A method and system for optimizing a layout of a plan

Abstract

The present application belongs to the technical field of planar design layout optimization, and particularly relates to a planar design layout optimization method and system, which comprises the following steps: evaluating a target layout state based on an evaluation model to determine whether it is a poor state; when it is determined to be a poor state, analyzing a characteristic vector corresponding to the poor state, inputting the characteristic vector into an evaluation item to calculate an evaluation result, marking components in the characteristic vector as interference degrees according to the evaluation result, determining group interference in the interference degrees, calculating a bias parameter, comparing the bias parameter with a matching parameter to determine whether the group interference has bias, and according to the determination result, adjusting a preset optimization order of non-group interference or performing an optimization operation to generate a planar layout optimization scheme. The present application can realize accurate quantitative diagnosis of layout problems, not only can determine whether the layout state is a poor state, but also can specifically identify the interference degree components causing the poor state, thereby enhancing the pertinence of the planar layout optimization scheme.

Description

Technical Field

[0001] This invention belongs to the field of graphic design layout optimization technology, specifically relating to a graphic design layout optimization method and system. Background Technology

[0002] With the deep integration of digital and intelligent technologies, floor plan layout planning has become an indispensable key link in many fields such as graphic design, human-computer interaction interface, industrial drawing and even intelligent manufacturing. It is not only related to the clarity of information transmission and visual aesthetics, but also directly affects user experience and operational efficiency.

[0003] Existing automated layout optimization technologies have limitations in terms of analytical dimensions. Most traditional solutions rely only on analyzing the local and shallow geometric features between layout elements, such as calculating and adjusting the contact area, overlapping area, or relative distance between elements, ignoring the global and structural features of the layout as a whole. At the same time, they lack the ability to accurately diagnose layout problems, and can only make a macroscopic judgment on whether the layout state is reasonable, but cannot further locate the specific reasons for the poor state, resulting in a lack of clear direction for optimization operations and insufficient targeting of the solutions. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for optimizing the layout of graphic design, so as to solve the problems existing in the existing graphic design layout optimization methods.

[0005] The specific technical solution adopted by this invention is as follows:

[0006] This invention provides a method for optimizing the layout of a planar design. When the current layout state of the target planar plane is determined to be in a suboptimal state based on an evaluation model, the method includes:

[0007] The eigenvectors corresponding to the inferior state are analyzed to identify the degree of interference. Based on the degree of interference, grouped interference is determined, and it is determined whether the grouped interference has bias.

[0008] And based on the determination of whether the grouped interference has a bias, a planar layout optimization scheme is generated.

[0009] In a preferred technical solution, determining that the current layout state is a suboptimal state includes:

[0010] Based on the evaluation model and the starting node position of the layout elements, the current layout state is evaluated to obtain the layout evaluation result;

[0011] And when the layout evaluation result is not greater than the preset evaluation threshold parameter, the current layout state is determined to be in a bad state.

[0012] In a preferred embodiment, the evaluation model includes a first verification parameter and a second verification parameter for evaluating the layout state. The first verification parameter includes the accessible distance between layout elements and the overlapping area judgment value of layout elements. The second verification parameter includes the symmetry structure judgment value and the deconstruction region judgment value.

[0013] In a preferred technical solution, the degree of interference identification includes:

[0014] The feature vector is input into at least one evaluation term defined in the evaluation model to calculate the evaluation result;

[0015] And when the evaluation result is less than or equal to zero, the component in the feature vector corresponding to the evaluation item is labeled as the interference degree.

[0016] In a preferred technical solution, determining grouped interference includes:

[0017] Arrange all components labeled as interference into an interference sequence;

[0018] And when consecutive interference values ​​in the interference sequence show a preset decreasing trend, the interference that forms this decreasing trend is identified as grouped interference.

[0019] In a preferred technical solution, determining whether grouped interference is biased includes:

[0020] For each group of interferences, calculate its proportion in the total number of interferences, and define the proportion as the bias parameter corresponding to that group of interferences;

[0021] It also compares the bias parameter with the preset matching parameter to determine whether the corresponding grouped interference has bias.

[0022] In a preferred embodiment, the method further includes a step for determining matching parameters, the step comprising performing an iterative matching determination, in a single iteration:

[0023] When the positive matching condition is met, the matching parameter is incremented based on the bias parameter to obtain the updated matching parameter for the next iteration.

[0024] And when it is determined that the reverse matching condition is met, the first parameter value that does not meet the forward matching condition is selected from the set of matching parameters used in previous forward matching, and the parameter value is determined as the final matching parameter, and the iteration is terminated.

[0025] In a preferred technical solution, generating a planar layout optimization scheme includes:

[0026] When grouped interference is determined to be biased, the preset optimization order of ungrouped interference is adjusted and optimized based on the bias parameter, and the ungrouped interference is optimized according to the adjusted optimization order to generate a planar layout optimization scheme.

[0027] And when it is determined that the grouped interference does not have bias, an optimization operation is performed based on the recorded reference parameters to calculate the optimization bias, and a planar layout optimization scheme is generated based on the optimization bias.

[0028] The present invention also provides a planar design layout optimization system, comprising:

[0029] The layout state evaluation module is used to determine whether the current layout state of the target plane is in a bad state based on the evaluation model.

[0030] The interference characteristic analysis module is used to analyze the feature vectors corresponding to the inferior state to identify the interference degree, and to determine whether the grouped interference has bias based on the interference degree;

[0031] And a layout optimization generation module, which generates a planar layout optimization scheme based on the judgment result of the interference characteristic analysis module on whether the grouped interference has a bias.

[0032] In a preferred embodiment, the interference characteristic analysis module, when identifying the interference degree, is specifically used to: input the feature vector into at least one evaluation item defined in the evaluation model to calculate the evaluation result; and when the evaluation result is less than or equal to zero, label the component in the feature vector corresponding to the evaluation item as the interference degree.

[0033] Beneficial effects

[0034] This invention constructs an evaluation model, analyzes feature vectors after determining that the current layout state is inferior, and inputs the components in the feature vectors into the evaluation items. Based on the calculation results, the components are labeled as interference degrees, thereby achieving accurate quantitative diagnosis of layout problems. It not only determines whether the layout state is inferior, but also specifically identifies the interference degree components that cause the inferiority state. This overcomes the shortcomings of traditional solutions that only provide evaluation conclusions but cannot locate specific problems, and provides a clear optimization direction for subsequent optimization operations, enhancing the pertinence of the planar layout optimization solution.

[0035] This invention analyzes all components labeled as interference levels, distinguishes between grouped interference and ungrouped interference, and calculates the bias parameter of grouped interference to determine whether it is biased. If the grouped interference is determined to be biased, the preset optimization order for ungrouped interference is adjusted based on the bias parameter. Thus, this application can prioritize the processing of biased grouped interference and use its bias parameter to guide the optimization process for ungrouped interference, ensuring that key layout conflicts are resolved first and improving the overall effect of layout optimization. Attached Figure Description

[0036] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0037] To make the objectives, features, and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0038] Example 1

[0039] This embodiment provides a method for optimizing the layout of a graphic design, which specifically includes the following steps:

[0040] Step S100: When the current layout state of the target plane is determined to be in a poor state based on the evaluation model, the feature vector corresponding to the poor state is analyzed to identify the interference degree, the group interference is determined based on the interference degree, and it is determined whether the group interference has bias.

[0041] Step S200: Generate a planar layout optimization scheme based on the determination result of whether the grouped interference has a bias.

[0042] Specifically, all layout elements within the target plane and their corresponding starting node positions are obtained. The target plane can be an architectural plan, an industrial production plan, or a virtual simulation space. The obtained layout elements can include functional units or furniture modules on drawings, and their corresponding starting node positions can further include information such as spatial location, size boundaries, placement direction, and arrangement order.

[0043] An evaluation model is constructed. This model is a computational framework used to quantitatively analyze the overall layout quality of the target plane and determine its current layout state. It includes a first verification parameter and a second verification parameter for evaluating the current layout state. The specific definition of the evaluation model is as follows:

[0044] S l = w1·V1(ε) + w2·V2(ε)

[0045] In the formula, S l The layout evaluation result represents a comprehensive quantitative score of the current floor plan layout scheme; a higher value indicates better layout quality. V1(ε) represents the first verification parameter function, which calculates the basic geometric and physical feasibility indicators. V2(ε) represents the second verification parameter function, which calculates the macroscopic structural and aesthetic characteristic indicators. w1 and w2 represent weighting coefficients, which are preset weights used to adjust the importance of physical feasibility and macroscopic structural integrity in the overall evaluation result. ε = {E1, E2, ..., E...} N} represents the set of all layout elements in the target plane, meaning that each element E is a set of all layout elements in the target plane. iFrom its state vector (x) i ,y i ,w i ,h i ,θ i The definitions represent the center point coordinates, width, height, and rotation angle, respectively.

[0046] Specifically, the first verification parameter focuses on basic geometric judgment indicators to ensure the physical feasibility and basic compliance of the layout scheme. The first verification parameter includes at least the accessible distance between layout elements and the overlapping area judgment value of layout elements. The accessible distance is used to determine whether sufficient operation or passage space is reserved between each layout element. The overlapping area judgment value is a quantitative indicator whose value is equal to the area of ​​two or more layout elements overlapping each other in space. It is used to identify physical interference. A value of zero indicates no conflict.

[0047] Specifically, the second verification parameter focuses on evaluating the overall structural rationality and aesthetic value of the layout scheme. The second verification parameter includes at least a symmetry structure judgment value and a deconstruction area judgment value. The symmetry structure judgment value evaluates the visual appeal, harmony, and stability of the layout by calculating the distribution balance of layout elements on both sides of a specific axis or center point. The deconstruction area judgment value is used to identify areas in the layout that are disorganized, underutilized, or functionally fragmented, providing a basis for subsequent structural reorganization.

[0048] In step S100, the current layout state of the target plane is determined to be suboptimal based on the evaluation model. Specifically, the current layout state of the target plane is evaluated based on the evaluation model and the starting node position to obtain a layout evaluation result; and when the layout evaluation result is not greater than a preset evaluation threshold parameter, the current layout state is determined to be suboptimal.

[0049] In this embodiment, the layout evaluation result is compared with a preset evaluation threshold parameter to determine the current layout state as a preset layout state type. The evaluation threshold parameter is a quality benchmark preset based on industry standards, historical best practices, or specific design goals. Those skilled in the art can set it according to actual conditions without specific restrictions. If the layout evaluation result is greater than the evaluation threshold parameter, the current layout state is determined to be excellent. If the layout evaluation result is not greater than the evaluation threshold parameter, it indicates that the current layout has defects, and the current layout state is determined to be poor. To improve processing efficiency, the step of extracting feature vectors corresponding to the layout state type is only performed when the current layout state is determined to be poor. The feature vector is a multi-dimensional data set that records the deviation value, deviation direction, and specific location information of each evaluation index, providing a data foundation for subsequent optimization.

[0050] When the current layout state is in a poor state, the extracted feature vector is input into the evaluation model. The evaluation model is defined to include at least one evaluation term. Each evaluation term corresponds to a component of the feature vector and is responsible for calculating the component to obtain the evaluation result, which is used to distinguish the deviations of different natures. If the evaluation result is greater than zero, it indicates that the layout feature adjustment corresponding to the component has a positive impact on the overall layout. Therefore, the component in the feature vector corresponding to the evaluation term is labeled as the influence degree. If the evaluation result is less than or equal to zero, it indicates that the layout feature corresponding to the component has a negative effect on the overall effect. Therefore, the component in the feature vector corresponding to the evaluation term is labeled as the interference degree. All components of the feature vector are classified to identify positive and negative factors in the layout.

[0051] Further, in step S100, the feature vector corresponding to the inferior state is analyzed to identify the interference degree, group interference is determined based on the interference degree, and it is determined whether the group interference has bias.

[0052] In this embodiment, all components labeled as interference are grouped to determine whether they are grouped or ungrouped interference, in order to identify the correlation of the problem. Specifically, the method for determining grouped interference includes: arranging all components labeled as interference according to their spatial position or logical order in the layout to form an interference sequence; comparing consecutive interference values ​​in the interference sequence; if consecutive interference values ​​show a preset decreasing trend, the interference values ​​forming this decreasing trend are determined as grouped interference; and the interference values ​​in the interference sequence that do not show a decreasing trend are determined as ungrouped interference. The preset decreasing trend is a predetermined rule used to determine whether a group of consecutive values ​​in the interference sequence constitutes a meaningful intensity decreasing pattern, such as monotonically decreasing or exponentially decaying.

[0053] For the identified grouped interferences, calculate their proportion in the total interference levels and define the proportion as the bias parameter corresponding to the grouped interference. The bias parameter reflects the degree of dominance of this grouped interference in the current layout problem. The bias parameter is compared with the preset matching parameter to determine whether the corresponding grouped interference has bias.

[0054] In some implementations, the step of determining the matching parameters includes: defining an objective function to evaluate whether a given first candidate matching parameter value can effectively distinguish the grouped interferences that need to be prioritized; setting initial matching parameters and setting an upper limit on the number of iterations, which is set to prevent infinite loops and is the maximum number of iterations allowed in the iterative matching determination process; performing iterative matching determination, in a single iteration, if the calculation result based on the objective function satisfies the positive matching condition (e.g., the evaluation score is still rising), it is determined to be a positive match, and the matching parameter is incremented based on the bias parameter to obtain the updated matching parameter for the next iteration; if the calculation result based on the objective function satisfies the negative matching condition (e.g., the evaluation score begins to fall), it is determined to be a negative match, at which point the first parameter value that does not satisfy the positive matching condition is selected from the set of matching parameters used in previous positive matches, and determined as the optimal matching parameter value for the final determination of bias, and this parameter value is determined as the final matching parameter, and the iteration is terminated. The objective function formula is as follows:

[0055]

[0056] In the formula, J(μ) c The score represents the evaluation score, which measures the candidate matching parameter μ. c A quantitative indicator of discrimination; a higher score indicates higher μ. c The better the effect as a segmentation threshold; μ c Represents the candidate matching parameters, meaning the matching parameter values ​​used for testing in the current iteration; the set of bias parameters for all grouped disturbances. This represents the set of bias parameters, which means the set of bias parameters that include all grouped disturbances in the current layout; where, and Explanation of the algorithm: This formula calculates the threshold μ. c The goal is to find the threshold that maximizes the difference between the biased and unbiased parameter means.

[0057] After the comparison is completed, if the bias parameter is greater than or equal to the matching parameter, the corresponding group of interferences is determined to be biased; if the bias parameter is less than the matching parameter, the corresponding group of interferences is determined to be unbiased, and the value of the bias parameter is recorded as the reference parameter.

[0058] In step S200, a planar layout optimization scheme is generated based on the determination result of whether the grouped interference has a bias.

[0059] Specifically, if the grouped interference is determined to be biased, optimization processing is performed. Optimization processing refers to a core optimization process initiated when biased grouped interference is detected, characterized by prioritizing the handling of the primary contradiction. Optimization processing includes: summarizing the bias parameters corresponding to all biased grouped interferences and recording the initial optimization counts for each parameter historically as optimization targets, defining a reference function; based on the reference function, calculating the recorded initial optimization counts by decreasing the counts to obtain the optimization reference coefficients for each parameter, which are calculated using the following formula: Optimization reference coefficient = Target optimization reference value × Optimization count, where the target optimization reference value is a preset value representing the maximum or initial optimization intensity; selecting the maximum value among all optimization reference coefficients as the dominant adjustment factor in this round of optimization, and determining this maximum value as the primary driving coefficient; and determining the final planar layout optimization scheme based on the product of the biased parameter and the primary driving coefficient.

[0060] Simultaneously, the preset optimization order is adjusted based on the bias parameter. This preset optimization order refers to a default processing order set for all ungrouped interferences before optimization begins. The adjusted optimization order is then used to optimize the ungrouped interferences. The method further includes: if the basic data or analysis parameters required for any sub-step are missing, the current sub-step is terminated, and subsequent sub-steps continue to be executed. This avoids interruption of the overall optimization process due to local data issues. The calculation formula for the optimization reference coefficient is as follows:

[0061]

[0062] Algorithm Explanation: An exponential decay model is used to ensure that the algorithm continues to function as the number of optimization iterations N increases. i The increase in the reference coefficient C optimizes the reference coefficient. r Decreasing the weighting reduces the adjustment weight for terms that have been optimized multiple times. In the formula, C... r This represents the optimization reference coefficient, which determines the adjustment range of the current optimization step. Its value decreases as the number of optimization iterations increases; V t This represents the target optimization reference value, which means defining the initial optimization (N). i The baseline value of strength when N = 0; i λ represents the initial optimization count, which means the number of times the corresponding group of disturbances has been optimized before entering this round of optimization; λ represents the decay constant, which means the normal number that controls the rate at which the optimization coefficient decreases as the number of optimization counts increases.

[0063] In this embodiment, if the grouped interference is determined to be unbiased, an optimization operation is performed based on the recorded reference parameters. The optimization operation refers to a backup optimization process initiated when no biased grouped interference is detected. Its characteristic is a more balanced adjustment based on the reference parameters, calculating the optimization bias as a quantitative indicator to guide layout fine-tuning. Based on the optimization results or the optimization bias, a planar layout optimization scheme is generated. This scheme includes the new node position information corresponding to all corrected interference levels, the optimization bias, remaining uncorrected items, and the optimization version number.

[0064] In some embodiments, if a certain disturbance value has the largest area in the same group and its direction is consistent with the default direction in the evaluation model, it can be used as the representative parameter of the group; other items in the same group can be automatically marked as its sub-parameters. Sub-parameters refer to all other disturbance values ​​in a group of disturbances except for the representative parameter, and their optimization processing will be associated with the representative parameter.

[0065] When comparing multiple versions of a layout, a floor plan score list can be generated. This score list is a structured report containing multi-dimensional scoring items, used to comprehensively evaluate and compare one or more floor plan optimization schemes. The list includes visual scores, structural scores, and loading latency scores, which together form the overall evaluation score to support the decision on whether to adopt the optimized layout scheme. Specifically, the visual score is a sub-item in the floor plan score list, assessing the layout scheme's performance in terms of aesthetics, balance, and harmony; the structural score is a sub-item, assessing the layout scheme's performance in terms of functionality, streamlined rationality, and space utilization; and the loading latency score is a sub-item, assessing the computational resources or time required to load and render the layout scheme, reflecting its complexity and performance.

[0066] Example 2

[0067] This embodiment provides a planar design layout optimization system for implementing the planar design layout optimization method described above. After identifying the current layout state of the target plan as suboptimal, it identifies interference levels and determines grouped interference and bias by deeply analyzing the feature vectors corresponding to the suboptimal state, generating a planar layout optimization scheme. In its implementation, this system can be integrated as a software module into professional design software or run as a standalone application on computing devices including personal computers, servers, and design workstations. The system can be divided into the following collaborative modules:

[0068] The layout state evaluation module is used to evaluate the current layout state of the target plane. Specifically, it obtains the starting node positions of the layout elements, calls the evaluation model, and performs a comprehensive evaluation of the current layout state to obtain the layout evaluation result. The evaluation model can be a comprehensive scoring function or a trained machine learning model. Its evaluation criteria include a first verification parameter and a second verification parameter. The first verification parameter can cover the contact distance and overlap area judgment values ​​between layout elements to evaluate the basic physical rationality of the layout. The second verification parameter can cover the symmetry structure judgment value and deconstruction region judgment value to evaluate the aesthetics and structural rationality of the layout. In this application, the layout evaluation result is compared with a preset evaluation threshold parameter. If the layout evaluation result is not greater than the evaluation threshold parameter, the current layout state is determined to be a poor state.

[0069] The interference characteristic analysis module is used to deeply analyze the root causes of layout degradation. Specifically, it includes the following steps: Identifying interference degree by inputting the feature vector into at least one evaluation item defined in the evaluation model for calculation. Each evaluation item is a subdivided component of the evaluation model, corresponding to different components of the feature vector. If the evaluation result is less than or equal to zero, it indicates that the feature vector component corresponding to that evaluation item has a negative impact on the overall layout. Therefore, this module labels the component in the feature vector corresponding to the evaluation item as the interference degree. Determining grouped interference: After identifying all interference degrees, all components labeled as interference degrees are arranged into an interference degree sequence according to their original order in the feature vector or other preset rules.

[0070] The system compares consecutive interference values ​​in the interference sequence. If consecutive interference values ​​show a preset decreasing trend, the interference values ​​forming this decreasing trend are identified as grouped interferences, representing a group of related layout problems. A bias determination is then performed: for each identified group of interferences, its proportion in all interference values ​​is calculated, and this proportion is defined as the bias parameter corresponding to this group of interferences. The calculated bias parameter is compared with a preset matching parameter. If the bias parameter is greater than or equal to the matching parameter, the corresponding group of interferences is determined to be biased, meaning that this group of interferences is the main problem causing layout degradation. If the bias parameter is less than the matching parameter, the corresponding group of interferences is determined to be unbiased.

[0071] In addition, to improve the accuracy and adaptability of the determination, a sub-step for determining the matching parameters may be included. The sub-step dynamically determines the matching parameters by performing iterative matching determination. In a single iteration, when the determination is that the positive matching condition is met, the matching parameters are incremented based on the bias parameter to obtain the updated matching parameters for the next iteration. When the determination is that the negative matching condition is met, the first parameter value that does not meet the positive matching condition is selected from the set of matching parameters used in previous positive matching, and this parameter value is determined as the final matching parameter, and the iteration is terminated.

[0072] The layout optimization generation module is used to generate the final planar layout optimization scheme based on the bias determination result. Specifically, if it is determined that there are biased grouped interferences, it is considered that the main problem in the layout has been identified. At this time, based on the bias parameter, the preset optimization order for optimizing ungrouped interferences is adjusted, and all ungrouped interferences are optimized according to the adjusted optimization order to generate a planar layout optimization scheme. If it is determined that all grouped interferences are not biased, or there are no grouped interferences, it indicates that the layout problem is relatively scattered and there is no obvious main contradiction. At this time, a more global optimization strategy is adopted. Based on the recorded reference parameters, optimization operations are performed, the optimization bias is calculated, and a planar layout optimization scheme is generated based on the optimization bias.

[0073] Through the collaborative work of the layout status evaluation module, interference characteristic analysis module, and layout optimization generation module, the system in this embodiment can achieve intelligent and automated analysis and optimization of graphic design layouts. It can not only identify problems in the layout, but also deeply analyze the internal structure of the problems (i.e., grouped interference and bias), and take more targeted optimization strategies accordingly. It is especially suitable for graphic design fields that require efficient processing of a large number of layout elements, such as poster design, user interface and user experience design, and publication layout.

[0074] This invention has been described in detail through embodiments, but these descriptions are not intended to limit the scope of protection of this invention. Those skilled in the art will recognize that modifications or equivalent substitutions can be made to the technical solutions of this invention without departing from the spirit and scope thereof, and such modifications or substitutions should all be covered within the scope of protection of this invention. Furthermore, structures, apparatuses, and method steps not specifically described or explained in the specification shall be implemented according to conventional methods in the art unless otherwise specified or limited.

Claims

1. A method for optimizing the layout of a graphic design, characterized in that, When the current layout state of the target plane is determined to be in a poor state based on the evaluation model, the method includes: The eigenvectors corresponding to the inferior state are analyzed to identify the degree of interference. Based on the degree of interference, grouped interference is determined, and it is determined whether the grouped interference has bias. And based on the determination of whether the grouped interference has a bias, a planar layout optimization scheme is generated; Determining the current layout state as inferior includes: evaluating the current layout state based on the evaluation model and the starting node position of the layout elements to obtain the layout evaluation result; and determining the current layout state as inferior when the layout evaluation result is not greater than a preset evaluation threshold parameter. The evaluation model includes a first verification parameter and a second verification parameter for evaluating the layout state. The first verification parameter includes the accessible distance between layout elements and the overlapping area judgment value of layout elements. The second verification parameter includes the symmetry structure judgment value and the deconstruction region judgment value. Identifying the interference degree includes: inputting a feature vector into at least one evaluation item defined in the evaluation model to calculate the evaluation result; and when the evaluation result is less than or equal to zero, labeling the component in the feature vector corresponding to the evaluation item as the interference degree. Determining grouped interference includes: arranging all components labeled as interference degrees into an interference degree sequence; and when consecutive interference degree values ​​in the interference degree sequence show a preset decreasing trend, determining the interference degree that forms the decreasing trend as grouped interference. Determining whether grouped interference is biased includes: for each grouped interference, calculating its proportion in the total interference, defining the proportion as the bias parameter corresponding to that grouped interference; and comparing the bias parameter with a preset matching parameter to determine whether the corresponding grouped interference is biased.

2. The method for optimizing the layout of a planar design according to claim 1, characterized in that, The method further includes a step for determining matching parameters, the step of which includes performing an iterative matching determination, in a single iteration: when a positive matching condition is determined to be met, the matching parameters are incremented based on a bias parameter to obtain updated matching parameters for the next iteration; And when it is determined that the reverse matching condition is met, the first parameter value that does not meet the forward matching condition is selected from the set of matching parameters used in previous forward matching, and the parameter value is determined as the final matching parameter, and the iteration is terminated.

3. The method for optimizing a floor plan layout according to claim 2, characterized in that, The generated planar layout optimization scheme includes: When grouped interference is determined to be biased, the preset optimization order of ungrouped interference is adjusted and optimized based on the bias parameter, and the ungrouped interference is optimized according to the adjusted optimization order to generate a planar layout optimization scheme; when grouped interference is determined to be unbiased, optimization operation is performed based on the recorded reference parameters to calculate the optimization bias, and a planar layout optimization scheme is generated based on the optimization bias.

4. A planar design layout optimization system, applied to the method of claim 3, characterized in that, include: The layout state evaluation module is used to determine whether the current layout state of the target plane is in a bad state based on the evaluation model. The interference characteristic analysis module is used to analyze the feature vectors corresponding to the inferior state to identify the interference degree, and to determine whether the grouped interference has bias based on the interference degree; And a layout optimization generation module, which generates a planar layout optimization scheme based on the judgment result of the interference characteristic analysis module on whether the grouped interference has a bias.

5. A planar design layout optimization system according to claim 4, characterized in that, When identifying the degree of interference, the interference characteristic analysis module is specifically used to: input the feature vector into at least one evaluation item defined in the evaluation model to calculate the evaluation result; and when the evaluation result is less than or equal to zero, label the component in the feature vector corresponding to the evaluation item as the degree of interference.

Images