KR102119076B1 - Dishwasher with function control based on artificial intelligence - Google Patents

Abstract

According to an embodiment of the present invention, the present invention relates to a dishwasher, which can communicate with a server and a user device. The dishwasher of the present invention comprises: a sensor unit for sensing a state of an object to be washed and a driving state of a washing function; an input unit for receiving a driving command from a user; a communication unit for performing wireless communication with a server and a user device, and receiving an AI analysis result from the server; a control unit for selecting AI analysis data required for AI calculation from data acquired by the sensor unit and the input unit, and controlling the selected AI analysis data to be transmitted to the server under a condition requiring the AI calculation; a washing module for driving a washing operation under the control of the control unit; and a display unit for displaying the AI analysis result under the control of the control unit. According to the present invention, a failure cause is more accurately analyzed based on artificial intelligence, and the failure cause can be simply solved.

Description

Dishwasher with function control based on artificial intelligence}

The present invention relates to a dishwasher that performs function control based on artificial intelligence. Specifically, the present invention relates to a dishwasher that performs a washing operation, a malfunction diagnosis operation, etc. in response to an analysis result through artificial intelligence.

The dishwasher is a device that performs dishwashing. In general, the dishwasher adopts a method of spraying washing water into washing water or a method of generating ultrasonic waves in washing water after dipping the washing water into washing water as a main washing method.

In the prior art, the user directly checks the degree of contamination and the amount of the washing to wash the washing using a dishwasher, and selects an appropriate washing mode correspondingly, or uniformly regardless of the characteristics of the washing. The same washing operation has been performed.

Accordingly, the conventional dishwasher was unable to provide a customized washing operation corresponding to the characteristics of the washing product, and the washing strength and the number of times were not variable according to the degree of contamination of the washing product, thereby causing a waste of resources.

The present invention has been made to solve the above-mentioned problems, and has an object to obtain condition information of a washing object to be washed using a dishwasher, and to derive a set value for an appropriate washing operation correspondingly.

In particular, the present invention has an object to easily calculate a washing mode in which various variables such as the number of washings, the kinds of washings, and the degree of contamination of washings are complexly considered using artificial intelligence in this process.

Dishwasher according to an embodiment of the present invention can communicate with the server and the user device, the sensor unit for sensing the state of the washing water and the driving state of the washing function, an input unit for receiving a driving command from the user, the server and the user device A communication unit that performs wireless communication and receives AI analysis results from the server, and selects AI analysis data necessary for AI calculation from among data acquired by the sensor unit and the input unit under a condition that requires AI calculation, It may be configured to include a control unit for controlling to transmit the selected AI analysis data to the server, a washing module for driving a washing operation under the control of the control unit and a display unit for displaying AI analysis results under the control of the control unit.

Various embodiments of the present invention may analyze a more accurate cause of failure based on artificial intelligence, and present a solution of a dishwasher corresponding thereto. Accordingly, in the case of a failure situation that can be easily solved, time required for repair request and diagnosis can be saved, and the cause of the failure can be easily solved.

Various embodiments of the present invention can calculate the most suitable washing mode corresponding to the current washing situation, such as the image of the washing water, the degree of contamination of the washing water. Accordingly, the present invention can prevent waste of washing water and waste of power due to excessive washing operation compared to the degree of contamination and the amount of washing.

And, according to the present invention, when additional washing water is dropped into the washing tank while the washing operation is being performed, an appropriate washing mode corresponding to the corresponding situation can be calculated by AI analysis in real time. Can be.

1 is a view showing an example of the appearance of a dishwasher according to an embodiment of the present invention.
2 is a diagram illustrating a network structure of a dishwasher according to an embodiment of the present invention.
3 is a view showing the configuration of a dishwasher according to an embodiment of the present invention.
4 is a diagram showing the configuration of a server according to an embodiment of the present invention.
5 is a diagram illustrating a conceptual illustration of an AI model according to an embodiment of the present invention.

Advantages and features of the present invention, and methods for achieving them will be clarified with reference to embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the disclosure of the present invention to be complete, and are common in the technical field to which the present invention pertains. It is provided to fully inform the skilled person of the scope of the present invention, and the present invention is only defined by the scope of the claims.

The terminology used herein is for describing the embodiments and is not intended to limit the present invention. In the present specification, the singular form also includes the plural form unless otherwise specified in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components other than the components mentioned. Throughout the specification, the same reference numerals refer to the same components, and “and/or” includes each and every combination of one or more of the components mentioned. Although "first", "second", etc. are used to describe various components, it goes without saying that these components are not limited by these terms. These terms are only used to distinguish one component from another component. Therefore, it goes without saying that the first component mentioned below may be the second component within the technical spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used as meanings commonly understood by those skilled in the art to which the present invention pertains. In addition, terms defined in the commonly used dictionary are not ideally or excessively interpreted unless explicitly defined.

The term "part" or "module" as used in the specification refers to a hardware component such as software, FPGA, or ASIC, and "part" or "module" performs certain roles. However, "part" or "module" is not meant to be limited to software or hardware. The "unit" or "module" may be configured to be in an addressable storage medium or may be configured to reproduce one or more processors. Thus, as an example, "part" or "module" means components, processes, functions, attributes, such as software components, object-oriented software components, class components and task components. Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, database, data structures, tables, arrays and variables. The functionality provided within components and "parts" or "modules" can be combined into a smaller number of components and "parts" or "modules" or into additional components and "parts" or "modules" Can be further separated.

The spatially relative terms “below”, “beneath”, “lower”, “above”, “upper”, etc., are as shown in the figure. It can be used to easily describe a correlation between a component and other components. Spatially relative terms should be understood as terms including different directions of components in use or operation in addition to the directions shown in the drawings. For example, if a component shown in the drawing is turned over, a component described as "below" or "beneath" of another component will be placed "above" the other component. Can be. Accordingly, the exemplary term “below” can include both the directions below and above. The component can also be oriented in other directions, so that spatially relative terms can be interpreted according to the orientation.

In the present specification, the computer means all kinds of hardware devices including at least one processor, and may be understood as a meaning encompassing software configurations operating in the corresponding hardware device according to embodiments. For example, a computer may be understood as meaning including, but not limited to, a smart phone, a tablet PC, a desktop, a laptop, and a user client and application running on each device.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

1 is a view showing an example of the appearance of a dishwasher according to an embodiment of the present invention.

Dishwasher 100 according to an embodiment of the present invention may be configured to include a housing 10 as shown in FIG. The housing 10 may have a shape similar to a sink, for example, and may include a shape of a water tank and a leg supporting the water tank.

In addition, the dishwasher 100 may include a display unit 140 that displays an operation state of the dishwasher and user input information on one surface. In addition, the dishwasher 100 may include an input unit 130 including at least one key for receiving user input on one surface. The key of the input unit 130 may receive a user input required to control the dishwasher.

2 is a diagram illustrating a network structure of a dishwasher according to an embodiment of the present invention.

The dishwasher 100 according to an embodiment of the present invention may perform communication with the user device 200 and the server 300 as illustrated in FIG. 2 to perform artificial intelligence-based operation control.

According to an embodiment, the dishwasher 100 may collect AI analysis data, which is information required to perform an AI-based analysis operation, and transmit it to the server 300. For example, the dishwasher 100 may transmit situation data such as image information of the washing water obtained through the image sensor and the degree of contamination of the washing water obtained through the turbidity sensor to the server 300. In addition, the dishwasher 100 may acquire driving data related to time information required during the washing operation of the dishwasher, a selected washing mode, and the like, and transmit it to the server 300.

The server 300 may perform AI calculation based on AI analysis data obtained from the dishwasher 100. The dishwasher 100 may obtain an AI calculation result from the server 300 and perform a washing operation applying the result value. For example, the dishwasher 100 may calculate the most suitable washing mode corresponding to the current washing situation (type of washing, contamination level of washing, etc.) as a result of AI calculation from the server 300, and correspondingly, the dish washing machine 100 may It can operate in the calculated washing mode.

In addition, the dishwasher 100 may receive information on the parts replacement timing, failure diagnosis, and the like, which are the result of AI calculation, from the server 300, and control the information to be displayed on the display unit.

In addition, the server 300 may provide the result of the AI operation to the user device 200 connected to the dishwasher 100, so that the user device 200 can check the result value.

An application for controlling the operation of the dishwasher 100 may be installed on the user device 200. The application may support remote control of the washing operation of the dishwasher 100, AI analysis result display, and the like. The user device 200 may also communicate with the server 300 through the application, and may provide driving data set by the user through the application (eg, washing reservation time, set washing mode type, etc.) to the server 300.

According to various embodiments, the application may automatically receive a repair request to a service center when a repair is required as a result of a failure diagnosis by AI. Alternatively, the application may perform a subsequent operation for AI diagnosis corresponding to this as well.

The following will briefly describe artificial intelligence (AI), which is the basis of the analysis operation performed by the server 300.

Artificial intelligence (AI) is a field of computer science and information technology that studies how computers can do thinking, learning, and self-development that human intelligence can do. It means being able to imitate behavior.

In addition, artificial intelligence does not exist by itself, but has many connections directly or indirectly with other fields of computer science. In particular, in recent years, attempts have been made to actively utilize artificial intelligence elements in various fields of information technology to solve problems in those fields.

Machine learning is a field of artificial intelligence that is a research field that gives computers the ability to learn without explicit programming. Specifically, machine learning can be said to be a technology that studies and builds systems and algorithms for learning and performing predictions based on empirical data and improving one's own performance. Rather than performing strictly defined static program instructions, machine learning algorithms take the form of building a specific model to make predictions or decisions based on input data.

The term'machine learning' can be used interchangeably with the term'machine learning'. On how to classify data in machine learning, many machine learning algorithms have been developed. Decision trees, Bayesian networks, support vector machines (SVMs), and artificial neural networks (ANNs) are typical examples.

Decision trees are an analysis method that performs classification and prediction by charting decision rules in a tree structure. The Bayesian network is a model that expresses the probabilistic relationship (conditional independence) between multiple variables in a graph structure. Bayesian networks are suitable for data mining through unsupervised learning. The support vector machine is a model of supervised learning for pattern recognition and data analysis, and is mainly used for classification and regression analysis.

Artificial neural networks are models of biological neurons' operation principles and connections between neurons, and are information processing systems in which a number of neurons, called nodes or processing elements, are connected in the form of a layer structure.

Artificial neural networks are models used in machine learning and are statistical learning algorithms inspired by the neural networks of biology (especially the brain of the animal's central nervous system) in machine learning and cognitive science. Specifically, the artificial neural network may refer to an overall model having a problem solving ability by changing the strength of synaptic binding through learning of artificial neurons (nodes) that have formed a network through the combination of synapses. The term artificial neural network may be used interchangeably with the term neural network.

The artificial neural network may include a plurality of layers, and each of the layers may include a plurality of neurons. Also, the artificial neural network may include neurons and synapses connecting neurons. Artificial neural networks generally have the following three factors: (1) the connection pattern between neurons in different layers (2) the learning process of updating the weight of the connection (3) the weighted sum of the inputs received from the previous layer and the output value It can be defined by an activation function that generates.

The artificial neural network may include network models such as Deep Neural Network (DNN), Recurrent Neural Network (RNN), Bidirectional Recurrent Deep Neural Network (BRDNN), Multilayer Perceptron (MLP), and Convolutional Neural Network (CNN). , But is not limited to this.

The term'layer' can be used interchangeably with the term'layer'.

Artificial neural networks are divided into single-layer neural networks and multi-layer neural networks according to the number of layers.

A typical single layer neural network is composed of an input layer and an output layer.

In addition, the general multi-layer neural network is composed of an input layer, a hidden layer, and an output layer.

The input layer is a layer that accepts external data, the number of neurons in the input layer is the same as the number of input variables, and the hidden layer is located between the input layer and the output layer, receives signals from the input layer, extracts characteristics, and delivers it to the output layer do. The output layer receives a signal from the hidden layer and outputs it to the outside. The input signal between neurons is multiplied and multiplied by each connection strength having a value between 0 and 1, and when this sum is greater than the threshold value of the neuron, the neuron is activated and implemented as an output value through an activation function.

Meanwhile, the deep neural network including a plurality of hidden layers between the input layer and the output layer may be a representative artificial neural network that implements deep learning, which is a kind of machine learning technology.

Meanwhile, the term “deep learning” may be used interchangeably with the term “deep learning”. The artificial neural network can be trained using training data. Here, learning refers to a process of determining parameters of an artificial neural network using learning data in order to achieve the purpose of classifying, regressing, or clustering input data. Can be. Representative examples of the parameters of the artificial neural network include a weight applied to a synapse or a bias applied to a neuron.

The artificial neural network learned by the training data may classify or cluster the input data according to a pattern of the input data.

Hereinafter, each component of the dishwasher will be described in more detail.

3 is a view showing the configuration of a dishwasher according to an embodiment of the present invention.

As shown in FIG. 3, the dishwasher 100 according to an embodiment of the present invention may include a communication unit 110, a storage unit 120, an input unit 130, a display unit 140, a sensor unit 150, a washing module 160, and a control unit 170. In addition, the control unit 170 may include a washing control unit 171 and an AI support unit 172.

The communication unit 110 includes a communication circuit for performing wired or wireless communication, and may perform wired or wireless communication with the server 100. Furthermore, the communication unit 110 may communicate with the user device 200.

The storage unit 120 may store data supporting various functions of the dishwasher. For example, the storage unit 120 may store information related to each washing mode supported by the dishwasher. Each washing mode may be configured with a plurality of washing settings (eg, washing intensity, washing time, washing frequency, etc.).

The input unit 130 is for receiving information from a user, and when information is input from the user, a command corresponding thereto may be transmitted to the control unit 170. The input unit 130 may include mechanical input means (keys, dome switches, etc.) or touch input means. The touch-type input means may be made of virtual keys or soft keys displayed on the touch screen through software processing, or may be made of touch keys disposed on parts other than the touch screen.

The display unit 140 may display information processed by the dishwasher 100. For example, the display unit 140 may display execution screen information of an application program driven by the dishwasher, or UI and GUI information according to the execution screen information.

According to an embodiment of the present invention, the display unit 140 may display result information calculated based on AI calculation. Information calculated by the AI operation may include, for example, optimal washing mode information corresponding to the current washing situation, failure diagnosis information, and the like.

The sensor unit 150 may include at least one of an image sensor, a temperature sensor, a turbidity sensor, a residual amount detection sensor, an open/close sensor, a voltage sensor, a current sensor, a flow sensor, and a pressure sensor.

The image sensor may sense image information of the washing water input to the washing tank to determine the quantity of the washing water, the type of the washing water (tableware, food materials) and the degree of contamination of the washing water. In addition, the image sensor may sense an image of the washing water in the washing tank for evaluating the degree of contamination of the washing water in the washing tank. In addition, the image sensor may sense image information of the washing object to determine whether the washing operation is completed.

The temperature sensor and the turbidity sensor may perform a sensing operation to evaluate the state (temperature, turbidity) of the washing water. The remaining amount detection sensor may detect the remaining amount of detergent. In addition, the opening/closing sensor and the flow sensor may perform a sensing operation to determine the supply/reception status of the washing water. In addition, the voltage sensor, the current sensor, and the pressure sensor may perform a sensing operation to determine characteristics of the washing operation (wash strength, output frequency, etc.).

The washing module 160 may perform an actual washing operation, an injection operation, an ultrasonic generation operation, a detergent input operation, and a bubble generation operation, under the control of the control unit.

Although not shown in the drawing, the dishwasher may further include a driving module driven under the control of a control unit in addition to the washing module 160. For example, the dishwasher may further include a drying module that performs a drying function, and a supply and drainage module that performs a water supply and drainage operation.

The control unit 170 may include a washing control unit 171 and an AI support unit 172.

The washing control unit 171 of the control unit 170 may control the overall operation of the dishwasher. Specifically, the washing control unit 171 may acquire sensing information received from the sensor unit, input information received from the input unit, and the like. Furthermore, the washing control unit 171 may acquire information related to an actual driving operation (eg, water supply is started, hot water supply is started, etc.). In addition, the washing control unit 171 may generate a control command based on sensing information or input information received from the user, and transmit the control command to the washing module 160.

In addition, the washing control unit 171 may command a washing operation based on various kinds of washing modes. The washing mode may be a setting value for at least one of washing strength, washing time, and washing frequency. For example, the first washing mode is a mode set with a washing strength of 1 stage, a washing time of 2 stages, a washing frequency of 3 stages, and a second washing mode is a washing strength of 2 stages, a washing time of 2 stages, a washing of 3 stages It may be a mode set by the number of times.

Each washing mode may be selected according to the type of washing material or the user's preference. In addition, each washing mode may be selected by a user's selection, or may be automatically selected according to AI calculation results.

The AI support unit 172 may check the acquisition and extraction conditions of AI analysis data (data acquired from the dishwasher 100 and sent to the server 300), and transmit AI analysis data to the server 300 under condition conditions.

The AI support unit 172 according to an embodiment of the present invention may be configured to include a suitable washing mode setting support unit for supporting a suitable washing mode setting and a failure diagnosis support unit using an AI operation function to perform a failure diagnosis of the dishwasher.

The suitable washing mode setting support unit and the failure diagnosis support unit may classify items that can be analyzed without AI intervention and analysis items that require AI intervention, respectively. In addition, the appropriate washing mode setting support unit and the failure diagnosis support unit may request the washing control unit 171 to perform an analysis operation on items that can be analyzed without AI intervention.

Accordingly, the washing control unit 171 may perform a self-analysis operation for each of a suitable washing mode setting field and a fault diagnosis field.

First, in the field of setting a suitable washing mode, the washing control unit 171 may perform a self-analysis operation as follows.

The washing control unit 171 may calculate output data (eg, driving data) matching 1:1 with input data (eg, sensing data, input data) based on information in a table format previously stored in the storage unit 120. . For example, the dishwasher may be set to start a washing operation when the weight of the washing water contained in the washing tank reaches a preset value. In this case, the washing control unit 171 may calculate whether to start a washing operation (output data) corresponding to the weight of the washing object (input data).

In addition, in the field of failure diagnosis, the washing control unit 171 may perform a self-analysis operation as follows.

When the self-analysis of the fault diagnosis, the washing control unit 171 may determine the type of fault corresponding to the current situation according to table information pre-stored in the storage unit. In this case, the table information may refer to data listing the dishwasher symptom and the name of the failure corresponding to the symptom or the error code 1:1.

That is, when the corresponding function does not operate in response to the driving command, the washing control unit 171 may perform a self-analysis operation for determining whether the function has failed and calculating a code name indicating the type of the corresponding failure. .

On the other hand, in the case of an analysis item requiring AI intervention, AI support unit 172 (suitable washing mode setting unit, failure diagnosis support unit) collects data for AI analysis and transmits it to server 300, and may request AI analysis operation from server 300. .

The AI support unit 172 may determine a condition situation in which an AI operation is requested, and selectively obtain AI analysis data under the condition condition. Thereafter, the AI support unit 172 may transmit the acquired AI analysis data to the server 300 and receive the result of the AI operation of the server 300. The result value of the AI operation received from the server 300 to the dishwasher 100 side is applied by the washing control unit 171, and a washing operation or a trouble shooting operation corresponding to the result value may be performed.

In addition, at this time, the AI support unit 172 (suitable washing mode setting support unit, failure diagnosis support unit) can commonly determine whether it is a condition situation (AI analysis request situation) capable of acquiring AI analysis data. Can be based on the results of its own analysis. For example, if the dishwasher has four types of error codes that can be determined by self-analysis, a, b, c, and d, the AI support unit 172 (fault diagnosis support unit) has one specific error code a Only the AI analysis request situation can be judged. In addition, the server 300 may perform specification (eg, a1, a2, a3) of the error code a through an AI-based analysis operation. Hereinafter, an error code calculated by self-analysis will be referred to as a primary error code, and an error code calculated based on AI analysis will be referred to as a secondary error code.

The operation of the AI support unit 172 requesting the AI operation to the server 300 is specifically as follows.

First, among the AI support units 172, a suitable washing mode setting support unit is used for AI analysis under condition conditions (for example, when a washing material is added during washing operation, the degree of contamination and quantity of washing water is greater than or equal to a reference value) Data can be acquired and transmitted to the server 300. As the server 300 performs AI calculation, it is possible to calculate an optimal washing mode corresponding to the washing situation (type of washing, amount of washing, contamination of the washing, etc.). And accordingly, the suitable washing mode setting support unit may receive the AI calculation result value calculated by the server 300, and transmit a signal corresponding to the received AI calculation result value (suitable washing mode) to the washing control unit 171. Accordingly, the washing control unit 171 may apply a suitable washing mode calculated as a result of AI calculation, and perform a function corresponding to the washing mode.

In addition, the failure diagnosis support unit of the AI support unit 172 may request the AI server 300 and the result values of the AI calculation to solve the failure symptoms occurring in the dishwasher.

Likewise, the failure diagnosis support unit may also determine whether an AI analysis request situation exists, and if it is determined to correspond to an AI analysis request situation (conditional situation), AI analysis data may be acquired and transmitted to the server 300.

The server 300 may input current symptom information based on an artificial intelligence algorithm, and calculate a result value (eg, a solution to a failure, a preventive measure) based on this, and display the result on the display unit or transmit it to the user device 200.

According to various embodiments of the present disclosure, when it is determined that a corresponding failure is a failure that cannot be solved by a user as a result of AI analysis of the server 300, the failure diagnosis support unit may assist the service center to request a repair through the user device 200. . According to various embodiments of the present disclosure, the server 300 may support remote communication by matching a pre-registered repair technician with a user device 200.

Hereinafter, the components of the server and their operation will be described.

4 is a diagram showing the configuration of a server according to an embodiment of the present invention.

As illustrated in FIG. 4, the server 300 according to an embodiment of the present invention may include a data classification unit 301 and an AI operation unit 302. Although not shown in the drawings, the server 300 may be configured to include a dishwasher and a communication module that can communicate with the user device 200. In addition, although omitted in the drawings, the server 300 may further include an AI algorithm model and a storage unit for storing AI analysis data received from the dishwasher 100 and the user device 200.

According to an embodiment of the present invention, the server 300 may obtain AI analysis data from the dishwasher 100 and the user device 200, classify the acquired AI analysis data, and then perform an AI analysis operation. The operation of classifying the acquired AI analysis data according to the category may be performed by the data classification unit 301 of the server 300, and the AI analysis operation may be performed by the AI operation unit 302.

First, the data classification unit 301 may perform a primary classification operation to classify data into categories related to setting a suitable washing mode and categories related to failure diagnosis.

First, the data classification unit 301 may classify AI data received in a situation where a failure is suspected into an AI-based failure diagnosis category. According to an embodiment, the data for AI analysis in a situation in which a failure is suspected may include a separate code (eg, a primary error code calculated as a result of self-analysis), and accordingly, the data classification unit 301 is a code You can perform category classification based on people. When the received AI analysis data does not include a primary error code or a different type of code from the primary error code, the data classification unit 301 may classify it as a category for setting a suitable washing mode. .

Furthermore, after the primary classification operation, the data classification unit 301 may perform a secondary classification operation for extracting individual input data to be input to an AI computation model among data items included in each category. For example, when the data classification unit 301 intends to calculate a suitable washing mode, it is determined by the type of washing material (which may be determined as a washing image) and the number of washing substances (weight data, the washing image dropped on the washing tank). May be performed), and a second classification operation for extracting the degree of contamination of the washing water (the turbidity of the washing water detected by the turbidity sensor and the image of the washing water) may be performed. For reference, the data classification unit 301 performs a pre-processing operation for determining the type information of the washing water from the washing image before the second sorting operation or the first sorting operation, or calculating the degree of contamination of the washing water based on the sensing value of the turbidity sensor. It can be done additionally.

In addition, the data classification unit 301 may perform a second classification operation for diagnosing a failure. Data classified into a fault diagnosis category by the first sorting operation may also be extracted as individual input data to be input to the AI calculation model, for example, the driving frequency, the setting value of the sudden multiple, and sensing information of the sensing unit during the washing operation. Field (washing tank situation information, washing water pollution level change information), and the like.

The data classification unit 301 may provide data items extracted by the two-character classification operation to the AI operation unit 302.

Hereinafter, the AI operation unit 302 will be described.

The AI operation unit 302 may input the acquired data items as input data to the AI model to perform AI learning and output data calculation operations.

The AI model utilized by the AI operation unit 302 may be information stored in a database for supervised or unsupervised learning, data mining, predictive analysis, or output of data for use in other machines.

The AI operation unit 302 may use any of various types of data analysis algorithms and machine learning algorithms.

Examples of such algorithms include k-recent neighbor systems, fuzzy logic (e.g., probability theory), neural networks, Boltzmann machines, vector quantization, pulse neural networks, support vector machines, maximum margin classifier, hill climbing, inductive logic system Bayesian network, Peritnet (e.g. finite state machine, milli machine, Moore finite state machine), classifier tree (e.g. perceptron tree, support vector tree, Markov tree, decision tree forest, random forest), stake models and systems, artificial fusion , Sensor fusion, image fusion, reinforcement learning, augmented reality, pattern recognition, automated planning, and more.

The AI operation unit 302 may perform various functions for implementing intelligent emulation (ie, a knowledge-based system, a reasoning system, and a knowledge acquisition system). It can be applied to various types of systems (eg, fuzzy logic systems), including adaptive systems, machine learning systems, artificial neural networks, and the like.

The AI operation unit 302 may also perform operations involving speech and natural language speech processing, such as an I/O processing module, an environmental condition module, a speech-text (STT) processing module, a natural language processing module, a work flow processing module, and a service processing module. It may include a sub-module to enable.

Each of these sub-modules can have access to one or more systems or data and models at the server, or a subset or superset thereof. In addition, each of these sub-modules can provide various functions, including vocabulary index, user data, work flow model, service model, and automatic speech recognition (ASR) system.

The AI operation unit 302 according to an embodiment of the present invention may perform an AI operation for calculating a suitable washing mode based on an AI model for setting a suitable washing mode, and an AI operation for diagnosing a failure based on the AI model for diagnosing a failure. The AI model is schematically illustrated through FIG. 5.

The AI operation unit 302 according to an embodiment performs artificial intelligence calculation by inputting input data (data items extracted by a secondary classification operation) into the AI model input layer (see the input layer in FIG. 5) for calculating the suitable washing mode. can do. As a result of the AI operation, as shown in FIG. 5, data input to the input layer may be calculated through the output layer through the hidden layer. That is, the AI operation unit 302 may output information regarding an optimal washing mode based on input data, such as the type of washing, the amount of washing, and the degree of contamination of the washing.

In addition, the AI operation unit 302 may accumulate and perform AI learning through a backpropagation operation. The initial AI model is the result of learning by designating the input layer input data (wash type, amount of wash water, pollution level of wash water, etc.) and the corresponding output layer data (suitable washing mode) based on the preset data set. You can.

The AI operation unit 302 may perform additional learning on the AI model through the acquired data. The AI calculator 302 may calculate a parameter value required to output data set in the output layer from data input to the input layer, and update the AI model with the calculated parameter value. At this time, the activation function applied to the AI model may include sigmoid, ReLU, etc., and may be implemented in other types.

According to another embodiment, the AI operation unit 302 may similarly perform a fault diagnosis through AI operation. Input data including at least one of a driving frequency, a sudden drainage set value, and sensing information of a sensing unit (washing bath condition information, washing water pollution level change information) may be input to the input layer of the AI model for fault diagnosis. At this time, it is obvious that the AI model for calculating the suitable washing mode setting and the AI model for diagnosing the failure are different types of models, and each AI model includes components such as an activation function, the number of input items of data, and learning speed. Can be set differently. The AI calculator 302 may input input data to the input layer of the AI model for fault diagnosis, and then perform AI calculation to output information on the type and cause of the fault.

In addition, the AI operation unit 302 may additionally train the AI model for fault diagnosis, similar to the AI model for calculating the suitable washing mode. In this learning process, the AI operation unit 302 may calculate and update parameter values required to be calculated from data input to the input layer to data set in the output layer. At this time, the activation function applied to the AI model may include sigmoid, ReLU, etc., and may be implemented in other types.

Although the present invention has been described in detail with reference to the above-mentioned examples, those skilled in the art can make modifications, alterations and modifications to the examples without departing from the scope of the present invention. In short, in order to achieve the intended effect of the present invention, it is not necessary to separately include all the functional blocks shown in the drawings or to follow all the order shown in the drawings in the order shown, and even if not, any number of technical aspects of the present invention described in the claims Note that it can fall within the scope.

100: dishwasher
110: communication unit
120: storage unit
130: input unit
140: display unit
150: sensor unit
160: cleaning module
170: control unit
171: washing control
172: AI support department
200: user device
300: server
301: data classification unit
302: AI operation unit

Claims (8)

In the dishwasher communicating with the server and user equipment,
Sensor unit for sensing the state of the washing water and the driving state of the washing function;
An input unit that receives a driving command from a user;
A communication unit that performs wireless communication with the server and user equipment and receives AI analysis results from the server;
A control unit for selecting AI analysis data necessary for AI calculation among data acquired by the sensor unit and the input unit, and controlling the selected AI analysis data to be transmitted to the server under a condition in which AI calculation is required;
A washing module that drives a washing operation under the control of the control unit; And
Includes; display unit for displaying the AI analysis results under the control of the control unit,
The server
1st classification operation to classify the AI analysis data received from the dishwasher into the category for setting the suitable washing mode and the category for diagnosing failure, and 2 to extract the individual input data to be input to the AI calculation model among the data items included in each category. A data classification unit performing a difference classification operation; And
And an AI operation unit that inputs data items extracted by the second classification operation of the data classification unit as input data to an AI model and calculates output data.
According to claim 1,
The control unit
Based on the sensing information and input information received from the user, a control command is generated, the control command is transmitted to the washing module, and when an AI analysis result is received from the server, a washing operation is performed by applying the received AI analysis result. Includes a washing control unit to control to perform;
The washing control unit
The washing operation is commanded based on a number of kinds of washing modes.
The washing mode is a dishwasher, characterized in that at least one set value of the washing intensity, washing time, washing frequency is specified. According to claim 2,
The control unit
Includes an AI support unit that classifies analysis items requiring AI intervention, and analyzes items that do not require AI intervention to be analyzed by the washing control unit.
The washing control unit
Performs self-analysis operation on items that can be analyzed without AI intervention by the AI support unit,
The self-analysis operation is an operation for calculating output data matching 1:1 with input data based on a pre-stored table. According to claim 3,
The AI support department
Dishwasher, characterized in that for determining the analysis items requiring AI intervention, and transmitting AI analysis data for the analysis items requiring AI intervention to the server. The method of claim 4,
The AI support department
A suitable washing mode setting support unit for requesting AI calculation and AI calculation result values to the server to calculate the most suitable washing mode in response to the washing situation of the dishwasher; And
And a fault diagnosis support unit for requesting a result of AI calculation and AI calculation from a server in order to diagnose and solve a malfunction symptom occurring in the dishwasher. According to claim 1,
The sensor unit
In order to determine the quantity of washing water, the type of washing water and the degree of contamination of the washing water, an image sensor for sensing image information of the washing water input to the washing tank, a temperature sensor for evaluating the temperature of the washing water, and a turbidity sensor for evaluating the turbidity of the washing water Dishwasher characterized in that it comprises a delete According to claim 1
The data classification unit
Prior to the second sorting operation, the type information of the washing water is calculated from the washing water image, the weight data of the washing water and the quantity of washing water information is calculated from the washing water image dropped on the washing tank, and the turbidity of the washing water sensed by the turbidity sensor is calculated. And a pre-processing operation for calculating the degree of contamination of the washing water from the washing water image.

Images