Multi-source commodity price monitoring method based on big data

Abstract

The invention relates to the field of big data analysis, and discloses a multi-source commodity price monitoring method based on big data, and the method comprises the steps: firstly collecting the prices of similar commodities of all platforms, and carrying out the classification and statistics of the commodities; performing big data analysis through a control variable method to obtain price change curves of different platforms and the same commodity and price change curves of the same platform and different commodities; integrating data to obtain a commodity unified change trend curve; related events are collected, influence factor analysis is carried out, the influence of the related events on the commodity price is judged, and the influence value of the related events and the commodity price is obtained; obtaining a commodity price prediction fluctuation index; dividing a commodity normal fluctuation interval, and monitoring and regulating commodity prices in real time; the problems that no systematic commodity price supervision method exists in the prior art, the commodity price cannot be pre-estimated in advance, systematic analysis cannot be carried out on different platform commodities, and the commodity price interval cannot be controlled are solved.

Description

Technical Field

[0001] The present invention relates to the field of big data analysis, and in particular to a multi-source commodity price monitoring method based on big data. Background Art

[0002] With the increasing abundance of materials and the development of the market, the channels for people to purchase commodities are becoming more and more diversified, and the types of commodities are also becoming more and more multi-source. However, the trading prices of commodities in different channels may sometimes vary greatly, which creates a price difference for consumers and easily affects the stability of the market. Under the influence of policies and some events, the prices of some commodities are also prone to fluctuations, which will lead to people's blind consumption or a large amount of purchases at one time, but the commodities are not useful after the event, resulting in an oversupply of commodities.

[0003] The existing commodity monitoring is basically a summary of commodities after the fact, without the function of predicting commodity prices in advance, and without incorporating the comparison of commodity prices between different platforms. There is no relatively systematic commodity supervision method, nor an interval for predicting commodity price fluctuations, which easily leads to too high or too low commodity prices, affecting the market. Summary of the Invention

[0004] The present invention aims to provide a multi-source commodity price monitoring method based on big data to solve the problems in the prior art that there is no systematic commodity price supervision method, cannot predict commodity prices in advance, and cannot conduct systematic analysis of commodities on different platforms to control the commodity price range.

[0005] To achieve the above object, the present invention provides the following method: A multi-source commodity price monitoring method based on big data provided by the present invention is as follows: S1: Collect the prices of the same type of commodities on each platform and the control policies of related commodity prices, and classify and count the commodities according to the daily classification types. The same type of commodities includes multiple different kinds of commodities; S2: Use the method of controlling variables to perform big data analysis to obtain the price change curves of the same type of commodities on different platforms and the price change curves of different types of commodities on the same platform; S3: Integrate the data according to the price change curves of the same type of commodities on different platforms and the price change curves of different types of commodities on the same platform to obtain a unified commodity change trend curve; S4: Collect the relevant events at the inflection point time points in the unified commodity change trend curve, conduct an analysis of influencing factors, judge the influence intensity of the relevant events on commodity prices, and obtain the influence intensity value of the relevant events on commodity prices; S5: Collect the occurrence probabilities of the relevant events in real time through big data, and predict the commodity price fluctuations in real time based on the occurrence probabilities of the relevant events to obtain a commodity price prediction fluctuation index; S6: Divide the normal commodity fluctuation range based on the relevant events, the commodity price influence strength value, the commodity price prediction fluctuation index, and the control policy of the relevant commodity price, and monitor and control the commodity price in real time.

[0006] Preferably, the steps of collecting the prices of the same-kind commodities on each platform and the control policies of the relevant commodity prices, and classifying and counting the commodities according to the daily classification types, where the same-type commodities include multiple different kinds of commodities, include: collecting the historical commodity prices on each online platform and offline platform and the control policies of the relevant commodity prices; classifying and counting the commodities according to the daily classification types, that is, the needs and characteristics of consumers, including multiple types of commodities, and among the multiple types of commodities, the same type of commodity includes multiple different kinds of commodities.

[0007] Preferably, the steps of obtaining the price change curves of the same-kind commodities on different platforms and the price change curves of different kinds of commodities on the same platform through the control variable method for big data analysis include: classifying and counting the same-kind commodities on different platforms to establish the price change curves of the same-kind commodities on different platforms, and marking each data point on the price change curves of the same-kind commodities on different platforms as platform data points to obtain the same-kind commodity index and the average price of the corresponding same-kind commodity index; classifying and counting the different kinds of commodities on the same platform to establish the price change curves of different kinds of commodities on the same platform to obtain the different-kind commodity index and the average price of the corresponding different-kind commodity index.

[0008] Preferably, the steps of classifying and counting the same-kind commodities on different platforms to establish the price change curves of the same-kind commodities on different platforms: classify and count the same-kind commodities on one platform, conduct big data analysis, and calculate the average price of the same-kind commodities; use the commodities that exist on different platforms in the same-kind commodities as the same-kind commodity index, and calculate the average price of the same-kind commodities as the average price of the same-kind commodity index with the commodity type closest to the commodities that exist on different platforms; count the same-kind commodity index on different platforms and the average price of the corresponding same-kind commodity index for historical data classification and counting to establish the price change curves of the same-kind commodities on different platforms.

[0009] Preferably, the steps of classifying and counting different types of commodities on the same platform and establishing a price change curve of different types of commodities on the same platform include: classifying and counting different types of commodities of the same category on each platform, and extracting common characteristic elements for each category of commodities as the index of different types of commodities; calculating the average price of the same category of commodities for each category as the average price of the index of different types of commodities; statistically classifying historical data of the index of different types of commodities on the same platform and the corresponding average price of the index of different types of commodities, and establishing a price change curve of different types of commodities on the same platform.

[0010] Preferably, the steps of integrating data according to the price change curve of the same type of commodity on different platforms and the price change curve of different types of commodities on the same platform to obtain a unified change trend curve of commodities include: establishing a multi-dimensional platform-commodity change trend curve according to the price change curve of the same type of commodity on different platforms, and binding the price change curve of different types of commodities on the same platform corresponding to each platform data point on the price change curve of the same type of commodity on different platforms; and integrating data of the index of the same type of commodity and the corresponding average price of the index of the same type of commodity, as well as the index of different types of commodities and the corresponding average price of the index of different types of commodities in the multi-dimensional platform-commodity change trend curve to obtain the unified change trend curve of commodities.

[0011] Preferably, the steps of collecting relevant events at the inflection point time of the unified change trend curve of commodities, analyzing influencing factors, and judging the influence strength of the relevant events on commodity prices to obtain the influence strength value of the relevant events on commodity prices include: collecting relevant events at the inflection point time of the unified change trend curve of commodities; if the price difference between adjacent inflection points in the unified change trend curve of commodities is more than 30% of the original commodity price, then the part exceeding 30% is marked as the influence strength value of the relevant events on commodity prices; marking the relevant events with a price difference between adjacent inflection points in the unified change trend curve of commodities more than 30% of the original commodity price as major events affecting commodity prices; marking the relevant events with a price difference between adjacent inflection points in the unified change trend curve of commodities less than 30% of the original commodity price but more than 10% as minor events affecting commodity prices.

[0012] Preferably, the steps of collecting the occurrence probability of the relevant events in real time through big data and predicting the commodity price fluctuation in real time according to the occurrence probability of the relevant events to obtain the commodity price prediction fluctuation index include: collecting the occurrence probability of the relevant events in real time through big data, judging the occurrence probability of the relevant events, and obtaining the commodity price prediction fluctuation index; if the occurrence probability of the relevant events is within 50%, then the commodity price prediction fluctuation index = 20% × the influence degree value of the relevant events on the commodity price; if the occurrence probability of the relevant events is not within 50%, then the commodity price prediction fluctuation index = 80% × the influence degree value of the relevant events on the commodity price; obtaining the first weight coefficients of the information data of the commodity supply dimension, commodity demand dimension, commodity purchase price dimension, and commodity logistics price dimension, and the second weight coefficients of the information data of the public opinion dimension and policy dimension; training the commodity price prediction model according to the commodity price prediction fluctuation index to obtain the first weight sub - coefficients of the commodity supply dimension, commodity demand dimension, commodity purchase price dimension, and commodity logistics price dimension, and the second weight sub - coefficients of the information data of the public opinion dimension and policy dimension; inputting the current commodity price into the commodity price prediction model to obtain the predicted price of the commodity.

[0013] Preferably, the steps of dividing the normal fluctuation range of the commodity according to the relevant events, the influence degree value of the commodity price, the commodity price prediction fluctuation index, and the control policy of the relevant commodity price, and monitoring and regulating the commodity price in real time include: obtaining the highest price point and the lowest price point of the commodity fluctuation according to the control policy of the relevant commodity price; obtaining the first fluctuation range of the commodity price according to the relevant events, the influence degree value of the commodity price, and the commodity price prediction fluctuation index; calculating the historical average price of the commodity according to the unified change trend curve of the commodity; calculating the average price point of the commodity fluctuation through the highest price point and the lowest price point of the commodity fluctuation; marking the historical average price of the commodity and the average price point of the commodity fluctuation as the second fluctuation range of the commodity price; overlapping the first fluctuation range of the commodity price and the second fluctuation range of the commodity price to obtain the best interval for monitoring and regulating the commodity price.

[0014] Preferably, overlapping the first fluctuation range of the commodity price and the second fluctuation range of the commodity price, marking the overlapping area of the first fluctuation range of the commodity price and the second fluctuation range of the commodity price as the best interval for monitoring and regulating the commodity price; marking the non - overlapping area of the first fluctuation range of the commodity price and the second fluctuation range of the commodity price as the control fluctuation range of the commodity price.

[0015] The beneficial effects of the present invention are as follows: the present invention collects commodity price data from various platforms, and then establishes price change curves for the same commodity on different platforms and price change curves for different commodities on the same platform, performs joint data, and combines the advantages of big data to integrate data to obtain a unified commodity change trend curve, making the commodity data change more detailed, performing price comparisons on various platforms, preventing people from blindly consuming, and playing a great role in stabilizing the market. The present invention also takes into account the impact of historical events on commodity prices, and can predict future commodity price adjustments, thereby adjusting commodity output through commodity price predictions to prevent a situation of supply exceeding demand, stabilizing the commodity market, and buffering market pressure by adjusting prices. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the description of the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0017] Figure 1 It is a flow chart of a multi-source commodity price monitoring method based on big data provided by an embodiment of the present invention.

[0018] Figure 2 It is a flow chart of commodity price monitoring steps provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the technical personnel in the technical field better understand the scheme of the present invention, the technical scheme in the embodiment of the present invention will be clearly and completely described below in combination with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0020] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0021] References to "embodiments" in this specification mean that the specific features, structures, or characteristics described in connection with the embodiments can be included in at least one embodiment of the invention. The phrase appears in various places in the specification and does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0022] Existing commodity monitoring is basically a summary of commodities after the fact, without the function of predicting commodity prices in advance, and does not incorporate price comparisons of commodities between different platforms. There is no relatively systematic commodity supervision method, nor is there an interval for predicting price fluctuations of commodities, which can easily lead to excessively high or low commodity prices, thus affecting the market.

[0023] The present invention aims to provide a multi-source commodity price monitoring method based on big data to solve the problems in the prior art, such as the lack of a systematic commodity price supervision method, the inability to predict commodity prices in advance, and the lack of systematic analysis of commodities on different platforms to control the commodity price range.

[0024] The specific implementation manner of the present invention provides a multi-source commodity price monitoring method based on big data. This method is as Figure 1 and Figure 2 shown, and includes the following steps: S1: Collect the prices of similar commodities and the control policies of related commodity prices on each platform, and classify and count the commodities according to the daily classification types. The same type of commodities includes multiple different kinds of commodities.

[0025] In the embodiments of the present invention, collect the historical commodity prices and the control policies of related commodity prices on each online platform and offline platform; classify and count the commodities according to the daily classification types, that is, the needs and characteristics of consumers. It includes a variety of commodities. Among the various commodities, the same kind of commodities includes multiple different kinds of commodities. For example, classified by consumers' clothing, food, housing, use, and transportation, there are food categories, clothing categories, shoes and hats categories, daily necessities categories, furniture categories, household appliances categories, textile categories, hardware and electrical materials categories, kitchenware categories, etc.; classified by the needs level of consumers, there are basic living categories, enjoyment categories, and development categories, etc.; classified by consumers' purchase behavior, there are daily necessities categories, selected purchase categories, and special categories; classified by consumers' age and gender, there are elderly supplies categories, middle-aged supplies categories, youth supplies categories, children and baby supplies categories, women's supplies categories, men's supplies categories, etc.

[0026] S2: Use the method of controlling variables to perform big data analysis to obtain the price change curves of the same kind of commodities on different platforms and the price change curves of different kinds of commodities on the same platform.

[0027] In the embodiment of the present invention, the same kind of commodities on different platforms are classified and counted to establish a price change curve of the same kind of commodities on different platforms. Each data point on the price change curve of the same kind of commodities on different platforms is marked as a platform data point, and the average price of the same kind of commodity index and the corresponding same kind of commodity index is obtained; the different kinds of commodities on the same platform are classified and counted to establish a price change curve of different kinds of commodities on the same platform, and the different kinds of commodity index and the corresponding average price of the different kinds of commodity index are obtained; the steps of classifying and counting the same kind of commodities on different platforms to establish a price change curve of the same kind of commodities on different platforms are as follows: classify and count the same kind of commodities on one platform, perform big data analysis, and calculate the average price of the same kind of commodities; use the commodities that exist on different platforms in the same kind of commodities as the same kind of commodity index, and use the commodity type closest to the commodities that exist on different platforms to calculate the average price of the same kind of commodities as the average price of the same kind of commodity index; count the same kind of commodity index on different platforms and the corresponding average price of the same kind of commodity index for historical data classification and statistics to establish a price change curve of the same kind of commodities on different platforms; the steps of classifying and counting the different kinds of commodities on the same platform to establish a price change curve of different kinds of commodities on the same platform include: classify and count the different kinds of commodities of the same category on each platform, extract common characteristic elements for each category of commodities as the different kinds of commodity index; calculate the average price of the same category of commodities for each category as the average price of the different kinds of commodity index; count the different kinds of commodity index on the same platform and the corresponding average price of the different kinds of commodity index for historical data classification and statistics to establish a price change curve of different kinds of commodities on the same platform.

[0028] S3: Integrate the data according to the price change curve of the same kind of commodities on different platforms and the price change curve of different kinds of commodities on the same platform to obtain a unified commodity change trend curve.

[0029] In the embodiment of the present invention, a multi-dimensional platform-commodity change trend curve is established according to the price change curve of the same kind of commodities on different platforms. The price change curve of different kinds of commodities on the same platform corresponding to the corresponding platform is bound to each platform data point on the price change curve of the same kind of commodities on different platforms; and data integration is performed on the same kind of commodity index and the corresponding average price of the same kind of commodity index as well as the different kinds of commodity index and the corresponding average price of the different kinds of commodity index in the multi-dimensional platform-commodity change trend curve to obtain a unified commodity change trend curve.

[0030] S4: Collect relevant events at the inflection point time of the unified commodity change trend curve, perform influence factor analysis, judge the influence strength of the relevant events on the commodity price, and obtain the influence strength value of the relevant events on the commodity price.

[0031] In the embodiments of the present invention, relevant events at the inflection point time points in the unified change trend curve of commodities are collected; if the price gap between adjacent inflection points in the unified change trend curve of commodities is more than 30% of the original commodity price, then the part exceeding 30% is marked as the relevant event and the commodity price impact strength value; relevant events with the price gap between adjacent inflection points in the unified change trend curve of commodities being more than 30% of the original commodity price are marked as major events affecting commodity prices; relevant events with the price gap between adjacent inflection points in the unified change trend curve of commodities being less than 30% of the original commodity price but more than 10% are marked as minor events affecting commodity prices.

[0032] S5: Real-time collect the occurrence probability of relevant events through big data, and perform real-time prediction of commodity price fluctuations based on the occurrence probability of relevant events to obtain the commodity price prediction fluctuation index.

[0033] In the real-time examples of the present invention, the occurrence probability of relevant events is collected in real time through big data, the occurrence probability of relevant events is judged, and the commodity price prediction fluctuation index is obtained; if the occurrence probability of relevant events is within 50%, then the commodity price prediction fluctuation index = 20% × the relevant event and commodity price impact strength value; if the occurrence probability of relevant events is not within 50%, then the commodity price prediction fluctuation index = 80% × the relevant event and commodity price impact strength value; obtain the first weight coefficients of the information data of the commodity supply dimension, commodity demand dimension, commodity purchase price dimension, and commodity logistics price dimension, and the second weight coefficients of the information data of the public opinion dimension and policy dimension; train the commodity price prediction model according to the commodity price prediction fluctuation index to obtain the first weight sub-coefficients of the commodity supply dimension, commodity demand dimension, commodity purchase price dimension, and commodity logistics price dimension, and the second weight sub-coefficients of the information data of the public opinion dimension and policy dimension; input the current commodity price into the commodity price prediction model to obtain the predicted price of the commodity.

[0034] S6: Divide the normal fluctuation range of commodities according to relevant events, commodity price impact strength value, commodity price prediction fluctuation index, and control policies of relevant commodity prices, and perform real-time monitoring and regulation of commodity prices.

[0035] In an embodiment of the present invention, the highest price point and the lowest price point of commodity fluctuation are obtained according to the control policy of relevant commodity prices; the first fluctuation range of commodity prices is obtained according to relevant events, commodity price impact intensity values and commodity price forecast fluctuation index; the historical average commodity price is calculated according to the unified change trend curve of commodities; the fluctuation mean price point of commodities is calculated by the highest price point and the lowest price point of commodities; the historical average commodity price and the fluctuation mean price point of commodities are marked as the second fluctuation range of commodity prices; the first fluctuation range of commodity prices and the second fluctuation range of commodity prices are overlapped to obtain the best range for commodity price monitoring and regulation; the first fluctuation range of commodity prices and the second fluctuation range of commodity prices are overlapped to mark the area where the first fluctuation range of commodity prices and the second fluctuation range of commodity prices overlap as the best range for commodity price monitoring and regulation; the area where the first fluctuation range of commodity prices and the second fluctuation range of commodity prices do not overlap is marked as the commodity price control fluctuation range.

[0036] The beneficial effects of the present invention are as follows: the present invention collects commodity price data from various platforms, and then establishes price change curves for the same commodity on different platforms and price change curves for different commodities on the same platform, performs joint data, and combines the advantages of big data to integrate data to obtain a unified commodity change trend curve, making the commodity data change more detailed, performing price comparisons on various platforms, preventing people from blindly consuming, and playing a great role in stabilizing the market. The present invention also takes into account the impact of historical events on commodity prices, and can predict future commodity price adjustments, thereby adjusting commodity output through commodity price predictions to prevent a situation of supply exceeding demand, stabilizing the commodity market, and buffering market pressure by adjusting prices.

[0037] The above is only an embodiment of the present invention, and the common knowledge such as the known specific technical schemes or characteristics in the scheme is not described in detail here; it should be pointed out that for those skilled in the art, several modifications and improvements can be made without departing from the scheme of the present invention, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A multi-source commodity price monitoring method based on big data, characterized in that, The method includes: S1: Collect the prices of similar products and the control policies of related product prices on each platform, classify and count the products according to the daily classification types, and the same type of products includes multiple different kinds of products; S2: Obtain the price change curves of the same kind of products on different platforms and the price change curves of different kinds of products on the same platform through data analysis of big data by the method of controlling variables; S3: Integrate the data according to the price change curves of the same kind of products on different platforms and the price change curves of different kinds of products on the same platform to obtain a unified product change trend curve; S4: Collect the relevant events at the inflection time points in the unified product change trend curve, conduct an analysis of influencing factors, judge the influence intensity of the relevant events on the product price, and obtain the influence intensity value of the relevant events on the product price; S5: Collect the occurrence probabilities of the relevant events in real time through big data, and conduct real-time prediction of product price fluctuations according to the occurrence probabilities of the relevant events to obtain a product price prediction fluctuation index; S6: Divide the normal fluctuation range of the product according to the relevant events, the influence intensity value of the product price, the product price prediction fluctuation index, and the control policies of the relevant product prices, and conduct real-time monitoring and regulation of the product price.

2. The multi-source commodity price monitoring method based on big data according to claim 1, wherein, The step of collecting the prices of similar products and the control policies of related product prices on each platform, classifying and counting the products according to the daily classification types, and the same type of products includes multiple different kinds of products includes: Collect the historical product prices and the control policies of related product prices on each online platform and offline platform; Classify and count the products according to the daily classification types, i.e., the needs and characteristics of consumers. The products include multiple categories. Among the multiple categories of products, the same category of products includes multiple different kinds of products.

3. The multi-source commodity price monitoring method based on big data according to claim 2, wherein, The step of obtaining the price change curves of the same kind of products on different platforms and the price change curves of different kinds of products on the same platform through data analysis of big data by the method of controlling variables includes: Classify and count the same kind of products on different platforms, establish a price change curve of the same kind of products on different platforms, mark each data point on the price change curve of the same kind of products on different platforms as a platform data point, and obtain the same kind of product index and the average price of the corresponding same kind of product index; Classify and count the different kinds of products on the same platform, establish a price change curve of different kinds of products on the same platform, and obtain the different kind of product index and the average price of the corresponding different kind of product index.

4. A method for monitoring multi-source commodity prices based on big data according to claim 3, characterized in that, The step of classifying and counting the same kind of products on different platforms and establishing a price change curve of the same kind of products on different platforms: Classify and count the same kind of products on one platform, conduct data analysis of big data, and calculate the average price of the same kind of products; Use the products that are the same among different platforms in the same kind of products as the same kind of product index, and use the product category closest to the products that are the same among different platforms to calculate the average price of the same kind of products as the average price of the same kind of product index; Statistically classify and count historical data by the index of the same kind of commodity on different platforms and the average price of the corresponding index of the same kind of commodity, and establish a price change curve for the same kind of commodity on different platforms.

5. A method for monitoring multi-source commodity prices based on big data according to claim 3, characterized in that, The steps of classifying and counting different kinds of commodities on the same platform and establishing a price change curve for different kinds of commodities on the same platform include: Classify and count different kinds of commodities of the same category on each platform, and extract common characteristic elements for each category of commodities as the index of different kinds of commodities; Calculate the average price of the same kind of commodities for each category as the average price of the index of different kinds of commodities; Statistically classify and count the index of different kinds of commodities on the same platform and the average price of the corresponding index of different kinds of commodities, and establish a price change curve for different kinds of commodities on the same platform.

6. The multi-source commodity price monitoring method based on big data according to claim 3, characterized in that, The steps of integrating data according to the price change curve of the same kind of commodity on different platforms and the price change curve of different kinds of commodities on the same platform to obtain a unified change trend curve of the commodity include: Establish a multi-dimensional platform-commodity change trend curve according to the price change curve of the same kind of commodity on different platforms, and bind the price change curve of different kinds of commodities on the same platform corresponding to each platform data point on the price change curve of the same kind of commodity on different platforms; And integrate the index of the same kind of commodity and the average price of the corresponding index of the same kind of commodity, as well as the index of different kinds of commodities and the average price of the corresponding index of different kinds of commodities in the multi-dimensional platform-commodity change trend curve to obtain the unified change trend curve of the commodity.

7. A multi-source commodity price monitoring method based on big data according to claim 1, characterized in that, The steps of collecting relevant events at the inflection point time point in the unified change trend curve of the commodity, analyzing influencing factors, and judging the influence intensity of the relevant events on the commodity price to obtain the influence intensity value of the relevant events and the commodity price include: Collect relevant events at the inflection point time point in the unified change trend curve of the commodity; If the price gap between adjacent inflection points in the unified change trend curve of the commodity is more than 30% of the original commodity price, then the part exceeding 30% is marked as the influence intensity value of the relevant event and the commodity price; Mark the relevant events with a price gap between adjacent inflection points in the unified change trend curve of the commodity more than 30% of the original commodity price as major events affecting the commodity price; Mark the relevant events with a price gap between adjacent inflection points in the unified change trend curve of the commodity less than 30% of the original commodity price but more than 10% as minor events affecting the commodity price.

8. A method for monitoring multi-source commodity prices based on big data according to claim 7, characterized in that The steps of collecting the occurrence probability of the relevant events in real time through big data and predicting the commodity price fluctuation in real time according to the occurrence probability of the relevant events to obtain the predicted fluctuation index of the commodity price include: Collect the occurrence probability of the relevant events in real time through big data, judge the occurrence probability of the relevant events, and obtain the predicted fluctuation index of the commodity price; If the occurrence probability of the relevant event is within 50%, then the predicted fluctuation index of the commodity price = 20% × the influence intensity value of the relevant event and the commodity price; If the occurrence probability of the relevant event is not within 50%, the commodity price prediction fluctuation index = 80% × the influence strength value of the relevant event on the commodity price; Obtain the first weight coefficient of the information data of the commodity supply dimension, commodity demand dimension, commodity purchase price dimension, and commodity logistics price dimension, and the second weight coefficient of the information data of the public opinion dimension and policy dimension; Train the commodity price prediction model according to the commodity price prediction fluctuation index to obtain the first weight sub-coefficient of the commodity supply dimension, commodity demand dimension, commodity purchase price dimension, and commodity logistics price dimension, and the second weight sub-coefficient of the information data of the public opinion dimension and policy dimension; Input the current commodity price into the commodity price prediction model to obtain the predicted price of the commodity.

9. A method for monitoring multi-source commodity prices based on big data according to claim 8, characterized in that, The step of dividing the normal fluctuation range of the commodity and performing real-time monitoring and control on the commodity price according to the relevant event, the influence strength value of the commodity price, the commodity price prediction fluctuation index, and the control policy of the relevant commodity price includes: Obtain the highest price point and the lowest price point of the commodity fluctuation according to the control policy of the relevant commodity price; Obtain the first price fluctuation range of the commodity according to the relevant event, the influence strength value of the commodity price, and the commodity price prediction fluctuation index; Calculate the historical average price of the commodity according to the unified change trend curve of the commodity; Calculate the average price point of the commodity fluctuation through the highest price point and the lowest price point of the commodity fluctuation; Mark the historical average price of the commodity and the average price point of the commodity fluctuation as the second price fluctuation range of the commodity; Overlap the first price fluctuation range of the commodity and the second price fluctuation range of the commodity to obtain the best range for monitoring and controlling the commodity price.

10. A multi-source commodity price monitoring method based on big data according to claim 9, characterized in that: Overlap the first price fluctuation range of the commodity and the second price fluctuation range of the commodity, and mark the overlapping area of the first price fluctuation range of the commodity and the second price fluctuation range of the commodity as the best range for monitoring and controlling the commodity price; Mark the non-overlapping area of the first price fluctuation range of the commodity and the second price fluctuation range of the commodity as the control fluctuation range of the commodity price.

Images