An intelligent internet-of-things control system and method for panel homes

Abstract

The application discloses an intelligent internet-of-things control system and method for plate home, and relates to the technical field of intelligentization, comprising: establishing a repair record of a plate in the intelligent home, extracting a plurality of target records from the repair record; obtaining a repair area of the plate of the target record, analyzing a plurality of corresponding internal defects in the repair area, and obtaining a wear degree corresponding to the target record; intercepting a historical monitoring video of the repair area, obtaining a wear coefficient of the target record, and establishing a scatter plot of the wear degree with the wear coefficient; obtaining a monitoring video of a to-be-detected plate from the last repair to the target time, and judging the timing of a repair prompt for the to-be-detected plate. The application obtains historical repair records, analyzes the living environment and user daily use habits of the intelligent home, reasonably judges the timing of a repair prompt for the to-be-detected plate, and avoids resource waste or safety hazard problems caused by early or late prompts.

Description

Technical Field

[0001] This invention relates to the field of intelligent technology, specifically to an intelligent IoT control system and method for panel furniture. Background Technology

[0002] Smart homes offer convenience and comfort to modern life, allowing people to remotely control various home appliances via mobile devices, greatly improving the convenience of life. Smart homes encompass a variety of wood-based panels, commonly including solid wood flooring. These panels form the foundation of home furnishing products and play a crucial role in the smart home system. After prolonged use, these panels gradually wear down, damaging the protective layer on the surface, affecting appearance and structural stability, and making them prone to absorbing and breeding bacteria, and even releasing harmful substances. Therefore, it is necessary to perform repair operations such as reinforcement, sanding, and filling on the panels.

[0003] However, the current judgment on whether board materials need repair is mainly done manually, which is not only subjective but also does not take into account the smart home living environment and users' daily usage habits. This can lead to unreasonable timing of repair operations, with premature repairs causing waste of resources and unnecessary economic expenditures, and delayed repairs causing safety hazards. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent IoT control system and method for panel furniture, so as to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] An intelligent IoT control method for panel furniture includes the following steps:

[0007] Step S100: Establish repair records for the boards in the smart home, extract and analyze the time of each repair of the boards corresponding to the repair records in history, and then extract several target records from the repair records;

[0008] Step S200: Obtain the repair area of ​​the board corresponding to the target record, take images of the repair area before and after the repair, obtain the feature value of each internal defect based on the changes of several internal defects in the images before and after the repair, and obtain the wear degree corresponding to the target record based on the weight of each internal defect.

[0009] Step S300: Capture the historical surveillance video of the repair area corresponding to the target record, extract and analyze the moving speed of the moving object when passing through the repair area in the surveillance video, and then obtain the wear coefficient corresponding to the target record. Based on the wear degree, establish a scatter plot of the wear degree changing with the wear coefficient.

[0010] Step S400: Obtain the monitoring video of the board to be inspected from the last repair to the target time, obtain the wear coefficient of the board to be inspected at the target time, pre-set the maximum wear degree of the board to be inspected, and obtain the maximum wear coefficient of the board to be inspected based on the scatter plot. Based on the wear coefficient at the target time, determine the timing of repair prompts for the board to be inspected.

[0011] Furthermore, step S100 includes:

[0012] Step S110: Obtain the repair time and target board material to be repaired for each repair record in the smart home, extract all repair records corresponding to a target board material B, obtain repair record R2 that is adjacent in time and later than a repair record R1, take the time interval between record R1 and record R2 as the usage period corresponding to record R2 in board material B, and then obtain the usage duration corresponding to all repair records, and sort each repair record in chronological order.

[0013] Step S120: Establish a function to change the usage time with the sequence number, and mark the coordinates corresponding to each repair record in the function; obtain the coordinates P corresponding to a certain repair record R0, take the coordinates of the repair record with the previous sequence number corresponding to record R0 and the vector pointing to coordinate P as V1, take the vector of coordinate P and the vector pointing to the coordinates of the repair record with the next sequence number corresponding to record R0 as V2, take the angle between the two vectors as the target angle of repair record R0, if the target angle is less than the preset angle threshold, then take repair record R0 as the target record, and then obtain all target records.

[0014] In this scheme, target records are set to filter out cases where board repair operations are performed due to special circumstances. Under normal circumstances, it is difficult to predict when board repair operations will be performed due to special circumstances, and these cases are not repairs performed according to the normal wear and tear pattern. By filtering out these records and using target records to determine the timing of board repairs, the accuracy and reliability of the judgment are improved. The main judgment criterion is: for the same board, under normal wear and tear patterns, the time interval between two repairs will not be too large. This is represented by a target angle. When the target angle is less than a preset angle threshold, it is judged as a target record.

[0015] Furthermore, step S200 includes:

[0016] Step S210: Obtain the repair area of ​​the board corresponding to a target record, and take images G1 before repair and G2 after repair of the repair area. Internal defects include cracks, decay and holes. Apply an edge detection algorithm to images G1 and G2 to obtain binary images T1 and T2 corresponding to images G1 and G2 respectively. Then obtain the number of pixels N1 and N2 in the crack area of ​​images T1 and T2, and obtain the first feature value R1 = 1-N2 / N1 when the internal defect is a crack.

[0017] Internal defects in solid wood flooring related to wear and tear include cracks, moisture content issues, rot, and insect infestation. These defects accelerate surface wear, affecting the floor's lifespan and appearance. Cracks are near-straight lines on the surface of solid wood flooring; the more pixels corresponding to a cracked area, the greater the degree of wear. Rotten wood is prone to wear and damage, and the floor surface may develop dents, cracks, and abrasion marks, leading to deformation and loss of original strength, thus accelerating wear. Wear and tear can also accelerate the decay process; when the wood surface is worn, the exposed wood may be more susceptible to moisture and fungal attack, further accelerating decay. When the wood surface is worn, the wood fibers may gradually wear down and break, eventually forming holes.

[0018] Step S220: Obtain grayscale images S1 and S2 corresponding to images G1 and G2 respectively, set the highest grayscale level to Q level, collect all pixel grayscale values ​​according to the grayscale value of each pixel in grayscale images S1 and S2, and then obtain the proportion of each grayscale level, and establish grayscale histograms H1 and H2 corresponding to grayscale images S1 and S2, with the ratio changing with the grayscale level, calculate the cosine similarity cos(H) between grayscale histograms H1 and H2, and then obtain the second feature value R2 = 1 - cos(H) corresponding to the internal defect being decay.

[0019] Step S230: Establish a neural network model. Obtain several images with holes and input them into the neural network model for training to obtain the trained neural network model. Substitute image G1 into the trained neural network model to obtain the number of holes N on image G1, and then obtain the third feature value R3 = 1 - e when the internal defect is a hole. -N Where e is a natural constant; weights are pre-set for each type of internal defect, and the wear degree corresponding to a target record is obtained based on the feature values ​​R1, R2, and R3: Where M = 3, W m It is the weight corresponding to the m-th type of internal defect, 1≤m≤M.

[0020] Furthermore, step S300 includes:

[0021] Step S310: Obtain the repair area corresponding to a certain target record Y. According to Step S110, obtain the usage period corresponding to record Y, and intercept the monitoring video segment including the repair area within the usage period; Take the range corresponding to the repair area in the monitoring video segment as the first area, obtain the rectangular range corresponding to the partial part of a certain moving object in the monitoring video segment, and take the rectangular range as the second area;

[0022] Take the moment when the partial part of a certain moving object first enters the repair area as D1, and take the moment when the partial part first leaves the repair area after moment D1 as D2. If within the time between moment D1 and moment D2, there is a moment when the intersection area of the first area and the second area is greater than the preset area threshold, then take the time period between moment D1 and moment D2 as the characteristic time period;

[0023] Step S320: Obtain the moving distance L of a certain moving object within the characteristic time period, and further obtain the characteristic moving speed of a certain moving object within the characteristic time period where, ln is the logarithmic function; Further, obtain the characteristic moving speeds corresponding to all the characteristic time periods within the usage period, and add up all the characteristic moving speeds as the wear coefficient corresponding to the target record Y; Further, according to the wear coefficient and wear degree of each target record, establish a scatter plot of the wear degree changing with the wear coefficient.

[0024] The wear of solid wood floors is usually related to the speed when people step on them. When walking or running quickly, the friction between the sole and the floor will increase, and a large impact force will be generated. This impact force will cause the pressure borne by the floor to increase instantaneously, exceeding the bearing capacity of the floor material, resulting in damage to the internal structure of the floor. In the long run, it may cause problems such as cracks, looseness, and even deformation of the floor, further aggravating the wear degree of the floor. Therefore, when the speed is fast and the number is large when passing through the solid wood floor, that is, the larger the characteristic moving speed V, the larger the wear coefficient should be.

[0025] Further, Step S400 includes:

[0026] Step S410: Obtain the monitoring video of the to-be-detected board from the last repair to the target moment, with a duration of F, and obtain the wear coefficient C0 corresponding to the to-be-detected board at the target moment; Set that a repair prompt is required when the to-be-detected board reaches the maximum wear degree X0. Obtain all the wear coefficients in the scatter plot where the wear degree is within the range of [k1×X0, k2×X0], where k1 and k2 are the first ratio and the second ratio respectively, 0 < k1 < 1 < k2, and obtain the average wear coefficient C1; [[ID=二十]]

[0027] Step S420: If the average wear coefficient C1 is greater than the wear coefficient C0, promptly prompt the board to be inspected to need repair. If the average wear coefficient C1 is not greater than the wear coefficient C0, after a period of F*(C1 / C0-1) from the target time, promptly prompt the board to be inspected to need repair.

[0028] An intelligent IoT control system for panel furniture includes a target record extraction module, a wear degree calculation module, a scatter plot creation module, and a repair prompt module;

[0029] Target record extraction module: used to establish repair records for boards in smart homes, extract and analyze the time of each historical repair of the boards corresponding to the repair records, and then extract several target records from the repair records;

[0030] Wear degree calculation module: used to obtain the repair area of ​​the board corresponding to the target record, take images of the repair area before and after the repair, obtain the feature value of each internal defect based on the changes of several internal defects in the images before and after the repair, and obtain the wear degree corresponding to the target record based on the weight of each internal defect.

[0031] Scatter plot building module: used to capture historical surveillance video of the repair area corresponding to the target record, extract and analyze the movement speed of moving objects in the surveillance video when passing through the repair area, and then obtain the wear coefficient corresponding to the target record, and build a scatter plot of wear degree as wear coefficient changes based on the wear degree.

[0032] Repair prompt module: It is used to acquire monitoring video of the board to be inspected from the last repair to the target time, obtain the wear coefficient of the board to be inspected at the target time, preset the maximum wear degree of the board to be inspected, obtain the maximum wear coefficient of the board to be inspected based on the scatter plot, and determine the timing of repair prompt for the board to be inspected based on the wear coefficient at the target time.

[0033] Furthermore, the target record extraction module includes a repair record sorting unit and a target record extraction unit;

[0034] Repair record sorting unit: used to obtain the repair records corresponding to the target board in the smart home, obtain the usage time corresponding to all repair records, and sort each repair record in chronological order;

[0035] Target record extraction unit: used to establish a function for the duration of use as a function of serial number, and to mark the coordinates corresponding to each repair record in the function; analyze the coordinates to obtain the target record.

[0036] Furthermore, the scatter plot creation module includes a characteristic time period judgment unit and a scatter plot creation unit;

[0037] Feature time period determination unit: used to extract the monitoring video segment of the repair area, obtain the first region and the second region in the monitoring video segment; and obtain the feature time period based on the first region and the second region.

[0038] Scatter plot building unit: used to obtain the moving distance of a moving object within a characteristic time period, obtain the characteristic moving speed of the moving object within the characteristic time period; then obtain the wear coefficient corresponding to the target record, and build a scatter plot of the wear degree changing with the wear coefficient.

[0039] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention provides an intelligent IoT control system and method for panel furniture, comprising: establishing a repair record for panels in a smart home; extracting several target records from the repair record; obtaining the repair area of ​​the panel in the target record; analyzing several internal defects corresponding to the repair area to obtain the wear degree corresponding to the target record; capturing historical monitoring videos of the repair area to obtain the wear coefficient of the target record; establishing a scatter plot of wear degree versus wear coefficient; acquiring monitoring videos of the panel to be inspected from the last repair to the target time, and determining the timing for prompting repair of the panel to be inspected. This invention obtains historical repair records, combines them with the living environment of the smart home and the user's daily usage habits for analysis, and reasonably determines the timing for prompting repair of the panel to be inspected, avoiding resource waste or safety hazards caused by prompting too early or too late. Attached Figure Description

[0040] Figure 1 This is a flowchart illustrating an intelligent IoT control method for panel furniture according to the present invention.

[0041] Figure 2 This is a structural diagram of an intelligent IoT control system for panel furniture according to the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Example: Figure 1 As shown, this invention provides a technical solution for an intelligent IoT control method for panel furniture, comprising the following steps:

[0044] Step S100: Establish repair records for the boards in the smart home, extract and analyze the time of each repair of the boards corresponding to the repair records in history, and then extract several target records from the repair records;

[0045] Step S110: Obtain the repair time and target board material to be repaired for each repair record in the smart home, extract all repair records corresponding to a target board material B, obtain repair record R2 that is adjacent in time and later than a repair record R1, take the time interval between record R1 and record R2 as the usage period corresponding to record R2 in board material B, and then obtain the usage duration corresponding to all repair records, and sort each repair record in chronological order.

[0046] Step S120: Establish a function to change the usage time with the sequence number, and mark the coordinates corresponding to each repair record in the function; obtain the coordinates P corresponding to a certain repair record R0, take the coordinates of the repair record with the previous sequence number corresponding to record R0 and the vector pointing to coordinate P as V1, take the vector of coordinate P and the vector pointing to the coordinates of the repair record with the next sequence number corresponding to record R0 as V2, take the angle between the two vectors as the target angle of repair record R0, if the target angle is less than the preset angle threshold, then take repair record R0 as the target record, and then obtain all target records.

[0047] Step S200: Obtain the repair area of ​​the board corresponding to the target record, take images of the repair area before and after the repair, obtain the feature value of each internal defect based on the changes of several internal defects in the images before and after the repair, and obtain the wear degree corresponding to the target record based on the weight of each internal defect.

[0048] Step S210: Obtain the repair area of ​​the board corresponding to a target record, and take images G1 before repair and G2 after repair of the repair area. Internal defects include cracks, decay and holes. Apply an edge detection algorithm to images G1 and G2 to obtain binary images T1 and T2 corresponding to images G1 and G2 respectively. Then obtain the number of pixels N1 and N2 in the crack area of ​​images T1 and T2, and obtain the first feature value R1 = 1-N2 / N1 when the internal defect is a crack.

[0049] Since Sobel edge detection has two sliding windows, one horizontal and one vertical, it can be used to extract crack features. The process of Sobel edge detection to extract crack features is existing technology and will not be described in detail here. The binary image is an image with only 0 and 1 pixel values. In this embodiment, 0 represents the pixel points in the crack area and 1 represents the pixel points in the non-crack area. Since N2 / N1 represents the ratio of the crack area pixels in image T2 excluding T1, the smaller N2 / N1 is, the more cracked parts there are in the image G1 before repair, indicating a greater degree of wear. Here, it is represented by a larger first feature value R1. However, when a special case occurs (N2 / N1) ≥ 1, the first feature value R1 becomes 0.

[0050] Step S220: Obtain grayscale images S1 and S2 corresponding to images G1 and G2 respectively, set the highest grayscale level to Q level, collect all pixel grayscale values ​​according to the grayscale value of each pixel in grayscale images S1 and S2, and then obtain the proportion of each grayscale level, and establish grayscale histograms H1 and H2 corresponding to grayscale images S1 and S2, with the ratio changing with the grayscale level, calculate the cosine similarity cos(H) between grayscale histograms H1 and H2, and then obtain the second feature value R2 = 1 - cos(H) corresponding to the internal defect being decay.

[0051] In this embodiment, the highest grayscale level is set to M=8 levels, that is, according to the grayscale value of the pixel 0-256, it is evenly divided into 8 intervals according to the equal interval quantization method, and each interval corresponds to a grayscale level. The proportion of each grayscale level in the grayscale histogram H1 is set to {d1,d2,…,d8}, where d1,d2,…,d8 are the proportions of the 1st, 2nd,…,8th grayscale levels, respectively, and d1+d2+…+d8=1; similarly, the proportion of each grayscale level in the grayscale histogram H2 is set to {q1,q2,…,q8}. The calculation of cosine similarity cos(H) is a prior art and will not be described in detail here.

[0052] Step S230: Establish a neural network model. Obtain several images with holes and input them into the neural network model for training to obtain the trained neural network model. Substitute image G1 into the trained neural network model to obtain the number of holes N on image G1, and then obtain the third feature value R3 = 1 - e when the internal defect is a hole. -N Where e is a natural constant; weights are pre-set for each type of internal defect, and the wear degree corresponding to a target record is obtained based on the feature values ​​R1, R2, and R3: Where M = 3, W m It is the weight corresponding to the m-th type of internal defect, 1≤m≤M.

[0053] Since the values ​​of R1, R2, and R3 in this scheme are all between 0 and 1, the wear level value is also between 0 and 1.

[0054] Step S300: Capture the historical surveillance video of the repair area corresponding to the target record, extract and analyze the moving speed of the moving object when passing through the repair area in the surveillance video, and then obtain the wear coefficient corresponding to the target record. Based on the wear degree, establish a scatter plot of the wear degree changing with the wear coefficient.

[0055] Step S310: Obtain the repair area corresponding to a target record Y. Based on the usage time period corresponding to record Y obtained in step S110, extract the monitoring video segment that includes the repair area within the usage time period. Take the range corresponding to the repair area in the monitoring video segment as the first area. Obtain the rectangular range corresponding to a local part of a moving object in the monitoring video segment and take the rectangular range as the second area.

[0056] The moment when a local part of a moving object first enters the repair area is taken as D1, and the moment when the local part first leaves the repair area after time D1 is taken as D2. If, within time D1 and time D2, the intersection area of ​​the first region and the second region at a certain time is greater than a preset area threshold, then the time period between time D1 and time D2 is taken as the feature time period.

[0057] Step S320: Obtain the moving distance L of a certain moving object within the characteristic time period, and then obtain the characteristic moving speed of the certain moving object within the characteristic time period. Wherein, ln is a logarithmic function; then, the characteristic movement speed corresponding to all characteristic time periods within the usage period is obtained, and all characteristic movement speeds are added together as the wear coefficient corresponding to the target record Y; then, based on the wear coefficient and wear degree of each target record, a scatter plot of wear degree changing with wear coefficient is established.

[0058] The wear and tear on solid wood flooring is usually related to the speed at which people walk on it. When walking or running quickly, the friction between the sole of the shoe and the floor increases, generating a large impact force. This impact force causes the floor to bear a sudden increase in pressure, exceeding the flooring material's capacity, leading to damage to the floor's internal structure. Over time, this may cause problems such as cracks, loosening, or even deformation, further aggravating the wear and tear on the floor. Therefore, the faster and more numerous the people walking on solid wood flooring, i.e., the larger the characteristic movement speed V, the greater the wear coefficient should be.

[0059] Step S400: Obtain the monitoring video of the board to be inspected from the last repair to the target time, obtain the wear coefficient of the board to be inspected at the target time, pre-set the maximum wear degree of the board to be inspected, and obtain the maximum wear coefficient of the board to be inspected based on the scatter plot. Based on the wear coefficient at the target time, determine the timing of repair prompts for the board to be inspected.

[0060] Step S410: Obtain the monitoring video of the to-be-detected board from the last repair to the target time, with a duration of F, and calculate the wear coefficient C0 corresponding to the to-be-detected board at the target time; Set that a repair prompt is required when the to-be-detected board reaches the maximum wear degree X0. Obtain all the wear coefficients in the scatter plot where the wear degree is within the range of [k1×X0, k2×X0], where k1 and k2 are the first ratio and the second ratio respectively, 0 < k1 < 1 < k2, and obtain the average wear coefficient C1;

[0061] Step S420: If the average wear coefficient C1 is greater than the wear coefficient C0, promptly prompt that the to-be-detected board needs to be repaired. If the average wear coefficient C1 is not greater than the wear coefficient C0, after a time period of F*(C1 / C0 - 1) from the target time, promptly prompt that the to-be-detected board needs to be repaired.

[0062] The present invention also provides an intelligent Internet of Things control system for board furniture, as shown in the appendix Figure 2 and includes a target record extraction module, a wear degree calculation module, a scatter plot establishment module, and a repair prompt module;

[0063] Target record extraction module: Used to establish the repair records corresponding to the boards in the smart home, extract and analyze the time of each historical repair of the boards corresponding to the repair records, and then extract several target records from the repair records;

[0064] Wear degree calculation module: Used to obtain the repair area of the board corresponding to the target record, take pictures of the repair area before and after repair, obtain the characteristic values of each internal defect according to the changes of several internal defects corresponding to the repair area in the images before and after repair, and obtain the wear degree corresponding to the target record based on the weight of each internal defect;

[0065] Scatter plot establishment module: Used to intercept the historical monitoring video of the repair area corresponding to the target record, extract and analyze the moving speed of the moving object passing through the repair area in the monitoring video, and then obtain the wear coefficient corresponding to the target record, and establish a scatter plot of the wear degree changing with the wear coefficient based on the wear degree;

[0066] Repair prompt module: Used to obtain the monitoring video of the to-be-detected board from the last repair to the target time, obtain the wear coefficient corresponding to the to-be-detected board at the target time, preset the maximum wear degree of the to-be-detected board, and obtain the maximum wear coefficient of the to-be-detected board according to the scatter plot, and judge the timing of the repair prompt for the to-be-detected board according to the wear coefficient at the target time.

[0067] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for intelligent Internet of Things control of a panel home, characterized in that, Includes the following steps: Step S100: Establish repair records for the boards in the smart home, extract and analyze the time of each repair of the boards corresponding to the repair records in history, and then extract several target records from the repair records; Step S200: Obtain the repair area of ​​the board corresponding to the target record, take images of the repair area before and after the repair, obtain the feature value of each internal defect based on the changes of several internal defects in the images before and after the repair, and obtain the wear degree corresponding to the target record based on the weight of each internal defect. Step S300: Capture the historical surveillance video of the repair area corresponding to the target record, extract and analyze the moving speed of the moving object when passing through the repair area in the surveillance video, and then obtain the wear coefficient corresponding to the target record. Based on the wear degree, establish a scatter plot of the wear degree changing with the wear coefficient. Step S400: Obtain the monitoring video of the board to be inspected from the last repair to the target time, obtain the wear coefficient of the board to be inspected at the target time, pre-set the maximum wear degree of the board to be inspected, and obtain the maximum wear coefficient of the board to be inspected based on the scatter plot. Based on the wear coefficient at the target time, determine the timing of repair prompts for the board to be inspected. 2.The intelligent internet-of-things control method for panel home according to claim 1, wherein, Step S100 includes: Step S110: Obtain the repair time and target board material to be repaired for each repair record in the smart home, extract all repair records corresponding to a target board material B, obtain repair record R2 that is adjacent in time and later than a repair record R1, take the time interval between record R1 and record R2 as the usage period corresponding to record R2 in board material B, and then obtain the usage duration corresponding to all repair records, and sort each repair record in chronological order. Step S120: Establish a function to change the usage time with the sequence number, and mark the coordinates corresponding to each repair record in the function; obtain the coordinates P corresponding to a certain repair record R0, take the coordinates of the repair record with the previous sequence number corresponding to record R0 and the vector pointing to the coordinates P as V1, take the coordinates P and the vector pointing to the coordinates of the repair record with the next sequence number corresponding to record R0 as V2, take the angle between the two vectors as the target angle of repair record R0, if the target angle is less than the preset angle threshold, then take repair record R0 as the target record, and then obtain all target records. 3.The intelligent and internet-of-things control method for panel home according to claim 1, wherein, Step S200 includes: Step S210: Obtain the repair area of ​​the board corresponding to a target record, and take images G1 before repair and G2 after repair of the repair area. Internal defects include cracks, decay and holes. Apply an edge detection algorithm to images G1 and G2 to obtain binary images T1 and T2 corresponding to images G1 and G2 respectively. Then obtain the number of pixels N1 and N2 in the crack area of ​​images T1 and T2, and obtain the first feature value R1 = 1-N2 / N1 when the internal defect is a crack. Step S220: Obtain the grayscale images S1 and S2 corresponding to the images G1 and G2 respectively. Set the highest gray level to Q levels. According to the gray values of each pixel in the grayscale images S1 and S2, pool all the pixel gray values, and then obtain the所占 ratio of each gray level. And establish the gray histograms H1 and H2 corresponding to the grayscale images S1 and S2, where the ratio varies with the gray level. Calculate the cosine similarity cos(H) between the gray histograms H1 and H2, and then obtain the second eigenvalue R2 = 1 - cos(H) corresponding to the internal defect being decay; Step S230: establishing a neural network model, obtaining a plurality of images with holes, substituting into the neural network model for training to obtain a trained neural network model; substituting the image G1 into the trained neural network model to obtain the number N of holes on the image G1, and further obtaining the third characteristic value R3=1-e corresponding to the internal defect being a hole -N , wherein e is a natural constant; the weight value corresponding to each kind of internal defect is set in advance, and the wear degree corresponding to a certain target record is obtained according to the characteristic values R1, R2 and R3: , wherein M=3, W m is the weight value corresponding to the mth internal defect, 1≤m≤M. 4.The intelligent internet-of-things control method for panel furniture according to claim 2, wherein, Step S300 includes: Step S310: Obtain the repair area corresponding to a certain target record Y. According to Step S110, obtain the usage period corresponding to the record Y, and intercept the monitoring video segment including the repair area within the usage period. Take the range corresponding to the repair area in the monitoring video segment as the first area, obtain the rectangular range corresponding to a local part of a certain moving object in the monitoring video segment, and take the rectangular range as the second area; Take the moment when the local part of the certain moving object first enters the repair area as D1, and take the moment when the local part first leaves the repair area after the moment D1 as D2. If within the moments D1 and D2, there is a moment when the intersection area of the first area and the second area is greater than the preset area threshold, then take the period between the moments D1 and D2 as the characteristic period; Step S320: Obtain the moving distance L of the certain mobile object in the feature period, and further obtain the feature moving speed of the certain mobile object in the feature period Wherein, ln is the logarithmic function; further, the feature moving speeds corresponding to all the feature periods in the use period are calculated, and all the feature moving speeds are added together as the wear coefficient corresponding to the target record Y; further, according to the wear coefficient and the wear degree of each target record, a scatter plot of the change of the wear degree with the wear coefficient is established. 5.The intelligent and internet-of-things control method for panel home according to claim 1, wherein, Step S400 includes: Step S410: Obtain the monitoring video of the to-be-detected board from the last repair to the target moment, with a duration of F. Obtain the wear coefficient C0 corresponding to the to-be-detected board at the target moment. Set that a repair prompt is required when the to-be-detected board reaches the maximum wear degree X0. Obtain all the wear coefficients in the scatter plot where the wear degree is within the range of [k1×X0, k2×X0], where k1 and k2 are the first ratio and the second ratio respectively, 0 < k1 < 1 < k2, and obtain the average wear coefficient C1; Step S420: If the average wear coefficient C1 is greater than the wear coefficient C0, promptly prompt that the to-be-detected board needs to be repaired. If the average wear coefficient C1 is not greater than the wear coefficient C0, obtain that after a period of F*(C1 / C0 - 1) from the target time, promptly prompt that the to-be-detected board needs to be repaired.

6. An intelligent IOT control system for performing the intelligent IOT control method for panel furniture according to any one of claims 1-5, characterized in that, The system includes a target record extraction module, a wear degree calculation module, a scatter plot establishment module, and a repair prompt module; Target record extraction module: Used to establish the repair records corresponding to the boards in the smart home, extract and analyze the time of each historical repair of the board corresponding to the repair record, and then extract several target records from the repair record; Wear degree calculation module: Used to obtain the repair area of the board corresponding to the target record, take pictures of the repair area before and after the repair, obtain the eigenvalue of each internal defect according to the changes of several internal defects corresponding to the repair area in the images before and after the repair, and obtain the wear degree corresponding to the target record based on the weight of each internal defect; Scatter plot building module: used to capture historical surveillance video of the repair area corresponding to the target record, extract and analyze the movement speed of moving objects in the surveillance video when passing through the repair area, and then obtain the wear coefficient corresponding to the target record, and build a scatter plot of wear degree as wear coefficient changes based on the wear degree. Repair prompt module: It is used to acquire monitoring video of the board to be inspected from the last repair to the target time, obtain the wear coefficient of the board to be inspected at the target time, preset the maximum wear degree of the board to be inspected, obtain the maximum wear coefficient of the board to be inspected based on the scatter plot, and determine the timing of repair prompt for the board to be inspected based on the wear coefficient at the target time.

7. The intelligent IoT control system according to claim 6, characterized in that, The target record extraction module includes a repair record sorting unit and a target record extraction unit; Repair record sorting unit: used to obtain the repair records corresponding to the target board in the smart home, obtain the usage time corresponding to all repair records, and sort each repair record in chronological order; Target record extraction unit: used to establish a function for the duration of use as a function of serial number, and to mark the coordinates corresponding to each repair record in the function; analyze the coordinates to obtain the target record.

8. The intelligent IoT control system according to claim 7, characterized in that, The scatter plot creation module includes a characteristic time period judgment unit and a scatter plot creation unit; Feature time period determination unit: used to extract the monitoring video segment of the repair area, obtain the first region and the second region in the monitoring video segment; and obtain the feature time period based on the first region and the second region. Scatter plot building unit: used to obtain the moving distance of a certain moving object within a characteristic time period, obtain the characteristic moving speed of the certain moving object within the characteristic time period; then obtain the wear coefficient corresponding to the target record, and build a scatter plot of the wear degree changing with the wear coefficient.

Images