Supply chain data management method and system for home furnishings
By receiving user requests in home soft decoration design, obtaining feature data and using data integration and dynamic update algorithms, creating a supply chain performance model, solving the problem of difficulty in combining user demand and market changes in the existing technology, and improving design proposal recommendations efficiency and supply chain operation efficiency.
Patent Information
- Application Number
- CN202410215647.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-02-27
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-02-27
AI Technical Summary
The existing technology is difficult to effectively combine user personalized needs with market changes in home soft furnishing design and supply chain management, resulting in insufficient design recommendation efficiency and supply chain operation efficiency.
By receiving user personalized design requests, obtaining relevant feature data, using preset data integration algorithms and dynamic update algorithms to create and adjust supply chain performance models, calculate product correlation strength and customized correlation scores, and recommending the most in line with user needs and market conditions. design plan.
It improves user satisfaction and supply chain operation efficiency, and achieves rapid response to market changes and user needs.
Smart Images

Figure CN118052406B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of data processing, and in particular to a supply chain data management method and system for home furnishings. Background Art
[0002] In the field of home furnishing design and supply chain management, with the growing demand for personalization and customization in the market, traditional supply chain management methods are facing more and more challenges. Current home furnishing design usually relies on consumers' personalized needs and market trends, and effective supply chain management is the key to ensuring that design solutions can be implemented quickly and accurately to meet market demand. Therefore, how to effectively combine users' personalized needs with supply chain efficiency has become an important issue in the industry.
[0003] At present, traditional data management methods, such as manual or semi-automatic data collection and analysis, are mainly relied on to process user needs and supply chain status information. These methods are often inefficient when processing large amounts of complex data, and it is difficult to quickly respond to market changes. In addition, existing technologies generally fail to make full use of advanced data processing and machine learning technologies, resulting in a lack of dynamism and accuracy in home furnishing product recommendations and supply chain optimization. The main technical defects of existing technologies lie in their limitations in processing personalized needs and supply chain data. These methods lack efficient and accurate mechanisms in analyzing user needs, predicting market trends, and optimizing supply chain responses, and are difficult to adapt to market changes and personalized user needs in real time, thereby affecting the overall efficiency of design solution recommendations and the operational efficiency of the supply chain.
[0004] Therefore, developing a management method that can efficiently integrate user personalized needs and supply chain data is of great significance to improving the satisfaction of home soft decoration design and supply chain efficiency. Summary of the invention
[0005] The present invention provides a supply chain data management method and system for home furnishing soft furnishings, which are used to improve the satisfaction with home furnishing soft furnishings design and the supply chain efficiency.
[0006] A first aspect of the present invention provides a supply chain data management method for home furnishings, the supply chain data management method for home furnishings comprising:
[0007] Receiving a personalized request from a user; wherein the personalized request includes a preferred element and a secondary element of a home furnishing design solution;
[0008] According to the personalized customization request, primary feature data and secondary feature data associated with the home furnishing design solution are obtained;
[0009] Performing a preliminary analysis on the primary feature data and the secondary feature data through a preset data integration algorithm to obtain a preliminary analysis result; and creating an initial supply chain efficiency model based on the preliminary analysis result;
[0010] Obtain market trend data and inventory status data from the supply chain database, and adjust the parameters in the initial supply chain performance model based on a preset dynamic update algorithm to generate a supply chain optimization model;
[0011] The supply chain optimization model is used to calculate the association strength between various home furnishing products, and obtain customized association scores for different user requests; wherein the customized association scores are used to reflect the degree of optimization of each soft furnishing product in accordance with user needs, so as to identify and recommend the home furnishing design solution that best meets user expectations and supply chain conditions;
[0012] The obtained customized association score is input into the trained recommendation model to obtain a recommendation plan; and based on the output recommendation plan, the preferred plan with the highest score is selected from multiple home soft decoration design plans, and the preferred plan with the highest score is pushed to the user terminal.
[0013] Optionally, in a first implementation of the first aspect of the present invention, the primary feature data and the secondary feature data are preliminarily analyzed by a preset data integration algorithm to obtain a preliminary analysis result; and based on the preliminary analysis result, an initial supply chain performance model is created, including:
[0014] Performing a preliminary analysis on the primary feature data and the secondary feature data to obtain first data and second data; wherein the first data at least includes the user's design preference data, space requirement data and budget constraint data; and the second data at least includes historical purchase data, regional fashion trend data and supply chain capability data;
[0015] Performing a preliminary evaluation of the first data and the second data through a preset data integration algorithm to obtain a preliminary evaluation result of the supply chain operation;
[0016] Based on the preliminary evaluation results of supply chain operations, an initial supply chain performance model is created; wherein the initial supply chain performance model is used to characterize the relationship between commodity flow, information flow and capital flow in the supply chain;
[0017] The created initial supply chain efficiency model is trained to obtain a trained initial supply chain efficiency model.
[0018] Optionally, in a second implementation of the first aspect of the present invention, the created initial supply chain efficiency model is trained to obtain a trained initial supply chain efficiency model, including:
[0019] Acquire multi-source data of the supply chain, and input the multi-source data into the constructed initial supply chain performance model; wherein the multi-source data is training sample data including at least commodity circulation, information exchange records, capital flow, market dynamics data, historical data and real-time data, customer feedback and service quality data; the initial supply chain performance model is composed of a commodity flow analysis sub-model, an information flow analysis sub-model, a capital flow monitoring sub-model, a demand response prediction sub-model, a risk assessment sub-model and a customer satisfaction evaluation sub-model, and each sub-model focuses on different supply chain dimensions;
[0020] The commodity flow analysis sub-model processes multi-source data, analyzes the commodity flow pattern from the starting point to the end point, determines the commodity flow speed and efficiency, and outputs commodity liquidity indicators;
[0021] The information exchange records are analyzed through the information flow analysis sub-model, the speed and accuracy of information transmission are evaluated, and information flow indicators are output;
[0022] Monitor and analyze capital flow through the capital flow monitoring sub-model, evaluate payment timeliness and capital utilization efficiency, and output capital circulation efficiency indicators;
[0023] Based on the demand response prediction sub-model and combined with market dynamics data, the adaptability of the supply chain to emerging demands is analyzed and demand adaptability indicators are output;
[0024] Based on the risk assessment sub-model, the risk points in the supply chain are assessed according to historical data and real-time data, and risk assessment indicators are output;
[0025] Based on the customer satisfaction evaluation sub-model, the satisfaction of the end-user experience is evaluated according to customer feedback and service quality data, and the customer satisfaction index is output;
[0026] Extracting preset standard values from multi-source data of the supply chain; wherein the preset standard values include the actual commodity flow rate, actual information circulation rate, actual capital turnover efficiency, actual demand adaptability, actual risk occurrence probability, and actual customer satisfaction under the best operating conditions;
[0027] Calculate the error value based on the difference between each indicator output by each sub-model of the constructed initial supply chain efficiency model and the preset standard value; wherein the error value is the deviation between the predicted indicator and the actual indicator;
[0028] Based on the preset optimization algorithm, the parameters of each sub-model of the initial supply chain efficiency model are gradually adjusted to minimize various error values until the training of the created initial supply chain efficiency model is completed to obtain the trained initial supply chain efficiency model.
[0029] Optionally, in a third implementation of the first aspect of the present invention, the first data and the second data are preliminarily evaluated by a preset data integration algorithm to obtain a preliminary evaluation result of the supply chain operation;
[0030] Extracting from the first data by a preset first data extraction algorithm to obtain first feature data, and extracting from the second data by a preset second data extraction algorithm to obtain second feature data; wherein the first feature data is used to characterize the purchasing power and personal style preference of the user; and the second feature data is used to characterize seasonal influence and regional market trend;
[0031] Performing data conversion processing on the first feature data to obtain a first feature vector; performing data conversion processing on the second feature data to obtain a second feature vector;
[0032] Based on a preset data fusion mechanism, the first feature vector and the second feature vector are fused to obtain a target fusion vector of a multi-dimensional analysis result; wherein the target fusion vector is used to reflect the impact of various internal and external factors on the overall operation of the supply chain;
[0033] A multi-level supply chain data representation framework is constructed based on the target fusion vector; wherein the multi-level supply chain data representation framework establishes a first mapping model between the first data and the target fusion data through a first mapping algorithm, and establishes a second mapping model between the second data and the target fusion data through a second mapping algorithm,
[0034] Performing a preliminary evaluation on the first data based on the first mapping model to obtain a first preliminary evaluation result of the supply chain operation;
[0035] Performing a preliminary evaluation on the first data based on the second mapping model to obtain a second preliminary evaluation result of the supply chain operation;
[0036] A preliminary evaluation result of supply chain operation is generated according to the first preliminary evaluation result and the second preliminary evaluation result.
[0037] A second aspect of the present invention provides a supply chain data management system for home furnishings, the supply chain data management system for home furnishings comprising:
[0038] A receiving module, configured to receive a personalized request from a user; wherein the personalized request includes a preferred element and a secondary element of a home furnishing design solution;
[0039] An acquisition module, used to acquire primary feature data and secondary feature data associated with the home furnishing design solution according to the personalized formulation request;
[0040] An analysis module, used to perform preliminary analysis on the primary feature data and the secondary feature data through a preset data integration algorithm to obtain preliminary analysis results; and to create an initial supply chain efficiency model based on the preliminary analysis results;
[0041] A generation module is used to obtain market trend data and inventory status data from the supply chain database, and based on a preset dynamic update algorithm, adjust the parameters in the initial supply chain performance model to generate a supply chain optimization model;
[0042] A calculation module, used to calculate the association strength between various home furnishing products using a supply chain optimization model, and obtain customized association scores for different user requests; wherein the customized association scores are used to reflect the degree of optimization of each soft furnishing product in accordance with user needs, thereby identifying and recommending the home furnishing design solution that best meets user expectations and supply chain conditions;
[0043] The push module is used to input the obtained customized association score into the trained recommendation model to obtain a recommendation plan; and according to the output recommendation plan, select the preferred plan with the highest score from multiple home soft decoration design plans, and push the preferred plan with the highest score to the user terminal.
[0044] A third aspect of the present invention provides a supply chain data management device for home soft furnishings, comprising: a memory and at least one processor, wherein the memory stores instructions; the at least one processor calls the instructions in the memory so that the supply chain data management device for home soft furnishings executes the above-mentioned supply chain data management method for home soft furnishings.
[0045] A fourth aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the above-mentioned supply chain data management method for home furnishings.
[0046] In the technical solution provided by the present invention, the beneficial effects are as follows: the present invention provides a supply chain data management method and system for home furnishings, by receiving a personalized formulation request from a user end; according to the personalized formulation request, obtaining primary feature data and secondary feature data associated with a home furnishing design scheme; performing a preliminary analysis on the primary feature data and secondary feature data through a preset data integration algorithm to obtain a preliminary analysis result; creating an initial supply chain efficiency model based on the preliminary analysis result; obtaining market trend data and inventory status data from a supply chain database, and adjusting the parameters in the initial supply chain efficiency model based on a preset dynamic update algorithm to generate a supply chain optimization model; using the supply chain optimization model to calculate the association strength between each home furnishing product, obtaining a customized association score for different user requests; inputting the obtained customized association score into a trained recommendation model to obtain a recommendation scheme; and according to the output recommendation scheme, selecting the preferred scheme with the highest score from multiple home furnishing design schemes, and pushing the preferred scheme with the highest score to the user terminal. The present invention uses a preset data integration algorithm, and the method can efficiently analyze the personalized needs of users and key data of the supply chain, providing support for creating a more accurate supply chain efficiency model. By using a dynamic update algorithm, this method can adjust the supply chain efficiency model according to real-time data on market trends and inventory status, thereby improving the flexibility and accuracy of supply chain response. In combination with the personalized needs of users, this method can recommend home furnishing solutions that best meet users' expectations and market conditions by calculating the correlation strength and customized correlation scores between products. Through the optimized recommendation model, this method not only improves user satisfaction, but also improves the overall operational efficiency of the supply chain. BRIEF DESCRIPTION OF THE DRAWINGS
[0047] Figure 1 A schematic diagram of an embodiment of a supply chain data management method for home furnishings in an embodiment of the present invention;
[0048] Figure 2 A schematic diagram of an embodiment of a supply chain data management system for home furnishings in an embodiment of the present invention; DETAILED DESCRIPTION
[0049] Embodiments of the present invention provide a supply chain data management method and system for home furnishings. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0050] For ease of understanding, the specific process of the embodiment of the present invention is described below. Figure 1 An embodiment of the supply chain data management method for home furnishings in the embodiment of the present invention includes:
[0051] Step 101: receiving a personalized request from a user; wherein the personalized request includes a preferred element and a secondary element of a home furnishing design solution;
[0052] It is understandable that the execution subject of the present invention may be a supply chain data management system for home furnishings, or a terminal or a server, which is not limited here. The embodiment of the present invention is described by taking a server as the execution subject as an example.
[0053] Specifically, step 101 is implemented as follows:
[0054] Receive the personalized request from the user:
[0055] The user's personalized request includes the preferred elements and secondary elements of the home furnishing design plan. The preferred elements refer to the elements that the user prioritizes in the soft furnishing design, such as color, material, style, etc.; the secondary elements are the alternative options when the user's preferred elements cannot be met.
[0056] For example, through the user interface or mobile application, users can input their personalized needs and preferences for home soft furnishings, including preferred elements such as red, cotton, modern style, etc., and secondary elements such as blue, silk, classical style, etc., and transmit them to the backend system through the network.
[0057] Step 102: acquiring primary feature data and secondary feature data associated with the home furnishing design solution according to the personalized formulation request;
[0058] Specifically, step 102 is implemented as follows:
[0059] According to the personalized customization request, primary feature data and secondary feature data related to the home furnishing design solution are obtained:
[0060] Primary feature data refers to important data directly related to the preferred elements in the user's personalized request, such as color, material, style, etc.; secondary feature data is auxiliary data related to the preferred elements, which is used to supplement and assist the description of the primary feature data.
[0061] For example, the system can extract primary and secondary feature data from the home soft decoration design database through intelligent algorithms, such as color schemes related to the red selected by the user, material combinations related to cotton, and home soft decoration design schemes that conform to modern styles.
[0062] Step 103: Perform a preliminary analysis on the primary feature data and the secondary feature data using a preset data integration algorithm to obtain a preliminary analysis result; and create an initial supply chain efficiency model based on the preliminary analysis result;
[0063] Specifically, step 103 is implemented as follows:
[0064] The primary feature data and secondary feature data are preliminarily analyzed through the preset data integration algorithm to obtain the preliminary analysis results:
[0065] The preset data integration algorithm refers to an algorithm built based on data mining, machine learning or artificial intelligence technology, which is used to integrate and analyze large-scale, multi-source home soft decoration design data to discover the correlation and patterns between the data.
[0066] For example, the system can use cluster analysis, association rule mining or decision tree algorithm to conduct preliminary analysis on the primary feature data and secondary feature data, so as to obtain analysis results such as the correlation, importance and priority between each design feature.
[0067] Based on the preliminary analysis results, an initial supply chain performance model is created:
[0068] The initial supply chain efficiency model refers to a mathematical model constructed based on the preliminary analysis results to describe the relationship between home soft furnishing design elements, including the degree of correlation, influence and transmission rules of design elements.
[0069] For example, the system can build a supply chain efficiency model based on the preliminary analysis results, conduct correlation analysis on the primary and secondary characteristics of home soft furnishing design, and reveal the relationship network between them, thereby providing a reference for subsequent intelligent supply chain management and production scheduling.
[0070] Step 104: Obtain market trend data and inventory status data from the supply chain database, and adjust parameters in the initial supply chain performance model based on a preset dynamic update algorithm to generate a supply chain optimization model;
[0071] Specifically, step 104 is implemented as follows:
[0072] Get market trend data and inventory status data from the supply chain database:
[0073] Supply chain database refers to an information system database that contains market trends, inventory status, and supply chain operation-related data. Market trend data includes product sales, market demand forecasts, etc.; inventory status data includes information such as inventory of raw materials and finished products, inventory turnover rate, etc.
[0074] For example, the system can obtain market trend data such as product sales, market demand, and inventory status data, such as raw material inventory, finished product inventory, and other information from the supply chain database to support subsequent supply chain optimization decisions.
[0075] Based on the preset dynamic update algorithm, the parameters in the initial supply chain efficiency model are adjusted to generate a supply chain optimization model:
[0076] The dynamic update algorithm is an algorithm that dynamically adjusts and optimizes the parameters in the supply chain performance model based on real-time information such as market trend data and inventory status data. This algorithm can ensure that the supply chain optimization model keeps pace with actual market changes.
[0077] For example, based on market trend data and inventory status data, the system can use a dynamic update algorithm to make real-time adjustments to the parameters in the initial supply chain efficiency model, generate a supply chain optimization model that adapts to the current market status, and achieve dynamic optimization scheduling of supply chain operations.
[0078] Step 105: Calculate the association strength between each home furnishing soft furnishing product using the supply chain optimization model to obtain customized association scores for different user requests; wherein the customized association scores are used to reflect the degree of optimization of each soft furnishing product in accordance with user needs, thereby identifying and recommending the home furnishing soft furnishing design solution that best meets user expectations and supply chain conditions;
[0079] Specifically, step 105 is implemented as follows:
[0080] Use the supply chain optimization model to calculate the correlation strength between various home furnishing products:
[0081] Through the supply chain optimization model, mathematical models, machine learning algorithms or neural networks can be used to calculate the correlation and association between different home furnishing products and their impact in the supply chain. These technologies can be calculated based on big data analysis, cross-selling analysis, user feedback and other data.
[0082] For example, collaborative filtering algorithms, association rule mining, or deep learning models can be used to calculate the strength of associations between home furnishing products to reveal their potential associations and the degree of mutual influence.
[0083] Get customized relevance scores for different user requests:
[0084] Customized association score refers to the score that reflects the degree of fit and optimization of home furnishing products, calculated for each user request based on user needs and preferences and the strength of association between home furnishing products. This can be achieved by extracting features and performing weighted analysis on user needs and combining the strength of association between home furnishing products.
[0085] For example, customized correlation scores for different soft furnishing product combinations can be calculated based on user demand characteristics, product features, and supply chain optimization models, thereby providing different users with home soft furnishing design solutions that best meet their needs and supply chain conditions.
[0086] Step 106: input the obtained customized association score into the trained recommendation model to obtain a recommendation plan; and based on the output recommendation plan, select the preferred plan with the highest score from multiple home soft decoration design plans, and push the preferred plan with the highest score to the user terminal.
[0087] Specifically, step 106 is implemented as follows:
[0088] Input the customized relevance score into the trained recommendation model to obtain the recommendation solution:
[0089] Customized relevance scores are calculated based on the strength of the association between user needs and home furnishing products, and these scores are input into a trained recommendation model. This recommendation model can use collaborative filtering, content recommendation or deep learning techniques to comprehensively consider user needs and product relevance.
[0090] For example, customized association scores are used as input features of the recommendation model, combined with user portraits, product features and other information, and after model calculation and prediction, a home furnishing recommendation plan for the user's request is obtained.
[0091] According to the output recommendation scheme, select the preferred scheme with the highest score from multiple home furnishing design schemes:
[0092] After obtaining multiple home furnishing design solutions through the recommendation model, the system will compare and optimize the solutions according to their scores and select the optimal solution with the highest score. This process can be achieved using an optimization algorithm or a multi-objective optimization algorithm.
[0093] For example, the system can conduct a comprehensive evaluation of multiple home furnishing design schemes based on the output of the recommendation model, and select the preferred scheme with the highest score as the final recommendation.
[0094] Push the best solution with the highest score to the user terminal:
[0095] The final selected optimal solution will be pushed to the user terminal for the user to view and confirm. This process may involve technologies such as push system, user terminal interface and data transmission.
[0096] For example, the system can use the push service to push the highest-scoring preferred solution to the user's mobile application or web page in real time so that the user can view and confirm it.
[0097] Another embodiment of the supply chain data management method for home furnishings in the embodiment of the present invention includes:
[0098] The method of performing a preliminary analysis on the primary feature data and the secondary feature data by using a preset data integration algorithm to obtain a preliminary analysis result; and creating an initial supply chain efficiency model based on the preliminary analysis result, including:
[0099] Performing a preliminary analysis on the primary feature data and the secondary feature data to obtain first data and second data; wherein the first data at least includes the user's design preference data, space requirement data and budget constraint data; and the second data at least includes historical purchase data, regional fashion trend data and supply chain capability data;
[0100] Performing a preliminary evaluation of the first data and the second data through a preset data integration algorithm to obtain a preliminary evaluation result of the supply chain operation;
[0101] Based on the preliminary evaluation results of supply chain operations, an initial supply chain performance model is created; wherein the initial supply chain performance model is used to characterize the relationship between commodity flow, information flow and capital flow in the supply chain;
[0102] The created initial supply chain efficiency model is trained to obtain a trained initial supply chain efficiency model.
[0103] Specific, important term explanations
[0104] Primary characteristic data: refers to data that has a significant impact on supply chain performance, such as user design preferences, space requirements, and budget constraints.
[0105] Secondary characteristic data: refers to data that has a certain impact on supply chain efficiency but has a smaller impact than primary characteristic data, such as historical purchase data, regional trends, and supply chain capabilities.
[0106] Data integration algorithms: Computational methods used to analyze and process data from different sources and types and fuse them into useful information to support decision making.
[0107] Supply chain performance model: A mathematical model or framework that represents the interaction between commodity flow, information flow and capital flow in a supply chain and is used to evaluate and optimize the performance of the supply chain.
[0108] Technical solution application scenarios
[0109] Interior design companies: Interior design companies use this technology solution to analyze customer preferences, optimize design solutions, and manage product supply chains more efficiently.
[0110] Home building materials distributors: Distributors use this technology solution to analyze market trends and supply chain capabilities to achieve inventory optimization and cost control.
[0111] E-commerce platforms: By integrating user data and market trends, e-commerce platforms can adjust product supply, optimize logistics, and enhance customer satisfaction.
[0112] Specific detailed plan:
[0113] Data Collection and Analysis:
[0114] User design preference data, space requirement data, and budget constraint data are collected as primary feature data.
[0115] Consider historical purchasing data, regional fashion trend data, and supply chain capability data as secondary feature data.
[0116] A data integration algorithm is applied to perform a preliminary analysis on the primary feature data and the secondary feature data to generate first data and second data.
[0117] Initial model creation and training:
[0118] Based on the preliminary evaluation results, create an initial supply chain efficiency model that reflects the relationship between commodity flow, information flow and capital flow.
[0119] The initial supply chain effectiveness model is iteratively trained and parameters are adjusted to improve forecast accuracy and operational efficiency.
[0120] Model optimization and application:
[0121] Use trained models to support supply chain decisions, such as inventory management, logistics optimization, and demand forecasting.
[0122] Continuously collect supply chain operation data to further refine and optimize the supply chain efficiency model.
[0123] In the embodiments of the present invention, the beneficial effects are as follows: the embodiments of the present invention can achieve coordinated optimization of each link of the supply chain and improve overall operational efficiency by accurately analyzing customer needs and market trends. The initial supply chain efficiency model helps reduce inventory backlogs and excessive inventory, reduces capital pressure, and thus reduces operating costs. The supply chain efficiency model improves the response speed to market changes and improves service quality through real-time data analysis and dynamic adjustment. The application of the supply chain efficiency model can provide data-driven decision support and enhance the accuracy of supply chain planning and management.
[0124] Another embodiment of the supply chain data management method for home furnishings in the embodiment of the present invention includes: training the created initial supply chain efficiency model to obtain the trained initial supply chain efficiency model, including:
[0125] Acquire multi-source data of the supply chain, and input the multi-source data into the constructed initial supply chain performance model; wherein the multi-source data is training sample data including at least commodity circulation, information exchange records, capital flow, market dynamics data, historical data and real-time data, customer feedback and service quality data; the initial supply chain performance model is composed of a commodity flow analysis sub-model, an information flow analysis sub-model, a capital flow monitoring sub-model, a demand response prediction sub-model, a risk assessment sub-model and a customer satisfaction evaluation sub-model, and each sub-model focuses on different supply chain dimensions;
[0126] The commodity flow analysis sub-model processes multi-source data, analyzes the commodity flow pattern from the starting point to the end point, determines the commodity flow speed and efficiency, and outputs commodity liquidity indicators;
[0127] The information exchange records are analyzed through the information flow analysis sub-model, the speed and accuracy of information transmission are evaluated, and information flow indicators are output;
[0128] Monitor and analyze capital flow through the capital flow monitoring sub-model, evaluate payment timeliness and capital utilization efficiency, and output capital circulation efficiency indicators;
[0129] Based on the demand response prediction sub-model and combined with market dynamics data, the adaptability of the supply chain to emerging demands is analyzed and demand adaptability indicators are output;
[0130] Based on the risk assessment sub-model, the risk points in the supply chain are assessed according to historical data and real-time data, and risk assessment indicators are output;
[0131] Based on the customer satisfaction evaluation sub-model, the satisfaction of the end-user experience is evaluated according to customer feedback and service quality data, and the customer satisfaction index is output;
[0132] Extracting preset standard values from multi-source data of the supply chain; wherein the preset standard values include the actual commodity flow rate, actual information circulation rate, actual capital turnover efficiency, actual demand adaptability, actual risk occurrence probability, and actual customer satisfaction under the best operating conditions;
[0133] Calculate the error value based on the difference between each indicator output by each sub-model of the constructed initial supply chain efficiency model and the preset standard value; wherein the error value is the deviation between the predicted indicator and the actual indicator;
[0134] Based on the preset optimization algorithm, the parameters of each sub-model of the initial supply chain efficiency model are gradually adjusted to minimize various error values until the training of the created initial supply chain efficiency model is completed to obtain the trained initial supply chain efficiency model.
[0135] Specific, important term explanations
[0136] Multi-source data: Data sets derived from multiple different data sources are aggregated to provide a comprehensive view of supply chain operations.
[0137] Supply Chain Effectiveness Model: A complex model used to evaluate, monitor and optimize the performance of the supply chain, involving multiple aspects such as the flow of goods, information flow and capital flow.
[0138] Commodity flow analysis sub-model: This is a model branch that focuses on the speed and efficiency of item flow and generates indicators related to commodity flow.
[0139] Information flow analysis sub-model: a model branch that mines information flow patterns and transmission efficiency, and provides key indicators of information circulation.
[0140] Fund flow monitoring sub-model: A model branch that tracks and analyzes fund flow conditions and generates indicators of fund circulation speed and efficiency.
[0141] Demand response prediction sub-model: This model branch analyzes the supply chain responsiveness based on market trends and outputs demand adaptability indicators.
[0142] Risk Assessment Sub-Model: A model branch that uses historical and real-time data to assess potential risks in the supply chain and generate risk assessment indicators.
[0143] Customer satisfaction evaluation sub-model: A model branch that evaluates service quality based on customer feedback and provides customer satisfaction indicators.
[0144] Optimization algorithm: A predetermined computational process used to adjust model parameters to improve model performance and reduce prediction errors.
[0145] Technical solution application scenarios
[0146] Supply Chain Management System: The model is integrated into supply chain management software to provide real-time data analysis and performance improvement suggestions.
[0147] Logistics companies: Logistics companies use models to monitor and optimize the flow of goods, information sharing, and funding arrangements.
[0148] Manufacturing companies: Manufacturers use models to optimize production plans, reduce risks and improve response speed to market demand.
[0149] Distribution and Retailers: The retail industry uses models to improve inventory management efficiency, optimize product delivery, and ensure high customer satisfaction.
[0150] Specific detailed plan:
[0151] Processing and application of multi-source data:
[0152] The implementation phase begins by integrating multi-source data from different channels, such as data from logistics tracking systems, sales system data, market research reports, and real-time social media trend analysis.
[0153] These data are preprocessed, including data cleaning, format unification and preliminary classification, to facilitate subsequent analysis and processing.
[0154] The specific working mechanism of the sub-model is as follows:
[0155] Commodity flow analysis sub-model: Apply machine learning algorithms, such as random forests or neural networks, to predict and optimize the storage, transportation, and distribution processes of commodities.
[0156] Information flow parsing sub-model: Use natural language processing (NLP) technology to parse communication records and improve the accuracy and efficiency of information processing.
[0157] Fund flow monitoring sub-model: Combine time series analysis and economic models to predict fund flow trends and optimize fund allocation and risk management.
[0158] Demand response forecasting sub-model: Combines historical sales data with market dynamics and uses predictive analytics tools such as regression analysis or time series analysis to predict future demand.
[0159] Risk assessment sub-model: By analyzing historical accident records and current market conditions, using methods such as Bayesian networks or decision trees to identify and assess potential risks.
[0160] Customer Satisfaction Evaluation Sub-Model: Combines online survey feedback, social media sentiment analysis, and customer service records to evaluate customer satisfaction using sentiment analysis and classification algorithms.
[0161] Model training and optimization process:
[0162] Use historical data and real-time data to train the model, and find the optimal model parameters through cross-validation and model parameter adjustment techniques.
[0163] Apply multiple optimization algorithms, such as gradient descent or genetic algorithms, to precisely tune the parameters of each sub-model to reduce errors and improve prediction accuracy.
[0164] Review the model's performance regularly and continuously adjust and optimize model parameters based on new market dynamics and data trends.
[0165] Model output and application:
[0166] Outputs include, but are not limited to, key performance indicators such as inventory levels, logistics time, cost efficiency, market demand response time, risk level and customer satisfaction.
[0167] Use model outputs for real-time monitoring and decision support, such as dynamically adjusting inventory levels, optimizing logistics routes, and predicting and managing changes in market demand.
[0168] Generate supply chain performance reports regularly to provide management with in-depth analytical insights and optimization recommendations.
[0169] In the embodiment of the present invention, the beneficial effects are as follows: The model of the embodiment of the present invention integrates multi-source data to provide relevant parties with a clear and comprehensive supply chain view. Quantitative performance indicators provide data support for management, enhancing the confidence and accuracy of decision-making. Through accurate prediction and monitoring, optimal allocation of resources is achieved and waste is reduced. The risk assessment sub-model helps to identify potential supply chain risks and strengthen risk prevention and control. By real-time monitoring of customer satisfaction and rapid response and adjustment, service levels and customer satisfaction are continuously improved.
[0170] Another embodiment of the supply chain data management method for home furnishings in the embodiment of the present invention includes: performing a preliminary evaluation on the first data and the second data by using a preset data integration algorithm to obtain a preliminary evaluation result of the supply chain operation;
[0171] Extracting from the first data by a preset first data extraction algorithm to obtain first feature data, and extracting from the second data by a preset second data extraction algorithm to obtain second feature data; wherein the first feature data is used to characterize the purchasing power and personal style preference of the user; and the second feature data is used to characterize seasonal influence and regional market trend;
[0172] Performing data conversion processing on the first feature data to obtain a first feature vector; performing data conversion processing on the second feature data to obtain a second feature vector;
[0173] Based on a preset data fusion mechanism, the first feature vector and the second feature vector are fused to obtain a target fusion vector of a multi-dimensional analysis result; wherein the target fusion vector is used to reflect the impact of various internal and external factors on the overall operation of the supply chain;
[0174] A multi-level supply chain data representation framework is constructed based on the target fusion vector; wherein the multi-level supply chain data representation framework establishes a first mapping model between the first data and the target fusion data through a first mapping algorithm, and establishes a second mapping model between the second data and the target fusion data through a second mapping algorithm,
[0175] Performing a preliminary evaluation on the first data based on the first mapping model to obtain a first preliminary evaluation result of the supply chain operation;
[0176] Performing a preliminary evaluation on the first data based on the second mapping model to obtain a second preliminary evaluation result of the supply chain operation;
[0177] A preliminary evaluation result of supply chain operation is generated according to the first preliminary evaluation result and the second preliminary evaluation result.
[0178] Specific, important term explanations
[0179] Data integration algorithm: A procedure or series of steps used to merge and reconcile different data sources into a unified view of the data.
[0180] Feature data extraction algorithm: A technique used to identify and extract key information from raw data, aiming to capture important attributes of the data.
[0181] First characteristic data: data characteristics that describe user purchasing power, personal style preferences, etc.
[0182] Second characteristic data: data characteristics that describe seasonal impacts, regional market trends, etc.
[0183] Feature vector: A numerical feature representation obtained through transformation processing, which is convenient for use in various computing models.
[0184] Data fusion mechanism: A processing technique used to merge multiple feature vectors to form a fused vector that fully reflects the characteristics of the data.
[0185] Multi-level supply chain data representation framework: A structure for organizing and representing supply chain data relationships that can represent multiple data levels simultaneously.
[0186] Mapping model: In the data representation framework, a relationship model between the original data and the target vector is established through a specific algorithm.
[0187] Application scenarios of technical solutions
[0188] Supply chain system for home furnishing companies: Use this technical solution to analyze customer needs and market trends, and optimize product design and inventory management.
[0189] Market trend analysis software: Combines user purchase data and seasonal market changes to generate in-depth market trend reports.
[0190] Personalized marketing and recommendation system: Provide personalized shopping experience through data analysis of users' personal style preferences and purchasing power.
[0191] Regional Economic Research: Evaluate seasonal patterns of consumer behavior and market trends in specific regions.
[0192] Detailed plan:
[0193] Data integration and feature extraction
[0194] In this embodiment, supply chain data management begins with the integration of two sets of data, which are pre-processed and synchronized using data integration algorithms to form a unified data set. The first set of data (first data) may contain customer purchase history, online consumption behavior, and customer feedback, while the second set of data (second data) may cover market reports, seasonal sales patterns, and economic indicators of geographic regions.
[0195] The first data extraction algorithm is able to identify key variables, such as customer income level and online behavior, which represent the user's purchasing power.
[0196] Personal style preferences may be extracted from purchase history and product reviews through data mining techniques such as association rule learning or cluster analysis.
[0197] The second data extraction algorithm focuses on macro-level trends, which includes how to capture seasonal fluctuations and market development trends using mathematical models.
[0198] Data conversion processing and feature vector generation
[0199] The conversion process of the first feature data and the second feature data includes a standardization step to make the feature data suitable for subsequent analysis, for example, using normalization or Z-score standardization technology.
[0200] Feature vectors are constructed through an encoding process, which may include one-hot encoding or vector embedding, to better represent the importance of the data in the model.
[0201] Data fusion and multi-dimensional analysis
[0202] The data fusion mechanism may combine the feature vectors through weighted averaging, principal component analysis (PCA), or deep learning methods such as deep belief networks.
[0203] The target fusion vector is the result of multi-dimensional analysis, reflecting how user purchasing behavior and macro market trends interact and affect supply chain performance.
[0204] Multi-level supply chain data representation framework and preliminary evaluation
[0205] The multi-level supply chain data representation framework is a complex mapping system built through statistical models, graphical models or deep learning architectures.
[0206] The first mapping model and the second mapping model are implemented by machine learning techniques (such as decision trees, support vector machines, or artificial neural networks), which map original data to target fusion vectors.
[0207] Based on these mapping models, the preliminary evaluation results can provide managers with immediate feedback on supply chain performance. The first and second preliminary evaluation results can give a comprehensive overview of the supply chain operation status, and then derive the overall preliminary evaluation results to provide a basis for further analysis and decision-making.
[0208] In the embodiment of the present invention, the beneficial effects are as follows: the embodiment of the present invention can use multi-source data more comprehensively and improve the analytical value and utilization efficiency of data by establishing a target fusion vector. By using a multi-level supply chain data representation framework, various aspects of supply chain operations can be predicted more accurately and the decision-making process can be optimized. Through the preliminary evaluation results, supply chain managers can quickly obtain information about the operating status of the supply chain and provide immediate adjustment strategies. By analyzing user style preferences and purchasing power data, companies can better meet user needs and improve customer satisfaction and loyalty. Through the analysis of seasonal effects and regional trends, the supply chain can adapt to market changes more flexibly and reduce excess inventory and out-of-stock risks.
[0209] The above describes the supply chain data management method of home furnishings in the embodiment of the present invention. The following describes the supply chain data management system of home furnishings in the embodiment of the present invention. Figure 2 In one embodiment of the present invention, a supply chain data management system for home furnishings includes:
[0210] A receiving module, configured to receive a personalized request from a user; wherein the personalized request includes a preferred element and a secondary element of a home furnishing design solution;
[0211] An acquisition module, used to acquire primary feature data and secondary feature data associated with the home furnishing design solution according to the personalized formulation request;
[0212] An analysis module, used to perform preliminary analysis on the primary feature data and the secondary feature data through a preset data integration algorithm to obtain preliminary analysis results; and to create an initial supply chain efficiency model based on the preliminary analysis results;
[0213] A generation module is used to obtain market trend data and inventory status data from the supply chain database, and based on a preset dynamic update algorithm, adjust the parameters in the initial supply chain performance model to generate a supply chain optimization model;
[0214] A calculation module, used to calculate the association strength between various home furnishing products using a supply chain optimization model, and obtain customized association scores for different user requests; wherein the customized association scores are used to reflect the degree of optimization of each soft furnishing product in accordance with user needs, thereby identifying and recommending the home furnishing design solution that best meets user expectations and supply chain conditions;
[0215] The push module is used to input the obtained customized association score into the trained recommendation model to obtain a recommendation plan; and according to the output recommendation plan, select the preferred plan with the highest score from multiple home soft decoration design plans, and push the preferred plan with the highest score to the user terminal.
[0216] The present invention also provides a supply chain data management device for home soft furnishings, the supply chain data management device for home soft furnishings comprising a memory and a processor, the memory storing computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor executes the steps of the supply chain data management method for home soft furnishings in the above-mentioned embodiments.
[0217] The present invention also provides a computer-readable storage medium, which may be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. Instructions are stored in the computer-readable storage medium. When the instructions are executed on a computer, the computer executes the steps of the supply chain data management method for home furnishings.
[0218] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0219] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the whole or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.
[0220] As described above, the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features thereof may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims
1. A supply chain data management method for home furnishings, characterized in that: The following steps are involved: Receiving a personalized request from a user; wherein the personalized request includes a preferred element and a secondary element of a home furnishing design solution; According to the personalized customization request, primary feature data and secondary feature data associated with the home furnishing design solution are obtained; Performing a preliminary analysis on the primary feature data and the secondary feature data through a preset data integration algorithm to obtain a preliminary analysis result; creating an initial supply chain efficiency model based on the preliminary analysis result; Performing a preliminary analysis on the primary feature data and the secondary feature data through a preset data integration algorithm to obtain a preliminary analysis result; creating an initial supply chain efficiency model based on the preliminary analysis result, including: performing a preliminary analysis on the primary feature data and the secondary feature data to obtain first data and second data; wherein the first data at least includes the user's design preference data, space requirement data and budget constraint data; the second data at least includes historical purchase data, regional fashion trend data and supply chain capability data; performing a preliminary evaluation on the first data and the second data through a preset data integration algorithm to obtain a preliminary evaluation result of the supply chain operation; creating an initial supply chain efficiency model based on the preliminary evaluation result of the supply chain operation; wherein the initial supply chain efficiency model is used to characterize the relationship between the commodity flow, information flow and capital flow in the supply chain; training the created initial supply chain efficiency model to obtain a trained initial supply chain efficiency model; The created initial supply chain effectiveness model is trained to obtain the trained initial supply chain effectiveness model, including: obtaining multi-source data of the supply chain, and inputting the multi-source data into the constructed initial supply chain effectiveness model; wherein the multi-source data is training sample data including at least commodity circulation, information exchange records, capital flow, market dynamics data, historical data and real-time data, customer feedback and service quality data, and the initial supply chain effectiveness model is composed of a commodity flow analysis sub-model, an information flow analysis sub-model, a capital flow monitoring sub-model, a demand response prediction sub-model, a risk assessment sub-model and a customer satisfaction evaluation sub-model, and each sub-model focuses on a different supply chain dimension; the multi-source data is processed by the commodity flow analysis sub-model, the flow mode of the commodity from the starting point to the end point is analyzed, the flow speed and flow efficiency of the commodity are determined, and the commodity liquidity index is output; the information exchange record is analyzed by the information flow analysis sub-model, the speed and accuracy of information transmission are evaluated, and the information circulation index is output; the capital flow monitoring sub-model is used to monitor and analyze the capital flow, the payment timeliness and capital utilization efficiency are evaluated, and the capital circulation efficiency index is output; based on Based on the demand response prediction sub-model, combined with market dynamic data, the adaptability of the supply chain to emerging demands is analyzed, and demand adaptability indicators are output; based on the risk assessment sub-model, risk points in the supply chain are evaluated based on historical data and real-time data, and risk assessment indicators are output; based on the customer satisfaction evaluation sub-model, the satisfaction of the end-user experience is evaluated based on customer feedback and service quality data, and customer satisfaction indicators are output; preset standard values are extracted from multi-source data of the supply chain; wherein the preset standard values include the actual commodity flow rate, actual information circulation rate, actual capital turnover efficiency, actual demand adaptability, actual risk occurrence probability, and actual customer satisfaction under the optimal operating state; according to the difference between the various indicators output by each sub-model of the constructed initial supply chain effectiveness model and the preset standard values, the error value is calculated; wherein the error value is the deviation between the predicted indicator and the actual indicator; based on the preset optimization algorithm, the parameters of each sub-model of the initial supply chain effectiveness model are gradually adjusted to minimize the various error values until the training of the created initial supply chain effectiveness model is completed to obtain the trained initial supply chain effectiveness model; Obtain market trend data and inventory status data from the supply chain database, and adjust the parameters in the initial supply chain performance model based on a preset dynamic update algorithm to generate a supply chain optimization model; The supply chain optimization model is used to calculate the association strength between various home furnishing products, and obtain customized association scores for different user requests; wherein the customized association scores are used to reflect the degree of optimization of each soft furnishing product in accordance with user needs, so as to identify and recommend the home furnishing design solution that best meets user expectations and supply chain conditions; The obtained customized association score is input into the trained recommendation model to obtain a recommendation plan; and based on the output recommendation plan, the preferred plan with the highest score is selected from multiple home soft decoration design plans, and the preferred plan with the highest score is pushed to the user terminal.
2. The supply chain data management method for home furnishings according to claim 1, characterized in that: The first data and the second data are preliminarily evaluated by a preset data integration algorithm to obtain a preliminary evaluation result of the supply chain operation; Extracting from the first data by a preset first data extraction algorithm to obtain first feature data, and extracting from the second data by a preset second data extraction algorithm to obtain second feature data; wherein the first feature data is used to characterize the purchasing power and personal style preference of the user; and the second feature data is used to characterize seasonal influence and regional market trend; Performing data conversion processing on the first feature data to obtain a first feature vector; performing data conversion processing on the second feature data to obtain a second feature vector; Based on a preset data fusion mechanism, the first feature vector and the second feature vector are fused to obtain a target fusion vector of a multi-dimensional analysis result; wherein the target fusion vector is used to reflect the impact of various internal and external factors on the overall operation of the supply chain; A multi-level supply chain data representation framework is constructed based on the target fusion vector; wherein the multi-level supply chain data representation framework establishes a first mapping model between the first data and the target fusion data through a first mapping algorithm, and establishes a second mapping model between the second data and the target fusion data through a second mapping algorithm, Performing a preliminary evaluation on the first data based on the first mapping model to obtain a first preliminary evaluation result of the supply chain operation; Performing a preliminary evaluation on the first data based on the second mapping model to obtain a second preliminary evaluation result of the supply chain operation; A preliminary evaluation result of supply chain operation is generated according to the first preliminary evaluation result and the second preliminary evaluation result.
3. A supply chain data management system for home furnishings, characterized in that: The supply chain data management system for home furnishings includes: A receiving module, configured to receive a personalized request from a user; wherein the personalized request includes a preferred element and a secondary element of a home furnishing design solution; An acquisition module, used to acquire primary feature data and secondary feature data associated with the home furnishing design solution according to the personalized formulation request; An analysis module, used to perform preliminary analysis on primary feature data and secondary feature data through a preset data integration algorithm to obtain preliminary analysis results; and create an initial supply chain efficiency model based on the preliminary analysis results; the preliminary analysis on primary feature data and secondary feature data through a preset data integration algorithm to obtain preliminary analysis results; and create an initial supply chain efficiency model based on the preliminary analysis results, including: performing preliminary analysis on primary feature data and secondary feature data to obtain first data and second data; wherein the first data at least includes user design preference data, space requirement data and budget constraint data; the second data at least includes historical purchase data, regional fashion trend data and supply chain capability data; performing preliminary evaluation on the first data and the second data through a preset data integration algorithm to obtain preliminary evaluation results of supply chain operations; and creating an initial supply chain efficiency model based on the preliminary evaluation results of supply chain operations; wherein the initial supply chain efficiency model is used to characterize the relationship between commodity flow, information flow and capital flow in the supply chain; and training the created initial supply chain efficiency model to obtain a trained initial supply chain efficiency model; The created initial supply chain effectiveness model is trained to obtain the trained initial supply chain effectiveness model, including: obtaining multi-source data of the supply chain, and inputting the multi-source data into the constructed initial supply chain effectiveness model; wherein the multi-source data is training sample data including at least commodity circulation, information exchange records, capital flow, market dynamics data, historical data and real-time data, customer feedback and service quality data, and the initial supply chain effectiveness model is composed of a commodity flow analysis sub-model, an information flow analysis sub-model, a capital flow monitoring sub-model, a demand response prediction sub-model, a risk assessment sub-model and a customer satisfaction evaluation sub-model, and each sub-model focuses on a different supply chain dimension; the multi-source data is processed by the commodity flow analysis sub-model, the flow mode of the commodity from the starting point to the end point is analyzed, the flow speed and flow efficiency of the commodity are determined, and the commodity liquidity index is output; the information exchange record is analyzed by the information flow analysis sub-model, the speed and accuracy of information transmission are evaluated, and the information circulation index is output; the capital flow monitoring sub-model is used to monitor and analyze the capital flow, the payment timeliness and capital utilization efficiency are evaluated, and the capital circulation efficiency index is output; based on Based on the demand response prediction sub-model, combined with market dynamic data, the adaptability of the supply chain to emerging demands is analyzed, and demand adaptability indicators are output; based on the risk assessment sub-model, risk points in the supply chain are evaluated based on historical data and real-time data, and risk assessment indicators are output; based on the customer satisfaction evaluation sub-model, the satisfaction of the end-user experience is evaluated based on customer feedback and service quality data, and customer satisfaction indicators are output; preset standard values are extracted from multi-source data of the supply chain; wherein the preset standard values include the actual commodity flow rate, actual information circulation rate, actual capital turnover efficiency, actual demand adaptability, actual risk occurrence probability, and actual customer satisfaction under the optimal operating state; according to the difference between the various indicators output by each sub-model of the constructed initial supply chain effectiveness model and the preset standard values, the error value is calculated; wherein the error value is the deviation between the predicted indicator and the actual indicator; based on the preset optimization algorithm, the parameters of each sub-model of the initial supply chain effectiveness model are gradually adjusted to minimize the various error values until the training of the created initial supply chain effectiveness model is completed to obtain the trained initial supply chain effectiveness model; A generation module is used to obtain market trend data and inventory status data from the supply chain database, and based on a preset dynamic update algorithm, adjust the parameters in the initial supply chain performance model to generate a supply chain optimization model; A calculation module, used to calculate the association strength between various home furnishing products using a supply chain optimization model, and obtain customized association scores for different user requests; wherein the customized association scores are used to reflect the degree of optimization of each soft furnishing product in accordance with user needs, thereby identifying and recommending the home furnishing design solution that best meets user expectations and supply chain conditions; The push module is used to input the obtained customized association score into the trained recommendation model to obtain a recommendation plan; and according to the output recommendation plan, select the preferred plan with the highest score from multiple home soft decoration design plans, and push the preferred plan with the highest score to the user terminal.
4. A supply chain data management device for home furnishings, characterized in that: The supply chain data management device for home furnishings includes: a memory and at least one processor, wherein instructions are stored in the memory; The at least one processor calls the instructions in the memory to enable the home furnishing supply chain data management device to execute the home furnishing supply chain data management method as described in any one of claims 1-2.
5. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by the processor, the supply chain data management method for home furnishings as described in any one of claims 1-2 is implemented.
Citation Information
Patent Citations
Method for realizing home residence overall solution based on informationized business mode
CN107657551A
Supply chain platform-based supplier screening method and system, and storage medium
CN114936869A
Retail management method and system based on supply chain big data platform
CN116739217A
Supply chain demand forecasting and planning
US20020169657A1
Computer-implemented system and method for assessing supply chain solutions
US20030229526A1
