Dynamic design strategy generation method, device and equipment and readable storage medium

Abstract

The invention discloses a dynamic design strategy generation method and device, equipment and a readable storage medium, and belongs to the field of architectural design, and the method comprises the steps: carrying out the matching of a design portrait from a portrait database according to the space preference data of a user; acquiring a corresponding design element correction coefficient from the design element priority correction table according to the basic feature data of the user; and dynamically correcting the priorities of the design elements in the design portrait by utilizing the design element correction coefficient, generating a corrected design element priority list, and generating and outputting a design strategy according to the corrected design element priority list. According to the method, the space preference of the user is accurately captured and analyzed in a data driving mode, and a more detailed and personalized design portrait is formed; and comprehensive analysis is carried out through further data subdivision demands and user feedback, and a data dynamic design feedback and adjustment mechanism is enhanced, so that design-oriented dynamic adjustment is realized, and a design scheme can flexibly respond to changes of user demands.

Description

Technical Field

[0001] The present application relates to the field of architectural design, and specifically relates to a method, device, equipment and readable storage medium for generating a dynamic design strategy. Background Art

[0002] In the field of architectural design, especially when it comes to designing user needs, spatial functions, and usage preferences, traditional design methods rely on the designer's experience and intuition, combined with some macro-market research and user interviews. These methods are often unable to flexibly respond to diverse and rapidly changing user needs, and lack sufficient refinement and personalized decision-making capabilities.

[0003] Currently, some architectural designs have begun to introduce data analysis and intelligent tools to optimize design decisions. However, there are still many shortcomings, such as: (1) Traditional spatial design relies on empirical judgment or static survey data, which makes it difficult to match needs. Many design projects collect data on users’ spatial preferences, usage habits, and other aspects through questionnaire surveys. However, this method relies heavily on manual analysis, and the survey content is usually fixed, making it difficult to accurately adjust the design based on individual user differences.

[0004] (2) Existing user portraits and group divisions lack precise connection with design. Some design fields use algorithms such as cluster analysis to classify users so that they can design at the group level. However, most of these methods focus on static group feature divisions and make it difficult to make design decisions and adjustments based on dynamic data and real-time feedback.

[0005] (3) The priorities of design elements are fixed and cannot be optimized in real time according to demand characteristics. Traditional methods determine the priorities of design elements through subjective judgment and expert scoring. However, they lack systematic data support and are prone to disconnection between design direction and user needs.

[0006] (4) The dynamic design strategy adjustment dimension is too limited. In actual design, the design plan is often completed in multiple iterations, but the modifications and adjustments in each iteration are usually based on user feedback and designer experience, rather than data-driven dynamic feedback. Therefore, it is easy to cause situations that do not match actual needs. Summary of the Invention

[0007] In order to solve the problems existing in existing intelligent building design technologies, this application proposes a dynamic design strategy generation method, device, equipment and readable storage medium.

[0008] This application is implemented through the following technical solutions: A dynamic design strategy generation method, comprising: Matching design portraits from a portrait database based on user spatial preference data; wherein the portrait database stores design portraits of different user groups generated by cluster analysis, and the design portraits include the demand characteristics and preferred design elements of the user groups; Obtaining corresponding design element correction coefficients from a design element priority correction table based on the user's basic characteristic data; wherein the design element priority correction table is generated by analyzing the preference of different classification groups for each design element through logistic regression; Dynamically modifying the priorities of the design elements in the design portrait using the design element modification coefficients to generate a modified design element priority list; A design strategy is generated and outputted based on the revised design element priority list.

[0009] In some implementations, the process of generating the design portrait includes: Collect a large amount of user basic feature data and their spatial preference data and perform pre-processing; Clustering algorithms are used to perform cluster analysis on the preprocessed data to divide users into user groups with similar spatial needs and preferences; Based on the cluster analysis results, a design portrait is generated for each user group and stored in the portrait database.

[0010] In some embodiments, the process of generating the design element priority correction table includes: Obtain detailed design requirement data for different user groups and determine characteristic classification variables; Dividing the model into different feature classification groups according to the feature classification variables, performing logistic regression analysis on the design elements of the different feature classification groups, and determining the preference of the different feature classification groups for each design element; Based on the results of the logistic regression analysis, a design element priority correction table is generated for each feature classification group, wherein the design element priority correction table includes correction coefficients for each design element for different feature classification groups; The logistic regression analysis process includes: Obtain the selection of a design element and different feature classification groups; Taking the preference of design elements as the dependent variable and multiple feature classification groups as independent variables, a regression function model is established: logit(Pr)=β0+β1X1+β2X2+…+βkXk; Where logit(Pr) refers to the logarithmic probability function, logit(Pr)=logit(Pr)=log(Pr / (1-Pr)), Pr is the probability of the dependent variable occurring, and 1-Pr is the probability of the dependent variable not occurring; β1, β2, ... βk are the regression coefficients of the respective variables; X1, X2, ... Xk are the independent variables; β0 is the baseline preference of the control group; Use historical data fitting to obtain the regression coefficients of each variable in the regression function model; According to the regression coefficient of each variable, the correction coefficient corresponding to each variable is calculated, so as to obtain the correction coefficient of each characteristic classification group for the design element.

[0011] In some embodiments, the design element priority correction table generation process further includes: The correction coefficients in the generated design element priority correction table are verified and optimized using cross-validation technology.

[0012] In some embodiments, the matching process includes: A similarity algorithm is used to calculate the similarity between the user's spatial preference data and all the design portraits in the portrait database, and the design portrait with the highest similarity is taken as the final matching result.

[0013] In some embodiments, the dynamic correction process includes: The matched design portrait is combined with the obtained design element correction coefficient to calculate the final design element priority, and the priority is sorted, and finally the design element priority list of the user is output.

[0014] In a second aspect, the present application proposes a dynamic design strategy generation device, comprising: A matching unit, which matches a design portrait from a portrait database based on the user spatial preference data; wherein the portrait database stores design portraits of different user groups generated by cluster analysis, and the design portraits include the demand characteristics and preferred design elements of the user groups; The extraction unit obtains a corresponding design element correction coefficient from a design element priority correction table based on the user basic characteristic data; the design element priority correction table is generated by analyzing the preference of different classification groups for each design element through logistic regression; a dynamic correction unit, which dynamically corrects the priorities of the design elements in the design portrait using the design element correction coefficients to generate a corrected design element priority list; And, a generating unit generates and outputs a design strategy according to the revised design element priority list.

[0015] In some embodiments, the device further comprises: Portrait database, used to store design portraits of all user groups.

[0016] In a third aspect, the present application proposes an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any one of the implementations of the above-mentioned dynamic design strategy generation method when executing the computer program.

[0017] In a fourth aspect, the present application proposes a computer-readable storage medium having a computer program stored thereon, which implements any one of the implementations of the above-mentioned dynamic design strategy generation method when executed by a processor.

[0018] A dynamic design strategy generation method proposed in this application accurately captures and analyzes users' spatial preferences in a data-driven manner, forming a more detailed and personalized design portrait to guide the design direction. It solves the problem that traditional spatial demand analysis often ignores the diversity of spatial preferences and functional requirements, resulting in the design scheme may not fully meet the personalized needs of different users; it also enhances the data dynamic design feedback and adjustment mechanism through further data segmentation requirements (such as age, gender, functional requirements, etc.) and user feedback for comprehensive analysis, thereby realizing dynamic adjustment of design guidance, enabling design schemes to flexibly respond to changes in user needs and achieve continuous optimization of the design process, solving the problem that existing designs are multi-dimensional and static, and once design decisions are made, it is difficult to effectively adjust them according to real-time feedback and changing user needs; in addition, through systematic data support and analysis, this application can more scientifically and reliably determine the priority of design elements, reduce subjective bias, and thus achieve more scientific and accurate design decisions.

[0019] The method of this application has high flexibility and scalability, allowing users in different fields to use the same data-driven design optimization method to achieve cross-industry applications.

[0020] Correspondingly, a dynamic design strategy generation device, electronic device, and computer-readable storage medium proposed in this application also have the same technical effects as above. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the embodiments of the present application, constitute a part of the present application, and do not constitute a limitation of the embodiments of the present application. In the drawings: Figure 1 A schematic diagram of the flow of the dynamic design strategy generation method proposed in an embodiment of the present application; Figure 2 This is a schematic structural block diagram of the dynamic design strategy generation device proposed in an embodiment of the present application; Figure 3This is a schematic diagram of the architecture of the dynamic design strategy generation system proposed in an embodiment of the present application; Figure 4 This is a block diagram of the electronic device architecture proposed in the embodiment of the present application; Figure 5 Schematic diagram of the computer-readable storage medium proposed in this application embodiment Reference numerals and corresponding component names: 200-Dynamic design strategy generation device, 201-Matching unit, 202-Extraction unit, 203-Dynamic correction unit, 204-Generation unit, 205-Portrait database, 300-Dynamic design strategy generation system, 301-Input device, 302-Output device, 303-Processor A, 304-Memory A, 400-Electronic device, 410-Memory B, 420-Processor B, 411-Computer program A, 500-Computer-readable storage medium, 511-Computer program B. DETAILED DESCRIPTION

[0022] Hereinafter, the terms "include" or "may include" as used in various embodiments of the present application indicate the presence of an invented function, operation, or element, and do not limit the addition of one or more functions, operations, or elements. In addition, as used in various embodiments of the present application, the terms "include," "have," and their cognates are intended only to indicate specific features, numbers, steps, operations, elements, components, or combinations of the foregoing, and should not be understood as excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing or the possibility of adding one or more features, numbers, steps, operations, elements, components, or combinations of the foregoing.

[0023] In various embodiments of the present application, the expression "or" or "at least one of A or / and B" includes any or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A or / and B" may include A, may include B, or may include both A and B.

[0024] The expressions (such as "first", "second", etc.) used in the various embodiments of the present application may modify the various constituent elements in the various embodiments, but may not limit the corresponding constituent elements. For example, the above expressions do not limit the order and / or importance of the elements. The above expressions are only used to distinguish one element from other elements. For example, a first user device and a second user device indicate different user devices, although both are user devices. For example, without departing from the scope of the various embodiments of the present application, a first element may be referred to as a second element, and similarly, a second element may also be referred to as a first element.

[0025] It should be noted that when a component is described as being “connected” to another component, the first component may be directly connected to the second component, and a third component may be “connected” between the first and second components. Conversely, when a component is described as being “directly connected” to another component, it can be understood that there is no third component between the first and second components.

[0026] The terms used in the various embodiments of the application are only used to describe the purpose of specific embodiments and are not intended to limit the various embodiments of the application. As used herein, the singular form is intended to also include the plural form, unless the context clearly indicates otherwise. Unless otherwise limited, all terms used here (including technical terms and scientific terms) have the same meaning as the meaning generally understood by those of ordinary skill in the art of the application. The terms (such as the terms defined in the dictionary generally used) will be interpreted as having the same meaning as the contextual meaning in the relevant technical field and will not be interpreted as having idealized meaning or too formal meaning, unless clearly defined in the various embodiments of the application.

[0027] In order to make the objectives, technical solutions and advantages of this application more clear, the present application is further described in detail below in conjunction with examples and drawings. The schematic implementation methods of this application and their descriptions are only used to explain this application and are not intended to limit this application.

[0028] Example 1: Existing architectural designs typically divide users into static, overly simplified groups and fail to fully consider individual differences among users; traditional spatial demand analysis typically ignores the diversity of spatial preferences and functional requirements, resulting in design solutions that may not fully meet the personalized needs of different users. At the same time, existing designs are mostly static, and once design decisions are made, it is difficult to make effective adjustments based on real-time feedback and changing user needs. In addition, in current designs, the weights and priorities of design elements usually rely on the designer's experience and judgment. This subjectivity can easily lead to a situation where the design strategy does not match actual needs. In response to the above problems, this example proposes a dynamic design strategy generation method.

[0029] like Figure 1 As shown, the method proposed in this embodiment includes the following steps: Step 110: Match design portraits from a portrait database based on the user space preference data. The portrait database stores design portraits of different user groups generated through cluster analysis, and the design portraits include the demand characteristics and preferred design elements of the user groups.

[0030] Step 120: Obtain corresponding design element correction coefficients from a design element priority correction table based on the user's basic characteristic data. The design element priority correction table is generated by analyzing the preference of different classification groups for each design element through logistic regression.

[0031] Step 130 : Dynamically correct the priorities of the design elements in the design portrait using the design element correction coefficients to generate a corrected design element priority list.

[0032] Step 140: Generate and output a design strategy based on the revised design element priority list.

[0033] Furthermore, the generation process of the design portrait is as follows: Step 111: Collect a large amount of user basic feature data and spatial preference data.

[0034] Basic user characteristic data primarily includes age, gender, occupation, etc.; spatial preference data includes preferences for natural elements, spatial layout, lighting, etc. Optionally, step 111 may also collect historical user behavior data (e.g., projects participated in, feedback records, etc.) and psychological and emotional data (e.g., emotional reactions to the space, etc.). It should be noted that this data can be collected from historical questionnaires, historical projects, the internet, and other channels. The specific acquisition methods can utilize conventional techniques in the art and will not be elaborated on here.

[0035] Step 112: pre-process the collected data.

[0036] The preprocessing process mainly includes: cleaning missing values ​​and outliers, data standardization, etc. In order to ensure the consistency and accuracy of the data, feature engineering is performed when necessary, such as converting some categorical variables into numerical variables (for example, converting specific choices in spatial preferences into numerical labels).

[0037] Step 113 : Perform cluster analysis on the pre-processed data using a clustering algorithm to divide the users into user groups with similar spatial requirements and preferences.

[0038] This embodiment can adopt the K-means clustering algorithm, DBSCAN algorithm, etc. Among them, taking the K-means clustering algorithm as an example, based on user feature data (such as spatial preferences, basic features, etc.), an appropriate K value is selected for clustering, and users are divided into different groups, such as "private healing type" and "open social type", etc. Each group represents users with similar spatial needs and preferences.

[0039] Step 114: Based on the cluster analysis results, a design portrait is generated for each user group and stored in a portrait database.

[0040] This design profile includes the spatial demand characteristics of the group (i.e., profile categories), as well as key preferred design elements (such as natural light and privacy needs) and functional requirements corresponding to each spatial demand characteristic, providing more comprehensive and reliable data support for subsequent design optimization. Key preferred design elements are selected based on the "P-value significance" of several design element analysis items in cluster analysis. At a 5% significance level (i.e., when P < 0.05), the association is considered significant. For example, there may be 29 original design elements, but after clustering, only 6 are found to determine the clustering results (spatial demand characteristics). These 6 elements are therefore considered key preferred design elements.

[0041] In actual application, similar design portraits can be matched from the portrait database based on a user's spatial preference data. Specifically, a similarity algorithm can be used for matching, that is, the similarity between the user's spatial preference data and all design portraits in the portrait database is calculated respectively, and the design portrait with the highest similarity is taken as the final matching result, so as to preliminarily determine the user's spatial demand characteristics (that is, portrait category) and the corresponding key preference design elements.

[0042] Optionally, the portrait database can also be dynamically updated and optimized.

[0043] Furthermore, the design element priority correction table generation process is as follows: Step 121 : Obtain detailed design requirement data of different user groups and determine feature classification variables.

[0044] Among them, the detailed design demand data of the user group includes the importance the group attaches to different design elements (such as functional layout, spatial privacy, leisure space needs, etc.).

[0045] The user group's age, gender, occupation and other characteristics can be used as classification variables to segment design needs. For example, the user group's age can be used as a classification variable, such as 18-30 years old, 31-45 years old, and over 45 years old, to obtain the needs of different age groups for segmentation.

[0046] Step 122 , dividing the feature classification variables into different feature classification groups, performing logistic regression analysis on the design elements of the different feature classification groups, and determining the preference of the different feature classification groups for each design element.

[0047] Logistic regression analysis was used to determine the preference of different feature classification groups for each design element. The specific process included: Data screening and preparation: Obtain the selection of a certain design element and different feature classification groups; for example, the design element is selected as "indoor plant configuration", and the different feature classification groups are different age groups (such as "18-30 years old, 31-40 years old, 41-50 years old, and over 51 years old"). The data type is the variable "0 or 1", 0 means dislike, and 1 means like.

[0048] Determine the regression model variables: the dependent variable Y is the design preference choice (0 or 1), and the independent variable X is a categorical variable, such as different age groups.

[0049] Establish a model and perform the fitting operation: logit(Pr)=β0+β1X1+β2X2+…+βkXk. Here, logit(Pr) refers to the logarithmic probability function, logit(Pr)=log(Pr / (1-Pr)). Pr is the probability of the dependent variable occurring (i.e., the probability of preferring a design element), and 1-Pr is the probability of the dependent variable not occurring (i.e., the probability of preferring not to choose a design element). β1, β2, …, βk are the regression coefficients of the respective variables; X1, X2, …, Xk are the independent variables. β0 is the baseline preference for the control group. When studying the relationship between the first experimental group and the control group, β1 is 1, and the remaining regression coefficients are 0. When fitting data using a logistic regression model, the regression coefficients are automatically estimated to minimize the error and achieve the best fit. For example, the 18-30 age group is used as the control group, and the other age groups are used as experimental groups for comparison. Under the condition that β0 remains unchanged, the model calculates a corresponding regression coefficient (β1, β2, β3) for each experimental group. If β1 is negative, it means that the preference of the 31-40 age group is lower than that of the 18-30 age group.

[0050] The correction factor is then calculated based on the regression coefficient obtained from the fitted regression. Specifically, the correction factor OR is calculated by exponentially increasing the regression coefficient (i.e., exp(β)).

[0051] According to the above process, the degree of influence of different feature classification groups on each design element can be determined, and the correction coefficient of each design element on the requirements of different feature classification groups can be obtained.

[0052] Results Analysis: Analyze whether the independent variable X is significant (P < 0.05) to explore its influence on the dependent variable Y. Analyze the P value (a statistic indicating whether the regression coefficient is significant) and the correction factor (OR) to compare and analyze the degree of influence of the independent variable X on the dependent variable Y. This example uses the control group's preference as a reference and determines the degree of difference in preference between the experimental group and the control group based on the correction factor (OR). The significance of the experimental group's preference compared to the control group is then analyzed based on the P value. If significant, the preference difference between the experimental and control groups is considered significant; otherwise, the preference difference between the experimental and control groups is not significant. Based on this, if the control group prefers a design element, then the experimental group, which has no significant difference in preference, will also prefer that design element. Conversely, the experimental group, which has a significant difference in preference, will not prefer that design element. For example, for the 41-50 age group, the regression coefficient is -1.273, the OR value is 0.28, and the P value is 0.003. An OR value of 0.28 indicates that the probability of preference in the 41-50 age group is only 28% of that in the 18-30 age group. Since the P value = 0.003, which is less than 0.05, the regression coefficient is significant, indicating that the 41-50 age group does have significantly lower design factor preferences than the 18-30 age group.

[0053] Step 123: Generate a design element priority correction table for each feature classification group based on the logistic regression analysis results.

[0054] Specifically, based on the correction coefficient OR in the logistic regression analysis results, the weight correction value of each design element under each characteristic classification group is determined.

[0055] The correction coefficient (OR) from the logistic regression analysis results can be used to assign values, thereby generating a table of corrections to design element priorities. For example, for the "Indoor Plant Configuration" section, the control group for the 18-30 age group is assigned a weight of 1, the 31-40 age group is assigned a weight of 0.9, the 41-50 age group is assigned a weight of 0.3, and the 51 and older age group is assigned a weight of 0.1. Table 1 provides an example of a correction table for the design element "Indoor Plants as Natural Elements" for each age group.

[0056] Table 1

[0057] Optionally, after the design element priority correction table is established, it can be optimized using cross-validation techniques (such as K-fold cross-validation). The specific process is as follows: Cross-validation is performed on different data sets. Through multiple iterations and verifications, the final correction coefficient is determined to ensure the optimal design match of the system, thereby improving the accuracy of the design strategy, effectively reducing the risk of overfitting, and verifying the stability and reliability of the model.

[0058] For example, for the 18-30 age group, based on preliminary data analysis, the priority of "indoor plant placement" should be increased, with a recommended correction factor of 1.0. To verify the reliability of the correction factor for the 18-30 age group's preference for "indoor plant placement," the data for this group was divided into N parts. Each time, the logistic regression model was trained using the first N-1 data samples, and the correction factor value was calculated. The final data sample was then used to verify the reliability of the revised design factor priorities. Based on the verification results, the correction factor was optimized to obtain the final correction factor. For an N of 5, the cross-validation example shown in Table 2 was obtained.

[0059] Table 2

[0060] Table 2 shows that the correction coefficient averaged 1.0, with a narrow range (0.8-1.2), indicating a stable logistic regression model. The average accuracy was 80%, confirming the effectiveness of the correction rule. Ultimately, the correction coefficient for individuals aged 18-30 was set to 1.0 to improve reliability.

[0061] Optionally, the design element priority revision table may be dynamically updated and optimized.

[0062] Furthermore, the dynamic correction process in step 130 is specifically as follows: The design profile matched in step 110 is combined with the design element correction coefficients obtained in step 120 to calculate the final design element priority. For example, if the design profile matched in step 110 is "private healing type," the preferred design element for this group includes "privacy space." After adjusting for age group, the priority of the relevant design element is increased accordingly.

[0063]

[0064] Among them, the final priority adjustment parameter adopts the multiplication superposition form, which is expressed as the product relationship of the weight correction values ​​of n features; Indicates the i The P value corresponding to each feature.

[0065] For the weight adjustment values ​​of different features, only those with significant P values ​​(P < 0.05) are retained. Insignificant features are weighted as 1 (i.e., have no impact on priority). For example, the age adjustment value (OR = 1.8, P = 0.02) and the gender adjustment value (OR = 1.2, P = 0.12) have an OR value of 1.8 for the age-based adjustment, while the gender-based adjustment value is 1. Therefore, the final priority adjustment parameter = 1.8 × 1 = 1.8. The design element priorities are then adjusted based on this final priority adjustment parameter to determine the final priority of each design element. This is then prioritized and ultimately outputted as a priority list for the user, ensuring that the design solution is optimized based on user needs. The priority list will cover all aspects of the design elements, such as spatial layout, lighting design, and material selection.

[0066] Furthermore, the design strategy generation process in step 140 is as follows: Based on the optimized list of design elements, design strategies are generated for specific users. For example, for the "private healing" group, the design strategy may emphasize spatial privacy, the introduction of natural elements, and quiet leisure areas; for the "open social" group, the design strategy may focus on social interaction areas, open space layout, and flexible functional zoning.

[0067] This design strategy provides designers with a clear design direction while also enabling dynamic adjustments based on new feedback and data during the design process.

[0068] The method proposed in this embodiment uses a data-driven approach to accurately capture and analyze users' spatial preferences, forming more detailed and personalized design profiles. These profiles then guide the design direction of the proposed solution. Further, through logistic regression analysis of design elements, the priorities of design elements can be adjusted based on the needs of different groups and users, achieving dynamic correction of design element priorities. This allows the design solution to flexibly respond to changing user needs and continuously optimize the design process. Furthermore, through systematic data support and analysis, this embodiment allows for a more objective and scientific determination of design element priorities, reducing subjective bias and ultimately enabling more scientific and accurate design decisions.

[0069] The method proposed in this embodiment has strong versatility. By adjusting the types of user data and design elements, it can be easily adapted to the needs of different fields. For example, in interior design, it can be done by adjusting elements such as space layout, material selection, and color matching; in space optimization, it can be optimized based on user behavior data, space display requirements, traffic flow planning, and other elements.

[0070] This embodiment also proposes an embodiment of a dynamic design strategy generating device 200, such as Figure 2 As shown, the dynamic design strategy generating device 200 includes: Matching unit 201 matches design profiles from a profile database based on the user's spatial preference data. The profile database stores design profiles for different user groups generated through cluster analysis. These profiles include user group demand characteristics and preferred design elements. The specific matching method and design profile generation process are described in the above method and will not be further elaborated here.

[0071] Extraction unit 202 retrieves corresponding design element correction coefficients from a design element priority correction table based on the user's basic characteristic data. The design element priority correction table is generated through a logistic regression analysis of the preferences of different classification groups for each design element. The specific process for establishing the design element priority correction table is described in the above method and will not be further elaborated here.

[0072] The dynamic correction unit 203 uses the design element correction coefficient to dynamically correct the priority of the design elements in the design portrait and generate a corrected design element priority list. The specific dynamic correction process is as described in the above method and will not be repeated here.

[0073] Furthermore, the generating unit 204 generates and outputs a design strategy based on the revised design element priority list.

[0074] In another embodiment, the dynamic design strategy generating apparatus 200 further includes: The portrait database 205 stores the design portraits of all user groups. The generation process of the design portraits is as described in the above method and will not be repeated here.

[0075] This embodiment also proposes a dynamic design strategy generation system 300, such as Figure 3 As shown, the dynamic design strategy generation system 300 proposed in this embodiment includes: Input device 301, output device 302, processor A303 and memory A304; wherein the number of processor A303 and memory A304 can be one or more, Figure 3 The input device 301, the output device 302, the processor A303 and the memory A304 can be connected by a bus or other means. Figure 3 The bus connection is taken as an example.

[0076] By calling the operation instructions stored in the memory A304, the processor A303 is configured to perform the following steps: Matching design portraits from a portrait database based on user spatial preference data; wherein the portrait database stores design portraits of different user groups generated through cluster analysis, and the design portraits include the demand characteristics and preferred design elements of the user groups; According to the basic characteristic data of users, the corresponding design element correction coefficient is obtained from the design element priority correction table; wherein the design element priority correction table is generated by analyzing the preference of different classification groups for each design element through logistic regression; Using the design element correction coefficient, the priority of the design elements in the design portrait is dynamically corrected to generate a corrected design element priority list; Based on the revised design element priority list, generate and output the design strategy.

[0077] Optionally, by calling the operation instructions stored in the memory A304, the processor A303 is also used to execute any implementation method in the corresponding embodiments of the above method.

[0078] This embodiment also provides an embodiment of an electronic device 400, such as Figure 4 As shown, the electronic device 400 includes: a memory B410, a processor B420, and a computer program A411 stored in the memory B410 and executable on the processor B420. When the processor B420 executes the computer program A411, the following steps are implemented: Matching design portraits from a portrait database based on user spatial preference data; wherein the portrait database stores design portraits of different user groups generated through cluster analysis, and the design portraits include the demand characteristics and preferred design elements of the user groups; According to the basic characteristic data of users, the corresponding design element correction coefficient is obtained from the design element priority correction table; wherein the design element priority correction table is generated by analyzing the preference of different classification groups for each design element through logistic regression; Using the design element correction coefficient, the priority of the design elements in the design portrait is dynamically corrected to generate a corrected design element priority list; Based on the revised design element priority list, generate and output the design strategy.

[0079] Optionally, when the processor B420 executes the computer program A411, any implementation method corresponding to the embodiments of the above method can be implemented.

[0080] It should be noted that the electronic device proposed in this embodiment is a device used to implement the above method. Therefore, based on the above method proposed in this embodiment, technical personnel in this field can understand the specific implementation of the electronic device of this embodiment and its various variations. Therefore, how the electronic device specifically implements the above method will not be introduced in detail here. As long as the electronic device used by technical personnel in this field to implement the above method falls within the scope of protection to be protected by this application.

[0081] This embodiment also provides an embodiment of a computer-readable storage medium 500, such as Figure 5 As shown, the computer readable storage medium 500 stores a computer program B511. When the computer program B511 is executed by the processor, the following steps are implemented: Matching design portraits from a portrait database based on user spatial preference data; wherein the portrait database stores design portraits of different user groups generated through cluster analysis, and the design portraits include the demand characteristics and preferred design elements of the user groups; According to the basic characteristic data of users, the corresponding design element correction coefficient is obtained from the design element priority correction table; wherein the design element priority correction table is generated by analyzing the preference of different classification groups for each design element through logistic regression; Using the design element correction coefficient, the priority of the design elements in the design portrait is dynamically corrected to generate a corrected design element priority list; Based on the revised design element priority list, generate and output the design strategy.

[0082] Optionally, when the computer program B511 is executed by a processor, it can implement any implementation method in the embodiments corresponding to the above method.

[0083] It should be noted that, in the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0084] Example 2: This example uses a certain interior design as an example to illustrate the application of the dynamic design strategy generation method proposed in Example 1. The specific process is as follows: First, by collecting and preprocessing data and then conducting basic data analysis, we can generate user design portraits based on spatial preference data. From the massive basic data, we can extract the intended population, important demand characteristics, and typical preference design elements, as shown in Table 3, which shows examples of four types of cluster portraits and typical preference design elements.

[0085] Table 3

[0086] Note: *** represents a significance level of 1%; the F (explanatory power) value is used to evaluate whether the differences between different categories of design elements are significant; the P (significance) value indicates whether the differences between different categories of design elements are statistically significant. If the P value is less than 0.05 (at a significance level of 5%), it means that there are significant differences between different categories in these design elements.

[0087] Then, we will refine the user segmentation data and prioritize important design elements: The following is a logistic regression analysis of data from different age groups for a very important design element, "Indoor plants as natural elements." The 18-30 age group is used as the control group, and the other three age groups are used as the experimental group. The correction coefficient is calculated as the exponential of the regression coefficient. The analysis results are shown in Table 4: Table 4

[0088] Note: *** represents a significance level of 1%; the regression coefficient β represents the degree of influence of the independent variable (such as age group) on the dependent variable, and its sign (positive or negative) indicates that an increase (or decrease) in the independent variable will have a positive or negative effect on the dependent variable; the standard error is used to measure the accuracy of the regression coefficient β; the smaller the value, the more accurate the estimate of the regression coefficient β; the Wald statistic is used to test whether the regression coefficient β is significant; the larger the value, the stronger the significance of the regression coefficient β; df is used to determine the distribution of the Wald statistic; the P value is used to determine whether the regression coefficient is significant; if the P value is less than 0.05, it means it is significant; the OR correction coefficient is the exponential result of the regression coefficient; if the OR is greater than 1, it means that an increase in the independent variable will increase the probability of the dependent variable occurring; the 95% confidence interval of the OR value is used to estimate the reliability of the OR; if the confidence interval does not contain 1, it means that the OR value is significant.

[0089] Table 4 shows that the baseline group (18-30 years old) showed a preference for "natural indoor plants" (OR = 1). This group showed a higher demand for indoor plants, likely due to a preference for a natural, fresh atmosphere among younger individuals. The constant term (β = -0.083, P = 0.773) for the experimental group (31-40 years old) was not significant, indicating no significant difference in preference for "natural indoor plants" between the 31-40 age group and the 18-30 age group. This suggests that the 31-40 age group has similar demands for indoor plants as the 18-30 age group, suggesting that adding natural elements to decorate spaces may be appropriate. According to the constant term of the 41-50 age group in the experimental group (β=-1.273, P=0.003***, OR=0.28), the OR value is 0.28, indicating that the probability of the 41-50 age group preferring indoor plants is only 28% of that of the 18-30 age group, and the P value is less than 0.05, indicating that the difference is statistically significant. Therefore, the preference of the 41-50 age group for "indoor plants in the application of natural elements" is significantly lower than that of the 18-30 age group; this shows that the 41-50 age group has a lower demand for indoor plants and may be more concerned with practicality or simple space design. Similarly, for the group over 51 years old, the constant term (β=-2.12, P=0.001***, OR=0.12) is significant. The probability of the group over 51 years old preferring indoor plants is only 12% of that of the group aged 18-30 years old. The P value is 0.001, which is less than 0.05, indicating that the difference is statistically significant, indicating that the group over 51 years old has a significantly lower preference for "indoor plants in natural element applications" than the group aged 18-30 years old, and drivers over 51 years old have the lowest demand for indoor plants.

[0090] The OR correction coefficient from the logistic regression results can be rounded to the nearest integer. For example, for the "Indoor Plant Arrangement" section, the OR correction coefficient for the 18-30 age group is 1; the 31-40 age group is 0.9; the 41-50 age group is 0.3; and the 51 and older age group is 0.1. This yields a correction table for the design element priorities, as shown in Table 5.

[0091] Table 5

[0092] Finally, make data decisions: The input data includes the user's important spatial preference data and basic feature data. The data structure is consistent with the previous data processing. For example, the user's preference data includes natural elements_indoor plants = 1, rest area_open interaction = 1; the age group is: 18-30 years old.

[0093] Based on the user's important space preference data, the "open social type" is matched; the core design elements of the "open social type" are "open interactive rest area" and "free activity space".

[0094] Dynamic Priority Adjustment: Because the user is between 18 and 30 years old, based on the results of the previous data analysis, the priority of "Diverse Leisure Space" needs to be increased. Optionally, cross-validation techniques can be used to optimize this adjustment factor, ultimately determining a correction factor of 1.0.

[0095] Finally, the output design strategy is that the core design elements determined based on the user's spatial preferences are: open rest area + free activity space; optimization suggestions: add diversified leisure functions (such as game area, social corner).

[0096] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0097] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0098] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0099] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1The steps for the function specified in one or more boxes.

[0100] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of this application. It should be understood that the above description is only the specific implementation methods of this application and is not intended to limit the scope of protection of this application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of this application should be included in the scope of protection of this application.

Claims

1. A dynamic design strategy generation method, characterized in that: include: Match design portraits from the portrait database based on user space preference data; The portrait database stores design portraits of different user groups generated through cluster analysis, and the design portraits include the demand characteristics and preferred design elements of the user groups; According to the user's basic characteristic data, the corresponding design element correction coefficient is obtained from the design element priority correction table; The design element priority correction table is generated by analyzing the preference of different classification groups for each design element through logistic regression; Dynamically modifying the priorities of the design elements in the design portrait using the design element modification coefficients to generate a modified design element priority list; A design strategy is generated and outputted based on the revised design element priority list.

2. A dynamic design strategy generation method according to claim 1, characterized in that: The generation process of the design portrait includes: Collect a large amount of user basic feature data and their spatial preference data and perform pre-processing; Clustering algorithms are used to perform cluster analysis on the preprocessed data to divide users into user groups with similar spatial needs and preferences; Based on the cluster analysis results, a design portrait is generated for each user group and stored in the portrait database.

3. A dynamic design strategy generation method according to claim 1, characterized in that: The design element priority correction table generation process includes: Obtain detailed design requirement data for different user groups and determine characteristic classification variables; Dividing the model into different feature classification groups according to the feature classification variables, performing logistic regression analysis on the design elements of the different feature classification groups, and determining the preference of the different feature classification groups for each design element; Based on the results of the logistic regression analysis, a design element priority correction table is generated for each feature classification group, wherein the design element priority correction table includes correction coefficients for each design element for different feature classification groups; The logistic regression analysis process includes: Obtain the selection of a design element and different feature classification groups; Taking the preference of design elements as the dependent variable and multiple feature classification groups as independent variables, a regression function model is established: logit(Pr)=β0+β1X1+β2X2+…+βkXk; Where logit(Pr) refers to the logarithmic probability function, logit(Pr)=logit(Pr)=log(Pr / (1-Pr)), Pr is the probability of the dependent variable occurring, and 1-Pr is the probability of the dependent variable not occurring; β1, β2, ... βk are the regression coefficients of the respective variables; X1, X2, ... Xk are the independent variables; β0 is the baseline preference of the control group; Use historical data fitting to obtain the regression coefficients of each variable in the regression function model; According to the regression coefficient of each variable, the correction coefficient corresponding to each variable is calculated, so as to obtain the correction coefficient of each characteristic classification group for the design element.

4. A dynamic design strategy generation method according to claim 3, characterized in that: The design element priority correction table generation process further includes: The correction coefficients in the generated design element priority correction table are verified and optimized using cross-validation technology.

5. A dynamic design strategy generation method according to any one of claims 1 to 4, characterized in that: The matching process includes: A similarity algorithm is used to calculate the similarity between the user's spatial preference data and all the design portraits in the portrait database, and the design portrait with the highest similarity is taken as the final matching result.

6. A dynamic design strategy generation method according to any one of claims 1 to 4, characterized in that: The dynamic correction process includes: The matched design portrait is combined with the obtained design element correction coefficient to calculate the final design element priority, and the priority is sorted, and finally the design element priority list of the user is output.

7. A dynamic design strategy generation device, characterized in that: include: The matching unit matches the design portrait from the portrait database based on the user's spatial preference data; The portrait database stores design portraits of different user groups generated through cluster analysis, and the design portraits include the demand characteristics and preferred design elements of the user groups; The extraction unit obtains the corresponding design element correction coefficient from the design element priority correction table according to the user basic characteristic data; The design element priority correction table is generated by analyzing the preference of different classification groups for each design element through logistic regression; a dynamic correction unit, which dynamically corrects the priorities of the design elements in the design portrait using the design element correction coefficients to generate a corrected design element priority list; And, a generating unit generates and outputs a design strategy according to the revised design element priority list.

8. A dynamic design strategy generating device according to claim 7, characterized in that: Also includes: Portrait database, used to store design portraits of all user groups.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the dynamic design strategy generation method according to any one of claims 1 to 6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the dynamic design strategy generation method according to any one of claims 1 to 6 is implemented.

Images