Method and system for preventing and predicting failures in robotic furniture

Abstract

One embodiment of the present disclosure provides a method for preventing and predicting failures in robotic furniture, the method including a step of: a server receiving drive history information, including motor drive deterioration data, deviation data, and power data, from the robotic furniture, and storing the information in a database; a step of the server determining a failure symptom based on a predetermined criterion; a step of the server transmitting a failure response message to the user terminal based on the failure symptom or monitoring the robotic furniture; and a step of the server examining the failure symptom after a predetermined time has elapsed, controlling the motor based on the examination result, and predicting a time of failure based on the motor drive deterioration data.

Description

[Technical Field]

[0001] The present invention relates to a method and system for preventing and predicting failures in robotic furniture, and more particularly to a method and system for preventing and predicting failure symptoms in robotic furniture based on an AI model and providing after-sales service following the failure. [Background technology]

[0002] The present invention relates to a method and system for preventing and predicting failures in robotic furniture, and more particularly to a method and system for preventing and predicting failure symptoms in robotic furniture based on an AI model and providing after-sales service in response to the failure.For example, the combined number of one-person and two-person households reaches 64%, while the proportion of four-person families consisting of two parents and two children has decreased significantly.

[0003] As a result, the lifestyle of single-person households is expected to have an impact on society, the economy, culture, and other areas, and changes are needed accordingly.

[0004] However, in the case of a typical home for a single-person household, the number of rooms is limited to one or two, making it difficult to utilize the space in a variety of ways as needed. For example, due to housing costs, many single-person households tend to live in studio apartments rather than two-room apartments, and in order to fit the basic components of a typical living space -- a living room, study, bedroom, kitchen, and laundry room -- into a studio apartment, all furniture except for those used regularly must be pushed into the corners. This means that the average floor area of ​​a home for a single-person household in Korea is so small that it reduces the quality of life.

[0005] Therefore, in order to reduce the area occupied by furniture in living spaces and enable more spacious living spaces, there is a need for research into smart variable furniture systems, including the development of IoT-based smart variable furniture, building automation design technology that provides optimal building design proposals for increasing the number of households that take into account the use of variable furniture, and fault management technology that predicts and responds to malfunctions in variable furniture. Summary of the Invention [Problem to be solved by the invention]

[0006] The present disclosure is intended to solve the problems of the conventional technology described above, and aims to provide a method and system for preventing and predicting signs of failure in robotic furniture based on an AI model and providing after-sales service in the event of a failure.

[0007] The technical object to be achieved by the present invention is not limited to the above-mentioned technical object, and other technical objects of the present invention can be derived from the following description. [Means for solving the problem]

[0008] As a technical means for solving the above-mentioned technical problems, an embodiment according to a first aspect of the present disclosure provides a method for preventing and predicting failures in robotic furniture. This method includes the steps of: a server receiving drive history information, including motor drive deterioration data, deviation data, and power data, from the robotic furniture, storing the information in a database, and determining signs of failure based on preset criteria; the server sending a failure response message to the user terminal based on the signs of failure or monitoring the robotic furniture; and the server examining the signs of failure after a preset time has elapsed, controlling the motor based on the examination results, and predicting the time of failure according to the motor drive deterioration data.

[0009] As a technical means for solving the above-mentioned technical problems, an embodiment according to a second aspect of the present disclosure provides a system for preventing and predicting failures of robotic furniture. The system includes a communication module communicatively connected to robotic furniture, a user terminal, and an administrator terminal, at least one processor, and a memory electrically connected to the processor and storing at least one code executed by the processor. The memory stores code that, when executed via the processor, causes the processor to receive and database operation history information, including motor operation deterioration data, deviation data, and power data, from the robotic furniture, determine failure symptoms based on preset criteria, send a failure response message to the user terminal based on the failure symptoms, or monitor the robotic furniture, and further examine the failure symptoms after a preset time has elapsed, control the motor based on the examination results, and predict the time of failure according to the motor operation deterioration data. [Effects of the Invention]

[0010] According to the present invention, it is possible to predict failures of robotic furniture in advance, thereby improving the safety of users.

[0011] According to the present invention, furniture that is not being used can be stored in the ceiling according to the user's needs, and only the necessary furniture can be deployed, thereby creating a space with high concentration.

[0012] Furthermore, according to the present invention, furniture to which IoT and robotics systems are applied can be easily controlled, even if the furniture is too heavy to move directly.

[0013] The effects of the present invention are not limited to those described above, but include all effects that will be understood from the following description. [Brief explanation of the drawings]

[0014] [Figure 1]1 is a diagram illustrating a robotic furniture failure prevention and prediction device, robotic furniture, and a user terminal according to an embodiment of the present invention. [Figure 2] 1 is a diagram illustrating a robotic furniture failure prevention and prediction device, robotic furniture, and a user terminal according to an embodiment of the present invention. [Figure 3] 2 is a diagram showing an example of a detailed configuration of the failure prevention and prediction device for robotic furniture shown in FIG. 1. FIG. [Figure 4] 1A to 1C are diagrams illustrating design examples of robotic furniture according to an embodiment of the present invention. [Figure 5] 1A to 1C are diagrams illustrating design examples of robotic furniture according to an embodiment of the present invention. [Figure 6] 1A to 1C are diagrams illustrating design examples of robotic furniture according to an embodiment of the present invention. [Figure 7] 1A to 1C are diagrams illustrating design examples of robotic furniture according to an embodiment of the present invention. [Figure 8] 1A to 1C are diagrams illustrating design examples of robotic furniture according to an embodiment of the present invention. [Figure 9] 1A to 1C are diagrams illustrating design examples of robotic furniture according to an embodiment of the present invention. [Figure 10] 10A and 10B are diagrams illustrating a method for preventing and predicting failures in robotic furniture according to another embodiment of the present invention. [Figure 11] 10A and 10B are diagrams illustrating detailed steps of a method for preventing and predicting failures in robotic furniture according to another embodiment of the present invention. [Figure 12] 10A and 10B are diagrams illustrating detailed steps of a method for preventing and predicting failures in robotic furniture according to another embodiment of the present invention. [Figure 13] 10A and 10B are diagrams illustrating detailed steps of a method for preventing and predicting failures in robotic furniture according to another embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0015] The present disclosure will be described in detail below with reference to the accompanying drawings. However, the present disclosure can be implemented in various different forms and is not limited to the embodiments described herein. Furthermore, the accompanying drawings are intended to facilitate understanding of the embodiments disclosed herein and are not intended to limit the technical ideas disclosed herein. All terms, including technical and scientific terms, used herein should be interpreted based on the meanings commonly understood by those of ordinary skill in the art to which the present disclosure belongs. Predefined terms should be interpreted as having additional meanings consistent with the relevant technical literature and the content of the present disclosure, and should not be interpreted in an extremely ideal or restrictive sense unless otherwise defined.

[0016] In order to clearly explain the present disclosure in the drawings, parts that are not relevant to the description are omitted, and the size, shape, and form of each component shown in the drawings may be modified in various ways. The same or similar parts are denoted by the same or similar reference numerals throughout this specification.

[0017] The suffixes "module" and "section" used in the following description for components are given or mixed to facilitate the description of the present specification, and do not have any mutually distinguishing meanings or roles. Furthermore, in describing the embodiments disclosed herein, if a detailed description of related publicly known technology is deemed to obscure the gist of the embodiments disclosed herein, such a detailed description will be omitted.

[0018] Throughout this specification, when a part is described as being "connected (in contact or coupled)" to another part, this includes not only "directly connected (in contact or coupled)" but also "indirectly connected (in contact or coupled)" via another member therebetween. Furthermore, when a part is described as "comprising (having or comprising)" a certain component, it does not mean that it excludes other components, but that it may further "comprise (comprise or comprise)" other components, unless otherwise specified.

[0019] As used herein, ordinal terms such as "first," "second," etc., are used only to distinguish one component from another, and do not limit the order or relationship of the components. For example, a first component of the present disclosure may be referred to as a second component, and similarly, a second component may be referred to as a first component. As used herein, singular terms should be construed as including plural terms unless clearly indicated to the contrary.

[0020] 1 and 2 are diagrams illustrating a robotic furniture failure prevention and prediction device, robotic furniture, and a user terminal according to an embodiment of the present invention.

[0021] Referring to Figures 1 and 2, the robotic furniture failure prevention and prediction device (100) can be communicatively connected to the robotic furniture (200) and the user terminal (300) via a pre-established network.

[0022] The robotic furniture failure prevention and prediction device (100) receives drive history information, including motor drive deterioration data, deviation data, and power data, from the robotic furniture, stores the information in a database, and determines failure signs based on preset criteria. For example, the drive history information may further include information regarding at least one of the robotic furniture's current position, current drive operation, motor speed, and force.

[0023] The robotic furniture failure prevention and prediction device (100) sends a failure response message to a user terminal based on the failure symptom or monitors the robotic furniture. For example, the failure response message can include information on at least one of the cause of the robotic furniture failure, the failure state, and a response method.

[0024] The robotic furniture failure prevention and prediction device (100) examines failure symptoms after a preset time has elapsed, controls the motor based on the examination results, and predicts the time of failure based on the motor's driving deterioration data. For example, the robotic furniture failure prevention and prediction device (100) examines failure symptoms after a predetermined period has elapsed since the sending of a failure response message and monitoring, and if the examination result shows that the failure symptoms have been resolved, it processes the failure prevention as complete, and if the examination result shows that the failure symptoms have not been resolved, it can predict the time of failure and manage a schedule for providing after-sales service.

[0025] The robotics furniture failure prevention and prediction device (100) may be realized in the form of a server, computing device, or various smart devices, and may operate in a cloud computing service model such as SaaS (Software as a Service), PaaS (Platform as a Service), or IaaS (Infrastructure as a Service). The robotics furniture failure prevention and prediction device (100) may also be built in the form of a private cloud, public cloud, or hybrid cloud system, but the scope of the present invention is not limited thereto.

[0026] The robotic furniture failure prevention and prediction device (100) is capable of health prediction and management technology, equipment abnormality detection, pre-failure prediction, and management optimization based on PHM (Prognostics and Health Management). As a result, the robotic furniture failure prevention and prediction device (100) can maximize user safety, minimize after-sales service resources, extend the service life, and reduce environmental impact.

[0027] The robotic furniture failure prevention and prediction device (100) can receive driving history information of the robotic furniture in real time and learn data based on PHM.

[0028] The robotic furniture failure prevention and prediction device (100) can detect failure symptoms based on the learned data, identify parts that are expected to fail, and send them to the administrator terminal (300). Here, the administrator terminal can provide the robotic furniture with pre-failure parts shipping and remote after-sales service (remote AS).

[0029] The robotic furniture failure prevention and prediction device (100) can update the fail-safe algorithm based on the learned data. Here, the fail-safe algorithm can include a malfunction replacement mechanism and a failure replacement mechanism. The fail-safe algorithm can use the malfunction replacement mechanism based on whether or not the mechanism can be modified. For example, if a mechanism modification is not possible, the malfunction replacement mechanism can be used.

[0030] The robotic furniture 200 can transmit drive history information to the robotic furniture failure prevention and prediction device 100. For example, the robotic furniture 200 can provide the robotic furniture failure prevention and prediction device 100 with information on at least one of drive operation, motor speed, force, and drive deterioration.

[0031] The robotic furniture (200) may be a piece of furniture that can be transformed or moved according to a user's settings, such as a vacuum cleaner, a humidifier, a dehumidifier, a washing machine, a desk, a chair, a bed, a dining table, a TV stand, storage, or a sofa.

[0032] The user terminal (300) may be the terminal of a user who intends to operate the robotic furniture, and may receive a fault response message or schedule information for providing after-sales service from the robotic furniture fault prevention and prediction device (100).

[0033] The user terminal (300) may refer to any type of handheld wireless communication device, such as a notebook, desktop, laptop, or portable and mobile wireless communication device equipped with a web browser, or a smartphone, tablet PC, or the like.

[0034] Although not shown, the robotics furniture failure prevention and prediction device (100) can be connected to an administrator terminal via a pre-configured network.

[0035] The administrator terminal may be a terminal of a repair technician or repair shop that provides after-sales service. The administrator terminal may manage an after-sales service schedule based on schedule information received from the user terminal, or may transmit an after-sales service schedule and after-sales service staff information to the user terminal.

[0036] FIG. 3 is a diagram showing an example of a detailed configuration of the failure prevention and prediction device for robotic furniture shown in FIG.

[0037] Referring to FIG. 3, the robotic furniture failure prevention and prediction device (100) may include a communication module (110), a processor (120) and a memory (130).

[0038] The communications module (110) may include a device containing the necessary hardware and software to send and receive signals, such as control or data signals, to other network devices over wired or wireless connections.

[0039] The communication module 110 can receive driving history information from the robotic furniture, and can also send a fault response message or schedule information for providing after-sales service to a user terminal.

[0040] The processor 120 may include various devices that control and process data. The processor 120 may refer to a data processing device built into hardware that has circuits physically configured to execute functions expressed by code or instructions contained in a program.

[0041] As an example, the processor 120 may be implemented in the form of a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or the like, but the scope of the present invention is not limited thereto.

[0042] The processor (120) executes operations according to the code stored in the memory (130).

[0043] The memory (130) may store at least one of information and data input to the communication module (110), information and data required for functions performed by the processor (120), and data generated by the execution of the processor (120).

[0044] The memory 130 should be interpreted as a general term for non-volatile storage devices that retain stored information even when power is not supplied, and volatile storage devices that require power to retain stored information. The memory 130 may include cloud storage, SSD, magnetic storage media, or flash storage media in addition to volatile storage devices that require power to retain stored information, but the scope of the present invention is not limited thereto.

[0045] The memory 130 is electrically connected to the processor 120 and stores at least one code that is executed by the processor 120. The memory 130 stores code that, when executed by the processor 120, causes the processor 120 to perform the following functions and procedures:

[0046] The memory (130) stores code that receives drive history information from the robotic furniture, including motor drive deterioration data, deviation data, and power data, and stores the information in a database, and then determines signs of failure based on preset criteria.

[0047] The memory 130 may store code that functions to receive drive history information corresponding to a predetermined period from the robotic furniture. For example, the memory 130 may store code that functions to collect drive history information from the robotic furniture on a daily basis to detect drive and drive deterioration.

[0048] The memory 130 may store code that extracts vertical and horizontal displacement data of the robotic furniture based on the drive history information and determines signs of a malfunction of the robotic furniture based on the extracted data. For example, the memory 130 may determine that a malfunction has occurred in the robotic furniture due to displacement if the extracted displacement data is equal to or greater than a preset threshold.

[0049] The memory (130) may store code that functions to input drive data of the robotic furniture to be evaluated using an AI model trained to input drive history information including motor drive deterioration data, deviation data, and power data for each of the defective robotic furniture for training and the normal robotic furniture for training as a training data set, and to determine signs of failure of the robotic furniture using an AI model trained to output signs of failure of the robotic furniture.

[0050] The memory (130) may store code that functions to receive vertical and horizontal data of the robotic furniture via a gyro sensor attached to the robotic furniture, compare the vertical angle of the robotic furniture with a preset vertical angle to determine whether or not there is a vertical misalignment, and compare the horizontal angle of the robotic furniture with a preset horizontal angle to determine whether or not there is a horizontal misalignment.

[0051] The memory (130) may store code that functions to determine failure symptoms associated with vertical and horizontal misalignment based on the presence or absence of vertical misalignment and the presence or absence of horizontal misalignment.

[0052] However, without being limited thereto, the memory 130 may store code for determining the degree of vertical misalignment by comparing the vertical angle of the robotic furniture with a preset vertical angle based on the drive history information, and for determining the degree of horizontal misalignment by comparing the horizontal angle of the robotic furniture with a preset horizontal angle. The memory 130 may store code for determining that there is a malfunction symptom when the degree of vertical misalignment and the degree of horizontal misalignment are each equal to or greater than a preset value.

[0053] The memory (130) stores a code that functions to send a failure response message to the user terminal when the deviation data is equal to or greater than a predetermined value, and to determine whether the cause of drive deterioration can be identified when the deviation data is less than the predetermined value, based on the deviation data.

[0054] The memory 130 may store code that allows a user to determine whether the user can solve the problem themselves if the cause of the drive deterioration is identified.

[0055] The memory (130) may store a code that, based on whether or not the cause of the drive deterioration can be identified, monitors the drive of the robotic furniture for a predetermined period of time if the cause of the drive deterioration cannot be identified, and, if the cause of the drive deterioration can be identified, determines whether or not the user can solve the problem themselves.

[0056] For example, the memory 130 may store code that causes the device to send a malfunction response message to the user terminal if the cause of the malfunction can be identified and the user can solve the problem themselves. The memory 130 may also store code that causes the device to monitor the device for a predetermined period of time if the user cannot solve the problem themselves. Here, the predetermined period may be one month.

[0057] The memory 130 may store code that functions to check for signs of a malfunction based on the AI ​​model after a predetermined time has elapsed from at least one of the start of monitoring and the transmission of the malfunction response message. For example, the memory 130 may store code that functions to determine, based on the AI ​​model, whether a problem related to at least one of drive deterioration and misalignment of the robotic furniture has been resolved, and to check for signs of a malfunction of the robotic furniture.

[0058] The memory 130 may store code that functions to control the force and speed of the motor based on the results of the examined fault symptoms. For example, the memory 130 may store code that functions to optimize the motor speed and force of the robotic furniture if the fault symptom problem remains unresolved in order to minimize failures caused by the problem. More specifically, the memory 130 may store code that functions to increase the motor speed and force if deterioration of the equipment parts (increased twisting and movement resistance) occurs to minimize vibration, noise, and sticking during operation.

[0059] The memory (130) may store code that, after controlling the motor force and speed, determines whether the motor's driving deterioration data is within a predetermined range, predicts the time of failure if the motor's driving deterioration data is not within the predetermined range, and determines that failure prevention is complete if the motor's driving deterioration data is within the predetermined range.

[0060] For example, based on an AI model, data on faulty robotics, data on normal robotics, and current robotics data can be compared to predict the time of a future failure. As another example, based on existing failure data stored in a database connected to a server, current operating history information can be compared with existing failure data to predict the time of a future failure. As yet another example, data on faulty robotics, data on normal robotics, and current robotics data can be graphed, and the time of a current robotics failure can be predicted based on the slope of the graph.

[0061] The memory (130) may store code operable to manage a schedule for providing after-sales service based on the predicted time of failure and the presence or absence of failure.

[0062] The memory 130 may store code that functions to determine at least one of the frequency of use and importance of the robotic furniture. For example, the memory 130 may store code that functions to provide a question regarding the frequency of use and importance of use to the user terminal, such as "Is this furniture something you use every day?", quantify the response to the question, and determine that the robotic furniture is important if the quantified response is equal to or greater than a predetermined value.

[0063] The memory (130) may store a code that functions to manage a schedule so that the user can receive after-sales service on the earliest possible schedule when at least one of the frequency of use and importance of the robotic furniture is equal to or greater than a predetermined value.

[0064] For example, memory 130 may store code that functions to receive a schedule available to a user from a user terminal and transmit the schedule to an administrator terminal. Memory 130 may also store code that functions to receive, from the administrator terminal, repair technician information and repair schedule information corresponding to the earliest schedule available to a user and transmit the received repair technician information and repair schedule information to the user terminal.

[0065] As another example, the memory 130 may store code that functions to receive a user schedule available to a user from a user terminal, receive multiple repair technician schedules from an administrator terminal, compare the user schedule with the multiple repair technician schedules, and then transmit repair technician schedule information and repair technician information corresponding to the earliest schedule to the user terminal.

[0066] The memory (130) may store a code that, when the determination result indicates that at least one of the frequency of use and importance of the robotic furniture is below a predetermined value, functions to manage the schedule so that the after-sales service manager provides after-sales service according to a schedule that is feasible for the user among the schedules that are feasible for the after-sales service manager.

[0067] The memory 130 may store code operable to compare the recorded time-save data with the recorded data to extract missing data, and to determine if missing data is extracted as a fault symptom that cannot be resolved by the user, and to determine if torsion and power related fault symptoms are fault symptoms that can be resolved by the user.

[0068] 4 to 8 are diagrams shown to explain a design example of robotic furniture according to an embodiment of the present invention.

[0069] Referring to FIGS. 4 to 8, the robotic furniture may include a mobile bed (Ceily) in the form of vertically variable furniture that can be transformed into at least one of a bed, a desk, and a TV stand using vertically movable rails.

[0070] FIG. 4(a) shows an example of the study mode, FIG. 4(b) shows an example of the living room (TV) mode, and FIG. 4(c) shows an example of the bedroom mode.

[0071] As shown in Figure 5, the drive unit of the mobile bed of the robotic furniture includes drive rails, which can be assembled in one to three pairs. This allows for saving parts and materials. For example, the robotic furniture may include three rails on the front and at least one pair of rails from one to three pairs on the back.

[0072] The drive system of robotic furniture can include one motor, a lead bolt, and an axis that precisely controls linear motion. The motor generates rotational motion, which is converted into vertical motion via a lead bolt and nut and can be connected to each structure. The motor can be connected to each structure and move a fixed group of furniture vertically.

[0073] The motor unit equipped with a sensor can precisely control the rotation speed and speed through a program using a stepping motor or other device, and can be linked to sensors attached to the outside of the robotic furniture, ensuring safety.

[0074] The robotic furniture may include a mobile closet (Wally) that is a horizontally variable furniture type that can be transformed into at least one of an openable shelf type, a clothes rack type, and a study type using horizontally movable rails.

[0075] Figure 6(a) shows an example of an openable shelf type in a closed state, Figure 6(b) shows an example of a wardrobe type including a dressing table, hangers and storage, and Figure 6(c) shows an example of a study type including a work desk, bookshelf and storage.

[0076] As shown in FIG. 7, the drive section of the mobile closet can be the same as or similar to the drive section of the mobile bed shown in FIG.

[0077] The drive unit of the mobile closet may include multiple drive systems, each of which may be composed of a motor, a lead bolt, and an axis that precisely controls linear motion.

[0078] The motor's rotational motion is converted into vertical motion via the lead bolt / nut, allowing the furniture connected to each structure to be moved vertically.

[0079] The motor section equipped with a sensor can precisely control the rotation speed and speed through a program using a stepping motor or the like, and can ensure safety by linking with a sensor attached to the outside of the device.

[0080] Fig. 8(a) shows an example of the living room mode, Fig. 8(b) shows the study mode, and Fig. 8(c) shows the bedroom mode. As shown in Fig. 8, robotic furniture can be designed to have a living room mode, a study mode, and a bedroom mode by combining vertical and horizontal movement.

[0081] As shown in Figure 9, robotic furniture can be designed in a variety of combinations depending on the horizontal and vertical modules. For example, if the first rail of the vertical module is designed as a vertical bed and the third rail as a desk, it can be designed as a form with a structure called Ceily_Double(L).

[0082] FIG. 10 is a diagram illustrating a method for preventing and predicting failures in robotic furniture according to another embodiment of the present invention.

[0083] The method for preventing and predicting failures in robotic furniture described below can be performed by the robotics management control device described above with reference to FIGS. 1 to 9. Therefore, the content related to the embodiments of the present disclosure described above with reference to FIGS. 1 to 9 can also be applied to the embodiments described below. Content that overlaps with the detailed description below will be omitted. The steps described below do not necessarily have to be performed in order, and the order of the steps can be set in various ways, and the steps may even be performed almost simultaneously.

[0084] Referring to FIG. 10, the method for preventing and predicting failures of robotic furniture includes a process for determining failure symptoms of robotic furniture (S100), a process for responding to the failure symptoms (S200), a process for predicting the time of failure (S300), and a process for managing an after-sales service schedule (S400).

[0085] The robotics furniture failure symptom determination process (S100) is a process of receiving drive history information including motor drive deterioration data, deviation data, and power data from the robotics furniture, creating a database, and determining failure symptoms based on preset criteria.

[0086] The robotic furniture failure symptom determination process (S100) may include a process of labeling motor drive deterioration data, deviation data, and power data for each of the defective robotic furniture and the normal robotic furniture, and determining the failure symptoms of the robotic furniture based on an AI model trained to output the failure symptoms of the robotic furniture.

[0087] For example, the process of determining signs of failure of robotic furniture (S100) may include a process of receiving drive history information corresponding to a predetermined period from the robotic furniture, creating a database of the drive history information, and a process of determining signs of failure of the robotic furniture based on deviation data in the vertical and horizontal directions of the robotic furniture and deterioration of the motor's drive based on the drive history information.

[0088] The step of responding in response to the fault symptom (S200) is a step of sending a fault response message to a user terminal or monitoring the robotic furniture based on the fault symptom. For example, the fault symptom may include at least one of twisting, motor overload, motor speed reduction, and motor failure.

[0089] The response process (S200) in response to the failure signs may include a process of inputting the driving data of the robotic furniture to be evaluated using driving history information including motor driving deterioration data, deviation data, and power data for each of the defective robotic furniture for training and the normal robotic furniture for training as a training data set, and determining the failure signs of the robotic furniture using an AI model trained to output the failure signs of the robotic furniture.

[0090] The failure time prediction step (S300) is a step of examining failure symptoms after a predetermined time has elapsed, controlling the motor based on the examination results, and predicting the time of failure based on the driving deterioration data of the motor.

[0091] The after-sales service schedule management step (S400) is a step of managing a schedule for providing after-sales service based on the predicted time of failure and whether or not a failure has occurred. For example, the after-sales service may be the A / S application date.

[0092] 11 to 13 are diagrams illustrating detailed steps of a method for preventing and predicting failures in robotic furniture according to another embodiment of the present invention.

[0093] Referring to FIG. 11, the response process (S200) in response to the failure symptom may include a deviation data determination process (S210), a failure response message transmission process to the user terminal (S220), a determination process of whether the cause of drive deterioration can be identified (S230), a monitoring process for a predetermined period of time (S240), and a self-resolvability determination process (S250).

[0094] The deviation data determination step (S210) may be a step of determining whether the deviation data is equal to or greater than a predetermined value. If the deviation data is equal to or greater than the predetermined value, a failure response message transmission step (S220) to the user terminal may be executed, and if the deviation data is less than the predetermined value, a determination step (S230) as to whether the cause of drive deterioration can be grasped may be executed.

[0095] The step of transmitting a failure response message to the user terminal (S220) may be a step of transmitting a failure response message to the user terminal to adjust the deviation when the deviation data is equal to or greater than a predetermined value.

[0096] The step of determining whether the cause of drive deterioration can be grasped (S230) may be a step of determining whether the cause of drive deterioration can be grasped when the deviation data is less than a predetermined value.

[0097] The step of performing monitoring for a predetermined period (S240) may be a step of monitoring the driving of the robotic furniture for a predetermined period based on whether or not the cause of the driving deterioration can be identified.

[0098] The self-solving possibility determination step (S250) may be a step of transmitting a failure response message to the user terminal based on whether or not the cause of the drive deterioration can be grasped.

[0099] Referring to FIG. 12, the failure time prediction process (S300) may include a process for determining whether or not the failure symptoms of the robotic furniture can be resolved (S310), a failure prevention completion process (S320), a motor speed and force control process for the robotic furniture (S330), a process for determining whether the drive deterioration of the robotic furniture falls within a predetermined range (S340), and a failure time prediction process (S350).

[0100] The step of determining whether the fault symptoms of the robotic furniture have been resolved (S310) may be a step of examining the fault symptoms of the robotic furniture and determining whether the problems of twisting and drive deterioration have been resolved. If the fault symptoms have been resolved in the step of determining whether the fault symptoms of the robotic furniture have been resolved (S310), the step of completing the fault prevention (S320) may be executed, and if the fault symptoms have not been resolved, the step of controlling the motor speed and force (S330) of the robotic furniture may be executed.

[0101] The process of determining whether the failure symptoms of the robotic furniture have been resolved (S310) may include a process of determining whether the failure symptoms of the robotic furniture have been resolved, a process of controlling the motor speed and force of the robotic furniture based on the determination result, and a process of determining whether the drive deterioration of the robotic furniture falls within a predetermined range and examining the failure symptoms of the robotic furniture.

[0102] The failure prevention completion step (S320) may be a step of determining that failure prevention is complete when the failure symptom has been eliminated.

[0103] The step of controlling the motor speed and force of the robotic furniture (S330) may be a step of controlling the motor speed and force of the robotic furniture based on the determination result.

[0104] The step of determining whether the driving deterioration of the robotic furniture falls within a predetermined range (S340) may be a step of determining whether the driving deterioration of the robotic furniture falls within a predetermined range and examining signs of failure of the robotic furniture. If the driving deterioration of the robotic furniture falls within the predetermined range, a step of predicting the time of failure (S350) may be executed, and if the driving deterioration of the robotic furniture does not fall within the predetermined range, an after-sales service schedule management step (S400) may be executed.

[0105] The failure time prediction step (S350) may be a step of predicting the failure time based on the results of the examined failure symptoms.

[0106] Referring to FIG. 13, the after-sales service schedule management process (S400) may include a process for determining the frequency and importance of use of robotic furniture (S410), a process for providing after-sales service based on the user schedule (S420), and a process for providing after-sales service based on the manager's and user schedules (S430).

[0107] The step of determining the frequency of use and importance of the robotic furniture (S410) may be a step of determining whether the frequency of use and importance of the robotic furniture are equal to or greater than a predetermined value. For example, the frequency of use and importance of the robotic furniture may be determined by providing the user with questions that can ascertain the frequency of use and importance of the robotic furniture, and the frequency of use and importance may be determined based on the user's response.

[0108] If the frequency of use and importance are equal to or greater than a predetermined value, an after-sales service provision process (S420) based on the user schedule can be executed, and if the frequency of use and importance are less than the predetermined value, an after-sales service provision process (S430) based on the administrator and user schedule can be executed.

[0109] The after-sales service providing process (S420) based on the user schedule may be a process of assigning a manager to manage the schedule so that after-sales service can be provided on the earliest possible schedule, since after-sales service should be given priority due to high frequency of use and importance.

[0110] The process of providing after-sales service based on the manager and user schedule (S430) may be a process of managing the schedule so that the manager who provides the after-sales service adjusts the schedule available to the user from among the schedules available to the manager who provides the after-sales service and provides the after-sales service.

[0111] Those skilled in the art to which the present disclosure pertains will understand that the present disclosure can be easily modified into other specific forms based on the above description without changing the technical idea or essential characteristics of the present disclosure. Therefore, the above-described embodiments are illustrative in all respects and should not be understood as limiting. The scope of the present disclosure is defined by the claims set forth below, and all modifications and variations derived from the meaning and scope of the claims and their equivalents should be interpreted as being included within the scope of the present disclosure. The scope of the present application is defined by the claims set forth below rather than the above detailed description, and all modifications and variations derived from the meaning and scope of the claims and their equivalents should be interpreted as being included within the scope of the present application.

[0112] [Embodiment] The mode for carrying out the present invention is substantially the same as the best mode for carrying out the invention described above. [Industrial Applicability]

[0113] The present invention can be used in a technology for preventing and predicting failure symptoms of robotic furniture based on an AI model, and therefore has industrial applicability.

Claims

1. A method for preventing and predicting failures of robotic furniture through a communication connection between the robotic furniture, a user terminal, and a server, comprising: a) the server receives drive history information including motor drive deterioration data, deviation data, and power data from the robotic furniture, stores the information in a database, and determines signs of failure based on preset criteria; b) the server sends a fault response message to the user terminal based on the fault symptom or performs monitoring on the robotic furniture; and c) the server examines the failure symptoms after a predetermined time has elapsed, controls the motor based on the examination results, and predicts the time of failure based on the driving deterioration data of the motor; A method for preventing and predicting failures in robotic furniture, comprising:

2. 10. The method of claim 1, The step a) comprises: a-1) receiving the operation history information corresponding to a predetermined period from the robotic furniture and creating a database of the operation history information; and a-2) A method for preventing and predicting failures in robotic furniture, comprising the steps of: determining deviation data in the vertical and horizontal directions of the robotic furniture based on the drive history information; and determining signs of failure of the robotic furniture based on drive deterioration of the motor.

3. 3. The method of claim 2, The step a-2) is A method for preventing and predicting failures in robotic furniture, comprising the steps of: inputting drive data of the robotic furniture to be evaluated, using drive history information including drive deterioration data, deviation data, and power data of the motor for each of a defective robotic furniture for training and a normal robotic furniture for training as a training data set, and determining signs of failure of the robotic furniture using an AI model trained to output signs of failure in the robotic furniture.

4. 10. The method of claim 1, The step b) comprises: A method for preventing and predicting failures in robotic furniture, comprising the steps of: sending a failure response message to the user terminal based on the deviation data if the deviation data is equal to or greater than a predetermined value; and determining whether the cause of drive deterioration can be identified if the deviation data is less than the predetermined value.

5. 10. The method of claim 1, The step b) comprises: A method for preventing and predicting failures in robotic furniture, comprising the steps of: based on whether the cause of the drive deterioration can be identified, performing drive monitoring of the robotic furniture for a predetermined period if the cause of the drive deterioration cannot be identified; and, if the cause of the drive deterioration can be identified, sending a failure response message corresponding to the cause of the drive deterioration to the user terminal.

6. 4. The method of claim 3, The step c) c-1) a step in which the server examines the failure symptoms of the robotic furniture based on the AI ​​model; c-2) controlling the force and speed of the motor based on the results of the failure symptoms examined; and c-3) A method for preventing and predicting failures in robotic furniture, characterized by including the steps of: determining whether the motor's drive deterioration data is within a predetermined range after control; predicting the time of failure if it is not within the predetermined range; and determining that failure prevention is complete if the drive deterioration of the robotic furniture falls within the predetermined range.

7. 10. The method of claim 1, d) a step of managing a schedule for providing after-sales service based on the predicted time of failure and whether or not a failure has occurred.

8. 8. The method of claim 7, The step d) is d-1) determining at least one of the frequency of use and importance of the robotic furniture; and d-2) A method for preventing and predicting failures in robotic furniture, characterized by including the steps of: managing a schedule so that after-sales service is provided on the earliest schedule possible for the user when the judgment result indicates that at least one of the frequency of use and importance of the robotic furniture is equal to or higher than a predetermined score; and managing a schedule so that after-sales service is provided on the schedule possible for the user when the judgment result indicates that the frequency of use and importance of the robotic furniture is lower than the predetermined score.

9. a communication module that is communicatively connected to the robotic furniture, the user terminal, and the administrator terminal; at least one processor; and a memory electrically connected to the processor and configured to store at least one code executed by the processor; The memory, when executed by the processor, causes the processor to: A robotics furniture failure prevention and prediction system characterized by receiving drive history information including motor drive deterioration data, deviation data, and power data from the robotics furniture, and storing the information in a database; determining signs of failure based on preset criteria; sending a failure response message to the user terminal based on the signs of failure, or performing monitoring of the robotics furniture; and storing code that functions to examine the signs of failure after a predetermined time has elapsed, control the motor based on the examination results, and predict the time of failure based on the motor drive deterioration data.

10. 10. The system of claim 9, The memory may include: A robotic furniture failure prevention and prediction system characterized by receiving the drive history information corresponding to a predetermined period from the robotic furniture, storing the drive history information in a database, and storing code that functions to determine deviation data in the vertical and horizontal directions of the robotic furniture based on the drive history information, as well as signs of failure of the robotic furniture based on deterioration of the motor's drive.

11. 11. The system of claim 10, The memory stores code that causes the processor to use driving history information, including motor driving deterioration data, deviation data, and power data for each of the defective robotic furniture for training and the normal robotic furniture for training, as a training data set, and to determine signs of failure of the robotic furniture using an AI model that has been trained to input driving data of the robotic furniture to be evaluated and output signs of failure of the robotic furniture.

12. 10. The system of claim 9, The memory stores code that causes the processor to, based on the deviation data, send a fault response message to the user terminal if the deviation data is equal to or greater than a predetermined value, and to determine whether the cause of drive deterioration can be identified if the deviation data is less than the predetermined value.

13. 10. The system of claim 9, The memory stores code that causes the processor to function to include a process of, based on whether the cause of the drive deterioration can be identified, monitoring the drive of the robotic furniture for a predetermined period of time if the cause of the drive deterioration cannot be identified, and, if the cause of the drive deterioration can be identified, sending a failure response message to the user terminal corresponding to the cause of the drive deterioration.

14. 12. The system of claim 11, The memory stores in the processor code that causes the server to examine the signs of failure of the robotic furniture based on the AI ​​model, control at least one of the force and speed of the motor based on the results of the examined signs of failure, determine whether the motor's drive deterioration data is within a predetermined range after control, predict the time of failure if it is not within the predetermined range, and determine that failure prevention is complete if the drive deterioration of the robotic furniture falls within the predetermined range.

15. 10. The system of claim 9, The memory stores code that causes the processor to manage a schedule for providing after-sales service based on the predicted time of failure and the presence or absence of a failure.

16. 16. The system of claim 15, The memory stores code that causes the processor to determine at least one of the frequency of use and importance of the robotic furniture, and if the determination result shows that at least one of the frequency of use and importance of the robotic furniture is equal to or greater than a predetermined score, manage the schedule so that after-sales service is provided on the earliest schedule possible for the user, and if the determination result shows that the frequency of use and importance of the robotic furniture is less than the predetermined score, manage the schedule so that after-sales service is provided on the schedule possible for the user by the after-sales service manager.

Images