A constrained modulation-based indoor layout generation method and system driven by user feature parameters

Abstract

This invention relates to the field of automated spatial layout generation technology, and discloses a constraint-modulated indoor layout generation method and system based on user feature parameters. The method includes: constructing a spatial topology model; generating a set of candidate furniture objects; constructing a user feature parameter vector representing user space usage preferences; modulating parameters of residential layout rules; and constraining and guiding candidate layout actions based on the rule modulation results during layout generation, gradually generating an indoor layout scheme that conforms to the spatial structure and user feature parameters. Compared with existing technologies, this invention introduces user feature parameters into the indoor layout generation process in a structured manner, allowing user preferences to participate in decision-making in a controllable way during layout generation. While ensuring spatial rationality and safety, it achieves personalized expression of the indoor layout results, improving the stability and consistency of the layout generation process.

Description

Technical Field

[0001] This invention relates to the field of spatial automated layout generation technology, and in particular to a constraint-modulated indoor layout generation method and system driven by user feature parameters. Background Technology

[0002] Currently, with the continuous development of artificial intelligence technology and spatial design software, the automated generation of interior layouts has gradually become an important research direction in the fields of residential design and smart homes. However, existing interior layout generation technologies still have significant shortcomings. For example, layout generation methods based on end-to-end deep learning models typically map apartment information directly to furniture layout results. Although the generation efficiency is high, in residential scenarios, problems such as furniture obstructing doors and windows, discontinuous traffic flow, and inconsistent layout styles in different rooms can easily occur. Moreover, the generated results are quite sensitive to model randomness and lack stability. On the other hand, methods based on explicit rules or heuristic search can ensure the satisfaction of basic spatial constraints, but since the rule weights and triggering conditions are usually fixed, it is difficult to reflect users' long-term stable living behavior and space usage preferences, resulting in limited personalization.

[0003] Furthermore, some existing technologies post-process or filter the generated results by collecting explicit user preferences or historical behaviors. However, these methods fail to effectively incorporate user preferences into the layout generation process itself, resulting in personalized information not participating in spatial structure decisions. This makes it difficult to achieve in-depth personalized layout needs while ensuring spatial rationality. Existing technologies cannot fully meet the interior layout generation needs in residential application scenarios with complex apartment structures, significant differences in user preferences, and the need to simultaneously consider spatial safety, accessibility, and stylistic consistency.

[0004] Therefore, there is an urgent need for a constraint-modulated indoor layout generation method driven by user feature parameters, which can effectively integrate user feature parameters into the entire layout generation process without disrupting the existing spatial constraint rule system, so as to improve the rationality and personalized consistency of the indoor layout generation results. Summary of the Invention

[0005] To address the aforementioned technical shortcomings, the present invention aims to propose a constraint-modulated indoor layout generation method driven by user feature parameters. This method aims to solve the technical problem that existing indoor layout generation methods based on fixed rules are difficult to achieve personalized expression while ensuring layout rationality, especially under the condition that user preferences vary significantly and spatial rationality must be met simultaneously.

[0006] To solve the above technical problems, the present invention adopts the following technical solution: The present invention provides a constraint modulation indoor layout generation method based on user feature parameters.

[0007] The user-feature parameter-driven constrained modulation indoor layout generation method includes: Step S10: Obtain the spatial structure data of the apartment type to be laid out, and construct a spatial topology model based on the spatial topology data of the apartment type to be laid out using a spatial topology construction method that combines reachability constraint propagation and regional connectivity decomposition. Step S20: Based on the spatial topology model, a candidate object generation mechanism based on functional consistency joint screening is used to perform the parameterized modeling task of candidate furniture objects, and output the candidate furniture object set F; Step S30: Obtain user preference feature parameters. Based on the user's long-term behavior stability constraints and space usage preference feature processing method, construct features for user space usage preferences to form a user preference feature vector U that represents the user's space usage tendency. Step S40: Introduce the lightweight mapping layer model CPML-Lite. Based on the user preference feature vector U and the lightweight mapping layer model CPML-Lite, perform the personalized rule weight and personalized rule threshold generation tasks using a modulation mechanism based on explicit modulation of rule parameters and lightweight neural inference, and output a personalized rule set. Step S50: Based on the personalized rule set, a phased constraint mechanism is used to execute the step-by-step layout generation task and output the final interior layout scheme.

[0008] Preferably, in step S10, the spatial structure data of the apartment layout to be arranged includes the boundary outlines, polygonal geometry, spatial dimensions, door and window positions, fixed and immovable obstacle positions, and available activity area range of each room; spatial topology model. Includes the set of placeable area constraints Room boundary constraint set Set of non-placeable regions The set of adjacency relationships between rooms .

[0009] Preferably, in step S20, based on the spatial topology model... The steps for performing parametric modeling of candidate furniture objects using a candidate object generation mechanism based on functional consistency joint screening, and outputting a set of candidate furniture objects F, specifically include: Step S201: Based on the set of placeable region constraints in the spatial topology model S Room boundary constraint set Set of non-placeable regions The set of adjacency relationships between rooms Perform spatial topology feasible region pruning processing and output a set of candidate placement sub-regions in each room space that meet the above constraints; Step S202: Obtain the spatial function attribute identifiers within each room. Furniture object functional property parameters Based on spatial functional attribute identification Furniture object functional property parameters Perform consistency matching judgment to generate a set of intermediate candidate furniture objects that meet the functional consistency constraints; Step S203: Based on the intermediate candidate furniture object set and the candidate placement sub-region set, form a candidate furniture object set F. The candidate furniture object set F includes furniture category identifier, furniture size parameters, furniture orientation parameters, and furniture object functional attribute parameters. .

[0010] Preferably, step S30, which involves obtaining user preference feature parameters and constructing user space usage preferences based on long-term user behavior stability constraints and space usage preference feature processing methods, to form a user preference feature vector U representing user space usage tendencies, specifically includes: Step S301: Obtain user preference feature parameters, which are used to characterize users' long-term stable residential behavior and space usage preferences; Step S302: Based on user preference feature parameters, a pre-trained Long Short-Term Memory (LSTM) network model and a Multilayer Perceptron (MLP) network model are used to sequentially perform long-term behavioral feature extraction and spatial usage preference decoupling mapping, outputting an intermediate feature representation of user preferences; Step S303: First, semantic grouping is performed on the intermediate feature representation of user preferences using a semantic analysis method based on feature similarity clustering, outputting spatial morphology-related preference feature representation, traffic behavior-related preference feature representation, visual-related preference feature representation, and safety-related feature representation; then, the intermediate feature representation of user preferences is normalized and vectorized according to the output order of semantic grouping to construct the user preference feature vector U.

[0011] Preferably, in step S40, a lightweight mapping layer model CPML-Lite is introduced. Based on the user preference feature vector U and the lightweight mapping layer model CPML-Lite, a modulation mechanism based on explicit modulation of rule parameters and lightweight neural inference is used to perform the task of generating personalized rule weights and personalized rule thresholds, and outputs a set of personalized rules. The steps specifically include: Step S401: First, load the preset residential layout rule library. , ;in, Residential Layout Rule Library The i-th rule, Residential Layout Rule Library Total number of rules; rules Includes rule type identifier Basic weights Basic trigger threshold Correlation vectors with regular features ; Step S402: Introduce the lightweight mapping layer model CPML-Lite to associate the regular features with vectors. The user preference feature vector U is input into the pre-trained lightweight mapping layer model CPML-Lite for lightweight neural inference. The lightweight mapping layer model CPML-Lite outputs the rule matching strength. Among them, rule matching strength Used to characterize the degree of fit between user preferences and the i-th rule; Step S403: Based on rule matching strength For basic weights and basic trigger threshold Perform explicit modulation to generate weighted personalized rule modulation parameters. And threshold personalized rule modulation parameters ; ; ;in, These are the weight modulation coefficients, used to control the modulation amplitude of the rule weights as the rule matching strength changes; This is the threshold modulation coefficient, used to control the modulation amplitude of the rule triggering threshold as the rule matching strength changes; Step S404: Merge rule matching strength Weighted personalized rule modulation parameters And threshold personalized rule modulation parameters Generate and output a personalized set of rules .

[0012] Preferably, in step S40, the lightweight mapping layer model CPML-Lite is a lightweight network model built on the CPML model and the multilayer perceptron (MLP), used to calculate the matching strength between user preference features and rule features without changing the residential layout rule structure. The lightweight mapping layer model CPML-Lite includes an input layer that receives regular feature association vectors. The input is a concatenation of the user preference feature vector U; The feature mapping layer is used to perform low-dimensional embedding mapping and nonlinear combination on the concatenated input using a multilayer perceptron structure to generate a joint representation of rule preferences. The stability constraint layer is used to constrain the joint representation of rule preferences using a layer normalization structure, and outputs the stabilized joint features. The matching strength regression layer is used to map the stabilized joint features into a scalar representation of the rule matching strength using a single-layer fully connected structure. The output layer is used to output the rule matching strength as a scalar representation based on the rule matching strength.

[0013] Preferably, in step S50, based on the personalized rule set The process of generating a layout using a phased, step-by-step constraint mechanism to output the final interior layout scheme includes: dividing the interior layout generation process into three stages: hard constraint feasibility determination, soft rule modulation determination, and user preference modulation determination; in the hard constraint feasibility determination stage, based on a personalized rule set... The system determines whether the layout generation action meets the preset spatial constraints in the residential space and outputs the corresponding hard constraint feasibility judgment result; in the soft rule modulation judgment stage, it is based on the personalized rule set. Determine whether the layout generation action meets the preset flow continuity constraint and output the corresponding soft rule modulation result; in the user preference modulation determination stage, based on the personalized rule set... Determine whether the layout generation action meets the preset user preference constraints and output the corresponding user preference modulation result; output the final indoor layout scheme by combining the hard constraint feasibility judgment result, soft rule modulation result and user preference modulation result.

[0014] The present invention also provides a constraint modulation indoor layout generation system driven by user feature parameters, comprising: The spatial topology construction module is used to acquire the spatial structure data of the apartment layout to be laid out. Based on the spatial structure data of the apartment layout to be laid out, a spatial topology model is constructed using a spatial topology construction method that combines reachability constraint propagation and regional connectivity decomposition. ; The candidate furniture object generation module is used for generating furniture based on spatial topology models. A candidate furniture object parameterization modeling task is performed using a candidate object generation mechanism based on functional consistency joint screening, and a candidate furniture object set F is output. The user preference feature construction module is used to obtain user preference feature parameters. Based on the user's long-term behavior stability constraints and the space usage preference feature processing method, it constructs features of user space usage preferences to form a user preference feature vector U that represents the user's space usage tendency. The personalized rule modulation module introduces the lightweight mapping layer model CPML-Lite. Based on the user preference feature vector U and the lightweight mapping layer model CPML-Lite, it employs a modulation mechanism that combines explicit modulation of rule parameters with lightweight neural inference to perform personalized rule weight and personalized rule threshold generation tasks, and outputs a personalized rule set. ; A progressively deployed generation module is used to generate data based on a set of personalized rules. A phased, step-by-step constraint mechanism is used to execute the step-by-step layout generation task and output the final interior layout scheme.

[0015] The present invention also provides a constraint modulation indoor layout generation device driven by user feature parameters, comprising: a memory, a processor, and a constraint modulation indoor layout generation program driven by user feature parameters stored in the memory and executable on the processor. When the constraint modulation indoor layout generation program driven by user feature parameters is executed by the processor, the constraint modulation indoor layout generation method driven by user feature parameters is implemented.

[0016] The present invention also provides a computer program product, including a constraint-modulated interior layout generation program driven by user feature parameters, wherein the constraint-modulated interior layout generation program driven by user feature parameters implements the constraint-modulated interior layout generation method driven by user feature parameters when executed by a processor.

[0017] The beneficial effects of this invention are as follows: By introducing user characteristic parameters into the parameter modulation process of residential layout rules, this invention enables user preferences to participate in the entire process of indoor layout generation in a structured and executable form. This allows for a personalized and in-depth expression of the layout results while ensuring spatial safety and reasonable accessibility, thus avoiding the problem in the prior art where user preferences only affect post-generation filtering and the personalization effect is unstable.

[0018] This invention improves the stability and interpretability of the layout generation process by dividing the indoor layout generation process into a phased constraint mechanism that includes hard constraint feasibility determination, soft rule modulation determination, and user preference modulation determination. This ensures that the layout generation meets the basic spatial constraints at any stage, and then performs joint modulation of rules and preferences. This avoids the problems of layout structure instability, rule failure, or uncontrollable results that are prone to occur in end-to-end generation methods. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart illustrating the first embodiment of a constraint-modulated indoor layout generation method driven by user feature parameters according to the present invention.

[0021] Figure 2 This is a schematic diagram of a device for a constraint-modulated indoor layout generation method based on user feature parameters according to the present invention. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] Example 1: As Figure 1 The diagram shown is a flowchart of the first embodiment of the constraint modulation indoor layout generation method driven by user feature parameters according to the present invention. The first embodiment of the constraint modulation indoor layout generation method driven by user feature parameters according to the present invention is presented.

[0024] In the first embodiment, the constraint-modulated indoor layout generation method driven by user feature parameters includes: Step S10: Obtain the spatial structure data of the unit type to be laid out, and construct a spatial topology model based on the spatial structure data of the unit type to be laid out using a spatial topology construction method that combines reachability constraint propagation and regional connectivity decomposition. ; It should be noted that the "spatial topology construction method based on the combination of accessibility constraint propagation and regional connectivity decomposition" refers to the joint modeling of two types of constraint information, accessibility analysis and spatial regional connectivity division, when modeling the layout of the apartment space. Among them, accessibility constraint propagation is used to characterize the accessibility relationship between different areas in the residential space, including but not limited to the accessibility paths and propagation range of doorways, corridors, and open connecting areas. Regional connectivity decomposition is used to divide the overall apartment space into connected areas according to spatial boundaries, fixed immovable structures, and functional zoning requirements, forming a set of spatial sub-regions with clear boundaries and connectivity relationships, thereby constructing a spatial topology model that can simultaneously reflect the spatial geometry and accessibility relationships.

[0025] It is understandable that by simultaneously introducing accessibility propagation and connectivity decomposition during the spatial topology construction stage, the constructed spatial topology model can not only describe the relative positional relationships of each room or functional area in a geometric sense, but also reflect the actual passage paths and access sequences in the residential space. This provides a stable and constrained spatial structural foundation for subsequent furniture object generation, layout action selection, and the gradual layout generation process, thereby ensuring consistency and interpretability of the layout generation process at the spatial structure level.

[0026] It should be understood that, compared to traditional topological modeling methods that rely solely on spatial geometric boundaries or simple room divisions, this invention avoids the problem of misjudging access paths caused by relying solely on geometric adjacency by introducing an accessibility constraint propagation mechanism. At the same time, through regional connectivity decomposition, it avoids situations where the boundaries between different functional areas are unclear, furniture is placed across areas, or the circulation is disrupted during the subsequent layout generation process. Thus, it constrains the rationality of spatial access and regional integrity before the layout is generated, improving the stability and rationality of the overall layout generation.

[0027] For example, in a residential apartment, the living room and dining room are an open, interconnected space, while the bedrooms and public areas are connected by doorways. If modeling is based solely on spatial geometric boundaries, it may be difficult to accurately distinguish between main passageways and secondary activity areas, leading to situations where main passageways are blocked during subsequent furniture placement. However, by propagating accessibility constraints, the path relationships from the entrance door to the living room, dining room, and each bedroom can be clearly defined. Furthermore, by decomposing regional connectivity, the living room, dining room, and bedrooms can be divided into spatial areas with clearly defined boundaries. This allows the spatial topology model to simultaneously reflect the passage sequence and regional boundaries, providing a reliable basis for the rational arrangement of furniture and the constraint of circulation continuity.

[0028] Step S20: Based on the spatial topology model A candidate furniture object parameterization modeling task is performed using a candidate object generation mechanism based on functional consistency joint screening, and a candidate furniture object set F is output. It should be noted that the "candidate object generation mechanism based on functional consistency joint screening" refers to using the functional attributes, area scale, access constraints, and adjacent area relationships of each spatial region in the spatial topology model as joint screening conditions during the candidate furniture object generation stage. This process involves screening furniture objects in a pre-set furniture object library under multiple constraints, and then parametrically modeling the size parameters, placement orientation parameters, and occupied space range of the furniture objects based on the screening results. This process constructs a set of candidate furniture objects that match the specific spatial region.

[0029] Understandably, by introducing functional area information and access constraint information from the spatial topology model, the generation of candidate furniture objects is no longer based solely on simple matching of furniture categories or size ranges. Instead, it ensures that the furniture objects are consistent with the target spatial area in terms of functional attributes and spatial scale during the generation stage. This ensures that the subsequent layout generation process has basic rationality at the candidate object level and reduces the probability of unreasonable furniture objects entering the layout generation stage.

[0030] Step S30: Obtain user preference feature parameters. Based on the user's long-term behavior stability constraints and space usage preference feature processing method, construct features for user space usage preferences to form a user preference feature vector U that represents the user's space usage tendency. It should be noted that the "user preference feature parameters" in this step are used to characterize the relatively stable space usage habits and preference characteristics formed by users during long-term residence. Their sources may include users' historical residence behavior records, interaction setting data, and users' long-term selection results of space usage methods. When constructing the user preference feature parameter vector, it is preferable to distinguish between short-term, occasional behavioral characteristics and long-term stable behavioral characteristics, and to characterize different types of space usage preferences separately, so as to form a user preference feature parameter vector U that can reflect users' long-term usage tendencies.

[0031] Understandably, in the process of constructing user preference feature parameter vectors, by reasonably summarizing and processing user behavior data over time, the impact of short-term fluctuations or occasional behaviors on feature parameters is reduced, so that the resulting user preference feature parameters can more realistically reflect users' long-term living habits. At the same time, different types of space usage preferences participate in the subsequent rule modulation and layout generation process in a relatively independent parameter form, thereby improving the stability and controllability of personalized modulation.

[0032] Step S40: Introduce the lightweight mapping layer model CPML-Lite. Based on the user preference feature vector U and the lightweight mapping layer model CPML-Lite, perform the personalized rule weight and personalized rule threshold generation tasks using a modulation mechanism based on explicit modulation of rule parameters and lightweight neural inference, and output a personalized rule set. ; It should be noted that the lightweight mapping layer model CPML-Lite is a lightweight neural inference model used to characterize the matching relationship between user preference features and residential layout rules. Its role is to explicitly modulate the parameters of the preset residential layout rules based on the user preference feature vector U. The "explicit modulation of rule parameters" means that without changing the logical structure of the rules themselves, only the weight parameters and trigger threshold parameters of the rules are continuously adjusted to generate a personalized set of rules that are adapted to user preferences.

[0033] It is understandable that by introducing the lightweight mapping layer model CPML-Lite, the user preference feature parameter vector U can be converted into rule parameter modulation information, thereby realizing the influence of user preferences on rule weights and thresholds. Since the rule structure remains unchanged, the modulated rules still participate in the subsequent layout generation process in the form of explicit parameters, so that the personalized rule set has both user preference adaptation capability and maintains the interpretability and controllability of the rule system.

[0034] For example, in a residential layout scenario, when the user preference feature vector U represents a high demand for continuity of passageways and spatial security, the lightweight mapping layer model CPML-Lite can increase the weight of the corresponding rules or adjust their trigger thresholds without changing the relevant passage rule logic, making these rules easier to satisfy in the subsequent step-by-step layout generation process. When users pay less attention to certain visual or decorative rules, the weight of these rules is reduced accordingly, thereby achieving personalized rule modulation effects for different users while maintaining the integrity of the overall rule system.

[0035] Step S50: Based on the personalized rule set A phased, step-by-step constraint mechanism is used to execute the step-by-step layout generation task and output the final interior layout scheme.

[0036] It should be noted that the "phased constraint mechanism" refers to dividing the indoor layout generation process into multiple consecutive generation stages, and applying necessary constraints and modulations to the candidate layout actions at the current generation moment based on a unified constraint modulation framework in each generation stage. Among them, hard spatial constraints are used to ensure basic feasibility, rule parameter modulation is used to guide the rationality of the layout, and user feature parameters are used to adjust the intensity of rule modulation, thus working together to advance the layout generation process step by step.

[0037] It is understandable that by adopting a phased, step-by-step constraint mechanism, the layout generation process is carried out by gradually updating the layout state. This allows rule constraints and user feature parameters to participate in the generation decision in a continuously modulated manner at each generation stage, thereby ensuring that the layout generation process satisfies the basic spatial constraints at any stage. On this basis, the layout results are gradually guided to converge toward the usage tendency represented by the user feature parameters.

[0038] It should be understood that, compared with traditional end-to-end generation methods or simple heuristic search methods, this invention introduces a phased constraint modulation mechanism in the layout generation process, so that spatial feasibility constraints, rule modulation parameters and user feature parameters work together in a unified generation process. This avoids the problems of uncontrollable layout results and difficulty in rules taking effect in end-to-end generation methods, and at the same time makes up for the lack of personalization capabilities in fixed rule methods, thereby improving the stability and rationality of layout generation results.

[0039] Furthermore, it should be noted that this invention aims to construct a constraint modulation mechanism driven by user feature parameters. Through a mapping layer, user feature parameters are converted into rule-based modulation parameters and probabilistic modulation criteria during the generation process, enabling user feature parameters to form a structured and executable control effect during the indoor layout generation process. The lightweight mapping layer model CPML-Lite, rule inference, rule customization, probabilistic modulation, and consistency verification mentioned in the specification are all specific implementation means or functional modules for achieving the above core technical solutions, used to support the modulation effect of user feature parameters on the layout generation process, and do not constitute an independent inventive point of this invention.

[0040] Example 2: Furthermore, the present invention provides a user-feature parameter-driven constraint-modulated interior layout generation system, which employs a user-feature parameter-driven constraint-modulated interior layout generation method from the above embodiments, and can solve a technical problem related to user-feature parameter-driven constraint-modulated interior layout generation. The beneficial effects of the user-feature parameter-driven constraint-modulated interior layout generation system provided by the present invention are the same as those of the user-feature parameter-driven constraint-modulated interior layout generation method provided in the above embodiments, and other technical features of the user-feature parameter-driven constraint-modulated interior layout generation system are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0041] Example 3: This invention provides a constraint-modulated indoor layout generation device driven by user feature parameters. Please refer to... Figure 2A user-feature parameter-driven constraint-modulated indoor layout generation device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to perform the user-feature parameter-driven constraint-modulated indoor layout generation method described in Embodiment 1 above. The user-feature parameter-driven constraint-modulated indoor layout generation device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. This user-feature parameter-driven constraint-modulated indoor layout generation device is merely an example and should not impose any limitations on the functionality or scope of use of this embodiment. A user-feature parameter-driven constraint modulation indoor layout generation device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory 1002 or a program loaded from a storage device 1003 into a random access memory 1004. The random access memory 1004 also stores various programs and data required for the operation of the user-feature parameter-driven constraint modulation indoor layout generation device. The processing unit 1001, the read-only memory 1002, and the random access memory 1004 are interconnected via a bus 1005. An I / O interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 allows a user-feature parameter-driven constrained modulation indoor layout generation device to wirelessly or wiredly communicate with other devices to exchange data. While the figure shows a user-feature parameter-driven constrained modulation indoor layout generation device with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0042] Example 4: This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the user-feature parameter-driven constraint-modulated interior layout generation method described above. The computer program product provided by this invention can solve the technical problem of user-feature parameter-driven constraint-modulated interior layout generation. Compared with the prior art, the beneficial effects of the computer program product provided by this invention are the same as those of the user-feature parameter-driven constraint-modulated interior layout generation method provided in the above embodiments, and will not be repeated here.

[0043] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this invention.

[0044] It should be understood that the various parts disclosed in this invention can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0045] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A constraint-modulated indoor layout generation method based on user feature parameters, characterized in that, The methods include: Step S10: Obtain the spatial structure data of the unit type to be laid out, and construct a spatial topology model based on the spatial structure data of the unit type to be laid out using a spatial topology construction method that combines reachability constraint propagation and regional connectivity decomposition. ; Step S20: Based on the spatial topology model A candidate furniture object parameterization modeling task is performed using a candidate object generation mechanism based on functional consistency joint screening, and a candidate furniture object set F is output. Step S30: Obtain user preference feature parameters. Based on the user's long-term behavior stability constraints and space usage preference feature processing method, construct features for user space usage preferences to form a user preference feature vector U that represents the user's space usage tendency. Step S40: Introduce the lightweight mapping layer model CPML-Lite. Based on the user preference feature vector U and the lightweight mapping layer model CPML-Lite, perform the personalized rule weight and personalized rule threshold generation tasks using a modulation mechanism based on explicit modulation of rule parameters and lightweight neural inference, and output a personalized rule set. ; Step S50: Based on the personalized rule set A phased, step-by-step constraint mechanism is used to execute the step-by-step layout generation task and output the final interior layout scheme.

2. The constraint-modulated indoor layout generation method based on user feature parameters as described in claim 1, characterized in that, In step S10, the spatial structure data of the apartment layout to be designed includes the boundary outlines, polygonal geometry, spatial dimensions, door and window positions, fixed and immovable obstacle positions, and available activity area range of each room; spatial topology model. Includes the set of placeable area constraints Room boundary constraint set Set of non-placeable regions The set of adjacency relationships between rooms .

3. The constraint-modulated indoor layout generation method based on user feature parameters as described in claim 2, characterized in that, In step S20, based on the spatial topology model The steps for performing parametric modeling of candidate furniture objects using a candidate object generation mechanism based on functional consistency joint screening, and outputting a set of candidate furniture objects F, specifically include: Step S201: Based on the set of placeable region constraints in the spatial topology model S Room boundary constraint set Set of non-placeable regions The set of adjacency relationships between rooms Perform spatial topology feasible region pruning processing and output a set of candidate placement sub-regions in each room space that meet the above constraints; Step S202: Obtain the spatial function attribute identifiers within each room. Furniture object functional property parameters Based on spatial functional attribute identification Furniture object functional property parameters Perform consistency matching judgment to generate a set of intermediate candidate furniture objects that meet the functional consistency constraints; Step S203: Based on the intermediate candidate furniture object set and the candidate placement sub-region set, form a candidate furniture object set F. The candidate furniture object set F includes furniture category identifier, furniture size parameters, furniture orientation parameters, and furniture object functional attribute parameters. .

4. The constraint-modulated indoor layout generation method based on user feature parameters as described in claim 1, characterized in that, Step S30 involves obtaining user preference feature parameters, constructing user space usage preferences based on long-term user behavior stability constraints and space usage preference feature processing methods, and forming a user preference feature vector U to characterize user space usage tendencies. This step specifically includes: Step S301: Obtain user preference feature parameters, which are used to characterize users' long-term stable residential behavior and space usage preferences; Step S302: Based on user preference feature parameters, a pre-trained Long Short-Term Memory (LSTM) network model and a Multilayer Perceptron (MLP) network model are used to sequentially perform long-term behavioral feature extraction and spatial usage preference decoupling mapping, outputting an intermediate feature representation of user preferences; Step S303: First, semantic grouping is performed on the intermediate feature representation of user preferences using a semantic analysis method based on feature similarity clustering, outputting spatial morphology-related preference feature representation, traffic behavior-related preference feature representation, visual-related preference feature representation, and safety-related feature representation; then, the intermediate feature representation of user preferences is normalized and vectorized according to the output order of semantic grouping to construct the user preference feature vector U.

5. The constraint-modulated indoor layout generation method based on user feature parameters as described in claim 1, characterized in that, In step S40, the lightweight mapping layer model CPML-Lite is introduced. Based on the user preference feature vector U and the lightweight mapping layer model CPML-Lite, a modulation mechanism based on explicit modulation of rule parameters and lightweight neural inference is used to perform the task of generating personalized rule weights and personalized rule thresholds, and outputs a set of personalized rules. The steps specifically include: Step S401: First, load the preset residential layout rule library. , ;in, Residential Layout Rule Library The i-th rule, Residential Layout Rule Library Total number of rules; rules Includes rule type identifier Basic weights Basic trigger threshold Correlation vectors with regular features ; Step S402: Introduce the lightweight mapping layer model CPML-Lite to associate the regular features with vectors. The user preference feature vector U is input into the pre-trained lightweight mapping layer model CPML-Lite for lightweight neural inference. The lightweight mapping layer model CPML-Lite outputs the rule matching strength. Among them, rule matching strength Used to characterize the degree of fit between user preferences and the i-th rule; Step S403: Based on rule matching strength For basic weights and basic trigger threshold Perform explicit modulation to generate weighted personalized rule modulation parameters. And threshold personalized rule modulation parameters ; ; ;in, These are the weight modulation coefficients, used to control the modulation amplitude of the rule weights as the rule matching strength changes; This is the threshold modulation coefficient, used to control the modulation amplitude of the rule triggering threshold as the rule matching strength changes; Step S404: Merge rule matching strength Weighted personalized rule modulation parameters And threshold personalized rule modulation parameters Generate and output a set of personalized rules .

6. The constraint-modulated indoor layout generation method based on user feature parameters as described in claim 5, characterized in that, In step S40, the lightweight mapping layer model CPML-Lite is a lightweight network model built on the CPML model and the multilayer perceptron (MLP). It is used to calculate the matching strength between user preference features and rule features without changing the residential layout rule structure. The lightweight mapping layer model CPML-Lite includes an input layer that receives regular feature association vectors. The input is concatenated with the user preference feature vector U; The feature mapping layer is used to perform low-dimensional embedding mapping and nonlinear combination on the concatenated input using a multilayer perceptron structure to generate a joint representation of rule preferences. The stability constraint layer is used to constrain the joint representation of rule preferences using a layer normalization structure, and outputs the stabilized joint features. The matching strength regression layer is used to map the stabilized joint features into a scalar representation of the rule matching strength using a single-layer fully connected structure. The output layer is used to output the rule matching strength as a scalar representation based on the rule matching strength.

7. The constraint-modulated indoor layout generation method based on user feature parameters as described in claim 1, characterized in that, In step S50, based on the personalized rule set The process of generating a layout using a phased, step-by-step constraint mechanism to output the final interior layout scheme includes: dividing the interior layout generation process into three stages: hard constraint feasibility determination, soft rule modulation determination, and user preference modulation determination; in the hard constraint feasibility determination stage, based on a personalized rule set... The system determines whether the layout generation action meets the preset spatial constraints in the residential space and outputs the corresponding hard constraint feasibility judgment result; in the soft rule modulation judgment stage, it is based on the personalized rule set. Determine whether the layout generation action meets the preset flow continuity constraint and output the corresponding soft rule modulation result; in the user preference modulation determination stage, based on the personalized rule set... Determine whether the layout generation action meets the preset user preference constraints and output the corresponding user preference modulation result; output the final indoor layout scheme by combining the hard constraint feasibility judgment result, soft rule modulation result and user preference modulation result.

8. A user-feature parameter-driven constraint-modulated indoor layout generation system, applied to the user-feature parameter-driven constraint-modulated indoor layout generation method according to any one of claims 1 to 7, characterized in that, The user-feature parameter-driven constraint-modulated indoor layout generation system includes: The spatial topology construction module is used to acquire the spatial structure data of the apartment layout to be laid out. Based on the spatial structure data of the apartment layout to be laid out, a spatial topology model is constructed using a spatial topology construction method that combines reachability constraint propagation and regional connectivity decomposition. ; The candidate furniture object generation module is used for generating furniture based on spatial topology models. A candidate furniture object parameterization modeling task is performed using a candidate object generation mechanism based on functional consistency joint screening, and a candidate furniture object set F is output. The user preference feature construction module is used to obtain user preference feature parameters. Based on the user's long-term behavior stability constraints and the space usage preference feature processing method, it constructs features of user space usage preferences to form a user preference feature vector U that represents the user's space usage tendency. The personalized rule modulation module introduces the lightweight mapping layer model CPML-Lite. Based on the user preference feature vector U and the lightweight mapping layer model CPML-Lite, it employs a modulation mechanism that combines explicit modulation of rule parameters with lightweight neural inference to perform personalized rule weight and personalized rule threshold generation tasks, and outputs a personalized rule set. ; A progressively deployed generation module is used to generate data based on a set of personalized rules. A phased, step-by-step constraint mechanism is used to execute the step-by-step layout generation task and output the final interior layout scheme.

9. A constraint-modulated indoor layout generation device driven by user feature parameters, characterized in that, The user-feature parameter-driven constraint modulation indoor layout generation device includes: a memory, a processor, and a user-feature parameter-driven constraint modulation indoor layout generation program stored in the memory and executable on the processor. When the user-feature parameter-driven constraint modulation indoor layout generation program is executed by the processor, it implements the user-feature parameter-driven constraint modulation indoor layout generation method according to any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a user-feature parameter-driven constraint modulation indoor layout generation program, which, when executed by a processor, implements a user-feature parameter-driven constraint modulation indoor layout generation method according to any one of claims 1 to 7.

Images