A dynamic design strategy generation method, device, equipment and readable storage medium

Abstract

The application discloses a dynamic design strategy generation method, device and equipment and a readable storage medium, and belongs to the field of architectural design. The method comprises the following steps: matching a design image from an image database according to user space preference data; obtaining corresponding design element correction coefficients from a design element priority correction table according to user basic characteristic data; dynamically correcting the priority of design elements in the design image by using the design element correction coefficients, generating a corrected design element priority list, and generating a design strategy and outputting the same according to the corrected design element priority list. The application accurately captures and analyzes the space preference of a user in a data-driven manner, forms a more detailed and personalized design image, and further analyzes the data subdivision requirement and user feedback, enhances the data dynamic design feedback and adjustment mechanism, and then realizes dynamic adjustment of the design orientation, so that the design scheme can flexibly respond to the change of the user requirement.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of architectural design, and particularly relates to a dynamic design strategy generation method, device, equipment and readable storage medium. BACKGROUND

[0002] In the field of architectural design, especially in the design involving user needs, space functions and use preferences, the traditional design method relies on the experience and intuition of designers, combined with some macro market research and user interviews. These methods often cannot flexibly cope with diversified and rapidly changing user needs, and lack sufficient fine and personalized decision-making functions.

[0003] At present, some architectural designs have begun to introduce data analysis and intelligent tools to optimize design decisions, but there are still many defects, for example:

[0004] (1) Traditional space design relies on experience judgment or static research data, and it is difficult to match the needs. Many design projects collect user space preferences, use habits and other data through questionnaires, but this method relies on manual analysis, and the research content is usually fixed, and it is difficult to accurately adjust the design according to individual differences of users.

[0005] (2) Existing user portraits and group division lack accurate connection with design. Some design fields use clustering analysis and other algorithms to classify users, so as to design from the group level, but these methods mostly focus on static group feature result division, and it is difficult to make design decisions and adjustments according to dynamic data and real-time feedback.

[0006] (3) The priority of design elements is fixed and cannot be optimized in real time according to demand characteristics. Traditional methods determine the priority of design elements through subjective judgment, expert scoring and other methods, lack of systematic data support, and are prone to design direction and user needs.

[0007] (4) The adjustment dimension of dynamic design strategy is too limited. In actual design, design schemes are often completed in multiple iterations, but each iteration of modification and adjustment is usually based on user feedback and designer experience, rather than dynamic feedback based on data-driven, so it is easy to appear mismatched with actual needs. SUMMARY

[0008] In order to solve the problems existing in the prior art intelligent architectural design technology, the application provides a dynamic design strategy generation method, device, equipment and readable storage medium.

[0009] The application realizes the following technical scheme:

[0010] A dynamic design strategy generation method comprises:

[0011] matching a design image from an image database according to the user spatial preference data; wherein the image database stores design images of different user groups generated by cluster analysis, and the design images include demand characteristics and preference design elements of the user groups;

[0012] obtaining a corresponding design element correction coefficient from a design element priority correction table according to the user basic characteristic data; wherein the design element priority correction table is generated by analyzing the preference degree of different classification groups to each design element by logistic regression;

[0013] correcting the priority of the design elements in the design image dynamically by using the design element correction coefficient, and generating a corrected design element priority list;

[0014] generating a design strategy and outputting according to the corrected design element priority list.

[0015] In some embodiments, the generation process of the design image includes:

[0016] collecting a large amount of user basic characteristic data and spatial preference data and pre-processing;

[0017] performing cluster analysis on the pre-processed data by using a clustering algorithm, and dividing the users into user groups with similar spatial demand and preference;

[0018] generating a design image for each user group based on the cluster analysis result and storing it in the image database.

[0019] In some embodiments, the generation process of the design element priority correction table includes:

[0020] obtaining detailed design demand data of different user groups, and determining characteristic classification variables;

[0021] dividing into different characteristic classification groups according to the characteristic classification variables, performing logistic regression analysis on the design elements of different characteristic classification groups, and determining the preference degree of different characteristic classification groups to each design element;

[0022] generating a design element priority correction table for each characteristic classification group according to the logistic regression analysis result, and the design element priority correction table includes correction coefficients of different characteristic classification groups to each design element;

[0023] wherein the logistic regression analysis process includes:

[0024] obtaining the selection of a design element and different characteristic classification groups;

[0025] Taking the preference selection of the design element as the dependent variable and multiple characteristic classification groups as the independent variables, a regression function model is established:

[0026] logit(Pr)=β0+β1X1+β2X2+…+βkXk;

[0027] wherein, logit(Pr) is a logit function, logit(Pr)= ln(Pr / (1-Pr)), Pr is the probability of the occurrence of the dependent variable, 1-Pr is the probability of the non-occurrence of the dependent variable; β1, β2, … βk are the regression coefficients of the respective independent variables; X1, X2, … Xk are the independent variables; β0 is the baseline preference of the control group;

[0028] The regression coefficients of the independent variables in the regression function model are fitted by using historical data;

[0029] According to the regression coefficients of the independent variables, the correction coefficients corresponding to the independent variables are calculated, so as to obtain the correction coefficients of the design elements of each characteristic classification group.

[0030] In some embodiments, the design element priority correction table generation process further comprises:

[0031] The correction coefficients in the generated design element priority correction table are verified and optimized by using a cross-validation technique.

[0032] In some embodiments, the matching process comprises:

[0033] The similarity algorithm is used to calculate the similarity between the user space preference data and all design images in the image database, and the design image with the highest similarity is taken as the final matching result.

[0034] In some embodiments, the dynamic correction process comprises:

[0035] The matched design image and the obtained design element correction coefficient are combined to calculate the final design element priority, and the priority is sorted to finally output the design element priority list of the user.

[0036] In a second aspect, the present application provides a dynamic design strategy generation device, comprising:

[0037] A matching unit matches a design image from an image database according to user space preference data; wherein the image database stores design images of different user groups generated by cluster analysis, and the design images include the demand characteristics and preferred design elements of the user groups.

[0038] The extraction unit obtains a corresponding design element correction coefficient from a design element priority correction table according to the user basic characteristic data; the design element priority correction table is generated by analyzing the preference degree of different classification groups to each design element through logistic regression;

[0039] The dynamic correction unit dynamically corrects the priority of the design element in the design image by using the design element correction coefficient, and generates a corrected design element priority list;

[0040] The generation unit generates a design strategy according to the corrected design element priority list and outputs the design strategy.

[0041] In some embodiments, the device further comprises:

[0042] An image database for storing design images of all user groups.

[0043] In a third aspect, the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any of the embodiments of the dynamic design strategy generation method when executing the computer program.

[0044] In a fourth aspect, the present application provides a computer readable storage medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement any of the embodiments of the dynamic design strategy generation method.

[0045] The dynamic design strategy generation method provided by the present application accurately captures and analyzes the spatial preferences of users in a data-driven manner, forms more detailed and personalized design images, and guides the design direction. The method solves the problem that the traditional spatial demand analysis often ignores the diversity of spatial preferences and functional requirements, resulting in a design scheme that may not fully meet the individual needs of different users. The method further analyzes the data by further subdividing the requirements (such as age, gender, functional requirements, etc.) and user feedback, enhances the data dynamic design feedback and adjustment mechanism, and then realizes the dynamic adjustment of the design direction, so that the design scheme can flexibly respond to changes in user needs, realize the continuous optimization of the design process, and solve the problem that the existing design is multi-dimensional and static, and once the design decision is made, it is difficult to effectively adjust according to real-time feedback and changing user needs. In addition, the present application can more scientifically and reliably determine the priority of design elements through systematic data support and analysis, reduce subjective bias, and thus realize more scientific and accurate design decisions.

[0046] The method of the present application has high flexibility and scalability, so that users in different fields can use the same data-driven design optimization method to realize cross-field application between industries.

[0047] Correspondingly, the dynamic design strategy generation device, the electronic device and the computer readable storage medium proposed in the application also have the same technical effects as described above. BRIEF DESCRIPTION OF DRAWINGS

[0048] The accompanying drawings, which are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this application, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings:

[0049] Figure 1 The dynamic design strategy generation method flowchart proposed in the embodiments of the application;

[0050] Figure 2 The schematic structural block diagram of the dynamic design strategy generation device proposed in the embodiments of the application;

[0051] Figure 3 The architecture schematic diagram of the dynamic design strategy generation system proposed in the embodiments of the application;

[0052] Figure 4 The architecture block diagram of the electronic device proposed in the embodiments of the application;

[0053] Figure 5 The principle block diagram of the computer readable storage medium proposed in the embodiments of the application

[0054] The reference signs and corresponding component names:

[0055] 200-dynamic design strategy generation device, 201-matching unit, 202-extraction unit, 203-dynamic correction unit, 204-generation unit, 205-image 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

[0056] Hereinafter, the term "include" or "may include" used in various embodiments of the present application indicates the existence of the invented function, operation or element, and does 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 synonyms merely mean to indicate a specific feature, number, step, operation, element, component or combination of the foregoing, and should not be understood as first excluding the existence or addition 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.

[0057] In various embodiments of the present application, the expression "or" or "at least one of A or / and B" includes any and all combinations of the listed terms. For example, the expression "A or B" or "at least one of A or / and B" can include A, can include B, or can include both A and B.

[0058] The expressions used in various embodiments of the present application, such as "first", "second", and the like, can modify various constituent elements in various embodiments, but can 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 used only for the purpose of distinguishing one element from another. For example, the first user device and the second user device indicate different user devices, although both are user devices. For example, a first element can be referred to as a second element, and likewise, a second element can be referred to as a first element, without departing from the scope of various embodiments of the present application.

[0059] It should be noted that if a description connects one constituent element to another constituent element, the first constituent element can be directly connected to the second constituent element, and a third constituent element can be "connected" between the first constituent element and the second constituent element. Conversely, when one constituent element is "directly connected" to another constituent element, it can be understood that there is no third constituent element between the first constituent element and the second constituent element.

[0060] The terms used in various embodiments of the present application are used only for the purpose of describing particular embodiments and are not intended to limit various embodiments of the present application. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Unless otherwise defined, all terms used herein, including technical terms and scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which various embodiments of the present application belong. The terms such as those defined in a generally used dictionary will be interpreted to have the same meaning as the contextual meaning in the relevant technical field and will not be interpreted to have idealized or overly formal meanings, unless clearly defined in various embodiments of the present application.

[0061] In order to make the purposes, technical solutions, and advantages of the present application more clear, further detailed explanations of the present application are made below in conjunction with embodiments and drawings, the illustrative embodiments and explanations thereof are used only for the purpose of explaining the present application and do not limit the present application.

[0062] Embodiment 1:

[0063] Existing architectural design usually divides users into static and oversimplified groups, without fully considering individual differences of users; traditional space demand analysis usually ignores the diversity of space preferences and functional requirements, resulting in design solutions that may not fully meet the individual needs of different users. At the same time, existing designs are mostly static, and once the design decisions are made, it is difficult to effectively adjust according to real-time feedback and changing user needs. In addition, in current designs, the weights and priorities of design elements usually depend on the experience of designers, and this subjectivity can easily lead to a situation where the design strategy does not fit the actual needs. To address the above problems, the embodiment proposes a dynamic design strategy generation method.

[0064] As shown in Figure 1 The method proposed in the embodiment includes the following steps:

[0065] Step 110, according to the user space preference data, match the design portrait from the portrait database. The portrait database stores design portraits of different user groups generated by clustering analysis, and the design portrait includes the demand characteristics and preferred design elements of the user group.

[0066] Step 120, according to the user basic characteristic data, obtain the corresponding design element correction coefficient from the design element priority correction table. The design element priority correction table is generated by analyzing the preference degree of different classification groups to each design element through logistic regression.

[0067] Step 130, use 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.

[0068] Step 140, generate a design strategy according to the corrected design element priority list and output.

[0069] Further, the generation process of the design portrait is as follows:

[0070] Step 111, collect a large amount of user basic characteristic data and space preference data.

[0071] The user basic characteristic data mainly includes age, gender, occupation, etc.; the space preference data includes preference for natural elements, space layout, lighting, etc. Optionally, this step 111 can also collect user historical behavior data (such as participated projects, feedback records, etc.) and psychological emotional data (such as emotional response to space, etc.). It should be noted that these data can be obtained from historical questionnaires, historical projects, networks, etc. The specific acquisition method can use conventional technical means in the art, which will not be described in detail here.

[0072] Step 112, pre-process the collected data.

[0073] 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 as necessary, such as converting some classification variables into numerical variables (for example, converting specific choices in space preference into numerical labels).

[0074] Step 113, using clustering algorithm to analyze the preprocessed data, and dividing users into user groups with similar space needs and preferences.

[0075] This embodiment can use K-means clustering algorithm, DBSCAN algorithm, etc. Taking the K-means clustering algorithm as an example, based on user feature data (such as space preference, basic characteristics, etc.), a suitable K value is selected for grouping, and users are divided into different groups, such as "private healing type" and "open social type". Each group represents users with similar space needs and preferences.

[0076] Step 114, based on the clustering analysis result, generating a design image for each user group and storing it in the image database.

[0077] The design image includes the space demand characteristics of the group (i.e. the image category), the key preference design elements corresponding to each space demand characteristic (such as natural light, privacy demand, etc.), and the functional requirements, etc., providing more comprehensive and reliable data support for subsequent design optimization. Among them, the selection of key preference design elements is determined by the "P value significance" of a number of design element analysis items in clustering analysis. For a 5% significance level, that is, when P<0.05, the correlation is considered significant. For example, there may be 29 original design elements, and only 6 of them can determine the clustering result (space demand characteristics) after clustering, so these 6 are the key preference design elements.

[0078] In actual application process, the space preference data of a certain user can be matched with similar design images from the image database. Specifically, a similarity algorithm can be used for matching, that is, the similarity between the user's space preference data and all design images in the image database is calculated, and the design image with the highest similarity is taken as the final matching result, thereby preliminarily determining the user's space demand characteristics (i.e. the image category) and the corresponding key preference design elements.

[0079] Optionally, the image database can also be dynamically updated and optimized.

[0080] Further, the design element priority correction table generation process is as follows:

[0081] Step 121, obtaining detailed design requirement data of different user groups and determining characteristic classification variables.

[0082] wherein the detailed design requirement data of the user group includes the importance of different design elements (such as functional layout, spatial privacy, and demand for leisure space) to the group.

[0083] The design requirements can be subdivided by taking the characteristics of the user group such as age, gender, and occupation as classification variables. For example, the age of the user group is taken as a classification variable, for example, divided into 18-30 years old, 31-45 years old, and 45 years old and above, and the requirements of different age groups are subdivided.

[0084] Step 122, according to the characteristic classification variable, the design elements of different characteristic classification groups are analyzed by logistic regression analysis, and the preference degree of different characteristic classification groups to each design element is determined.

[0085] The preference degree of different characteristic classification groups to each design element is determined by logistic regression analysis. The specific process includes:

[0086] Data screening and preparation: obtain the selection of a design element and different characteristic classification groups; for example, the design element is selected as "indoor plant configuration", the different characteristic classification groups are different age groups (for example, "18-30 years old, 31-40 years old, 41-50 years old, and 51 years old and above"), and the data type is variable "0 or 1", 0 represents dislike, and 1 represents like.

[0087] Determine the regression model variable: the dependent variable Y is the selection of design preference (0 or 1), and the independent variable X is the classification variable, such as different age groups.

[0088] Establish the model and perform fitting operation: logit(Pr)=β0+β1X1+β2X2+…+βkXk. Wherein, logit(Pr) is the logarithm ratio function, logit(Pr)=ln(Pr / (1-Pr)), Pr is the probability of the dependent variable occurring (i.e. the probability of preferring a certain design element), 1-Pr is the probability of the dependent variable not occurring (i.e. the probability of not preferring a certain design element); β1, β2, … βk are the regression coefficients of the respective independent variables; X1, X2, … Xk are the independent variables; β0 is the baseline preference of the control group, when the first experimental group is compared with the control group, β1 is 1, and the rest of the regression coefficients are 0. When fitting the data using the logistic regression model, the regression coefficients are automatically estimated to minimize the error and obtain the best fitting effect. For example, taking 18-30 years old as the control group and other age groups as the experimental groups for comparison, under the condition that β0 is 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.

[0089] Then the correction coefficient is calculated according to the regression coefficient obtained by fitting regression. Specifically, the correction coefficient OR is calculated by the exponential of the regression coefficient (i.e. exp(β)).

[0090] According to the above process, the influence degree of different feature classification groups on each design element can be determined, and the correction coefficient of each design element for the demand of different feature classification groups is obtained.

[0091] Result analysis: analyze whether the independent variable X is significant (P<0.05) to explore the influence of the independent variable X on the dependent variable Y; analyze the P value (a statistical quantity representing whether the regression coefficient is significant) and the correction coefficient OR, and compare the influence degree of the independent variable X on the dependent variable Y. In this embodiment, the preference of the control group is taken as a reference, and the difference degree of the experimental group relative to the control group is determined according to the correction coefficient OR value; then the preference significance of the experimental group compared with the control group is analyzed, if significant, it is considered that the preference of the experimental group and the control group has significant difference, otherwise the preference of the experimental group and the control group has no significant difference. Based on this, if the control group prefers a certain design element, the experimental group which has no significant difference with the control group also prefers the design element, and vice versa. For example, for the 41-50 group, the regression coefficient is -1.273, the OR value is 0.28, and the P value is 0.003. The OR value is 0.28, which means that the preference probability of the 41-50 age group is only 28% of the 18-30 age group. Since the P value is 0.003, which is less than 0.05, it means that the regression coefficient is significant, which means that the 41-50 age group is significantly lower than the 18-30 age group in design element preference.

[0092] Step 123, generating a design element priority correction table of each feature classification group according to the result of logistic regression analysis.

[0093] Specifically, the weight correction value of each design element under each feature classification group is determined according to the correction coefficient OR in the result of logistic regression analysis.

[0094] The correction coefficient OR in the result of logistic regression analysis can be called to assign values, thereby generating a design element priority correction table. For example, for the "indoor plant configuration" part, the 18-30 age group control group is taken as 1, the 31-40 age group is 0.9, the 41-50 age group is 0.3, and the 51 age group and above is 0.1. Table 1 shows an example of weight correction of the "indoor plant" design element in the "natural element application" of each age group.

[0095] Table 1

[0096]

[0097] Optionally, the design element priority correction table can be optimized using cross-validation techniques (such as K-fold cross-validation) after being established. The specific process is as follows:

[0098] Cross-validation is performed on different data sets, and through multiple iterations and verifications, the final correction coefficient is determined to ensure that the system design matches the best, thereby improving the accuracy of the design strategy, effectively reducing the risk of overfitting, and verifying the stability and reliability of the model.

[0099] For example, for the age group of 18-30 years old, according to the results of the previous data analysis, the priority of "indoor plant configuration" needs to be improved, and the correction coefficient is recommended to be 1.0. To verify whether the correction coefficient of the 18-30 age group's preference for "indoor plant configuration" is reliable, divide the data of the 18-30 age group into N parts, train the logistic regression model with the first N-1 data samples each time, calculate the correction coefficient value, and then use the last data sample to verify the reliability of the corrected design element priority. According to the verification result, optimize the correction coefficient to obtain the final correction coefficient. Taking N as 5 as an example, the cross-validation example shown in Table 2 is obtained.

[0100] Table 2

[0101]

[0102] As shown in Table 2, the average correction coefficient is 1.0, the fluctuation range is small (0.8-1.2), and the specification logistic regression model is stable. The average accuracy is 80%, and the verification correction rule is effective. Finally, the correction coefficient of the 18-30 age group is set to 1.0 to improve the reliability.

[0103] Optionally, the design element priority correction table can be dynamically updated and optimized.

[0104] Further, the dynamic correction process in step 130 is as follows:

[0105] The design image matched in step 110 is combined with the design element correction coefficient obtained in step 120 to calculate the final design element priority. For example, the design image matched in step 110 is "private healing type", and the preferred design elements of this group include "privacy space"; after correction according to the age group, the priority of the related design elements is correspondingly improved.

[0106]

[0107] wherein the final priority adjustment parameter adopts a multiplication superposition form, represented as the product relationship of the weight correction values of n characteristics; represents the P value corresponding to the i-th characteristic.

[0108] For different characteristic weight correction values, only the P-value significant (P<0.05) characteristic correction value is retained, and the insignificant characteristic weight is set to 1 (i.e. does not affect the priority). For example, the age correction value (OR=1.8, P=0.02), the gender correction value (OR=1.2, P=0.12), i.e. the correction value obtained according to the age characteristic classification is 1.8, and the correction value obtained according to the gender characteristic classification is 1, so the final priority adjustment parameter = 1.8 x 1 = 1.8. Then, the priority of the design elements is adjusted based on the above final priority adjustment parameter, the final priority of each design element is determined, and the priority is sorted, and finally the design element priority list of the user is output, ensuring that the design scheme is optimized from the user's needs. The priority list will cover various aspects of design elements, such as space layout, lighting design, material selection, etc.

[0109] Further, the design strategy generation process in step 140 is as follows:

[0110] According to the optimized design element priority list, a design strategy for a specific user is generated. For example, for the "private healing type" group, the design strategy may emphasize space privacy, natural element introduction, and quiet leisure areas; for the "open social type" group, the design strategy may focus on social interaction areas, open space layout, and flexible functional zoning.

[0111] The design strategy provides a clear design direction for designers, and can also be dynamically adjusted according to new feedback and data during the design process.

[0112] The method proposed in this embodiment accurately captures and analyzes the spatial preference characteristics of users through data-driven methods, forms more detailed and personalized design portraits, and guides the design direction according to these design portraits; then further through logistic regression analysis of design elements, the priority of design elements can be adjusted according to different groups and user needs, realizing dynamic correction of design element priority, so that the design scheme can flexibly respond to changes in user needs, and realize continuous optimization of the design process. In addition, through systematic data support and analysis in this embodiment, the priority of design elements can be determined more objectively and scientifically, reducing subjective bias, and thus realizing more scientific and accurate design decisions.

[0113] The method proposed in this embodiment has strong versatility, and by adjusting user data and design element types, it can easily adapt to the needs of different fields, for example, in interior design, elements such as space layout, material selection, color matching, etc. can be adjusted; in space optimization, elements such as user behavior data, space display needs, and traffic planning can be optimized.

[0114] The embodiment also provides an embodiment of a dynamic design strategy generation device 200, as shown in the figure. Figure 2 The dynamic design strategy generation device 200 includes:

[0115] A matching unit 201 matches a design image from an image database according to user space preference data. The image database stores design images of different user groups generated by cluster analysis, and the design images include demand characteristics and preferred design elements of the user groups. The specific matching method and the design image generation process are described in the above method, and will not be described in detail here.

[0116] An extraction unit 202 obtains corresponding design element correction coefficients from a design element priority correction table according to user basic characteristic data. The design element priority correction table is generated by analyzing the preference degree of different classification groups to each design element by logistic regression. The specific design element priority correction table establishment process is described in the above method, and will not be described in detail here.

[0117] A dynamic correction unit 203 dynamically corrects the priority of the design elements in the design image by using the design element correction coefficients to generate a corrected design element priority list. The specific dynamic correction process is described in the above method, and will not be described in detail here.

[0118] And a generation unit 204 generates a design strategy according to the corrected design element priority list and outputs.

[0119] In another embodiment, the dynamic design strategy generation device 200 further includes:

[0120] An image database 205 stores design images of all user groups. The generation process of the design image is described in the above method, and will not be described in detail here.

[0121] The embodiment also provides a dynamic design strategy generation system 300, as shown in the figure. Figure 3 The dynamic design strategy generation system 300 includes:

[0122] An input device 301, an output device 302, a processor A 303 and a memory A 304; wherein the number of the processor A 303 and the memory A 304 can be one or more, Figure 3 The input device 301, the output device 302, the processor A 303 and the memory A 304 can be connected through a bus or other means, Figure 3 Taking connection through a bus as an example.

[0123] Specifically, by calling the operation instructions stored in memory A304, processor A303 executes the following steps:

[0124] Based on user space preference data, design profiles are matched from the profile database; the profile database stores design profiles of different user groups generated through cluster analysis, and the design profiles include the user group's needs and preferred design elements.

[0125] Based on user basic characteristic data, the corresponding design element correction coefficients are obtained from the design element priority correction table; the design element priority correction table is generated by logistic regression analysis of the preference of different groups for each design element;

[0126] By using design element correction coefficients, the priority of design elements in the design profile is dynamically corrected, and a corrected list of design element priorities is generated.

[0127] Based on the revised list of design element priorities, generate and output a design strategy.

[0128] Optionally, by calling the operation instructions stored in memory A304, processor A303 is also used to execute any of the embodiments in the corresponding examples of the above methods.

[0129] This embodiment also proposes 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, it performs the following steps:

[0130] Based on user space preference data, design profiles are matched from the profile database; the profile database stores design profiles of different user groups generated through cluster analysis, and the design profiles include the user group's needs and preferred design elements.

[0131] Based on user basic characteristic data, the corresponding design element correction coefficients are obtained from the design element priority correction table; the design element priority correction table is generated by logistic regression analysis of the preference of different groups for each design element;

[0132] By using design element correction coefficients, the priority of design elements in the design profile is dynamically corrected, and a corrected list of design element priorities is generated.

[0133] Based on the revised list of design element priorities, generate and output a design strategy.

[0134] Optionally, the processor B 420, when executing the computer program A 411, can implement any of the implementation manners in the corresponding embodiments of the above method.

[0135] It should be noted that the electronic device proposed in this embodiment is a device used to implement the above method, and therefore based on the above method proposed in this embodiment, those skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various forms of changes, and therefore the specific implementation of the electronic device to implement the above method is not described in detail here, as long as the electronic device used by those skilled in the art to implement the above method belongs to the scope of protection of the present application.

[0136] This embodiment also proposes an embodiment of a computer readable storage medium 500, as shown in the figure, the computer readable storage medium 500 stores a computer program B 511, and the computer program B 511 is executed by a processor to implement the following steps: Figure 5

[0137] According to the user space preference data, a design image is matched from an image database; wherein the image database stores design images of different user groups generated by clustering analysis, and the design image includes the demand characteristics and preference design elements of the user group;

[0138] According to the user basic characteristic data, a corresponding design element correction coefficient is obtained from a design element priority correction table; wherein the design element priority correction table is generated by analyzing the preference degree of different classification groups to each design element by logistic regression;

[0139] The design element priority correction table is generated by analyzing the preference degree of different classification groups to each design element by logistic regression;

[0140] According to the corrected design element priority list, a design strategy is generated and output.

[0141] Optionally, the computer program B 511, when executed by the processor, can implement any of the implementation manners in the corresponding embodiments of the above method.

[0142] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0143] Embodiment 2:

[0144] This embodiment takes a certain interior design as an example to apply the dynamic design strategy generation method proposed in embodiment 1, and the specific process is as follows:

[0145] ​First, by collecting data and pre-processing, then the basic analysis of data, can be generated according to the design of the user's portrait, from the mass of basic data, the intention of the crowd and the important demand characteristics and typical preference design elements, such as the four types of clustering portrait and typical preference design elements shown in Table 3.

[0146] Table 3

[0147]

[0148] Note: *** represents a significant level of 1%; F (explanation) value is used to assess whether the difference between design elements in different categories is significant; P (significance) value indicates whether the difference between design elements in different categories is statistically significant. If the P value is less than 0.05 (5% significant level), it means that there is a significant difference between different categories in these design elements.

[0149] Then, the user segmentation data and the priority of the important design elements are corrected:

[0150] The following is a data logistic regression analysis of the important design element "indoor plants in natural element application" for different age groups, with 18-30 years old as the control group and the other three age groups as the experimental group. The correction coefficient is the exponential of the regression coefficient. The analysis results are shown in Table 4:

[0151] Table 4

[0152]

[0153] Note: *** represents a significant level of 1%; regression coefficient β represents the influence of independent variable (such as age group) on dependent variable, its sign (positive or negative) indicates that the increase (or decrease) of independent variable will have a positive or negative impact on dependent variable; standard error is used to measure the accuracy of regression coefficient β, the smaller the value, the more accurate the estimation of regression coefficient β; 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 Wald statistic; P value is used to determine whether the regression coefficient is significant, if the P value is less than 0.05, it means significant; OR correction coefficient is the exponential result of regression coefficient, if OR is greater than 1, it means that the increase of independent variable will increase the probability of dependent variable; 95% confidence interval of OR value is used to estimate the reliability of OR, if the confidence interval does not contain 1, it means that the OR value is significant.

[0154] As can be seen from Table 4, the preference of the reference group 18-30 years old for "indoor plants in the application of natural elements" is taken as a reference (OR = 1); the 18-30 year-old group has a high demand for indoor plants, and the young group may be more inclined to natural and fresh space atmosphere. The constant term (β = -0.083, P = 0.773) of the experimental group 31-40 years old is not significant, indicating that there is no significant difference in the preference of the 31-40 year-old group for "indoor plants in the application of natural elements" compared with the 18-30 year-old group; it shows that the demand for indoor plants of the 31-40 year-old group is similar to that of the 18-30 year-old group, and the natural element decoration can be appropriately increased. According to the constant term (β = -1.273, P = 0.003***, OR = 0.28) of the experimental group 41-50 years old, the OR value is 0.28, indicating that the preference probability of the 41-50 year-old group for indoor plants is only 28% of that of the 18-30 year-old group, and the P value is less than 0.05, indicating that the difference is statistically significant, so the preference of the 41-50 year-old group for "indoor plants in the application of natural elements" is significantly lower than that of the 18-30 year-old group; it shows that the demand for indoor plants of the 41-50 year-old group is low, and they may pay more attention to 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, and the preference probability of the group over 51 years old for indoor plants is only 12% of that of the 18-30 year-old group, and the P value is 0.001, which is less than 0.05, indicating that the difference is statistically significant, indicating that the preference of the group over 51 years old for "indoor plants in the application of natural elements" is significantly lower than that of the 18-30 year-old group, and the demand for indoor plants of the group over 51 years old is the lowest.

[0155] The OR correction coefficient in the result of calling the logistic regression can be rounded and assigned. For example, for the "indoor plant configuration" part, the 18-30 year-old group is 1; the 31-40 year-old group is 0.9; the 41-50 year-old group is 0.3; and the 51-year-old and above group is 0.1. Thus, the design element priority correction table is obtained, as shown in Table 5.

[0156] Table 5

[0157]

[0158] Finally, data decision is made:

[0159] The input data includes the important space preference data of the user and the basic characteristic data, and the data structure is consistent with the previous data processing; for example, the preference data of the user includes natural elements_indoor plants = 1, rest area_open interaction = 1; the age group is 18-30 years old.

[0160] According to the important space preference data of the user, it is matched to "open social type"; the core design element of "open social type" is "open interactive rest area" and "free activity space".

[0161] Priority dynamic correction: since the user is 18-30 years old, according to the previous data analysis result, the priority of "diversified leisure space" needs to be improved. Alternatively, cross-validation technology can also be used to optimize the correction coefficient, and the finally determined correction coefficient is 1.0.

[0162] Finally, the output design strategy is that the core design element determined according to the space preference of the user is: open rest area + free activity space; the optimization suggestion is: increase diversified leisure functions (such as game area, social corner).

[0163] Those skilled in the art will understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0164] The present application is described with reference to flowcharts and / or block diagrams according to the method, device (system), and computer program product of the embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of the flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The means for performing the functions specified in one or more blocks.

[0165] These computer program instructions can also be stored in a computer-readable memory that can guide the computer or other programmable data processing devices to work in a specific way, so that the instructions stored in the computer-readable memory produce a product including instruction means, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in one or more flows and / or blocks Figure 1 The means for performing the functions specified in one or more blocks.

[0166] These computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are generated to realize the computer-implemented processes in the computer or other programmable devices, and the instructions executed in the computer or other programmable devices provide processes for implementing the functions specified in the flowchart Figure 1 one flow or a plurality of flows and / or the functions specified in the block Figure 1 one flow or a plurality of flows and / or the functions specified in the block

[0167] The above detailed description of the specific implementation is further detailed for the purpose of the application, technical solutions and beneficial effects. It should be understood that the above description is only a specific implementation of the application and is not used to limit the protection scope of the application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the application shall be included in the protection scope of the application.

Claims

1. A method for dynamic design strategy generation, the method comprising: The application comprises the following steps: matching a design image from an image database according to user space preference data; wherein the image database stores design images of different user groups generated by cluster analysis, and the design images include demand characteristics and preferred design elements of the user groups; obtaining a corresponding design element correction coefficient from a design element priority correction table according to user basic characteristic data; wherein the design element priority correction table is generated by analyzing the preference degree of different classification groups to each design element through logistic regression; correcting the priority of the design elements in the design image dynamically by using the design element correction coefficient to generate a corrected design element priority list; generating a design strategy and outputting according to the corrected design element priority list; the design element priority correction table generation process comprises the following steps: obtaining detailed design requirement data of different user groups and determining characteristic classification variables; dividing into different characteristic classification groups according to the characteristic classification variables, and performing logistic regression analysis on the design elements of different characteristic classification groups to determine the preference degree of different characteristic classification groups to each design element; generating a design element priority correction table for each characteristic classification group according to the logistic regression analysis results, wherein the design element priority correction table includes the correction coefficients of different characteristic classification groups to each design element; wherein the logistic regression analysis process comprises the following steps: obtaining the selection of a design element by different characteristic classification groups; establishing a regression function model with the preference selection of the design element as the dependent variable and multiple characteristic classification groups as the independent variables: logit(Pr)=β0+β1X1+β2X2+…+βkXk; wherein logit(Pr) is a logarithmic odds function, logit(Pr)= ln(Pr / (1-Pr)), Pr is the probability of the dependent variable occurring, 1-Pr is the probability of the dependent variable not occurring; β1, β2, … βk are the regression coefficients of the independent variables; X1, X2, … Xk are the independent variables; β0 is the baseline preference of the control group; fitting the regression coefficients of the independent variables in the regression function model by using historical data; calculating the correction coefficients corresponding to each independent variable to obtain the correction coefficients of each characteristic classification group to the design element.

2. The method of claim 1, wherein, The design image generation process comprises the following steps: collecting a large amount of user basic characteristic data and space preference data and preprocessing; performing cluster analysis on the preprocessed data by using a clustering algorithm to divide users into user groups with similar space demand and preference; generating a design image for each user group based on the cluster analysis results and storing it in the image database.

3. The method of claim 1, wherein, The design element priority correction table generation process further comprises the following steps: verifying and optimizing the correction coefficients in the generated design element priority correction table by using cross-validation technology.

4. The method of claim 1-3, wherein, The matching process comprises the following steps: calculating the similarity between the user space preference data and all design images in the image database by using a similarity algorithm, and taking the design image with the highest similarity as the final matching result.

5. The method of claim 1-3, wherein, The dynamic correction process comprises the following steps: The matched design image is combined with the obtained design element correction coefficient to calculate a final design element priority, and the priority is sorted to finally output a design element priority list of the user.

6. A dynamic design strategy generation apparatus characterized by comprising: The method comprises: a matching unit that matches a design image from an image database according to user space preference data; wherein the image database stores design images of different user groups generated by cluster analysis, and the design images include demand characteristics and preferred design elements of the user groups; a extraction unit that obtains corresponding design element correction coefficients from a design element priority correction table according to user basic characteristic data; The design element priority correction table is generated by analyzing the preference degree of different classification groups for each design element by logistic regression; a dynamic correction unit that dynamically corrects the priority of the design elements in the design image by using the design element correction coefficients to generate a corrected design element priority list; and a generation unit that generates a design strategy according to the corrected design element priority list and outputs it; The design element priority correction table generation process comprises: obtaining detailed design requirement data of different user groups and determining characteristic classification variables; dividing into different characteristic classification groups according to the characteristic classification variables, and performing logistic regression analysis on the design elements of different characteristic classification groups to determine the preference degree of different characteristic classification groups for each design element; According to the results of logistic regression analysis, generate a design element priority correction table for each characteristic classification group, which includes the correction coefficients of different characteristic classification groups for each design element; The logistic regression analysis process comprises: obtaining the selection of a design element by different characteristic classification groups; establishing a regression function model with the preference selection of the design element as the dependent variable and multiple characteristic classification groups as the independent variables: logit(Pr)=β0+β1X1+β2X2+…+βkXk; wherein logit(Pr) is the logit function, logit(Pr)= ln(Pr / (1-Pr)), Pr is the probability of the dependent variable occurring, 1-Pr is the probability of the dependent variable not occurring; β1, β2, … βk are the regression coefficients of the independent variables; X1, X2, … Xk are the independent variables; β0 is the baseline preference of the control group; fitting the regression function model to obtain the regression coefficients of the independent variables; According to the regression coefficients of the independent variables, the correction coefficients corresponding to the independent variables are calculated, and the correction coefficients of each characteristic classification group for the design element are obtained.

7. The dynamic design strategy generation apparatus according to claim 6, wherein Further comprising: an image database for storing design images of all user groups. 8.An electronic device comprising a memory and a processor, the memory storing a computer program, wherein, The processor executes the computer program to realize the dynamic design strategy generation method of any one of claims 1-5.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to realize the dynamic design strategy generation method of any one of claims 1-5.

Images