A method and system for determining coating information in the decoration industry

Abstract

The present invention provides a method and system for determining paint information in the decoration industry, and the invention relates to the field of paint technology. The method includes using a drying information determination model based on a drying monitoring video of an initial time period after the paint is applied to the wall to determine the drying information of four edge points after the paint is applied to the wall, the drying information of the center point after the paint is applied to the wall, and the directions and distances between the four edge points after the paint is applied to the wall and the center point after the paint is applied to the wall; constructing a graph structure; processing the graph structure based on a graph neural network model to determine the wall drying point with the slowest drying time after the paint is applied to the wall; and using the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall as the overall remaining drying time after the paint is applied to the wall. The method can quickly and accurately determine the drying time of the paint.

Description

Technical Field

[0001] The present invention relates to the field of coating technology, and in particular to a method and system for determining coating information in the decoration industry. Background Art

[0002] In the decoration industry, the drying time of paint directly affects the overall construction progress. Accurately determining the drying time of paint can help construction personnel arrange construction plans scientifically and reasonably, avoiding construction delays due to insufficient or excessive drying time. At the same time, paint may release volatile organic compounds during the drying process. If it is used in advance before the drying time is sufficient, it may pollute the indoor air quality and cause harm to human health.

[0003] Traditional evaluation of paint drying time usually relies on human experience, which often lacks precision and consistency. For example, manual observation of the paint drying process is not only time-consuming, but also easily affected by subjective factors, resulting in reduced reliability of the evaluation results.

[0004] Therefore, how to quickly and accurately determine the drying time of the paint is a problem that needs to be solved urgently. Summary of the invention

[0005] The main technical problem solved by the present invention is how to quickly and accurately determine the drying time of the coating.

[0006] According to a first aspect, the present invention provides a method for determining paint information in the decoration industry, comprising: obtaining a drying monitoring video of an initial time period after the paint is applied to the wall; using a drying information determination model to determine the drying information of four edge points after the paint is applied to the wall, the drying information of a center point after the paint is applied to the wall, and the directions and distances between the four edge points after the paint is applied to the wall and the center point after the paint is applied to the wall; constructing a graph structure, the graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes comprising a central node and four edge nodes, wherein the central node represents the center point after the paint is applied to the wall, the four edge nodes represent the four edge points after the paint is applied to the wall, and the four edge nodes respectively establish four edges with the central node. , the node feature of the central node includes the drying information of the central point after the paint is applied to the wall, the node feature of each edge node includes the drying information of each edge point of the paint applied to the wall, and the feature of the edge established between the edge node and the central node includes the direction and distance between the edge point and the central point after the paint is applied to the wall; the graph structure is processed based on the graph neural network model to determine the wall drying point with the slowest drying time after the paint is applied to the wall; based on the drying monitoring video of the initial time period after the paint is applied to the wall and the wall drying point with the slowest drying time after the paint is applied to the wall, the remaining drying time of the wall drying point with the slowest drying time after the paint is applied is determined using the drying time determination model; the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall is used as the overall remaining drying time after the paint is applied to the wall.

[0007] Furthermore, the drying information determination model is a recurrent neural network model.

[0008] Furthermore, the input of the graph neural network model is a graph structure, and the output of the graph neural network model is the wall drying point where the paint dries the slowest after being applied to the wall.

[0009] Furthermore, the drying information of the four edge points after the paint is applied to the wall includes a color change sequence of the four edge points, a glossiness change sequence of the four edge points, and a thickness change sequence of the four edge points.

[0010] Furthermore, the drying information of the center point after the paint is applied to the wall includes a color change sequence of the center point, a glossiness change sequence of the center point, and a thickness change sequence of the center point.

[0011] According to a second aspect, the present invention provides a system for determining paint information in the decoration industry, including: an acquisition module, used to acquire a drying monitoring video of an initial time period after the paint is applied to the wall; a drying monitoring module, used to determine the drying information of four edge points after the paint is applied to the wall, the drying information of the center point after the paint is applied to the wall, and the directions and distances between the four edge points after the paint is applied to the wall and the center point after the paint is applied to the wall based on the drying monitoring video of the initial time period after the paint is applied to the wall; a construction module, used to construct a graph structure, the graph structure including multiple nodes and multiple edges between the multiple nodes, the multiple nodes including a central node and four edge nodes, wherein the central node represents the center point after the paint is applied to the wall, and the four edge nodes represent the four edge points after the paint is applied to the wall, wherein the four edge nodes respectively establish four edges with the central node, and the node of the central node The features include drying information of the center point of the wall after the paint is applied, the node features of each edge node include drying information of each edge point of the wall after the paint is applied, and the features of the edge established between the edge node and the center node include the direction and distance between the edge point and the center point of the wall after the paint is applied; a wall drying point determination module is used to process the graph structure based on a graph neural network model to determine the wall drying point with the slowest drying time after the paint is applied to the wall; the slowest wall drying point analysis module is used to determine the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall based on the drying monitoring video of the initial time period after the paint is applied to the wall and the wall drying point with the slowest drying time after the paint is applied to the wall using a drying time determination model; a remaining drying time determination module is used to use the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall as the overall remaining drying time after the paint is applied to the wall.

[0012] Furthermore, the drying information determination model is a recurrent neural network model.

[0013] Furthermore, the input of the graph neural network model is a graph structure, and the output of the graph neural network model is the wall drying point where the paint dries the slowest after being applied to the wall.

[0014] Furthermore, the drying information of the four edge points after the paint is applied to the wall includes a color change sequence of the four edge points, a glossiness change sequence of the four edge points, and a thickness change sequence of the four edge points.

[0015] Furthermore, the drying information of the center point after the paint is applied to the wall includes a color change sequence of the center point, a glossiness change sequence of the center point, and a thickness change sequence of the center point.

[0016] The present invention provides a method and system for determining paint information in the decoration industry, the method comprising: obtaining a drying monitoring video of an initial time period after the paint is applied to the wall; using a drying information determination model to determine the drying information of four edge points after the paint is applied to the wall, the drying information of the center point after the paint is applied to the wall, and the directions and distances between the four edge points after the paint is applied to the wall and the center point after the paint is applied to the wall; constructing a graph structure, the graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes comprising a central node and four edge nodes, wherein the central node represents the center point after the paint is applied to the wall, the four edge nodes represent the four edge points after the paint is applied to the wall, wherein the four edge nodes respectively establish four edges with the central node, and the node feature package of the central node The method comprises the following steps: comprising: comprising: comprising: comprising: comprising: a drying information of a center point of the wall after the paint is applied, a node feature of each edge node comprising the drying information of each edge point of the wall after the paint is applied, and a feature of an edge established between an edge node and a center node comprising a direction and a distance between an edge point and a center point of the wall after the paint is applied; processing the graph structure based on a graph neural network model to determine a wall drying point with the slowest drying time after the paint is applied to the wall; using a drying time determination model based on a drying monitoring video of an initial time period after the paint is applied to the wall and the wall drying point with the slowest drying time after the paint is applied to the wall; and taking the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall as the overall remaining drying time after the paint is applied to the wall. The method can quickly and accurately determine the drying time of the paint. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A schematic flow chart of a method for determining coating information in the decoration industry provided by an embodiment of the present invention;

[0018] Figure 2 A schematic diagram of a system for determining paint information in the decoration industry provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In an embodiment of the present invention, there is provided Figure 1 A method for determining coating information in the decoration industry is shown, and the method for determining coating information in the decoration industry includes steps S1 to S6:

[0020] Step S1, obtaining a drying monitoring video of the initial time period after the paint is applied to the wall.

[0021] The initial time period refers to the first time period after the paint application is completed. For example, the initial time period can be 2 hours, 5 hours, or one day after the application. The initial time period can be manually set in advance. The drying monitoring video of the initial time period can be used to determine how much remaining drying time the paint needs.

[0022] As an example, a surveillance camera is installed at a construction site and video recording is started. After the paint worker finishes applying the paint, the camera records the initial state of the wall surface, and after reaching the initial time period, a drying surveillance video of the initial time period after the paint is applied to the wall is obtained.

[0023] Step S2, based on the drying monitoring video of the initial time period after the paint is applied to the wall, a drying information determination model is used to determine the drying information of the four edge points after the paint is applied to the wall, the drying information of the center point after the paint is applied to the wall, and the directions and distances of the four edge points after the paint is applied to the wall and the center point after the paint is applied to the wall.

[0024] The drying information determination model is a recurrent neural network model. The recurrent neural network model includes a recurrent neural network (RNN). The recurrent neural network includes an input layer, a hidden layer, and an output layer. The neurons in the hidden layer receive the input data at the current moment and the output data of the hidden layer at the previous moment, obtain the state of the hidden layer at the current moment by calculation, and use it as part of the input data at the next moment. This structure enables the recurrent neural network to process sequence data of indefinite length and remember previous information during the processing process.

[0025] The four edge points after the paint is applied to the wall are key points on the four edges of the area formed by the paint on the wall. As an example, the paint forms a rectangular area on the wall, and its four edges are the upper edge, the lower edge, the left edge, and the right edge. The four edge points after the paint is applied to the wall are located on these four edges, and their positions on the wall can be represented by coordinates.

[0026] The center point of the paint after it is applied to the wall is the center point of the area formed by the paint applied on the wall.

[0027] The drying information of the four edge points after the paint is applied to the wall includes a color change sequence of the four edge points, a glossiness change sequence of the four edge points, and a thickness change sequence of the four edge points.

[0028] The drying information of the center point after the paint is applied to the wall includes a color change sequence of the center point, a glossiness change sequence of the center point, and a thickness change sequence of the center point.

[0029] The color change sequence refers to the sequence of changes in the paint color over time during the initial time period. For example, the color change sequence of four edge points or center points records the color values ​​of the four edge points or center points at different time points.

[0030] The gloss change sequence refers to the sequence of changes in the gloss of the coating over time during the initial time period. For example, the gloss change sequence of four edge points or center points records the gloss values ​​of the four edge points or center points at different time points.

[0031] When the paint is first applied to the wall, it has a certain fluidity and forms a certain thickness on the surface. As the paint dries and solidifies, the fluidity of the paint gradually weakens, causing the thickness of the paint to change to a certain extent. The thickness change sequence refers to the sequence of changes in the paint thickness over time during the initial time period. For example, the thickness change sequence of four edge points or center points records the thickness values ​​of the four edge points or center points at different time points.

[0032] Each frame in the drying monitoring video of the initial time period after the paint is applied to the wall contains a large amount of pixel information, which reflects the distribution and characteristics of the paint on the wall. By processing and analyzing the video frames, information such as the color and brightness of the paint surface can be extracted to understand the drying characteristics of the paint. The drying monitoring video of the initial time period after the paint is applied to the wall records the change process of the paint on the wall over time, thus providing time series data. These data can be used by recurrent neural networks to analyze the state changes of the paint at different time points, such as changes in color, changes in gloss, etc.

[0033] Paint drying monitoring videos can provide rich time series data and spatial distribution information. By analyzing the pixel information and optical properties in the video, we can effectively determine the change information of paint on the wall over time, including drying characteristics such as color, glossiness, and thickness.

[0034] In some embodiments, the drying information determination model includes a point determination layer and a point information analysis layer. The point determination layer and the point information analysis layer both include a recurrent neural network structure. The input of the point determination layer is the drying monitoring video of the initial time period after the paint is applied to the wall, and the output of the point determination layer is the four edge points after the paint is applied to the wall and the center point after the paint is applied to the wall. The input of the point information analysis layer is the four edge points after the paint is applied to the wall and the center point after the paint is applied to the wall, and the drying monitoring video of the initial time period after the paint is applied to the wall, and the output of the point information analysis layer is the drying information of the four edge points after the paint is applied to the wall, the drying information of the center point after the paint is applied to the wall, and the direction and distance of the four edge points after the paint is applied to the wall and the center point after the paint is applied to the wall. The function of the point determination layer is to accurately determine the key points of the paint-applied wall from the drying monitoring video, including the four edge points and the center point. After obtaining the position information of the key points, the point information analysis layer analyzes the key points in the paint drying process and outputs the corresponding drying information and position relationship analysis results.

[0035] Step S3, constructing a graph structure, wherein the graph structure includes multiple nodes and multiple edges between the multiple nodes, wherein the multiple nodes include a central node and four edge nodes, wherein the central node represents the central point of the wall after the paint is applied, and the four edge nodes represent the four edge points of the wall after the paint is applied, wherein the four edge nodes respectively establish four edges with the central node, the node feature of the central node includes the drying information of the central point of the wall after the paint is applied, the node feature of each edge node includes the drying information of each edge point of the wall after the paint is applied, and the feature of the edge established between the edge node and the central node includes the direction and distance between the edge point and the central point of the wall after the paint is applied.

[0036] The graph structure is a data structure consisting of two parts: nodes and edges. The multiple nodes include a central node and four edge nodes, wherein the central node represents the central point of the wall after the paint is applied, and the four edge nodes represent the four edge points of the wall after the paint is applied, wherein the four edge nodes respectively establish four edges with the central node, the node feature of the central node includes the drying information of the central point of the wall after the paint is applied, the node feature of each edge node includes the drying information of each edge point of the wall after the paint is applied, and the feature of the edge established between the edge node and the central node includes the direction and distance between the edge point and the central point of the wall after the paint is applied.

[0037] An edge is a line segment connecting two nodes, representing the relationship between the nodes. The characteristics of the edge established between the edge node and the center node include the direction and distance between the edge point and the center point after the paint is applied to the wall.

[0038] Step S4: Process the graph structure based on the graph neural network model to determine the wall drying point where the paint dries the slowest after being applied to the wall.

[0039] The graph neural network model includes a graph neural network (GNN) and a fully connected layer. The graph neural network is a neural network that directly acts on graph structure data. The input of the graph neural network model is the graph structure, and the output of the graph neural network model is the wall drying point where the paint dries the slowest after being applied to the wall.

[0040] The wall drying point where the paint takes the slowest time to dry after it is applied to the wall is the point where the paint takes the slowest time to dry after it is applied to the wall.

[0041] The graph neural network model can effectively learn the complex relationships between nodes in the graph structure. When paint is applied to a wall, the drying time of the wall at different locations is affected by many factors, such as air circulation, temperature, humidity, etc. Through the graph neural network model, these factors can be associated with nodes at different locations on the wall, so as to better understand the distribution of drying time.

[0042] The graph neural network model can comprehensively consider the characteristics of the nodes and the connection relationship between the nodes. In the case of the wall surface, the nodes at each position have their own characteristics (such as air circulation, light intensity, etc.), and the distance between the nodes will also affect the drying time. By comprehensively considering this information, the graph neural network model can more accurately predict the wall drying point with the slowest drying time. The graph neural network model can learn features and patterns from the data. Through a large amount of training, the graph neural network model can learn the drying time relationship between nodes at different positions on the wall surface, thereby realizing the prediction of the slowest drying point.

[0043] Step S5, based on the drying monitoring video of the initial time period after the paint is applied to the wall and the wall drying point with the slowest drying time after the paint is applied to the wall, use a drying time determination model to determine the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall.

[0044] The remaining drying time at the wall drying point with the slowest drying time after the paint is applied to the wall is the remaining drying time of the paint after the initial time period.

[0045] The drying time determination model is a recurrent neural network model. The input of the drying time determination model is the drying monitoring video of the initial time period after the paint is applied to the wall, and the wall drying point with the slowest drying time after the paint is applied to the wall. The output of the drying time determination model is the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall.

[0046] The monitoring video of the initial time period can provide real-time drying process information, including paint color changes, surface conditions, etc. The monitoring video of the initial time period can be combined with the slowest drying point to provide drying information of the wall drying point with the slowest drying time in the initial time period.

[0047] The drying time determination model can process the surveillance video of the initial time period of the continuous time period, and can better capture the relationship in the surveillance video time series of the initial time period, and finally output the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall.

[0048] Once the slowest drying point is determined, the recurrent neural network model can focus on this specific point, analyze its drying process based on the monitoring video of the initial time period of the continuous time period, and predict the remaining time required for the slowest drying point to go from the current state to complete drying. The recurrent neural network model can be trained end-to-end and eventually be able to learn the complex pattern of paint drying from the drying monitoring video and accurately predict the remaining drying time of the slowest drying point.

[0049] Step S6, taking the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall as the overall remaining drying time after the paint is applied to the wall.

[0050] The importance of determining the remaining drying time of the slowest drying point on the wall after the paint is applied is that when this point is completely dried, it can be confirmed that the paint on the entire wall has been completely dried. Once the slowest drying point on the wall is completely dried, it means that all other points have also been dried, so the remaining drying time of the slowest drying point on the wall after the paint is applied can be used as the overall remaining drying time of the paint after the wall is applied.

[0051] Based on the same inventive concept, Figure 2 A schematic diagram of a system for determining paint information for the decoration industry provided by an embodiment of the present invention, wherein the system for determining paint information for the decoration industry comprises:

[0052] An acquisition module 21 is used to acquire a drying monitoring video of the initial period of time after the paint is applied to the wall;

[0053] A drying monitoring module 22 is used to determine the drying information of four edge points after the paint is applied to the wall, the drying information of the center point after the paint is applied to the wall, and the directions and distances between the four edge points after the paint is applied to the wall and the center point after the paint is applied to the wall based on the drying monitoring video of the initial time period after the paint is applied to the wall using a drying information determination model;

[0054] A construction module 23 is used to construct a graph structure, wherein the graph structure includes a plurality of nodes and a plurality of edges between the plurality of nodes, wherein the plurality of nodes include a central node and four edge nodes, wherein the central node represents the central point of the wall after the paint is applied, and the four edge nodes represent the four edge points of the wall after the paint is applied, wherein the four edge nodes respectively establish four edges with the central node, the node feature of the central node includes the drying information of the central point of the wall after the paint is applied, the node feature of each edge node includes the drying information of each edge point of the wall after the paint is applied, and the feature of the edge established between the edge node and the central node includes the direction and distance between the edge point and the central point of the wall after the paint is applied;

[0055] A wall drying point determination module 24 is used to process the graph structure based on a graph neural network model to determine the wall drying point where the paint has the slowest drying time after being applied to the wall;

[0056] The slowest wall drying point analysis module 25 is used to determine the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall based on the drying monitoring video of the initial time period after the paint is applied to the wall and the wall drying point with the slowest drying time after the paint is applied to the wall using a drying time determination model;

[0057] The remaining drying time determination module 26 is used to use the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall as the overall remaining drying time after the paint is applied to the wall.

Claims

1. A method for determining coating information in the decoration industry, characterized in that: include: Obtain drying monitoring video of the initial period after the paint is applied to the wall; Based on the drying monitoring video of the initial time period after the paint is applied to the wall, a drying information determination model is used to determine the drying information of the four edge points after the paint is applied to the wall, the drying information of the center point after the paint is applied to the wall, and the directions and distances between the four edge points after the paint is applied to the wall and the center point after the paint is applied to the wall; Constructing a graph structure, the graph structure comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the plurality of nodes comprising a central node and four edge nodes, wherein the central node represents the central point of the wall after the paint is applied, the four edge nodes represent the four edge points of the wall after the paint is applied, wherein the four edge nodes respectively establish four edges with the central node, the node feature of the central node comprises the drying information of the central point of the wall after the paint is applied, the node feature of each edge node comprises the drying information of each edge point of the wall after the paint is applied, and the feature of the edge established between the edge node and the central node comprises the direction and distance between the edge point and the central point of the wall after the paint is applied; Processing the graph structure based on a graph neural network model to determine a wall drying point where the paint has the slowest drying time after being applied to the wall; Based on the drying monitoring video of the initial time period after the paint is applied to the wall and the wall drying point with the slowest drying time after the paint is applied to the wall, a drying time determination model is used to determine the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall; The remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall is taken as the overall remaining drying time after the paint is applied to the wall.

2. The method for determining coating information in the decoration industry according to claim 1, characterized in that: The drying information determination model is a recurrent neural network model.

3. The method for determining coating information in the decoration industry according to claim 1, characterized in that: The input of the graph neural network model is a graph structure, and the output of the graph neural network model is the wall drying point where the paint dries the slowest after being applied to the wall.

4. The method for determining coating information in the decoration industry according to claim 1, characterized in that: The drying information of the four edge points after the paint is applied to the wall includes a color change sequence of the four edge points, a glossiness change sequence of the four edge points, and a thickness change sequence of the four edge points.

5. The method for determining coating information in the decoration industry according to claim 1, characterized in that: The drying information of the center point after the paint is applied to the wall includes a color change sequence of the center point, a glossiness change sequence of the center point, and a thickness change sequence of the center point.

6. A system for determining coating information in the decoration industry, characterized in that: include: An acquisition module is used to acquire a drying monitoring video of the initial period after the paint is applied to the wall; A drying monitoring module is used to determine the drying information of four edge points after the paint is applied to the wall, the drying information of the center point after the paint is applied to the wall, and the directions and distances between the four edge points after the paint is applied to the wall and the center point after the paint is applied to the wall based on the drying monitoring video of the initial time period after the paint is applied to the wall using a drying information determination model; A construction module, for constructing a graph structure, wherein the graph structure includes a plurality of nodes and a plurality of edges between the plurality of nodes, wherein the plurality of nodes include a central node and four edge nodes, wherein the central node represents the central point of the wall after the paint is applied, and the four edge nodes represent the four edge points of the wall after the paint is applied, wherein the four edge nodes respectively establish four edges with the central node, the node feature of the central node includes the drying information of the central point of the wall after the paint is applied, the node feature of each edge node includes the drying information of each edge point of the wall after the paint is applied, and the feature of the edge established between the edge node and the central node includes the direction and distance between the edge point and the central point of the wall after the paint is applied; A wall drying point determination module, used to process the graph structure based on a graph neural network model to determine the wall drying point where the paint has the slowest drying time after being applied to the wall; The slowest wall drying point analysis module is used to determine the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall based on the drying monitoring video of the initial time period after the paint is applied to the wall and the wall drying point with the slowest drying time after the paint is applied to the wall using the drying time determination model; The remaining drying time determination module is used to take the remaining drying time of the wall drying point with the slowest drying time after the paint is applied to the wall as the overall remaining drying time after the paint is applied to the wall.

7. The system for determining coating information in the decoration industry as claimed in claim 6, characterized in that: The drying information determination model is a recurrent neural network model.

8. The system for determining coating information in the decoration industry as claimed in claim 6, characterized in that: The input of the graph neural network model is a graph structure, and the output of the graph neural network model is the wall drying point where the paint dries the slowest after being applied to the wall.

9. The system for determining coating information in the decoration industry as claimed in claim 6, characterized in that: The drying information of the four edge points after the paint is applied to the wall includes a color change sequence of the four edge points, a glossiness change sequence of the four edge points, and a thickness change sequence of the four edge points.

10. The system for determining coating information in the decoration industry as claimed in claim 6, characterized in that: The drying information of the center point after the paint is applied to the wall includes a color change sequence of the center point, a glossiness change sequence of the center point, and a thickness change sequence of the center point.

Images