WO2020122291A1

WO2020122291A1 - Apparatus and method for automating artificial intelligence-based apartment house management work instructions

Info

Publication number: WO2020122291A1
Application number: PCT/KR2018/015910
Authority: WO
Inventors: 장하니
Original assignee: (주)하니소프트
Priority date: 2018-12-14
Filing date: 2018-12-14
Publication date: 2020-06-18
Also published as: KR20210107042A

Abstract

The present invention relates to an apparatus and a method for automating artificial intelligence-based apartment house management work instructions, the apparatus comprising: an assigned duty identification unit for identifying an assigned duty of a worker when an access request is approved through an apartment house work-performing terminal; a work log repository unit for storing a work log for each assigned duty, having been electronically created by the apartment house work-performing terminal and confirmed by an electronic approval scheme through an apartment house work-managing terminal; a work log machine learning unit for classifying the assigned duty into apartment house situation-based work details through the machine learning of contents of the work log for each assigned duty, thereby generating a plurality of work modules; an apartment house situation-determining unit for determining the current apartment house situation; and a work guide unit for determining at least one apartment house situation work module according to the current apartment house situation from among the plurality of work modules, so as to guide the apartment house work-performing terminal by means of a work checklist.

Description

Artificial Intelligence-based Apartment Housing Management Order Automation Device and Method

The present invention relates to an artificial intelligence-based apartment housing management work order automation technology, and more particularly, to an artificial intelligence-based apartment housing management work order automation device and method capable of providing an automated business guide for apartment housing management. It is about.

Apartment houses such as apartments, villas, tenements, and officetels are inhabited by a large number of people. For example, a complaint related to an apartment house may include complaints related to various inquiries or inconveniences related to living, requests for facility inspection or repair, and various reports and reservations. It is very important to have a system that can effectively handle complaints in multi-unit apartment houses where various complaints occur.

In addition, in the management of multi-family houses, a system that supports business practitioners to perform business effectively is not sufficient to date. Various systems are being developed that can effectively manage MDUs, but interest in systems that can effectively support various management tasks such as building housing management and facilities, landscaping, environmental beautification, and security is increasing. Trend.

Korean Patent Publication No. 10-2000-0036965 (2000.07.05) relates to a method and a recording medium for managing an apartment complex in a computer network system, internal and external tasks and activities of residents of the apartment complex This can be done smoothly, reducing the costs levied on the residents of the apartment complex by performing the joint management step, and improving the quality of community life of the residents of the apartment complex.

Korean Patent Publication No. 10-2000-0009022 (2000.02.15) relates to a computer comprehensive information system in public housing, to establish a common computer communication network in a public housing complex as hubs and routers and manage it in connection with a server computer Thus, the computers of the connected homes, malls, and management offices have disclosed a technique of providing a program having a function of providing various computer communication functions that are useful for living in public housing as well as Internet access.

[Advanced technical literature]

[Patent Document]

(Patent Document 1) Korean Patent Publication No. 10-2000-0036965 (2000.07.05)

(Patent Document 1) Korean Patent Publication No. 10-2000-0009022 (2000.02.15)

One embodiment of the present invention is to provide an artificial intelligence-based apartment housing management automation device and method capable of providing an automated business guide for apartment housing management.

One embodiment of the present invention is an artificial intelligence-based apartment housing management instruction that guides the performance of a machine by learning the contents of a journal written by business practitioners who manage the apartment house and using the business checklist generated therefrom. It is intended to provide an automated device and method.

According to an embodiment of the present invention, an artificial intelligence-based apartment house management business instruction that can generate a business checklist using a business related keyword extracted from the contents of a journal and a business related apartment house situation according to the current apartment house situation It is intended to provide an automated device and method.

Among embodiments, the artificial intelligence-based apartment house management work order automation device is provided by a job identification unit for identifying a job performer's job duties when the access request through the apartment house performance terminal is approved, by the apartment house business execution terminal. A journal repository that stores electronically created and verified journals for each job by electronic payment method through the MDU business management terminal, machine learning the contents of the journals for each job in charge, and the job in question for each apartment A work journal machine learning unit that generates a plurality of work modules by classifying them into work contents, a multi-unit situation determination unit for determining the current multi-unit housing status, and at least one of the plurality of business modules according to the current multi-unit housing status. And a business guide unit for determining the apartment housing situation business module and guiding it to the apartment housing performance terminal as a business checklist.

The journal repository section may store the corresponding apartment housing situation together during the storage of the journal for each job in charge.

The journal machine learning unit may estimate a job-related keyword associated with the corresponding job in the content of the job log for each job, and determine a job-related apartment house condition associated with the job in charge in the apartment housing situation.

The journal machine learning unit may determine N business-related keywords (N is a natural number) that are frequently generated above a specific criterion in the business-related apartment housing situation.

The machine learning unit of the journal may generate a non-normal work module by separately learning the non-normal event and the content of the non-standard work of the multi-unit apartment in the multi-unit situation related to the work.

The machine learning unit of the journal may machine-learn the N business related keywords according to the normality event excluding the non-normality event in the business-related apartment house situation to determine the job content for each apartment house situation.

The journal machine learning unit may generate the plurality of job modules by determining a job content associated with each of the N job-related keywords.

The responsible job identification unit identifies an access request receiving module for receiving a connection request from the MDU business execution terminal, and identifies device information of the MDU business execution terminal, and then accesses the MDU according to whether the MDU business execution terminal is a registered terminal. It may include a connection request approval module for determining whether to approve the request, and if the connection request is approved, a task determination module for determining the responsibility of the task performer based on the registration information of the terminal for performing business of the MDU. .

The multi-unit situation determination unit determines a current time point consisting of a date and time, a time point determination module that determines the weather at the current time point, and an event that detects an event within a specific time period based on the current time point And a detection module and a multi-unit status determination module that determines the date and time, weather, and event as the current multi-unit status.

The business guide unit receives the current multi-unit housing status module from the multi-unit status determination unit, and the multi-unit situation determining the at least one multi-unit status business module based on the current multi-unit status. Based on the business decision module, the at least one apartment housing situation business module, the apartment work situation business analysis module for extracting work content, work place, estimated time and work check contents, and performing work based on the business place and the estimated time And a checklist generation module for generating the order and task execution path to generate the task checklist.

Among the embodiments, the method for automating the artificial intelligence-based MDU management order is a step of identifying a job performer's responsibility when an access request through the MDU execution terminal is approved, and electronically created by the MDU operation terminal. And the step of storing the journals for each job in charge confirmed by the electronic payment method through the MDU business management terminal, and machine learning the contents of the job log for each job in charge to classify the job in charge as the job contents for each apartment housing situation. Generating business modules, determining a current MDU status, and determining at least one MDU business module according to the current MDU status among the plurality of MDUs to perform the MDU business terminal Includes steps to guide you to the task checklist.

The step of identifying the responsible job includes receiving a connection request from the MDU execution terminal, identifying device information of the MDU execution terminal, and then accessing the terminal according to whether the MDU execution terminal is a registered terminal. The method may include determining whether to approve the request and, if the access request is approved, determining the job duties of the work performer based on the registration information of the multi-family housing performance terminal.

Determining the status of the multi-family house includes: determining a current time point consisting of a date and time, determining weather at the current time point, detecting an event existing within a specific time period based on the current time point, and And determining the date and time, weather, and event as the current apartment housing situation.

The step of guiding to the business checklist includes receiving the current apartment housing status from the apartment housing determination unit, and determining the at least one apartment housing business module based on the current apartment housing status, Extracting work content, work place, expected time and work check content based on the at least one apartment housing situation work module and generating a work execution sequence and work execution path based on the work place and the estimated time to And generating a task checklist.

The disclosed technology can have the following effects. However, since the specific embodiment does not mean that all of the following effects should be included or only the following effects are included, the scope of rights of the disclosed technology should not be understood as being limited thereby.

The artificial intelligence-based apartment house management work order automation device and method according to an embodiment of the present invention are machine-learned the contents of the journal written by business operators who manage the apartment house and use the business checklist generated based on this You can guide your work.

The apparatus and method for automating the artificial intelligence-based apartment housing management work according to an embodiment of the present invention checks the work using the business-related keyword extracted from the contents of the journal and the business-related apartment housing situation according to the current apartment housing situation. You can create a list.

1 is a view for explaining an artificial intelligence-based apartment house management work order automation system according to an embodiment of the present invention.

FIG. 2 is a view for explaining the physical configuration of an automated device for managing an apartment house management order in FIG. 1.

FIG. 3 is a block diagram illustrating a functional configuration of an automated device for managing an apartment house management business in FIG. 1.

4 is a block diagram illustrating detailed modules for each configuration of an automatic device for managing an apartment house management business according to an embodiment of the present invention.

FIG. 5 is a flow chart illustrating the process of automating the MDU management work instruction performed in the MDU management automation apparatus in FIG. 1.

FIG. 6 is a flowchart illustrating an embodiment of a process of identifying a responsible job performed by the responsible job identification unit in FIG. 4.

FIG. 7 is a flowchart illustrating an embodiment of a process for determining a condition of a multi-family house performed by the condition determining unit of a multi-family house in FIG. 4.

8 is a flowchart illustrating an embodiment of a business guide process performed in the business guide unit in FIG. 4.

Since the description of the present invention is merely an example for structural or functional description, the scope of the present invention should not be interpreted as being limited by the examples described in the text. That is, since the embodiments can be variously changed and have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing technical ideas. In addition, the purpose or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such an effect, and the scope of the present invention should not be understood as being limited thereby.

Meanwhile, the meaning of terms described in the present application should be understood as follows.

Terms such as "first" and "second" are for distinguishing one component from other components, and the scope of rights should not be limited by these terms. For example, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component.

When a component is said to be "connected" to another component, it may be understood that other components may exist in the middle, although they may be directly connected to the other component. On the other hand, when a component is said to be "directly connected" to another component, it should be understood that no other component exists in the middle. On the other hand, other expressions describing the relationship between the components, that is, "between" and "immediately between" or "neighboring to" and "directly neighboring to" should be interpreted similarly.

Singular expressions are to be understood as including plural expressions unless the context clearly indicates otherwise, and terms such as “comprises” or “have” are used features, numbers, steps, actions, components, parts or the like. It is to be understood that a combination is intended to be present, and should not be understood as pre-excluding the existence or addition possibility of one or more other features or numbers, steps, actions, components, parts or combinations thereof.

In each step, the identification code (for example, a, b, c, etc.) is used for convenience of explanation. The identification code does not describe the order of each step, and each step clearly identifies a specific order in context. Unless stated, it may occur in a different order than specified. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

The present invention can be embodied as computer readable code on a computer readable recording medium, and the computer readable recording medium includes all kinds of recording devices in which data readable by a computer system is stored. . Examples of computer-readable recording media include ROM, RAM, CD-ROM, magnetic tape, floppy disks, and optical data storage devices. In addition, the computer-readable recording medium can be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion.

All terms used herein have the same meaning as generally understood by a person skilled in the art to which the present invention pertains, unless otherwise defined. The terms defined in the commonly used dictionary should be interpreted as being consistent with the meanings in the context of the related art, and cannot be interpreted as having ideal or excessively formal meanings unless explicitly defined in the present application.

Referring to Figure 1, artificial intelligence-based apartment housing management work order automation system 100 includes a multi-unit business execution terminal 110, a multi-unit management work order automation device 130, a database 150, and multi-unit business management It may include a terminal 170.

The MDU terminal 110 is a computing device that is used by the MDU's work entrepreneurs and is capable of creating and verifying work journals for managing the MDU, and using a smart phone, laptop, or computer. It may be implemented, and is not necessarily limited thereto, and may be implemented with various devices such as a tablet PC. The MDU terminal 110 may be connected to the MDU management instruction automation device 130 through a network, and the plurality of MDU execution terminals 110 and the MDU management instruction automation device 130 may be simultaneously Can be connected.

The apartment unit management work order automation device 130 corresponds to a computer or program that can generate and provide a work checklist that includes information about the work to be performed to each business operator regarding various tasks required for the management of the apartment house It can be implemented as a server. The apartment house management work order automation device 130 may be connected to the apartment house execution terminal 110 and the apartment house management terminal 170 through a wired network or a wireless network such as Bluetooth, WiFi, etc., through a wired or wireless network. Communication with the MDU terminal 110 and the MDU management terminal 170 may be performed.

In one embodiment, the multi-unit management task order automation device 130 may store information necessary to manage various tasks related to the multi-unit housing in conjunction with the database 150. On the other hand, the apartment house management business order automation device 130, unlike Figure 1, may be implemented by including a database 150 therein. In addition, the multi-unit management task order automation device 130 may be implemented including a processor, a memory, a user input/output unit, and a network input/output unit, which will be described in more detail in FIG. 2.

The database 150 performs the various tasks necessary for the management of the MDU through communication with the MDU management terminal 110 and the MDU management terminal 170 by the automation device 130 of the MDU management instruction. In the process of applying, various information needed can be stored. For example, the database 150 may store various journals received from the MDU task terminal 110 and the MDU task management terminal 170, and store information on the status of the MDU and the status of the work process. It may be, and is not necessarily limited to, it is possible to store information collected or processed in various forms in the process of supporting and managing the performance of business.

The apartment house management terminal 170 corresponds to a computing device capable of confirming an apartment house related journal and providing approval regarding it, and may be implemented as a smartphone, a laptop, or a computer, and is not necessarily limited thereto, and a tablet PC It can also be implemented with various devices. The apartment house management terminal 170 may be connected to the apartment house management business instruction automation device 130 through a network, and the plurality of apartment house management terminal 170 may be concurrent with the apartment house management business instruction automation device 130 Can be connected. In one embodiment, the MDU management terminal 170 may be implemented with the same device as the MDU execution terminal 110, and may perform a role of each other in accordance with the user of each terminal.

Referring to FIG. 2, the apparatus 130 for automating an apartment house management work order may include a processor 210, a memory 230, a user input/output unit 250, and a network input/output unit 270.

The processor 210 may execute each procedure defined to perform automation of various tasks related to the apartment house in the apartment house management business instruction automation device 130, and the memory 230 read or written throughout the process And a synchronization time between volatile and nonvolatile memory in the memory 230. The processor 210 can control the overall operation of the apartment management management instruction automation device 130, and is electrically connected to the memory 230, the user input/output unit 250, and the network input/output unit 270, and data therebetween. You can control the flow. The processor 210 may be embodied as a central processing unit (CPU) of the multi-unit management instruction automation device 130.

The memory 230 is implemented as a non-volatile memory, such as a solid state disk (SSD) or a hard disk drive (HDD), and includes an auxiliary storage device used to store overall data required for the automation device 130 for managing the apartment complex. And a main memory device implemented with volatile memory such as random access memory (RAM).

The user input/output unit 250 may include an environment for receiving user input and an environment for outputting specific information to the user. For example, the user input/output unit 250 may include an input device including an adapter such as a touch pad, a touch screen, an image keyboard, or a pointing device, and an output device including an adapter such as a monitor or touch screen. In one embodiment, the user input/output unit 250 may correspond to a computing device connected through a remote connection, and in such a case, the apartment unit management business order automation device 130 may be performed as a server.

The network input/output unit 270 includes an environment for connecting to an external device or system through a network, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a VAN ( Value Added Network).

Referring to FIG. 3, the apartment house management work order automation device 130 includes a responsible job identification unit 310, a journal repository unit 320, a journal machine learning unit 330, and an apartment house situation determination unit 340. , May include a business guide unit 350 and a control unit 360.

The charge job identification unit 310 may identify the charge job of the business performer when the access request through the MDU terminal 110 is approved. The management tasks for apartment houses can be very diverse, can be classified according to the type of each task, and in the case of a task performer who directly performs management tasks, the job duties can be determined according to the type of task in charge. For example, the job duties of a business performer may include facilities, security, environmental beautification, general administration, landscaping, and the like, but is not limited thereto, the size of an organization for the management of apartment houses, the type and scale of apartment houses, etc. Accordingly, it can be defined in various forms.

In one embodiment, the responsible job identification unit 310 identifies the device information of the access request receiving module, the apartment housing business execution terminal 110 to receive the connection request from the apartment housing business execution terminal 110, and then the corresponding apartment The access request approval module for determining whether to approve the access request according to whether the work execution terminal 110 is a registered terminal and, if the access request is approved, the work performer based on the registration information of the multi-family work execution terminal 110 It may include a job determination module for determining the job description. This will be described in more detail in FIGS. 4 and 6.

The journal repository unit 320 may store a journal for each job in charge, which is electronically created by the MDU task execution terminal 110 and confirmed by an electronic payment method through the MDU management terminal 170. The journal repository 320 can interwork with the database 150 to store the journal, confirm the completion of the journal entry from the MDU terminal 110, and confirm the corresponding job from the MDU management terminal 170. By checking the electronic payment processing for the journal, the journal for which the final processing has been completed can be stored and stored in an independently implemented storage area for each job in charge.

In one embodiment, the journal repository section 320 may be implemented as a device independent of the MDU management automation instruction 130 and may be operated as an external database 150, in this case the MDU management task Communication with the instruction automation device 130 may be performed through a network.

In one embodiment, the journal repository section 320 may also store the corresponding apartment housing situation in the process of storing the journal for each job in charge. Apartment housing situation may include the date, time, weather, event, etc. at that time, and the event is a specific event that may occur in relation to the apartment complex, such as moving in or out of residents, internal construction of certain households, or congratulations can do. In particular, the event may be classified into a regularity event that occurs with a certain regularity and an irregularity event that occurs irregularly in the process of residence in a multi-family house or a management process related to a multi-family house.

The machine learning unit 330 may generate a plurality of job modules by classifying the job in charge of each apartment housing situation by machine learning the contents of the job log for each job. Here, the work module may correspond to a work unit that contains content related to work required for managing a multi-family house, and may include information such as work content, work place, and estimated time. The journal machine learning unit 330 learns the contents of the journals categorized by job duties, and classifies them into work contents according to the apartment housing condition by reflecting the apartment house status for each job in charge based on the learning contents. It is possible to create a work module for the work content for each housing situation.

In one embodiment, the journal machine learning unit 330 estimates a job-related keyword associated with the corresponding job in the content of the journal for each job, and determines a job-related apartment house associated with the job in the apartment house situation. Can be. The job-related keyword may correspond to a keyword frequently used for a specific job, and may be generated and utilized in advance as a result of learning about the journal for each job. The journal machine learning unit 330 may extract a job-related keyword from the journal by applying an analysis model as a learning result to the journal for each job.

In addition, the work journal machine learning unit 330 may determine a work-related multi-housing situation associated with a job in charge from the multi-housing situation information. The work-related apartment housing situation may correspond to the apartment housing situation composed of context variables related to a specific task among various context variables constituting the apartment housing situation. For example, if the apartment housing information consists of the current date, time, weather, event, etc., in the case of the'outdoor cleaning' job, because the weather is an important situation, the business-related apartment housing situation may consist of date, time, and weather. In the case of'Gas Inspection', households moving in cannot be inspected, so the status of apartments related to work may consist of dates, times, and events.

In one embodiment, the journal machine learning unit 330 may determine N business-related keywords (N is a natural number) that are frequently generated above a specific criterion in a business-related apartment house situation. The journal machine learning unit 330 can learn the job-related keywords and job-related apartment housing conditions extracted from the journal for each job position, and determine the business-related keyword for each job-related apartment house situation as a result of the learning. At this time, the business-related keyword for each business-related apartment house situation may be limited to N presets. A specific criterion is the frequency of occurrence of business-related keywords, and may correspond to the number of criteria for selecting business-related keywords that are highly likely to be closely related to the business-related apartment housing situation.

In one embodiment, the journal machine learning unit 330 may generate a non-normal work module by separately learning the non-normal event and the content of the non-standard work of the multi-unit apartment in the context of a business-related apartment. The non-normality event is an event opposite to the normality event, and may correspond to an event in which a certain regularity does not exist among events that may occur in the apartment house, and may include, for example, a fire of a specific generation, a fire event, or the like. Can be. The irregular business module may correspond to a business unit containing irregular business content related to an apartment house, and may include information such as business content, work place, and estimated time. The journal machine learning unit 330 learns the irregularity events that actually occurred in the context of a business-related apartment complex and the non-standard business content of the apartment complexes performed in connection with the event as separate learning from the business journal for each job in charge. It can be done.

In one embodiment, the journal machine learning unit 330 may determine N job related keywords according to the normal housing event by excluding the non-normal event in the business related apartment housing situation to determine the job content for each apartment housing situation. The journal machine learning unit 330 can determine normality events excluding non-normality events based on the contents of the journal, and learning data including N business-related keywords that are highly correlated with normality events occurring in a business-related apartment housing situation. By creating and learning machine, it is possible to determine the work content for each apartment house situation as a learning result.

In one embodiment, the journal machine learning unit 330 may generate a plurality of job modules by determining the job contents associated with each of the N job-related keywords. The journal machine learning unit 330 may determine related job contents for each job-related keyword, and may generate a plurality of job modules based on the job contents. Accordingly, each task module may include information related to task contents together with associated task related keywords.

The apartment housing situation determination unit 340 may determine the current apartment housing situation. The apartment housing situation is information about the apartment complex at the present time and can be composed of various situation variables. The situation variable is an item related to the situation and may correspond to a date, time, weather, event, etc. necessary for the management of the apartment complex. For example, the apartment housing situation may be expressed as a vector such as (date, time, weather, location, event), and each situation variable constituting the apartment housing situation may be numerically expressed or expressed as a grade or level. .

In one embodiment, the apartment housing situation determination unit 340 is a time determination module for determining a current time point consisting of a date and time, a weather determination module for determining weather at the current time point, and is present within a specific time interval based on the current time point It may include an event detection module for detecting the event and the date and time, weather and events to determine the current state of the multi-family housing apartment module. This will be described in more detail in FIGS. 4 and 7.

The business guide unit 350 may determine at least one multi-family housing business module according to the current multi-family housing situation among a plurality of business modules and guide the multi-family business execution terminal 110 as a business checklist. The apartment housing situation task module is a task module that includes tasks related to tasks for managing an apartment complex, and may correspond to a task module determined to be suitable for the current situation of the apartment complex. The work guide unit 350 may provide a work checklist to the MDU terminal 110 based on the MDU situation work module. Therefore, the MDU task performer may perform the work according to the work checklist through the MDU execution terminal 110.

In one embodiment, the business guide unit 350 determines at least one MDU situation module based on the MDU condition receiving module that receives the current MDU situation condition from the MDU decision unit, and the current MDU situation. An apartment house situation task analysis module for extracting work contents, a work place, estimated time, and work check contents based on at least one apartment house task decision module; And a checklist generation module that generates a work checklist by generating a work execution sequence and a work execution path based on the work place and the estimated time. This will be described in more detail in FIGS. 4 and 8.

The control unit 360 controls the overall operation of the apartment unit management work order automation device 130, and the responsible job identification unit 310, the journal repository unit 320, the journal machine learning unit 330, the apartment house situation A control flow or a data flow between the determination unit 340 and the business guide unit 350 may be managed.

Referring to FIG. 4, the apparatus 130 for automating an apartment house management business according to an embodiment of the present invention includes a responsible job identification unit 410, an apartment house status determination unit 430, and a business guide unit 450. Can be implemented.

The charge job identification unit 410 may include a connection request receiving module 411, a connection request approval module 413, and a charge job determination module 415. The access request receiving module 411 may receive a connection request from the apartment housing performance terminal 110. In this case, the access request receiving module 411 may receive identification information of the corresponding terminal together with the access request from the apartment housing execution terminal 110 and provide it to the access request approval module 413.

The access request approval module 413 may identify device information of the MDU terminal 110 and determine whether to approve the connection request according to whether the MDU terminal 110 is a registered terminal. The access request approval module 413 may receive identification information corresponding to device information of the corresponding terminal from the access request receiving module 411, and based on this, determine whether the corresponding terminal is registered or not, thereby determining final approval, When the approval is completed, the approval result may be provided to the responsible job determination module 415.

Responsible job determination module 415 receives the approval result from the access request approval module 413 and determines that the access request is approved, then determines the job performance of the work performer based on the registration information of the MDU terminal 110 Can be. The registration information of the apartment housing business execution terminal 110 and information about the job duties of the business performer can be stored and managed in the database 150, and the job determination module 415 is registered with the database 150 Confirmation and decision-making tasks can be performed.

The apartment housing situation determination unit 430 may be implemented by including a viewpoint determination module 431, a weather determination module 433, an event detection module 435, and an apartment housing situation determination module 437. The viewpoint determination module 431 may determine a current viewpoint composed of the current date and time based on the time when the access request of the MDU terminal 110 is received. The viewpoint determination module 431 can receive information about the current date and time through the system clock of the apartment management management instruction automation device 130, the weather determination module 433, the event detection module 435, and the joint The current situation information may be provided to the housing situation determination module 437.

The weather determination module 433 may determine weather based on the current time point received from the time point determination module 431. In one embodiment, the weather determination module 433 may be connected to an external system to receive weather information, determine the final weather based on location information of the MDU terminal 110, and determine the MDU status Current weather can be provided to the module 437.

The event detection module 435 may detect an event existing within a specific time period based on the current time point. The event detection module 435 may detect an event existing in a predetermined time period based on a current time point received from the time point determination module 431, for example, about one hour or so. The event detection module 435 may be connected to the database 150, and may detect an event stored in a specific time period based on the event information stored in the database 150, and events to the apartment housing situation determination module 437 Information can be provided.

The multi-unit situation determination module 437 determines the multi-unit situation based on the current date, time, weather, and events provided from the viewpoint determination module 431, the weather determination module 433, and the event detection module 435, respectively. Can be. In one embodiment, the multi-unit situation determination module 437 may determine the multi-unit situation as a vector generated by using dates, times, weather, and events as components.

The business guide unit 450 may be implemented by including a multi-family situation reception module 451, a multi-family situation business determination module 453, a multi-family situation business analysis module 455, and a checklist generation module 457. .

The apartment housing reception module 451 may receive the current apartment housing status from the apartment housing determination unit 430. The apartment housing reception module 451 may check the formal error regarding the apartment housing situation and provide it to the apartment housing business decision module 453.

The apartment housing situation task determination module 453 may determine at least one apartment housing situation task module based on the current apartment housing situation. The apartment housing situation task determination module 453 may use the learning result to determine the apartment housing situation task module suitable for the current apartment housing situation. More specifically, the apartment housing situation business determination module 453 may determine a business related keyword required in the current apartment housing situation, and may determine a apartment housing situation business module matching the business related keyword.

The apartment housing situation business analysis module 455 may extract a work content, a work place, an estimated time, and a business check content based on at least one apartment housing business module. The apartment housing situation business analysis module 455 may extract specific items constituting the business content from the apartment housing situation business module and provide it to the checklist generation module 457.

The checklist generation module 457 may generate a work checklist by generating a work execution sequence and a work execution path based on a work place and an estimated time. More specifically, the checklist generation module 457 may determine a task execution order to optimize the task execution path based on the work place and the expected time. The checklist creation module 457 can sort the work contents according to the work execution order, and can generate a work checklist by adding a check item for each work content, and the generated work checklist is a terminal for conducting an apartment house work ( 110).

Referring to FIG. 5, when the request for access through the MDU execution terminal 110 is approved through the MDU 310, the MDU management automation instruction 130 may identify the MDU's responsibility. There is (step S510). The apartment house management work order automation device 130 is electronically created by the apartment house performance terminal 110 through the journal repository section 320 and confirmed by an electronic payment method through the apartment house management terminal 170. It is possible to store a journal for each job in charge (step S530).

The multi-unit management work order automation device 130 generates a plurality of work modules by classifying the work in charge of each apartment housing situation by machine learning the contents of the work log by each job through the machine learning unit 330 It can be made (step S550). The multi-unit management instruction automation device 130 may determine the current multi-unit status through the multi-unit status determination unit 340 (step S570). The multi-unit management order automation device 130 determines the at least one multi-unit status module according to the current multi-unit status among the plurality of business modules through the business guide unit 350 to perform the multi-unit business execution terminal 110 ) To a work checklist (step S590).

Referring to FIG. 6, the responsible job identification unit 410 may receive an access request from the MDU performing terminal 110 through the access request receiving module 411 (step S610). The responsible job identification unit 410 identifies device information of the MDU terminal 110 through the access request approval module 413 and then requests a connection according to whether the MDU terminal 110 is a registered terminal. Whether to approve can be determined (step S630). The responsible job identification unit 410 may determine the responsible job performer based on the registration information of the MDU terminal 110 when the connection request is approved through the responsible job determination module 415 (step S650). .

Referring to FIG. 7, the apartment housing situation determination unit 430 may determine a current time point composed of a date and time through the time point determination module 431 (step S710). The apartment housing situation determination unit 430 may determine the weather at the current time point through the weather determination module 433 (step S730). The apartment housing situation determination unit 430 may detect an event existing within a specific time period based on the current time point through the event detection module 435 (step S750). The apartment housing situation determination unit 430 may determine the date and time, weather, and event as the current apartment housing situation through the apartment housing determination module 437 (step S770).

Referring to FIG. 8, the business guide unit 450 may receive the current apartment housing status from the apartment housing status determination unit 430 through the apartment housing status receiving module 451 (step S810). The business guide unit 450 may determine at least one MDU situation business module based on the current MDU status through the MDU situation determination module 453 (step S830). The work guide unit 450 may extract work content, work place, estimated time, and work check content based on at least one multi-family situation work module through the multi-family situation work analysis module 455 (step S850). . The work guide unit 450 may generate a work check list by generating a work execution sequence and a work execution path based on the work place and the estimated time through the check list generation module 457 (step S870 ).

Although described above with reference to preferred embodiments of the present invention, those skilled in the art variously modify and change the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. You can understand that you can.

[Description of codes]

100: Artificial intelligence-based apartment housing management order automation system

110: apartment housing performance terminal

130: apartment house management work order automation device

150: database 170: apartment housing management terminal

210: processor 230: memory

250: user input/output unit 270: network input/output unit

310: responsible job identification department 320: journal repository department

330: Workbook Machine Learning Department 340: Apartment Housing Determination Department

350: business guide unit 360: control unit

410: responsible job identification unit 430: apartment housing situation determination unit

450: business guide unit 411: connection request receiving module

413: access request approval module 415: responsible job determination module

431: Time determination module 433: Weather determination module

435: Event detection module 437: Apartment housing situation determination module

451: Apartment housing reception module 453: Apartment housing business decision module

455: Apartment housing situation analysis module

457: checklist generation module

Claims

If the request for access through the apartment housing performance terminal is approved, the job identification unit that identifies the job performance of the business performer;

A journal repository unit for electronically created by the MDU business execution terminal and storing the business diary for each responsible job identified by an electronic payment method through the MDU management terminal;

A machine learning unit that generates a plurality of job modules by classifying the job in each apartment house by learning the contents of the job log for each job;

An apartment housing determination unit for determining the current apartment housing status; And

An artificial intelligence-based multi-unit housing including a business guide unit for determining at least one multi-unit housing unit business module according to the current multi-unit housing module and guiding it to the multi-unit business execution terminal as a business checklist. Automation device for management work orders.
The method of claim 1, wherein the journal repository section

The artificial intelligence-based apartment house management business order automation device characterized by storing the relevant apartment house situation together during the storage of the journal for each job in charge.
According to claim 1, The journal machine learning department

Artificial intelligence-based apartment housing management, characterized by estimating a business-related keyword associated with the job in charge in the content of the journal for each job in charge and determining the job-related apartment house status associated with the job in charge in the apartment housing situation Work order automation device.
According to claim 3, The journal machine learning department

An artificial intelligence based autonomous house management business order automation device characterized by determining N business-related keywords frequently generated above a specific criterion in the business-related apartment housing situation.
According to claim 4, The journal machine learning department

An artificial intelligence based autonomous house management work order automation device characterized by generating a non-regular work module by separately learning the non-regular event and the content of the non-regular work of the multi-unit apartment in the multi-unit housing situation related to the work.
According to claim 5, The journal machine learning department

Artificial intelligence-based apartment housing management business order characterized by determining the business content for each apartment housing situation by machine learning the N business-related keywords according to the regularity event excluding the irregular events in the business-related apartment housing situation. Automation device.
According to claim 6, The journal machine learning department

An artificial intelligence-based apartment house management business order automation device, characterized in that the plurality of business modules are generated by determining the business contents associated with each of the N business-related keywords.
The method of claim 1, wherein the job identification department

A connection request receiving module that receives a connection request from the apartment housing performance terminal;

An access request approval module that identifies device information of the MDU service terminal and determines whether to approve the access request according to whether the MDU service terminal is a registered terminal; And

When the access request is approved, an artificial intelligence-based apartment house management business order automation device, characterized in that it comprises a responsible job determination module for determining a responsible job performer based on the registration information of the apartment housing execution terminal. .
The method of claim 1, wherein the apartment housing determination unit

A time point determination module for determining a current time point consisting of a date and time;

A weather determination module for determining weather at the current time point;

An event detection module detecting an event existing in a specific time period based on the current time point; And

An artificial intelligence-based apartment housing management order automation device comprising the apartment housing determination module that determines the date and time, weather and events as the current apartment housing status.
According to claim 1, The business guide unit

A multi-unit situation receiving module for receiving the current multi-unit situation from the multi-unit situation determining unit;

An apartment house situation task determination module for determining the at least one apartment house task module based on the current apartment house situation;

An apartment housing situation business analysis module for extracting work content, work place, estimated time, and business check content based on the at least one apartment housing business module; And

And a checklist generation module for generating the work checklist by generating a work execution sequence and a work execution path based on the work place and the estimated time.
In the method for automating the apartment house management business instruction performed in the apartment house management business instruction automation device,

When the request to access through the apartment housing performance terminal is approved, identifying the job duties of the business performer;

Storing a journal for each job in charge that is electronically created by the MDU terminal and confirmed by an electronic payment method through the MDU management terminal;

Generating a plurality of job modules by classifying the job contents for each apartment housing situation by machine learning the contents of the job log for each job;

Determining the current status of the apartment complex; And

Artificial intelligence-based apartment housing management comprising the step of determining at least one apartment housing status business module according to the current apartment housing status from among the plurality of business modules and guiding it to a business checklist on the terminal for performing the apartment housing business. How to automate work orders.
The method of claim 11, wherein the step of identifying the responsible job

Receiving a connection request from the apartment housing performance terminal;

Identifying device information of the MDU terminal, and determining whether to approve the access request according to whether the MDU terminal is a registered terminal; And

If the access request is approved, comprising the step of determining the responsibility of the task performer on the basis of the registration information of the MDU terminal, the artificial intelligence-based MDU management automation method.
The method of claim 11, wherein the step of determining the situation of the apartment

Determining a current time point consisting of a date and time;

Determining weather at the current time point;

Detecting an event existing in a specific time period based on the current time point; And

And determining the date and time, weather, and event as the current multi-family housing situation.
The method of claim 11, wherein the step of guiding to the task checklist is

Receiving the current multi-unit status from the multi-unit status determination unit;

Determining the at least one apartment housing business module based on the current apartment housing situation;

Extracting work content, work place, estimated time and work check content based on the at least one apartment housing situation work module; And

And generating the work checklist by generating a work execution sequence and a work execution path based on the work place and the estimated time.