CN119538381B

CN119538381B - Personalized indoor design method based on user house type graph

Info

Publication number: CN119538381B
Application number: CN202411656894.XA
Authority: CN
Inventors: 刘紫东; 李永燚; 钟鸿毅
Original assignee: Shenzhen Habitat Technology Co ltd
Current assignee: Shenzhen Habitat Technology Co ltd
Priority date: 2024-11-19
Filing date: 2024-11-19
Publication date: 2025-09-26
Anticipated expiration: 2044-11-19
Also published as: CN119538381A

Abstract

The invention relates to a personalized indoor design method based on a user pattern diagram, which comprises the following steps of analyzing behavior data of a target user to obtain preference parameters of the target user, carrying out vector conversion on a house plan diagram to obtain vector space relation characteristic data, inputting the vector space relation characteristic data and space function arrangement parameters into a preset graphic neural network to carry out space layout to generate an initial furniture layout scheme, carrying out scheme screening on the initial furniture layout scheme to obtain a screened furniture layout scheme, carrying out matching design on collocation parameters and the screened furniture layout scheme to obtain a matching design scheme, and carrying out initial visualization on the matching design scheme on a preset interactive interface to generate a three-dimensional visual effect diagram. Solves the technical problems that the traditional indoor design service is often high in cost and long in time consumption, and is difficult for common consumers to bear, so that the market has larger unbalanced supply and demand.

Description

Personalized indoor design method based on user house type graph

Technical Field

The invention relates to the technical field of indoor design, in particular to a personalized indoor design method based on a user house type diagram.

Background

With the acceleration of the urban process, the demands of people on living environment are increasingly increased, not only is the basic life requirement met, but also individualization and comfort are pursued. However, conventional indoor design services tend to be costly and time consuming, and are not affordable to average consumers. This results in a large imbalance of supply and demand in the market, on the one hand, consumers have a strong demand for high-quality, personalized indoor designs, and on the other hand, the existing design service modes cannot efficiently meet these demands, and in particular have a significant disadvantage in quickly responding to the personalized preferences of users.

In addition, in the conventional indoor design process, a designer usually needs to spend a lot of time and effort to communicate with the customer to understand the specific requirements and preferences, which is not only inefficient, but also easily generates information transmission deviation, thereby affecting the final design effect. With the development of information technology, especially the application of big data, artificial intelligence and other technologies, new possibilities are provided for solving the problems. By analyzing the user behavior data to predict the preference, the accuracy and service efficiency of the design can be remarkably improved, and personalized indoor designs become more convenient and popular.

Despite the advantages of using advanced technology to achieve personalized indoor designs, challenges remain in practical applications. For example, how to ensure that the recommendation algorithm can accurately capture the real needs of the user rather than just the surface preferences, how to balance the differences between design creatives and user expectations, and how to protect user privacy. If not effectively solved, the problems directly affect the user experience and market acceptance of the personalized indoor design system. Therefore, the exploration of a design method which can meet the personalized demands of users and ensure the privacy safety of the users is one of the important directions of the current research.

Disclosure of Invention

The invention mainly aims to provide a personalized indoor design method based on a user house type graph, which solves the technical problems that the traditional indoor design service is often high in cost and long in time consumption, and is difficult for common consumers to bear, so that larger unbalanced supply and demand exists in the market.

In order to achieve the above purpose, the invention provides a personalized indoor design method based on a user house type graph, which comprises the following steps:

analyzing behavior data of a target user through a preset recommendation algorithm to obtain preference parameters of the target user, wherein the preference parameters comprise space function arrangement parameters and collocation parameters;

Acquiring a house plan uploaded by a target user, and performing vector conversion on the house plan by using a plan image vectorization technology to obtain vector space relation characteristic data;

Inputting the vector space relation characteristic data and the space function configuration parameters into a preset graphic neural network to carry out space layout, and generating an initial furniture layout scheme;

carrying out scheme screening on the initial furniture layout scheme through a preset design hard rule to obtain a screened furniture layout scheme;

matching the matching parameters and the screened furniture layout schemes to obtain matching design schemes, and performing initial visualization on the matching design schemes on a preset interactive interface;

detecting whether the target user performs interface interaction operation on the interaction interface in real time, if so, taking a matching design scheme aimed by the interface interaction operation as a target scheme, and performing scheme editing and scheme rendering on the target scheme according to the interface interaction operation through a preset AI editing system to obtain a three-dimensional visual effect diagram corresponding to the house plan.

Further, the behavior data includes furniture browsing records and input text data, and the analyzing the behavior data of the target user through a preset recommendation algorithm to obtain preference parameters of the target user includes:

analyzing the furniture commodity browsing records and the input text data of the target user through a preset recommendation algorithm to obtain user-commodity interaction information, wherein the user-commodity interaction information is the browsing duration, the clicking times and the collection state of different furniture commodities by the target user;

Performing cluster analysis on the user-commodity interaction information to obtain a preference furniture style feature vector of a target user;

Analyzing the furniture commodity co-occurrence relationship in the user-commodity interaction information to obtain a furniture collocation mode vector;

analyzing furniture commodity description text in the user-commodity interaction information, and extracting space function keywords in the furniture commodity description text to obtain space function keyword vectors;

constructing a target user preference matrix based on the preference furniture style feature vector, the furniture collocation mode vector and the spatial function keyword vector;

inputting the target user preference matrix into a preset Bayesian inference algorithm to obtain the preference probability distribution of the target user;

and predicting furniture selection behaviors of the target user based on the preference probability distribution to obtain preference parameters of the target user, wherein the preference parameters of the target user comprise space function arrangement parameters and collocation parameters.

Further, the performing vector transformation on the house plan by using a plan image vectorization technology to obtain vector space relation feature data includes:

Identifying and marking each functional area in the house plan to obtain functional area marking data;

preprocessing the house plan by using a plan image vectorization technology to obtain a preprocessed image;

extracting contour lines in the preprocessed image to obtain a contour line image, classifying and marking the contour lines in the contour line image based on the functional area marking data to obtain a contour line image with functional area information;

Converting the contour line image with the functional area information into a vector graphic to obtain vector graphic data;

and carrying out spatial relationship analysis on the vector graphic data to obtain vector spatial relationship characteristic data.

Further, the step of inputting the vector spatial relationship feature data and the spatial function configuration parameters into a preset graphic neural network to perform spatial layout optimization, and generating an initial furniture layout scheme includes:

extracting spatial features from the vector spatial relationship feature data to obtain extracted spatial features, wherein the extracted spatial features comprise the area, shape, window position and door opening direction information of a house plan;

Classifying the space function arrangement parameters to obtain function region division information, wherein the function region division information comprises the area requirements and the relative position requirements of different function regions;

Constructing a spatial layout relation diagram based on the spatial feature vector and the functional division information;

performing feature propagation and fusion on the spatial layout relation graph based on a multi-scale graph neural network to obtain a fusion feature graph;

inputting the fusion feature map into a preset map neural network to perform furniture layout exploration and space layout optimization to obtain a candidate furniture layout scheme;

And carrying out rationality evaluation and screening on the candidate furniture layout schemes to obtain an initial furniture layout scheme.

Further, the method for performing scheme screening on the initial furniture layout scheme through a preset design hard rule to obtain a screened furniture layout scheme includes:

carrying out spatial relationship analysis on the initial furniture layout scheme by using a spatial topology analysis algorithm to obtain a spatial topology relationship diagram between furniture, wherein the spatial topology relationship diagram comprises relative positions, distances and connectivity between furniture;

Based on an ergonomic principle, performing ergonomic evaluation on the initial furniture layout scheme based on the spatial topological relation diagram to obtain an ergonomic scoring matrix;

Performing optimization calculation on the initial furniture layout scheme based on the ergonomic scoring matrix through a multi-objective optimization algorithm to obtain an ergonomic layout scheme set, wherein the ergonomic layout scheme set is a candidate layout scheme set meeting ergonomic requirements;

performing functional region division on the ergonomic layout scheme set to obtain a functional region semantic graph;

performing rule constraint checking on the functional area semantic graph through a preset design hard rule to obtain a constrained checked ergonomic layout scheme set;

And comprehensively evaluating and screening the ergonomic layout scheme set after constraint inspection by a multi-criterion decision analysis method to obtain a screened furniture layout scheme.

Further, the matching design is performed on the matching parameters and the screened furniture layout scheme to obtain a matching design scheme, which includes:

Respectively carrying out characteristic deconstructment on the collocation parameters and the screened furniture layout scheme to correspondingly obtain a deconstructed parameter set and a layout element set;

carrying out semantic coding on the deconstructed parameter set to obtain a coded semantic vector;

Carrying out spatial relation coding on the layout element set to obtain a spatial relation vector;

performing correlation calculation on the encoded semantic vector and the spatial relationship vector based on the attention mechanism network and a matching algorithm to obtain a matching weight matrix;

carrying out layout reorganization on the screened furniture layout scheme based on the matching weight matrix to obtain a layout reorganization scheme;

And carrying out style consistency check and adjustment on the layout reorganization scheme to obtain a matching design scheme, and carrying out initial visualization on the matching design scheme on a preset interactive interface.

Further, by using a preset AI editing system, performing scheme editing and scheme rendering on the target scheme according to the interface interaction operation, to obtain a three-dimensional visual effect diagram corresponding to the house plan, including:

Monitoring interface interaction operation of the target user on the interaction interface in real time to obtain an operation instruction sequence of the target user on the matching design scheme, wherein the operation instruction sequence comprises clicking, dragging and zooming of the recording user;

Adjusting parameters in the target scheme based on the operation instruction sequence by utilizing a multi-target optimization algorithm to obtain adjustment design parameters and adjustment design schemes corresponding to the adjustment design parameters, wherein the parameters in the target scheme comprise furniture layout parameters, color scheme parameters and material parameters;

Performing space mapping on the adjustment design scheme through a preset space mapping algorithm to obtain a three-dimensional space layout model;

Performing material and illumination rendering on the three-dimensional space layout model to obtain a three-dimensional space layout model with material textures and illumination effects;

and generating a three-dimensional visual effect diagram based on the three-dimensional space layout model with the texture and the illumination effect by a virtual reality technology.

The invention also provides a personalized indoor design system based on the user house type graph, which comprises:

the recommendation module is used for analyzing behavior data of the target user through a preset recommendation algorithm to obtain preference parameters of the target user, wherein the preference parameters comprise space function arrangement parameters and collocation parameters;

The acquisition module is used for acquiring the house plan uploaded by the target user, and carrying out vector conversion on the house plan by utilizing a plan image vectorization technology to obtain vector space relation characteristic data;

the screening module is used for carrying out scheme screening on the initial furniture layout scheme through a preset design hard rule to obtain a screened furniture layout scheme;

The matching module is used for carrying out matching design on the matching parameters and the screened furniture layout schemes to obtain matching design schemes, and carrying out initial visualization on the matching design schemes on a preset interactive interface;

And the editing module is used for detecting whether the target user performs interface interaction operation on the interaction interface in real time, if so, taking the matched design scheme aimed at by the interface interaction operation as a target scheme, and performing scheme editing and scheme rendering on the target scheme according to the interface interaction operation through a preset AI editing system to obtain a three-dimensional visual effect diagram corresponding to the house plan.

The invention also provides a computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the steps of any of the methods described above when the computer program is executed.

The invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the preceding claims.

The personalized indoor design method based on the user pattern comprises the following steps of analyzing behavior data of a target user through a preset recommendation algorithm to obtain preference parameters of the target user, wherein the preference parameters comprise space function arrangement parameters and collocation parameters, acquiring a house plane pattern uploaded by the target user, performing vector transformation on the house plane pattern through a plane pattern image vectorization technology to obtain vector space relation characteristic data, inputting the vector space relation characteristic data and the space function arrangement parameters into a preset graph neural network to perform space layout, generating an initial furniture layout scheme, performing scheme screening on the initial furniture layout scheme through preset design hard rules to obtain a screened furniture layout scheme, performing matching design on the collocation parameters and the screened furniture layout scheme to obtain a matching design scheme, and performing initial visualization on the matching design scheme on a preset interaction interface, detecting whether the target user performs interface interaction operation on the interaction interface in real time, taking the matching design scheme aimed at the interface interaction operation as the target scheme, performing scheme on the basis of the preset interaction scheme, performing scheme by using a preset AI (advanced design) according to a preset design hard rule, performing scheme-based on the target interaction scheme, and performing scheme-based on the conventional graph, thereby solving the problem that a conventional three-dimensional graph is difficult to achieve a high-dimensional consumer demand map, and a high-cost map is required to be optimized, the method not only can generate a reasonable furniture layout scheme according to the actual house type diagram of the user, but also can further screen out the optimal solution through the preset design hard rule. More importantly, the method allows the user to directly adjust the design scheme on the interactive interface, and views the adjusted three-dimensional visual effect graph in real time, so that the beneficial effects of user participation and satisfaction are greatly improved.

Drawings

FIG. 1 is a schematic diagram illustrating steps of a personalized indoor design method based on a user profile in an embodiment of the invention;

FIG. 2 is a block diagram of a personalized indoor design system based on a user profile in an embodiment of the invention;

Fig. 3 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present invention.

The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.

Detailed Description

The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.

Referring to fig. 1, fig. 1 is a schematic diagram illustrating steps of a personalized indoor design method based on a user profile in an embodiment of the invention;

the embodiment of the invention provides a personalized indoor design method based on a user house type graph, which comprises the following steps:

step S1, analyzing behavior data of a target user through a preset recommendation algorithm to obtain preference parameters of the target user, wherein the preference parameters comprise space function arrangement parameters and collocation parameters.

Specifically, in the personalized indoor design method, behavior data of a target user is analyzed through a preset recommendation algorithm, which is a key starting point of the whole design flow. The "behavior data" herein may include design style preferences of online browsing of the user, past purchase records, interactive content on social media, etc., which can reflect the user's specific preference for indoor design. For example, if a user frequently browses home cases in a modern conclusive style, the system may identify that the user may prefer such style. Next, according to the behavior data, the recommendation algorithm calculates and extracts the preference parameters of the target user, wherein the preference parameters are specifically divided into two parts, namely a 'space function arrangement parameter', namely the functional requirements of the user on different rooms or areas, such as an open kitchen or a closed kitchen, whether a bedroom needs to be provided with a working area or not, and the like, and a 'collocation parameter', namely the personal preference of the user on the aspects of color, material, ornament and the like, such as preference of cold tone or warm tone, preference of wooden furniture or metal furniture and the like. To accomplish this, the system may employ a machine learning model that, by training a large number of labeled datasets, enables the model to accurately capture the relevance of user preferences to specific design elements, thereby providing unique design suggestions for each user. For example, in an actual application scenario, when a user uploads a family pattern of his own and authorizes the system to access its online behavior data, the system can quickly generate a set of indoor design schemes that both conform to the user's lifestyle and reflect the aesthetic preferences of the individual.

And S2, acquiring a house plan uploaded by a target user, and performing vector conversion on the house plan by using a plan image vectorization technology to obtain vector space relation characteristic data.

In particular, in a personalized indoor design method, it is a crucial step to obtain a house plan uploaded by a target user, since this directly determines the basis of the subsequent design work. When a user uploads his house floor plan through an application or web site, the system will immediately process the floor plan. Reference herein to "planogram image vectorization technique" refers to the process of converting a planogram, possibly in a picture format (e.g., JPEG, PNG, etc.), uploaded by a user, into a vector graphic. The vector graphics are composed of geometric elements such as points, lines, planes and the like, can more accurately represent space structure and size information, is not limited by resolution, and is convenient for subsequent editing and calculation. In the conversion process, the system automatically recognizes and extracts key elements such as room boundaries, door and window positions and the like, and then converts the information into vector data to form so-called vector space relation characteristic data. For example, suppose a user wishes to design a modern living room layout for his new home, he first uploads a plan of his home to the design platform. Upon receiving this plan, the platform immediately initiates the vectorization technique to process it. In this process, the system can not only recognize the outline of each room, but also accurately mark the position and the size of the door and the window, and even can distinguish different wall materials, such as a bearing wall and a partition wall. Therefore, the system can obtain a detailed vector space relation characteristic data which not only contains basic structural information of the room, but also provides accurate data support for subsequent space layout planning and furniture placement. Through such processing, a designer or AI system can more efficiently perform space layout design, ensure that the design scheme not only meets the actual requirements of users, but also can fully utilize each inch space, and achieve the optimal design effect.

And S3, inputting the vector space relation characteristic data and the space function configuration parameters into a preset graphic neural network for space layout, and generating an initial furniture layout scheme.

Specifically, after the vectorization processing of the house plan is completed, the following steps are to input the vector spatial relationship characteristic data and the spatial function configuration parameters into a preset graphic neural network so as to perform deeper spatial layout analysis and optimization. This process aims to generate the most appropriate initial furniture layout solution based on user-provided plan view information and specific functional requirements through advanced machine learning algorithms. A graph neural network is a deep learning model particularly suited for processing graph structure data that can effectively capture complex relationships between nodes, which for the house design application in this example can be understood to be a good understanding and optimization of spatial relationships and functional allocations between parts within a room. For example, continuing with the living room design of the user, the vectorized house plan has been converted into vector space relationship feature data containing information about all room boundaries, door and window positions, wall types, and the like. At the same time, the user explicitly indicates his/her need for living room space, such as the need for a sufficient leisure area, television viewing area, and possibly office corners, etc., which constitute the spatial function arrangement parameters. When the data are input into the preset graphic neural network, the network comprehensively considers the shape, the size, the orientation and other factors of each room, and finally outputs one or more optimal initial furniture layout schemes by simulating various layout possibilities in combination with specific functional requirements set by users. The schemes not only can meet the functional requirements of users, but also can furthest improve the space utilization rate and the aesthetic degree, and provide an intuitive and practical design reference for the users. By the mode, even non-professional users can easily obtain the professional-level indoor design scheme, and the efficiency and satisfaction of the whole design flow are greatly improved.

And S4, carrying out scheme screening on the initial furniture layout scheme through a preset design hard rule to obtain a screened furniture layout scheme.

Specifically, after the initial furniture layout solution is generated, in order to ensure the rationality and practicality of the design solution, further screening of these solutions by preset design hard rules is required. As used herein, "design hard rules" refers to a series of criteria established based on interior design basic principles and ergonomics for evaluating the feasibility and comfort of a furniture layout solution. These rules may include, but are not limited to, minimum spacing requirements between furniture, unobstructed areas of passage in front of doors and windows, safety distances of electrical outlets and switches, etc., in order to ensure that the design is not only aesthetically pleasing, but also safe and practical. Taking the living room design previously mentioned as an example, assume that the graphic neural network has generated several different initial furniture layout schemes. At this point, the system will automatically invoke the preset design hard rules to evaluate each solution. For example, one rule might be to ensure that a distance of at least 3 meters is maintained between the sofa and the television to provide a comfortable viewing experience, and another rule would require that the width of all major channels must not be less than 90 cm to ensure smooth movement of the family members. By applying these rules, the system can exclude layout schemes that do not meet the standard, such as a scheme where the distance between the sofa and the tea table is too small, or where the television cabinet is located to obstruct access to the balcony. After the screening, the system finally keeps furniture layout schemes which meet the personalized requirements of users and basic design specifications, and the screened furniture layout schemes not only can be better suitable for actual life modes of the users, but also ensure the safety and convenience of home environments. Through the screening process, the quality of the design scheme can be improved, and the trust degree and satisfaction degree of the user on the final design result can be enhanced.

And S5, carrying out matching design on the matching parameters and the screened furniture layout schemes to obtain matching design schemes, and carrying out initial visualization on the matching design schemes on a preset interactive interface.

Specifically, after the screening of the furniture layout scheme is completed, the matching parameters and the screened furniture layout scheme are subjected to matching design to generate a final matching design scheme. The "collocation parameters" herein refer to specific preferences of users in terms of color, material, decoration style, etc., and the "screened furniture layout scheme" is a layout scheme conforming to functionality and safety after being checked by design hard rules. By combining the two, the system can provide a design scheme which meets the personalized requirements and has practical feasibility for users. For example, in a living room designed application scenario, it is assumed that users prefer modern conciseness styles, tend to use white and gray as main hues, and enjoy the natural feel of wooden furniture. After the system obtains the collocation parameters, the collocation parameters are combined with the furniture layout schemes screened before, and furniture styles, colors and materials which accord with the style preference of users are automatically selected, for example, white sofa is selected to be matched with gray carpets, and wooden coffee tables and TV cabinets are selected. In addition, the system also considers the selection of ornaments, such as hanging pictures, lamps and lanterns, etc., and ensures the consistency and coordination of the whole style. After the matching design is completed, the system can perform initial visual display on a preset interactive interface on the obtained matching design scheme. This means that the user can see the design effect of the living room in a virtual three-dimensional environment, including details such as the placement position, color collocation, texture of materials, etc. of the furniture, so as to obtain visual feeling. If the user has any opinion or suggestion on the preliminary design scheme, the user can also adjust the design scheme in real time through the interactive interface, for example, the user can change the sofa with different styles or change the color of the wall surface, and the system can update the design scheme in real time according to the feedback of the user until the user is satisfied. The interactive design flow not only improves the flexibility of design and the participation of users, but also ensures that the final design result completely meets the expectations of the users.

And S6, detecting whether the target user performs interface interaction operation on the interaction interface in real time, if so, taking a matching design scheme aimed at by the interface interaction operation as a target scheme, and performing scheme editing and scheme rendering on the target scheme according to the interface interaction operation through a preset AI editing system to obtain a three-dimensional visual effect diagram corresponding to the house plan.

Specifically, in the process of personalized indoor design, the system can detect whether the target user performs any interface interaction operation on a preset interaction interface in real time. This link is a key part of the user's participation in the design process, and in this way, the user can directly participate in the adjustment and refinement of the design. Once the interface interaction operation is detected by the user, the system immediately takes the matching design scheme aimed at by the operation as a target scheme, and correspondingly edits and renders the target scheme according to the operation of the user through a preset AI editing system, so that an updated three-dimensional visual effect diagram is finally generated. For example, in the foregoing living room design case, the user first sees the living room design scheme generated by the system for the user through the interactive interface, including the placement position of furniture, color matching, and selection of decorations. Assuming that the user feels the sofa somewhat monotonous in color, it is desirable to activate the spatial atmosphere by adding some colors. The user then selects the sofa on the interactive interface and selects a dark blue color from the color options. At this time, the system detects the operation of the user in real time, and immediately uses the current design scheme as a target scheme, and calls a preset AI editing system for editing. The AI editing system can recalculate the color collocation between the sofa and other furniture, walls, floors and other elements according to the new color selected by the user, so as to ensure the harmony and unity of the whole visual effect. Meanwhile, the system can render the new design scheme to generate the latest three-dimensional visual effect graph, so that a user can immediately see the adjusted actual effect. If the user is still dissatisfied with the new scheme, other aspects of adjustment can be continuously carried out through the interactive interface, such as changing tea tables of different styles or adding wall decorations, etc., the system can respond and update in real time in the same way. Through the real-time interaction mode, the participation of the user is greatly enhanced, the design process is more flexible and efficient, and the final design scheme is ensured to meet the personalized requirements of the user to the greatest extent.

In a specific embodiment, the behavior data includes furniture browsing records and input text data, and the analyzing the behavior data of the target user by a preset recommendation algorithm to obtain preference parameters of the target user includes:

Specifically, in the personalized indoor design scheme, in order to meet the requirements of the target user more accurately, the system collects and analyzes the behavior data of the target user, wherein the data mainly comprise furniture browsing records and text data input by the user. Through the data, the system can deeply understand the preference of the user for the furniture, so that furniture recommendation and service which are more in line with personal preference are provided for the user. Specifically, the system firstly carries out deep analysis on furniture commodity browsing records and input text data of a target user through a preset recommendation algorithm, and aims to acquire interaction information between the user and the commodity. The user-commodity interaction information covers various contents such as browsing time length, clicking times and collection state of different furniture commodities by a target user. For example, when a user stays on a sofa page of a modern reduced style for a long time, clicks multiple times to view details and even collect them, this indicates that the user may have a high interest in the sofa, and even the entire modern reduced style furniture. The system then performs a cluster analysis of the user-merchandise interaction information to refine the target user's preferred furniture style feature vector. The clustering process is to group user groups with similar browsing behaviors and preferences together, and by means of comparison analysis, it can be identified which style of furniture the target user is more prone to, such as northern Europe wind, industrial wind or classical wind. In this process, the system may find that the target user browses the modern conciseness style furniture longer and clicks higher, thereby determining that their preferred furniture style feature vector favors the modern conciseness style. Meanwhile, the system can further conduct deep analysis on the furniture commodity co-occurrence relationship in the user-commodity interaction information so as to obtain a furniture collocation mode vector. This analysis is mainly to know which furniture has a high co-occurrence probability, i.e. when a user browses or purchases a certain commodity, the user will often pay attention to or purchase which related furniture. For example, the system may find that the user is browsing the sofa while also often looking at a matching coffee table, carpet, etc., suggesting a certain tendency for the user to coordinate when purchasing furniture. Through analysis of the co-occurrence relationship, the system can better understand the collocation preference of the user, and further recommend more coordinated furniture combinations. In addition, the system further analyzes the furniture commodity description text in the user-commodity interaction information, extracts the space function keywords from the furniture commodity description text, and constructs space function keyword vectors. This step is to capture points of interest of the user for a particular spatial function, such as an office area, a leisure area, or a child play area. For example, if a user frequently searches for merchandise containing keywords such as "bookshelf", "work table", etc., this may mean that the user is looking for furniture suitable for an office area provided in a home. Through such analysis, the system can more accurately understand the space requirement of the user and provide more targeted suggestions for the user. Based on the obtained preferred furniture style feature vector, furniture collocation mode vector and space function keyword vector, the system constructs a comprehensive target user preference matrix. The matrix reflects the preference of the user for furniture style and collocation mode, also contains the requirement of the user for specific space functions, and is a multi-dimensional data set for comprehensively showing the furniture selection preference of the user. And then, the system inputs the preference matrix into a preset Bayesian inference algorithm, and the preference probability distribution of the target user is obtained through calculation. The bayesian inference algorithm is used here to model probability of various preference parameters of the user, and predict which style, collocation or spatial layout the user prefers in future furniture selection behavior. Finally, the system predicts furniture selection behavior of the target user based on the preference probability distribution, thereby obtaining final target user preference parameters including but not limited to spatial function arrangement parameters and collocation parameters. These parameters will direct subsequent furniture recommendation and service optimization, ensuring that the provided solution can maximally fit the personal preferences and actual needs of the user. For example, if the system predicts that a user has a strong preference for the furniture collocation of the modern conciseness style and the functional layout of the home office space, then the modern conciseness style furniture will be prioritized when recommending furniture solutions to the user, and the design of the office area will be emphasized in particular, thereby improving the user's satisfaction and use experience. Through the systematic and personalized analysis flow, not only can the accuracy of furniture recommendation be effectively improved, but also the participation degree and satisfaction degree of users can be obviously enhanced, and more careful and efficient home design service experience is brought to the users.

In a specific embodiment, the performing vector transformation on the house plan by using a plan image vectorization technology to obtain vector space relationship feature data includes:

Specifically, in the personalized indoor design flow, the planar image vectorization technology is utilized to carry out vector conversion on the planar image of the house, which is one of key steps for realizing efficient and accurate design. The process not only can convert the plan uploaded by the user into the vector data which can be processed by the computer, but also can extract the detailed vector space relation characteristic data from the vector space relation characteristic data, thereby providing a solid foundation for the subsequent design optimization. Specifically, the step includes several closely connected operations, firstly, identifying and marking each functional area in the manually or automatically uploaded house plan to obtain functional area marking data. The importance of this step is that it can help the system understand the use of different areas in the plan view, such as living room, bedroom, kitchen, etc., providing basis for the subsequent space layout design. For example, after a user uploads a plan view containing a plurality of rooms, the system automatically or manually inputs the names and functions of the rooms to ensure that each area can be accurately identified. Next, the system will preprocess the house plan using a plan image vectorization technique to obtain a preprocessed image. The main purpose of preprocessing is to remove noise, blurring and other interference factors in the image, so that the image is clearer and is easy to process. This stage may involve various technical means such as image denoising, contrast adjustment, edge enhancement, etc., to ensure that the subsequent contour line extraction can be more accurate. Taking living room design as an example, the pretreated plan view shows cleaner and clearer effects, and lays a good foundation for the next step. After the preprocessing is completed, the system enters the next important stage, namely, extracting the contour lines in the preprocessed image to generate a contour line image. The process relates to the application of an edge detection algorithm, and by detecting the region with obvious pixel value change in the image, the system can accurately outline the outline lines of key elements such as the boundary of a room, the positions of doors and windows and the like. Based on the method, the system can classify and mark the contour lines in the contour line image based on the previously acquired functional area marking data, so that the contour line image with the functional area information is obtained. for example, the system marks which lines belong to the boundary of the living room in the outline line image, which lines represent doors and windows of the bedroom, and the like, and the step is important for subsequent spatial relationship analysis. Next, the system converts the contour line image with the functional area information into a vector graphic to generate vector graphic data. The vectorization process is to convert the elements such as lines, shapes and the like in the image into geometric objects such as mathematical points, lines, planes and the like, and the objects not only have accurate coordinate information, but also can be infinitely scaled without distortion. Through the conversion, the system can more flexibly adjust and optimize the space layout, and meanwhile, the subsequent data processing and storage are also convenient. For example, the living room boundary in the vector graphics will no longer be a string of pixels, but a line consisting of a series of coordinate points, which can be easily edited and modified. Finally, the system analyzes the spatial relationship of the generated vector graphic data to extract the characteristic data of the vector spatial relationship. The analysis process involves analysis of multiple aspects such as space topological relation, geometric relation and the like, and aims to comprehensively understand information such as relative positions, connection modes and the like of all areas in a house. For example, the system can identify whether a gateway is directly communicated between a living room and a restaurant, and what is the distance between a bedroom and a bathroom, and the information has important significance for reasonably designed furniture layout and streamline planning. Through the space relation analysis, the system can provide more scientific and practical design suggestions for users, and ensures that the design scheme is attractive and meets the actual use requirements. In summary, the planar image vectorization technology is utilized to perform vector conversion on the house planar image, and the vector space relation characteristic data is extracted, so that the whole design flow can not only greatly improve the design efficiency and precision, but also better meet the personalized requirements of users. For example, in the foregoing living room design case, the system can accurately identify the specific position and shape of the living room through the series of technical means, and can also know the requirements of the user on the living room function in detail, such as needing enough leisure areas, television watching areas and the like, so as to provide a design scheme which is not only in line with personal preference, but also has practicability for the user. the process fully embodies the advancement and practicability of the personalized indoor design method.

In a specific embodiment, the inputting the vector spatial relationship feature data and the spatial function configuration parameter into a preset graphic neural network to perform spatial layout optimization, and generating an initial furniture layout scheme includes:

Specifically, in the personalized indoor design method, vector space relation characteristic data and space function configuration parameters are input into a preset graphic neural network to perform space layout optimization, which is one of the core steps of generating an initial furniture layout scheme. The process not only depends on advanced graphic neural network technology, but also needs to carry out fine processing on input data so as to ensure that the finally generated layout scheme not only meets the functional requirements of users, but also has good space utilization efficiency and attractive appearance. Firstly, the system performs spatial feature extraction on vector spatial relationship feature data to obtain extracted spatial features. The goal of this stage is to extract information from the vector graphics data that is useful for optimization of the spatial layout, including but not limited to the area, shape, window position, and door opening direction of the house plan. for example, in processing a user-uploaded living room plan, the system can accurately measure the total area of the living room, identify the specific location and number of windows, and the door opening direction, which is critical to subsequent furniture layout designs. Through these extraction space characteristics, the system can better understand the basic structure and characteristics of space, lay a foundation for reasonable placement of furniture. Then, the system classifies the space function arrangement parameters to obtain the function division information. The spatial function arrangement parameters reflect specific requirements of the user on different functional areas, such as the area requirement of each room, the relative position requirement and the like. For example, a user may wish that the living room not only be sufficiently spacious to accommodate a multi-person gathering, but also have a reading corner near a window. The system divides the living room into different functional areas such as an entertainment area, a rest area and a reading area according to the requirements of users, and defines the approximate area and ideal position of each area. The sorting process ensures that the function requirements of users can be fully considered in the subsequent layout optimization, and the inconvenience in use caused by unreasonable space division is avoided. Based on the extracted spatial features and the functional partition information, the system constructs a spatial layout relationship diagram. The spatial layout relation diagram is diagram structure data, wherein each node represents a functional area, and the edges represent the connection relation and the relative positions of different functional areas. For example, in the living room design, the system creates a plurality of nodes in the graph, corresponding to the entertainment area, the rest area and the reading area, respectively, and then determines the connection mode and the distance between the nodes according to the requirements of the user and the actual conditions of the space. By constructing the spatial layout relation diagram, the system can more intuitively show the logic relation among all the functional areas, and provides a clear framework for the subsequent spatial layout optimization. And then, the system performs feature propagation and fusion on the spatial layout relation graph based on the multi-scale graph neural network to obtain a fused feature graph. The multi-scale graph neural network is a powerful tool capable of processing graph structure data, and can capture local and global relations between nodes on different scales, so that richer and accurate characteristic representations are generated. In the example of living room design, the system would utilize a multi-scale map neural network to capture specific features of each functional area, such as the size and shape of furniture, at the microscopic level while understanding interactions between different areas, such as the transition space between the entertainment and rest areas, at the macroscopic level. Through feature propagation and fusion, the system can generate a fused feature map which not only contains basic information of each functional area, but also reflects complex relations among the functional areas. Then, the system inputs the fusion feature map into a preset map neural network to perform furniture layout exploration and space layout optimization so as to generate a candidate furniture layout scheme. The task at this stage is to explore a variety of possible furniture layout schemes through simulation and calculation based on the fused feature maps. The graphic neural network intelligently selects proper furniture according to the characteristics of each functional area and the requirements of users, and determines the optimal placement position of the furniture in the space. For example, in a living room design, the system may attempt to dispense sand near the window to take full advantage of natural light while placing the cabinet opposite the sofa to create an ideal viewing area. Through continuous iteration and optimization, the system is able to generate multiple candidate furniture layout schemes for subsequent evaluation and selection. Finally, the system performs rationality assessment and screening of the candidate furniture layout scenarios to determine the initial furniture layout scenario. The rationality assessment is based primarily on both design hard rules and user experience. The design hard rules comprise minimum spacing between furniture, accessible passing areas in front of doors and windows and the like, feasibility of the design scheme is guaranteed, user experience focuses on attractiveness, comfort and practicability of the scheme, and the design scheme can meet actual requirements of users. For example, in evaluating candidate solutions for living room design, the system will check if each solution meets basic design specifications, such as whether the distance between the sofa and the television is appropriate, and will also consider the user's personalized needs, such as whether the reading corner is quiet and comfortable. Through comprehensive evaluation, the system eventually selects one or more optimal solutions as the initial furniture layout solution for further viewing and adjustment by the user. In summary, the vector spatial relationship feature data and the spatial function configuration parameters are input into the preset graphic neural network to perform spatial layout optimization, so that the whole design flow can not only efficiently generate a furniture layout scheme meeting the user requirements, but also ensure the rationality and the attractiveness of the scheme. The process fully shows the intelligentization and technical advantages of the personalized indoor design method, and brings more convenient and high-quality design experience for users.

In a specific embodiment, the step of performing scheme screening on the initial furniture layout scheme through a preset design hard rule to obtain a screened furniture layout scheme includes:

Specifically, in the personalized indoor design flow, scheme screening is performed on the initial furniture layout scheme through a preset design hard rule, so that the design scheme is an important link which meets the human engineering principle and the actual use requirement. This process involves multiple steps, from analysis of spatial topological relationships to comprehensive evaluation and screening of the final solution, each of which aims to improve design solution rationality and user satisfaction. Firstly, the system analyzes the spatial relationship of the initial furniture layout scheme by using a spatial topology analysis algorithm, and generates a spatial topology relationship diagram among furniture. The space topological relation diagram records information such as relative positions, distances, connectivity and the like among furniture in detail, and provides basic data for subsequent evaluation and optimization. For example, in a living room design, the system would analyze the distance between the sofa and the television, the relative position of the tea table and the sofa, the path of passage from the doorway to the various furniture, and so forth. Through the analysis, the system can comprehensively understand the spatial relationship of furniture layout, and provides accurate data support for subsequent evaluation. Next, the system will perform an ergonomic evaluation of the initial furniture layout plan based on ergonomic principles using the generated spatial topological graph, resulting in an ergonomic scoring matrix. The ergonomic scoring matrix reflects the scoring of each furniture layout plan in terms of human comfort, accessibility, safety, and the like. For example, the system may evaluate whether the line of sight between the sofa and the television is appropriate, whether the height of the tea table is convenient to use, whether the doorway is clear of the path of passage to the respective furniture, etc. Through these evaluations, the system is able to quantify the ergonomic performance of each regimen, providing basis for subsequent optimization. Based on the generated ergonomic scoring matrix, the system performs optimization calculation on the initial furniture layout scheme through a multi-objective optimization algorithm to generate an ergonomic layout scheme set. The multi-objective optimization algorithm can find the optimal balance among a plurality of optimization objectives, so that the generated layout scheme is ensured to meet the requirements of human engineering, and attractive appearance and practicability can be achieved. For example, the system may generate a plurality of layout schemes, each having a different performance in view distance, path of traffic, furniture spacing, etc., but all meeting basic ergonomic requirements. These schemes constitute an ergonomic layout set of schemes that provide a rich choice for subsequent screening. The system then performs a functional region division on the ergonomic layout solution set to generate a functional region semantic graph. The functional area semantic graph not only marks the specific position of each functional area, but also clarifies the functions and purposes of each area. For example, in a living room design, the system would divide the living room into an entertainment area, a rest area, and a reading area, and label the main furniture and functions of each area in a functional area semantic map. Through the function area division, the system can ensure that each layout scheme meets the requirements of human engineering and simultaneously meets the function requirements of users. Then, the system performs rule constraint checking on the functional area semantic graph through a preset design hard rule to generate an ergonomic layout scheme set after constraint checking. Design rules include, but are not limited to, minimum spacing between furniture, unobstructed areas of passage in front of doors and windows, safe distances of electrical outlets and switches, and the like. These rules are intended to ensure feasibility and safety of the design. For example, the system would check if the distance between the sofa and the tea table in each layout scenario is greater than 60 cm, if the doorway to each piece of furniture is wider than 90 cm, etc. Only schemes that pass these rule constraint checks can go to the next step of evaluation and screening. Finally, the system comprehensively evaluates and screens the ergonomic layout scheme set after constraint inspection through a multi-criterion decision analysis method, and finally obtains the screened furniture layout scheme. The multi-criterion decision analysis method can comprehensively consider a plurality of evaluation indexes such as human engineering scores, space utilization rate, attractiveness and the like, and score each scheme. For example, the system may score each solution comprehensively according to the needs and preferences of the user, and finally select several solutions with the highest scores as the filtered furniture layout solutions. These solutions not only meet ergonomic requirements, but also maximize the functional needs and aesthetic preferences of the user. In summary, the scheme screening is performed on the initial furniture layout scheme through the preset design hard rule, so that the rationality and safety of the design scheme can be ensured in the whole process, and the satisfaction degree and the use experience of a user can be obviously improved. For example, in the living room design case described above, the system through this series of steps not only creates a plurality of ergonomically desirable layout schemes, but also provides the user with an optimized design choice through comprehensive evaluation and screening. The process fully shows the scientificity and the intellectualization of the personalized indoor design method, and brings more careful and efficient design service for users.

In a specific embodiment, the matching parameters and the filtered furniture layout scheme to obtain a matching design scheme includes:

Specifically, in the personalized indoor design flow, matching design is performed on the matching parameters and the screened furniture layout scheme, which is one of key steps for generating a final matching design scheme. The process not only needs to deeply analyze the user preference and the existing layout scheme, but also ensures that the final design scheme meets the personalized requirements of the user through an advanced calculation method, and has high style consistency and practicability. Firstly, the system respectively carries out characteristic deconstructing on the collocation parameters and the screened furniture layout scheme, and correspondingly obtains a deconstructed parameter set and a layout element set. The collocation parameters comprise the preferences of users in terms of colors, materials, decoration styles and the like, and the screened furniture layout scheme comprises optimized space layout information. For example, in a living room design, the collocation parameters of the user may include preference for modern conciseness style, preference for white and gray as dominant hues, tendency to use wooden furniture, and so forth. The system will deconstruct these parameters into specific color codes, material categories, etc. information to form deconstructed parameter sets. Meanwhile, the system can deconstruct each piece of furniture and the position information thereof in the screened furniture layout scheme into a layout element set, such as the position of a sofa, the size of a tea table and the like. Next, the system performs semantic coding on the deconstructed parameter set to obtain a coded semantic vector. The purpose of semantic coding is to translate the user's preference parameters into a form that can be processed by a computer for subsequent computation and matching. For example, the system may encode a "modern conclusive style" as a particular vector, "white" and "gray" as color vectors, and "wooden furniture" as texture vectors. Through these encodings, the system can translate the user's abstract preferences into a concrete numerical representation, providing the basis for subsequent matching calculations. Meanwhile, the system can perform spatial relation coding on the layout element set to obtain a spatial relation vector. The purpose of spatial relationship coding is to capture spatial structure information in furniture layout schemes, such as relative position, distance, connectivity, etc. between furniture. For example, the system encodes the distance between the sofa and the television as a number and the relative position of the tea table and the sofa as a vector. Through the codes, the system can convert the spatial characteristics of the layout scheme into a vector form, and data support is provided for subsequent correlation calculation. Based on the attention mechanism network and the matching algorithm, the system can perform correlation calculation on the encoded semantic vector and the spatial relationship vector to obtain a matching weight matrix. The attention mechanism network can dynamically focus on the user preferences and key features in the layout scheme, thereby improving the accuracy and rationality of the matching. For example, the system may calculate the similarity between the semantic vector of the modern conciseness style preferred by the user and the spatial relationship vector of furniture such as sofas, tea tables and the like in living rooms, and generate a matching weight matrix. Each element in this matrix represents the degree of matching of the user's preference to a certain piece of furniture or area in the layout scheme, with higher values representing better matching. Based on the generated matching weight matrix, the system performs layout reorganization on the screened furniture layout scheme to obtain a layout reorganization scheme. The purpose of layout reorganization is to adjust the position and collocation of furniture according to the preference of the user so as to generate a design scheme which meets the requirements of the user. For example, if the matching weight matrix shows that the user prefers the matching of a white sofa with a gray carpet, the system will adjust the sofa color in the living room to white and the carpet color to gray. By such reorganization, the system is able to generate a layout scheme that is both user-preferred and highly consistent. Finally, the system performs style consistency check and adjustment on the layout reorganization scheme to ensure that the final design scheme is kept highly consistent in terms of color, material, decoration style and the like. The purpose of the style consistency check is to avoid the condition of style mixing and overlapping in the design scheme and ensure the consistency and the aesthetic degree of the whole design. For example, the system may check whether the color, material and style of the furniture are uniform in the adjusted layout scheme, and if not, the system may further adjust until the best effect is achieved. After the style consistency check is completed, the system can initially visually display the final matched design scheme on a preset interactive interface, so that a user can intuitively see the design effect. if the user has any opinion or suggestion on the preliminary design scheme, the user can also adjust the preliminary design scheme through the interactive interface in real time, and the system can update the design scheme in real time according to the feedback of the user until the user is satisfied. In summary, through carrying out the matching design with collocation parameter and the furniture layout scheme after the screening, the whole process not only can reflect user's individualized demand accurately, can also ensure design scheme's high uniformity and practicality in style and function. For example, in the living room design case, through the series of steps, the system not only generates the design scheme which accords with the modern conciseness style preference of the user, but also ensures the overall harmony and the attractiveness of the design scheme through style consistency check and adjustment. the process fully shows the intelligentization and technical advantages of the personalized indoor design method, and brings more efficient and satisfactory home design experience for users.

In a specific embodiment, through a preset AI editing system, performing scheme editing and scheme rendering on the target scheme according to the interface interaction operation to obtain a three-dimensional visual effect diagram corresponding to the house plan, where the method includes:

Specifically, in the personalized indoor design flow, the scheme editing and scheme rendering are performed on the target scheme according to the interface interaction operation of the target user on the interaction interface through the preset AI editing system, so that the method is an important step for realizing real-time participation of the user in design and real-time viewing of the design effect. The process not only needs to monitor the operation of a user in real time, but also generates a three-dimensional visual effect diagram with material textures and illumination effects through a multi-target optimization algorithm and a space mapping algorithm, thereby ensuring the accuracy and the attractiveness of a design scheme. Firstly, the system monitors interface interaction operation of a target user on an interaction interface in real time, and obtains an operation instruction sequence of the target user on a matching design scheme. These sequences of operational instructions include user clicking, dragging, zooming, etc. actions on the interactive interface. For example, when a user clicks on a furniture icon and drags it to a new location on the interactive interface, or resizes the furniture by a zoom gesture, the system will record these operations in real-time. The operation instruction sequences not only reflect the instant demands of users, but also provide basis for subsequent design adjustment. And then, the system utilizes a multi-objective optimization algorithm to adjust parameters in the objective scheme based on the operation instruction sequence, so as to obtain an adjustment design parameter and an adjustment design scheme corresponding to the adjustment design parameter. Parameters in the target scheme include furniture layout parameters, color scheme parameters, and material parameters. For example, if a user drags a sofa from one corner of the living room to another location, the system will adjust the layout parameters of the sofa according to the user's operation instructions, ensuring that the new location meets both the user's intent and the rationality of the spatial layout. Meanwhile, if the user changes the color of the wall surface or selects different floor materials, the system can correspondingly adjust the parameters of the color matching scheme and the parameters of the materials, so that the overall harmony of the design scheme is ensured. Through a preset space mapping algorithm, the system performs space mapping on the adjustment design scheme to obtain a three-dimensional space layout model. The function of the space mapping algorithm is to convert the two-dimensional plane layout diagram into a three-dimensional space model, so that the position, the size and the shape of each piece of furniture in the three-dimensional space are accurate. for example, in living room design, the system maps the information of the adjusted sofa position, the tea table size and the like into a three-dimensional space to generate a complete three-dimensional space layout model. The model not only comprises the specific position of furniture, but also comprises structural information such as walls, doors and windows of a room, and the like, thereby providing a foundation for subsequent rendering. Then, the system performs material and illumination rendering on the three-dimensional space layout model to obtain the three-dimensional space layout model with material textures and illumination effects. The aim of material rendering is to add real material textures for elements such as furniture, walls and the like, such as wood grains of wooden furniture, fabric textures of cloth sofas and the like. The illumination rendering simulates the illumination effect of different light sources in a room, such as natural light entering from a window, light emitted from a ceiling lamp or a wall lamp, and the like. Through the rendering, the system can generate a highly realistic three-dimensional space layout model, so that a user can intuitively feel the actual effect of the design scheme. Finally, the system generates a three-dimensional visual effect diagram based on a three-dimensional space layout model with material textures and illumination effects through a virtual reality technology. Virtual reality technology can provide an immersive experience for users who can "walk" and "observe" through VR devices in a virtual environment, looking at every detail of a design solution all around. For example, the user can walk in the virtual living room, closely observe the material and the color of sofa, feel the softness of light, can simulate the natural illumination effect of different time periods even, ensure that design scheme's performance accords with the expectations under various environment. In summary, through the preset AI editing system, the scheme editing and scheme rendering are performed on the target scheme according to the interface interaction operation of the target user on the interaction interface, so that the whole process can not only respond to the operation of the user in real time, but also generate a highly realistic three-dimensional visual effect diagram, and design participation and satisfaction of the user are remarkably improved. For example, in the living room design case, the user can adjust the furniture layout and the color scheme in real time through simple clicking and dragging operations, and preview the final effect in the three-dimensional environment through the virtual reality technology. The process not only simplifies the design flow, but also provides more visual and flexible design experience for the user, and ensures that the final design scheme can completely meet the personalized requirements and aesthetic preferences of the user.

The personalized indoor design method based on the user pattern in the embodiment of the present invention is described above, and the personalized indoor design system based on the user pattern in the embodiment of the present invention is described below, referring to fig. 2, and one embodiment of the personalized indoor design system based on the user pattern in the embodiment of the present invention includes:

the recommendation module 21 is used for analyzing behavior data of the target user through a preset recommendation algorithm to obtain preference parameters of the target user, wherein the preference parameters comprise space function arrangement parameters and collocation parameters;

The obtaining module 22 is configured to obtain a house plan uploaded by a target user, and perform vector conversion on the house plan by using a plan image vectorization technology, so as to obtain vector space relationship feature data;

The generating module 23 is configured to input the vector spatial relationship feature data and the spatial function configuration parameter into a preset neural network for spatial layout, and generate an initial furniture layout scheme;

The screening module 24 is configured to perform scheme screening on the initial furniture layout scheme according to a preset design hard rule, so as to obtain a screened furniture layout scheme;

The matching module 25 is configured to match the matching parameters with the screened furniture layout scheme to obtain a matching design scheme, and perform initial visualization on the matching design scheme at a preset interactive interface;

And the editing module 26 is configured to detect in real time whether the target user performs interface interaction operation on the interaction interface, if yes, take the matching design scheme for the interface interaction operation as a target scheme, and perform scheme editing and scheme rendering on the target scheme according to the interface interaction operation through a preset AI editing system, so as to obtain a three-dimensional visual effect diagram corresponding to the house plan.

In this embodiment, for specific implementation of each unit in the above system embodiment, please refer to the description in the above method embodiment, and no further description is given here.

Referring to fig. 3, a computer device is further provided in an embodiment of the present invention, and the internal structure of the computer device may be as shown in fig. 3. The computer device includes a processor, a memory, a display screen, an input device, a network interface, and a database connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used for communicating with an external terminal through a network connection. Which computer program, when being executed by a processor, carries out the above-mentioned method.

It will be appreciated by those skilled in the art that the architecture shown in fig. 3 is merely a block diagram of a portion of the architecture in connection with the present inventive arrangements and is not intended to limit the computer devices to which the present inventive arrangements are applicable.

An embodiment of the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above method. It is understood that the computer readable storage medium in this embodiment may be a volatile readable storage medium or a nonvolatile readable storage medium.

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present invention and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, apparatus, article, or method that comprises the element.

The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention or direct or indirect application in other related technical fields are included in the scope of the present invention.

Claims

1. The personalized indoor design method based on the user house type graph is characterized by comprising the following steps of:

Detecting whether the target user performs interface interaction operation on the interaction interface in real time, if so, taking a matching design scheme aimed by the interface interaction operation as a target scheme, and performing scheme editing and scheme rendering on the target scheme according to the interface interaction operation through a preset AI editing system to obtain a three-dimensional visual effect diagram corresponding to the house plan;

the behavior data comprises furniture browsing records and input text data, and the behavior data of the target user is analyzed through a preset recommendation algorithm to obtain preference parameters of the target user, wherein the method comprises the following steps:

2. The personalized indoor design method based on user pattern drawing according to claim 1, wherein the performing vector transformation on the house pattern by using pattern image vectorization technology to obtain vector space relation characteristic data comprises:

3. The personalized indoor design method based on user pattern diagram according to claim 1, wherein the inputting the vector spatial relationship characteristic data and the spatial function configuration parameter into a preset pattern neural network to perform spatial layout optimization, and generating an initial furniture layout scheme comprises:

constructing a spatial layout relation diagram based on the extracted spatial features and the functional division information;

4. The personalized indoor design method based on user pattern drawing according to claim 1, wherein the scheme screening of the initial furniture layout scheme by the preset design hard rule to obtain a screened furniture layout scheme comprises the following steps:

5. The personalized indoor design method based on user profile according to claim 1, wherein the matching design is performed on the collocation parameters and the screened furniture layout scheme to obtain a matching design scheme, comprising:

6. The personalized indoor design method based on the user profile according to claim 1, wherein the method for performing scheme editing and scheme rendering on the target scheme according to the interface interaction operation through a preset AI editing system to obtain a three-dimensional visual effect diagram corresponding to the house plan comprises the following steps:

7. A personalized indoor design system based on a user profile, comprising:

The editing module is used for detecting whether the target user performs interface interaction operation on the interaction interface in real time, if so, taking a matching design scheme aimed at by the interface interaction operation as a target scheme, and performing scheme editing and scheme rendering on the target scheme according to the interface interaction operation through a preset AI editing system to obtain a three-dimensional visual effect diagram corresponding to the house plan;

8. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, carries out the steps of the method according to any one of claims 1 to 6.

9. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method of any of claims 1 to 6.