Product supply chain portrait generation and product resource optimization method, system and device

Abstract

The invention discloses a product supply chain portrait generation and product resource optimization method, system and device, and the method comprises the steps: obtaining and preprocessing a product production data set, a product processing data set and a product sales data set, and obtaining a production standard data set, a processing standard data set and a sales standard data set; through feature extraction, a production feature data set, a processing feature data set and a sales feature data set are obtained; generating production portrait data, processing portrait data and sales portrait data based on the production feature data set, the processing feature data set and the sales feature data set; and performing product resource optimization through the production feature data set, the processing feature data set, the sales feature data set, the production portrait data, the processing portrait data and the sales portrait data to obtain a product resource optimization result. According to the method, portrait construction is carried out on the supply chain, so that the problems of incomplete information acquisition, update lag and insufficient intelligence in the existing method are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of image generation, and particularly relates to a method, a system and a device for generating a product supply chain image and optimizing product resources. Background Art

[0002] The current customer image is realized by analyzing simple customer information data and historical transaction data, relying on manual records and simple data storage to achieve customer management, order management and sales management. At the same time, in the production, processing and sales links of products, traditional manual recording methods or single data systems are still used for information collection and processing. Such methods lack data collection and data integration capabilities. The limitations of data collection ignore behavioral data such as production requirements and inventory fluctuations in the supply chain, resulting in incomplete customer images; insufficient data integration capabilities lead to superficial analysis of customer data, and the failure to fully utilize data mining and intelligent analysis technologies makes it difficult to insight into potential customer needs and future behavioral characteristics, and difficult to accurately construct customer images.

[0003] In addition, existing methods cannot reasonably allocate personalized product resources according to distribution resources, regional differences and customer needs, resulting in problems such as product inventory backlog or out-of-stock, low resource collaboration efficiency, and affecting the overall operation effect of the supply chain. In terms of optimizing resource allocation based on customer images and supporting customers' efficient decision-making, existing methods have obvious deficiencies, making it difficult to deeply analyze and respond to customer data and market feedback in real time, resulting in lagging information flow, difficult to adapt to the rapid changes in the market, unable to meet the requirements of rapid response time changes, and resulting in low product-market matching degree and insufficient customer satisfaction. Summary of the Invention

[0004] The present invention aims at the deficiencies in the prior art and provides a method, a system and a device for generating a product supply chain image and optimizing product resources.

[0005] To solve the above technical problems, the present invention is solved by the following technical solutions: A method for generating a product supply chain image and optimizing product resources includes the following steps: Obtain a product production data set, a product processing data set and a product sales data set and perform preprocessing to obtain a production standard data set, a processing standard data set and a sales standard data set; Extract features from the production standard data set, the processing standard data set and the sales standard data set to obtain a production feature data set, a processing feature data set and a sales feature data set; Based on the production feature data set, the processing feature data set and the sales feature data set, generate production image data, processing image data and sales image data; Optimize product resources through production feature datasets, processing feature datasets, sales feature datasets, production portrait data, processing portrait data, and sales portrait data to obtain product resource optimization results, including at least: production volume optimization data, inventory optimization data, matching optimization data, distribution optimization data, and supply chain optimization data; Among them, optimize the production plan based on the production feature dataset, sales feature dataset, and production portrait data to obtain production volume optimization data and inventory optimization data; optimize product matching based on the production feature dataset, sales feature dataset, and sales portrait data to obtain matching optimization data; optimize product distribution based on the sales feature dataset, production portrait data, and sales portrait data to obtain distribution optimization data; optimize the product supply chain based on the processing feature dataset, sales feature dataset, production portrait data, processing portrait data, and sales portrait data to obtain supply chain optimization data.

[0006] As an implementable manner, generating production portrait data, processing portrait data, and sales portrait data based on the production feature dataset, processing feature dataset, and sales feature dataset includes the following steps: According to the importance degrees of the production feature dataset, processing feature dataset, and sales feature dataset for the production portrait data, processing portrait data, and sales portrait data, set corresponding production weights, processing weights, and sales weights through mapping; Through the production weights, processing weights, and sales weights, combine with the production feature dataset, processing feature dataset, and sales feature dataset to obtain production feature scores, processing feature scores, and sales feature scores; Preset production clustering thresholds, processing clustering thresholds, and sales clustering thresholds, classify the production feature dataset, processing feature dataset, and sales feature dataset, and obtain corresponding category centers; Based on the production feature dataset, processing feature dataset, and sales feature dataset and their corresponding category centers, and perform iteration through the iterative optimization function until the iterative optimization function is minimized to obtain the corresponding feature clustering results, and obtain production feature labels, processing feature labels, and sales feature labels through the corresponding feature clustering results; Form production portrait data through production feature scores and production feature labels, form processing portrait data through processing feature scores and processing feature labels, and form sales portrait data through sales feature scores and sales feature labels; Among them, the production feature scores, processing feature scores, and sales feature scores are respectively expressed as follows:

[0007] The category centers are expressed as follows:

[0008] The iterative optimization function is expressed as follows:

[0009] Wherein, represents the production feature score, or the processing feature score, or the sales feature score, represents the th production weight, or processing weight, or sales weight, the th production feature data set, or processing feature data set, or sales feature data set, represents the number of features in the production feature data set, or processing feature data set, or sales feature data set, represents the class center, represents the th clustering center, represents the iterative optimization function, represents the production clustering threshold.

[0010] As an implementable manner, optimizing the production plan based on the production feature data set, the sales feature data set and the production portrait data to obtain the output optimization data and the inventory optimization data includes the following steps: Obtaining the demand for all category products in the customer order through the customer order data to obtain the category demand data; Analyzing the importance degree of the customers based on the customer order data to obtain the customer weight data, and obtaining the customer comprehensive weight based on the sales portrait data, and combining the category demand data and the customer weight data to obtain the output optimization data; Analyzing the regional characteristics of the product output data, the customer order data and the order type data to obtain the demand for the products in each region to obtain the regional demand data; Obtaining the regional comprehensive weight through the production portrait data and the sales portrait data, and combining the regional demand data to optimize the inventory allocation to obtain the inventory optimization data; Wherein, the output optimization data is expressed as follows:

[0011] The inventory optimization data is expressed as follows:

[0012] Wherein, represents the output optimization data of the th category of products, represents the customer 's customer weight data, represents the customer 's category demand data for the th category of products Represents the customer For the comprehensive weight of customers for the For the inventory optimization data of the Represents the region Within the regional demand data of the Represents the region Within the regional comprehensive weight of the Represents the number of regions.

[0013] As an implementable manner, the product matching optimization is performed based on the production feature dataset, the sales feature dataset, and the sales portrait data to obtain the matching optimization data, including the following steps: Obtain the matching degree between the production feature dataset and the sales feature dataset to obtain the feature matching data; Based on the processing portrait data and the sales portrait data, obtain the preference data of customers for products to obtain the label weight data, and combine the feature matching data to perform product matching optimization to obtain the matching optimization data, which is expressed as follows:

[0014] Among them, Represents the customer For the matching optimization data of the Represents the customer Of the The feature matching data of the Represents the feature matching dataset, Represents the customer Of the label weight data of the Represents the number of features.

[0015] As an implementable manner, the product distribution optimization is performed based on the sales feature dataset, the production portrait data, and the sales portrait data to obtain the distribution optimization data, including the following steps: Based on the customer weight data and the customer order data, obtain the priority of customer order distribution to obtain the order distribution data; Through the production portrait data and the sales portrait data, obtain the urgency of the customer order, and obtain the customer priority data according to the urgency, and combine the order distribution data and the customer weight data to perform product distribution optimization to obtain the distribution optimization data, which is expressed as follows:

[0016] Among them, represents the distribution optimization data of the th type of product, represents the customer priority data for the th type of product, represents the number of customers, represents the customer weight data, represents the customer demand data for the th type of product.

[0017] As an implementable manner, the product supply chain is optimized based on the processing feature dataset, the sales feature dataset, the production portrait data, the processing portrait data, and the sales portrait data to obtain supply chain optimization data, including the following steps: Obtain the matching degree of the processing feature dataset and the sales feature dataset to obtain product adaptation data; Through the production portrait data, the processing portrait data, and the sales portrait data, obtain the adaptation degree between the processing factory and the customer to obtain supply chain adaptation data, and combine the product adaptation data to optimize the product supply chain to obtain supply chain optimization data, which is expressed as follows:

[0018] Among them, represents the supply chain optimization data, represents the th product adaptation data for the th sale of the th type of product, represents the supply chain adaptation data for the th sale of the

[0019] As an implementable manner, the acquisition of the product production dataset, the product processing dataset, and the product sales dataset includes the following steps: Obtain the product output data, the product inventory data, the customer demand data, and the production quality scoring data to form a product production dataset; Obtain the material supply data and the product specification data and perform analysis to obtain production processing matching data, and combine the product processing volume data, the product specification data, and the regional demand scoring data to form a product processing dataset; Obtain the customer order data, and perform analysis in combination with the product processing dataset to obtain sales processing matching data, and combine the customer order data, the order type data, and the order fluctuation data to form a product sales dataset.

[0020] As an implementable manner, the preprocessing includes the following steps: Remove the missing data and error data in the product production dataset, product processing dataset, and product sales dataset, and obtain the initial product production dataset, initial product processing dataset, and initial product sales dataset through data deduplication; Perform standardization processing on the initial product production dataset, initial product processing dataset, and initial product sales dataset to obtain the production standard dataset, processing standard dataset, and sales standard dataset, which are expressed as follows:

[0021] Among them, represents the production standard dataset or processing standard dataset or sales standard dataset, represents the production standard data or processing standard data or sales standard data, represents the minimum value of the production standard dataset or the minimum value of the processing standard dataset or the minimum value of the sales standard dataset, represents the maximum value of the production standard dataset or the maximum value of the processing standard dataset or the maximum value of the sales standard dataset, represents the initial product production dataset or initial product processing dataset or initial product sales dataset, represents the missing data and error data.

[0022] As an implementable manner, the production feature dataset is obtained through the following steps: Analyze the product output data and product inventory data to obtain the total product production data and average inventory data; Analyze based on the customer demand data and product inventory data to obtain the procurement satisfaction rate data; Solve the average value of the customer demand data and production quality score data to obtain the average demand data and quality average data, and perform volatility analysis based on the average demand data and customer demand data to obtain the demand volatility data; Obtain the customized demand data based on the customer demand data, and analyze to obtain the customization ratio data; Form the production feature dataset through the total product production data, average inventory data, procurement satisfaction rate data, demand volatility data, quality average data, and customization ratio data.

[0023] As an implementable manner, the processing feature dataset is obtained through the following steps: Obtain the total product processing data through the product processing data, analyze based on the product specification data to obtain the specification frequency data, and then obtain the specification diversity data; Solve the average values of the regional demand scoring data and the production and processing matching data to obtain the demand average data and the matching average data; Analyze the product processing volume data and the customer demand data to obtain the product delivery time data and solve the average value to obtain the delivery average data; Form a processing feature data set through the total product price data, the specification diversity data, the demand average data, the matching average data, the customization ratio data, and the delivery average data.

[0024] As an implementable manner, the sales feature data set is obtained through the following steps: Obtain the total customer order data and the order type data from the customer order data, and solve the average value of the order type data to obtain the order average data; Obtain the mean values of the order fluctuation data and the sales and processing matching data to obtain the average fluctuation data and the processing average data, and obtain the demand fluctuation data through the order fluctuation data and the average fluctuation data; Form a sales feature data set through the total customer order data, the order average data, the demand fluctuation data, the processing average data, and the customization ratio data.

[0025] A product supply chain portrait generation and product resource optimization system includes a data acquisition module, a feature extraction module, a portrait generation module, and a resource optimization module; The data acquisition module acquires the product production data set, the product processing data set, and the product sales data set and performs preprocessing to obtain the production standard data set, the processing standard data set, and the sales standard data set; The feature extraction module extracts features from the production standard data set, the processing standard data set, and the sales standard data set to obtain the production feature data set, the processing feature data set, and the sales feature data set; The portrait generation module generates production portrait data, processing portrait data, and sales portrait data based on the production feature data set, the processing feature data set, and the sales feature data set; The resource optimization module performs product resource optimization through the production feature data set, the processing feature data set, the sales feature data set, the production portrait data, the processing portrait data, and the sales portrait data to obtain the product resource optimization result, which at least includes: production volume optimization data, inventory optimization data, matching optimization data, distribution optimization data, and supply chain optimization data; Among them, production plan optimization is performed based on the production feature dataset, sales feature dataset, and production portrait data to obtain production volume optimization data and inventory optimization data; product matching optimization is performed based on the production feature dataset, sales feature dataset, and sales portrait data to obtain matching optimization data; product distribution optimization is performed based on the sales feature dataset, production portrait data, and sales portrait data to obtain distribution optimization data; product supply chain optimization is performed based on the processing feature dataset, sales feature dataset, production portrait data, processing portrait data, and sales portrait data to obtain supply chain optimization data.

[0026] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following method is implemented: Obtain a product production dataset, a product processing dataset, and a product sales dataset and perform preprocessing to obtain a production standard dataset, a processing standard dataset, and a sales standard dataset; Extract features from the production standard dataset, the processing standard dataset, and the sales standard dataset to obtain a production feature dataset, a processing feature dataset, and a sales feature dataset; Generate production portrait data, processing portrait data, and sales portrait data based on the production feature dataset, the processing feature dataset, and the sales feature dataset; Perform product resource optimization through the production feature dataset, the processing feature dataset, the sales feature dataset, the production portrait data, the processing portrait data, and the sales portrait data to obtain a product resource optimization result, including at least: production volume optimization data, inventory optimization data, matching optimization data, distribution optimization data, and supply chain optimization data; Among them, production plan optimization is performed based on the production feature dataset, sales feature dataset, and production portrait data to obtain production volume optimization data and inventory optimization data; product matching optimization is performed based on the production feature dataset, sales feature dataset, and sales portrait data to obtain matching optimization data; product distribution optimization is performed based on the sales feature dataset, production portrait data, and sales portrait data to obtain distribution optimization data; product supply chain optimization is performed based on the processing feature dataset, sales feature dataset, production portrait data, processing portrait data, and sales portrait data to obtain supply chain optimization data.

[0027] A product supply chain portrait generation and product resource optimization device includes a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the following method is implemented: Obtain a product production dataset, a product processing dataset, and a product sales dataset and perform preprocessing to obtain a production standard dataset, a processing standard dataset, and a sales standard dataset; Feature extraction is performed on the production standard data set, the processing standard data set, and the sales standard data set to obtain the production feature data set, the processing feature data set, and the sales feature data set; Based on the production feature data set, the processing feature data set, and the sales feature data set, production portrait data, processing portrait data, and sales portrait data are generated; Product resource optimization is performed through the production feature data set, the processing feature data set, the sales feature data set, the production portrait data, the processing portrait data, and the sales portrait data to obtain the product resource optimization result, including at least: production volume optimization data, inventory optimization data, matching optimization data, distribution optimization data, and supply chain optimization data; Among them, production plan optimization is performed based on the production feature data set, the sales feature data set, and the production portrait data to obtain production volume optimization data and inventory optimization data; product matching optimization is performed based on the production feature data set, the sales feature data set, and the sales portrait data to obtain matching optimization data; product distribution optimization is performed based on the sales feature data set, the production portrait data, and the sales portrait data to obtain distribution optimization data; product supply chain optimization is performed based on the processing feature data set, the sales feature data set, the production portrait data, the processing portrait data, and the sales portrait data to obtain supply chain optimization data.

[0028] Due to the adoption of the above technical solutions, the present invention has significant technical effects: The present invention obtains the product production data set, the product processing data set, and the product sales data set, and performs preprocessing to ensure the accuracy and high quality of the data, constructs the production portrait data, the processing portrait data, and the sales portrait data, and updates the portrait data in real time according to the changes in market demand and customer behavior. Based on the accurate portrait data, the product resource allocation is optimized to help the enterprise improve the efficiency of production planning, inventory management, logistics distribution, and customer service. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0030] Figure 1 is a flowchart of the method of the present invention; Figure 2 is an overall schematic diagram of the system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0031] The present invention will be further described in detail below in conjunction with embodiments. The following embodiments are explanations of the present invention, and the present invention is not limited to the following embodiments.

[0032] Embodiment 1: A method for generating a product supply chain portrait and optimizing product resources, as Figure 1 shown, includes the following steps: S100. Obtain a product production data set, a product processing data set, and a product sales data set, and perform preprocessing to obtain a production standard data set, a processing standard data set, and a sales standard data set; S200. Extract features from the production standard data set, the processing standard data set, and the sales standard data set to obtain a production feature data set, a processing feature data set, and a sales feature data set; S300. Generate production portrait data, processing portrait data, and sales portrait data based on the production feature data set, the processing feature data set, and the sales feature data set; S400. Optimize product resources through the production feature data set, the processing feature data set, the sales feature data set, the production portrait data, the processing portrait data, and the sales portrait data to obtain a product resource optimization result, including at least: production volume optimization data, inventory optimization data, matching optimization data, distribution optimization data, and supply chain optimization data; Among them, optimize the production plan based on the production feature data set, the sales feature data set, and the production portrait data to obtain production volume optimization data and inventory optimization data; optimize product matching based on the production feature data set, the sales feature data set, and the sales portrait data to obtain matching optimization data; optimize product distribution based on the sales feature data set, the production portrait data, and the sales portrait data to obtain distribution optimization data; optimize the product supply chain based on the processing feature data set, the sales feature data set, the production portrait data, the processing portrait data, and the sales portrait data to obtain supply chain optimization data.

[0033] The present invention obtains a product production data set, a product processing data set, and a product sales data set. Through preprocessing and feature extraction, the corresponding production feature data set, processing feature data set, and sales feature data set are obtained. Based on the feature data set, portrait generation is performed to obtain production portrait data, processing portrait data, and sales portrait data. Through the obtained portrait data, product resource optimization is performed, including at least: production plan optimization, product matching optimization, product distribution optimization, and product supply chain optimization, thereby maximizing the utilization rate of product resources and improving the operation efficiency and customer satisfaction of the product supply chain.

[0034] In this embodiment, the glass industry is taken as an example. In the glass industry supply chain, data of upstream glass sheet factories (such as production capacity, inventory, etc.) directly affect the production arrangements of midstream processing factories; the processing capacity, delivery time, and product specifications of midstream processing factories affect the choices and orders of downstream customers. By conducting a linkage analysis on the data of the glass industry supply chain, the operating efficiency of the entire supply chain is optimized, including production arrangements, inventory allocation, and demand matching, etc.

[0035] According to the data characteristics of the glass industry, corresponding product production datasets, product processing datasets, and product sales datasets of upstream glass sheet factories, midstream processing factories, and downstream customers are obtained, fully considering the particularities of the glass industry, such as batch management of raw sheet production, customized requirements and services of processing factories, as well as personalized preferences and seasonal demand fluctuations of end customers. By collecting the behavior data of upstream and downstream customers (including glass sheet factories, processing factories, door and window stores, curtain wall companies, etc.), integrating procurement, production, logistics, and inventory information, and constructing a precise portrait model based on data. Through a multi-source data collection scheme, Internet of Things devices are used to collect the production capacity and inventory fluctuations of glass sheet factories, the ERP system integrates the order and processing specification information of processing factories, and market research feedbacks the preferences and project requirements of door and window stores and curtain wall companies for product types such as tempered glass and Low-E glass. The collected data is cleaned, de-duplicated, and standardized to ensure data quality. Combining behavior data with historical data, through a portrait generation model, customer portraits are generated to accurately depict customers' purchasing frequencies, product preferences, demand fluctuations, and delivery sensitivities. Through real-time data stream analysis technology and dynamic learning algorithms, the customer portraits are further optimized to dynamically respond to changes in customer needs and market fluctuations. Based on the obtained portraits, enterprises can optimize the resource allocation of the glass industry supply chain, such as: reasonably adjusting the raw sheet production capacity, optimizing the production scheduling order of processing factories, and customizing and recommending products and services that meet the needs of end customers, so as to improve the supply chain operation efficiency, reduce inventory costs, and help enterprises gain more business opportunities and increase profits in the highly competitive glass market.

[0036] During the data collection process, the data of upstream original factories includes production volume, inventory, demand from midstream processing factories, quality feedback, etc. Considering factors such as demand fluctuations and customized requirements of bulk purchasing customers, the corresponding product production volume data, product inventory data, customer demand data, and production quality scoring data of upstream original factories are obtained to form a product production data set; the key data of midstream processing factories are the production data of the processing factories, processing specification requirements, and the matching degree with upstream original factories. Especially in the case of glass processing factories, which often involve a large number of customized processes with diverse order types and specifications, the material supply data of upstream original factories is obtained and a matching degree analysis is carried out with product specification data to obtain production processing matching data. The demand score of processing orders in the region is obtained to get regional demand score data. The product processing volume data represents the processing volume of a certain processing by a midstream processing factory. Based on the production processing matching data, product processing volume data, product specification data, and regional demand score data, a product processing data set is formed; in the glass industry, downstream customers often rely on project requirements, such as construction projects and decoration projects, etc. The important data of downstream customers includes purchase records, project types, seasonal demand fluctuations, personalized demand services, and the matching degree with the products of midstream processing factories. Through the purchase records, project data, and personalized demand services of customers, customer order data and order type data are obtained. Through seasonal demand fluctuations, order fluctuation data is obtained. The matching degree between customer order data and the product processing data set is calculated to get sales processing matching data. Combining customer order data, order type data, and order fluctuation data, a product sales data set is formed.

[0037] Preprocess the product production data set, product processing data set, and product sales data set collected from the glass industry. The preprocessing process requires operations such as cleaning, deduplication, and standardization of the original data. In the data of the glass industry, especially when dealing with glass data of various specifications and types, attention needs to be paid to the unification and conversion between different data formats. Through data cleaning, missing values, unreasonable values, or error values are removed to ensure the integrity and validity of the data. Through standardization processing, the data is mapped to the [0,1] interval to ensure the comparability between different data. The specific formula for standardizing the data is as follows:

[0038] Among them, represents the production standard data set or processing standard data set or sales standard data set, represents the production standard data or processing standard data or sales standard data, represents the minimum value of the production standard data set or the minimum value of the processing standard data set or the minimum value of the sales standard data set, represents the maximum value of the production standard data set or the maximum value of the processing standard data set or the maximum value of the sales standard data set, Represents the initial product production dataset, or the initial product processing dataset, or the initial product sales dataset, Represents missing data and error data.

[0039] Through the data preprocessing process, the production standard dataset, the processing standard dataset, and the sales standard dataset are obtained, and feature extraction is performed respectively to obtain the corresponding production feature dataset, processing feature dataset, and sales feature dataset. Among them, the production feature dataset is obtained through the following steps: Step 1: Analyze the upstream data of the glass industry through the product output data and the product inventory data to obtain the total product production data and the average inventory data, which are expressed as follows:

[0040]

[0041] Step 2: Measure whether the inventory and production can meet the procurement requirements of specific midstream customers for the upstream data. Analyze based on the customer demand data and the product inventory data to obtain the procurement satisfaction rate data, which is expressed as follows:

[0042] Step 3: Calculate the average values of the customer demand data and the production quality score data to obtain the average demand data and the average quality data. Conduct volatility analysis based on the average demand data and the customer demand data to obtain the demand volatility data. Among them, the demand volatility data and the average quality data are expressed as follows:

[0043]

[0044] Step 4: Obtain the proportion of customized requirements of customers. If it is a customized order, the customer demand data is represented as 1. If it is non-customized, the customer demand data is represented as 0. Statistically obtain the customized demand data based on the customer demand data, and analyze to obtain the customized proportion data, which is expressed as follows:

[0045] Step 5: Form the production feature dataset through the total product production data, the average inventory data, the procurement satisfaction rate data, the demand volatility data, the average quality data, and the customized proportion data; Among them, Represents the total product production data, Represents the Product output data of the Represents the average inventory data, Represents the Product inventory data after the second production, indicating the procurement satisfaction rate data, indicating the customer demand data for the second production, indicating the demand volatility data, indicating the average demand data, indicating the average quality data, indicating the production quality score data for the second production, indicating the customization ratio data, indicating the customization ratio data, indicating the total number of production times, indicating the second production.

[0046] The processing feature dataset is obtained through the following steps: Step 1: Based on the processing standard dataset collected in the midstream of the glass industry, and based on the frequency of processing volume and specifications, obtain the diversity data of the total processing volume and processing specifications. Obtain the total product processing data through the product processing data, analyze the product specification data to obtain the specification frequency data, and then obtain the specification diversity data. Among them, the total product price data and the specification diversity data are expressed as follows:

[0047]

[0048] Step 2: Based on the demand score in the region where the processing order is located, obtain the average value of the regional demand score, and calculate the compatibility degree between the processing factory and the upstream raw sheet factory, that is, measure the coordination of material supply and specification matching. Specifically, solve the average value of the regional demand score data and the production and processing matching data to obtain the demand average data and the matching average data, which are expressed as follows:

[0049]

[0050] Step 3: Analyze the product processing volume data and the customer demand data to obtain the product delivery time data and solve the average value to obtain the delivery average data, which are expressed as follows:

[0051] Step 4: Form a processing feature dataset through the total product price data, specification diversity data, demand average data, matching average data, customization ratio data, and delivery average data; Among them, indicating the total product price data, Indicates the product processing volume data for the th processing, indicates the specification diversity data, indicates the product specification, indicates the specification frequency data, indicates the demand average data, Indicates the regional demand score data for the th processing, indicates the matching average data, Indicates the production processing matching data for the th processing, indicates the total number of processing times, Indicates the th processing, Indicates the th processing's product delivery time data, indicates the delivery average data.

[0052] The sales feature dataset is obtained through the following steps: Step 1: For the order data and order types collected downstream, obtain the total customer order data and order type data through the customer order data, and calculate the average value of the order type data to obtain the order average data. Among them, the total customer order data and the order average data are expressed as follows:

[0053]

[0054] Step 2: Obtain the mean values of the order fluctuation data and the sales processing matching data to obtain the average fluctuation data and the processing average data, which represent the matching degree between downstream orders and midstream processing plant products. Calculate the seasonal demand fluctuation characteristics through the order fluctuation data and the average fluctuation data to obtain the demand fluctuation data. Among them, the demand fluctuation data and the processing average data are expressed as follows:

[0055]

[0056] Step 3: Form a sales feature dataset through the total customer order data, order average data, demand fluctuation data, processing average data, and customization ratio data; Among them, represents the total customer order data, Indicates the th customer order data for sales, represents the order average data, Indicates the th order type data for sales, represents the number of sales, represents the order fluctuation data of the th sale, represents the average processing data, represents the sales - processing matching data of the th sale, represents the demand fluctuation data, represents the

[0057] In the process of image generation, in this embodiment, weight analysis and clustering analysis are respectively performed on the production feature dataset, the processing feature dataset, and the sales feature dataset to obtain the corresponding production image data, processing image data, and sales image data, including the following steps: Step 1: Set weight coefficients for each feature in the production feature dataset, the processing feature dataset, and the sales feature dataset to represent the corresponding importance degree, and obtain the corresponding production weights, processing weights, and sales weights; Step 2: According to the production feature dataset, the processing feature dataset, and the sales feature dataset and the corresponding production weights, processing weights, and sales weights, perform weight analysis on the production feature dataset, the processing feature dataset, and the sales feature dataset to obtain the corresponding production feature scores, processing feature scores, and sales feature scores, which are expressed as follows:

[0058] Step 3: Preset production clustering thresholds, processing clustering thresholds, and sales clustering thresholds, and classify the production feature dataset, the processing feature dataset, and the sales feature dataset, that is, group the corresponding feature datasets and obtain the corresponding class centers, which are expressed as follows:

[0059] Step 4: Respectively based on the production feature dataset, the processing feature dataset, and the sales feature dataset and the corresponding class centers, and perform iterative clustering through the iterative optimization function to obtain the corresponding feature clustering results, and obtain production feature labels, processing feature labels, and sales feature labels through the corresponding feature clustering results, where the iterative optimization function is expressed as follows:

[0060] Step 5: Form production image data through production feature scores and production feature labels, form processing image data through processing feature scores and processing feature labels, and form sales image data through sales feature scores and sales feature labels; wherein, represents the production feature score or the processing feature score or the sales feature score, Indicates the th production weight or processing weight or sales weight, the th production feature data or processing feature data set or sales feature data set, indicates the number of features in the production feature data set or processing feature data set or sales feature data set, indicates the category center, indicates the th clustering center, indicates the iterative optimization function, indicates the production clustering threshold.

[0061] The upstream production portrait data combines the data relationship between the upstream and the midstream and is based on factors such as the production capacity, inventory, and customer demand of the original film factory. The weight coefficient is set based on the characteristics of the customers. For example, the characteristics of large customers are: 、 The corresponding production weight is high, the corresponding one is low, described as: large total production volume, stable procurement demand and high satisfaction rate; The characteristics of customers with customization preferences are: The corresponding production weight is high, described as: high proportion of customization demand and emphasis on personalized products. The midstream processing portrait data focuses on processing capacity, regional demand characteristics and compatibility with the upstream, providing support for optimizing production, inventory scheduling and downstream order management. For example, the characteristics of large-scale customized processing factories are: 、 The corresponding processing weight is high, described as: strong processing ability and high proportion of customization demand; The characteristics of high-diversity processing factories are: The corresponding processing weight is high, described as: strong ability of the processing factory to handle multiple specifications; The characteristics of regionally demand-oriented processing factories are: The corresponding processing weight is high, described as: processing orders are mainly concentrated in high-demand regions. The downstream sales portrait data describes the purchasing behavior, demand characteristics, seasonal preferences of customers and the matching situation with midstream processing factories. For example, the characteristics of customers with high seasonal demand are: The corresponding sales weight is high, described as: the order demand changes significantly with seasons, and supply needs to be guaranteed preferentially during peak seasons; Customers with customization services: The corresponding sales weight is high, described as: customers have high demand for personalized services and need customized products or special service support; The characteristics of long-term stable customers are: 、 The corresponding sales weight is high, the corresponding sales weight is low, described as: large and stable purchases and high matching degree with midstream processing factories.

[0062] Adjust the production plan and inventory management according to the production feature dataset, sales feature dataset, and production portrait data to maximize resource utilization and meet customer needs, that is, optimize the production plan, including the following steps: Step 1: Obtain the demand for all categories of products from customers through the customer order data in the product sales dataset to obtain category demand data; Step 2: Analyze the importance of customers based on the customer order data to obtain customer weight data, which is used to reflect the size of customer orders, and obtain the comprehensive customer weight based on the sales portrait data. Combine the category demand data and customer weight data to optimize the production plan to obtain production volume optimization data, expressed as follows:

[0063] Step 3: According to the product production volume data, customer order data, and order type data, obtain the demand for all types of products from customers in the region to obtain regional demand data; Step 4: Obtain the regional comprehensive weight through the production portrait data and sales portrait data, and combine the regional demand data to optimize the inventory allocation to obtain inventory optimization data, expressed as follows:

[0064] Among them, represents the production volume optimization data of the th category of products, represents the customer weight data of customer , represents customer 's category demand data for the th category of products, represents the comprehensive customer weight of customer for the th category of products, represents the inventory optimization data of the th category of products, represents the regional demand data of the th category of products within region , represents the regional comprehensive weight of the th category of products within region , represents the number of regions.

[0065] Based on the preference and demand characteristics of the portraits in the sales portrait data, accurately recommend products or services to end customers to achieve product matching optimization and obtain matching optimization data, which specifically includes the following steps: Step 1: Obtain the matching degree between the production feature dataset and the sales feature dataset to obtain feature matching data; Step 2: Obtain label weight data based on the processed image data and the sales image data. For example, if the image data reflects that customers have a preference for a certain specific label product (such as "energy-saving glass preference"), the label weight data is obtained through mapping, and the product matching is optimized by combining the feature matching data to obtain the matching optimization data, which is expressed as follows:

[0066] Among them, represents the customer for the th class of product matching optimization data, represents the th sales feature data of the customer and the feature matching data of the th class of product, represents the feature matching data set, represents the th label weight data of the customer's th feature,

[0067] Utilize the upstream and downstream customer portraits to optimize the logistics distribution and supply chain collaboration, improve the efficiency of the entire supply chain, and obtain the distribution optimization data through product distribution optimization. The specific steps are as follows: Step 1: Analyze the priority of order distribution through customer order data to obtain order distribution data; Step 2: Analyze the urgency of customer orders through the production image data and the sales image data. For example, for "high-frequency customers", the economic degree of customer orders is higher. Obtain the customer priority data, and combine the order distribution data and the customer weight data to optimize the product distribution to obtain the distribution optimization data, which is expressed as follows:

[0068] Among them, represents the th class of product distribution optimization data, represents the customer's th class of product customer priority data, represents the number of customers, represents the customer's customer weight data, represents the customer's th class of product category demand data.

[0069] Based on the processed feature data set, the sales feature data set, the production image data, the processed image data, and the sales image data, conduct product supply chain optimization to obtain the supply chain optimization data. The specific steps are as follows: Step 1: Obtain the matching degree between the processing feature dataset and the sales feature dataset to obtain product adaptation data; Step 2: Through production portrait data, processing portrait data, and sales portrait data, obtain supply chain adaptation data, and combine the product adaptation data to optimize the product supply chain to obtain supply chain optimization data, expressed as follows:

[0070] Wherein, represents the supply chain optimization data, represents the th product adaptation data for the th sale of the th type of product, represents the supply chain adaptation data for the th sale of the

[0071] In this embodiment, a specific example is given. If, according to the sales feature tags of the sales portrait data, the current customer portrait tag 1 is a large customer and tag 2 is a seasonal peak customer, the customer weight data is set to 1.5 and 1.2 respectively according to tag 1 and tag 2. If the category demand data for product A1 is and the category demand data for product A2 is , the production volume optimization data obtained through production plan optimization is: ; Assuming that the matching degree between product B1 and the customer is and the matching degree between product B2 and the customer is , and the corresponding tag weight data is 1.3 and 1.1, then the matching optimization data for product B1 is and the matching optimization data for product B2 is . It can be obtained that the matching optimization data for product B1 is higher, so product B1 is recommended first.

[0072] This embodiment is optimized through production portrait data, processing portrait data, and sales portrait data, which not only fully considers the unique needs of the glass industry, but also can efficiently utilize customer portraits to improve operation efficiency, supply chain operation efficiency, and decision-making accuracy.

[0073] Embodiment 2: A product supply chain portrait generation and product resource optimization system, as Figure 2 shown, includes a data acquisition module 100, a feature extraction module 200, a portrait generation module 300, and a resource optimization module 400; The data acquisition module 100 acquires the product production dataset, product processing dataset, and product sales dataset, and performs preprocessing to obtain the production standard dataset, processing standard dataset, and sales standard dataset; The feature extraction module 200 extracts features from the production standard dataset, processing standard dataset, and sales standard dataset to obtain the production feature dataset, processing feature dataset, and sales feature dataset; The portrait generation module 300 generates production portrait data, processing portrait data, and sales portrait data based on the production feature dataset, processing feature dataset, and sales feature dataset; The resource optimization module 400 performs product resource optimization through the production feature dataset, processing feature dataset, sales feature dataset, production portrait data, processing portrait data, and sales portrait data to obtain the product resource optimization result, including at least: production volume optimization data, inventory optimization data, matching optimization data, distribution optimization data, and supply chain optimization data; Among them, production plan optimization is performed based on the production feature dataset, sales feature dataset, and production portrait data to obtain production volume optimization data and inventory optimization data; product matching optimization is performed based on the production feature dataset, sales feature dataset, and sales portrait data to obtain matching optimization data; product distribution optimization is performed based on the sales feature dataset, production portrait data, and sales portrait data to obtain distribution optimization data; product supply chain optimization is performed based on the processing feature dataset, sales feature dataset, production portrait data, processing portrait data, and sales portrait data to obtain supply chain optimization data.

[0074] All changes and variations made without departing from the spirit and scope of the present invention, and all equivalent technical solutions also fall within the scope of the present invention.

[0075] Each embodiment in this specification is described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same and similar parts among the embodiments, reference can be made to each other.

[0076] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, devices, or computer program products. Therefore, the present invention can be implemented in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can be implemented in the form of a computer program product on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] The present invention is described with reference to the flowcharts and / or block diagrams of methods, terminal devices (systems), and computer program products according to the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing terminal devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing terminal devices generate means for implementing the functions specified in one or more of the flows Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0078] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in one or more of the flows Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0079] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, such that a series of operation steps are executed on the computer or other programmable terminal device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0080] It should be noted that: The phrase "an embodiment" or "embodiments" mentioned in the specification means that the specific features, structures, or characteristics described in connection with the embodiments are included in at least one embodiment of the present invention. Therefore, the phrases "an embodiment" or "embodiments" that appear throughout the specification do not necessarily all refer to the same embodiment.

[0081] In addition, it should be noted that for the specific embodiments described in this specification, the shapes, names, etc. of their components can be different. Any equivalent or simple changes made to the structures, features, and principles described according to the inventive concept of the present invention are included within the protection scope of the present invention. Those skilled in the art to which the present invention pertains can make various modifications, supplements, or use similar ways of substitution to the specific embodiments described, as long as they do not deviate from the structure of the present invention or exceed the scope defined by the claims of the present invention, they should all fall within the protection scope of the present invention.

Claims

1. A method for generating a product supply chain portrait and optimizing product resources, characterized in that, It includes the following steps: Obtain the product production dataset, product processing dataset, and product sales dataset and perform preprocessing to obtain the production standard dataset, processing standard dataset, and sales standard dataset; Extract features from the production standard dataset, processing standard dataset, and sales standard dataset to obtain the production feature dataset, processing feature dataset, and sales feature dataset; Generate production portrait data, processing portrait data, and sales portrait data based on the production feature dataset, processing feature dataset, and sales feature dataset; Optimize product resources through the production feature dataset, processing feature dataset, sales feature dataset, production portrait data, processing portrait data, and sales portrait data to obtain the product resource optimization result, which at least includes: production volume optimization data, inventory optimization data, matching optimization data, distribution optimization data, and supply chain optimization data; Among them, optimize the production plan based on the production feature dataset, sales feature dataset, and production portrait data to obtain the production volume optimization data and inventory optimization data; optimize product matching based on the production feature dataset, sales feature dataset, and sales portrait data to obtain the matching optimization data; optimize product distribution based on the sales feature dataset, production portrait data, and sales portrait data to obtain the distribution optimization data; optimize the product supply chain based on the processing feature dataset, sales feature dataset, production portrait data, processing portrait data, and sales portrait data to obtain the supply chain optimization data.

2. The method for generating a product supply chain portrait and optimizing product resources according to claim 1, wherein The generating of the production portrait data, processing portrait data, and sales portrait data based on the production feature dataset, processing feature dataset, and sales feature dataset includes the following steps: According to the importance degrees of the production portrait data, processing portrait data, and sales portrait data with respect to the production feature dataset, processing feature dataset, and sales feature dataset, set the corresponding production weights, processing weights, and sales weights through mapping; Obtain the production feature scores, processing feature scores, and sales feature scores by combining the production weights, processing weights, and sales weights with the production feature dataset, processing feature dataset, and sales feature dataset; Preset the production clustering threshold, processing clustering threshold, and sales clustering threshold, classify the production feature dataset, processing feature dataset, and sales feature dataset, and obtain the corresponding class centers; Based on the production feature dataset, processing feature dataset, and sales feature dataset and the corresponding class centers, and perform iteration through the iterative optimization function until the iterative optimization function is minimized, obtain the corresponding feature clustering results, and obtain the production feature labels, processing feature labels, and sales feature labels through the corresponding feature clustering results; Form the production portrait data through the production feature scores and production feature labels, form the processing portrait data through the processing feature scores and processing feature labels, and form the sales portrait data through the sales feature scores and sales feature labels; Among them, the production feature scores, processing feature scores, and sales feature scores are respectively expressed as follows: The class centers are expressed as follows: The iterative optimization function is expressed as follows: Among them, represents the production feature score or the processing feature score or the sales feature score, represents the th production weight or processing weight or sales weight, the th production feature data or processing feature data set or sales feature data set, represents the number of features in the production feature data set or the processing feature data set or the sales feature data set, represents the class center, represents the th clustering center, represents the iterative optimization function, represents the production clustering threshold.

3. The method for generating a product supply chain portrait and optimizing product resources according to claim 1, wherein Based on the production feature dataset, sales feature dataset, and production portrait data, optimize the production plan to obtain production volume optimization data and inventory optimization data, including the following steps: Obtain the demand for all categories of products in the customer orders through the customer order data to get category demand data; Analyze the importance degree of customers based on the customer order data to obtain customer weight data, and obtain the comprehensive customer weight based on the sales portrait data. Combine the category demand data and customer weight data to obtain production volume optimization data; Analyze the regional characteristics of the product production volume data, customer order data, and order type data to obtain the demand for products in each region to get regional demand data; Obtain the comprehensive regional weight through the production portrait data and sales portrait data, and combine the regional demand data to optimize the inventory allocation to obtain inventory optimization data; Among them, the production volume optimization data is expressed as follows: The inventory optimization data is expressed as follows: Among them, represents the production optimization data of the th type of product, represents the customer weight data, represents the customer 's category demand data for the th type of product, represents the customer 's comprehensive customer weight for the th type of product, represents the inventory optimization data of the th type of product, represents the regional demand data of the th type of product within the region , represents the regional comprehensive weight of the th type of product within the region , represents the number of regions.

4. The method for generating a product supply chain portrait and optimizing product resources according to claim 1, wherein Based on the production feature dataset, sales feature dataset, and sales portrait data, optimize the product matching to obtain matching optimization data, including the following steps: Obtain the matching degree between the production feature dataset and the sales feature dataset to get feature matching data; Based on the processing portrait data and sales portrait data, obtain the preference data of customers for products to get label weight data. Combine the feature matching data to optimize the product matching to obtain matching optimization data, which is expressed as follows: Among them, represents the matching optimization data of the customer for the category of products, represents the th sales feature data of the customer and the feature matching data of the category of products, represents the feature matching data set, represents the th label weight data of the feature of the customer, represents the number of features.

5. The method for generating a product supply chain portrait and optimizing product resources according to claim 1, wherein Based on the sales feature dataset, production portrait data, and sales portrait data, optimize the product distribution to obtain distribution optimization data, including the following steps: Based on the customer weight data and customer order data, obtain the priority of customer order distribution to get order distribution data; Through the production portrait data and sales portrait data, obtain the urgency of the customer order, and obtain the customer priority data according to the urgency. Combine the order distribution data and customer weight data to optimize the product distribution to obtain distribution optimization data, which is expressed as follows: Among them, represents the distribution optimization data of the th class of products, represents the customer priority data for the th class of products, represents the number of customers, represents the customer weight data, represents the customer demand data for the th class of products.

6. The product supply chain portrait generation and product resource optimization method according to claim 1, wherein Based on the processing feature dataset, sales feature dataset, production portrait data, processing portrait data, and sales portrait data, optimize the product supply chain to obtain supply chain optimization data, including the following steps: Obtain the matching degree between the processing feature dataset and the sales feature dataset to get product adaptation data; Through the production portrait data, processing portrait data, and sales portrait data, obtain the adaptation degree between the processing factory and the customer to get supply chain adaptation data. Combine the product adaptation data to optimize the product supply chain to obtain supply chain optimization data, which is expressed as follows: Among them, represents supply chain optimization data, represents the product adaptation data for the th sale of products in category represents the supply chain adaptation data for the th sale of products in category represents the number of sales.

7. The method for generating a product supply chain portrait and optimizing product resources according to claim 1, wherein The steps for obtaining the product production dataset, product processing dataset, and product sales dataset include the following: Obtain the product production volume data, product inventory data, customer demand data, and production quality scoring data to form the product production dataset; Obtain the material supply data and product specification data and analyze them to get production processing matching data. Combine the product processing volume data, product specification data, and regional demand scoring data to form the product processing dataset; Obtain customer order data, analyze it in combination with the product processing data set, obtain the sales and processing matching data, and form a product sales data set by combining the customer order data, order type data, and order fluctuation data.

8. The method for generating a product supply chain portrait and optimizing product resources according to claim 1, wherein The preprocessing includes the following steps: Remove the missing data and error data in the product production data set, product processing data set, and product sales data set, and obtain the initial product production data set, initial product processing data set, and initial product sales data set through data deduplication; Perform standardization processing on the initial product production data set, initial product processing data set, and initial product sales data set to obtain the production standard data set, processing standard data set, and sales standard data set, which are expressed as follows: Among them, represents a production standard data set or a processing standard data set or a sales standard data set, represents production standard data or processing standard data or sales standard data, represents the minimum value of a production standard data set or the minimum value of a processing standard data set or the minimum value of a sales standard data set, represents the maximum value of a production standard data set or the maximum value of a processing standard data set or the maximum value of a sales standard data set, represents an initial product production data set or an initial product processing data set or an initial product sales data set, represents missing data and error data.

9. The method for generating a product supply chain portrait and optimizing product resources according to claim 1, wherein The production feature data set is obtained through the following steps: Analyze the product output data and product inventory data to obtain the total product production data and average inventory data; Analyze based on the customer demand data and product inventory data to obtain the procurement satisfaction rate data; Solve the average values of the customer demand data and production quality score data to obtain the average demand data and quality average data, and perform fluctuation analysis based on the average demand data and customer demand data to obtain the demand volatility data; Obtain the customized demand data based on the customer demand data and analyze to obtain the customization ratio data; Form a production feature data set through the total product production data, average inventory data, procurement satisfaction rate data, demand volatility data, quality average data, and customization ratio data.

10. The method for generating a product supply chain portrait and optimizing product resources according to claim 1, wherein, The processing feature data set is obtained through the following steps: Obtain the total product processing data from the product processing data, analyze based on the product specification data to obtain the specification frequency data, and then obtain the specification diversity data; Solve the average values of the regional demand score data and production and processing matching data to obtain the demand average data and matching average data; Analyze the product processing volume data and customer demand data to obtain the product delivery time data and solve the average value to obtain the delivery average data; Form a processing feature data set through the total product price data, specification diversity data, demand average data, matching average data, customization ratio data, and delivery average data.

11. The method for generating a product supply chain portrait and optimizing product resources according to claim 1, wherein The sales feature data set is obtained through the following steps: Obtain the total customer order data and order type data from the customer order data, and solve the average value of the order type data to obtain the order average data; Obtain the mean values of the order fluctuation data and sales and processing matching data to obtain the average fluctuation data and processing average data, and obtain the demand fluctuation data through the order fluctuation data and average fluctuation data; Form a sales feature data set through the total customer order data, order average data, demand fluctuation data, processing average data, and customization ratio data.

12. A product supply chain portrait generation and product resource optimization system, characterized in that, It includes a data acquisition module, a feature extraction module, a portrait generation module, and a resource optimization module; The data acquisition module obtains the product production data set, product processing data set, and product sales data set and performs preprocessing to obtain the production standard data set, processing standard data set, and sales standard data set; The feature extraction module extracts features from the production standard dataset, processing standard dataset, and sales standard dataset to obtain a production feature dataset, a processing feature dataset, and a sales feature dataset; The portrait generation module generates production portrait data, processing portrait data, and sales portrait data based on the production feature dataset, processing feature dataset, and sales feature dataset; The resource optimization module optimizes product resources through the production feature dataset, processing feature dataset, sales feature dataset, production portrait data, processing portrait data, and sales portrait data to obtain product resource optimization results, including at least: production volume optimization data, inventory optimization data, matching optimization data, distribution optimization data, and supply chain optimization data; Among them, production plan optimization is performed based on the production feature dataset, sales feature dataset, and production portrait data to obtain production volume optimization data and inventory optimization data; product matching optimization is performed based on the production feature dataset, sales feature dataset, and sales portrait data to obtain matching optimization data; product distribution optimization is performed based on the sales feature dataset, production portrait data, and sales portrait data to obtain distribution optimization data; product supply chain optimization is performed based on the processing feature dataset, sales feature dataset, production portrait data, processing portrait data, and sales portrait data to obtain supply chain optimization data.

13. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method according to any one of claims 1 to 11.

14. A product supply chain portrait generation and product resource optimization device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1 to 11.

Images