CN117874901A - House type modeling optimization method and system based on parameterized house type information - Google Patents
House type modeling optimization method and system based on parameterized house type information Download PDFInfo
- Publication number
- CN117874901A CN117874901A CN202410282004.7A CN202410282004A CN117874901A CN 117874901 A CN117874901 A CN 117874901A CN 202410282004 A CN202410282004 A CN 202410282004A CN 117874901 A CN117874901 A CN 117874901A
- Authority
- CN
- China
- Prior art keywords
- area
- house type
- type
- scheme
- requirement
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000005457 optimization Methods 0.000 title claims abstract description 36
- 238000013461 design Methods 0.000 claims abstract description 41
- 238000012545 processing Methods 0.000 claims abstract description 40
- 238000010586 diagram Methods 0.000 claims abstract description 29
- 238000011156 evaluation Methods 0.000 claims description 30
- 230000002093 peripheral effect Effects 0.000 claims description 26
- 238000010606 normalization Methods 0.000 claims description 22
- 230000004927 fusion Effects 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 16
- 230000003068 static effect Effects 0.000 claims description 15
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 10
- 238000012216 screening Methods 0.000 claims description 8
- 238000012986 modification Methods 0.000 claims description 6
- 230000004048 modification Effects 0.000 claims description 6
- 230000006872 improvement Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 210000000746 body region Anatomy 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 9
- 230000006870 function Effects 0.000 description 12
- 230000006978 adaptation Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007621 cluster analysis Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The disclosure provides a house type modeling optimization method and system based on parameterized house type information, and relates to the technical field of data processing, wherein the method comprises the following steps: receiving a house type reconstruction requirement and an initial house type diagram; generating a function identification area; generating a house type dynamic area; frequent searching is carried out on the house type dynamic region, and a house type reconstruction scheme set is generated; and performing full-connection constraint optimization on the house type reconstruction scheme set to obtain a recommended house type reconstruction scheme, and modeling to generate a house type reconstruction conceptual model. The method and the device can solve the technical problems that in the prior art, due to the fact that house type information modeling is input by a designer, the fit degree of a house type design scheme and an actual scene cannot be evaluated digitally, and further the viscosity of the actual design scheme and the client requirement is difficult to guarantee, the house type reconstruction optimization is achieved, the fit degree of house type reconstruction and an actual house type structure is improved, and meanwhile the technical effect of the viscosity of house type reconstruction modeling and the user requirement is improved.
Description
Technical Field
The disclosure relates to the technical field of data processing, in particular to a house type modeling optimization method and system based on parameterized house type information.
Background
With the rapid development of the three-dimensional model technology, the house type display method has the advantages of intuitiveness, convenience, high display degree and the like, is widely applied, and can assist a user to know the house type structure composition more clearly by displaying the house type graph through the three-dimensional model.
However, the traditional house type modeling depends on house type information modeling input by a designer, so that the fit degree of a house type design scheme and an actual scene cannot be digitally evaluated, and the fit degree with the requirements of clients is difficult to ensure.
In summary, in the prior art, due to the modeling of house type information input by a designer, the fit degree between a house type design scheme and an actual scene cannot be digitally evaluated, and further, the technical problem that the viscosity between the actual design scheme and the client requirement is difficult to ensure is solved.
Disclosure of Invention
The disclosure aims to provide a house type modeling optimization method and system based on parameterized house type information, which are used for solving the technical problems that in the prior art, digital evaluation of the fit degree between a house type design scheme and an actual scene cannot be realized due to house type information modeling input by a designer, and further the viscosity between the actual design scheme and a customer requirement is difficult to ensure.
In view of the above problems, the present disclosure provides a method and a system for optimizing house type modeling based on parameterized house type information.
In a first aspect, the present disclosure provides a method for optimizing house type modeling based on parameterized house type information, the method being implemented by a house type modeling optimization system based on parameterized house type information, wherein the method includes: receiving a house type reconstruction requirement and an initial house type diagram through a client, wherein the house type reconstruction requirement comprises a requirement area type list, a requirement length threshold list, a requirement width threshold list and a requirement area threshold list; performing running water treatment on the initial house type graph through a functional area identification pipeline embedded in a server to generate a functional identification area, wherein the functional identification area comprises a bearing wall area, a kitchen area and a toilet area; carrying out static treatment on the bearing wall body area, the kitchen area and the toilet area in the initial house type diagram to generate a house type dynamic area; according to the requirement area type list, frequent searching is carried out on the house type dynamic area, and a house type reconstruction scheme set is generated; and performing full-connection constraint optimization on the house type reconstruction scheme set according to the requirement length threshold list, the requirement width threshold list and the requirement area threshold list to obtain a recommended house type reconstruction scheme, modeling based on the recommended house type reconstruction scheme, generating a house type reconstruction conceptual model, and feeding back to the client.
In a second aspect, the present disclosure further provides a house type modeling optimization system based on parameterized house type information, for performing a house type modeling optimization method based on parameterized house type information as described in the first aspect, where the system includes: the house type demand receiving module is used for receiving house type reconstruction demands and an initial house type diagram through a client, wherein the house type reconstruction demands comprise a demand area type list, a demand length threshold list, a demand width threshold list and a demand area threshold list; the function area identification module is used for performing running water treatment on the initial house type graph through a function area identification pipeline embedded in the server side to generate a function identification area, wherein the function identification area comprises a bearing wall area, a kitchen area and a toilet area; the static processing module is used for carrying out static processing on the bearing wall body area, the kitchen area and the toilet area in the initial house type diagram to generate a house type dynamic area; the frequent searching module is used for carrying out frequent searching on the household type dynamic area according to the requirement area type list to generate a household type reconstruction scheme set; the household type reconstruction recommendation module is used for executing full-connection constraint optimization on the household type reconstruction scheme set according to the requirement length threshold list, the requirement width threshold list and the requirement area threshold list to obtain a recommended household type reconstruction scheme, modeling is conducted based on the recommended household type reconstruction scheme, a household type reconstruction conceptual model is generated, and the household type reconstruction conceptual model is fed back to the client.
One or more technical solutions provided in the present disclosure have at least the following technical effects or advantages:
receiving a house type reconstruction requirement and an initial house type diagram through a client, wherein the house type reconstruction requirement comprises a requirement area type list, a requirement length threshold value list, a requirement width threshold value list and a requirement area threshold value list; performing running water treatment on the initial house type graph through a functional area identification assembly line embedded in the server side to generate a functional identification area, wherein the functional identification area comprises a bearing wall area, a kitchen area and a toilet area; carrying out static treatment on the bearing wall body area, the kitchen area and the toilet area in the initial house type diagram to generate a house type dynamic area; according to the requirement region type list, frequent searching is carried out on the household type dynamic region, and a household type reconstruction scheme set is generated; and performing full-connection constraint optimization on the house type reconstruction scheme set according to the requirement length threshold list, the requirement width threshold list and the requirement area threshold list to obtain a recommended house type reconstruction scheme, modeling based on the recommended house type reconstruction scheme, generating a house type reconstruction conceptual model, and feeding back to the client. The method comprises the steps of carrying out static processing on an initial house type diagram after functional area identification to generate a house type dynamic area, carrying out preliminary screening on house type reconstruction schemes by combining a demand area type list, and finally carrying out full-connection constraint optimization by combining house type reconstruction demands to realize house type reconstruction optimization, so that the adaptation degree of house type reconstruction and an actual house type structure is improved, and meanwhile, the technical effect of viscosity of house type reconstruction modeling and user demands is improved.
The foregoing description is merely an overview of the technical solutions of the present disclosure, and may be implemented according to the content of the specification in order to make the technical means of the present disclosure more clearly understood, and in order to make the above and other objects, features and advantages of the present disclosure more clearly understood, the following specific embodiments of the present disclosure are specifically described. It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.
Drawings
For a clearer description of the present disclosure or of the prior art, the drawings used in the description of the embodiments or of the prior art will be briefly described, it being obvious that the drawings in the description below are only exemplary and that other drawings may be obtained, without inventive effort, by a person skilled in the art, from the provided drawings.
Fig. 1 is a flow chart of a house type modeling optimization method based on parameterized house type information;
fig. 2 is a schematic structural diagram of a house type modeling optimization system based on parameterized house type information.
Reference numerals illustrate: the system comprises a house type demand receiving module 11, a functional area identifying module 12, a static processing module 13, a frequency searching module 14 and a house type reconstruction recommending module 15.
Detailed Description
The house type modeling optimization method and system based on parameterized house type information solve the technical problems that in the prior art, digital evaluation of the fit degree of a house type design scheme and an actual scene cannot be achieved due to house type information modeling input by a designer, and further the viscosity of the actual design scheme and the client requirement is difficult to guarantee. The house type reconstruction optimization is realized, the adaptation degree of house type reconstruction and an actual house type structure is improved, and meanwhile, the technical effects of house type reconstruction modeling and viscosity of user requirements are improved.
In the following, the technical solutions in the present disclosure will be clearly and completely described with reference to the accompanying drawings, and it is apparent that the described embodiments are only some embodiments of the present disclosure, but not all embodiments of the present disclosure, and it should be understood that the present disclosure is not limited by the example embodiments described herein. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present disclosure without making any inventive effort, are intended to be within the scope of the present disclosure. It should be further noted that, for convenience of description, only a part, but not all, of the drawings related to the present disclosure are shown.
Example 1
Referring to fig. 1, the disclosure provides a house type modeling optimization method based on parameterized house type information, wherein the method is applied to a house type modeling optimization system based on parameterized house type information, and the method specifically comprises the following steps:
step one: receiving a house type reconstruction requirement and an initial house type diagram through a client, wherein the house type reconstruction requirement comprises a requirement area type list, a requirement length threshold list, a requirement width threshold list and a requirement area threshold list;
specifically, the disclosure provides a house type modeling optimization method based on parameterized house type information, wherein the method is applied to a house type modeling optimization system based on parameterized house type information. The client refers to a platform of a user and a server, so that the user uploads data, in this embodiment, the user uploads a house type reconstruction requirement and an initial house type diagram through the client, and the server receives the house type reconstruction requirement and the initial house type diagram and then performs house type modeling analysis, and then returns a modeling result to the client, so that the user can check conveniently. For example, a user interface may be created based on the prior art, providing a form or text box for the user to enter the home improvement needs and the initial home map.
The initial house type diagram is a house type structural diagram which is formed by modifying a user currently and comprises house type composition structures and sizes. The house type reconstruction requirements comprise a requirement region type list, a requirement length threshold list, a requirement width threshold list and a requirement area threshold list, and the requirement region type list comprises region types such as living rooms, bedrooms and study rooms; the demand length threshold list, the demand width threshold list, and the demand area threshold list have a correspondence relationship with the demand area type list, such as a demand for the length, width, area of a bedroom, living room, or the like.
From this, through the customer end, receive house type transformation demand and initial house type drawing, for follow-up house type transformation modeling that carries out provides basis, guarantee transformation result and user's actual demand's adaptation degree.
Step two: performing running water treatment on the initial house type graph through a functional area identification pipeline embedded in a server to generate a functional identification area, wherein the functional identification area comprises a bearing wall area, a kitchen area and a toilet area;
specifically, the server is a server for performing house type reconstruction and modeling, the functional area identification pipeline is a functional module for performing traversal processing identification on the initial house type diagram, and is used for automatically identifying and marking each functional area in the house type diagram, namely identifying and marking the position areas of a bearing wall, a toilet and a kitchen in the initial house type diagram, and generating a functional identification area, wherein the functional identification area comprises a bearing wall area, a kitchen area and a toilet area.
Step three: carrying out static treatment on the bearing wall body area, the kitchen area and the toilet area in the initial house type diagram to generate a house type dynamic area;
specifically, the static treatment is to fix the positions of the bearing wall body area, the kitchen area and the toilet area, and then to use other areas except the bearing wall body area, the kitchen area and the toilet area, such as bedrooms, living rooms, study rooms, clothes rooms and the like, as house type dynamic areas, so that the house type dynamic areas can be modified and adjusted. Because the bearing wall body can not be adjusted at will as a house supporting structure, otherwise, safety accidents are easy to cause, the kitchen and the bathroom relate to the design of a sewer pipeline, and the design can not be changed at will, so that the phenomena of sewer blockage, water leakage and the like are easy to cause.
Step four: according to the requirement area type list, frequent searching is carried out on the house type dynamic area, and a house type reconstruction scheme set is generated;
specifically, the requirement area type list and the house type dynamic area are taken as constraints, preliminary house type reconstruction is carried out, the scheme in the house type reconstruction scheme set is a house type design history scheme which meets the requirement area type list and the house type dynamic area, that is, the scheme in the house type reconstruction scheme set is completely consistent with the bearing wall area, the kitchen area and the toilet area in the initial house type diagram, namely, the positions of the bearing wall, the kitchen and the toilet are not changed in the reconstruction process, and potential safety hazards are prevented after house type reconstruction.
Step five: and performing full-connection constraint optimization on the house type reconstruction scheme set according to the requirement length threshold list, the requirement width threshold list and the requirement area threshold list to obtain a recommended house type reconstruction scheme, modeling based on the recommended house type reconstruction scheme, generating a house type reconstruction conceptual model, and feeding back to the client.
Specifically, full-connection constraint optimizing is performed on the house type reconstruction scheme set according to the requirement length threshold list, the requirement width threshold list and the requirement area threshold list, that is, the house type reconstruction scheme set only meets the requirement area type list and the house type dynamic area, deviation among all the requirement type areas in the scheme, the requirement length threshold list, the requirement width threshold list and the requirement area threshold list is required to be minimum, a recommended house type reconstruction scheme with minimum deviation is obtained, and then modeling is performed based on the recommended house type reconstruction scheme based on the existing three-dimensional modeling technology, namely, the recommended house type reconstruction scheme is subjected to three-dimensional display, namely, a house type reconstruction conceptual model is a three-dimensional model corresponding to the recommended house type reconstruction scheme, and is fed back to the client, so that scene fit of the reconstruction scheme is digitally evaluated through house type reconstruction modeling, and the viscosity of the house type modeling and users is improved.
Further, step two of the present disclosure further includes:
the functional area identification assembly line comprises a bearing wall body identification assembly line, a kitchen identification node and a toilet identification node, wherein the bearing wall body identification assembly line, the kitchen identification node and the toilet identification node are connected in parallel; performing running water treatment on the initial house type graph according to the bearing wall identification assembly line to generate the bearing wall area; performing pipeline processing on the initial house type graph according to the kitchen identification node to generate the kitchen area; and executing pipeline processing on the initial house type graph according to the toilet identification node to generate the toilet area.
Further, the present disclosure also includes the following steps:
the bearing wall identification assembly line comprises bearing wall identification nodes and region fusion nodes; performing processing on the initial house type graph according to the bearing wall identification node to obtain a bearing wall position point cloud; fitting the position point cloud of the bearing wall body according to the region fusion node to generate the bearing wall body region; the bearing wall body identification node is obtained by performing gradient descent supervision training on a house type graph fitting data set and a bearing wall body position identification truth value set;
The region fusion node has a region fusion rule:
step A: a clustering distance threshold value is configured, clustering analysis is carried out on the bearing wall position point cloud, and a multi-cluster position point cloud is generated; and (B) step (B): traversing the peripheral positions of the multi-cluster position point clouds to perform wall association to obtain a plurality of wall areas, wherein the plurality of wall areas have a plurality of area areas; step C: traversing the areas of the plurality of areas, and carrying out point cloud density statistics on the point clouds of the plurality of clusters of positions to generate a plurality of point cloud densities of the plurality of wall areas; step D: and adding the wall bodies which are larger than or equal to the point cloud density threshold value in the wall body areas into the bearing wall body area according to the point cloud densities.
Further, the present disclosure also includes the following steps:
obtaining a first peripheral position and a second peripheral position of a wall body of a first cluster position point cloud of the multi-cluster position point clouds in the length direction; making a vertical line perpendicular to the side edge of the wall body to which the point cloud of the first cluster of positions belongs through the first peripheral position to obtain a first intercepting line; making a vertical line perpendicular to the side edge of the wall body to which the point cloud of the second cluster position belongs through the second peripheral position to obtain a second intercepting line; and intercepting the wall body to which the first cluster of position point clouds belong according to the first intercepting line and the second intercepting line to obtain a first wall body area, and adding the first wall body area into the plurality of wall body areas.
The method for generating the function identification area comprises the following steps of:
the functional area recognition assembly line comprises a bearing wall body recognition assembly line, a kitchen recognition node and a toilet recognition node, wherein the bearing wall body recognition assembly line, the kitchen recognition node and the toilet recognition node are connected in parallel, that is, the bearing wall body recognition assembly line, the kitchen recognition node and the toilet recognition node can simultaneously execute running water treatment on the initial house type graph, namely, all positions of the initial house type graph for executing the running water treatment are traversed, and position recognition of the bearing wall body, the kitchen and the toilet is performed.
The initial house type graph is subjected to running water treatment according to the bearing wall body identification assembly line, and the specific method for generating the bearing wall body area comprises the following steps: the bearing wall body recognition assembly line comprises bearing wall body recognition nodes and region fusion nodes, wherein the bearing wall body recognition nodes and the region fusion nodes are built based on an existing machine learning model, the bearing wall body recognition nodes are obtained through gradient descent supervision training of a house type map fitting dataset and a bearing wall body position identification truth set, the house type map fitting dataset and the bearing wall body position identification truth set are used as data samples for training the bearing wall body recognition nodes, the house type map fitting dataset comprises historical house type map data which are called based on the prior art, the bearing wall body position identification truth set comprises bearing wall body position region identification results corresponding to the historical house type map data, and the house type map fitting dataset and the bearing wall body position identification truth set can be identified by a person skilled in the art. The method comprises the steps of constructing the bearing wall identification node based on an existing machine learning model, such as a neural network, taking data in a house type graph fitting data set as input, taking data in a bearing wall position identification truth value set as output supervision training for the bearing wall identification node, carrying out repeated iterative training, colloquially calculating errors between a bearing wall position predicted value and a bearing wall position identification truth value output by training each time of iterative training, and then adjusting model parameters, such as weights, of the bearing wall identification node, reducing the errors, wherein the errors are gradient descent supervision training processes.
And inputting the initial house type graph into the bearing wall body identification node to perform processing, obtaining the position of the bearing wall body, and then performing point cloud conversion, namely establishing a three-dimensional coordinate system, mapping the position of the bearing wall body into the three-dimensional coordinate system, and obtaining a position coordinate as the position point cloud of the bearing wall body.
Fitting the bearing wall position point cloud according to the region fusion node to generate the bearing wall region, wherein the region fusion node has a region fusion rule as follows:
step A: and configuring a clustering distance threshold, wherein the clustering distance threshold refers to a distance reference threshold for clustering point clouds, namely, the distance between two bearing wall position point clouds is smaller than or equal to the clustering distance threshold, and the two bearing wall position point clouds can be clustered into a cluster, and the clustering distance threshold is specifically set by combining actual setting by a person skilled in the art. And carrying out cluster analysis on the position point clouds of the bearing wall body by taking a cluster distance threshold value as a standard, namely calculating the distance between any two point clouds in the position point clouds of the bearing wall body, and if the distance is smaller than or equal to the cluster distance threshold value, clustering the point clouds into a cluster to generate multi-cluster position point clouds.
And (B) step (B): traversing the peripheral positions of the multi-cluster position point clouds to perform wall body association, wherein the peripheral positions are two end edge positions in the length direction of the wall body corresponding to the multi-cluster position point clouds, and the area between the two end edge positions is a wall body area, so that the wall body is intercepted, the area of the intercepted wall body area is calculated, and a plurality of wall body areas can be obtained, wherein the wall body areas have a plurality of area areas.
Specifically, the specific method for obtaining the plurality of wall areas by traversing the peripheral positions of the multi-cluster position point clouds to perform wall association is as follows: first, a first peripheral position and a second peripheral position of a wall body in the length direction of a first cluster position point cloud of the multi-cluster position point clouds are obtained, wherein the first cluster position point cloud generally refers to any cluster position point cloud in the multi-cluster position point clouds, the wall body comprises a length direction, a width direction and a height direction, the wall body length direction is the other direction relative to the thickness direction and the height direction of the wall body, and the wall body length direction is specifically determined by combining reality. The first peripheral position and the second peripheral position are position point clouds which belong to two ends of the edge of the wall body in the length direction in the first cluster position point cloud.
Making a vertical line perpendicular to the side edge of the wall body to which the point cloud of the first cluster of positions belongs at the first peripheral position, namely a line segment which is parallel to the ground of the wall body and intersects with the first peripheral position, and taking the line segment as a first intercepting line; and similarly, making a vertical line perpendicular to the side edge of the wall body to which the point cloud of the second cluster position belongs at the second peripheral position to obtain a second intercepting line. And intercepting the wall body to which the first cluster of position point clouds belong according to the first intercepting line and the second intercepting line, namely intercepting a point cloud area which belongs to the space between the first intercepting line and the second intercepting line as a first wall body area, and adding the first wall body area into the plurality of wall body areas. By adopting the same method, the wall areas corresponding to the point clouds at the multiple clusters are obtained and added to the wall areas, so that the identification and segmentation of the wall areas are realized, the subsequent analysis of the bearing wall is facilitated, a foundation is provided for house type reconstruction, and the bearing wall is prevented from being reconstructed, so that potential safety hazards are brought.
Step C: and traversing the areas of the multiple areas, and carrying out point cloud density statistics on the multi-cluster position point clouds, namely analyzing the number of the point clouds in the area of the unit area in the multi-cluster position point clouds, specifically counting the number of the point clouds in the multi-cluster position point clouds, dividing the number of the point clouds by the area of the areas, and obtaining a result which is the density of the multiple point clouds in the multiple wall areas.
Step D: according to the plurality of point cloud densities, adding the wall body larger than or equal to the point cloud density threshold value in the plurality of wall body areas into the bearing wall body area, wherein the point cloud density threshold value is set by a person skilled in the art in combination with practical experience, that is, under normal conditions, the distance between the point clouds on the bearing wall body should be relatively close, the number of the point clouds in the unit area is regular, that is, the point cloud density is necessarily larger than the point cloud density threshold value, if the point cloud density is relatively small, the number of the point clouds in the unit area is relatively small, the problem that the identification error of the wall body position occurs in the bearing wall body identification node is likely to occur, and only the wall body larger than or equal to the point cloud density threshold value is added into the bearing wall body area, so that the accuracy of wall body identification is improved.
The initial house type diagram is used for distinguishing the bearing wall body from the common wall body only by using different colors, so that a relatively complex identification method is arranged for ensuring the identification accuracy of the bearing wall body. However, since the character recognition is performed on the functional area, the kitchen area and the toilet area can be recognized by performing the character recognition. The kitchen identification node and the toilet identification node can be constructed based on the existing two-class model, namely, the kitchen identification node only needs to identify the text marking results of all the position areas in the initial house type graph and then judge whether the kitchen identification node is a kitchen or not, and if so, the kitchen identification node is used as a kitchen area; similarly, the toilet identification node only needs to identify the text marking results of each position area in the initial house type diagram and then judges whether the toilet is a toilet or not, and if so, the toilet is used as the toilet area.
Therefore, the identification of the functional identification area is realized, a foundation is laid for the follow-up house type reconstruction, and the bearing wall is prevented from being reconstructed, so that potential safety hazards are brought.
Further, step four of the present disclosure further includes:
taking the requirement area type list and the house type dynamic area as constraints, and collecting a house type design history scheme set; traversing the household design history scheme set to perform pairwise distance analysis to generate a scheme distance set; configuring a scheme distance threshold, and clustering the scheme distance set to generate a multi-cluster house type design history scheme, wherein the multi-cluster house type design history scheme is provided with a cluster scheme quantity proportion which is equal to the ratio of the cluster scheme quantity to the total number of schemes; and deleting the clusters with the intra-cluster scheme quantity ratio smaller than or equal to the intra-cluster scheme quantity ratio threshold value to obtain the house type reconstruction scheme set.
Further, the present disclosure also includes the following steps:
according to the requirement area type list, a first layout center position and a first layout shape of a first requirement area type of a first scheme are obtained; obtaining a second layout center position and a second layout shape of the first requirement region type of the second scheme according to the requirement region type list; obtaining the position distance between the first layout center position and the second layout center position, and carrying out normalization processing on the position distance to generate a first characteristic distance, wherein the first characteristic distance has a first weight; obtaining the shape distance of the first layout shape and the second layout shape, and carrying out normalization processing on the shape distance to generate a second characteristic distance, wherein the second characteristic distance has a second weight; according to the first weight and the second weight, a weighted average value is obtained for the first characteristic distance and the second characteristic distance, and a first requirement area type distance is generated; repeating the analysis to obtain the first demand area type distance and the second demand area type distance until the N demand area type distance, wherein N is an integer, and N is the total number of the demand area types; and carrying out average value evaluation on the first requirement area type distance and the second requirement area type distance to the N requirement area type distance to obtain scheme distances of the first scheme and the second scheme, and adding the scheme distances into the scheme distance set.
Specifically, according to the requirement area type list, frequent searching is performed on the house type dynamic area, and the method for generating the house type reconstruction scheme set is as follows:
and taking the required area type list and the household type dynamic area as constraints, collecting a household type design history scheme set, wherein it can be understood that the required area type list comprises area types required by users, such as bedrooms, children rooms, study rooms, living rooms and the like, so that the area types in all schemes in the household type design history scheme set are completely consistent with the required area types in the required area type list, and the positions of the area types in all schemes are in the household type dynamic area range. The user type design history scheme set can be built by calling the history user type design scheme meeting the requirement area type list and the user type dynamic area through the existing internet big data. And then traversing any two schemes in the house type design history scheme set to analyze the distance between every two schemes, namely analyzing the difference between the two schemes, wherein the scheme distance reflects the difference between the schemes, thereby generating a scheme distance set.
Traversing the household design history scheme set to analyze the distance between every two, and generating a scheme distance set by the following steps: first, according to the requirement area type list, a first layout center position and a first layout shape of a first requirement area type of a first scheme are obtained, wherein the first scheme generally refers to any scheme in the household type design history scheme set, and the first requirement area type generally refers to any requirement area type in the requirement area type list, such as a bedroom. The central point coordinate position of the area corresponding to the first requirement area type in the first scheme is extracted as a first layout central position, and the edge shape of the corresponding area is extracted as a first layout shape.
Similarly, according to the requirement area type list, a second layout center position and a second layout shape of a first requirement area type of a second scheme are obtained, the second scheme refers to any scheme except the first scheme in the household type design history scheme set, and the second layout center position and the second layout shape are obtained by adopting the same method. The position distances of the first layout center position and the second layout center position are further calculated, normalization processing is performed on the position distances, the normalization processing is an existing common data processing method, the purpose of the normalization processing is to convert data into a specific range or standard so as to perform analysis and processing better, in the embodiment, the normalization processing is used for processing the position distances to eliminate the influence of different distance units, meanwhile, data is reduced, analysis and calculation are convenient, the normalization processing is a common technical means for a person skilled in the art, the normalization processing is not performed, the position distances after the normalization processing are used as first feature distances, the first feature distances have first weights, and the first weights are set by a person skilled in the art in combination with actual requirements, and can also be set by a user through a client terminal according to own requirements.
The shape distance between the first layout shape and the second layout shape is an index for measuring the difference between the first layout shape and the second layout shape, specifically, the similarity between the first layout shape and the second layout shape can be obtained based on a similarity analysis method in the prior art, such as cosine similarity calculation, and then the similarity is subtracted by 1, so that the obtained result is the shape distance, and the similarity comparison is a common technical means for those skilled in the art, and is not developed here. And further carrying out normalization processing on the shape distances, converting all shape distance data into a form with the same scale so as to facilitate comparison and analysis, and taking the normalized shape distances as second characteristic distances, wherein the second characteristic distances have second weights, the second weights are set by a person skilled in the art in combination with actual demands, and can also be set by a user through a client terminal according to own demands, and the sum of the first weights and the second weights is 1.
And further according to the first weight and the second weight, calculating weighted average values of the first characteristic distance and the second characteristic distance, namely multiplying the first characteristic distance by the first weight and multiplying the second characteristic distance by the second weight respectively, and then adding and then calculating average values, wherein the obtained result is the first required region type distance. Repeating the steps, obtaining the position distance and the shape distance of the first scheme and the second scheme on the second requirement region type, then obtaining a weighted average value, obtaining the second requirement region type distance, and the like, traversing all the requirement region types in the requirement region type list, and obtaining the first requirement region type distance and the second requirement region type distance until the N requirement region type distance, wherein N is an integer, and N is the total number of the requirement region types. And finally, carrying out average value evaluation on the first requirement area type distance and the second requirement area type distance to the N requirement area type distance, namely calculating an average value, taking an average value calculation result as the scheme distances of the first scheme and the second scheme, and adding the scheme distances into the scheme distance set. And similarly, traversing the house type design history scheme set by adopting the same method to analyze the distance two by two to obtain the scheme distance between any two schemes and obtain the scheme distance set, so that the preliminary screening of house type reconstruction schemes is realized by carrying out the difference analysis on the schemes in the house type design history scheme set, and the technical effect of providing support for obtaining the house type reconstruction scheme set is achieved.
Further, a scheme distance threshold is configured, wherein the scheme distance threshold refers to a scheme distance for judging that any two schemes can be clustered, and the scheme distance threshold is set by a person skilled in the art in combination with actual experience. And clustering the scheme distance sets, namely, if the scheme distance of any two schemes is smaller than or equal to a scheme distance threshold value, clustering the two schemes into one cluster, traversing the scheme distance sets, realizing the clustering of all schemes in the household type design history scheme set, obtaining multi-cluster household type design history schemes based on a clustering result, counting the number of schemes respectively contained in the multi-cluster household type design history schemes as the number of schemes in the cluster, taking the number of schemes in the household type design history scheme set as the total number of schemes, calculating the ratio of the number of schemes in the cluster to the total number of schemes, and marking the ratio of the number of schemes in the cluster of the multi-cluster household type design history scheme. And finally, deleting the cluster with the intra-cluster scheme quantity ratio smaller than or equal to the intra-cluster scheme quantity ratio threshold, wherein the intra-cluster scheme quantity ratio threshold is set by a person skilled in the art in combination with actual requirements, that is, any cluster house type design history scheme with smaller intra-cluster scheme quantity ratio contains fewer schemes, namely, other users select fewer schemes in the history, delete the schemes and do not recommend the schemes, and the rest schemes form the house type reconstruction scheme set. Therefore, the preliminary screening of the schemes is carried out by carrying out the distance evaluation between the historical schemes, and the technical effects of reducing the number of schemes for carrying out the subsequent deviation evaluation and improving the efficiency are achieved.
Further, step five of the present disclosure further includes:
configuring a third weight for the demand length normalized deviation, a fourth weight for the demand width normalized deviation, and a fifth weight for the demand area normalized deviation; constructing a deviation evaluation function:
；
wherein,the deviation evaluation value of the i-th scheme is characterized,the demand length normalized deviation of the jth demand field type characterizing the ith scenario,the normalized deviation of demand width for the jth demand field type characterizing the ith scenario,the normalized deviation of the demand area for the jth demand area type characterizing the ith scenario,as a result of the third weight being given,for the fourth weight to be the fourth weight,as a result of the fifth weight being given,characterizing the total number of the types of the demand areas;
traversing the house type reconstruction scheme set according to the deviation evaluation function, and obtaining a deviation evaluation set by taking the required length threshold value list, the required width threshold value list and the required area threshold value list as references; and screening the minimum value of the deviation evaluation set, and setting the minimum value as the recommended house type reconstruction scheme.
Specifically, a third weight is configured for the normalized deviation of the required length, a fourth weight is configured for the normalized deviation of the required width, a fifth weight is configured for the normalized deviation of the required area, the sum of the third weight, the fourth weight and the fifth weight is 1, and the specific weight value can be set by a person skilled in the art in combination with the actual requirement. Constructing a deviation evaluation function:
；
Wherein,the deviation evaluation value of the i-th scheme is characterized,the demand length normalized deviation of the jth demand field type characterizing the ith scenario,the normalized deviation of demand width for the jth demand field type characterizing the ith scenario,characterizing the normalized deviation of the demand area of the jth demand area type of the ith scheme, which belongs to the house type reconstruction scheme set,is of a third weight，For the fourth weight to be the fourth weight,as a result of the fifth weight being given,and (3) representing the total number of the demand region types, namely, carrying out weighted averaging on the demand length normalization deviation, the demand width normalization deviation and the demand area normalization deviation corresponding to the N demand region types corresponding to the ith scheme, adding and summing, and dividing by the total number of the demand region types.
Based on this, according to the deviation evaluation function, the house type reconstruction scheme set is traversed, the requirement length threshold list, the requirement width threshold list and the requirement area threshold list are used as references, that is, the requirement length threshold list, the requirement width threshold list and the requirement area threshold list need to be guaranteed that the recommended house type reconstruction scheme can be met to the maximum extent, the requirement area type list comprises requirement areas of users, such as bedrooms and living rooms, the requirement length threshold list, the requirement width threshold list and the requirement area threshold list have a one-to-one correspondence with the requirement area type list, the difference value is calculated after normalization processing is carried out on the length in the scheme in the house type reconstruction scheme set and the requirement length in the requirement length threshold list according to any requirement area type in the requirement length threshold list, and the calculated result is used as a requirement length normalization deviation corresponding to the requirement area type. And similarly, traversing a demand area type list, calculating the demand length normalization deviation corresponding to all demand area types, adopting the same method, calculating and obtaining the demand width normalization deviation and the demand area normalization deviation, substituting the deviation evaluation function, and calculating the deviation evaluation values of all schemes in the house type reconstruction scheme set to form a deviation evaluation set. And finally, screening a scheme corresponding to the minimum value of the deviation evaluation set as the recommended house type reconstruction scheme. The recommendation of the house type reconstruction scheme is realized, the difference between the recommendation scheme and the customer demand is reduced, and the technical effects of house type modeling and the viscosity of the customer demand are improved.
In summary, the house type modeling optimization method based on parameterized house type information provided by the present disclosure has the following technical effects:
receiving a house type reconstruction requirement and an initial house type diagram through a client, wherein the house type reconstruction requirement comprises a requirement area type list, a requirement length threshold value list, a requirement width threshold value list and a requirement area threshold value list; performing running water treatment on the initial house type graph through a functional area identification assembly line embedded in the server side to generate a functional identification area, wherein the functional identification area comprises a bearing wall area, a kitchen area and a toilet area; carrying out static treatment on the bearing wall body area, the kitchen area and the toilet area in the initial house type diagram to generate a house type dynamic area; according to the requirement region type list, frequent searching is carried out on the household type dynamic region, and a household type reconstruction scheme set is generated; and performing full-connection constraint optimization on the house type reconstruction scheme set according to the requirement length threshold list, the requirement width threshold list and the requirement area threshold list to obtain a recommended house type reconstruction scheme, modeling based on the recommended house type reconstruction scheme, generating a house type reconstruction conceptual model, and feeding back to the client. The method comprises the steps of carrying out static processing on an initial house type diagram after functional area identification to generate a house type dynamic area, carrying out preliminary screening on house type reconstruction schemes by combining a demand area type list, and finally carrying out full-connection constraint optimization by combining house type reconstruction demands to realize house type reconstruction optimization, so that the adaptation degree of house type reconstruction and an actual house type structure is improved, and meanwhile, the technical effect of viscosity of house type reconstruction modeling and user demands is improved.
Example two
Based on the same inventive concept as the house type modeling optimization method based on parameterized house type information in the foregoing embodiment, the present disclosure further provides a house type modeling optimization system based on parameterized house type information, referring to fig. 2, the system includes:
the house type demand receiving module 11 is configured to receive a house type reconstruction demand and an initial house type graph through a client, where the house type reconstruction demand includes a demand area type list, a demand length threshold list, a demand width threshold list and a demand area threshold list;
the functional area identification module 12 is configured to perform pipeline processing on the initial house type graph through a functional area identification pipeline embedded in a server side, so as to generate a functional identification area, where the functional identification area includes a bearing wall area, a kitchen area and a toilet area;
the static processing module 13 is used for performing static processing on the bearing wall body area, the kitchen area and the toilet area in the initial house type diagram to generate a house type dynamic area;
the frequent searching module 14 is configured to perform frequent searching on the household type dynamic area according to the requirement area type list, and generate a household type modification scheme set;
The house type reconstruction recommendation module 15, the house type reconstruction recommendation module 15 is configured to perform full-connection constraint optimization on the house type reconstruction scheme set according to the requirement length threshold list, the requirement width threshold list and the requirement area threshold list, obtain a recommended house type reconstruction scheme, perform modeling based on the recommended house type reconstruction scheme, generate a house type reconstruction conceptual model, and feed back to the client.
Further, the functional area identification module 12 in the system is further configured to:
the functional area identification assembly line comprises a bearing wall body identification assembly line, a kitchen identification node and a toilet identification node, wherein the bearing wall body identification assembly line, the kitchen identification node and the toilet identification node are connected in parallel;
performing running water treatment on the initial house type graph according to the bearing wall identification assembly line to generate the bearing wall area;
performing pipeline processing on the initial house type graph according to the kitchen identification node to generate the kitchen area;
and executing pipeline processing on the initial house type graph according to the toilet identification node to generate the toilet area.
Further, the functional area identifying module 12 is further configured to:
The bearing wall identification assembly line comprises bearing wall identification nodes and region fusion nodes;
performing processing on the initial house type graph according to the bearing wall identification node to obtain a bearing wall position point cloud;
fitting the position point cloud of the bearing wall body according to the region fusion node to generate the bearing wall body region;
the bearing wall body identification node is obtained by performing gradient descent supervision training on a house type graph fitting data set and a bearing wall body position identification truth value set;
the region fusion node has a region fusion rule:
step A: a clustering distance threshold value is configured, clustering analysis is carried out on the bearing wall position point cloud, and a multi-cluster position point cloud is generated;
and (B) step (B): traversing the peripheral positions of the multi-cluster position point clouds to perform wall association to obtain a plurality of wall areas, wherein the plurality of wall areas have a plurality of area areas;
step C: traversing the areas of the plurality of areas, and carrying out point cloud density statistics on the point clouds of the plurality of clusters of positions to generate a plurality of point cloud densities of the plurality of wall areas;
step D: and adding the wall bodies which are larger than or equal to the point cloud density threshold value in the wall body areas into the bearing wall body area according to the point cloud densities.
Further, the functional area identifying module 12 is further configured to:
obtaining a first peripheral position and a second peripheral position of a wall body of a first cluster position point cloud of the multi-cluster position point clouds in the length direction;
making a vertical line perpendicular to the side edge of the wall body to which the point cloud of the first cluster of positions belongs through the first peripheral position to obtain a first intercepting line;
making a vertical line perpendicular to the side edge of the wall body to which the point cloud of the second cluster position belongs through the second peripheral position to obtain a second intercepting line;
and intercepting the wall body to which the first cluster of position point clouds belong according to the first intercepting line and the second intercepting line to obtain a first wall body area, and adding the first wall body area into the plurality of wall body areas.
Further, the frequent search module 14 in the system is also configured to:
taking the requirement area type list and the house type dynamic area as constraints, and collecting a house type design history scheme set;
traversing the household design history scheme set to perform pairwise distance analysis to generate a scheme distance set;
configuring a scheme distance threshold, and clustering the scheme distance set to generate a multi-cluster house type design history scheme, wherein the multi-cluster house type design history scheme is provided with a cluster scheme quantity proportion which is equal to the ratio of the cluster scheme quantity to the total number of schemes;
And deleting the clusters with the intra-cluster scheme quantity ratio smaller than or equal to the intra-cluster scheme quantity ratio threshold value to obtain the house type reconstruction scheme set.
Further, the frequent searching module 14 is further configured to:
according to the requirement area type list, a first layout center position and a first layout shape of a first requirement area type of a first scheme are obtained;
obtaining a second layout center position and a second layout shape of the first requirement region type of the second scheme according to the requirement region type list;
obtaining the position distance between the first layout center position and the second layout center position, and carrying out normalization processing on the position distance to generate a first characteristic distance, wherein the first characteristic distance has a first weight;
obtaining the shape distance of the first layout shape and the second layout shape, and carrying out normalization processing on the shape distance to generate a second characteristic distance, wherein the second characteristic distance has a second weight;
according to the first weight and the second weight, a weighted average value is obtained for the first characteristic distance and the second characteristic distance, and a first requirement area type distance is generated;
Repeating the analysis to obtain the first demand area type distance and the second demand area type distance until the N demand area type distance, wherein N is an integer, and N is the total number of the demand area types;
and carrying out average value evaluation on the first requirement area type distance and the second requirement area type distance to the N requirement area type distance to obtain scheme distances of the first scheme and the second scheme, and adding the scheme distances into the scheme distance set.
Further, the house type improvement recommendation module 15 in the system is further configured to:
configuring a third weight for the demand length normalized deviation, a fourth weight for the demand width normalized deviation, and a fifth weight for the demand area normalized deviation;
constructing a deviation evaluation function:
；
wherein,the deviation evaluation value of the i-th scheme is characterized,the demand length normalized deviation of the jth demand field type characterizing the ith scenario,the normalized deviation of demand width for the jth demand field type characterizing the ith scenario,characterization of the jth demand region of the ith scenarioThe required area of the domain type normalizes the deviation,as a result of the third weight being given,for the fourth weight to be the fourth weight,as a result of the fifth weight being given, Characterizing the total number of the types of the demand areas;
traversing the house type reconstruction scheme set according to the deviation evaluation function, and obtaining a deviation evaluation set by taking the required length threshold value list, the required width threshold value list and the required area threshold value list as references;
and screening the minimum value of the deviation evaluation set, and setting the minimum value as the recommended house type reconstruction scheme.
In this description, each embodiment is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, so that the foregoing method and specific example for optimizing house type modeling based on parameterized house type information in the first embodiment of fig. 1 are also applicable to the house type modeling optimizing system based on parameterized house type information in this embodiment, and by the foregoing detailed description of the house type modeling optimizing method based on parameterized house type information, those skilled in the art can clearly know about the house type modeling optimizing system based on parameterized house type information in this embodiment, so that the description is not further detailed herein. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present disclosure without departing from the spirit or scope of the disclosure. Thus, given that such modifications and variations of the disclosure are within the scope of the disclosure and its equivalents, the disclosure is also intended to include such modifications and variations.
Claims (8)
1. The house type modeling optimization method based on parameterized house type information is characterized by comprising the following steps of:
receiving a house type reconstruction requirement and an initial house type diagram through a client, wherein the house type reconstruction requirement comprises a requirement area type list, a requirement length threshold list, a requirement width threshold list and a requirement area threshold list;
Performing running water treatment on the initial house type graph through a functional area identification pipeline embedded in a server to generate a functional identification area, wherein the functional identification area comprises a bearing wall area, a kitchen area and a toilet area;
carrying out static treatment on the bearing wall body area, the kitchen area and the toilet area in the initial house type diagram to generate a house type dynamic area;
according to the requirement area type list, frequent searching is carried out on the house type dynamic area, and a house type reconstruction scheme set is generated;
and performing full-connection constraint optimization on the house type reconstruction scheme set according to the requirement length threshold list, the requirement width threshold list and the requirement area threshold list to obtain a recommended house type reconstruction scheme, modeling based on the recommended house type reconstruction scheme, generating a house type reconstruction conceptual model, and feeding back to the client.
2. The method of claim 1, wherein the step of performing a pipeline process on the initial floor plan through a functional area identification pipeline embedded in a server to generate a functional identification area, wherein the functional identification area comprises a bearing wall area, a kitchen area and a toilet area, and comprises:
The functional area identification assembly line comprises a bearing wall body identification assembly line, a kitchen identification node and a toilet identification node, wherein the bearing wall body identification assembly line, the kitchen identification node and the toilet identification node are connected in parallel;
performing running water treatment on the initial house type graph according to the bearing wall identification assembly line to generate the bearing wall area;
performing pipeline processing on the initial house type graph according to the kitchen identification node to generate the kitchen area;
and executing pipeline processing on the initial house type graph according to the toilet identification node to generate the toilet area.
3. The method of claim 2, wherein performing a pipelining process on the initial floor plan based on the loadwall identification pipeline to generate the loadwall area comprises:
the bearing wall identification assembly line comprises bearing wall identification nodes and region fusion nodes;
performing processing on the initial house type graph according to the bearing wall identification node to obtain a bearing wall position point cloud;
fitting the position point cloud of the bearing wall body according to the region fusion node to generate the bearing wall body region;
The bearing wall body identification node is obtained by performing gradient descent supervision training on a house type graph fitting data set and a bearing wall body position identification truth value set;
the region fusion node has a region fusion rule:
step A: a clustering distance threshold value is configured, clustering analysis is carried out on the bearing wall position point cloud, and a multi-cluster position point cloud is generated;
and (B) step (B): traversing the peripheral positions of the multi-cluster position point clouds to perform wall association to obtain a plurality of wall areas, wherein the plurality of wall areas have a plurality of area areas;
step C: traversing the areas of the plurality of areas, and carrying out point cloud density statistics on the point clouds of the plurality of clusters of positions to generate a plurality of point cloud densities of the plurality of wall areas;
step D: and adding the wall bodies which are larger than or equal to the point cloud density threshold value in the wall body areas into the bearing wall body area according to the point cloud densities.
4. The method of claim 3, wherein traversing the peripheral locations of the multi-cluster location point cloud for wall association obtains a plurality of wall areas, comprising:
obtaining a first peripheral position and a second peripheral position of a wall body of a first cluster position point cloud of the multi-cluster position point clouds in the length direction;
Making a vertical line perpendicular to the side edge of the wall body to which the point cloud of the first cluster of positions belongs through the first peripheral position to obtain a first intercepting line;
making a vertical line perpendicular to the side edge of the wall body to which the point cloud of the second cluster position belongs through the second peripheral position to obtain a second intercepting line;
and intercepting the wall body to which the first cluster of position point clouds belong according to the first intercepting line and the second intercepting line to obtain a first wall body area, and adding the first wall body area into the plurality of wall body areas.
5. The method of claim 1, wherein the frequent searching of the home type dynamic area according to the requirement area type list to generate a home type modification scheme set comprises:
taking the requirement area type list and the house type dynamic area as constraints, and collecting a house type design history scheme set;
traversing the household design history scheme set to perform pairwise distance analysis to generate a scheme distance set;
configuring a scheme distance threshold, and clustering the scheme distance set to generate a multi-cluster house type design history scheme, wherein the multi-cluster house type design history scheme is provided with a cluster scheme quantity proportion which is equal to the ratio of the cluster scheme quantity to the total number of schemes;
And deleting the clusters with the intra-cluster scheme quantity ratio smaller than or equal to the intra-cluster scheme quantity ratio threshold value to obtain the house type reconstruction scheme set.
6. The method of claim 5, wherein traversing the family type design history solution set for two-by-two distance resolution generates a solution distance set, comprising:
according to the requirement area type list, a first layout center position and a first layout shape of a first requirement area type of a first scheme are obtained;
obtaining a second layout center position and a second layout shape of the first requirement region type of the second scheme according to the requirement region type list;
obtaining the position distance between the first layout center position and the second layout center position, and carrying out normalization processing on the position distance to generate a first characteristic distance, wherein the first characteristic distance has a first weight;
obtaining the shape distance of the first layout shape and the second layout shape, and carrying out normalization processing on the shape distance to generate a second characteristic distance, wherein the second characteristic distance has a second weight;
according to the first weight and the second weight, a weighted average value is obtained for the first characteristic distance and the second characteristic distance, and a first requirement area type distance is generated;
Repeating the analysis to obtain the first demand area type distance and the second demand area type distance until the N demand area type distance, wherein N is an integer, and N is the total number of the demand area types;
and carrying out average value evaluation on the first requirement area type distance and the second requirement area type distance to the N requirement area type distance to obtain scheme distances of the first scheme and the second scheme, and adding the scheme distances into the scheme distance set.
7. The method of claim 1, wherein performing full connection constraint optimization on the set of home improvement schemes based on the list of demand length thresholds, the list of demand width thresholds, and the list of demand area thresholds to obtain recommended home improvement schemes comprises:
configuring a third weight for the demand length normalized deviation, a fourth weight for the demand width normalized deviation, and a fifth weight for the demand area normalized deviation;
constructing a deviation evaluation function:
；
wherein,deviation evaluation value characterizing the ith regimen, +.>Normalized deviation of demand length for the jth demand region type characterizing the ith scenario, ++>Normalized deviation of demand width characterizing the jth demand area type of the ith scenario, ++ >Normalized deviation of the demand area characterizing the jth demand area type of the ith scenario, ++>For the third weight->For the fourth weight, ++>For the fifth weight, ++>Characterizing the total number of the types of the demand areas;
traversing the house type reconstruction scheme set according to the deviation evaluation function, and obtaining a deviation evaluation set by taking the required length threshold value list, the required width threshold value list and the required area threshold value list as references;
and screening the minimum value of the deviation evaluation set, and setting the minimum value as the recommended house type reconstruction scheme.
8. A house type modeling optimization system based on parameterized house type information, characterized by the steps for implementing the method of any of claims 1 to 7, the system comprising:
the house type demand receiving module is used for receiving house type reconstruction demands and an initial house type diagram through a client, wherein the house type reconstruction demands comprise a demand area type list, a demand length threshold list, a demand width threshold list and a demand area threshold list;
the function area identification module is used for performing running water treatment on the initial house type graph through a function area identification pipeline embedded in the server side to generate a function identification area, wherein the function identification area comprises a bearing wall area, a kitchen area and a toilet area;
The static processing module is used for carrying out static processing on the bearing wall body area, the kitchen area and the toilet area in the initial house type diagram to generate a house type dynamic area;
the frequent searching module is used for carrying out frequent searching on the household type dynamic area according to the requirement area type list to generate a household type reconstruction scheme set;
the household type reconstruction recommendation module is used for executing full-connection constraint optimization on the household type reconstruction scheme set according to the requirement length threshold list, the requirement width threshold list and the requirement area threshold list to obtain a recommended household type reconstruction scheme, modeling is conducted based on the recommended household type reconstruction scheme, a household type reconstruction conceptual model is generated, and the household type reconstruction conceptual model is fed back to the client.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410282004.7A CN117874901B (en) | 2024-03-13 | 2024-03-13 | House type modeling optimization method and system based on parameterized house type information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410282004.7A CN117874901B (en) | 2024-03-13 | 2024-03-13 | House type modeling optimization method and system based on parameterized house type information |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117874901A true CN117874901A (en) | 2024-04-12 |
| CN117874901B CN117874901B (en) | 2024-05-14 |
Family
ID=90590332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410282004.7A Active CN117874901B (en) | 2024-03-13 | 2024-03-13 | House type modeling optimization method and system based on parameterized house type information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117874901B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6424359B1 (en) * | 2017-12-01 | 2018-11-21 | 株式会社ヌカヅカ設計 | Floor plan structure of dwelling units of collective housing |
| CN110390153A (en) * | 2019-07-15 | 2019-10-29 | 贝壳技术有限公司 | Generation method, device and the equipment of layout structure modification scheme, storage medium |
| CN113657303A (en) * | 2021-08-20 | 2021-11-16 | 北京千丁互联科技有限公司 | Room structure identification method and device, terminal device and readable storage medium |
| CN114419152A (en) * | 2022-01-14 | 2022-04-29 | 中国农业大学 | Target detection and tracking method and system based on multi-dimensional point cloud characteristics |
| CN115310174A (en) * | 2022-07-14 | 2022-11-08 | 北京五八信息技术有限公司 | House information processing method, device, equipment and storage medium |
| CN115718937A (en) * | 2021-08-24 | 2023-02-28 | 久瓴(江苏)数字智能科技有限公司 | House type reconstruction design method, device and equipment based on neural network |
-
2024
- 2024-03-13 CN CN202410282004.7A patent/CN117874901B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6424359B1 (en) * | 2017-12-01 | 2018-11-21 | 株式会社ヌカヅカ設計 | Floor plan structure of dwelling units of collective housing |
| CN110390153A (en) * | 2019-07-15 | 2019-10-29 | 贝壳技术有限公司 | Generation method, device and the equipment of layout structure modification scheme, storage medium |
| CN113657303A (en) * | 2021-08-20 | 2021-11-16 | 北京千丁互联科技有限公司 | Room structure identification method and device, terminal device and readable storage medium |
| CN115718937A (en) * | 2021-08-24 | 2023-02-28 | 久瓴(江苏)数字智能科技有限公司 | House type reconstruction design method, device and equipment based on neural network |
| CN114419152A (en) * | 2022-01-14 | 2022-04-29 | 中国农业大学 | Target detection and tracking method and system based on multi-dimensional point cloud characteristics |
| CN115310174A (en) * | 2022-07-14 | 2022-11-08 | 北京五八信息技术有限公司 | House information processing method, device, equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 周燕珉;秦岭;: "老龄化背景下城市新旧住宅的适老化转型", 时代建筑, no. 06, 18 November 2016 (2016-11-18), pages 22 - 28 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117874901B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| De Cáceres et al. | The management of vegetation classifications with fuzzy clustering | |
| Xia et al. | Research on parallel adaptive canopy-k-means clustering algorithm for big data mining based on cloud platform | |
| KR101957760B1 (en) | System for estimating market price of real estate using sales cases determined based on similarity score and method thereof | |
| Kasim et al. | Application of Gibbs sampling to nested variance components models with heterogeneous within-group variance | |
| Wu et al. | Modified data-driven framework for housing market segmentation | |
| CN108205570B (en) | Data detection method and device | |
| Jochem et al. | Tools for mapping multi-scale settlement patterns of building footprints: An introduction to the R package foot | |
| US10817626B2 (en) | Design-model management | |
| Yang et al. | A Point Cloud Simplification Method Based on Modified Fuzzy C‐Means Clustering Algorithm with Feature Information Reserved | |
| CN114547749B (en) | House type prediction method, device and storage medium | |
| Adouane et al. | A model-based approach to convert a building BIM-IFC data set model into CityGML | |
| KR20220034701A (en) | Tag-based content recommendation method and server performing the same | |
| Yamada et al. | Graph structure extraction from floor plan images and its application to similar property retrieval | |
| CN114387332B (en) | Pipeline thickness measuring method and device | |
| CN107958068A (en) | A kind of language model smoothing method based on entity knowledge base | |
| CN117874901B (en) | House type modeling optimization method and system based on parameterized house type information | |
| CN111340601B (en) | Commodity information recommendation method and device, electronic equipment and storage medium | |
| KR101924448B1 (en) | Real estate clustering method and apparatus, system and method for estimating market price of real estate using the same | |
| CN106779181B (en) | Medical institution recommendation method based on linear regression factor non-negative matrix factorization model | |
| CN113537324A (en) | Family type space matching method and device based on thin geometric plane spline interpolation | |
| CN112632857A (en) | Method, device, equipment and storage medium for determining line loss of power distribution network | |
| Yang et al. | A zoning method for the extreme wind pressure coefficients of buildings based on weighted K-means clustering | |
| Azizi et al. | Application of comparative strainer clustering as a novel method of high volume of data clustering to optimal power flow problem | |
| CN117010373A (en) | Recommendation method for category and group to which asset management data of power equipment belong | |
| Wen et al. | Measuring 3D process plant model similarity based on topological relationship distribution |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |