An artificial intelligence-based decoration design management platform

Abstract

This invention relates to the field of interior design technology, and more particularly to an artificial intelligence-based interior design management platform. The platform includes: a requirements analysis module for determining initial execution parameters of recommended execution targets; a monitoring and analysis module for determining whether to perform requirements tendency optimization analysis on the recommended execution targets based on an execution difference evaluation index; an optimization analysis module for determining whether requirements composition optimization is included when performing requirements loading optimization on the recommended execution targets based on the requirements tendency status of the recommended execution targets; a composition optimization module for determining the key response evaluation index of each requirement keyword; and a loading optimization module for determining loading execution parameters based on a reference execution evaluation index or an execution evaluation prominence index. This invention improves the adaptability of the design scheme recommendation loading results to the dynamic evolution of the preferences of design personnel.

Description

Technical Field

[0001] This invention relates to the field of decoration design technology, and in particular to a decoration design management platform based on artificial intelligence. Background Technology

[0002] Interior design platforms need to recommend design schemes to clients and provide 3D renderings to meet their online needs for understanding design options. However, existing platforms often rely on big data analysis based on keywords and criteria entered by clients to match scheme preferences from clients with similar needs. This fails to effectively utilize actual client browsing processes as feedback data for scheme recommendation quality and timely optimization of the recommendation and loading process. Therefore, how to optimize the recommendation and loading process of interior design schemes to ensure that the recommended schemes dynamically evolve to match client preferences and avoid ineffective scheme recommendations and loading over longer timescales is a problem that urgently needs to be solved by those skilled in the art.

[0003] Chinese patent application publication number discloses a method and system for online intelligent interactive display service of interior decoration images. The method includes the following steps: S1, obtaining the user's intention attributes for interior decoration; S2, refreshing and recommending a dynamic decoration design library based on the user's intention attributes, and extracting a dynamic design effect chain; S3, dynamically displaying the dynamic design effect chain based on 3D virtual software; S4, determining the final decoration design based on the dynamic design effect chain. This invention establishes a live interactive scene based on a cloud server, automatically generates a decoration budget list on the server based on the user's intention characteristics, and sends the decoration budget list online. Users do not need to go to a decoration company and can complete the effect design online, saving time and effort. It recommends a dynamic decoration design library based on user intentions, dynamically displays effect images, improves the user's choice of interior effects, and provides diverse home decoration services. However, the above solution has the following drawbacks: it fails to predict the matching situation of the user's actual usage process for the interaction process, and fails to adjust the dynamic rendering process of the interaction process in a timely manner, resulting in poor dynamic rendering loading efficiency in the actual interaction process. Summary of the Invention

[0004] To address this issue, the present invention provides an artificial intelligence-based decoration design management platform to overcome the problem in existing technologies that fail to predict the matching of user needs during the interaction process and adjust the dynamic rendering process in a timely manner, resulting in poor dynamic rendering loading efficiency during the actual interaction process.

[0005] To achieve the above objectives, the present invention provides an artificial intelligence-based decoration design management platform, comprising: The requirements analysis module is used to obtain the required input information for the recommended execution goals; The monitoring and analysis module, which is connected to the demand analysis module, is used to determine whether to perform demand tendency optimization analysis for the recommended execution target based on the execution difference assessment index. The execution difference assessment index is determined based on the execution duration difference parameter and the execution loading degree difference parameter. An optimization analysis module, which is connected to the monitoring and analysis module, is used to determine whether the demand loading optimization process for the recommended execution target includes demand composition optimization based on the demand tendency of the recommended execution target. The demand tendency is determined based on the key related difference index and the key demand change index. An optimization module is formed, which is connected to the optimization analysis module. It is used to determine whether to adjust the key response evaluation index for each demand keyword based on the clustering reference difference index or the relevant evaluation difference index, and to determine whether to adjust the difference demand ratio index based on the execution evaluation highlight index of the recommended execution target. The loading optimization module, which is connected to both the optimization analysis module and the component optimization module, is used to determine the recommended access execution scheme for the recommended execution target based on the key response demand keywords, and to determine the loading execution parameters of each recommended access execution scheme based on the reference execution evaluation index or the execution evaluation prominence index.

[0006] Furthermore, the monitoring and analysis module performs demand-oriented optimization analysis on recommended execution targets whose execution difference assessment index is greater than the preset execution difference assessment index; The monitoring and analysis module periodically detects the execution difference evaluation index of the recommended execution target. The execution difference evaluation index is positively correlated with the execution duration difference parameter and the execution loading degree difference parameter.

[0007] Furthermore, the aforementioned demand propensity trend includes a first-type demand propensity trend and a second-type demand propensity trend; The recommended execution target for the first type of demand tendency is a key relevance difference index greater than the preset key relevance difference index or a key demand change index greater than the preset key demand change index. The recommended execution target for the second type of demand tendency is a key relevance difference index that is less than or equal to the preset key relevance difference index and a key demand change index that is less than or equal to the preset key demand change index.

[0008] Furthermore, the key relevance difference index and the key demand change index are determined based on the key access execution plan demand keywords for each recommended execution target; The key access execution scheme is a recommended access execution scheme where the load execution evaluation index determined for the target analysis cycle is greater than the preset load execution evaluation index.

[0009] Furthermore, the composition optimization module performs demand composition optimization processing on recommended execution targets that are in a demand tendency state, and determines the key response evaluation index of each demand keyword based on the reference associated execution evaluation parameters; The key response demand keywords are those whose key response evaluation index is greater than the preset key response evaluation index. The adjustment method of the key response evaluation index is set according to the association coverage parameter of each demand keyword.

[0010] Furthermore, the composition optimization module performs relevant clustering analysis on the required keywords whose association coverage parameter is greater than the preset association coverage parameter, and determines the clustering reference difference index based on the set of relevant clusters of the required keywords to evaluate the difference index. The composition optimization module adjusts the key response evaluation index of the required keywords whose clustering reference difference index is greater than the preset clustering reference difference index based on the clustering reference difference index. The set coverage association index of any related cluster set is greater than the preset set coverage association index.

[0011] Furthermore, the composition optimization module performs relevant difference analysis on the required keywords whose associated coverage parameters are less than or equal to the preset associated coverage parameters, and determines the relevant evaluation difference index based on the loading execution evaluation index of each relevant access execution scheme; The composition optimization module adjusts the response evaluation index of key keywords whose relevant evaluation difference index is greater than the preset relevant evaluation difference index based on the relevant evaluation difference index.

[0012] Furthermore, the composition optimization module adjusts the proportion of difference in recommended execution targets where the execution evaluation highlight index is greater than the preset execution evaluation highlight index by increasing the proportion of difference in demand. The execution evaluation highlight index is determined based on the load execution evaluation index of the differential access execution scheme.

[0013] Furthermore, the loading optimization module performs demand loading optimization processing on recommended execution targets that are in a second-class demand tendency state or have completed demand composition optimization processing; The loading and execution parameters of the recommended access execution scheme are determined based on the demand matching index of the recommended access execution scheme.

[0014] Furthermore, the loading optimization module determines the loading execution parameters of the recommended access execution scheme with a demand matching index greater than the preset demand matching index based on the reference execution evaluation index; The loading optimization module determines the loading execution parameters of the recommended access execution scheme based on the execution evaluation highlight index, where the demand matching index is less than or equal to the preset demand matching index.

[0015] Compared with existing technologies, the advantages of this invention lie in its ability to monitor and analyze the differences in the access behavior feedback of recommendation execution targets to different recommendation execution access schemes. This allows for the assessment of potential user preference drift within a certain time frame, and the analysis of subsequent scheme generation and resource allocation strategies during the recommendation loading process. This achieves a shift from static matching based on initial conditions to proactive optimization based on dynamic feedback. By periodically quantifying the differences in the access behavior of recommendation execution targets to recommendation schemes, and using this to conduct keyword and scheme dimension correlation analysis on identified users with fluctuating needs, this invention effectively avoids the inability of recommendation results to meet quality requirements over a longer time scale due to evolving user preferences. This improves the adaptability of design scheme recommendation loading results to the dynamic evolution of the preferences of design personnel.

[0016] Furthermore, this invention periodically determines the execution difference evaluation index for each recommended execution target based on the execution duration difference parameter and the execution loading degree difference parameter, and uses this as a basis to determine whether to trigger demand preference optimization analysis. By characterizing the recommendation mismatch risk caused by user interest shifts or deepening needs through the execution difference evaluation index, it enables direct response to the adaptation deviation between the current set of recommended solutions and the user's real-time behavioral preferences. This avoids the huge computational resource consumption caused by continuous demand preference optimization analysis, ensuring the efficiency and necessity of the optimization analysis. This invention improves the resource utilization efficiency of the system monitoring and analysis process while ensuring timely response to potential preference drift.

[0017] Furthermore, this invention determines the demand tendency of each recommended execution target based on the key relevance difference index and the key demand change index. These indices characterize the degree of semantic difference in the user's recent focus on certain solutions and their deviation from historical focus patterns. This identifies whether the user is in an unstable state of broad exploration or a stable state of focused attention. This provides a reliable basis for subsequent selection of targeted demand component optimization or conventional loading efficiency optimization, making the initiated optimization process more aligned with the user's current actual demand stage. This invention improves the accuracy of judging the user's demand status and the targeting of subsequent optimization strategies.

[0018] Furthermore, this invention optimizes the demand composition for recommendation execution targets exhibiting a certain demand tendency. Since the recommended access execution schemes accessed by these targets show a certain degree of tendency variation, based on identifying key demand keywords, cluster analysis is used to eliminate interference from internal data, or difference analysis is used to eliminate the influence of low-frequency, accidental samples. This allows for refined adjustment of the keyword evaluation results, and simultaneously adjusts the proportion of difference access execution schemes. This invention improves the ability to dynamically perceive user preferences, the effectiveness of optimization decisions, and the adaptability to changes in preferences.

[0019] Furthermore, after strategy optimization, this invention determines the loading execution parameters for each recommended access execution scheme differently based on a reference execution evaluation index or an execution evaluation prominence index. For deterministic schemes with high matching degree, rendering resources are allocated according to the historical interaction popularity of their key demand points; for exploratory schemes with low matching degree, resources are allocated according to the user's overall interest level in the differentiated content. This ensures that the preloading decisions for the recommended schemes are consistent with the actual situation, thereby ensuring that the loading of the rendering process for the recommended schemes balances presentation smoothness and user preference requirements. Attached Figure Description

[0020] Figure 1 This is a module connection diagram of the artificial intelligence-based decoration design management platform of the present invention; Figure 2 This is a flowchart illustrating the process of determining whether to perform demand-oriented optimization analysis for the recommended execution target based on the execution difference assessment index in this invention. Figure 3 This is a flowchart illustrating the process of determining demand trends based on key relevance difference indices and key demand change indices in this invention. Figure 4 This is a flowchart illustrating whether the requirement composition optimization process should be included when determining the requirement loading optimization process for the recommended execution target based on the demand tendency of the recommended execution target. Detailed Implementation

[0021] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0022] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0023] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0024] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0025] Please see Figures 1 to 4 As shown, this embodiment of the invention provides an artificial intelligence-based decoration design management platform, including: The requirements analysis module is used to obtain the required input information for the recommended execution goals; The monitoring and analysis module, which is connected to the demand analysis module, is used to determine whether to perform demand tendency optimization analysis for the recommended execution target based on the execution difference assessment index. The execution difference assessment index is determined based on the execution duration difference parameter and the execution loading degree difference parameter. An optimization analysis module, which is connected to the monitoring and analysis module, is used to determine whether the demand loading optimization process for the recommended execution target includes demand composition optimization based on the demand tendency of the recommended execution target. The demand tendency is determined based on the key related difference index and the key demand change index. An optimization module is formed, which is connected to the optimization analysis module. It is used to determine whether to adjust the key response evaluation index for each demand keyword based on the clustering reference difference index or the relevant evaluation difference index, and to determine whether to adjust the difference demand ratio index based on the execution evaluation highlight index of the recommended execution target. The loading optimization module, which is connected to both the optimization analysis module and the component optimization module, is used to determine the recommended access execution scheme for the recommended execution target based on the key response demand keywords, and to determine the loading execution parameters of each recommended access execution scheme based on the reference execution evaluation index or the execution evaluation prominence index.

[0026] This invention optimizes the design scheme recommendation and loading process to ensure that the recommended schemes adapt to the dynamic evolution of the preferences of the design personnel. This avoids the problem of low effectiveness in scheme recommendation and loading over long periods caused by continuously matching schemes based on input requirements. The design personnel currently receiving the proposed scheme are designated as the recommendation execution target. The requirements information input by the recommendation execution target before the scheme is pushed to them is designated as the requirement input information. The categories of requirement input information include, but are not limited to: spatial data, functional requirements, total budget, itemized budgets (such as the percentages of hard furnishings, cabinets, and furniture), house orientation, lighting conditions, ventilation paths, and style keywords (e.g., modern minimalist, Nordic, vintage style). In this invention, before pushing design schemes, an initial push scheme is set based on the input requirement information of the recommended execution target. After the recommended execution target has access behavior for the recommended access execution scheme, the execution difference evaluation index of the recommended execution target is periodically detected. The recommended access execution scheme is the recommended decoration design scheme determined for each access monitoring period. The platform sets several requirement keywords for each decoration design scheme. The category of the requirement keywords is consistent with the category of the requirement input information. The specific content of the requirement keywords can be set by the user according to the actual situation. This is content that is easy for those skilled in the art to understand. For example, the requirement keywords can be Japanese wood, light French, industrial style, cream color scheme, Morandi color scheme, natural stone, solid wood flooring, etc.

[0027] Specifically, the monitoring and analysis module performs demand-oriented optimization analysis on recommended execution targets whose execution difference assessment index is greater than the preset execution difference assessment index; The monitoring and analysis module periodically detects the execution difference evaluation index of the recommended execution target. The execution difference evaluation index is positively correlated with the execution duration difference parameter and the execution loading degree difference parameter.

[0028] In this invention, the execution difference evaluation index of the recommended execution target is periodically detected. Specifically, an access monitoring cycle is set. Each access monitoring cycle detects the dynamic index of the execution demand of each identified execution point. A value for the duration of the access monitoring cycle is provided, which is 15 minutes. For a single access monitoring period, the execution duration parameter and execution loading degree parameter of each recommended access execution scheme accessed by the recommended execution target within that access monitoring period are obtained. The execution difference evaluation index is the sum of the execution duration difference parameter and the execution loading degree difference parameter. , This is the average execution duration parameter of each recommended access execution plan accessed within the access monitoring period. The execution load difference parameter is the standard deviation between the execution duration parameters of each recommended access execution scheme accessed within the access monitoring period. , This represents the average execution loading level parameter of each recommended access execution plan accessed during the access monitoring period. The standard deviation of the execution loading level parameters among the recommended access execution schemes accessed within the access monitoring period is defined as follows: For any recommended access execution scheme accessed within the access monitoring period, the execution duration parameter is the dwell time of the recommended execution target on the recommended access execution scheme within the access monitoring period; the execution loading level parameter is... , This represents the maximum amount of data that the recommended execution target can load for the recommended access execution plan within this access monitoring period. The amount of data required to fully load the recommended access execution scheme for the target execution; The value of the preset execution difference evaluation index can be understood as follows: the higher the user's requirement for the effectiveness of the recommended loading result of the recommended access execution plan, the smaller the value of the preset execution difference evaluation index. The execution difference evaluation index characterizes the degree of difference in the access process of the recommended access execution plan for the corresponding access in each access monitoring period. A preset execution difference evaluation index value of 0.5 is provided.

[0029] Specifically, the demand propensity trend includes a first type of demand propensity trend and a second type of demand propensity trend; The recommended execution target for the first type of demand tendency is a key relevance difference index greater than the preset key relevance difference index or a key demand change index greater than the preset key demand change index. The recommended execution target for the second type of demand tendency is a key relevance difference index that is less than or equal to the preset key relevance difference index and a key demand change index that is less than or equal to the preset key demand change index.

[0030] Specifically, the key relevance difference index and the key demand change index are determined based on the key access execution scheme demand keywords for each recommended execution target; The key access execution scheme is a recommended access execution scheme where the load execution evaluation index determined for the target analysis cycle is greater than the preset load execution evaluation index.

[0031] Wherein, if the execution difference assessment index determined by the current access monitoring period for the recommended execution target is greater than the preset execution difference assessment index, then the access monitoring period is recorded as the target analysis period. The key relevant difference index is the average of the relevant difference indices of each key access execution scheme accessed within the access monitoring period. For a single key access execution scheme, the relevant difference index... , To determine the number of different demand keywords for this key access execution plan within the target analysis period. The key requirement change index is the number of overlapping key requirement keywords between the different key requirement keywords present in this key access execution plan and the other key access execution plans accessed during the target analysis period. , This refers to the number of required keywords for each key access execution plan accessed during the previous access monitoring period of the target analysis cycle. The number of demand keywords that exist in all key access execution schemes accessed within the target analysis period and the previous access monitoring period of the target analysis period. For a single recommended access execution scheme, the loading execution evaluation index is the sum of values ​​obtained by normalizing the execution duration parameter and the execution loading degree parameter. In this invention, the normalization process adopts the minimum-maximum normalization method to map the index to the [0,1] interval. How to perform the normalization process is a content that is already known to those skilled in the art, and will not be elaborated here. The values ​​of the preset loading execution evaluation index, preset key relevance difference index, and preset key demand change index are understood to reflect the following: the higher the user's requirement for the effectiveness of the recommended access execution plan's loading results, the smaller the values ​​of the preset loading execution evaluation index, the preset key relevance difference index, and the preset key demand change index. The loading execution evaluation index represents the loading demand level of the recommended access execution plan's access process. The key relevance difference index represents the degree of difference between the demand keywords corresponding to the recommended access execution plans accessed within a certain time range. The key demand change index represents the degree of difference between the demand keywords corresponding to the recommended access execution plans accessed within a certain time range and those accessed within a previous time range. One preset loading execution evaluation index value is 0.7; another preset key relevance difference index value is 1.75; and another preset key demand change index value is 4.

[0032] Specifically, the composition optimization module performs demand composition optimization processing on recommended execution targets that are in a demand tendency state, and determines the key response evaluation index of each demand keyword based on the reference associated execution evaluation parameters; The key response demand keywords are those whose key response evaluation index is greater than the preset key response evaluation index. The adjustment method of the key response evaluation index is set according to the association coverage parameter of each demand keyword.

[0033] If the recommended execution target is in a demand tendency state, it indicates that the key relevance difference index or key demand change index of the recommended execution target is large. This indicates that the recommended execution target has a large degree of difference between the demand keywords corresponding to the recommended access execution plan accessed in the target analysis period, or that the demand keywords corresponding to the recommended access execution plan accessed in the target analysis period have a large degree of difference with the demand keywords corresponding to the recommended access execution plan accessed in a certain period of time before. At this time, the recommended access execution plan accessed by the recommended execution target has a certain degree of tendency change. Therefore, demand composition optimization processing is carried out for the recommended execution target to adjust the composition of the key response demand keywords of the recommended execution target, so as to ensure the recommendation quality of the recommended access execution plan for the next access monitoring period of the target analysis period. For a single demand keyword, the reference associated execution evaluation parameter is the average value of the loading execution evaluation index of the relevant access execution schemes of the demand keyword. The relevant access execution schemes are the recommended access execution schemes that are accessed by the recommended execution target and involve the demand keyword during the preference evaluation stage. The reference associated execution evaluation parameter for the demand keyword is recorded as the key response evaluation index of the demand keyword. The value of the preset key response evaluation index can be understood as follows: the higher the user's requirement for the effectiveness of the recommended loading result of the recommended access execution plan, the larger the value of the preset key response evaluation index. The key response evaluation index represents the degree of matching between the demand keywords and the demand preferences of the current recommendation execution target. A preset key response evaluation index value of 0.8 is provided.

[0034] Specifically, the composition optimization module performs relevant clustering analysis on the required keywords whose association coverage parameters are greater than the preset association coverage parameters, and determines the clustering reference difference index based on the set of relevant clusters of the required keywords to evaluate the difference index. The composition optimization module adjusts the key response evaluation index of the required keywords whose clustering reference difference index is greater than the preset clustering reference difference index based on the clustering reference difference index. The set coverage association index of any related cluster set is greater than the preset set coverage association index.

[0035] Specifically, for a single demand keyword, the associated coverage parameter , The number of relevant access execution schemes for the keyword in question. The preset association coverage parameter is the number of recommended access execution schemes accessed by the recommended execution target during the preference evaluation phase. It can be understood that the higher the user's requirement for the effectiveness of the recommended loading results of the recommended access execution schemes, the larger the value of the preset association coverage parameter. A preset association coverage parameter value of 0.35 is provided. For a single demand keyword, if the association coverage parameter of the demand keyword is greater than the preset association coverage parameter, it indicates that there are relatively rich recommended access execution schemes involving the demand keyword during the preference evaluation phase. Therefore, cluster analysis is performed on the relevant access execution schemes for the demand keyword to evaluate whether there is a deviation in the key response evaluation index determined for the demand keyword. The relevant cluster set is a set of several relevant access execution schemes for the demand keyword. For a single relevant cluster set, the set covers the association index. , This refers to the number of different requirement keywords involved in each relevant access execution scheme within the relevant cluster set. The number of different requirement keywords involved in each relevant access execution scheme of the relevant cluster set is used to evaluate the difference index of the set for a single relevant cluster set. , This represents the average load execution evaluation index of all relevant access execution schemes existing in this relevant cluster set. The standard deviation of the loading execution evaluation index among the relevant access execution schemes existing in the relevant cluster set is the standard deviation of the cluster reference difference index, which is the average of the set evaluation difference indices of the relevant cluster sets existing in the requirement keyword. For a single demand keyword, if its clustering reference difference index is greater than the preset clustering reference difference index, it indicates that the determination of the key response evaluation index for that demand keyword is influenced by related access execution schemes with low reference value, resulting in poor effectiveness of the determined key response evaluation index. Therefore, the initially determined key response evaluation index for that demand keyword is reduced. , This is the unadjusted key response assessment index. This serves as a clustering reference difference index for the keywords related to this demand. The values ​​of the preset set coverage association index and the preset clustering reference difference index are understood to reflect the following: the higher the user's requirement for the effectiveness of the recommended access execution scheme's loading result, the larger the value of the preset association coverage parameter and the smaller the value of the preset clustering reference difference index. The association coverage parameter characterizes the degree of overlap between the demand keywords involved in each related access execution scheme within the relevant cluster set. The clustering reference difference index characterizes the overall difference in the loading access evaluation index of the recommended access execution schemes in each relevant cluster set where the demand keywords exist. One preset set coverage association index value is 0.75, and another preset clustering reference difference index value is 0.3.

[0036] Specifically, the composition optimization module performs relevant difference analysis on the required keywords whose associated coverage parameters are less than or equal to the preset associated coverage parameters, and determines the relevant evaluation difference index based on the loading and execution evaluation index of each relevant access execution scheme; The composition optimization module adjusts the response evaluation index of key keywords whose relevant evaluation difference index is greater than the preset relevant evaluation difference index based on the relevant evaluation difference index.

[0037] Specifically, for a single demand keyword, if the association coverage parameter of that demand keyword is less than or equal to a preset association coverage parameter, it indicates that there are few recommended access execution schemes involving that demand keyword during the preference evaluation phase. Therefore, a correlation difference analysis is performed on the relevant access execution schemes for that demand keyword, and the correlation evaluation difference index is... , This represents the average loading and execution evaluation index of all relevant access execution schemes for the keyword in question. This is the standard deviation among the loading execution evaluation indices of various related access execution schemes for the keyword in question. If the related evaluation difference index for the keyword in question is greater than the preset related evaluation difference index, it indicates that there is interference from related access execution schemes with low reference value in the determination process of the key response evaluation index for the keyword in question, resulting in poor effectiveness of the determined key response evaluation index. Therefore, the determined key response evaluation index is reduced. The adjusted key response evaluation index is... , This is the unadjusted key response assessment index. The relevant evaluation difference index for the keywords of this demand; The value of the preset related evaluation difference index can be understood as follows: the higher the user's requirement for the effectiveness of the recommended loading result of the recommended access execution plan, the smaller the value of the preset related evaluation difference index. The related evaluation difference index represents the degree of difference in the loading access evaluation index of the related access execution plan for the existence of the demand keyword. A preset value of 0.3 is provided.

[0038] Specifically, the component optimization module adjusts the proportion of difference requirements for recommended execution targets whose execution evaluation prominence index is greater than the preset execution evaluation prominence index based on the execution evaluation prominence index. The execution evaluation highlight index is determined based on the load execution evaluation index of the differential access execution scheme.

[0039] In this invention, to promptly capture the dynamic changes in the demand preferences of the recommended execution targets, a certain proportion of the recommended access execution schemes determined in each access monitoring cycle contain differential access execution schemes. The demand matching index of these differential access execution schemes is less than a preset demand matching index. The execution evaluation highlight index... , This represents the average loading execution evaluation index of the recommended access execution plans visited during the preference evaluation phase. The average loading execution evaluation index of the differential access execution schemes accessed during the preference evaluation phase is the average loading execution evaluation index of the preference evaluation phase. The end time of the preference evaluation phase is the end time of the target analysis cycle. The duration of the preference evaluation phase can be set by the user according to actual needs. The higher the user's requirements for the effectiveness of the recommended loading results of the recommended access execution scheme, the longer the duration of the preference evaluation phase is. One possible value for the duration of the preference evaluation phase is 45 minutes. If the performance evaluation prominence index is greater than the preset performance evaluation prominence index, it indicates that the recommended execution target has a greater preference for the differentiated access execution scheme within a certain time range. Therefore, the differentiated demand proportion index is increased. , The number of recommended access execution plans determined for the next access monitoring cycle of the target analysis cycle. The adjusted differential demand ratio index is the number of differential access execution plans among the recommended access execution plans determined for the next access monitoring cycle of the target analysis cycle. , The initial difference demand ratio index can be set by the user based on actual needs. The higher the user's requirement for the effectiveness of the recommended access execution plan's loading results, the smaller the initial difference demand ratio index. One possible value for the initial difference demand ratio index is 0.05. The preset execution evaluation highlight index, as understood, also increases with the user's requirement for the effectiveness of the recommended access execution plan's loading results. The execution evaluation highlight index characterizes the degree of access preference of the recommended execution target for the difference access execution plan within a certain time range. One possible value for the preset execution evaluation highlight index is 0.2.

[0040] Specifically, the loading optimization module performs demand loading optimization processing on recommended execution targets that are in a state of second-class demand tendency or have completed demand composition optimization processing; The loading and execution parameters of the recommended access execution scheme are determined based on the demand matching index of the recommended access execution scheme.

[0041] If the recommended execution target is in a second-type demand tendency state, it indicates that the key relevance difference index and key demand change index of the recommended execution target are both small. This further indicates that the difference between the recommended execution target and the demand keywords corresponding to the recommended access execution schemes accessed during the target analysis period is small, and the difference between the demand keywords corresponding to the recommended access execution schemes accessed during the target analysis period and the demand keywords corresponding to the recommended access execution schemes accessed within a certain time range before this period is small. In this case, the recommended access execution schemes accessed by the recommended execution target do not exhibit any tendency change or have only a small tendency change. Therefore, no demand composition optimization processing is required for the recommended execution target. Demand loading optimization processing is performed for recommended execution targets in a second-type demand tendency state or those that have completed demand composition optimization processing to ensure the smoothness of the rendering process for each recommended access execution scheme. For a single recommended access execution scheme, the demand matching index... , The number of required keywords for this recommended access execution plan. The number of key response keywords among the key keywords in the recommended access execution plan.

[0042] Optimize the loading of requirements for the recommended execution target to determine a set of recommended access execution schemes. The number of recommended access execution schemes determined for the target in the next access monitoring cycle of the target analysis cycle is positively correlated with the reference access duration parameter of the target analysis cycle. The reference access duration parameter is the average execution duration parameter of the recommended access execution schemes accessed within the target analysis cycle. The number of recommended access execution schemes determined for the next access monitoring cycle of the target analysis cycle is... , This serves as the base number for the number of recommended access execution plans determined for each access monitoring period. As a reference access duration parameter for the target analysis cycle, for the set of recommended access execution schemes determined in the next access monitoring cycle of the target analysis cycle, the number of differential access execution schemes is determined according to the differential demand ratio index. A corresponding number of schemes are randomly selected from the recommended schemes whose demand matching index is less than or equal to the preset demand matching index as differential access execution schemes. Schemes with demand matching indices greater than the preset demand matching index are selected from the remaining recommended access execution schemes in descending order. The recommended schemes are decoration design schemes that have not been accessed by the recommended execution target.

[0043] Specifically, the loading optimization module determines the loading execution parameters of the recommended access execution scheme with a demand matching index greater than the preset demand matching index based on the reference execution evaluation index; The loading optimization module determines the loading execution parameters of the recommended access execution scheme based on the execution evaluation highlight index, where the demand matching index is less than or equal to the preset demand matching index.

[0044] Specifically, for any recommended access execution plan determined in the next access monitoring cycle of the target analysis cycle, if the demand matching index is greater than the preset demand matching index, it indicates that the recommended access execution plan has a high degree of matching with the current demand preference of the recommended execution target. In this case, the loading execution parameters are determined based on the overall criticality of the corresponding demand keywords in the preference evaluation stage. The reference execution evaluation index is the average of the relevant scheme evaluation indices of each demand keyword involved in the recommended access execution plan. For a single demand keyword, the relevant scheme evaluation index is the average of the execution loading degree parameters of each recommended access execution plan involving that demand keyword accessed during the preference evaluation stage. The determined reference execution evaluation index is normalized, and the loading execution parameters of the recommended access execution plan are then determined. , To complete the reference performance evaluation index for normalization, The initial values ​​for the load execution parameters; For any recommended access execution plan determined in the next access monitoring cycle of the target analysis cycle, if the demand matching index is less than or equal to the preset demand matching index, it indicates that the recommended access execution plan has a low degree of matching with the current demand preference of the recommended execution target. As an evaluation scheme for the potential preference of the differentiated access execution plan for the recommended execution target, there are no rated loading execution parameters based on the access status of the recommended execution target to the differentiated access execution plan during the preference evaluation stage. The determined execution evaluation prominence index is normalized, and the loading execution parameters of the recommended access execution plan are... , To complete the performance evaluation of the normalized process, highlight the key indices. The initial values ​​for the load execution parameters; The loading execution parameters are the preloading degree of rendering resources corresponding to each recommended access execution scheme after determining the set of recommended access execution schemes for the next access monitoring cycle of the target analysis cycle. For a single recommended access execution scheme, the loading execution parameters are... , The amount of data required to perform a full 3D rendering for this recommended access execution scheme. This refers to the amount of data loaded when preloading the recommended access execution scheme; the initial loading execution parameter value can be set by the user according to the actual situation. The higher the user's requirement for the smoothness of the recommended loading result of the recommended access execution scheme, the larger the initial loading execution parameter value. One initial loading execution parameter value is provided, which is 0.15. The value of the preset demand matching index can be understood as follows: the higher the user's requirement for the effectiveness of the recommended loading result of the recommended access execution plan, the larger the value of the preset demand matching index. The demand matching index represents the degree of matching between the recommended access execution plan and the currently determined demand keyword with the highest preference. A preset demand matching index value of 0.7 is provided.

[0045] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

Claims

1. A decoration design management platform based on artificial intelligence, characterized in that, include: The requirements analysis module is used to obtain the required input information for the recommended execution goals; The monitoring and analysis module, which is connected to the demand analysis module, is used to determine whether to perform demand tendency optimization analysis for the recommended execution target based on the execution difference assessment index. The execution difference assessment index is determined based on the execution duration difference parameter and the execution loading degree difference parameter. An optimization analysis module, which is connected to the monitoring and analysis module, is used to determine whether the demand loading optimization process for the recommended execution target includes demand composition optimization based on the demand tendency of the recommended execution target. The demand tendency is determined based on the key related difference index and the key demand change index. An optimization module is formed, which is connected to the optimization analysis module. It is used to determine whether to adjust the key response evaluation index for each demand keyword based on the clustering reference difference index or the relevant evaluation difference index, and to determine whether to adjust the difference demand ratio index based on the execution evaluation highlight index of the recommended execution target. The loading optimization module, which is connected to both the optimization analysis module and the component optimization module, is used to determine the recommended access execution scheme for the recommended execution target based on the key response demand keywords, and to determine the loading execution parameters of each recommended access execution scheme based on the reference execution evaluation index or the execution evaluation prominence index.

2. The artificial intelligence-based decoration design management platform according to claim 1, characterized in that, The monitoring and analysis module performs demand-oriented optimization analysis on recommended execution targets whose execution difference assessment index is greater than the preset execution difference assessment index; The monitoring and analysis module periodically detects the execution difference evaluation index of the recommended execution target. The execution difference evaluation index is positively correlated with the execution duration difference parameter and the execution loading degree difference parameter.

3. The artificial intelligence-based decoration design management platform according to claim 2, characterized in that, The demand trend includes a first-type demand trend and a second-type demand trend. The recommended execution target for the first type of demand tendency is a key relevance difference index greater than the preset key relevance difference index or a key demand change index greater than the preset key demand change index. The recommended execution target for the second type of demand tendency is a key relevance difference index that is less than or equal to the preset key relevance difference index and a key demand change index that is less than or equal to the preset key demand change index.

4. The artificial intelligence-based decoration design management platform according to claim 3, characterized in that, The key relevance difference index and key demand change index are determined based on the key access execution plan requirements keywords for each recommended execution target; The key access execution scheme is a recommended access execution scheme where the load execution evaluation index determined for the target analysis cycle is greater than the preset load execution evaluation index.

5. The artificial intelligence-based decoration design management platform according to claim 3, characterized in that, The composition optimization module optimizes the composition of recommended execution targets that are in a certain demand tendency state, and determines the key response evaluation index of each demand keyword based on the reference associated execution evaluation parameters. The key response demand keywords are those whose key response evaluation index is greater than the preset key response evaluation index. The adjustment method of the key response evaluation index is set according to the association coverage parameter of each demand keyword.

6. The artificial intelligence-based decoration design management platform according to claim 5, characterized in that, The composition optimization module performs relevant clustering analysis on the required keywords whose association coverage parameters are greater than the preset association coverage parameters, and determines the clustering reference difference index based on the set of relevant clusters of the required keywords to evaluate the difference index. The composition optimization module adjusts the key response evaluation index of the required keywords whose clustering reference difference index is greater than the preset clustering reference difference index based on the clustering reference difference index. The set coverage association index of any related cluster set is greater than the preset set coverage association index.

7. The artificial intelligence-based decoration design management platform according to claim 6, characterized in that, The composition optimization module performs relevant difference analysis on the required keywords whose associated coverage parameters are less than or equal to the preset associated coverage parameters, and determines the relevant evaluation difference index based on the loading and execution evaluation index of each relevant access execution scheme; The composition optimization module adjusts the response evaluation index of key keywords whose relevant evaluation difference index is greater than the preset relevant evaluation difference index based on the relevant evaluation difference index.

8. The artificial intelligence-based decoration design management platform according to claim 7, characterized in that, The component optimization module adjusts the percentage of difference in recommended execution targets where the execution evaluation highlight index is greater than the preset execution evaluation highlight index by increasing the percentage of such differences. The execution evaluation highlight index is determined based on the load execution evaluation index of the differential access execution scheme.

9. The artificial intelligence-based decoration design management platform according to claim 8, characterized in that, The loading optimization module performs demand loading optimization processing on recommended execution targets that are in a second-class demand tendency state or have completed demand composition optimization processing. The loading and execution parameters of the recommended access execution scheme are determined based on the demand matching index of the recommended access execution scheme.

10. The artificial intelligence-based decoration design management platform according to claim 1, characterized in that, The loading optimization module determines the loading execution parameters of the recommended access execution scheme with a demand matching index greater than the preset demand matching index based on the reference execution evaluation index. The loading optimization module determines the loading execution parameters of the recommended access execution scheme based on the execution evaluation highlight index, where the demand matching index is less than or equal to the preset demand matching index.

Images