Financial service big data warehouse management system

Abstract

The invention discloses a financial service big data warehouse management system, and relates to the technical field of data warehouses, and the system comprises an inventory information monitoring module which is used for carrying out the warehouse-in and warehouse-out recording of existing goods in a warehouse; and the goods demand analysis module is electrically connected with the inventory information monitoring module, and the goods demand analysis module is used for analyzing goods demands according to the inventory information in combination with the big data information. According to the financial service big data warehouse management system, through the inventory information monitoring module, the system can automatically record warehouse-in and warehouse-out conditions of goods in a warehouse in real time, dependence of manual operation is greatly reduced, the management efficiency is improved, the goods demand analysis module combines inventory information and external big data information, and the management efficiency is improved. The goods demand is accurately predicted, the accuracy of demand prediction is improved, and enterprises can better grasp market trends.

Description

Technical Field

[0001] The present invention relates to the technical field of data warehouses, and in particular to a financial services big data warehouse management system. Background Art

[0002] In the financial services industry, big data warehouse management systems play a vital role. However, traditional warehouse management systems often face many challenges. First, the monitoring and management of inventory information often rely on manual operations, which is not only inefficient but also prone to errors. Second, for the forecasting and analysis of product demand, traditional systems usually only rely on limited internal data, such as historical sales records, and ignore the importance of external big data information, such as seasonal sales trends, market trends, consumer behavior data, and competitor information, which greatly reduces the accuracy of demand forecasts. In addition, in the selection and evaluation of procurement suppliers, traditional systems also lack scientificity and comprehensiveness. They often only consider the basic information of suppliers, such as price and quality, but ignore the correlation between suppliers and procurement demand goods, as well as the supplier's own risk assessment and the risk-bearing capacity of downstream companies. This one-sided evaluation method not only leads to low procurement efficiency, but also increases procurement risks. In this regard, we propose a financial services big data warehouse management system. Summary of the invention

[0003] In order to solve the above technical problems, a financial services big data warehouse management system is provided. This technical solution solves the above problems.

[0004] In order to achieve the above purpose, the technical solution adopted by the present invention is: A financial services big data warehouse management system, the warehouse management system comprising: Inventory information monitoring module, which is used to record the entry and exit of existing goods in the warehouse; A product demand analysis module, which is electrically connected to the inventory information monitoring module, and is used to analyze product demand based on inventory information and combined with big data information, and output purchase demand; A procurement supplier information acquisition and analysis module, which is electrically connected to the product demand analysis module, and is used to acquire basic information of each procurement supplier, and analyze and calculate the relevance of the acquired supplier basic information with the purchase demand products, and match the corresponding procurement supplier according to the calculated relevance result; A procurement supplier evaluation module, which is electrically connected to the procurement supplier information acquisition and analysis module, and is used to perform a comprehensive evaluation on the procurement supplier based on the correlation calculation result and output the evaluation result; A procurement plan generation module is electrically connected to the product demand analysis module and the procurement supplier evaluation module. The procurement plan generation module is used to combine the procurement demand and the evaluation results of the procurement supplier evaluation module to output a procurement plan.

[0005] Preferably, the purchase demand output by the product demand analysis module specifically includes: Based on the inventory information monitoring module, obtain the inventory quantity, in and out records and inventory turnover rate information of warehouse goods; Collect external big data information related to product demand, including: historical sales data of the same category, seasonal sales trends, market trends, consumer behavior data and competitor information; Clean the collected data, remove duplicate, erroneous and invalid data, and standardize the processed data; Extracting characteristic data related to product demand from the cleaned existing inventory information and big data information, wherein the extracted characteristic data related to product demand includes inventory volume, sales growth rate, seasonal fluctuation and market growth rate; Establish a forecasting model for goods purchase demand; Based on the product purchase demand forecasting model, several characteristic data related to the product purchase demand are used as the influencing conditions, the inventory information is used as the input, and the corresponding future product purchase demand at the forecast time node is used as the output; Based on the forecast results, combined with the safety stock and reorder point of the inventory strategy, the purchasing demand index is calculated and output.

[0006] Preferably, the commodity purchase demand forecasting model expression is:

[0007] In the formula, Y represents the demand for goods, t represents the corresponding time node, and p is the autoregressive order, that is, the number of time points involved when the values ​​of several past time points are used in the model to predict the current value. and are model parameters, represents the error term, q represents the moving average order, that is, the number of time points involved when the prediction errors of several past time points used in the model affect the current prediction value. represents the demand for goods at time t.

[0008] Preferably, the calculation method of safety stock and reorder point is: The calculation formula for safety stock is:

[0009] In the formula, S represents the safety stock, Z represents the Z value of the standard normal distribution corresponding to the percentage of order fulfillment rate, represents the demand standard deviation, L represents the lead time, represents the replenishment cycle, represents the standard deviation of the lead time, and d represents the average daily demand; The calculation formula for the reorder point is:

[0010] Where R represents the reorder point.

[0011] Preferably, the procurement supplier information acquisition and analysis module acquires the basic information of the procurement supplier and calculates the relevance specifically including: The procurement supplier information acquisition and analysis module acquires basic information of each procurement supplier from several data sources, wherein the basic information of the procurement supplier includes financial information, production information, warehousing information, logistics information and operation information, and aggregates the acquired procurement suppliers into a set by name; Based on the purchasing suppliers in set 1, their basic information is cleaned, the cleaned information is standardized, and the feature vectors related to the goods in the purchasing supplier information are extracted; Extract the feature vector of the goods according to the purchase demand output by the goods demand analysis module; For each supplier, calculate the correlation between the key attributes of the products it provides and the purchased goods. The correlation calculation method is:

[0012] In the formula, C represents the correlation between the purchasing supplier and the purchase demand goods, n represents the total number of feature vectors, k represents the kth feature vector, G represents the purchase demand goods, F represents the purchasing supplier, e represents the number of the eth purchase demand goods, h represents the number of the hth purchasing suppliers, represents the value of the e-th purchase demand item G on the k-th feature vector, represents the value of the h-th purchasing supplier F on the k-th feature vector; According to the calculated correlation results, the procurement suppliers with correlation in set one are screened out and aggregated into set two. The procurement suppliers in set two are sorted according to the size of the correlation, and the results are output to the procurement supplier evaluation module.

[0013] Preferably, the risk assessment score given by the procurement supplier assessment module specifically includes: A second summary set of relevant procurement suppliers selected based on the procurement supplier information acquisition and analysis module; Conduct risk assessments on several procurement suppliers in Set 2 and risk-bearing capacity assessments on downstream companies; Based on the risk assessment results of the procurement suppliers themselves and the risk-bearing capacity assessment results of the downstream companies, the procurement suppliers are re-ranked, the procurement supplier with the best comprehensive assessment is selected, and the results of the comprehensive assessment are output.

[0014] Preferably, the method for risk assessment of procurement suppliers themselves is: Acquire basic data of procurement suppliers based on the procurement supplier information acquisition and analysis module, wherein the basic information includes: registered capital, years of establishment and credit record; Acquire the procurement supplier operation status data based on the procurement supplier information acquisition and analysis module, wherein the operation status data includes: annual sales, profit margin and debt-to-asset ratio; Based on the procurement supplier information acquisition and analysis module, the location information of the procurement demand goods in the supplier company is obtained, and the location information includes: whether it is a core product, production scale and technical capabilities; Based on the procurement supplier information acquisition and analysis module, the market share information of the procurement demand goods in the supplier company is obtained, and the market share information includes: market share, market growth rate and competition situation; Clean and preprocess the data; Extract several characteristics reflecting the supplier's financial status, market position and product quality from the cleaned data; The Delphi expert method is used to calculate the weights of the extracted features that affect the risk assessment of procurement suppliers; Establish a procurement supplier risk assessment model; Based on the procurement supplier risk assessment model, a number of data reflecting the supplier's financial status, market position and product quality characteristics are extracted and input into the assessment model to conduct risk assessment on the supplier and calculate the risk assessment score; Among them, the expression of the procurement supplier risk assessment model is:

[0015] In the formula, represents the total number of features, Indicates The weights of the factors that reflect the supplier's financial status, market position, and product quality characteristics are w, x, and the weights of the factors that reflect the supplier's financial status, market position, and product quality characteristics are x. Indicates weights that reflect the supplier's financial situation, market position, and product quality characteristics. Indicates A standardized value that reflects a supplier's financial condition, market position, and product quality characteristics.

[0016] Preferably, the method for assessing the risk-bearing capacity of downstream companies is: Based on the procurement supplier information acquisition and analysis module, basic information of downstream companies of procurement suppliers is obtained, and the basic information includes: registered capital, years of establishment and credit records; Acquire the operating status data of downstream companies of the purchasing supplier based on the purchasing supplier information acquisition and analysis module, wherein the operating status data includes: annual sales, profit margin and cash flow status; Based on the procurement supplier information acquisition and analysis module, the cooperation history and scale information between downstream companies and procurement suppliers are obtained; Clean and preprocess the data; Extract features reflecting the risk-bearing capacity of downstream companies that purchase suppliers from the cleaned data; The weights of the extracted features that affect the risk-bearing capacity assessment of downstream companies are calculated through the Delphi expert method; Establish a risk-bearing capacity assessment model for downstream companies; Based on the downstream company risk bearing capacity assessment model, the extracted characteristic data affecting the downstream company risk bearing capacity assessment is input into the assessment model, the risk bearing capacity of the downstream company is assessed, and the risk bearing capacity assessment score is calculated; Among them, the expression of the downstream company risk bearing capacity assessment model is:

[0017] In the formula, represents the total number of features used by downstream companies to assess their risk-taking capacity, Indicates The feature that reflects the risk-bearing capacity of the downstream company is represented by u, which represents the feature weight that reflects the risk-bearing capacity of the downstream company, and v represents the standardized value of the feature that reflects the risk-bearing capacity of the downstream company.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The financial service big data warehouse management system proposed in the present invention uses an inventory information monitoring module, and the system can automatically record the entry and exit of goods in the warehouse in real time, greatly reducing the reliance on manual operations and improving management efficiency. The product demand analysis module combines inventory information and external big data information to accurately predict product demand, thereby improving the accuracy of demand forecasting, helping companies to better grasp market dynamics and optimize inventory management. Through a comprehensive assessment of procurement suppliers, including an assessment of their own risks and the risk-bearing capacity of downstream companies, companies can better identify and control potential risks in the procurement process, helping companies to establish a stable and reliable supply chain system and ensure their normal operation and sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of the present invention; DETAILED DESCRIPTION

[0020] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0021] Reference Figure 1 As shown, a financial service big data warehouse management system, the warehouse management system includes: The warehouse management system includes an inventory information monitoring module. The core function of the module is to monitor and record the entry and exit of existing goods in the warehouse in real time. This module can ensure that warehouse managers can grasp the inventory dynamics of goods in real time; The product demand analysis module uses inventory information and external big data information to conduct in-depth analysis of product demand. These big data information include historical sales data of the same category, seasonal sales trends, market trends, consumer behavior data and competitor information. Through the cleaning, standardization and feature extraction of these data, the product demand analysis module can establish a product purchase demand forecasting model and predict the product purchase demand at a certain time point in the future based on the model. At the same time, combined with the safety inventory and reorder point of the inventory strategy, the module can calculate and output specific purchase demand indicators to provide strong support for procurement decisions; The main responsibility of the procurement supplier information is to obtain the basic information of each procurement supplier, and analyze and calculate the relevance with the procurement demand goods based on this information. This information covers the supplier's financial information, production information, warehousing information, logistics information and operation information. By calculating the relevance between the products provided by the supplier and the key attributes of the procurement demand goods, this module can screen out the procurement suppliers that best match the demand and sort them by the size of the relevance; The procurement supplier evaluation module will conduct a comprehensive evaluation of these selected suppliers. This module not only considers the risk assessment of the supplier itself, but also pays attention to the supplier's market share. At the same time, the module will also evaluate the risk-bearing capacity of the supplier's downstream companies, including the basic information of the downstream companies, operating conditions, and cooperation history and scale with the supplier. By comprehensively considering these factors, the procurement supplier evaluation module can give the supplier's risk assessment score and output the evaluation results; The procurement plan generation module combines the purchase demand output by the product demand analysis module and the evaluation results of the procurement supplier evaluation module to automatically generate the optimal procurement plan.

[0022] The product demand analysis module outputs the purchasing demand, including: The product demand analysis module will obtain detailed inventory data of warehouse products from the inventory information monitoring module. These data cover the inventory quantity, in-and-out records and inventory turnover rate of the products, providing a solid foundation for subsequent product demand analysis. The module will widely collect external big data information related to product demand. These information sources are extensive, including but not limited to historical sales data of the same category, seasonal sales trends, market trends, consumer behavior data and competitor information. The collection of these data is intended to help the module understand market dynamics and consumer demand more comprehensively, so as to more accurately predict future product demand; After collecting a large amount of data, the product demand analysis module will strictly clean and process the data. This step is crucial because it can remove duplicate, erroneous and invalid data to ensure the accuracy and reliability of subsequent analysis. The cleaned data will be further standardized so that it can be better used in the subsequent analysis and modeling process. The product demand analysis module extracts characteristic data closely related to product demand from the existing inventory information and big data information after cleaning. These characteristic data include but are not limited to inventory volume, sales growth rate, seasonal fluctuations and market growth rate. By extracting these characteristic data, the module can have a deeper understanding of the inherent laws and changing trends of product demand. On this basis, the module will establish a product purchase demand forecasting model. This model can predict the product purchase demand at future time nodes based on the extracted characteristic data and historical data, and can comprehensively consider multiple influencing factors to obtain more accurate forecasting results. After the model is established, the module will take several characteristic data related to the product purchase demand as influencing conditions, take inventory information as input, and calculate the corresponding future product purchase demand at the forecast time node through the model. This process makes full use of the model's forecasting ability and the correlation of data, making the forecast results more in line with the actual situation. Based on the forecast results, the module will combine the safety inventory and reorder point of the inventory strategy to calculate and output the final purchase demand indicators. These indicators not only consider future product demand, but also fully consider the safety and stability of inventory, providing strong support for the company's procurement decisions.

[0023] The commodity purchase demand forecasting model expression is:

[0024] In the formula, Y represents the demand for goods, t represents the corresponding time node, and p is the autoregressive order, that is, the number of time points involved when the values ​​of several past time points are used in the model to predict the current value. and are model parameters, represents the error term, q represents the moving average order, that is, the number of time points involved when the prediction errors of several past time points used in the model affect the current prediction value. represents the demand for goods at time t.

[0025] The calculation method of safety stock and reorder point is: The calculation formula for safety stock is:

[0026] In the formula, S represents the safety stock, Z represents the Z value of the standard normal distribution corresponding to the percentage of order fulfillment rate, represents the demand standard deviation, L represents the lead time, represents the replenishment cycle, represents the standard deviation of the lead time, and d represents the average daily demand; The calculation formula for the reorder point is:

[0027] Where R represents the reorder point.

[0028] The procurement supplier information acquisition and analysis module acquires the basic information of procurement suppliers and calculates the relevance, including: The workflow of the procurement supplier information acquisition and analysis module can be summarized as follows: obtain the basic information of procurement suppliers from multiple data sources, summarize and process this information, then extract the feature vectors related to the goods, calculate the correlation between the products provided by the suppliers and the key attributes of the purchased goods, and finally select the procurement suppliers with correlation according to the correlation results and sort them; For each supplier, calculate the correlation between the key attributes of the products it provides and the purchased goods. The correlation calculation method is:

[0029] In the formula, C represents the correlation between the purchasing supplier and the purchase demand goods, n represents the dimension of the feature vector, k represents the feature vector of the kth dimension, G represents the purchase demand goods, F represents the purchasing supplier, e represents the number of the eth purchase demand goods, h represents the number of the hth purchasing suppliers, represents the value of the e-th purchase demand item G in the k-th dimension, represents the value of the h-th purchasing supplier F on the k-th dimension; According to the calculated correlation results, the procurement suppliers with correlation in set one are screened out and aggregated into set two. The procurement suppliers in set two are sorted according to the size of the correlation, and the results are output to the procurement supplier evaluation module.

[0030] The risk assessment module of the procurement supplier assessment module provides the following risk assessment points: Based on the collection of related suppliers provided by the supplier information acquisition and analysis module, the evaluation module will evaluate each supplier in the collection in two aspects: one is the risk assessment of the supplier itself, and the other is the risk-bearing capacity assessment of downstream companies. In the self-risk assessment, the assessment module will comprehensively consider the basic data of the procurement supplier, the operation status data, the location information of the procurement demand goods in the supplier company and the market share information. Through the cleaning, preprocessing and feature extraction of these data, the assessment module will use the corresponding assessment model to calculate the self-risk assessment score of each procurement supplier; In the downstream company risk-bearing capacity assessment, the assessment module will focus on the basic information, operating conditions, cooperation history and scale of cooperation with the procurement supplier's downstream companies. Similarly, through the cleaning, preprocessing and feature extraction of these data, the assessment module will use the corresponding assessment model to calculate the downstream company risk-bearing capacity assessment score of each procurement supplier; Based on the risk assessment results of the procurement suppliers themselves and the risk-bearing capacity assessment results of the downstream companies, the evaluation module will re-rank the procurement suppliers. The ranking is based on the comprehensive consideration of these two evaluation scores, so as to select the procurement supplier with the best comprehensive evaluation. The evaluation module will output the results of the comprehensive evaluation, which includes the comprehensive evaluation score and ranking of each procurement supplier, providing strong support for subsequent procurement decisions.

[0031] The method for risk assessment of procurement suppliers is: Based on the procurement supplier information acquisition and analysis module, we conduct a comprehensive risk assessment of procurement suppliers and obtain basic data of procurement suppliers from multiple data sources. These data cover the registered capital, years of establishment and credit records of suppliers, providing us with the basic background and reputation of suppliers. We then obtain the operating status data of suppliers, including annual sales, profit margins and debt-to-asset ratios. These data can reflect the profitability and operational stability of suppliers. At the same time, we will also pay attention to the positioning information of procurement demand goods in supplier companies. This information helps to understand the importance and production capacity of suppliers for specific products. In addition, we also collect market share information of procurement demand goods in supplier companies, including market share, market growth rate and competitive situation. These data can reveal the competitive position and development trend of suppliers in the market. After obtaining these data, we will clean and pre-process the data to ensure the accuracy and consistency of the data. Next, we will extract key information reflecting the supplier's financial status, market position and product quality characteristics from the cleaned data. This information will serve as an important basis for assessing supplier risks. In order to more scientifically assess the risks of suppliers, the Delphi expert method is used to calculate the weights of the extracted features that affect the risk assessment of procurement suppliers. The Delphi expert method is a method of predicting and making decisions based on expert opinions. It can help us more accurately determine the importance of each feature in risk assessment. Finally, a procurement supplier risk assessment model will be established, and the extracted feature data that affects the risk assessment of procurement suppliers will be input into the assessment model. Through the calculation and analysis of the model, the supplier will be risk assessed and a risk assessment score will be obtained. This score will serve as an important reference for us to select procurement suppliers and help us better identify and manage potential risks. Among them, the expression of the procurement supplier risk assessment model is:

[0032] In the formula, represents the total number of features, Indicates features, w represents weight, x represents feature, Indicates The weight of the feature, Indicates The normalized value of each feature.

[0033] The method for assessing the risk-bearing capacity of downstream companies is: Based on the procurement supplier information acquisition and analysis module, basic information of downstream companies of procurement suppliers is obtained, and the basic information includes: registered capital, years of establishment and credit records; Acquire the operating status data of downstream companies of the purchasing supplier based on the purchasing supplier information acquisition and analysis module, wherein the operating status data includes: annual sales, profit margin and cash flow status; Based on the procurement supplier information acquisition and analysis module, the cooperation history and scale information between downstream companies and procurement suppliers are obtained; Clean and preprocess the data; Extract features reflecting the risk-bearing capacity of downstream companies that purchase suppliers from the cleaned data; The weights of the extracted features that affect the risk-bearing capacity assessment of downstream companies are calculated through the Delphi expert method; Establish a risk-bearing capacity assessment model for downstream companies; Based on the downstream company risk bearing capacity assessment model, the extracted characteristic data affecting the downstream company risk bearing capacity assessment is input into the assessment model, the risk bearing capacity of the downstream company is assessed, and the risk bearing capacity assessment score is calculated; The risk-bearing capacity assessment method for downstream companies relies on the procurement supplier information acquisition and analysis module to collect basic information and operating status data of downstream companies for analysis; Among them, the expression of the downstream company risk bearing capacity assessment model is:

[0034] In the formula, represents the total number of features used by downstream companies to assess their risk-taking capacity, Indicates The feature that reflects the risk-bearing capacity of the downstream company is represented by u, which represents the feature weight that reflects the risk-bearing capacity of the downstream company, and v represents the standardized value of the feature that reflects the risk-bearing capacity of the downstream company.

[0035] The use process of the present invention is: The inventory information monitoring module records the real-time entry and exit of the existing goods in the warehouse, and monitors the inventory quantity, entry and exit records and inventory turnover rate information; The product demand analysis module analyzes product demand based on the data provided by the inventory information monitoring module and external big data information, cleans and standardizes the collected data, extracts feature data, establishes a product purchase demand forecasting model, and outputs purchase demand indicators based on the model; The procurement supplier information acquisition and analysis module obtains the basic information of each procurement supplier from multiple data sources, cleans and standardizes the procurement supplier information, extracts feature vectors, and calculates the correlation with the feature vectors of the purchase demand goods output by the goods demand analysis module. Based on the correlation results, the procurement suppliers with correlation are screened out and sorted by the correlation size; The procurement supplier evaluation module conducts risk assessment on the selected procurement suppliers and the risk-bearing capacity of downstream companies, calculates the feature weights affecting the evaluation through the Delphi expert method, establishes an evaluation model, inputs feature data, outputs risk assessment scores, comprehensively evaluates the results, re-ranks the procurement suppliers, and selects the procurement supplier with the best comprehensive evaluation; The procurement plan generation module combines the purchasing needs output by the goods demand analysis module and the evaluation results of the procurement supplier evaluation module to generate a procurement plan and output the procurement plan for reference and decision-making by warehouse managers.

[0036] To sum up, the advantages of the present invention are: the system improves the efficiency and accuracy of inventory management, optimizes inventory management through real-time monitoring and accurate prediction, optimizes the procurement process, reduces procurement costs, comprehensively obtains and analyzes supplier information, scientifically matches and evaluates suppliers, enhances the intelligence and automation level of the system, makes quick and accurate decisions through big data analysis and machine learning technology, improves the risk management capabilities of enterprises, comprehensively evaluates supplier risks, establishes a stable and reliable supply chain system, and provides the financial services industry with a more efficient, accurate and secure warehouse management solution.

[0037] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A financial services big data warehouse management system, characterized in that: The warehouse management system includes: Inventory information monitoring module, which is used to record the entry and exit of existing goods in the warehouse; A product demand analysis module, which is electrically connected to the inventory information monitoring module, and is used to analyze product demand based on inventory information and combined with big data information, and output purchase demand; A procurement supplier information acquisition and analysis module, which is electrically connected to the product demand analysis module, and is used to acquire basic information of each procurement supplier, and analyze and calculate the relevance of the acquired supplier basic information with the purchase demand products, and match the corresponding procurement supplier according to the calculated relevance result; A procurement supplier evaluation module, the procurement supplier evaluation module is electrically connected to the procurement supplier information acquisition and analysis module, and the procurement supplier evaluation module is used to perform a comprehensive evaluation on the procurement supplier based on the correlation calculation result and output the evaluation result; A procurement plan generation module is electrically connected to the product demand analysis module and the procurement supplier evaluation module. The procurement plan generation module is used to combine the procurement demand and the evaluation results of the procurement supplier evaluation module to output a procurement plan.

2. A financial service big data warehouse management system according to claim 1, characterized in that: The product demand analysis module outputs the purchasing demand, including: Based on the inventory information monitoring module, obtain the inventory quantity, in and out records and inventory turnover rate information of warehouse goods; Collect external big data information related to product demand, including: historical sales data of the same category, seasonal sales trends, market trends, consumer behavior data and competitor information; Clean the collected data, remove duplicate, erroneous and invalid data, and standardize the processed data; Extracting characteristic data related to product demand from the cleaned existing inventory information and big data information, wherein the extracted characteristic data related to product demand includes inventory volume, sales growth rate, seasonal fluctuation and market growth rate; Establish a forecasting model for goods purchase demand; Based on the product purchase demand forecasting model, several characteristic data related to the product purchase demand are used as the influencing conditions, the inventory information is used as the input, and the corresponding future product purchase demand at the forecast time node is used as the output; Based on the forecast results, combined with the safety stock and reorder point of the inventory strategy, the purchasing demand index is calculated and output.

3. A financial service big data warehouse management system according to claim 2, characterized in that: The commodity purchase demand forecasting model is expressed as: ； In the formula, Y represents the demand for goods, t represents the corresponding time node, and p is the autoregressive order, that is, the number of time points involved when the values ​​of several past time points are used in the model to predict the current value. and are model parameters, represents the error term, q represents the moving average order, that is, the number of time points involved when the prediction errors of several past time points used in the model affect the current prediction value. represents the demand for goods at time t.

4. A financial service big data warehouse management system according to claim 2, characterized in that: The calculation method of safety stock and reorder point is: The calculation formula for safety stock is: ； In the formula, S represents the safety stock, Z represents the Z value of the standard normal distribution corresponding to the percentage of order fulfillment rate, represents the demand standard deviation, L represents the lead time, represents the replenishment cycle, represents the standard deviation of the lead time, and d represents the average daily demand; The calculation formula for the reorder point is: ； Where R represents the reorder point.

5. A financial service big data warehouse management system according to claim 1, characterized in that: The procurement supplier information acquisition and analysis module acquires the basic information of procurement suppliers and calculates the relevance, including: The procurement supplier information acquisition and analysis module acquires basic information of each procurement supplier from several data sources, wherein the basic information of the procurement supplier includes financial information, production information, warehousing information, logistics information and operation information, and aggregates the acquired procurement suppliers into a set by name; Based on the purchasing suppliers in set 1, their basic information is cleaned, the cleaned information is standardized, and the feature vectors related to the goods in the purchasing supplier information are extracted; Extract the feature vector of the goods according to the purchase demand output by the goods demand analysis module; For each supplier, calculate the correlation between the key attributes of the products it provides and the purchased goods. The correlation calculation method is: ； In the formula, C represents the correlation between the purchasing supplier and the purchase demand goods, n represents the total number of feature vectors, k represents the kth feature vector, G represents the purchase demand goods, F represents the purchasing supplier, e represents the number of the eth purchase demand goods, h represents the number of the hth purchasing suppliers, represents the value of the e-th purchase demand item G on the k-th feature vector, represents the value of the h-th purchasing supplier F on the k-th feature vector; According to the calculated correlation results, the procurement suppliers with correlation in set one are screened out and aggregated into set two. The procurement suppliers in set two are sorted according to the size of the correlation, and the results are output to the procurement supplier evaluation module.

6. A financial service big data warehouse management system according to claim 1, characterized in that: The risk assessment module of the procurement supplier assessment module provides the following risk assessment points: A second summary set of relevant procurement suppliers selected based on the procurement supplier information acquisition and analysis module; Conduct risk assessments on several procurement suppliers in Set 2 and risk-bearing capacity assessments on downstream companies; Based on the risk assessment results of the procurement suppliers themselves and the risk-bearing capacity assessment results of the downstream companies, the procurement suppliers are re-ranked, the procurement supplier with the best comprehensive assessment is selected, and the results of the comprehensive assessment are output.

7. A financial services big data warehouse management system according to claim 6, characterized in that: The method for risk assessment of procurement suppliers is: Acquire basic data of procurement suppliers based on the procurement supplier information acquisition and analysis module, wherein the basic information includes: registered capital, years of establishment and credit record; Acquire the procurement supplier operation status data based on the procurement supplier information acquisition and analysis module, wherein the operation status data includes: annual sales, profit margin and debt-to-asset ratio; Based on the procurement supplier information acquisition and analysis module, the location information of the procurement demand goods in the supplier company is obtained, and the location information includes: whether it is a core product, production scale and technical capabilities; Based on the procurement supplier information acquisition and analysis module, the market share information of the procurement demand goods in the supplier company is obtained, and the market share information includes: market share, market growth rate and competition situation; Clean and preprocess the data; Extract several characteristics reflecting the supplier's financial status, market position and product quality from the cleaned data; The Delphi expert method is used to calculate the weights of the extracted features that affect the risk assessment of procurement suppliers; Establish a procurement supplier risk assessment model; Based on the procurement supplier risk assessment model, a number of data reflecting the supplier's financial status, market position and product quality characteristics are extracted and input into the assessment model to conduct risk assessment on the supplier and calculate the risk assessment score; Among them, the expression of the procurement supplier risk assessment model is: ； In the formula, represents the total number of features, Indicates The weights of the factors that reflect the supplier's financial status, market position, and product quality characteristics are w, x, and the weights of the factors that reflect the supplier's financial status, market position, and product quality characteristics are x. Indicates weights that reflect the supplier's financial situation, market position, and product quality characteristics. Indicates A standardized value that reflects a supplier's financial condition, market position, and product quality characteristics.

8. A financial services big data warehouse management system according to claim 5, characterized in that: The method for assessing the risk-bearing capacity of downstream companies is: Based on the procurement supplier information acquisition and analysis module, basic information of downstream companies of procurement suppliers is obtained, and the basic information includes: registered capital, years of establishment and credit records; Acquire the operating status data of downstream companies of the purchasing supplier based on the purchasing supplier information acquisition and analysis module, wherein the operating status data includes: annual sales, profit margin and cash flow status; Based on the procurement supplier information acquisition and analysis module, the cooperation history and scale information between downstream companies and procurement suppliers are obtained; Clean and preprocess the data; Extract features reflecting the risk-bearing capacity of downstream companies that purchase suppliers from the cleaned data; The weights of the extracted features that affect the risk-bearing capacity assessment of downstream companies are calculated through the Delphi expert method; Establish a risk-bearing capacity assessment model for downstream companies; Based on the downstream company risk bearing capacity assessment model, the extracted characteristic data affecting the downstream company risk bearing capacity assessment is input into the assessment model, the risk bearing capacity of the downstream company is assessed, and the risk bearing capacity assessment score is calculated; Among them, the expression of the downstream company risk bearing capacity assessment model is: ； In the formula, represents the total number of features used by downstream companies to assess their risk-taking capacity, Indicates The feature that reflects the risk-bearing capacity of the downstream company is represented by u, which represents the feature weight that reflects the risk-bearing capacity of the downstream company, and v represents the standardized value of the feature that reflects the risk-bearing capacity of the downstream company.

Images