Search

CN-122023008-A - Intelligent period-present fusion automatic purchasing system and method

CN122023008ACN 122023008 ACN122023008 ACN 122023008ACN-122023008-A

Abstract

The invention relates to an intelligent period present fusion automatic purchasing system and method, wherein the method comprises the steps of collecting real-time market quotation data and spot market quotation data of a futures market according to collection frequency, preprocessing the collected data, calculating key indexes by a period present analysis module, judging market states, identifying whether a arbitrage opportunity or price abnormal fluctuation occurs, marking the arbitrage opportunity as the period present price difference rate stock-frying threshold alpha, generating purchasing strategies by an intelligent decision engine according to the market states and enterprise requirements, carrying out risk inspection on the generated purchasing strategies by a risk control module, executing purchasing instructions after all risk inspection passes, monitoring order states in real time, and finally storing complete records of the purchasing. The invention realizes real-time synchronization and centralized display of futures and spot market data, and purchasing personnel can acquire comprehensive market information on a single interface, so that the information acquisition efficiency is improved by more than 80%, and decision errors caused by information lag are effectively avoided.

Inventors

  • Yao Aijia
  • CAO PENG

Assignees

  • 普杉科技发展(四川)有限公司

Dates

Publication Date
20260512
Application Date
20260316

Claims (7)

  1. 1. The intelligent period present fusion automatic purchasing system is characterized by comprising a data acquisition module, a data definition module, a period present analysis module, an intelligent decision engine, a risk control module and an automatic transaction module; the data acquisition module is configured to acquire market data of a futures exchange, a spot exchange platform and an industry information website in real time; The data definition module is configured to perform outlier detection, missing value filling and data standardization processing on the collected original data; the period present analysis module is configured to analyze the price trend of futures, the current price trend of the futures, the period present price difference and the change of the base difference in real time by adopting a time sequence analysis algorithm and a statistical model to generate a market trend prediction report; The intelligent decision engine is configured to automatically generate purchasing suggestions based on a multi-factor quantization model and a machine learning algorithm by comprehensively considering price factors, inventory factors, fund factors and risk factors; The risk control module is configured to set a multi-level risk threshold, and automatically pauses the transaction or sends alarm information when the risk early warning is triggered; the automatic trading module is configured to automatically send trading instructions to futures brokers or spot suppliers through a trading interface according to instructions of the intelligent decision engine and track order execution states in real time.
  2. 2. The intelligent phase-out fusion automatic purchasing system of claim 1, further comprising a data storage module configured to store historical transaction data, market data, and decision records using a distributed database.
  3. 3. The intelligent phase-current fusion automatic purchasing system of claim 1, wherein the intelligent decision engine automatically generates purchasing advice comprises: a1, calculating futures purchase cost C_futures and spot purchase cost C_spot; A2, calculating a phase present price difference dominance index K= (C_present-C_future)/C_present multiplied by 100%; A3, if K is greater than or equal to beta, preferentially selecting futures purchase, if K is greater than or equal to beta, preferentially selecting spot purchase, and if-beta is less than or equal to K is less than or equal to beta, adopting a mixed purchase strategy, wherein beta is a threshold value; A4, calculating a purchase quantity Q=max (S-I+D, 0) according to the enterprise library level I and the safety stock S, wherein D is a predicted demand quantity of 30 days in the future; a5, calculating a set protection ratio H=min (lambda multiplied by sigma/0.15,1.0) according to the price fluctuation ratio sigma and the risk preference coefficient lambda, wherein lambda is the risk preference coefficient.
  4. 4. The intelligent phase-out fusion automatic purchasing system of claim 1, wherein said risk control module performs risk verification on the generated purchasing strategy comprising: b1, whether the single transaction amount exceeds a preset upper limit L1; b2, whether the accumulated transaction amount exceeds the daily allowance L2 or not in the same day; b3, judging whether the proportion of the purchased warehouse to be kept exceeds the maximum warehouse-keeping proportion R_max; b4, whether the current market fluctuation rate exceeds an abnormal fluctuation threshold sigma_max; b5, whether the available funds meet the requirements of the guarantee funds.
  5. 5. The method for intelligent phase-based fusion automatic purchasing system according to any one of claims 1-4, wherein the method comprises the steps of: S1, acquiring real-time market quotation data and spot market quotation data of a futures market according to acquisition frequency, and preprocessing the acquired data; S2, calculating key indexes by the period present analysis module, judging the market state, identifying whether a arbitrage opportunity or abnormal price fluctuation occurs, and marking the value as the arbitrage opportunity if the period present price difference rate is equal to the stock-frying threshold alpha; S3, the intelligent decision engine generates a purchasing strategy according to the market state and the enterprise demand, and performs risk inspection on the generated purchasing strategy through the risk control module; And S4, executing a purchasing instruction after all risk checks pass, monitoring the order state in real time, and finally storing the complete record of the purchasing.
  6. 6. The method of an intelligent phase present fusion-based automatic purchasing system as recited in claim 5, wherein the intelligent decision engine generating purchasing strategies according to market conditions and enterprise requirements comprises: a1, calculating futures purchase cost C_futures and spot purchase cost C_spot; A2, calculating a phase present price difference dominance index K= (C_present-C_future)/C_present multiplied by 100%; A3, if K is greater than or equal to beta, preferentially selecting futures purchase, if K is greater than or equal to beta, preferentially selecting spot purchase, and if-beta is less than or equal to K is less than or equal to beta, adopting a mixed purchase strategy, wherein beta is a threshold value; A4, calculating a purchase quantity Q=max (S-I+D, 0) according to the enterprise library level I and the safety stock S, wherein D is a predicted demand quantity of 30 days in the future; a5, calculating a set protection ratio H=min (lambda multiplied by sigma/0.15,1.0) according to the price fluctuation ratio sigma and the risk preference coefficient lambda, wherein lambda is the risk preference coefficient.
  7. 7. The method of claim 5, wherein the risk checking the generated purchase strategy by the risk control module comprises: b1, whether the single transaction amount exceeds a preset upper limit L1; b2, whether the accumulated transaction amount exceeds the daily allowance L2 or not in the same day; b3, judging whether the proportion of the purchased warehouse to be kept exceeds the maximum warehouse-keeping proportion R_max; b4, whether the current market fluctuation rate exceeds an abnormal fluctuation threshold sigma_max; b5, whether the available funds meet the requirements of the guarantee funds.

Description

Intelligent period-present fusion automatic purchasing system and method Technical Field The invention relates to the field of data processing, in particular to an intelligent period and current fusion automatic purchasing system and method. Background With the rapid development of mass commodity markets, enterprises face increasingly complex market environments in raw material purchasing processes. The futures market and the spot market are taken as two markets which are related with each other but have different operation mechanisms, and a diversified purchasing channel is provided for enterprises. The futures market has the functions of price discovery and risk hedging, and the spot market can meet the actual material demands of enterprises. Traditional purchasing modes generally separate futures trading and spot purchasing, are independently operated by different business departments, and lack an effective cooperative mechanism. In recent years, with the development of financial technology, some enterprises begin to try to build a purchase management system to assist in purchase decision. However, the existing purchasing system is mainly concentrated in the traditional fields of order management, supplier management and the like, has weak fusion processing capacity for futures market and spot market, and is difficult to realize intelligent purchasing decision and automatic transaction execution. Therefore, the prior art has the defects that 1, futures and spot market data are scattered, a unified data acquisition and integration platform is lacking, purchasing personnel need to switch among a plurality of systems to view information, the information acquisition efficiency is low, and key market signals are easy to miss. 2. The purchasing decision depends on manual experience judgment, lacks a scientific quantitative analysis tool, is difficult to quickly make an optimal decision when facing complex market fluctuation, and has larger decision delay and subjective deviation. 3. The lack of a linkage mechanism between the future stock cover period guarantee value and the spot stock purchase can not automatically adjust the purchase strategy according to market signals such as period current price difference, base difference change and the like, so that the cover guarantee effect is poor or the purchase cost is higher. 4. The purchasing execution process needs manual ordering operation, when the price rapidly fluctuates, the optimal trading opportunity is easily missed, and the manual operation has error risks, so that economic loss can be caused. 5. The price risk, the fund risk and the operation risk in the purchasing process cannot be monitored in real time due to the lack of an effective risk control mechanism, and timely damage stopping is difficult once an abnormal situation occurs. 6. The purchasing data is stored in a scattered manner, the historical transaction data is difficult to effectively use, the purchasing strategy cannot be continuously optimized through the data mining and machine learning technology, and the data asset is wasted. Disclosure of Invention The invention aims to overcome the defects of the prior art, provides an intelligent period-present fusion automatic purchasing system and method, and solves the defects in the prior art. The intelligent period-present fusion automatic purchasing system comprises a data acquisition module, a data definition module, a period-present analysis module, an intelligent decision engine, a risk control module and an automatic transaction module; the data acquisition module is configured to acquire market data of a futures exchange, a spot exchange platform and an industry information website in real time; The data definition module is configured to perform outlier detection, missing value filling and data standardization processing on the collected original data; the period present analysis module is configured to analyze the price trend of futures, the current price trend of the futures, the period present price difference and the change of the base difference in real time by adopting a time sequence analysis algorithm and a statistical model to generate a market trend prediction report; The intelligent decision engine is configured to automatically generate purchasing suggestions based on a multi-factor quantization model and a machine learning algorithm by comprehensively considering price factors, inventory factors, fund factors and risk factors; The risk control module is configured to set a multi-level risk threshold, and automatically pauses the transaction or sends alarm information when the risk early warning is triggered; the automatic trading module is configured to automatically send trading instructions to futures brokers or spot suppliers through a trading interface according to instructions of the intelligent decision engine and track order execution states in real time. The system also includes a data storage module configured to s