KR102422872B1 - AI temperature control system of carbon fiber heating mat - Google Patents

Abstract

An AI temperature adjustment system of a carbon fiber heating mat according to an embodiment of the present invention comprises: a heating mat made by weaving carbon fiber and equipped with a temperature sensor; a temperature adjustment device that sets a heating temperature of the heating mat to a temperature corresponding to a key operation of a user or a user-customized temperature calculated according to an AI operation, and performs a heating operation at the set temperature; and a user device that calculates the user-customized temperature according to the AI operation, and transmits a heating command to the calculated user-customized temperature to the temperature adjustment device. Therefore, the present invention is capable of enabling a heating step to be adjusted differently.

Description

AI temperature control system of carbon fiber heating mat

The present invention relates to automatically adjusting the temperature of a carbon fiber heating mat based on AI (artificial intelligence).

Recently, the use of heating tools such as heating mats is gradually increasing. Depending on the size of the heating mat, there are heating seats for vehicles, heating cushions for offices, and heating mats for home use.

While the heating mat is being used in various fields like this, there is a need for a technology for automatically controlling the heating operation according to the usage environment and target of the heating mat. In addition, as the subject of using the heating mat in the home may vary, a technology is required to automatically control the heating operation to a suitable temperature according to the characteristics of the person currently using it. The technology related to this is incomplete.

The present invention automatically adjusts the heating stage to a temperature suitable for the user based on AI in the carbon fiber heating mat so that the user can perform the heating function at the user's preferred heating temperature even if the manual input operation for temperature control is not performed. designed to do

In addition, the present invention is designed to automatically perform the temperature control operation of the heating mat at a suitable heating temperature in response to various environments and various objects of use.

The AI temperature control system of the carbon fiber heating mat according to an embodiment of the present invention is manufactured by weaving carbon fibers and includes a heating mat having a temperature sensor, a temperature corresponding to a user's key operation, or a user-customized temperature calculated according to AI calculation A temperature controller that sets the heating temperature of the heating mat and performs a heating operation at the set temperature, and a user who calculates a user-customized temperature according to an AI operation, and transmits a heating command to the calculated user-customized temperature to the temperature controller It may consist of a device.

The present invention can automatically adjust the heating stage to a temperature suitable for the user based on AI in the carbon fiber heating mat.

According to the present invention, the fever level may be differently adjusted in response to the user's gender and age-specific characteristics.

In the present invention, when the object of use is a companion animal, the heating level can be differently adjusted in response to the cold resistance of the companion animal.

1 is a diagram showing the configuration of an AI thermostat system according to an embodiment of the present invention.
2 is a diagram showing the configuration of a temperature controller according to an embodiment of the present invention.
3 is a diagram illustrating a configuration of a user device according to an embodiment of the present invention.
4 is a diagram for explaining the configuration of a server according to an embodiment of the present invention.
5 is a view for explaining an automatic temperature control operation of the heating mat according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction 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 these embodiments allow the disclosure of the present invention to be complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully inform those skilled in the art 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 the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural, unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Therefore, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

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

As used herein, the term “unit” or “module” refers to a hardware component such as software, FPGA, or ASIC, and “unit” or “module” performs certain roles. However, “part” or “module” is not meant to be limited to software or hardware. A “part” or “module” may be configured to reside on an addressable storage medium or may be configured to reproduce one or more processors. Thus, by way of example, “part” or “module” refers to components such as software components, object-oriented software components, class components and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. Components and functionality provided within “parts” or “modules” may be combined into a smaller number of components and “parts” or “modules” or additional components and “parts” or “modules”. can be further separated.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe the correlation between a component and other components. A spatially relative term should be understood as a term that includes different directions of components during use or operation in addition to the directions shown in the drawings. For example, when a component shown in the drawing is turned over, a component described as “beneath” or “beneath” of another component may be placed “above” of the other component. can Accordingly, the exemplary term “below” may include both directions below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

In the present specification, a user device refers to all types of personalized hardware devices including at least one processor, and may be understood as encompassing a software configuration operating in the corresponding hardware device according to an embodiment. For example, a user device may be understood to include all of a smart phone, a tablet PC, a wearable device, and a user client and an application running in each device, but is not limited thereto.

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

1 is a diagram illustrating the configuration of an AI thermostat system according to an embodiment of the present invention.

1, the AI temperature control system 10 of the carbon fiber heating mat according to the embodiment of the present invention is manufactured by weaving carbon fibers and includes a heating mat 100 having a temperature sensor, and a heating mat ( It may include a temperature controller 200 for receiving the user's operation information for adjusting the temperature of the 100), and controlling the heating operation of the heating mat (100). And the AI temperature control system 10 may be configured to further include a user device 300 and a server 400 that can communicate with the temperature controller 200 in addition to the heating mat 100 and the temperature controller 200 . can

The heating mat 100 may include a sensor (not shown) according to various embodiments, and may sense the current temperature of the heating mat through the sensor. Furthermore, the sensor may include a folding detection sensor for determining whether the heating mat is folded. In addition, the sensor may perform a pressure sensing operation according to various embodiments, and accordingly, the sensor may acquire information on a position in which a user is lying or sitting and a mat contact position required in the present invention.

The temperature controller 200 may set the heating temperature of the heating mat to a temperature corresponding to the user's key operation or a user-customized temperature according to the result of the AI operation received from the user device 300 . And the temperature controller 200 may perform a heating operation at a set temperature.

The user device 300 may calculate a user-customized temperature according to an AI operation, and transmit a heating command to the calculated user-customized temperature to the temperature controller.

The server 400 performs an operation of calculating a user-customized temperature by performing AI learning and AI operation based on the mat use data obtained by the user's use of the heating mat, and this is performed through the user device 300 or directly information on the user-customized temperature calculated by the temperature controller 200 may be transmitted. Accordingly, an in-depth user-customized temperature is calculated at the server 400 level, and a heating operation corresponding to the value may be performed in the heating mat 100 .

A detailed description of each configuration of the AI temperature control system 10 of the carbon fiber heating mat according to an embodiment of the present invention will be described with reference to the following drawings.

2 is a diagram illustrating a configuration of a temperature controller according to an embodiment of the present invention.

As shown in FIG. 2 , the temperature controller 200 according to an embodiment of the present invention may include a communication unit 210 , a storage unit 220 , a key input unit 230 , and a control unit 240 . In addition, the control unit 240 may include a temperature control unit 241 , a mode setting unit 242 , and a state determination unit 243 .

First, the communication unit 210 may support communication with the user device 300 and the server 400 . Specifically, the communication unit 210 may receive information such as a user-customized temperature calculated as a result of an AI operation from the user device 300 . In addition, the communication unit 210 may transmit usage data (eg, temperature control step, number of temperature changes per hour, etc.) generated while the user uses the heating mat 100 to the user device 300 or the server 400 . have.

The storage unit 220 may store basic information required in relation to the control of the heating mat. For example, the storage unit 220 may store information on the heating temperature corresponding to a specific heating stage of the temperature controller 200 . In addition, the storage unit 220 may store information on various heating modes and information meaning various types of sensing values.

The key input unit 230 may provide a button for allowing the temperature controller 200 to receive user's operation information, and may receive the button input and transmit control information corresponding thereto to the control unit 240 .

The control unit 240 may check the command received through the communication unit 210 and the temperature control command received through the key input unit 230 and control the heating mat 100 to perform a corresponding heating operation. .

Specifically, the control unit 240 may include a temperature control unit 241 , a mode setting unit 242 , and a state determination unit 243 .

First, the temperature control unit 241 may control the temperature of the heating mat 100 in response to a command obtained through the communication unit 210 or the user's manipulation of the key input unit 230 .

According to various embodiments, the temperature control unit 241 checks the current temperature of the heating mat 100 in response to a request for automatic setting of the heating temperature from the user, and sets the user-customized temperature to the user device 300 or the server 400 . You can adjust the heating temperature by receiving from According to various embodiments, the temperature control unit 241 automatically performs a heating temperature or a heating step based on the difference between the checked current temperature of the heating mat and a user-customized temperature (eg, a user preference temperature or a user preset initial temperature, etc.) can be adjusted with

The temperature control unit 241 may check whether or not a user's request for automatic heating temperature setting is input through the key input unit 230 according to various embodiments of the present disclosure. ) or through a communication operation with the server 400, it is possible to request to transmit the user-customized temperature calculated by the AI operation. Accordingly, the temperature control unit 241 may set the heating stage based on the user-customized temperature received from the user device 300 and the server 400, and in this case, the heating stage may be a value corresponding to the user-customized temperature one-to-one. , may be a value calculated by combining the user-customized temperature and other condition information (eg, the current mat temperature, the current indoor temperature, etc.).

The mode setting unit 242 may include a mode setting unit that provides a variety of heating modes and generates a heating operation in the heating mode selected by the user. In this case, the heating mode may include a mode for each user and a mode for each use environment.

The user-specific mode may be a mode in which a user-customized temperature calculation method is applied differently for each user account. Also, the user-specific mode may be a mode in which items such as an initial setting temperature and a temperature change period are set differently according to a user account. The user-specific mode may be a mode configured to include different types of setting values for each user account, such as user 1 and user 2, for example. Also, according to various embodiments, the user-specific mode may be classified according to user characteristics. For example, the user-specific mode may be classified according to age characteristics, such as the elderly mode and the child mode.

Also, the user-specific mode may include a companion animal mode. The companion animal mode may be a mode in which a control function by the key input unit is set to stop. Also, the companion animal mode may be a mode in which a suitable heating level is set differently according to the type of companion animal. For example, in the companion animal mode, the system of the present invention determines that the cold resistance is high when the animal has a lot of hair and lives in a cold area, so that the suitable heating level can be set lower than the general level. According to various embodiments, the information on the cold resistance of the animal may be pre-stored in the storage unit.

The mode for each use environment may mean a mode according to a situation in which the heating mat is used and the characteristics of the environment. The mode for each use environment may be configured to include, for example, an indoor mode, a camping mode, a sleep mode, a work mode, a driving mode, and the like. And, the camping mode may be a mode in which a suitable heating temperature is calculated and applied in response to the external temperature, and the heating level is set higher than that of the indoor mode. For example, in the case of the same external temperature of 0 degrees, the suitable temperature is calculated in one step in the indoor mode, but the suitable temperature is adjusted upward in two steps in the camping mode and can be calculated.

In addition, the control unit 240 acquires information about whether the heating mat 100 is folded, whether the heating mat is in contact with the user, and the user's usage posture through the sensor of the heating mat 100, and generates heat based on this. It may include a state determination unit 243 that determines the current state of the mat. According to one embodiment, the edge of the heating mat 100 may be equipped with a sensor that detects that the distance is getting closer, and when the edge part of the mat comes into contact as the folding is made, the sensor detects this and the heating mat is folded can determine whether

In addition, the state determination unit 243 may determine whether or not the heating function is suitable for the implementation of the heating function in response to the determined current state of the heating mat, and as the heating non-suitability determination is made, the temperature control unit 241 may request to stop the heating operation. . Specifically, for example, the heating mat may be set so that the heating operation is not made in the folded state. In this case, the state determination unit 243 may determine whether the heating mat 100 is folded, and if it is determined that the heating mat 100 is in a folded state, it may be determined to be unsuitable for heating accordingly. In addition, the state determination unit 243 may stop the heating operation in the temperature control unit 241 or turn off the power so that the heating operation does not start according to the determination that the heating is not suitable.

In the case of a heating mat woven with carbon fiber, the heat wire that generates heat and the fibers constituting the surface of the mat are not separated, but the surface of the mat is woven with fibers that generate heat. It has the feature of being free to fold. Accordingly, there is a possibility that the carbon fiber heating mat generates heat in the folded state, resulting in overheating than the intended temperature. Therefore, it is possible to determine whether the heating mat is folded in the state determination unit 243 and limit the heating operation in response thereto.

3 is a diagram illustrating a configuration of a user device according to an embodiment of the present invention.

As shown in FIG. 3 , the user device 300 according to an embodiment of the present invention may include a data selection unit 310 , a suitable temperature calculation unit 320 , and a temperature control command unit 330 . .

First, the data selection unit 310 acquires the mat use data including the temperature value and the set temperature change number manually set by the user through the temperature controller, and among the acquired use data for learning that corresponds to the artificial intelligence learning condition data can be selected.

In other words, the data selector 310 may classify and select data necessary for learning the AI algorithm and data that are not. For example, the data selection unit 310 may distinguish the temperature control history data of the registered user, which is data of a preset item for learning the AI algorithm, and the temperature control history data of the non-registered user, which is data for removal.

The data selection unit 310 transmits the data to the server 400 when data of a preset item for learning an artificial intelligence algorithm is collected, and allows the server 400 to learn an artificial intelligence algorithm with the transmitted data. let it be

The server 400 may generate a user-suitable temperature calculation algorithm model as a result of learning the artificial intelligence algorithm.

A detailed description of the server 400 will be described later.

The suitable temperature calculator 320 of the user device 300 may calculate a user-customized temperature for each user account according to the first AI algorithm set based on the app (eg, the heating mat temperature control app). The suitable temperature calculation unit 320 in the user device 300 may calculate the suitable temperature for each user in a relatively simple manner, and thus communication with the server 400 may be omitted.

The suitable temperature calculation unit 320 may first request to create an account for each user in order to calculate the suitable temperature for each user. If the user wants to use the automatic temperature setting function through the app of the user device 300 , the suitable temperature calculating unit 320 determines whether to create a new user account, use an existing user account or a common account set by default You can ask whether When creating a new user account, the suitable temperature calculator 320 may receive information about the user's main preferred temperature, including personal information such as the user's gender and age, in advance, and create an account based on this. . In this case, the suitable temperature calculator 320 may support input of information on a use target when creating a user account, considering the case where the use target is a companion animal rather than a human. The suitable temperature calculation unit 320 may support input of the type of companion animal when the user account is created and the target is not a person.

The suitable temperature calculator 320 may determine whether usage data equal to or greater than the first reference value is obtained when the user account is completed and an automatic temperature setting operation is requested with a specific user account. The use data may refer to mat use data including a heating temperature value (eg, a heating stage) manually set by a user through a temperature controller and the number of times the set temperature is changed. In addition, a case in which usage data equal to or greater than the first reference value is obtained may mean, for example, a case in which the temperature control history is confirmed three or more times. The operation of determining whether usage data equal to or greater than the first reference value is obtained may mean a minimum standard for determining whether a user of a previously created account has a history of using the heating mat.

The suitable temperature calculator 320 may calculate a user-customized temperature based on the first AI algorithm as usage data equal to or greater than the first reference value is obtained for each user's account after the user account creation is completed. In this case, the suitable temperature calculation unit 320 may calculate a user-customized temperature based on the preferred heating information included in the pre-registered user account. It may be information such as the preferred heating temperature registered in the upper body, the user's cold resistance (classified as high, normal, low, etc.).

The temperature control command unit 330 may remotely transmit a temperature control command to the thermostat attached to the mat. At this time, the temperature control command unit 330 may automatically transmit a command signal to the temperature controller 200 according to the calculation of the user-customized temperature, but check the manual temperature control command manually input by the user through the user device And, it can be delivered to the temperature controller 200 side. The temperature control command unit 330 may include a user preset time, a user preset temperature, and a user preset indoor temperature (eg, the current temperature measured through a temperature sensor of the heating mat) according to various embodiments. When the condition is satisfied, the heating operation to a specific temperature may be automatically commanded to the temperature controller 200 .

In addition, the temperature control command unit 330 may transmit a command signal to the temperature controller 200 to set the heating temperature to the user-customized temperature calculated by the suitable temperature calculation unit 320 .

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

As shown in FIG. 4 , the server 400 according to an embodiment of the present invention may include a data recording unit 410 , a data learning unit 420 , and an artificial intelligence operation unit 430 .

The server 400 is a configuration for calculating a user-customized temperature by performing AI learning and AI operation based on the mat use data obtained by the user's use of the heating mat.

The data recording unit 410 may obtain and record the learning data selected from the user device 300 and the mat use data transmitted from the temperature controller 200 . More specifically, the data recording unit 410 may obtain, process, and record the mat use data corresponding to the characteristics of the user registered in the user account. For example, according to the account information, if the characteristics of User 1 are senior citizens in their 70s or older, and the cold resistance is set to low, the data recorder 410 stores the mat use data of User 1 and the characteristics of User 1 (the elderly, cold resistance). low) can be recorded.

The data learning unit 420 may learn the second AI algorithm with the learning data processed and recorded by the data recording unit 410 . Accordingly, the data learning unit 420 may generate an AI model capable of calculating a user-customized temperature in response to various situations.

The artificial intelligence calculating unit 330 may calculate a user-customized temperature based on the second AI algorithm that has been learned by the data learning unit 420 . In this case, the second AI algorithm may perform an operation for calculating the suitable temperature according to the user characteristics included in the user account in various situations. More specifically, for example, the difference between the first AI algorithm and the second AI algorithm will be described as follows.

The first AI algorithm is based on the user's preferred heating information (preferred heating temperature, cold resistance level) registered in the user account, and the appropriate temperature or heating stage corresponding to the current situation (temperature, indoor temperature, mode by use environment, etc.) will yield Since the reference information necessary to calculate the suitable heating temperature is information included in the user account, a separate learning operation of the AI algorithm is not required.

Meanwhile, the second AI algorithm may perform a learning process to calculate a user-customized temperature (suitable temperature) in more diverse situations. As the second AI algorithm is learned by utilizing the user's personal information included in the user account, the calculation can be performed by inputting the user's personal information even when calculating the user-customized temperature. For example, the second AI algorithm may calculate different suitable temperatures for users in their 70s who have low cold resistance and users in their 20s who have high cold resistance in an environment where the external temperature is the same as 0 degrees Celsius. . Furthermore, the second AI algorithm can calculate not only the heating temperature but also the value for the heating temperature change period according to the user characteristics, and accordingly, the method of setting both the initial heating temperature and the heating temperature change period to high values, the initial heating temperature and Various types of heating operation, such as setting all heating temperature change cycles to low values, can help to be automatically performed according to user preference.

5 is a view for explaining the automatic temperature control operation of the heating mat according to an embodiment of the present invention.

As shown in FIG. 5 , the AI temperature control system according to an embodiment of the present invention may calculate a customized heating temperature (heating stage of the mat) in consideration of the current temperature and the degree of the user's preferred temperature. Referring to FIG. 5 , the user's current location is information calculated based on the current location of the user device, and the current temperature of the corresponding location is displayed as in the temperature display window 501 . And correspondingly, the system of the present invention may display through the heating stage display window 502 that the customized heating stage for each user account (user 1) has been calculated as one stage. And according to an embodiment of the present invention, the user device 300 may display the directly applying button 503 of the calculated user's customized heating step on the screen, and when the user selects the apply button 503, it By applying the corresponding calculated user-customized heating step (corresponding to the user-customized temperature), it is possible to control the heating operation of the heating mat to be performed immediately.

As shown in FIG. 5, the AI temperature control system according to an embodiment of the present invention may automatically set the heating stage (heating temperature) in response to the outdoor temperature, but the indoor space may be additionally heated. In consideration of the case, the heating level may be calculated in response to the indoor temperature instead of the outside temperature. In this case, the indoor temperature may be obtained from a pre-interlocked indoor thermometer (eg, a Bluetooth indoor thermometer, a thermometer of an air conditioner, etc.).

In addition, as shown in FIG. 5 , the user-customized temperature may lead to a mat heating operation after the user's apply button operation is performed through a user confirmation process. However, according to various embodiments of the present disclosure, the user device 300 may provide an automatic temperature setting function, and when the user's customized temperature (custom heating step) is calculated in a state where the automatic temperature setting function is applied, the mat heats automatically immediately It may lead to action. And as the conditions such as the current temperature and the current temperature measured on the heating mat change, the user-customized temperature may be changed and calculated. In such a case, the user device 300 automatically applies the changed and calculated user-customized temperature to the heating mat heating operation can be controlled.

In short, the AI temperature control system of the carbon fiber heating mat according to the embodiment of the present invention is produced by weaving carbon fibers and the heating mat having a temperature sensor, the temperature corresponding to the user's key operation, or the user calculated according to the AI operation A temperature controller that sets the heating temperature of the heating mat as a customized temperature and performs a heating operation at the set temperature and calculates a user-customized temperature according to an AI operation, and transmits a heating command to the calculated user-customized temperature to the temperature controller It may be configured to include a user device that does.

In this case, the temperature controller includes a key input unit for receiving a user's key input for controlling the heating operation, and a control unit for controlling a series of operations related to temperature control of the heating mat, wherein the control unit automatically sets the heating temperature from the user In response to this request, a temperature control unit and various heating modes for checking the current temperature of the heating mat and automatically adjusting the heating temperature based on the difference between the user-customized temperature and the checked current temperature are provided, and by the user It may include a mode setting unit for generating a heating operation in the selected heating mode. In this case, the heating mode may include a mode for each user and a mode for each use environment.

In addition, the control unit may include a state determination unit for obtaining information on whether the heating mat is folded, whether the heating mat is in contact with the user, and the user's usage posture, and determines the current state of the heating mat based on this.

In addition, the state determination unit may determine whether or not the heating function is suitable for performing the heating function in response to the determined current state of the heating mat, and may request the temperature controller to stop the heating operation according to the determination of the heating incompatibility.

Also, the user-specific mode may include a companion animal mode, and the companion animal mode may be a mode in which a control function by the key input unit is set to stop.

And the user device acquires the mat use data including the temperature value and the number of set temperature changes that the user manually sets through the temperature controller, and selects learning data corresponding to the artificial intelligence learning condition among the acquired use data A data selection unit, a suitable temperature calculation unit for requesting account creation for each user, and a suitable temperature calculation unit for calculating a user-customized temperature based on the first AI algorithm as usage data above the first reference value is obtained for each created account of each user and the suitable It may be configured to include a temperature control command unit that transmits a command signal to the temperature controller to set the heating temperature to the user-customized temperature calculated by the temperature calculation unit.

AI temperature control system according to an embodiment of the present invention may be configured to further include a server that calculates a user-customized temperature by performing AI learning and AI operation based on the mat use data obtained by the user's use of the heating mat. . At this time, the server acquires and records the selected learning data from the user device and the mat use data transmitted from the temperature controller, and performs learning on the second AI algorithm with the learning data accumulated and recorded in the data recording unit. It may include a data learning unit and an artificial intelligence calculating unit for calculating a user-customized temperature based on the second AI algorithm that has been learned by the data learning unit.

Although not shown in the drawings, the user device 300 according to an embodiment of the present invention may include a memory, a communication module, and a processor.

The memory may store various programs and data necessary for the operation of the server. The memory may be implemented as a non-volatile memory, a volatile memory, a flash-memory, a hard disk drive (HDD), or a solid state drive (SSD).

The communication module may communicate with an external device. In particular, the communication module may include various communication chips such as a Wi-Fi chip, a Bluetooth chip, a wireless communication chip, an NFC chip, a low-power Bluetooth chip (BLE chip), and the like. At this time, the Wi-Fi chip, the Bluetooth chip, and the NFC chip perform communication in a LAN method, a WiFi method, a Bluetooth method, and an NFC method, respectively. In the case of using a Wi-Fi chip or a Bluetooth chip, various types of connection information such as an SSID and a session key are first transmitted and received, and then various types of information can be transmitted and received after communication connection using this. The wireless communication chip refers to a chip that performs communication according to various communication standards, such as IEEE, ZigBee, 3rd Generation (3G), 3rd Generation Partnership Project (3GPP), and Long Term Evolution (LTE).

The processor may control the overall operation of the user device by using various programs stored in the memory. The processor may include a RAM, a ROM, a graphic processing unit, a main CPU, first to n interfaces, and a bus. In this case, the RAM, ROM, graphic processing unit, main CPU, first to n interfaces, etc. may be connected to each other through a bus.

RAM stores O/S and application programs. Specifically, when the server 100 is booted, O/S may be stored in the RAM, and various application data selected by the user may be stored in the RAM.

The ROM stores an instruction set for booting the system, and the like. When a turn-on command is input and power is supplied, the main CPU copies the O/S stored in the memory 110 to the RAM according to the command stored in the ROM, and executes the O/S to boot the system. When booting is completed, the main CPU copies various application programs stored in the memory 110 to the RAM, and executes the application programs copied to the RAM to perform various operations.

The graphic processing unit generates a screen including various objects such as items, images, and texts by using a calculation unit (not shown) and a rendering unit (not shown). Here, the calculating unit may be configured to calculate attribute values such as coordinate values, shape, size, color, etc. of each object to be displayed according to the layout of the screen by using the control command received from the input unit. In addition, the rendering unit may be configured to generate screens of various layouts including objects based on the attribute values calculated by the operation unit. The screen generated by the rendering unit may be displayed in the display area of the display.

The main CPU accesses the memory and performs booting using the OS stored in the memory. In addition, the main CPU performs various operations using various programs, contents, data, etc. stored in the memory.

The first to n interfaces are connected to the various components described above. One of the first to n interfaces may be a network interface connected to an external device through a network.

Meanwhile, further, the processor may control the artificial intelligence model. In this case, of course, the processor may include a graphics-only processor (eg, GPU) for controlling the artificial intelligence model.

Meanwhile, the artificial intelligence model according to the present invention may be a model based on teacher supervised learning or unsupervised learning. Furthermore, the artificial intelligence model according to the present invention may include a support vector machine (SVM), a decision tree, a neural network, and the like, and methodologies to which these are applied.

In one embodiment, the artificial intelligence model according to the present invention may be an artificial intelligence model based on a convolutional deep neural network (CNN) learned by inputting learning data. However, the present invention is not limited thereto, and various artificial intelligence models may be applied to the present invention. For example, a model such as a Deep Neural Network (DNN), a Recurrent Neural Network (RNN), or a Bidirectional Recurrent Deep Neural Network (BRDNN) may be used as the AI model, but is not limited thereto.

In this case, convolutional deep neural networks (CNNs) are a type of multilayer perceptrons designed to use minimal preprocessing. A convolutional neural network consists of one or several convolutional layers and general artificial neural network layers on top of it, and additionally utilizes weights and pooling layers. Thanks to this structure, the convolutional neural network can fully utilize the input data of the two-dimensional structure. In addition, convolutional neural networks can be trained via standard backpropagation. Convolutional neural networks are easier to train than other feed-forward neural network techniques and have the advantage of using fewer parameters.

In addition, deep neural networks (DNNs) are artificial neural networks (ANNs) composed of a plurality of hidden layers between an input layer and an output layer.

In this case, the structure of the deep neural network may be composed of a perceptron. A perceptron consists of several inputs, one processor, and one output value. The processor multiplies each input value by a weight, and then sums the input values multiplied by the weight. Then, the processor outputs one output value by substituting the summed value into the activation function. If a specific value is desired as the output value of the activation function, the weight multiplied by each input value may be corrected, and the output value may be recalculated using the modified weight. In this case, each perceptron may use a different activation function. In addition, each perceptron receives the outputs from the previous layer as input, and then uses the activation function to obtain the output. The obtained output is transferred to the input of the next layer. Through the process as described above, some output values can be finally obtained.

A recursive neural network (RNN) refers to a neural network in which connections between units constituting an artificial neural network constitute a directed cycle. Unlike forward neural networks, recurrent neural networks can utilize the memory inside the neural network to process arbitrary inputs.

Deep Belief Networks (DBN) is a generative graphical model used in machine learning, and in deep learning, it means a deep neural network composed of multiple layers of latent variables. There is a connection between layers, but there is no connection between units within a layer.

The deep trust neural network can be used for prior learning due to the nature of the generative model, and after learning the initial weights through prior learning, the weights can be fine-tuned through backpropagation or other discrimination algorithms. This characteristic is very useful when the training data is small, because the smaller the training data, the stronger the influence of the initial value of the weight on the resulting model. The pre-learned initial weight value is closer to the optimal weight compared to the arbitrarily set initial weight value, which enables performance and speed improvement in the fine-tuning stage.

The above-described artificial intelligence and its learning method have been described for illustrative purposes, and the artificial intelligence and its learning method used in the embodiments described below are not limited. For example, all kinds of artificial intelligence technology and a learning method thereof that a person skilled in the art can apply to solve the same problem may be utilized to implement the system according to the disclosed embodiment.

The processor may include one or more cores (not shown), a graphic processing unit (not shown), and/or a connection path (eg, a bus, etc.) for transmitting and receiving signals to and from other components.

A processor according to an embodiment performs the method described in connection with the present invention by executing one or more instructions stored in a memory.

For example, the processor acquires new training data by executing one or more instructions stored in the memory, performs a test on the acquired new training data using the learned model, and the test result, labeled information Extracting first learning data obtained with an accuracy equal to or greater than a predetermined first reference value, deleting the extracted first learning data from the new learning data, and using the new learning data from which the extracted learning data is deleted The trained model can be retrained.

On the other hand, the processor further adds a RAM (Random Access Memory, not shown) and ROM (Read-Only Memory, not shown) that temporarily and/or permanently store signals (or data) processed inside the processor. may include In addition, the processor 130 may be implemented in the form of a system on chip (SoC) including at least one of a graphic processing unit, a RAM, and a ROM.

The memory may store programs (one or more instructions) for processing and controlling the processor. Programs stored in the memory may be divided into a plurality of modules according to functions.

The steps of a method or algorithm described in relation to an embodiment of the present invention may be implemented directly in hardware, as a software module executed by hardware, or by a combination thereof. A software module may include random access memory (RAM), read only memory (ROM), erasable programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, hard disk, removable disk, CD-ROM, or It may reside in any type of computer-readable recording medium well known in the art to which the present invention pertains.

The components of the present invention may be implemented as a program (or application) to be executed in combination with a computer, which is hardware, and stored in a medium. Components of the present invention may be implemented as software programming or software components, and similarly, embodiments may include various algorithms implemented as data structures, processes, routines, or combinations of other programming constructs, including C, C++ , Java, assembler, etc. may be implemented in a programming or scripting language. Functional aspects may be implemented in an algorithm running on one or more processors.

Although the present invention has been described in detail with reference to the above-described examples, those skilled in the art can make modifications, changes, and modifications to these 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 follow all the orders shown in the drawings. Note that it may fall within the scope.

10: AI temperature control system
100: heating mat
200: thermostat
210: communication department
220: storage
230: key input unit
240: control unit
300: user device
400 : server

Claims (7)

In the AI temperature control system of the carbon fiber heating mat,
a heating mat manufactured by weaving carbon fibers and having a temperature sensor;
a temperature controller that sets the heating temperature of the heating mat to a temperature corresponding to a user's key operation or a user-customized temperature calculated according to AI calculation and performs a heating operation at the set temperature;
a user device that calculates a user-customized temperature according to an AI operation and transmits a heating command to the calculated user-customized temperature to the temperature controller; and
A sensor positioned at the edge of the heating mat to detect contact between the edges of the heating mat as the heating mat is folded.
the temperature controller
a key input unit for receiving a user's key input for controlling the heating operation;
Including; a control unit for controlling a series of operations related to temperature control of the heating mat;
the control unit
a temperature control unit that checks the current temperature of the heating mat in response to a request for automatic setting of the heating temperature from the user, and automatically adjusts the heating temperature based on the difference between the user-customized temperature and the checked current temperature; and
and a mode setting unit that provides a variety of heating modes and generates a heating operation in a heating mode selected by a user.
The heating mode is
Including mode by user and mode by use environment,
the control unit
A state determination unit for obtaining information on whether the heating mat is folded, whether the heating mat is in contact with the user, and the user's posture, and determines the current state of the heating mat based on this;
The state determination unit
In response to the determined current state of the heating mat, it is determined whether the implementation of the heating function is suitable, and as the heating inappropriate determination is made, the temperature control unit is requested to stop the heating operation,
When the state of the heating mat is preset so that the heating operation is not made in the folded state, if the current state of the heating mat determined through the sensor is the folded state, a determination is made as to be unsuitable for heating,
To stop the heating operation, or to control the temperature controller so that the heating operation does not start,
The user device is
A data sorting unit for obtaining mat use data including a temperature value set manually by the user through the temperature controller and the number of set temperature changes, and selecting learning data corresponding to the artificial intelligence learning condition from among the acquired use data; including,
The AI operation is
It is a user-customized temperature based on the mat use data obtained by the user's use of the heating mat, calculated by the user-suited temperature calculation algorithm model,
The user-suited temperature calculation algorithm model is,
AI temperature control system of carbon fiber heating mat, characterized in that it is an artificial intelligence model learned to calculate a user-suitable temperature according to the user's temperature control history based on the learning data selected by the data selection unit. delete delete delete 2. The method of claim 1
The user-specific mode is
Includes pet mode,
AI temperature control system of carbon fiber heating mat, characterized in that the companion animal mode stops the control function by the key input unit. ◈Claim 6 was abandoned when paying the registration fee.◈ The method of claim 1,
The user device is
a suitable temperature calculator for requesting account creation for each user, and calculating a user-customized temperature based on a first AI algorithm as usage data equal to or greater than a first reference value is obtained for each created account of each user; and
a temperature control command unit that remotely controls the temperature control operation of the temperature controller and transmits a command signal to the temperature controller to set the heating temperature to a user-customized temperature calculated by the suitable temperature calculation unit; including,
The first AI algorithm is
Carbon fiber heating, characterized in that it is an algorithm for calculating a suitable temperature corresponding to at least one of the current temperature, the current indoor temperature, and the mode for each current use environment, and the heating level based on the user's preferred heating information registered in the user account Mat's AI temperature control system The method of claim 1,
A server that calculates a user-customized temperature by performing AI learning and AI operation based on the mat use data obtained by the user's use of the heating mat; and
the server is
a data recording unit for acquiring and recording the selected learning data from the user device and the mat use data transmitted from the temperature controller;
a data learning unit for learning a second AI algorithm with the learning data accumulated and recorded in the data recording unit; and
an artificial intelligence calculating unit for calculating a user-customized temperature based on a second AI algorithm that has been learned by the data learning unit; including,
The AI learning is
To learn the user-suited temperature calculation algorithm model for the AI calculation based on the mat use data,
The second AI algorithm,
AI temperature control system of carbon fiber heating mat, characterized in that it is an algorithm learned based on user's personal information to calculate values for suitable temperature and heating temperature change cycle according to the age of the user included in the user account.

Images