperature measured by the sensor unit is lower than the freezing limit temperature or when the water level change during water supply or spin-drying of the washing unit is out of the normal reference range, a message about the occurrence of freezing is displayed on the interface unit or transmitted to the user terminal. doing
washing machine.
According to claim 1,
In the freeze protection cycle, the control unit,
When the temperature measured by the sensor unit is higher than the freezing limit temperature and the water level change during water supply and spin-drying of the washing unit is within the normal reference range, performing an anti-freezing operation of rotating the tub included in the washing unit to the left and right
washing machine.
In a cloud server communicating with a washing machine,
a communication unit receiving at least one parameter calculated based on the temperature measured by the washing machine;
a learning unit receiving the parameter received from the communication unit as a learning factor and outputting a freezing probability of the washing machine as an output thereof; and
And a server control unit controlling an operation of the washing machine so that the washing machine performs a freeze prevention cycle to prevent freezing when the freezing probability is higher than a predetermined reference value.
cloud server.
According to claim 10,
The learning unit,
An input layer having the parameter as an input node;
An output layer having the freezing probability as an output node;
Including one or more hidden layers disposed between the input layer and the output layer;
Weights of nodes and edges between the input node and the output node are updated by the learning process of the learning unit.
cloud server.
According to claim 11,
The communication unit additionally receives information about external temperature,
The server control unit calculates one or more parameters based on the received external temperature,
The learning unit receives the parameter calculated by the server control unit and the parameter received through the communication unit through the input node.
cloud server.
According to claim 10,
The communication unit receives information about the cold season,
The server control unit
Using the information on the cold season to increase the freezing probability,
cloud server.
According to claim 10,
The server control unit,
When the freezing probability is higher than a predetermined reference value, generating a freezing warning message and transmitting it to a pre-stored user terminal
cloud server.
According to claim 10,
The server control unit,
When the freezing probability is higher than a predetermined reference value, determining whether the washing machine is in a remote controllable state,
The remote controllable state,
Indicates that the door remains closed after the door installed in the washing unit of the washing machine is closed by the user
cloud server.
According to claim 15,
The server control unit,
When the washing machine is in the remote controllable state, a message about performing an anti-freeze operation is transmitted to a user terminal;
Controlling the washing machine to perform the freeze protection cycle when there is an agreement response to the message from the user terminal.
cloud server.
According to claim 16,
In the freeze protection cycle, the server control unit,
When the temperature measured by the washing machine is lower than the freezing limit temperature or when the water level change during water supply or spin-drying of the washing machine is out of the normal reference range, a message about the occurrence of freezing is transmitted to the user terminal
cloud server.
According to claim 10,
In the freeze protection cycle, the server control unit,
Controlling the operation of the washing machine so that the tub included in the washing machine rotates left and right when the temperature measured by the washing machine is higher than the freezing limit temperature and the water level change during water supply and spin-drying of the washing machine is within the normal reference range
cloud server.

Images