A customized home hardware supply chain digital collaborative management system

Abstract

The application discloses a kind of custom home spare and accessory supply chain digital collaborative management system, specifically relates to supply chain data management technical field, including internet of things terminal equipment control module, custom home data acquisition module, supply chain collaborative prediction module, user demand intelligent matching module, the present application is by collecting each link data of supply chain, the home demand of user, and is assembled as demand gene sequence, demand gene sequence is split, with system database is matched with multiple target optimization, generates not less than two groups of supply chain resource matching scheme, constructs risk characteristic index system, by objective function, the value of each scheme is calculated, generates the optimal supply chain resource matching scheme, and creates production task, realizes from user demand acquisition, supply chain data acquisition, resource matching, the whole process digital management of production task creation, promote the real-time intercommunication and collaborative decision of information between multiple subjects, improve supply chain overall operation efficiency.

Description

Technical Field

[0001] This invention relates to the field of supply chain data management technology, and more specifically, to a digital collaborative management system for the supply chain of customized home furnishing parts. Background Technology

[0002] In recent years, with the deep application of industrial internet platforms, the iterative upgrading of big data analytics technology, and the breakthrough development of artificial intelligence algorithms, the global manufacturing and service industries are accelerating their digital transformation. Some leading industries have already taken the lead in building a digital collaborative system across the entire supply chain. In the customized home furnishing sector, a typical discrete manufacturing field, driven by consumption upgrades and personalized demands, the product system exhibits the distinct characteristics of "multiple varieties, small batches, and short cycles." As the core material foundation for customized home furnishing production, the efficiency of the supply chain management of spare parts not only directly determines the entire product lifecycle from design to delivery, but also profoundly affects the level of quality stability control during the production process, as well as the cost control capabilities in key areas such as raw material procurement, warehousing and logistics, and inventory turnover. This has become a core bottleneck restricting the industry's digital transformation.

[0003] However, in actual use, it still has some shortcomings, such as insufficient integration depth and flexibility of existing supply chain management systems, differences in data formats and technical architectures between different systems, and only superficial interoperability. When faced with significant adjustments to business processes or new business scenarios, it is difficult to adapt quickly and cannot flexibly meet the needs of enterprises. Traditional supply chain management systems struggle to achieve precise matching between products and user needs. They lack effective means to deeply integrate the two, enabling dynamic matching and data interaction between demand and products in a manner similar to precise gene editing. This results in slow and inaccurate supply chain responses to user needs, often leading to mismatches between products and demand. Summary of the Invention

[0004] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a digital collaborative management system for the supply chain of customized home furnishing parts, which addresses the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a digital collaborative management system for the supply chain of customized home furnishing parts, comprising: IoT terminal device control module: used to deploy IoT terminal devices in the entire supply chain of customized home furnishing parts, and embed intelligent microcontrollers with self-learning capabilities in the devices to collect data from each link of the supply chain. The IoT terminal device control module includes a sensing device deployment unit, a data preprocessing unit and a distributed storage unit.

[0006] Customized home furnishing data acquisition module: used to collect users' home furnishing needs through multiple channels and assemble users' home furnishing needs into a demand gene sequence.

[0007] Supply chain collaborative forecasting module: It is used to receive demand gene sequences, perform multi-objective optimization matching with the system database, and generate no less than two sets of supply chain resource matching schemes.

[0008] The intelligent matching module for user needs is used to identify supply chain risks based on the supply chain resource matching scheme, using an anomaly detection algorithm to generate the optimal supply chain resource matching scheme and create production tasks. The intelligent matching module for user needs includes a supply chain risk anomaly detection unit and an optimal scheme generation unit.

[0009] Preferably, the IoT terminal device control module specifically comprises: Sensing device deployment unit: used to attach RFID tags to raw materials to record information such as origin, material, and environmental protection level; to install sensors on production equipment to collect operating parameters of each piece of equipment; to deploy millimeter-wave radar in the storage area to collect inventory quantity; and to install Beidou positioning and temperature and humidity sensors on logistics vehicles to record transportation trajectory and environmental data. Data preprocessing unit: Employs edge computing technology to clean, format-convert, and time-space-align data from all stages of the supply chain; Distributed storage unit: Construct a supply chain data lake and store data in real time by raw materials, production, warehousing and logistics.

[0010] Preferably, the customized home furnishing data acquisition module specifically comprises: By collecting data from users' residences through smart home sensors, a 3D point cloud model is generated, which includes the dimensions of room length, width, and height, coordinates of door and window positions, and spatial distribution of beams and columns. Simultaneously, temperature and humidity sensors and light sensors are deployed in various functional areas of the residence to collect the temperature, humidity, and light intensity of each area. The 3D point cloud model and the temperature, humidity, and light intensity data are uploaded to the cloud to build a digital twin model of the residence. By connecting to the customer service dialogue system, text data between users and customer service is obtained. Based on the pre-trained language model of Transformer, semantic analysis is performed on text data from multiple channels to extract non-standardized keywords from users. A standardized library of home furnishing demand keywords is established. The extracted non-standardized keywords are mapped to terms in the library to obtain the user's demand keywords. By connecting to the user browsing log API of e-commerce platforms, we can obtain users' home furnishing product interaction behavior, and calculate users' home furnishing product preferences using a weighted algorithm. We acquire user residential data, demand keywords, and home furnishing product preferences, perform standardized processing, generate a structured language that conforms to coding specifications, and assemble user home furnishing needs into a demand gene sequence. This sequence consists of multiple demand bases, with each base representing a dimension of the demand.

[0011] Preferably, the supply chain collaborative forecasting module specifically comprises: Used to receive demand gene sequences, break down demand gene sequences into spatial genes, functional genes, and product genes, and extract key dimensions; The system database's supply chain resource library, which includes a raw material resource layer, a spare parts resource layer, and a logistics resource layer, is invoked for preliminary matching of the parsed demand gene sequence. Based on the required bases corresponding to functional genes, a candidate list of spare parts is selected; based on the required bases corresponding to product genes, a candidate list of raw materials is selected; and by combining the required bases corresponding to space genes, functional genes, and product genes, a candidate list of logistics materials is selected.

[0012] Preferably, the multi-objective optimization matching specifically includes: Obtain the raw material procurement costs, spare parts procurement costs, and logistics and transportation costs required by the user to obtain the cost target required by the user; Obtain the delivery time of raw materials, spare parts, and finished product logistics required by the user to obtain the timeliness target required by the user. Obtain the quality scores of raw materials, spare parts, and logistics required by the user to obtain the quality targets required by the user. Using a genetic algorithm, at least two sets of supply chain resource matching solutions are obtained by searching among cost, timeliness, and quality objectives.

[0013] Preferably, the supply chain risk anomaly detection unit: based on the received supply chain resource matching scheme, constructs a risk characteristic index system, which includes raw material supply risk indicators, spare parts production risk indicators, and logistics and transportation risk indicators; The raw material supply risk indicators are as follows: Obtain the raw material cost of the current plan, the historical average cost of the raw material, and calculate the raw material supply risk indicator: ,in, Let be the raw material supply risk indicator for the i-th option. Let be the raw material cost of the i-th option. This is expressed as the historical average cost of the raw material; The specific risk indicators for the production of the spare parts are as follows: Obtain the quality pass rate of the spare parts manufacturers for the current solution, and calculate the spare parts production risk indicators: ,in, Let be the component production risk index for the i-th scheme. Let represent the quality pass rate of the parts manufacturer for the i-th scheme; The logistics and transportation risk indicators are as follows: Obtain the current logistics transportation time, the logistics company's historical average transportation time, and calculate the logistics transportation risk indicators: ,in Let be the logistics and transportation risk index for the i-th option. Let represent the logistics transportation time for the i-th option. Let represent the historical average transportation time of the logistics company for the i-th option; Obtain the risk indicators for raw material supply, spare parts production, and logistics transportation of the current plan. Normalize each risk indicator and sum the normalized risk indicators for raw material supply, spare parts production, and logistics transportation to obtain the comprehensive risk indicator for the current plan.

[0014] Preferably, the optimal solution generation unit: obtains the comprehensive risk index of the current solution, compares it with the preset comprehensive risk index threshold, filters out solutions with a comprehensive risk index greater than the preset comprehensive risk index threshold, and if all solutions are high-risk, triggers the supply chain collaborative prediction module to regenerate the matching solution. After obtaining the filtered solutions, calculate the objective function for each solution. Value, select The optimal supply chain resource matching solution is generated by finding the supply chain resource matching solution with the highest value. The objective function is: ; Based on the optimal supply chain resource matching scheme, a production task containing process parameters, schedule nodes, and quality standards is created and sent to the production execution system.

[0015] The technical effects and advantages of this invention are as follows: 1. This invention provides a digital collaborative management system for the customized home furnishing parts supply chain. It deploys IoT terminal devices throughout the entire supply chain, embedding self-learning intelligent microcontrollers within these devices to collect data from each stage. This data is gathered from multiple channels, including user residential data, demand keywords, and home furnishing product preferences. User home furnishing needs are assembled into a demand gene sequence, which is then broken down into spatial, functional, and product genes. Key dimensions are extracted, and a candidate list of parts is selected based on the demand bases corresponding to the functional genes. A candidate list of raw materials is selected based on the demand bases corresponding to the product genes. A logistics candidate list is then selected by combining the demand bases corresponding to the spatial, functional, and product genes. A genetic algorithm is used to obtain at least two supply chain resource matching schemes. Based on the received supply chain resource matching schemes, a risk characteristic index system is constructed. An objective function is used to calculate the risk of each scheme. Value, select The algorithm generates the optimal supply chain resource matching scheme by maximizing the supply chain resource matching value, and creates production tasks to achieve precise matching between demand and the supply chain. This ensures that the produced customized home furnishing products better suit users' actual living spaces, functional needs, and product preferences. Utilizing the global search characteristics of genetic algorithms, it can quickly discover better solutions from massive resource combinations, thereby improving the efficiency of supply chain resource allocation. A risk characteristic indicator system is constructed, and the scheme is calculated through an objective function. The optimal solution is selected by value-based approach, and supply chain risks are incorporated into the solution evaluation dimension to enhance the supply chain risk management capability. This enables full-process digital management from user demand collection, supply chain data acquisition, resource matching, and production task creation, promotes real-time information exchange and collaborative decision-making among multiple entities, and improves the overall operational efficiency of the supply chain. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the structure of a digital collaborative management system for the supply chain of customized home furnishing parts according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Please see Figure 1 As shown, the present invention provides a digital collaborative management system for the supply chain of customized home furnishing parts, including an Internet of Things terminal device control module, a customized home furnishing data acquisition module, a supply chain collaborative prediction module, and a user demand intelligent matching module.

[0019] The IoT terminal device control module is connected to the customized home furnishing data acquisition module, the customized home furnishing data acquisition module is connected to the supply chain collaborative forecasting module, and the supply chain collaborative forecasting module is connected to the user demand intelligent matching module.

[0020] The IoT terminal device control module is used to deploy IoT terminal devices throughout the entire supply chain of customized home furnishing parts, and embeds a smart microcontroller with self-learning capabilities into the device to collect data from each link of the supply chain. The IoT terminal device control module includes a sensing device deployment unit, a data preprocessing unit, and a distributed storage unit.

[0021] In one possible design, the IoT terminal device control module specifically comprises: Sensing device deployment unit: used to attach RFID tags to raw materials to record information such as origin, material, and environmental protection level; to install sensors on production equipment to collect operating parameters of each piece of equipment; to deploy millimeter-wave radar in the storage area to collect inventory quantity; and to install Beidou positioning and temperature and humidity sensors on logistics vehicles to record transportation trajectory and environmental data. Data preprocessing unit: Employs edge computing technology to clean, format-convert, and time-space-align data from all stages of the supply chain; Distributed storage unit: Construct a supply chain data lake and store data in real time by raw materials, production, warehousing and logistics.

[0022] The customized home furnishing data acquisition module is used to collect users' home furnishing needs through multiple channels and assemble these needs into a demand gene sequence.

[0023] In one possible design, the customized home furnishing data acquisition module specifically comprises: By collecting data from users' residences through smart home sensors, a 3D point cloud model is generated, which includes the dimensions of room length, width, and height, coordinates of door and window positions, and spatial distribution of beams and columns. Simultaneously, temperature and humidity sensors and light sensors are deployed in various functional areas of the residence to collect the temperature, humidity, and light intensity of each area. The 3D point cloud model and the temperature, humidity, and light intensity data are uploaded to the cloud to build a digital twin model of the residence. By connecting to the customer service dialogue system, text data between users and customer service is obtained. Based on the pre-trained language model of Transformer, semantic analysis is performed on text data from multiple channels to extract non-standardized keywords from users. A standardized library of home furnishing demand keywords is established. The extracted non-standardized keywords are mapped to terms in the library to obtain the user's demand keywords. By connecting to the user browsing log API of e-commerce platforms, we can obtain users' home furnishing product interaction behavior, and calculate users' home furnishing product preferences using a weighted algorithm. We acquire user residential data, demand keywords, and home furnishing product preferences, perform standardized processing, generate a structured language that conforms to coding specifications, and assemble user home furnishing needs into a demand gene sequence. This sequence consists of multiple demand bases, with each base representing a dimension of the demand.

[0024] The supply chain collaborative forecasting module is used to receive demand gene sequences, perform multi-objective optimization matching with the system database, and generate no less than two sets of supply chain resource matching schemes.

[0025] In one possible design, the supply chain collaborative forecasting module specifically comprises: Used to receive demand gene sequences, break down demand gene sequences into spatial genes, functional genes, and product genes, and extract key dimensions; The system database's supply chain resource library, which includes a raw material resource layer, a spare parts resource layer, and a logistics resource layer, is invoked for preliminary matching of the parsed demand gene sequence. Based on the required bases corresponding to the functional genes, a candidate list of spare parts is selected; based on the required bases corresponding to the product genes, a candidate list of raw materials is selected; and based on the required bases corresponding to the space genes, functional genes, and product genes, a candidate list of logistics is selected. The multi-objective optimization matching specifically refers to: Obtain the raw material procurement costs, spare parts procurement costs, and logistics and transportation costs required by the user to obtain the cost target required by the user; Obtain the delivery time of raw materials, spare parts, and finished product logistics required by the user to obtain the timeliness target required by the user. Obtain the quality scores of raw materials, spare parts, and logistics required by the user to obtain the quality targets required by the user. Using a genetic algorithm, at least two sets of supply chain resource matching solutions are obtained by searching among cost, timeliness, and quality objectives.

[0026] In this embodiment, it should be specifically noted that the raw material procurement cost is obtained by multiplying the supplier's quotation by the demand quantity, the spare parts procurement cost is obtained by multiplying the manufacturer's quotation by the demand quantity, and the logistics and transportation cost is obtained by multiplying the logistics company's quotation by the volume. Raw material delivery time is based on supplier order confirmation time, transportation time, and receipt time; spare parts delivery time is based on manufacturer order confirmation time, transportation time, and receipt time; finished product logistics delivery time is based on logistics company timeliness. Raw material quality scores are based on the supplier's historical pass rate, spare parts quality scores are based on the manufacturer's spare parts pass rate, and logistics quality scores are based on the transportation damage rate.

[0027] The intelligent matching module for user needs is used to identify supply chain risks based on the supply chain resource matching scheme using an anomaly detection algorithm, generate the optimal supply chain resource matching scheme, and create production tasks. The intelligent matching module for user needs includes a supply chain risk anomaly detection unit and an optimal scheme generation unit.

[0028] In one possible design, the intelligent user demand matching module specifically comprises: Supply chain risk anomaly detection unit: Based on the received supply chain resource matching scheme, a risk characteristic indicator system is constructed, which includes raw material supply risk indicators, spare parts production risk indicators and logistics and transportation risk indicators; The raw material supply risk indicators are as follows: Obtain the raw material cost of the current plan, the historical average cost of the raw material, and calculate the raw material supply risk indicator: ,in, Let be the raw material supply risk indicator for the i-th option. Let be the raw material cost of the i-th option. This is expressed as the historical average cost of the raw material; Specifically, the raw material supply risk indicator reflects the degree to which raw material costs deviate from the historical average; the higher the value, the higher the risk of cost fluctuations. The specific risk indicators for the production of the spare parts are as follows: Obtain the quality pass rate of the spare parts manufacturers for the current solution, and calculate the spare parts production risk indicators: ,in, Let be the component production risk index for the i-th scheme. Let represent the quality pass rate of the parts manufacturer for the i-th scheme; Specifically, the risk index for spare parts production reflects the quality risk in spare parts production; the higher the value, the higher the quality risk. The logistics and transportation risk indicators are as follows: Obtain the current logistics transportation time, the logistics company's historical average transportation time, and calculate the logistics transportation risk indicators: ,in Let be the logistics and transportation risk index for the i-th option. Let represent the logistics transportation time for the i-th option. Let represent the historical average transportation time of the logistics company for the i-th option; Specifically, the logistics and transportation risk index reflects the degree to which the logistics and transportation timeliness deviates from the historical average. The larger the value, the higher the risk of timeliness fluctuation. Obtain the risk indicators of raw material supply, spare parts production, and logistics transportation for the current plan; normalize each risk indicator; sum the normalized risk indicators of raw material supply, spare parts production, and logistics transportation to obtain the comprehensive risk indicator of the current plan. Optimal solution generation unit: Obtain the comprehensive risk index of the current solution, compare it with the preset comprehensive risk index threshold, filter solutions with comprehensive risk index greater than the preset comprehensive risk index threshold, and if all solutions are high risk, trigger the supply chain collaborative prediction module to regenerate matching solutions. After obtaining the filtered solutions, calculate the objective function for each solution. Value, select The optimal supply chain resource matching solution is generated by finding the supply chain resource matching solution with the highest value. The objective function is: ; Based on the optimal supply chain resource matching scheme, a production task containing process parameters, schedule nodes, and quality standards is created and sent to the production execution system.

[0029] In this embodiment, it should be specifically explained that the present invention deploys IoT terminal devices throughout the entire supply chain of customized home furnishing components, embedding intelligent microcontrollers with self-learning capabilities into these devices to collect data from each stage of the supply chain. This involves collecting user residential data, demand keywords, and home furnishing product preferences through multiple channels, assembling user home furnishing needs into a demand gene sequence, and then splitting this sequence into spatial genes, functional genes, and product genes. Key dimensions are extracted, and a candidate list of components is selected based on the demand bases corresponding to the functional genes. A candidate list of raw materials is selected based on the demand bases corresponding to the product genes. A logistics candidate list is then selected by combining the demand bases corresponding to the spatial, functional, and product genes. A genetic algorithm is used to obtain at least two sets of supply chain resource matching schemes. Based on the received supply chain resource matching schemes, a risk characteristic index system is constructed, and the objective function is used to calculate the risk of each scheme. Value, select The algorithm generates the optimal supply chain resource matching scheme by maximizing the supply chain resource matching value, and creates production tasks to achieve precise matching between demand and the supply chain. This ensures that the produced customized home furnishing products better suit users' actual living spaces, functional needs, and product preferences. Utilizing the global search characteristics of genetic algorithms, it can quickly discover better solutions from massive resource combinations, thereby improving the efficiency of supply chain resource allocation. A risk characteristic indicator system is constructed, and the scheme is calculated through an objective function. The optimal solution is selected by value-based approach, and supply chain risks are incorporated into the solution evaluation dimension to enhance the supply chain risk management capability. This enables full-process digital management from user demand collection, supply chain data acquisition, resource matching, and production task creation, promotes real-time information exchange and collaborative decision-making among multiple entities, and improves the overall operational efficiency of the supply chain.

[0030] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A digital collaborative management system for the supply chain of customized home furnishing parts, characterized in that, include: IoT terminal device control module: used to deploy IoT terminal devices in the entire supply chain of customized home furnishing parts, and embed intelligent microcontrollers with self-learning capabilities in the devices to collect data from each link of the supply chain. The IoT terminal device control module includes a sensing device deployment unit, a data preprocessing unit and a distributed storage unit. Customized home furnishing data acquisition module: used to collect users' home furnishing needs through multiple channels and assemble users' home furnishing needs into a demand gene sequence; Supply chain collaborative forecasting module: used to receive demand gene sequences, perform multi-objective optimization matching with the system database, and generate no less than two sets of supply chain resource matching schemes; The intelligent matching module for user needs is used to identify supply chain risks based on the supply chain resource matching scheme, using an anomaly detection algorithm to generate the optimal supply chain resource matching scheme and create production tasks. The intelligent matching module for user needs includes a supply chain risk anomaly detection unit and an optimal scheme generation unit.

2. The customized home furnishing parts supply chain digital collaborative management system according to claim 1, characterized in that: The IoT terminal device control module is specifically as follows: Sensing device deployment unit: used to attach RFID tags to raw materials to record information such as origin, material, and environmental protection level; to install sensors on production equipment to collect operating parameters of each piece of equipment; to deploy millimeter-wave radar in the storage area to collect inventory quantity; and to install Beidou positioning and temperature and humidity sensors on logistics vehicles to record transportation trajectory and environmental data. Data preprocessing unit: Employs edge computing technology to clean, format-convert, and time-space-align data from all stages of the supply chain; Distributed storage unit: Construct a supply chain data lake and store data in real time by raw materials, production, warehousing and logistics.

3. The customized home furnishing parts supply chain digital collaborative management system according to claim 1, characterized in that: The customized home furnishing data acquisition module is specifically as follows: By collecting data from users' residences through smart home sensors, a 3D point cloud model is generated, which includes the dimensions of room length, width, and height, coordinates of door and window positions, and spatial distribution of beams and columns. Simultaneously, temperature and humidity sensors and light sensors are deployed in various functional areas of the residence to collect the temperature, humidity, and light intensity of each area. The 3D point cloud model and the temperature, humidity, and light intensity data are uploaded to the cloud to build a digital twin model of the residence. By connecting to the customer service dialogue system, text data between users and customer service is obtained. Based on the pre-trained language model of Transformer, semantic analysis is performed on text data from multiple channels to extract non-standardized keywords from users. A standardized library of home furnishing demand keywords is established. The extracted non-standardized keywords are mapped to terms in the library to obtain the user's demand keywords. By connecting to the user browsing log API of e-commerce platforms, we can obtain users' home furnishing product interaction behavior, and calculate users' home furnishing product preferences using a weighted algorithm. We acquire user residential data, demand keywords, and home furnishing product preferences, perform standardized processing, generate a structured language that conforms to coding specifications, and assemble user home furnishing needs into a demand gene sequence. This sequence consists of multiple demand bases, with each base representing a dimension of the demand.

4. The customized home furnishing parts supply chain digital collaborative management system according to claim 1, characterized in that: The supply chain collaborative forecasting module is specifically as follows: Used to receive demand gene sequences, break down demand gene sequences into spatial genes, functional genes, and product genes, and extract key dimensions; The system database's supply chain resource library, which includes a raw material resource layer, a spare parts resource layer, and a logistics resource layer, is invoked for preliminary matching of the parsed demand gene sequence. Based on the required bases corresponding to functional genes, a candidate list of spare parts is selected; based on the required bases corresponding to product genes, a candidate list of raw materials is selected; and by combining the required bases corresponding to space genes, functional genes, and product genes, a candidate list of logistics materials is selected.

5. The customized home furnishing parts supply chain digital collaborative management system according to claim 1, characterized in that: The multi-objective optimization matching specifically refers to: Obtain the raw material procurement costs, spare parts procurement costs, and logistics and transportation costs required by the user to obtain the cost target required by the user; Obtain the delivery time of raw materials, spare parts, and finished product logistics required by the user to obtain the timeliness target required by the user. Obtain the quality scores of raw materials, spare parts, and logistics required by the user to obtain the quality targets required by the user. Using a genetic algorithm, at least two sets of supply chain resource matching solutions are obtained by searching among cost, timeliness, and quality objectives.

6. The customized home furnishing parts supply chain digital collaborative management system according to claim 1, characterized in that: The supply chain risk anomaly detection unit: Based on the received supply chain resource matching scheme, it constructs a risk characteristic indicator system, which includes raw material supply risk indicators, spare parts production risk indicators, and logistics and transportation risk indicators. The raw material supply risk indicators are as follows: Obtain the raw material cost of the current plan, the historical average cost of the raw material, and calculate the raw material supply risk indicator: ,in, Let be the raw material supply risk indicator for the i-th option. Let be the raw material cost of the i-th option. This is expressed as the historical average cost of the raw material; The specific risk indicators for the production of the spare parts are as follows: Obtain the quality pass rate of the spare parts manufacturers for the current solution, and calculate the spare parts production risk indicators: ,in, Let be the component production risk index for the i-th scheme. Let represent the quality pass rate of the parts manufacturer for the i-th scheme; The logistics and transportation risk indicators are as follows: Obtain the current logistics transportation time, the logistics company's historical average transportation time, and calculate the logistics transportation risk indicators: ,in Let be the logistics and transportation risk index for the i-th option. Let represent the logistics transportation time for the i-th option. Let represent the historical average transportation time of the logistics company for the i-th option; Obtain the risk indicators for raw material supply, spare parts production, and logistics transportation of the current plan. Normalize each risk indicator and sum the normalized raw material supply risk indicators, spare parts production risk indicators, and logistics transportation risk indicators to obtain the comprehensive risk indicator of the current plan.

7. The customized home furnishing parts supply chain digital collaborative management system according to claim 1, characterized in that: The optimal solution generation unit: obtains the comprehensive risk index of the current solution, compares it with the preset comprehensive risk index threshold, filters out solutions with a comprehensive risk index greater than the preset comprehensive risk index threshold, and if all solutions are high-risk, triggers the supply chain collaborative prediction module to regenerate the matching solution. After obtaining the filtered solutions, calculate the objective function for each solution. Value, select The optimal supply chain resource matching solution is generated by finding the supply chain resource matching solution with the highest value. The objective function is: ; Based on the optimal supply chain resource matching scheme, a production task containing process parameters, schedule nodes, and quality standards is created and sent to the production execution system.

Images