Tatami mat laying area measurement support system

Abstract

To provide a tatami mat laying section measurement support system that makes it easy to take measurements. [Solution] A mobile terminal (200) displays a measurement target for a laying section in a first manner, determines the dimensions of the measurement target based on a photographed image of the laying section, and displays the measurement target with the determined dimensions in a second manner. The dimensions are determined by sending a request to a generation AI server (120) that includes image data of the photographed image and requests the generation of dimensional information, and obtaining dimensional information from the generation AI server (120) in response to the request. This makes it possible to know that the dimensions of the measurement target have been determined when the display of the measurement target changes from the first manner to the second manner, making measurement relatively easy compared to conventional methods. Furthermore, because dimensional information is obtained by an AI model (50) based on the photographed image, determining dimensions is relatively easy.

Description

[Technical Field]

[0001] The present invention relates to a system for assisting in the measurement of an area for laying tatami mats, and more particularly to a system for assisting in the measurement of an area for laying tatami mats that makes it easy to take measurements. [Background technology]

[0002] Conventionally, techniques for measuring an area for laying tatami mats are known, for example, from Patent Documents 1 and 2.

[0003] The technology (dimension measuring device) described in Patent Documents 1 and 2 comprises a circular base with three legs and a circular rotating table mounted on this base via bearings so that it can rotate freely. Gears are fixed concentrically to the circular base, and the rotating table is equipped with an incremental rotary encoder that detects the rotation angle, an incremental linear encoder that detects the length, a storage battery that serves as the power source for the device, a circuit board with a signal processing circuit built in, and an optical signal photodetector that receives the light beam from a remote control device. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP-A-9-294886 (

[0032]

[0033] ) [Patent Document 2] Japanese Patent Application Publication No. 5-149740 Summary of the Invention [Problem to be solved by the invention]

[0005] However, the techniques described in Patent Documents 1 and 2 require the use of special dimension measuring devices, which poses the problem that measuring requires specialized knowledge and skills and is not easy.

[0006] Therefore, the present invention was made with a focus on the unresolved problems of the conventional technology, and aims to provide a tatami-laying section measurement support system that makes it easy to take measurements. [Means for solving the problem]

[0007] [Invention 1] In order to achieve the above object, the tatami laying area measurement support system of Invention 1 comprises a first measurement object display means for displaying the measurement object of the tatami laying area in a first manner, a dimension specifying means for specifying the dimensions of the measurement object based on a photographed image of the laying area, and a second measurement object display means for displaying the measurement object whose dimensions have been specified by the dimension specifying means in a second manner different from the first manner.

[0008] With this configuration, the first measurement object display means displays the measurement object in the laying section in a first manner. When the dimension specifying means specifies the dimension of the measurement object based on the captured image, the second measurement object display means displays the measurement object whose dimensions have been specified in a second manner.

[0009] Here, dimensions include, for example, length, width, height, depth, thickness, diameter, radius, and angle.

[0010] Here, the present system may be realized as a single device, apparatus, terminal, or other device, or as a network system in which multiple devices, apparatus, terminals, or other devices are communicatively connected. In the latter case, each component may belong to any of the multiple devices as long as they are communicatively connected.

[0011] [Invention 2] Furthermore, the tatami laying area measurement support system of Invention 2 is the tatami laying area measurement support system of Invention 1, wherein the dimension specification means includes image information about the captured image, and the system has an input means for inputting a request to the AI ​​model requesting the generation of dimension information about the dimensions of the measurement object, and a dimension information acquisition means for acquiring the dimension information output from the AI ​​model in response to the request.

[0012] With this configuration, the input means inputs a request including image information and requesting the generation of dimensional information to the AI ​​model, and the dimensional information acquisition means acquires the dimensional information output from the AI ​​model in response to the request.

[0013] Here, input means includes, for example, directly inputting a request to the AI ​​model, or indirectly inputting the request to the AI ​​model via a process, function, device, network, or other means.

[0014] In addition, the dimensional information acquisition means includes, for example, directly acquiring the output information of the AI ​​model, or indirectly acquiring the output information of the AI ​​model via processing, function, device, network, or other means.

[0015] Furthermore, the request or the information contained therein may be configured in any format, such as vector data.

[0016] In addition, the image information can be composed of, for example, the captured image (including a still image or a moving image) itself, or it can be composed of information for identifying the captured image (for example, link information such as a name, number, ID, code, URL, etc.), or feature information regarding statistics or other features of the captured image.

[0017] [Invention 3] Furthermore, the Tatami laying area measurement support system of Invention 3 is the Tatami laying area measurement support system of Invention 2, and is equipped with processing means which performs a first process of discarding the dimensional information or a second process of notifying a predetermined notification destination without discarding the dimensional information, based on condition information which specifies a plurality of conditions according to the level of the dimensional information and the dimensional information acquired by the dimensional information acquisition means.

[0018] With this configuration, the processing means performs the first process or the second process based on the condition information and the acquired dimension information.

[0019] [Invention 4] Furthermore, the Tatami laying area measurement support system of Invention 4 is the Tatami laying area measurement support system of either Invention 2 or 3, wherein the dimension specification means is provided with dimension information selection means which acquires a plurality of pieces of dimension information for the same measurement object using the dimension information acquisition means, and selects from the plurality of pieces of dimension information acquired by the dimension information acquisition means that which meets a predetermined standard.

[0020] With this configuration, the dimension specifying means acquires multiple pieces of dimension information for the same measurement object, and the dimension information selecting means selects from the acquired multiple pieces of dimension information that meets a predetermined standard. [Effects of the Invention]

[0021] As explained above, according to the tatami mat area measurement support system of Invention 1, when the display of the object to be measured changes from the first mode to the second mode, it is possible to know that the dimensions of the object to be measured have been identified, making measurement relatively easier than before.

[0022] Furthermore, according to the tatami mat laying area measurement support system of Invention 2, dimensional information can be obtained using an AI model based on photographed images, making it relatively easy to identify dimensions.

[0023] Furthermore, the tatami mat laying area measurement support system of Invention 3 can respond according to the level of dimensional information obtained by the AI ​​model.

[0024] Furthermore, according to the tatami mat laying section measurement support system of Invention 4, it is possible to correct the variation in the output of the AI ​​model. [Brief explanation of the drawings]

[0025] [Figure 1] 1 is a block diagram showing a configuration of a network system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a diagram showing the hardware configuration of a tatami mat manufacturing support server 100. [Figure 3]4A and 4B are diagrams illustrating the data structures of a dimension table 400 and an obstacle table 402. [Figure 4] FIG. 1 is a functional block diagram of a generation AI server 120. [Figure 5] 10 is a flowchart showing a laying section measurement process. [Figure 6] 1 is a display screen of a mobile terminal 200. DETAILED DESCRIPTION OF THE INVENTION

[0026] An embodiment of the present invention will be described below, with reference to Figures 1 to 6 showing the embodiment. First, the configuration of this embodiment will be described.

[0027] FIG. 1 is a block diagram showing the configuration of a network system according to this embodiment. As shown in Fig. 1, the Internet 199 is connected to a tatami mat manufacturing support server 100 that supports the manufacturing of tatami mats, a generation AI server 120 that generates answer information in response to requests using an AI (Artificial Intelligence) model, and a base station 210. The base station 210 is connected to a plurality of mobile terminals 200 so that they can communicate wirelessly, and relays communication between the mobile terminals 200 and the Internet 199. The mobile terminals 200 are terminals used by people taking measurements at the measurement site.

[0028] [Tatami manufacturing support server 100] Next, the configuration of the tatami mat manufacturing support server 100 will be described. FIG. 2 is a diagram showing the hardware configuration of the tatami mat manufacturing support server 100. As shown in FIG.

[0029] The tatami mat manufacturing support server 100 automates the tatami mat manufacturing process. It receives dimensional information from the mobile terminal 200, measuring the dimensions of the area (e.g., a room) where the tatami mats will be laid. The received dimensional information is then registered separately in a dimension table 400 and an obstacle table 402. The optimal layout and accurate cutting shape of each tatami mat are automatically designed based on the dimensional information in tables 400 and 402 and a predetermined laying pattern. Then, the manufacturing equipment is controlled based on control data generated as a result of the design, thereby manufacturing tatami mats as designed. For example, the configuration of the control device 60 in Patent Document 1 can be adopted as the tatami mat manufacturing support server 100.

[0030] As shown in Figure 2, the tatami manufacturing support server 100 is made up of a CPU (Central Processing Unit) 30 which controls calculations and the entire system based on a control program, a ROM (Read Only Memory) 32 which has the CPU 30's control program and the like stored in advance in a specified area, a RAM (Random Access Memory) 34 which stores data read from the ROM 32 and the calculation results required in the CPU 30's calculation process, and an I / F (Interface) 38 which mediates the input and output of data to and from external devices, and these are connected to each other and able to send and receive data by a bus 39 which is a signal line for transferring data.

[0031] The I / F 38 is connected to external devices such as an input device 40 consisting of a keyboard, mouse, etc. that can input data as a human interface, a memory device 42 that stores data, tables, etc. as files, a display device 44 that displays a screen based on an image signal, and a signal line for connecting to the Internet 199.

[0032] [Data Structure] Next, the data structure of the storage device 42 will be described. 3 is a diagram showing the data structures of the dimension table 400 and the obstacle table 402. In the diagram, underlined attributes indicate primary keys.

[0033] As shown in FIG. 3, the storage device 42 stores a dimension table 400 and an obstacle table 402.

[0034] The dimension table 400 is a table that registers the basic dimensions of the laying section among the dimensions of the dimension information acquired from the mobile terminal 200. As shown in Fig. 3(a), the dimension table 400 is configured to have a column that registers a measurement ID for uniquely identifying the measurement of the laying section, a column that registers a case ID for uniquely identifying the case, a column that registers a measurer ID for uniquely identifying the measurer who performed the measurement, a column that registers the measurement date, and a column that registers the name of the laying section. It also has a column for registering side 1 (left side) of the laying section, a column for registering side 2 (rear side) of the laying section, a column for registering side 3 (right side) of the laying section, a column for registering side 4 (front side) of the laying section, a column for registering diagonal 1 of the laying section (from rear left to front right), a column for registering diagonal 2 of the laying section (from rear right to front left), a column for registering middle 1 (from left to right), a column for registering middle 2 (from rear to front), and columns for registering other information.

[0035] Obstacle table 402 is a table for registering the dimensions of obstacles present in the installation section, among the dimensions of the dimensional information acquired from mobile terminal 200. As shown in Fig. 3(b), obstacle table 402 is configured to have a column for registering a measurement ID, a column for registering an obstacle ID for uniquely identifying an obstacle, and a column for registering the type of obstacle. It also has a column for registering a reference side from sides 1 to 4 of the installation section, a column for registering the distance from the reference side to the obstacle, a column for registering the width of the obstacle, a column for registering the depth of the obstacle, and a column for registering other information.

[0036] [Generation AI Server] Next, the configuration of the generation AI server 120 will be described. Like the tatami mat manufacturing support server 100, the generation AI server 120 has a hardware configuration similar to that of a general computer, with a CPU, ROM, RAM, I / F, etc. connected via a bus, and is configured as, for example, a cloud server.

[0037] FIG. 4 is a functional block diagram of the generation AI server 120. As shown in Figure 4, the generation AI server 120 is configured to include multiple AI models 50, an AI model control unit 52 that controls the AI ​​models 50, and a knowledge base 54 that registers data that the AI ​​models 50 refer to for inference.

[0038] The AI ​​model 50 is an AI model trained on a large data set and is a highly versatile model capable of performing a variety of tasks. For example, a large language model can be used as the AI ​​model 50. A large language model is a deep learning model that pre-trains a language model, which models human-spoken language based on its occurrence probability, from a massive amount of data. When a prompt is input, the large language model statistically infers the probability of generating the next word from the sentence included in the input prompt and outputs the inference result. For example, known technologies described on the internet sites "https: / / chatgpt-lab.com / n / n418d3aa56f0b" and "https: / / agirobots.com / chatgpt-mechanism-and-problem / " can be used as the large language model. More specifically, for example, Titan Text G1 - Express, Titan Text G1 - Lite, Titan Image Generator G1, Titan Embeddings G1 - Text, Titan Embeddings Text V2, Titan Multimodal Embeddings G1, Claude, Claude Instant, Claude 3 Sonnet, Claude 3 Haiku, Claude 3 Opus, Jurassic-2 Mid, Jurassic-2 Ultra, Command, Command Light, Command R, Command R+, Embed English, Embed Multilingual, Llama 2 Chat 13B, Llama 2 Chat 70B, Llama 2 13B, Llama 2 70B, Llama 3 8b Instruct, Llama 3 70b Instruct, Mistral 7B Instruct, Mixtral 8X7B Instruct, Mistral Large, and Stable Diffusion XL can be adopted.

[0039] The AI ​​model control unit 52 selects one of the multiple AI models 50 to be used for inference in response to a selection request from the request processing unit 58. Furthermore, when a reference request is input from the request processing unit 58, the AI ​​model control unit 52 causes the selected AI model 50 (hereinafter referred to as the "selected AI model") to refer to the data in the knowledge base 54 in response to the input reference request. Furthermore, when a prompt is input from the request processing unit 58, the input prompt is input to the selected AI model. Then, when an execution request is input from the request processing unit 58, the AI ​​model control unit 52 causes the selected AI model to execute inference in response to the input execution request, obtains an inference result from the selected AI model, and outputs the obtained inference result to the request processing unit 58.

[0040] The knowledge base 54 can register reference information to be referenced for inference. The reference information in the knowledge base 54 is in a data format (for example, vector data) that can be referenced by the AI ​​model 50.

[0041] The generation AI server 120 is further configured to include a request receiving unit 56 that receives requests, a request processing unit 58 that processes the requests received by the request receiving unit 56, and a response information sending unit 60 that sends response information to the request received by the request receiving unit 56 to the mobile terminal 200.

[0042] The request receiving unit 56 receives a request for generating answer information from the mobile terminal 200 and outputs the received request to the request processing unit 58. The request includes (1) image data and other parameters, (2) a generation request for generating answer information, (3) a selection request for selecting an AI model 50, and (4) a reference request for referencing reference information in the knowledge base 54. (3) and (4) are not essential but are included additionally.

[0043] If the request received by the request receiving unit 56 includes a selection request or a reference request, the request processing unit 58 outputs the selection request or the reference request to the AI ​​model control unit 52. Furthermore, based on the request received by the request receiving unit 56, the request processing unit 58 generates a prompt that instructs the AI ​​model 50. The prompt, for example, requests the AI ​​model 50 to generate dimensional information for the laying section by referencing image data in the knowledge base 54. The generated prompt and execution request are then output to the AI ​​model control unit 52. If an inference result is input from the AI ​​model control unit 52 in response to the execution request, the request processing unit 58 outputs the input inference result to the answer information sending unit 60.

[0044] The answer information transmitting unit 60 transmits answer information including the inference result input from the request processing unit 58 to the mobile terminal 200 .

[0045] The generation AI server 120 further comprises a request receiving unit 62 that receives requests, and a reference information registration unit 64 that registers reference information in the knowledge base 54.

[0046] The request receiving unit 62 receives a request for registering reference information from the mobile terminal 200, and outputs the received request to the reference information registering unit 64. The request includes (1) image data and an image ID.

[0047] The reference information registration unit 64 stores the image data included in the request received by the request receiving unit 62 in storage (not shown) and converts it into a data format (e.g., vector data) that can be referenced by the AI ​​model 50. Vector data can be generated using a technology (embedding) that converts data including characters, images, audio, etc. into a numerical vector. The image data converted into vector data is then associated with an image ID and registered in the knowledge base 54. The AI ​​model control unit 52 causes the selected AI model to reference the image data in response to a reference request from the request processing unit 58.

[0048] [Mobile terminal 200] Next, the configuration of the mobile terminal 200 will be described. The mobile terminal 200 is composed of a portable terminal such as a smartphone or tablet. The hardware configuration is made up of a CPU, ROM, RAM, I / F, etc. connected via a bus. A touch panel, a storage device, a camera, a GPS, an acceleration sensor, a gyro sensor, a wireless communication device, etc. are connected to the I / F.

[0049] Next, the operation of this embodiment will be described. FIG. 5 is a flowchart showing the laying section measurement process.

[0050] The CPU of the mobile terminal 200 is composed of an MPU (Micro-Processing Unit) or the like, and starts a predetermined program stored in a predetermined area of ​​the ROM, and in accordance with the program, executes the laying section measurement process shown in the flowchart of Fig. 5. When the laying section measurement process is executed by the CPU, as shown in Fig. 5, it first proceeds to step S100.

[0051] In step S100, an image captured by a camera is acquired from the camera, and the process proceeds to step S102, where a measurement target setting process is executed.

[0052] In the measurement target setting process, first, a wireframe is generated by analyzing the photographed image acquired in step S100, in which a measurement target whose dimensions are to be determined is represented by lines. The measurement target, for example, includes dimension lines corresponding to the dimensional information of tables 400 and 402, such as sides 1 to 4 of the installation area, diagonals 1 and 2 of the installation area, middles 1 and 2, and dimension lines of obstacles. The dimension lines of obstacles include, for example, a reference side, distance from the reference side, width, and depth. The wireframe is then displayed superimposed on the photographed image acquired in step S100. The superimposed display may involve displaying a portion of the wireframe (the measurement target) in correspondence with the location of the measurement target in the photographed image, or all or a portion of the wireframe may be displayed independently of the location of the measurement target in the photographed image.

[0053] Second, since the presence of tatami wedges in the laying section is a prerequisite for measurement, the captured image acquired in step S100 is analyzed to determine whether tatami wedges are present in the laying section, and if it is determined that tatami wedges are present, a tatami wedges flag is set. The determination of tatami wedges can also be made for each side of the laying section. If the analysis of the captured images has been completed for the main parts of the laying section (for example, all four sides or all parts where tatami wedges are expected to exist), or if the tatami wedges flag has not been set when the processing of step S116 has been completed, measurement is interrupted.

[0054] Third, by analyzing the captured image acquired in step S100, it is determined whether the installation area is a polygon other than a square, whether each side of the installation area is straight, and whether there are any notches or the like in the installation area.If it is determined that the installation area is a polygon other than a square, if it is determined that any side of the installation area is not straight, or if it is determined that there are any notches or the like in the installation area, the object to be measured is defined as an uneven polygon and a wireframe is generated.

[0055] FIG. 6 shows the display screen of the mobile terminal 200. Next, the process proceeds to step S104, where measurement targets on the wire frame displayed in step S102, whose dimensions have not been specified, are displayed in a first manner (for example, dotted lines). In the example of Fig. 6, parts 500 and 502 of the wire frame are displayed superimposed on the captured image, and of these, measurement target 500, whose dimensions have not been specified, is displayed in dotted lines.

[0056] Next, the process proceeds to step S106, where a dimension specification process is executed. In the dimension identification process, a request for generating dimension information regarding the dimensions of the measurement object is sent to the generation AI server 120. The request includes (1) image data of the captured image acquired in step S100, (2) a generation request to generate multiple pieces of dimension information for the same measurement object, and (3) a selection request to select a specific AI model 50. In response to the request, the dimension information is obtained from the generation AI server 120 as response information.

[0057] Next, the process proceeds to step S108, where a matching selection process is executed. In the compatibility selection process, the dimension information acquired in step S106 for the same measurement target is selected based on a predetermined standard. Specifically, the dimension information with the highest compatibility is selected. The compatibility can be determined, for example, by calculating the error between the expected dimensions or their ratios of the measurement target's measurement target based on statistical information (e.g., statistical information on dimensions or their ratios) obtained from the measurement of multiple measurement areas, taking into account the relationship with the dimensions of measurement targets with specified dimensions, if any. For example, if polygon A is an expected measurement area consisting of the expected dimensions or their ratios, and polygon B is a measured measurement area consisting of dimension X and the specified dimensions, the compatibility of polygon B can be calculated as the distortion ratio of polygon B to polygon A (e.g., the area of ​​the intersection of A and B / the area of ​​the union of A and B).

[0058] Next, the process proceeds to step S110, where a discard notification process is executed. In the discard notification process, it is determined whether the dimensional information, etc. selected in step S108 satisfies the conditions of a condition table in which conditions and actions are associated with each level of dimensional information, and if it is determined that the conditions are satisfied, processing related to the action corresponding to the condition table is executed.

[0059] The condition table can register (1) the conditions under which dimensional information, etc., is within the discard range, and the action of discarding the dimensional information selected in step S108 in association with each other. The discard range defines the range of dimensional information to be discarded. If this condition is met, the dimensional information selected in step S108 is discarded.

[0060] As the discard range, the following (a), (b), and (c) can be defined as cases where the dimension selected in step S108 exceeds the reference value or reference range.

[0061] (a) is the case where the measured laying section consisting of the dimensions selected in step S108 and the specified dimensions is a polygon, and the sum of the interior angles of the polygon exceeds a predetermined range. For example, for a triangle, the sum of the interior angles exceeds the range of 180°±α, for a quadrangle, the sum of the interior angles exceeds the range of 360°±α, and for a pentagon, the sum of the interior angles exceeds the range of 540°±α.

[0062] (b) is a case where the end points of the straight line to be measured according to the dimension selected in step S108 and another straight line to be measured that is parallel to this do not match.

[0063] (c) is a case where the length of the side, the angle between the sides, and the height of the measurement target related to the dimensions selected in step S108 each exceed the predetermined range.

[0064] The condition table can register (2) conditions under which dimensional information, etc. falls within the measurer notification range, and actions for notifying the measurer, in association with each other. The measurer notification range defines the range of dimensional information for which notification is to be sent to the measurer. As for the measurer notification range, one or two of (a), (b), and (c) above can be set as the discard range, while the rest can be defined. If this condition is met, the measurer is notified. The notification can include the dimensional information selected in step S108. The measurer's email address, account information, etc. can be set as the notification destination.

[0065] The condition table can register (3) conditions under which dimension information, etc. falls within the designer notification range, and actions for notifying the tatami mat designer in association with each other. The designer notification range defines the range of dimension information for which notification is to be sent to the designer. If this condition is met, the designer is notified. The dimension information selected in step S108 can be included in the notification. The designer's email address, account information, etc. can be set as the notification destination.

[0066] As the designer notification range, for example, the following (d) and (e) can be defined. (d) is a case where the dimensions selected in step S108 differ from the specifications of the tatami mat.

[0067] (e) is the case where the tatami mat before replacement is present in the laying section and its tatami mat surface is made of a predetermined material. The material of the tatami mat surface can be determined by analyzing the photographed image acquired in step S100. For example, if the weft threads of the tatami mat surface are natural rush, resin, or machine-spun Japanese paper, and the warp threads of the tatami mat surface are hemp, cotton-linen, cotton, cotton, or resin, and the combination of weft and warp threads is a predetermined combination, a notification is sent to the designer to make corrections.

[0068] Next, the process proceeds to step S112, where it is determined whether the dimension information selected in step S108 was not discarded in step S110 and the dimensions were able to be specified. If it is determined that the dimensions were able to be specified (YES), the process proceeds to step S114, where the measurement objects on the wireframe displayed in step S102 whose dimensions have been specified are displayed in a second manner (e.g., solid lines). In the example of FIG. 6, portions 500 and 502 of the wireframe are displayed superimposed on the captured image, and the measurement object 502 whose dimensions have been specified is displayed in solid lines. In the figure, side 2 (the back side), middle 1 (from the left to the right), and middle 2 (from the back to the front) are displayed in solid lines, indicating that their dimensions have been specified. In contrast, diagonal line 1 (from the back left to the front right) and diagonal line 2 (from the back right to the front left) are displayed in dotted lines, indicating that their dimensions have not been specified.

[0069] Next, the process proceeds to step S116, where it is determined whether the dimensions have been determined for all measurement objects in the wireframe displayed in step S102, and if it is determined that the dimensions have been determined for all measurement objects (YES), the process ends and returns to the original process.

[0070] As the person taking pictures of the laying area using the camera on the mobile terminal 200, changing position and orientation, the objects to be measured will one after another change to the second form, and this process is repeated until all objects to be measured have changed to the second form, completing the measurement. Once the measurement is complete, the mobile terminal 200 sends the specified dimensional information to the tatami mat production support server 100, which then registers the received dimensional information in tables 400 and 402.

[0071] On the other hand, if it is determined in step S116 that the dimensions of any of the measurement targets have not been specified (NO), the process proceeds to step S100.

[0072] On the other hand, if it is determined in step S112 that the dimensions cannot be specified (NO), the process proceeds to step S116.

[0073] Next, the effects of this embodiment will be described. In this embodiment, the mobile terminal 200 displays the measurement object of the installation section in a first manner, determines the dimensions of the measurement object based on a photographed image of the installation section, and displays the measurement object whose dimensions have been determined in a second manner.

[0074] This makes it easier to take measurements than before, since when the display of the measurement object changes from the first state to the second state, it is possible to know that the dimensions of the measurement object have been identified. All that is needed is to repeat the photographing until all measurement objects are in the second state.

[0075] Furthermore, in this embodiment, the mobile terminal 200 transmits a request to the generation AI server 120, which includes image data of the captured image and requests the generation of dimension information, and obtains the dimension information from the generation AI server 120 in response to the request.

[0076] This allows dimensional information to be obtained by the AI ​​model 50 based on the captured image, making it relatively easy to identify the dimensions.

[0077] Furthermore, in this embodiment, if the dimension information, etc. selected in step S108 satisfies the conditions in a condition table in which conditions and actions are registered in correspondence with each level of dimension information, the mobile terminal 200 executes processing related to the corresponding action in the condition table.

[0078] This allows for a response according to the level of dimensional information obtained by the AI ​​model 50.

[0079] Furthermore, in this embodiment, the mobile terminal 200 acquires a plurality of pieces of dimensional information for the same measurement object, and selects one piece of dimensional information with the highest degree of compatibility from the plurality of pieces of dimensional information acquired for the same measurement object.

[0080] This makes it possible to correct variations in the output of the AI ​​model 50. In this embodiment, step S104 corresponds to the first measurement object display means of invention 1, step S106 corresponds to the dimension specifying means of invention 1, 2 or 4, the input means of invention 2, or the dimension information acquiring means of inventions 2 to 4, and step S108 corresponds to the dimension information selecting means of invention 4. Also, step S110 corresponds to the processing means of invention 3, and step S114 corresponds to the second measurement object display means of invention 1.

[0081] [Modification] In the above embodiment and its variations, the generation of the wireframe, the determination of tatami mat positioning, the determination of polygons, the determination of straight lines, the determination of pillar notches, etc., and the determination of the material of the tatami mat are performed by analyzing the captured image, but this is not limiting, and a configuration can be adopted in which some or all of these are performed by the AI ​​model 50, similar to the processing in step S106.

[0082] The following configuration can be employed as a configuration for generating a wireframe, for example: A request for generating a wireframe is sent to the generation AI server 120. The request includes (1) image data of the captured image acquired in step S100, (2) a generation request for generating a wireframe, and (3) a selection request for selecting a predetermined AI model 50. In response to the request, wireframe information is acquired from the generation AI server 120 as response information.

[0083] The following configuration can be used, for example, to determine whether tatami mats are gathered, whether they are polygons, whether they are straight lines, or whether there are any notches or the like in the laying section. A request is sent to the generation AI server 120 requesting determination information indicating whether tatami mats are gathered, whether they are polygons other than quadrilaterals, whether each side of the laying section is a straight line, or whether there are any notches or the like in the laying section. The request includes (1) image data of the captured image acquired in step S100, (2) a generation request to generate determination information, and (3) a selection request to select a predetermined AI model 50. In response to the request, the determination information is obtained as response information from the generation AI server 120.

[0084] The following configuration, for example, can be employed as a configuration for determining the material of a tatami facing: A request for generating material information related to the material of the tatami facing is sent to the generation AI server 120. The request includes (1) image data of the captured image acquired in step S100, (2) a generation request for generating material information, and (3) a selection request for selecting a predetermined AI model 50. In response to the request, the material information is acquired from the generation AI server 120 as response information.

[0085] Furthermore, in the above embodiment and its variants, the dimensions are identified using the AI ​​model 50, but this is not limited to this, and a configuration can be adopted in which the dimensions are identified by analyzing the captured image, similar to the processing in steps S102 and S110.

[0086] In the above embodiment and its variations, measurement objects are displayed with dotted or solid lines. However, specific display modes include, for example, adding dotted or solid lines or other line types, line thicknesses, colors, arrows, or other decorations to the measurement objects, adding text in a specific font or font size to the measurement objects, and adding annotations, icons, links, or other elements to the measurement objects. Any mode can be adopted as long as it allows for distinguishing between measurement objects with unspecified dimensions and measurement objects with specified dimensions. These modes can also be combined arbitrarily. For example, a configuration can be adopted in which measurement objects with unspecified dimensions are displayed in a specific color and measurement objects with specified dimensions are displayed with an icon.

[0087] In the above embodiment and its modified examples, the image data of the captured image is included in the request, but this is not limiting. The image data of the captured image may be associated with an image ID and registered in the knowledge base 54, and the request may include the image ID and a reference request instead of the image data. In addition, the request may include a URL (Uniform Resource Locator) to the image data or other access information instead of the image data.

[0088] In the above embodiment and its modifications, if the dimensional information etc. satisfies the conditions, the dimensional information is not discarded but is notified to the person making the measurement or the designer. In this case, however, a configuration can be adopted in which the person making the measurement or the designer receiving the notification requests the mobile terminal 200 to discard the dimensional information, and the mobile terminal 200 discards the dimensional information selected in step S108 in response to the received discard request. Depending on the content of the notification, the person making the measurement or the designer can request the person making the measurement to redo the measurement of the measurement object related to the notification.

[0089] Furthermore, in the above embodiment and its modified examples, multiple pieces of dimensional information were obtained for the same measurement object, but this is not limited to this. The following configuration can be adopted as a configuration in which an average value of the degree of conformance or other statistical quantity is calculated for multiple pieces of dimensional information, and the measurement accuracy is adjusted according to the calculated average value of the degree of conformance or other statistical quantity.

[0090] The first configuration can be used to increase or decrease the number of dimensional information pieces generated for a measurement object depending on the average value of the degree of conformance or other statistical values. For example, for a measurement object with a low average value of the degree of conformance or other statistical values, the number of pieces of dimensional information generated is increased, and additional dimensional information is generated by the AI ​​model 50, or all dimensional information is regenerated, and the conformance selection process of step S108 is executed.

[0091] The second configuration can be to increase or decrease the resolution of the camera of mobile terminal 200 depending on the average value of the degree of conformance or other statistical quantities. For example, for a measurement target with a low average value of the degree of conformance or other statistical quantities, the camera resolution is increased and the image is re-photographed, and the dimension determination process of step S106 is executed based on the re-photographed image.

[0092] The third configuration can be to apply stricter conditions in the discard notification process of step S110 depending on the average value of the degree of conformance or other statistical values. For example, multiple condition tables are prepared depending on the level of strictness of the conditions, and for measurement targets with low average value of the degree of conformance or other statistical values, a higher level condition table is applied instead of the normal condition table to execute the discard notification process of step S110.

[0093] In the fourth configuration, the measurer or designer who receives the notification requests measurement accuracy from the mobile terminal 200, and the mobile terminal 200 changes the adjustment elements (number of generations, resolution, strict conditions) in the first to third configurations according to the received measurement accuracy request.

[0094] In the above embodiment and its modified examples, the wire frame is displayed superimposed on the captured image, but this is not limiting, and a configuration in which the wire frame is displayed separately from the captured image may be adopted. For example, the screen may be switched to display the wire frame on a separate screen.

[0095] In the above embodiment and its modified examples, the measurement target of the wireframe is displayed superimposed on the corresponding portion of the photographed image. However, this is not limited to this. A configuration in which the measurement target of the wireframe does not correspond to the corresponding portion of the photographed image, but a part or the whole of the wireframe is superimposed on the photographed image can be adopted. In this case, a part or the whole of the wireframe can be displayed as, for example, a plan view, a side view, or a perspective view. These views can be switched as needed.

[0096] Furthermore, in the above embodiment and its variations, the measurement target setting process in step S102 employs a process for determining whether tatami mats are being pushed together. However, this is not limited to this, and other configurations are possible: (1) a configuration in which no process for determining whether tatami mats are being pushed together is provided; or (2) a configuration in which measurement is not interrupted and information indicating whether tatami mats are being pushed together is included in the measurement information.

[0097] Furthermore, in the above embodiment and its variations, the measurement target setting process in step S102 employs a process for determining whether the laying area is a polygon other than a square, but is not limited to this. Alternatively, the following may be employed: (1) a configuration that does not employ a process for determining polygons, etc.; (2) a configuration that determines whether the old tatami mat in the laying area where the replaced tatami mat (referred to as the "old tatami mat" in this paragraph) is present is a polygon other than a square, whether each side of the old tatami mat is a straight line, or whether the old tatami mat has a notch or the like; or (3) a configuration that does not interrupt the measurement, and includes shape information regarding the shape of the laying area or the old tatami mat in the dimension information.

[0098] Furthermore, in the above embodiment and its modified example, a plurality of pieces of dimensional information are acquired for the same measurement target, but this is not limiting, and a configuration in which one piece of dimensional information is acquired can also be adopted.

[0099] Furthermore, in the above embodiment and its modified examples, the compatibility selection process in step S108 is provided, but the present invention is not limited to this, and a configuration that does not include the compatibility selection process in step S108 can also be adopted.

[0100] Furthermore, in the above embodiment and its modified example, the discard notification process in step S110 is provided, but the present invention is not limited to this, and a configuration in which the discard notification process in step S110 is not provided can also be adopted.

[0101] Furthermore, in the above embodiment and its variations, the processing of steps S102, S106 to S110 is configured to be executed by the mobile terminal 200, but this is not limited to this, and a configuration in which the processing is executed by the tatami manufacturing support server 100, the generation AI server 120, or other devices can also be adopted.

[0102] Furthermore, in the above embodiment and its modifications, the generation AI server 120 is configured with the functions 50 to 64 integrated as in the above embodiment, but this is not limited to this, and some functions may be configured on separate servers, etc. The same applies to the tatami mat manufacturing support server 100.

[0103] Furthermore, while the above embodiment and its variations are implemented as a network system, the present invention is not limited to this and may be implemented as a single device or application. For example, a configuration may be adopted in which an on-device AI is implemented in the mobile terminal 200 instead of the AI ​​model 50.

[0104] Furthermore, in the above embodiment and its modifications, the case where the present invention is applied to a network system consisting of the Internet 199 has been described, but the present invention is not limited to this, and may be applied, for example, to a so-called intranet that communicates using the same method as the Internet 199. Of course, the present invention is not limited to a network that communicates using the same method as the Internet 199, and may be applied to a network of any communication method.

[0105] Furthermore, in the above embodiment and its variations, the tatami manufacturing support server 100 is configured to use the storage device 42, but this is not limiting and it can also be configured to use an external storage device such as a database server. The same applies to the knowledge base 54 of the generation AI server 120 and the storage device of the mobile terminal 200.

[0106] Furthermore, in the above embodiment and its variants, the processing shown in the flowchart of FIG. 5 is performed by executing a program that is pre-stored in ROM. However, this is not limited to this, and the program showing these procedures may be read into RAM from a storage medium on which the program is stored and executed.

[0107] Furthermore, in the above embodiment and its modified examples, the present invention has been applied to a case where the measurement of a tatami mat laying area is assisted, but it is not limited to this and can be applied to other cases as long as it does not deviate from the spirit of the present invention. [Explanation of symbols]

[0108] 100...Tatami manufacturing support server, 30...CPU, 32...ROM, 34...RAM, 38...I / F, 39...bus, 40...input device, 42...storage device, 44...display device, 120...generation AI server, 50...AI model, 52...AI model control unit, 54...knowledge base, 56, 62...request receiving unit, 58...request processing unit, 60...answer information sending unit, 64...reference information registration unit, 200...mobile terminal, 210...base station, 199...Internet, 400...dimension table, 402...obstacle table, 500...measurement target (dotted line), 502...measurement target (solid line)

Claims

1. a first measurement object display means for displaying a measurement object of the tatami mat laying area in a first manner; a size specifying means for specifying the size of the measurement target based on a photographed image of the installation section; and a second measurement object display means for displaying the measurement object whose dimensions have been identified by the dimension identification means in a second manner different from the first manner.

2. In claim 1, The dimension specifying means an input means for inputting a request to generate dimensional information regarding the dimensions of the measurement object, the request including image information regarding the captured image, into the AI ​​model; A tatami mat laying area measurement support system characterized by having a dimension information acquisition means that acquires dimension information output from the AI ​​model in response to the request.

3. In claim 2, A tatami mat laying area measurement support system characterized by comprising a processing means for performing a first process of discarding the dimensional information or a second process of notifying a predetermined notification destination without discarding the dimensional information, based on condition information that specifies multiple conditions according to the level of the dimensional information and the dimensional information acquired by the dimensional information acquisition means.

4. In any one of claims 2 and 3, The dimension specifying means acquires a plurality of pieces of dimension information for the same measurement object using the dimension information acquiring means, The tatami mat laying section measurement support system is characterized by comprising a dimension information selection means for selecting dimension information that meets predetermined standards from the plurality of dimension information acquired by the dimension information acquisition means.

Images