Apparatus and method for suggesting facility improvement for the elderly using residential space image analysis

Abstract

The present invention relates to an apparatus and method for proposing improvements to facilities for the elderly using residential space image analysis. An electronic device according to one embodiment of the present invention includes a memory and a processor connected to the memory, and the processor receives a drawing and a photograph of a target space from a user terminal, analyzes the drawing and the photograph through an artificial intelligence module to identify zones and objects for each zone of the target space, and based on a safety element DB including information on essential objects for each zone and information on whether there are risk factors for each object, derives essential objects that are not included as objects in the zone among the essential objects for the zone as objects requiring installation, derives objects corresponding to risk factors among the objects as objects requiring removal, generates a proposed drawing by indicating the installation location of the objects requiring installation and the objects requiring removal on the drawing, and transmits the proposed drawing to the user terminal.

Description

Technology Field

[0001] The present invention relates to an apparatus and method for proposing improvements to facilities for the elderly using residential space image analysis. Background Technology

[0003] Unless otherwise indicated in this specification, the contents described in this section are not prior art for the claims of this application, and are not to be recognized as prior art simply because they are included in this section.

[0004] Due to the rapid aging of the population structure in recent years, social interest in 'Aging in Place,' which supports independent living for the senior generation, is increasing. The elderly are at high risk of experiencing inconveniences in typical residential environments, such as falls or limited range of motion, due to the decline in physical function and changes in cognitive abilities.

[0005] Therefore, considering the physical characteristics of seniors, the introduction of senior-tailored interior elements such as removing door thresholds, installing safety handrails, applying non-slip tiles, and ensuring appropriate lighting is essential.

[0006] Previously, renovating a residential space or changing the interior required a professional to visit the site in person to take measurements and provide consultation. However, this method is not only time-consuming and costly, but also has limitations in that it is difficult for non-expert users to intuitively identify what senior-specific elements are needed in their living space based solely on floor plans or photos.

[0007] In particular, since standard interior design drawings are composed primarily of structural information, it is difficult to visually confirm where and how safety and convenience elements specialized for seniors should be placed within the actual space.

[0008] Accordingly, there is a need for technical means to analyze interior elements optimized for seniors based on floor plans or photographic data of residential spaces provided by users, and to provide intuitive guidelines by visually displaying them on the floor plan. Prior art literature

[0010] Korean Registered Patent No. 10-2413604 (June 22, 2022) The problem to be solved

[0011] One embodiment of the present invention provides a device and method for proposing improvements to facilities for the elderly using residential space image analysis.

[0012] The technical problems to be solved by the present invention are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which the present invention belongs from the description below. means of solving the problem

[0014] To achieve the above-mentioned purpose, an electronic device according to one embodiment of the present invention includes a memory and a processor connected to the memory, and the processor receives a drawing and a photograph of a target space from a user terminal, analyzes the drawing and the photograph through an artificial intelligence module to identify zones and objects for each zone of the target space, and based on a safety element DB containing information on essential objects for each zone and information on whether there are risk factors for each object, derives essential objects that are not included as objects in the zone among the essential objects for the zone as objects requiring installation, derives objects corresponding to risk factors among the objects as objects requiring removal, generates a proposed drawing by indicating the installation location of the objects requiring installation and the objects requiring removal on the drawing, and transmits the proposed drawing to the user terminal.

[0015] At this time, the safety element DB further includes information on a replacement object that can replace an object corresponding to a risk element, and the processor indicates the object to be removed on the proposed drawing, and if a replacement object for the object to be removed exists, the replacement object may also be indicated.

[0016] At this time, the artificial intelligence module includes an object recognition model that identifies the type of object by extracting the external shape and texture information of the object from the photograph, and a drawing analysis model that identifies the structural layout of the space by extracting the locations of walls, doors, and windows from the drawing, and the processor can finally identify the object located within each zone by matching the coordinates of the object identified through the object recognition model with the coordinate system of the target space identified through the drawing analysis model.

[0017] At this time, the artificial intelligence module may use a model trained based on at least one algorithm among a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Generative Adversarial Network (GAN), a Transformer, and a Support Vector Machine (SVM).

[0018] At this time, the processor may derive objects that do not correspond to the objects requiring removal among the entire identified objects as general objects, derive a risk score for the general objects based on their location, set the general objects as objects requiring movement if the risk score exceeds a preset first threshold risk score, set the general objects as objects requiring movement if the risk score exceeds a preset second threshold risk score lower than the first threshold risk score but is less than or equal to the first threshold risk score, set the general objects as objects requiring movement caution if the risk score is less than or equal to the second threshold risk score, set the general objects as safe objects, and distinguish and display the objects requiring movement, objects requiring movement caution, and safe objects on the proposed drawing.

[0019] At this time, the processor can connect a movement path of a predetermined width between a plurality of predetermined movement nodes in the drawing, and for the general object, derive the risk score for the general object based on the number of movement paths and the overlapping area that overlap with the area occupied by the general object.

[0020] At this time, the above movement node includes the entrances and exits of each zone in the above drawing and objects set as being used by the user, and the above movement path width can be set to the average shoulder width of the users using the corresponding target space.

[0021] At this time, the above risk score is derived by the following mathematical formula,

[0022]

[0023] rs represents the above risk score for the corresponding general object, n represents the number of paths overlapping with the area occupied by the corresponding general object, a_i represents the area overlapping with the i-th path and the area occupied by the corresponding general object, and oa represents the area of ​​the area occupied by the corresponding general object. Effects of the invention

[0025] As such, according to one embodiment of the present invention, a device and method for proposing improvements to facilities for the elderly using residential space image analysis can be provided.

[0026] The effects obtainable from the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art from the description below. Brief explanation of the drawing

[0028] Other aspects, features, and benefits of specific preferred embodiments of the present invention, as described above, will become more apparent from the following description in conjunction with the accompanying drawings. FIG. 1 is a conceptual diagram of a device for proposing facility improvements for the elderly using residential space image analysis according to one embodiment of the present invention. FIG. 2 is a block diagram of an electronic device according to one embodiment of the present invention. FIG. 3 is a drawing showing a drawing and an object according to an embodiment of the present invention. FIG. 4 is a drawing showing a movement node and a movement path according to an embodiment of the present invention. FIG. 5 is a drawing showing a general object and a movement path according to an embodiment of the present invention. FIG. 6 is a flowchart of a method for proposing improvements to facilities for the elderly using residential space image analysis according to one embodiment of the present invention. It should be noted that in the drawings above, similar reference numbers are used to illustrate identical or similar elements, features, and structures. Specific details for implementing the invention

[0029] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0030] In describing the embodiments, technical details that are well known in the art to which the present invention belongs and are not directly related to the present invention are omitted. This is intended to convey the essence of the present invention more clearly without obscuring it by omitting unnecessary explanations.

[0031] For the same reason, some components in the attached drawings have been exaggerated, omitted, or schematically depicted. Additionally, the size of each component does not entirely reflect its actual dimensions. Identical or corresponding components in each drawing have been assigned the same reference numbers.

[0032] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but can be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the invention, and the present invention is defined only by the scope of the claims. Throughout the specification, the same reference numerals refer to the same components.

[0033] At this point, it will be understood that each block of the process flow diagrams and combinations of the flow diagrams can be executed by computer program instructions. Since these computer program instructions can be loaded into the processor of a general-purpose computer, a special-purpose computer, or other programmable data processing equipment, the instructions executed through the processor of the computer or other programmable data processing equipment create means to perform the functions described in the flow diagram block(s). Since these computer program instructions can also be stored in computer-available or computer-readable memory that can be directed toward the computer or other programmable data processing equipment to implement the function in a specific way, the instructions stored in computer-available or computer-readable memory can also produce a manufactured item containing instruction means to perform the function described in the flow diagram block(s). Since computer program instructions can be loaded onto a computer or other programmable data processing equipment, instructions that perform a series of operation steps on the computer or other programmable data processing equipment to create a process executed by the computer can also provide steps for executing the functions described in the flowchart block(s).

[0034] Additionally, each block may represent a module, segment, or part of code containing one or more executable instructions for executing a specified logical function(s). It should also be noted that in some alternative execution examples, the functions mentioned in the blocks may occur out of order. For instance, two blocks described in succession may actually be executed substantially simultaneously, or the blocks may be executed in reverse order according to their corresponding functions.

[0035] In this embodiment, the term "part" refers to a software or hardware component such as a field-programmable gate array (FPGA) or an application-specific integrated circuit (ASIC), and the "part" performs certain roles. However, the meaning of "part" is not limited to software or hardware. The "part" may be configured to reside in an addressable storage medium or configured to run one or more processors. Accordingly, as an example, the "part" includes components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and "parts" may be combined into a smaller number of components and "parts" or further separated into additional components and "parts." In addition, the components and '~parts' may be implemented to play one or more CPUs within the device or secure multimedia card.

[0036] In describing the embodiments of the present invention in detail, the primary focus will be on examples of specific systems, but the main point claimed in this specification is applicable to other communication systems and services having a similar technical background without significantly departing from the scope disclosed in this specification, and this will be possible at the judgment of a person with skilled technical knowledge in the relevant technical field.

[0037] In addition, the user terminal described below may include a communication-capable desktop computer, laptop computer, notebook, smartphone, tablet PC, mobile phone, smart watch, smart glass, e-book reader, PMP (portable multimedia player), portable game console, navigation device, digital camera, DMB (digital multimedia broadcasting) player, digital audio recorder, digital audio player, digital video recorder, digital video player, PDA (Personal Digital Assistant), etc.

[0039] FIG. 1 is a conceptual diagram of a device for proposing improvements to facilities for the elderly using residential space image analysis according to one embodiment of the present invention, and FIG. 2 is a block diagram of an electronic device (100) according to one embodiment of the present invention.

[0040] An electronic device (100) according to one embodiment includes a processor (110) and a memory (120). The processor (110) can perform at least one of the methods described above. The memory (120) can store information related to the method described above or store a program in which the method described above is implemented. The memory (120) may be volatile memory or non-volatile memory. The memory (120) may be referred to as a 'database', 'storage unit', etc.

[0041] The processor (110) can execute a program and control the electronic device (100). The code of the program executed by the processor (110) can be stored in memory (120). The device (100) can be connected to an external device (e.g., a personal computer or a network) through an input / output device (not shown) and exchange data.

[0042] At this time, the processor (110) can receive drawings and photos of the target space from the user terminal.

[0043] In this case, the above drawing is a floor plan for understanding the overall structure of the target space and may include information on the location of walls, the opening and closing direction of doors, the location of windows, and the boundaries of each area (living room, bedroom, kitchen, bathroom, etc.). Such a drawing may be in the form of an architectural design drawing, a model house floor plan, or a simplified drawing in which the user has directly entered numerical values ​​and structures, and may be received in the format of an image file (JPG, PNG, etc.) or a vector file (PDF, DWG, etc.).

[0044] In addition, the above photograph serves as visual data for understanding the actual status of the target space and may be a real-world image including the floor material, the height of the threshold, the arrangement of furniture, the location of lighting, and the presence or absence of safety handles. In particular, the above photograph may include multiple images taken from multiple angles so that the artificial intelligence module can identify the three-dimensional shape and texture of the object.

[0045] In addition, the processor can obtain structured numerical data of space from a received drawing and extract information on unstructured objects that do not appear on the drawing from a received photograph.

[0046] For example, for an area defined as a 'bathroom' on a drawing, photo data analysis can be used to identify in real-time whether non-slip tiles have been installed in the bathroom or whether safety bars have been installed around the toilet.

[0047] In addition, the processor can identify zones and objects for each zone of the target space by analyzing the drawing and the photograph through an artificial intelligence module.

[0049] FIG. 3 is a drawing showing a drawing and an object according to an embodiment of the present invention.

[0050] Referring to FIG. 3, the processor can derive essential objects that are not included as objects in the area among the essential objects for the area, based on a safety element DB containing information on essential objects for each area and information on whether there are risk factors for each object, as objects that need to be installed, derive objects that are risk factors among the objects as objects that need to be removed, generate a proposed drawing by indicating the installation location of the objects that need to be installed and the objects that need to be removed on the drawing, and transmit the proposed drawing to the user terminal.

[0051] In this case, the above safety element DB is a standardized database designed considering the physical characteristics and behavioral patterns of seniors, and may include a list of items that must be provided to prevent safety accidents in each residential area (e.g., bathroom, bedroom, entrance, etc.) (essential objects) and information on object attributes that are highly likely to cause accidents (risk factors).

[0052] Specifically, as examples of the essential objects for each zone, the processor may set a 'safety handle next to the toilet' and a 'non-slip mat' as essential objects for the bathroom zone, and may define a 'foot light for nighttime walking' or an 'emergency call bell', etc., as essential objects for the bedroom zone.

[0053] If, as a result of analyzing the received photos and drawings, such objects are not identified within the area, the processor can classify them as objects requiring installation and manage them.

[0054] In addition, the information on risk factors for each object may include criteria regarding the installation status and location as well as the type of object.

[0055] For example, 'high door thresholds' or 'flooring materials that easily accumulate water' in the bathroom can be defined as risk factors that cause falls, and 'wheeled chairs' or 'bundles of wires' located in the middle of the living room that obstruct movement can be identified as objects that need to be removed.

[0056] The proposed drawings generated based on these analysis results may adopt various visual notation methods to provide intuitive information to the user.

[0057] For example, in the case of an object that needs to be installed, it may be indicated by a translucent icon or a dotted guideline at the optimal location where the object should be placed, and in the case of an object that needs to be removed, an immediate warning message may be conveyed to the user by overlaying a red X mark or an accented border over the object.

[0058] In addition, different colors (e.g., Danger-Red, Caution-Orange, Recommended-Green) may be assigned to the proposed drawings according to the risk level of each object. The risk level may be pre-set for each object in the safety element database.

[0059] In addition, the above safety element DB further includes information on a replacement object that can replace an object corresponding to a risk element, and the processor indicates the object to be removed on the proposed drawing, and if a replacement object for the object to be removed exists, the replacement object may also be indicated.

[0060] In addition, the fact that the processor displays replacement objects along with objects that need to be removed may be intended to practically support the user's decision-making regarding the improvement of their living environment by suggesting specific directions for improvement, rather than merely pointing out risk factors.

[0061] In this case, this alternative object proposal method enables users to immediately recognize the optimal alternative that ensures the safety of seniors without significantly altering the existing familiar furniture arrangement, and allows them to experience the image of the improved space in advance by visualizing the placement of a safe alternative in the location where risk factors have been removed on the proposed drawing.

[0062] As a specific example of the above replacement object, if the processor identifies the 'high threshold' of the bathroom entrance as an object requiring removal, it may propose a 'bathroom ramp' as a replacement object that can be leveled or replaced with a gentle ramp.

[0063] In addition, if a 'high bed frame' in the bedroom is identified as a fall risk, a low-profile frame or a 'senior-specific motion bed' equipped with a safety guard can be matched and provided as alternative object information.

[0064] In addition, in situations where slippery 'standard living room tiles' are classified as a risk factor, instead of replacing the entire area, 'non-adhesive non-slip mats' or 'rubber safety flooring' that can be partially attached can be indicated as alternatives.

[0065] At this time, when displaying such alternative objects, the processor may extract information on product specifications, installation difficulty, and estimated replacement costs stored in the safety element DB and expose additional information in the form of text or graphics on one side of the proposal drawing, and when a user selects a specific alternative object, it may generate and provide a link that leads to the purchase page of the corresponding product or a video of a construction example.

[0066] The simultaneous display of such alternative objects can contribute to deriving interior solutions that compensate for the decline in seniors' physical functions without compromising the aesthetics of the residence, and can offer the technical advantage of lowering the barriers to home renovation that non-expert users often feel uncertain about.

[0067] In addition, the artificial intelligence module includes an object recognition model that identifies the type of object by extracting the external shape and texture information of the object from the photograph, and a drawing analysis model that identifies the structural layout of the space by extracting the locations of walls, doors, and windows from the drawing, and the processor can finally identify the object located within each zone by matching the coordinates of the object identified through the object recognition model with the coordinate system of the target space identified through the drawing analysis model.

[0068] More specifically, the artificial intelligence module may utilize a model trained based on at least one algorithm among a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Generative Adversarial Network (GAN), a Transformer, and a Support Vector Machine (SVM).

[0069] At this time, the processor can perform an operation to project different data sources, such as photos (3D site data) and drawings (2D structural data), into a unified spatial coordinate system in order to integrate the analysis results of the object recognition model and the drawing analysis model.

[0070] Through this coordinate system matching process, the coordinates of the geometric center point or ground plane of a specific object identified in the photograph can be synchronized with the absolute coordinates within a specific area (e.g., Bedroom 1) on the drawing, and based on this, the processor can precisely identify the physical area where each object is located and calculate the distance between objects.

[0071] Furthermore, the algorithms applied to the aforementioned artificial intelligence module can perform functions optimized for the characteristics of each data. Specifically, a Convolutional Neural Network (CNN) can be used to classify visual objects such as furniture or obstacles by stepwise extracting features such as edges, textures, and shapes from pixel data within an image, and can distinguish the precise occupied area of ​​an object at the pixel level by combining it with image segmentation techniques.

[0072] In addition, the Transformer algorithm can be utilized to identify correlations between lines within a drawing or the contextual meaning of space, and to structure separated individual lines into a single completed 'Room' or 'Corridor'.

[0073] In addition, Recurrent Neural Networks (RNNs) can contribute to estimating the three-dimensional location of objects by analyzing the continuity between multiple photographic data captured in a time series, and Generative Adversarial Networks (GANs) can be used to restore low-resolution or partially obscured drawing / photographic data to high resolution or to supplement by inferring object information in obscured areas.

[0074] Furthermore, machine learning algorithms such as Support Vector Machines (SVM) can be applied to a final decision model that performs binary classification or classifies into multiple classes whether an identified object is a dangerous or safe element for seniors based on the feature vectors of the object. By utilizing these algorithms individually or in combination in an ensemble form, the artificial intelligence module can ensure the accuracy of object identification and the reliability of spatial analysis even under various residential environment variables.

[0076] FIG. 4 is a drawing showing a movement node and a movement path according to an embodiment of the present invention, and FIG. 5 is a drawing showing a general object and a movement path according to an embodiment of the present invention.

[0077] Even if it is not a risk factor, if it obstructs the user's movement path and poses a risk of safety accidents, it is necessary to adjust the placement or remove it. Accordingly, with reference to FIGS. 4 and 5, the processor derives objects that do not correspond to the objects requiring removal among the identified total objects as general objects, derives a risk score for the general objects based on the location of the general objects, sets the general objects as objects requiring movement if the risk score exceeds a preset first threshold risk score, sets the general objects as objects requiring movement if the risk score exceeds a preset second threshold risk score lower than the first threshold risk score but is less than or equal to the first threshold risk score, sets the general objects as objects requiring movement caution, and sets the general objects as safe objects if the risk score is less than or equal to the second threshold risk score, and can distinguish and display the objects requiring movement, objects requiring movement caution, and safe objects on the proposed drawings.

[0078] In this case, the above general object may refer to an object among ordinary items placed within a residential space, such as furniture, home appliances, and interior accessories, which itself does not exceed a predetermined standard for defects or risks.

[0079] For example, a 'sofa' in the living room, a 'dining table' in the kitchen, or a 'display cabinet' in the hallway may fall into this category. Although these objects are not inherently dangerous, depending on their placement, they can obstruct the user's movement and cause secondary accidents.

[0080] In addition, the processor can classify and manage the risk level based on how much these general objects encroach upon the senior's main walking path. Specifically, objects requiring movement may refer to a state where the risk of falls or collisions is very high due to severely blocking the main path, and may be identified as objects for which an immediate change of location is recommended on the proposed drawing. On the other hand, objects requiring caution regarding movement may refer to a state where, although they do not cause a direct inability to walk, they form a narrow passageway that may cause inconvenience when using walking aids or making sudden changes in direction.

[0081] In addition, the first critical risk score and the second critical risk score may serve as quantitative criteria for classifying these grades. The first critical risk score may be set as an upper threshold value where the probability of a safety accident occurring is judged to be very high, and the second critical risk score may be set as a lower threshold value at a level requiring routine caution.

[0082] The method for setting these thresholds may assign default values ​​based on statistical thinking data during system design, but can be variably adjusted according to the judgment of the system administrator.

[0083] For example, an administrator can provide more conservative safety guidelines by lowering the aforementioned thresholds to strengthen safety standards in accordance with the target user's mobility or cognitive level, or conversely, perform actions to flexibly raise them to suit the user's environment.

[0084] In addition, these settings can be optimized and applied in real time based on the user's physical information or preferences entered through the user terminal.

[0085] More specifically, the processor can connect a movement path of a predetermined width between a plurality of predetermined movement nodes in the drawing, and for the general object, derive the risk score for the general object based on the number of movement paths and the overlapping area that overlap with the area occupied by the general object.

[0086] At this time, the above-mentioned movement node may include the entrances and exits of each zone in the above-mentioned drawing and objects set to be used by the user.

[0087] In addition, the above movement width can be set to the average shoulder width of users using the target space.

[0088] At this time, when the processor interconnects the plurality of movement nodes to generate a virtual movement path, it can calculate the path based on the shortest orthogonal distance connecting two points.

[0089] This orthogonal distance-based circulation generation takes into account that walls or corridors within residential spaces are typically designed with a vertical or horizontal grid structure, and may be intended to model the actual walking patterns of seniors who move by turning at right angles along a designated path without crossing furniture.

[0090] Accordingly, the processor can construct a movement path network by searching for the shortest orthogonal path between objects primarily used by the user, such as beds, sofas, and dining tables, from the entrance of each zone.

[0091] In addition, the fact that the above movement path width is set based on the average shoulder width of users using the space may be intended to secure the minimum effective width that is physically occupied during actual walking.

[0092] Generally, the average shoulder width of an adult is the minimum value that does not include lateral swaying or personal space during walking; however, seniors may require a wider stride than the general population for walking stability or frequently use walking aids such as canes or walkers.

[0093] Therefore, the above processor determines the movement path width by adding a preset safety margin to the average shoulder width of the user, thereby enabling a more conservative and safer prediction of the possibility of collision that may occur when a general object encroaches within the movement path.

[0094] In addition, if specific circumstances regarding the target user's use of a wheelchair are identified, this movement path width setting can be automatically changed and applied based on the standard turning radius or full width of the wheelchair instead of the average shoulder width mentioned above, thereby enabling movement path interference analysis optimized for the individual user.

[0096] In addition, regarding the risk score, to look more specifically, the above risk score can be derived by the following mathematical formula 1.

[0097] [Mathematical Formula 1]

[0098]

[0099] In this case, rs represents the risk score for the general object, n represents the number of paths overlapping with the area occupied by the general object, a_i represents the area overlapping with the i-th path and the area occupied by the general object, and oa represents the area of ​​the area occupied by the general object.

[0100] At this time, the above mathematical formula 1 is designed to quantify the degree to which a general object obstructs movement within a residential space, and can calculate the risk level by organically combining the overlap ratio (a_i / oa) with the movement relative to the physical area occupied by the object and the number of overlapping movement paths (n).

[0101] Specifically, the above mathematical formula sums the area ratios occupied by individual movement paths within the object area through sigma operations, and by applying a natural logarithm (log) function thereto, it can be designed so that as a specific object overlaps with multiple movement paths, the risk level increases more gradually than simple summation, while the basic risk level is reflected immediately.

[0102] In particular, the '1+' term inside the logarithmic function prevents the risk score from becoming negative when there is no overlap area (0), and can play a role in ensuring that a meaningful risk value is derived even with slight overlap.

[0103] In addition, a structure that utilizes the number of overlapping wires (n) as the coefficient of an exponential function (exp) may be a key technical feature of the present invention.

[0104] This may be a result reflecting that an object that simultaneously blocks multiple movement paths (e.g., a point where the living room-master bedroom path and the living room-bathroom path intersect) is much more critical to the mobility rights and safety of seniors than an object that encroaches on a single movement path. Consequently, as the number of movement paths (n) increases, the rs value increases exponentially and converges to 1, through which the processor can identify an object causing complex walking difficulties as a priority object requiring movement.

[0105] Furthermore, a combined structure of an exponential function with a natural constant as the base and a natural logarithm enables the derivation of a risk score (rs) within a standardized range between 0 and 1. This normalized value provides a form optimized for performing comparison operations with the first and second critical risk scores, and can provide the technical effect of enabling the system to evaluate and visualize risk levels based on consistent standards for residential spaces of various sizes or furniture of different specifications.

[0106] This mathematical modeling can contribute to providing a guide to a practically safe and optimal living environment for seniors by moving beyond planar analysis that merely considers the size of an area and analyzing the importance of circulation paths and the placement of objects within the residential space in three dimensions.

[0108] FIG. 6 is a flowchart of a method for proposing improvements to facilities for the elderly using residential space image analysis according to one embodiment of the present invention.

[0109] Referring to FIG. 6, a method for proposing improvements to facilities for the elderly using residential space image analysis according to one embodiment of the present invention can receive drawings and photos of a target space from a user terminal (S101).

[0110] In addition, the method for proposing improvements to facilities for the elderly using residential space image analysis according to one embodiment of the present invention can identify zones and objects for each zone of the target space by analyzing the drawing and the photograph through an artificial intelligence module (S103).

[0111] In addition, the method for proposing improvements to facilities for the elderly using residential space image analysis according to one embodiment of the present invention can derive essential objects that are not included as objects in the area among the essential objects for the area as objects that need to be installed, and among the objects that correspond to risk factors as objects that need to be removed, based on a safety factor DB that includes information on essential objects for each area and information on whether there are risk factors for each object (S105).

[0112] In addition, a method for proposing improvements to facilities for the elderly using residential space image analysis according to one embodiment of the present invention can generate a proposal drawing by indicating the installation location of the object requiring installation and the object requiring removal on the drawing (S107).

[0113] In addition, the method for proposing improvements to facilities for the elderly using residential space image analysis according to one embodiment of the present invention can transmit the proposed drawing to the user terminal (S109).

[0114] In addition, the method for proposing improvements to facilities for the elderly using residential space image analysis according to one embodiment of the present invention may be configured in the same way as the device for proposing improvements to facilities for the elderly using residential space image analysis disclosed in FIGS. 1 to 5.

[0116] The embodiments described above may be implemented as hardware components, software components, and / or combinations of hardware and software components. For example, the devices, methods, and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are also possible.

[0117] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0118] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or command the processing unit independently or collectively. Software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0119] Although the embodiments have been described above with reference to the limited drawings, those skilled in the art can apply various technical modifications and variations based on the above. For example, suitable results may be achieved even if the described techniques are performed in a different order than described, and / or if the components of the described system, structure, device, circuit, etc. are combined or assembled in a form different from described, or replaced or substituted by other components or equivalents.

[0120] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims set forth below.

Claims

Claim 1 In an electronic device, memory; and a processor connected to said memory; The processor comprises: receiving a drawing and a photograph of a target space from a user terminal; analyzing the drawing and the photograph through an artificial intelligence module to identify zones and objects for each zone of the target space; and, based on a safety element DB containing information on essential objects for each zone and information on whether each object is a risk factor, deriving essential objects that are not included as objects in the zone among the essential objects for the zone as objects requiring installation, deriving objects corresponding to risk factors among the objects as objects requiring removal, generating a proposed drawing by marking the installation location of the objects requiring installation and the objects requiring removal on the drawing, and transmitting the proposed drawing to the user terminal; the safety element DB further includes information on replacement objects that can replace the objects corresponding to risk factors; the processor marks the objects requiring removal on the proposed drawing, and if a replacement object exists for the objects requiring removal, also marks the replacement object; and the artificial intelligence module obtains the object's external shape and texture information from the photograph It includes an object recognition model that extracts and identifies the type of object, and a drawing analysis model that extracts the locations of walls, doors, and windows from the drawing to determine the structural layout of the space, and the processor matches the coordinates of the object identified through the object recognition model with the coordinate system of the target space identified through the drawing analysis model to finally identify the object located within each zone, and the artificial intelligence module includes a Convolutional Neural Network (CNN), a Recurrent Neural Network (RNN), a Generative Adversarial Network (GAN), a Transformer, and a Support Vector Machine (SVM,A model trained based on at least one algorithm (Support Vector Machine) is used, and the processor derives objects that do not correspond to objects requiring removal among all identified objects as general objects, derives a risk score for the general object based on the location of the general object, and if the risk score exceeds a preset first threshold risk score, sets the general object as an object requiring movement, if the risk score exceeds a preset second threshold risk score lower than the first threshold risk score but is less than or equal to the first threshold risk score, sets the general object as an object requiring movement caution, and if the risk score is less than or equal to the second threshold risk score, sets the general object as a safe object, distinguishes the object requiring movement, the object requiring movement caution, and the safe object and displays them on the proposed drawing, and the processor connects movement paths of a preset width between a plurality of preset movement nodes in the drawing, and for the general object, the number of movement paths overlapping with the area occupied by the general object and the overlapping The above risk score for the corresponding general object is derived based on the area, the above movement node includes the entrances of each zone in the above drawing and objects set as being used by the user, the above movement path width is set as the average shoulder width of users using the corresponding target space, and the above risk score is derived by the following mathematical formula, An electronic device characterized in that rs represents the risk score for the general object, n represents the number of paths overlapping with the area occupied by the general object, a_i represents the area overlapping with the i-th path and the area occupied by the general object, and oa represents the area of ​​the area occupied by the general object. Claim 2 delete Claim 3 delete

Images