A big data-based commodity operation strategy supervision method and system

Abstract

The application relates to the technical field of commodity operation, in particular to a commodity operation strategy supervision method and system based on big data, which comprises the following steps: collecting historical commodity supply information and historical commodity price data in a historical period and operation change information of commodities in a future preset time period, constructing a correlation curve of the historical commodity supply information and the historical commodity price data, obtaining a commodity price dynamic curve of each commodity in the historical period, determining an event time node and price fluctuation data of a price change event according to the commodity price dynamic curve, searching the historical commodity supply information according to the event time node, obtaining commodity change information, and performing management prediction analysis on the price fluctuation data and the commodity change information based on the operation change information, so as to obtain future commodity sales and future commodity pricing in the future time period. The application improves the timeliness and accuracy of commodity operation strategy supervision.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of commodity operation, in particular to a commodity operation strategy supervision method and system based on big data. BACKGROUND

[0002] In the field of commodity operation and sales management, accurately predicting future commodity sales and reasonably formulating commodity pricing strategies are key links for enterprises to improve market competitiveness and maximize profits.

[0003] At present, there is a lack of effective integration and utilization of change information in the commodity operation process. In the commodity operation process, various change events such as promotion activities, product upgrades and channel adjustments will occur. These operation change information will directly or indirectly affect the price and sales of commodities. For example, a large-scale promotion activity will lead to a decrease in commodity price, and sales will increase in the short term; product upgrading will improve the quality and brand image of the commodity, allowing the enterprise to increase the price and drive sales growth. However, traditional prediction methods fail to incorporate these operation change information into the analysis system, and cannot timely reflect the dynamic influence of these factors on commodity price and sales, making the prediction results difficult to adapt to the rapid changes in the market, reducing the timeliness and accuracy of commodity operation strategy supervision. SUMMARY

[0004] In order to solve at least one of the above technical problems, the application provides a commodity operation strategy supervision method and system based on big data.

[0005] In a first aspect, the application provides a commodity operation strategy supervision method based on big data, which adopts the following technical solution:

[0006] Collecting historical commodity supply information and historical commodity price data in a historical period and operation change information of commodities in a future preset time period;

[0007] Correlating curve construction is performed on the historical commodity supply information and the historical commodity price data to obtain a commodity price dynamic curve of each commodity in the historical period;

[0008] According to the commodity price dynamic curve, an event time node of a price change event and price fluctuation data are determined;

[0009] According to the event time node, the historical commodity supply information is searched to obtain commodity change information;

[0010] Based on the operation change information, management and prediction analysis are performed on the price fluctuation data and the commodity change information to obtain future commodity sales and future commodity pricing in a future time period.

[0011] By adopting the technical scheme, the rich historical commodity supply information, historical commodity price data and operation change information of the commodity in the future preset time period in the historical period are collected. The historical commodity supply information and price data are the basis, record the supply situation and price fluctuation of the commodity in different stages, and provide original materials for subsequent analysis. The operation change information reflects the factors that affect the commodity in the future. Then, the historical commodity supply information and price data are associated to construct a curve, and a commodity price dynamic curve is obtained. The trend of the commodity price change with the supply change is intuitively presented, and the price change is clearly understood, which lays a foundation for accurately grasping the commodity price trend. After obtaining the commodity price dynamic curve, the event time node and the price fluctuation data of the price change event are determined according to the curve. By analyzing the ups and downs of the curve, the specific time point of the price change, i.e. the event time node, can be accurately positioned. At the same time, the amplitude of the price change, i.e. the price fluctuation data, is determined. These key information is an important basis for understanding the commodity price fluctuation. Only by accurately obtaining these data, the reasons and influences of the price change can be further explored, and a clear direction for subsequent search of commodity supply information is provided. According to the determined event time node, the historical commodity supply information is searched, and commodity change information is obtained. The event time node is like a precise locator, which determines that the commodity price has changed at a specific time. The historical commodity supply information is searched as a clue, and the related change of the commodity supply at the time point, such as the increase or decrease of the supply amount and the change of the supply channel, can be quickly found, which is the commodity change information. The commodity change information is closely related to the price change. By obtaining these information, the internal relationship between the commodity supply and the price can be deeply analyzed, and key data support is provided for subsequent management and prediction analysis based on the operation change information. Based on the operation change information, the price fluctuation data and the commodity change information are managed and predicted, and the future commodity sales and future commodity pricing in the future time period are obtained. The operation change information reflects various factors that may affect the commodity in the future, such as market strategy adjustment. Combined with the price fluctuation data and the commodity change information obtained before, these data cover the past price and supply change of the commodity. The multi-dimensional data are comprehensively managed and predicted, which can more comprehensively and accurately predict the performance of the commodity in the market in the future. Not only the future commodity sales can be accurately estimated, but also the future commodity pricing can be reasonably determined, which provides a scientific basis for the business decision-making of the enterprise in the future market, and improves the timeliness and accuracy of the commodity operation strategy supervision.

[0012] In a possible implementation manner, the associating the historical commodity supply information and the historical commodity price data to construct a curve to obtain a commodity price dynamic curve of each commodity in the historical period comprises:

[0013] create historical commodity dynamic coordinates, an X axis of the historical commodity dynamic coordinates is different time nodes, and a Y axis of the historical commodity dynamic coordinates is price data of different specifications;

[0014] respectively associate commodity information in the historical commodity supply information with commodity information in the historical commodity price data, to obtain commodity dynamic price data of each commodity in the historical commodity supply information in a historical period;

[0015] import the commodity dynamic price data into the historical commodity dynamic coordinates, to obtain a commodity price dynamic curve of each commodity in the historical period.

[0016] In a possible implementation manner, the management and prediction analysis of the price floating data and the commodity variation information based on the operation change information to obtain future commodity sales and future commodity pricing in a future time period comprises the following steps.

[0017] According to the commodity variation information, determine a price variation factor causing a price variation event and commodity sales at different time nodes after the price variation event, and perform factor category division on the price variation factor, to obtain a variation empty set of different factor categories;

[0018] respectively add the price floating data and the commodity sales to the variation empty set according to time occurrence nodes, to obtain a variation data set of different factor categories;

[0019] based on the variation data set, calculate a price representative slope and a sales representative slope of each price variation event corresponding to each factor category;

[0020] perform supervised prediction on the price representative slope and the sales representative slope, to obtain a price representative prediction slope and a sales representative prediction slope of each factor category of each commodity in a future preset time period;

[0021] According to the operation change information, determine a change commodity in a future time period and a change factor category of the change commodity, and perform commodity screening on the change commodity and commodities in the commodity variation information, to obtain a commodity price slope and a commodity sales slope corresponding to each factor category of the change commodity;

[0022] match the change factor category with the factor category, to obtain a target commodity price slope and a target commodity sales slope corresponding to the change factor category;

[0023] determine whether the change commodity is still sold in a current time period, and if so, determine a current commodity price and a current commodity sales in a preset time period;

[0024] determining future commodity pricing in a future time period according to the current commodity price and the target commodity price slope;

[0025] determining future commodity sales in a future time period according to the current commodity sales and the target commodity sales slope.

[0026] In a possible implementation, the calculation of the price representative slope and the sales representative slope of each price fluctuation event corresponding to each factor category based on the fluctuation data set comprises:

[0027] creating commodity price fluctuation coordinates and commodity sales fluctuation coordinates, the X-axis of the commodity price fluctuation coordinates and the commodity sales fluctuation coordinates being different time nodes, the Y-axis of the commodity price fluctuation coordinates being commodity price data in different units, and the Y-axis of the commodity sales fluctuation coordinates being commodity sales data in different units;

[0028] respectively importing commodity price data in the fluctuation data set into the commodity price fluctuation coordinates according to time nodes, to obtain a plurality of commodity factor price curves;

[0029] respectively importing commodity sales data in the fluctuation data set into the commodity sales fluctuation coordinates according to time nodes, to obtain a plurality of commodity factor sales curves;

[0030] respectively performing curve waveform analysis on the plurality of commodity factor price curves and the plurality of commodity factor sales curves, to obtain a price representative slope corresponding to each commodity factor price curve and a sales representative slope corresponding to each commodity factor sales curve.

[0031] In a possible implementation, the supervised prediction of the price representative slope and the sales representative slope to obtain a price representative prediction slope and a sales representative prediction slope of each factor category of each commodity in a future preset time period comprises:

[0032] based on the time sequence length and the factor category, arranging the price representative slope and the sales representative slope to obtain commodity slope matrix data;

[0033] performing basic data distribution exploration on the commodity slope matrix data, to obtain a relative periodicity rule of the slope corresponding to each factor category;

[0034] determining a time period length according to the relative periodicity rule of the slope, performing supervised time sequence data arrangement on the commodity slope matrix data based on the time period length, and inputting the arranged commodity slope matrix data into a preset model to perform slope data deduction, to obtain a price representative prediction slope and a sales representative prediction slope of each factor category of each commodity in a future preset time period.

[0035] In a possible implementation manner, the curve waveform analysis on the plurality of commodity factor price curves and the plurality of commodity factor quantity curves respectively is performed to obtain a price representative slope corresponding to each commodity factor price curve and a quantity representative slope corresponding to each commodity factor quantity curve, including:

[0036] It is determined whether there is a rising abnormal point or a falling abnormal point in each commodity factor price curve and each commodity factor quantity curve respectively, if there is, the rising abnormal point or the falling abnormal point is defined as an interference point, and it is determined whether the interference point existing in each commodity factor price curve and each commodity factor quantity curve is unique;

[0037] If the interference point is a unique interference point and the interference point is located in the commodity factor price curve, a disturbance price data corresponding to the interference point, an initial price data corresponding to an initial point of the commodity factor price curve, and a terminal price data corresponding to a terminal point of the commodity factor price curve are determined, a first price fluctuation data and a first price fluctuation period are determined according to the disturbance price data and the initial price data, a second price fluctuation data and a second price fluctuation period are determined according to the disturbance price data and the terminal price data, a ratio of the first price fluctuation data to the first price fluctuation period and a ratio of the second price fluctuation data to the second price fluctuation period are calculated respectively, to obtain a first price slope corresponding to the first price fluctuation data and a second price slope corresponding to the second price fluctuation data;

[0038] The first price slope and the second price slope are integrated according to a proportional relationship between the first price fluctuation period and the second price fluctuation period, to obtain the price representative slope;

[0039] If the interference point is a unique interference point and the interference point is located in the commodity factor quantity curve, a disturbance quantity data corresponding to the interference point, an initial quantity data corresponding to an initial point of the commodity factor quantity curve, and a terminal quantity data corresponding to a terminal point of the commodity factor quantity curve are determined, a first quantity fluctuation data and a first quantity fluctuation period are determined according to the disturbance quantity data and the initial quantity data, a second quantity fluctuation data and a second quantity fluctuation period are determined according to the disturbance quantity data and the terminal quantity data, a ratio of the first quantity fluctuation data to the first quantity fluctuation period and a ratio of the second quantity fluctuation data to the second quantity fluctuation period are calculated respectively, to obtain a first quantity slope corresponding to the first quantity fluctuation data and a second quantity slope corresponding to the second quantity fluctuation data;

[0040] The first quantity slope and the second quantity slope are integrated according to a proportional relationship between the first quantity fluctuation period and the second quantity fluctuation period, to obtain the quantity representative slope.

[0041] In a possible implementation, the determining whether each commodity factor price curve and each commodity factor sales curve has a unique interference point includes:

[0042] If the interference point is not a unique interference point and the interference point is located in the commodity factor price curve, the interference point is sequentially marked according to time sequence, and the interference price data corresponding to each interference point, the initial price data corresponding to the initial point of the commodity factor price curve, and the terminal price data corresponding to the terminal point of the commodity factor price curve are determined, the first price fluctuation data and the first price fluctuation period between adjacent interference points are determined according to the adjacent characteristics between the interference points and the interference price data, the second price fluctuation data and the second price fluctuation period are determined according to the initial price data and the interference price data corresponding to the first interference point, the third price fluctuation data and the third price fluctuation period are determined according to the terminal price data and the interference price data corresponding to the Nth interference point, the ratio of the first price fluctuation data to the first price fluctuation period, the ratio of the second price fluctuation data to the second price fluctuation period, and the ratio of the third price fluctuation data to the third price fluctuation period are calculated respectively, the first price slope corresponding to the first price fluctuation data, the second price slope corresponding to the second price fluctuation data, and the third price slope corresponding to the third price fluctuation data are obtained, and N is the total number of interference points.

[0043] The first price slope, the second price slope, and the third price slope are integrated according to the proportional relationship of the first price fluctuation period, the second price fluctuation period, and the third price fluctuation period, to obtain a price representative slope.

[0044] If the interference point is not the only interference point and the interference point is located on the commodity factor sales curve, the interference points are sequentially marked in time sequence, and the interference sales data corresponding to each interference point, the initial sales data corresponding to the initial point of the commodity factor sales curve and the terminal sales data corresponding to the terminal point of the commodity factor sales curve are determined, the first sales fluctuation data and the first sales fluctuation period between adjacent interference points are determined according to the adjacent characteristics between the interference points and the interference sales data, the second sales fluctuation data and the second sales fluctuation period are determined according to the initial sales data and the interference sales data corresponding to the first interference point, the third sales fluctuation data and the third sales fluctuation period are determined according to the terminal sales data and the interference sales data corresponding to the Mth interference point, the ratio of the first sales fluctuation data to the first sales fluctuation period, the ratio of the second sales fluctuation data to the second sales fluctuation period and the ratio of the third sales fluctuation data to the third sales fluctuation period are calculated respectively, the first sales slope corresponding to the first sales fluctuation data, the second sales slope corresponding to the second sales fluctuation data and the third sales slope corresponding to the third sales fluctuation data are obtained, and the M is the total number of interference points.

[0045] The first sales slope, the second sales slope and the third sales slope are integrated and calculated according to the proportional relationship of the first sales fluctuation period, the second sales fluctuation period and the third sales fluctuation period, and a sales representative slope is obtained.

[0046] In a possible implementation, the determining whether the battery charging environment corresponding to the first battery charging data and the battery charging environment corresponding to the second battery charging data have a second preset environment difference includes:

[0047] If the battery charging environment corresponding to the first battery charging data and the battery charging environment corresponding to the second battery charging data have a second preset environment difference, the same battery charging data of the same battery charging environment in the second battery charging data is determined, the target battery charging data of the first battery charging is determined based on the same battery charging data, the first battery charging data and the second battery charging data are updated based on the target battery charging data, and the updated first battery charging data and the second battery charging data are obtained.

[0048] In a second aspect, the application provides a commodity operation strategy supervision system based on big data, which adopts the following technical scheme:

[0049] A commodity operation strategy supervision system based on big data includes:

[0050] The information collection module is configured to collect historical commodity supply information and historical commodity price data in a historical period and operation change information of the commodity in a future preset time period;

[0051] The curve construction module is configured to construct a correlation curve of the historical commodity supply information and the historical commodity price data, and obtain a commodity price dynamic curve of each commodity in the historical period;

[0052] The event determination module is configured to determine an event time node and price fluctuation data of a price change event according to the commodity price dynamic curve;

[0053] The information retrieval module is configured to retrieve the historical commodity supply information according to the event time node, and obtain commodity change information;

[0054] The prediction analysis module is configured to perform management prediction analysis on the price fluctuation data and the commodity change information based on the operation change information, and obtain future commodity sales and future commodity pricing in a future time period.

[0055] In a third aspect, the present application provides an electronic device, which adopts the technical scheme as follows:

[0056] at least one processor;

[0057] a memory;

[0058] at least one application program, wherein the at least one application program is stored in the memory and configured to be executed by the at least one processor, and the at least one application program is configured to execute the big data-based commodity operation strategy supervision method according to any one of the first aspect.

[0059] In a fourth aspect, the present application provides a computer readable storage medium, which adopts the technical scheme as follows:

[0060] A computer readable storage medium, which stores a computer program, and when the computer program is executed in a computer, the computer is caused to execute the big data-based commodity operation strategy supervision method according to any one of the first aspect.

[0061] In summary, the present application includes at least one of the following beneficial technical effects:

[0062] By adopting the technical scheme, the rich historical commodity supply information, historical commodity price data and operation change information of the commodity in the future preset time period in the historical period are collected. The historical commodity supply information and price data are the basis, record the supply situation and price fluctuation of the commodity in different stages, and provide original materials for subsequent analysis. The operation change information reflects the factors that affect the commodity in the future. Then, the historical commodity supply information and price data are associated to construct a correlation curve to obtain a commodity price dynamic curve. The trend of the commodity price change with the supply change is intuitively presented, and the price change is clearly understood, which lays a foundation for accurately grasping the commodity price trend. After obtaining the commodity price dynamic curve, the event time node and the price fluctuation data of the price change event are determined according to the curve. By analyzing the ups and downs of the curve, the specific time point of the price change, that is, the event time node, can be accurately positioned. At the same time, the amplitude of the price change, that is, the price fluctuation data, is determined. These key information is an important basis for understanding the commodity price fluctuation. Only by accurately obtaining these data, can the reasons and influences of the price change be further explored, and a clear direction for subsequent search of commodity supply information is provided. According to the determined event time node, the historical commodity supply information is searched to obtain commodity change information. The event time node is like a precise locator, which determines that the commodity price has changed at a specific time. With this clue, the historical commodity supply information is searched to quickly find the related change of the commodity supply at the time point, such as the increase or decrease of the supply amount, the change of the supply channel and the like, which is the commodity change information. The commodity change information is closely related to the price change. By obtaining these information, the internal relationship between the commodity supply and the price can be deeply analyzed, and key data support is provided for subsequent management and prediction analysis based on the operation change information. Based on the operation change information, the price fluctuation data and the commodity change information are managed and predicted to obtain the future commodity sales and the future commodity pricing in the future time period. The operation change information reflects various factors that may affect the commodity in the future, such as market strategy adjustment. Combined with the price fluctuation data and the commodity change information obtained before, these data cover the past price and supply change of the commodity. The multi-dimensional data are comprehensively managed and predicted, which can more comprehensively and accurately predict the performance of the commodity in the future market, not only can the future commodity sales be accurately estimated, but also the future commodity pricing can be reasonably determined, which provides a scientific basis for the future market operation decision of the enterprise, and improves the timeliness and accuracy of the commodity operation strategy supervision. BRIEF DESCRIPTION OF DRAWINGS

[0063] Figure 1 A flowchart of a commodity operation strategy supervision method based on big data provided by the embodiment of the application.

[0064] Figure 2A structural schematic diagram of a commodity operation strategy supervision system based on big data provided by an embodiment of the present application.

[0065] Figure 3 A structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0066] The following will be further described in detail in combination with the accompanying drawings of the present application. Figures 1-3 The present application will be further described in detail.

[0067] The present embodiment is merely an explanation of the present application, and is not a limitation of the present application. Those skilled in the art can make modifications to the present embodiment without creative contribution after reading the present specification, and the modifications are protected by the patent law as long as they are within the scope of the present application.

[0068] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme of the embodiments of the present application will be described clearly and completely below in combination with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments of the present application, all the other embodiments obtained by those skilled in the art without creative contribution fall within the scope of the present application.

[0069] In addition, the term "and / or" in the present application is merely to describe the association relationship of the associated objects, and represents that there can be three relationships, for example, A and / or B can represent that there are three cases of A alone, A and B together, and B alone. In addition, the character " / " in the present application generally represents an "or" relationship between the associated objects unless otherwise specified.

[0070] The embodiments of the present application will be further described in detail below in combination with the accompanying drawings of the present application.

[0071] The embodiments of the present application provide a commodity operation strategy supervision method based on big data, which is executed by an electronic device. The electronic device can be an independent physical electronic device, an electronic device cluster or a distributed system composed of multiple physical electronic devices, or a cloud electronic device providing cloud computing services. The present application does not limit the electronic device in the embodiments of the present application. For example, as shown in the figure, the method comprises the following steps. Figure 1

[0072] Step S10, collecting historical commodity supply information and historical commodity price data in a historical period and operation change information of commodities in a future preset time period.

[0073] ​For the embodiments of the present application, the historical commodity supply information refers to various types of data related to commodity supply in the past historical period, including the inventory quantity of the commodity, the supply situation of the supplier, the replenishment time, the promotion activity arrangement, the product upgrade plan, the sales channel adjustment, etc., which refers to the information set that can reflect the commodity supply state and changes. The historical commodity price data refers to the price records of the commodity at different time points in the past historical period, which is used to represent the change of the commodity price over time. The future preset time period refers to a certain time interval in the future that is set in advance, such as the next week, the next month, etc., which is used to represent the planning range of the future time. The operation change information of the commodity refers to the information that changes in the future preset time period related to the operation of the commodity, including the promotion activity arrangement, the product upgrade plan, the sales channel adjustment, etc., which is used to represent various change factors that affect the operation state of the commodity.

[0074] Step S11, the historical commodity supply information and the historical commodity price data are associated to construct a curve, and the commodity price dynamic curve of each commodity in the historical period is obtained.

[0075] Specifically, the collected historical commodity supply information and historical commodity price data are preprocessed. Since the original data may have missing values, abnormal values or inconsistent formats, the preprocessing work includes data cleaning, i.e. removing duplicate data, correcting error data, filling missing values, etc., to ensure the accuracy and integrity of the data. At the same time, the data is standardized to make data from different sources and different dimensions comparable, for example, the inventory quantity and price data are unified to a suitable numerical range. Then, determine the mathematical model or algorithm used for the construction of the correlation curve. Commonly used are linear regression models, which are suitable for data that presents an approximate linear relationship; nonlinear regression models, such as polynomial regression, exponential regression, etc., which can be used to handle more complex data relationships; there are also time series analysis methods, such as moving average method, exponential smoothing method, etc., which can consider the influence of time factors on data. According to the characteristics of the historical commodity supply information and the historical commodity price data, select the appropriate model for fitting. In the model fitting process, the historical commodity supply information is taken as the independent variable, and the historical commodity price data is taken as the dependent variable. By adjusting the model parameters, the model can be fitted to the actual data to the greatest extent. After multiple iterations and optimization, the final correlation curve model is obtained. Finally, according to the model, the commodity price dynamic curve of each commodity in the historical period is generated, taking time as the horizontal coordinate and commodity price as the vertical coordinate. The price values calculated by the model are plotted in the coordinate system to form a curve, which intuitively shows the change of the commodity price over time.

[0076] In the embodiments of the present application, a historical commodity dynamic coordinate is created, wherein the X-axis of the historical commodity dynamic coordinate is different time nodes, and the Y-axis of the historical commodity dynamic coordinate is price data of different specifications. The commodity information in the historical commodity supply information is associated with the commodity information in the historical commodity price data respectively to obtain commodity dynamic price data of each commodity in the historical commodity supply information in a historical period, the commodity dynamic price data is imported into the historical commodity dynamic coordinate to obtain a commodity price dynamic curve of each commodity in the historical period.

[0077] In step S12, an event time node of a price change event and price fluctuation data are determined according to the commodity price dynamic curve.

[0078] For the embodiments of the present application, the data of the commodity price dynamic curve is read and stored in the format of pandas DataFrame. Then, a price change threshold is set, the change amplitude of the prices of adjacent time nodes is calculated, and compared with the threshold, when the change amplitude exceeds the threshold, the time node is recorded as the time node of the price change event. Finally, according to the recorded time node, the corresponding price value is extracted from the original price data, and the difference with the reference price (such as the price of the previous time node) is calculated to obtain the price fluctuation data.

[0079] In step S13, the historical commodity supply information is searched according to the event time node to obtain commodity change information.

[0080] For the embodiments of the present application, the time range of the historical commodity supply information to be searched is determined, the time range is centered on the determined event time node, and is appropriately extended forward and backward according to the analysis requirements. For example, if the event time node is a specific date, the search time range can be set to one week or one month before and after the date. Then, the dimensions of the search are determined, and the key dimensions in the historical commodity supply information are selected according to the analysis purpose, such as promotion activity arrangement, product upgrade plan, sales channel adjustment, etc. According to the determined time range and search dimensions, the search is performed in the database storing the historical commodity supply information. Structured Query Language (SQL) can be used to write a query statement to extract the data meeting the conditions from the database. The searched data is sorted and analyzed, the data of different dimensions is summarized and compared, the change of the commodity supply information before and after the event time node is found out, and the commodity change information is obtained.

[0081] In step S14, the price fluctuation data and the commodity change information are managed and predicted based on the operation change information to obtain future commodity sales and future commodity pricing in a future time period.

[0082] Specifically, the price change factor causing the price change event and the commodity sales volume at different time nodes after the occurrence of the price change event are determined according to the commodity change information, the price change factors are classified by factor categories, and the change empty set of different factor categories is obtained. The price floating data and the commodity sales volume are respectively added to the change empty set according to the time occurrence node to obtain the change data set of different factor categories, and the price representative slope and the sales volume representative slope of each price change event corresponding to each factor category are calculated based on the change data set. The price representative slope and the sales volume representative slope are supervised and predicted to obtain the price representative prediction slope and the sales volume representative prediction slope of each factor category of each commodity in a future preset time period. The changed commodity and the change factor category of the changed commodity in the future time period are determined according to the operation change information, and the changed commodity is screened with the commodity in the commodity change information to obtain the commodity price slope and the commodity sales volume slope corresponding to each factor category of the changed commodity. The change factor category is matched with the factor category to obtain the target commodity price slope and the target commodity sales volume slope corresponding to the change factor category. It is judged whether the changed commodity is still on sale in the current time period, if it is still on sale, the current commodity price and the current commodity sales volume in the preset time period are determined, the future commodity pricing in the future time period is determined according to the current commodity price and the target commodity price slope, and the future commodity sales volume in the future time period is determined according to the current commodity sales volume and the target commodity sales volume slope.

[0083] Specifically, the price change factor refers to the specific reason causing the price change event to occur, rather than the root cause, such as promotion arrangement, product upgrade plan, sales channel adjustment, etc. The determined price change factor is classified by factor category, which is divided into different categories according to the nature and characteristics of the factor, such as supply, market, competition, etc., and an empty change set is created for each factor category. Then, the price float data and the commodity sales volume are added to the corresponding change set according to the time occurrence node to form the change data set of different factor categories. Based on these change data sets, mathematical methods (such as linear regression analysis) are used to calculate the price representative slope and the sales volume representative slope of each price change event corresponding to each factor category. These slopes can directly reflect the change trend of price and sales volume. The calculated price representative slope and sales volume representative slope are supervised and predicted to obtain the price representative prediction slope and the sales volume representative prediction slope of each factor category of each commodity in the future preset time period. Next, the changed commodities and the changed factor categories in the future time period are determined according to the operation change information, and the changed commodities are screened with the commodities in the commodity change information by comparing the commodity name, specification and other information to find the commodity price slope and commodity sales volume slope corresponding to each factor category of the changed commodities. The changed factor categories are matched with the previously classified factor categories, and the target commodity price slope and the target commodity sales volume slope corresponding to the changed factor categories are selected from the calculated slope data. Finally, it is determined whether the changed commodities are still on sale in the current time period, which can be determined by querying the enterprise's inventory management system and sales system. If they are still on sale, the current commodity price and the current commodity sales volume in the preset time period are determined, the future commodity pricing in the future time period is determined by the formula future commodity pricing = current commodity price + target commodity price slope × time interval according to the current commodity price and the target commodity price slope; the future commodity sales volume in the future time period is determined by the formula future commodity sales volume = current commodity sales volume + target commodity sales volume slope × time interval according to the current commodity sales volume and the target commodity sales volume slope.

[0084] If the current commodity is not on sale, the last sale price and the sale volume of the current commodity are taken as the current commodity price and the current commodity sales volume.

[0085] In the embodiments of the present application, the price representative slope and the sales representative slope are supervised predicted to obtain the price representative predicted slope and the sales representative predicted slope of each factor category of each commodity in a future preset time period, including: based on the time series length and the factor category, the price representative slope and the sales fluctuation slope are arranged to obtain commodity slope matrix data, the commodity slope matrix data is subjected to basic data distribution exploration to obtain the slope relative periodicity law corresponding to each factor category. The time period length is determined according to the slope relative periodicity law, and the commodity slope matrix data is subjected to supervised time series data arrangement based on the time period length, and the arranged commodity slope matrix data is input into a preset model for slope data deduction to obtain the price representative predicted slope and the sales representative predicted slope of each factor category of each commodity in a future preset time period.

[0086] For the embodiments of the present application, the price representative slope and the sales fluctuation slope are arranged based on the time series length and the factor category. From the previously collected and calculated price representative slope and sales fluctuation slope data, the slope data at different time points under the same factor category is integrated together according to the time sequence and different factor categories to form commodity slope matrix data with commodity, factor category and time series as dimensions. Then, the commodity slope matrix data is subjected to basic data distribution exploration. Statistical methods are used to calculate various statistical indicators of the data, such as calculating the mean, variance, etc. of the price representative slope and the sales fluctuation slope under each factor category, and the distribution of the data is visually displayed through drawing histograms, box plots and other charts, so as to find the abnormal values, outliers and the concentration trend and dispersion degree of the data, and then obtain the slope relative periodicity law corresponding to each factor category. For example, by observing the data distribution graph, it is found that the price representative slope and the sales fluctuation slope of a certain factor will appear similar change patterns in a specific month of each year, showing a certain periodicity. The time period length is determined according to the slope relative periodicity law, such as determining the period of the above factor as 12 months. Then, the commodity slope matrix data is subjected to supervised time series data arrangement based on the determined time period length. The data is divided and labeled according to the time period, the corresponding label is set for the data in each period, and feature engineering processing is performed on the data to extract features that are helpful for model learning, such as adding the average slope and slope change rate in the time period as new features to the data, so that the data is more in line with the requirements of supervised learning model. Finally, the arranged commodity slope matrix data is input into a preset model for slope data deduction. The preset model can be a bidirectional LSTM model, which learns the patterns and laws in the historical data to predict the price representative slope and the sales fluctuation slope in a future preset time period, thereby obtaining the price representative predicted slope and the sales representative predicted slope of each factor category of each commodity in a future preset time period.

[0087] The embodiment of the application provides a commodity operation strategy supervision method based on big data, rich historical commodity supply information, historical commodity price data and operation change information of the commodity in a future preset time period are collected in a historical period. The historical commodity supply information and the price data are bases, record the supply conditions and the price fluctuation of the commodity in different stages, and provide original materials for subsequent analysis. The operation change information reflects factors that may affect the commodity in the future. Then, the historical commodity supply information and the price data are associated to construct a curve, and a commodity price dynamic curve is obtained. The trend of the commodity price change with the supply is intuitively presented, and the price change condition is clearly understood, so that the foundation for accurately grasping the commodity price trend is laid. After the commodity price dynamic curve is obtained, the event time node of the price change event and the price fluctuation data are determined according to the curve. Through analysis of the ups and downs of the curve, the specific time point of the price change, that is, the event time node, can be accurately positioned. At the same time, the amplitude of the price change, that is, the price fluctuation data, is determined. These key information is an important basis for understanding the commodity price fluctuation. Only by accurately obtaining these data, the reasons and influences of the price change can be further explored, and a clear direction for subsequent search of the commodity supply information is provided. The historical commodity supply information is searched according to the determined event time node, and commodity change information is obtained. The event time node is like a precise locator, which clearly indicates that the commodity price has changed at a specific time. The historical commodity supply information is searched as a clue, and the related change conditions of the commodity supply at the time point, such as the increase or decrease of the supply amount and the change of the supply channel, can be quickly found, which is the commodity change information. The commodity change information is closely related to the price change. By obtaining these information, the internal relationship between the commodity supply and the price can be deeply analyzed, and key data support is provided for subsequent management and prediction analysis based on the operation change information. The price fluctuation data and the commodity change information are managed and predicted based on the operation change information, and future commodity sales and future commodity pricing in a future time period are obtained. The operation change information reflects various factors that may affect the commodity in the future, such as market strategy adjustment. Combined with the price fluctuation data and the commodity change information obtained before, these data cover the past price and supply change of the commodity. The multi-dimensional data are comprehensively managed and predicted, the performance of the commodity in the market in the future can be more comprehensively and accurately predicted, not only the future commodity sales can be accurately estimated, but also the future commodity pricing can be reasonably determined, a scientific basis is provided for the business decision of the enterprise in the future market, and the timeliness and accuracy of the commodity operation strategy supervision are improved.

[0088] Further, the price representative slope and the sales representative slope corresponding to each price change event of each factor category are calculated based on the change data set, including: creating a commodity price change coordinate and a commodity sales change coordinate, the X axis of the commodity price change coordinate and the commodity sales change coordinate being different time nodes, the Y axis of the commodity price change coordinate being commodity price data of different units, and the Y axis of the commodity sales change coordinate being commodity sales data of different units. The commodity price data in the change data set is respectively imported into the commodity price change coordinate according to the time nodes, to obtain a plurality of commodity factor price curves. The commodity sales data in the change data set is respectively imported into the commodity sales change coordinate according to the time nodes, to obtain a plurality of commodity factor sales curves. Curve waveform analysis is performed on the plurality of commodity factor price curves and the plurality of commodity factor sales curves, to obtain a price representative slope corresponding to each commodity factor price curve and a sales representative slope corresponding to each commodity factor sales curve.

[0089] Specifically, it is determined whether there is a rising abnormal point or a falling abnormal point in each commodity factor price curve and each commodity factor sales curve, if there is, the rising abnormal point or the falling abnormal point is defined as an interference point, and it is determined whether the interference point existing in each commodity factor price curve and each commodity factor sales curve is unique. If the interference point is a unique interference point and the interference point is located in the commodity factor price curve, the interference price data corresponding to the interference point, the initial price data corresponding to the initial point of the commodity factor price curve, and the terminal price data corresponding to the terminal point of the commodity factor price curve are determined, the first price fluctuation data and the first price fluctuation period are determined according to the interference price data and the initial price data, the second price fluctuation data and the second price fluctuation period are determined according to the interference price data and the terminal price data, the ratio of the first price fluctuation data to the first price fluctuation period and the ratio of the second price fluctuation data to the second price fluctuation period are calculated, to obtain a first price slope corresponding to the first price fluctuation data and a second price slope corresponding to the second price fluctuation data. The first price slope and the second price slope are integrated and calculated according to the proportional relationship of the first price fluctuation period and the second price fluctuation period, to obtain the price representative slope.

[0090] If the several disturbance points are the only disturbance points and the disturbance points are located on the commodity factor sales curve, the disturbance sales data corresponding to the disturbance points, the initial sales data corresponding to the initial point of the commodity factor sales curve and the terminal sales data corresponding to the terminal point of the commodity factor sales curve are determined, the first sales fluctuation data and the first sales fluctuation period are determined according to the disturbance sales data and the initial sales data, the second sales fluctuation data and the second sales fluctuation period are determined according to the disturbance sales data and the terminal sales data, the ratio of the first sales fluctuation data to the first sales fluctuation period and the ratio of the second sales fluctuation data to the second sales fluctuation period are calculated respectively, the first sales slope corresponding to the first sales fluctuation data and the second sales slope corresponding to the second sales fluctuation data are obtained. The first sales slope and the second sales slope are integrated and calculated according to the proportional relationship of the first sales fluctuation period and the second sales fluctuation period, and the sales representative slope is obtained.

[0091] Specifically, if the several disturbance points are not the only disturbance points and the disturbance points are located on the commodity factor price curve, the disturbance points are sequentially marked according to the time sequence, the disturbance price data corresponding to each disturbance point, the initial price data corresponding to the initial point of the commodity factor price curve and the terminal price data corresponding to the terminal point of the commodity factor price curve are determined, the first price fluctuation data and the first price fluctuation period between adjacent disturbance points are determined according to the adjacent characteristics between the disturbance points and the disturbance price data, the second price fluctuation data and the second price fluctuation period are determined according to the initial price data and the disturbance price data corresponding to the first disturbance point, the third price fluctuation data and the third price fluctuation period are determined according to the terminal price data and the disturbance price data corresponding to the Nth disturbance point, the ratio of the first price fluctuation data to the first price fluctuation period, the ratio of the second price fluctuation data to the second price fluctuation period and the ratio of the third price fluctuation data to the third price fluctuation period are calculated respectively, the first price slope corresponding to the first price fluctuation data, the second price slope corresponding to the second price fluctuation data and the third price slope corresponding to the third price fluctuation data are obtained, N is the total number of disturbance points, the first price slope, the second price slope and the third price slope are integrated and calculated according to the proportional relationship of the first price fluctuation period, the second price fluctuation period and the third price fluctuation period, and the price representative slope is obtained.

[0092] If the several disturbance points are not the only disturbance points and the disturbance points are located on the commodity factor sales curve, the disturbance points are sequentially marked according to time sequence, the disturbance sales data corresponding to each disturbance point, the initial sales data corresponding to the initial point of the commodity factor sales curve and the terminal sales data corresponding to the terminal point of the commodity factor sales curve are determined, the first sales fluctuation data and the first sales fluctuation period between the adjacent disturbance points are determined according to the adjacent characteristics between the disturbance points and the disturbance sales data, the second sales fluctuation data and the second sales fluctuation period are determined according to the initial sales data and the disturbance sales data corresponding to the first disturbance point, the third sales fluctuation data and the third sales fluctuation period are determined according to the terminal sales data and the disturbance sales data corresponding to the Mth disturbance point, the ratio of the first sales fluctuation data to the first sales fluctuation period, the ratio of the second sales fluctuation data to the second sales fluctuation period and the ratio of the third sales fluctuation data to the third sales fluctuation period are respectively calculated, the first sales slope corresponding to the first sales fluctuation data, the second sales slope corresponding to the second sales fluctuation data and the third sales slope corresponding to the third sales fluctuation data are obtained, M is the total number of the disturbance points, the first sales slope, the second sales slope and the third sales slope are integrated and calculated according to the proportional relationship of the first sales fluctuation period, the second sales fluctuation period and the third sales fluctuation period, and the sales representative slope is obtained.

[0093] A kind of based on big data's commodity operation strategy supervision system provided in the embodiment of the application is introduced below, a kind of based on big data's commodity operation strategy supervision system described below and the based on big data's commodity operation strategy supervision method described above can be mutually corresponding reference, please refer to Figure 2 , Figure 2 It is the structure schematic view of a kind of based on big data's commodity operation strategy supervision system 20 provided in the embodiment of the application, including:

[0094] Information acquisition module 21 is used to collect historical commodity supply information and historical commodity price data in historical period and operation change information of commodity in future preset time period;

[0095] Curve construction module 22 is used to construct associated curve for historical commodity supply information and historical commodity price data, and obtain commodity price dynamic curve of each commodity in historical period;

[0096] Event determination module 23 is used to determine event time node and price fluctuation data of price change event according to commodity price dynamic curve;

[0097] Information retrieval module 24 is used to retrieve historical commodity supply information according to event time node, and obtain commodity change information;

[0098] The prediction analysis module 25 is configured to perform management prediction analysis on the price fluctuation data and the commodity variation information based on the operation change information, to obtain future commodity sales and future commodity pricing in a future time period.

[0099] In one possible implementation of the embodiments of the present application, when the curve construction module constructs a historical commodity supply information and historical commodity price data associated curve to obtain a commodity price dynamic curve of each commodity in a historical period, the curve construction module is specifically configured to:

[0100] create a historical commodity dynamic coordinate, wherein an X-axis of the historical commodity dynamic coordinate is different time nodes, and a Y-axis of the historical commodity dynamic coordinate is different specifications of price data;

[0101] associate commodity information in the historical commodity supply information with commodity information in the historical commodity price data respectively, to obtain commodity dynamic price data of each commodity in the historical commodity supply information in the historical period;

[0102] import the commodity dynamic price data into the historical commodity dynamic coordinate, to obtain a commodity price dynamic curve of each commodity in the historical period.

[0103] In another possible implementation of the embodiments of the present application, when the prediction analysis module performs management prediction analysis on the price fluctuation data and the commodity variation information based on the operation change information, to obtain future commodity sales and future commodity pricing in a future time period, the prediction analysis module is specifically configured to:

[0104] determine a price variation factor causing a price variation event and commodity sales at different time nodes after the price variation event according to the commodity variation information, and perform factor category division on the price variation factor, to obtain a variation empty set of different factor categories;

[0105] add the price fluctuation data and the commodity sales to the variation empty set respectively according to time occurrence nodes, to obtain a variation data set of different factor categories;

[0106] calculate a price representative slope and a sales representative slope of each price variation event corresponding to each factor category based on the variation data set;

[0107] perform supervised prediction on the price representative slope and the sales representative slope, to obtain a price representative prediction slope and a sales representative prediction slope of each factor category of each commodity in a future preset time period;

[0108] determine a changed commodity and a change factor category of the changed commodity in the future time period according to the operation change information, and perform commodity screening on the changed commodity and commodities in the commodity variation information, to obtain a commodity price slope and a commodity sales slope corresponding to each factor category of the changed commodity;

[0109] match the change factor category with the factor category to obtain a target commodity price slope and a target commodity sales slope corresponding to the change factor category;

[0110] determine whether the changed commodity is still on sale in the current time period, and if so, determine a current commodity price and a current commodity sales in a preset time period;

[0111] determine a future commodity pricing in a future time period according to the current commodity price and the target commodity price slope;

[0112] determine a future commodity sales in a future time period according to the current commodity sales and the target commodity sales slope.

[0113] In another possible implementation manner of the embodiment, when the prediction analysis module calculates the price representative slope and the sales representative slope of each price change event corresponding to each factor category based on the change data set, it is specifically used for:

[0114] create a commodity price change coordinate and a commodity sales change coordinate, the X axis of the commodity price change coordinate and the commodity sales change coordinate being different time nodes, the Y axis of the commodity price change coordinate being different units of commodity price data, and the Y axis of the commodity sales change coordinate being different units of commodity sales data;

[0115] respectively import the commodity price data in the change data set into the commodity price change coordinate according to the time nodes to obtain a plurality of commodity factor price curves;

[0116] respectively import the commodity sales data in the change data set into the commodity sales change coordinate according to the time nodes to obtain a plurality of commodity factor sales curves;

[0117] respectively perform curve waveform analysis on the plurality of commodity factor price curves and the plurality of commodity factor sales curves to obtain a price representative slope corresponding to each commodity factor price curve and a sales representative slope corresponding to each commodity factor sales curve.

[0118] In another possible implementation manner of the embodiment, when the prediction analysis module performs supervised prediction on the price representative slope and the sales representative slope to obtain a price representative prediction slope and a sales representative prediction slope of each factor category of each commodity in a future preset time period, it is specifically used for:

[0119] based on the time series length and the factor category, collate the price representative slope and the sales representative slope to obtain commodity slope matrix data;

[0120] perform basic data distribution exploration on the commodity slope matrix data to obtain a slope relative periodicity rule corresponding to each factor category;

[0121] The length of the time period is determined according to the relative periodicity of the slope, the supervised time series data of the commodity slope matrix data is arranged based on the length of the time period, and the arranged commodity slope matrix data is input into a preset model to derive the slope data, so as to obtain the price representative prediction slope and the sales representative prediction slope of each factor category of each commodity in a future preset time period.

[0122] In another possible implementation manner of the embodiment, when the prediction analysis module respectively analyzes the multiple commodity factor price curves and the multiple commodity factor sales curves to obtain the price representative slope corresponding to each commodity factor price curve and the sales representative slope corresponding to each commodity factor sales curve, the prediction analysis module is specifically configured to:

[0123] respectively determine whether there is a rising abnormal point or a falling abnormal point in each commodity factor price curve and each commodity factor sales curve, if there is, define the rising abnormal point or the falling abnormal point as an interference point, and determine whether the interference point existing in each commodity factor price curve and each commodity factor sales curve is unique;

[0124] if the interference point is a unique interference point and the interference point is located in the commodity factor price curve, determine the interference price data corresponding to the interference point, the initial price data corresponding to the initial point of the commodity factor price curve, and the terminal price data corresponding to the terminal point of the commodity factor price curve, determine the first price fluctuation data and the first price fluctuation period according to the interference price data and the initial price data, determine the second price fluctuation data and the second price fluctuation period according to the interference price data and the terminal price data, respectively calculate the ratio of the first price fluctuation data to the first price fluctuation period and the ratio of the second price fluctuation data to the second price fluctuation period, obtain the first price slope corresponding to the first price fluctuation data and the second price slope corresponding to the second price fluctuation data;

[0125] integrate and calculate the first price slope and the second price slope according to the proportional relationship between the first price fluctuation period and the second price fluctuation period, to obtain the price representative slope;

[0126] If the several disturbance points are unique disturbance points and the disturbance points are located in the commodity factor sales curve, the disturbance sales data corresponding to the disturbance points, the initial sales data corresponding to the initial point of the commodity factor sales curve and the terminal sales data corresponding to the terminal point of the commodity factor sales curve are determined, the first sales floating data and the first sales floating period are determined according to the disturbance sales data and the initial sales data, the second sales floating data and the second sales floating period are determined according to the disturbance sales data and the terminal sales data, the ratio of the first sales floating data to the first sales floating period and the ratio of the second sales floating data to the second sales floating period are calculated respectively, and the first sales slope corresponding to the first sales floating data and the second sales slope corresponding to the second sales floating data are obtained;

[0127] The first sales slope and the second sales slope are integrated and calculated according to the proportional relationship of the first sales floating period and the second sales floating period, and the sales representative slope is obtained.

[0128] In another possible implementation manner in the embodiment of the application, when the prediction analysis module determines whether the disturbance points existing in each commodity factor price curve and each commodity factor sales curve are unique, the prediction analysis module is specifically configured to:

[0129] If the several disturbance points are not unique disturbance points and the disturbance points are located in the commodity factor price curve, the disturbance points are sequentially marked according to time sequence, the disturbance price data corresponding to each disturbance point, the initial price data corresponding to the initial point of the commodity factor price curve and the terminal price data corresponding to the terminal point of the commodity factor price curve are determined, the first price floating data and the first price floating period between adjacent disturbance points are determined according to the adjacent characteristics between the disturbance points and the disturbance price data, the second price floating data and the second price floating period are determined according to the initial price data and the disturbance price data corresponding to the first disturbance point, the third price floating data and the third price floating period are determined according to the terminal price data and the disturbance price data corresponding to the Nth disturbance point, the ratio of the first price floating data to the first price floating period, the ratio of the second price floating data to the second price floating period and the ratio of the third price floating data to the third price floating period are calculated respectively, the first price slope corresponding to the first price floating data, the second price slope corresponding to the second price floating data and the third price slope corresponding to the third price floating data are obtained, and N is the total number of the disturbance points.

[0130] The first price slope, the second price slope and the third price slope are integrated and calculated according to the proportional relationship of the first price floating period, the second price floating period and the third price floating period, and the price representative slope is obtained.

[0131] If the several disturbance points are not the only disturbance points and the disturbance points are located on the commodity factor sales curve, the disturbance points are sequentially marked according to time sequence, the disturbance sales data corresponding to each disturbance point, the initial sales data corresponding to the initial point of the commodity factor sales curve and the terminal sales data corresponding to the terminal point of the commodity factor sales curve are determined, the first sales fluctuation data between adjacent disturbance points and the first sales fluctuation period are determined according to the adjacent characteristics between the disturbance points and the disturbance sales data, the second sales fluctuation data and the second sales fluctuation period are determined according to the initial sales data and the disturbance sales data corresponding to the first disturbance point, the third sales fluctuation data and the third sales fluctuation period are determined according to the terminal sales data and the disturbance sales data corresponding to the Mth disturbance point, the ratio of the first sales fluctuation data to the first sales fluctuation period, the ratio of the second sales fluctuation data to the second sales fluctuation period and the ratio of the third sales fluctuation data to the third sales fluctuation period are respectively calculated, the first sales slope corresponding to the first sales fluctuation data, the second sales slope corresponding to the second sales fluctuation data and the third sales slope corresponding to the third sales fluctuation data are obtained, and M is the total number of the disturbance points.

[0132] The first sales slope, the second sales slope and the third sales slope are integrated and calculated according to the proportional relationship of the first sales fluctuation period, the second sales fluctuation period and the third sales fluctuation period, and the sales representative slope is obtained.

[0133] Embodiments of the present application provide an electronic device, as shown in Figure 3 , the electronic device 300 shown in Figure 3 is a structural schematic diagram of an electronic device provided by the embodiments of the present application, Figure 3 The electronic device 300 shown in

[0134] The processor 301 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array) or other programmable logic device, transistor logic device, hardware component, or any combination thereof. The processor 301 can implement or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure of the embodiments of the present application. The processor 301 can also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0135] The bus 302 can include a path for transmitting information between the above-mentioned components. The bus 302 can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, or the like. The bus 302 can be divided into an address bus, a data bus, a control bus, and the like. For ease of representation, Figure 3 In the figure, only one thick line is used to represent the bus, but it does not mean that there is only one bus or only one type of bus.

[0136] The memory 303 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0137] The memory 303 is used to store application program code for implementing the embodiments of the present application, and is controlled by the processor 301 to execute. The processor 301 is used to execute the application program code stored in the memory 303 to realize the content shown in the foregoing method embodiments.

[0138] The electronic device includes, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a car terminal (for example, a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. Figure 3 The illustrated electronic device is merely an example and should not impose any limitation on the function and use range of the embodiments of the present application.

[0139] A computer readable storage medium according to an embodiment of the present application is described below, and the computer readable storage medium described below can be referred to in correspondence with the method described above.

[0140] The embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to realize the steps of the above-mentioned big data-based commodity operation strategy supervision system.

[0141] Since the embodiments of the computer readable storage medium part correspond to the embodiments of the method part, the embodiments of the computer readable storage medium part are described with reference to the description of the embodiments of the method part.

[0142] It should be understood that, although each step in the flowchart of the accompanying drawings is shown in sequence according to the direction of the arrow, these steps are not necessarily executed in sequence according to the direction of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other orders. Moreover, at least part of the steps in the flowchart of the accompanying drawings can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0143] The above is only some embodiments of the present application, and it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, some improvements and refinements can be made, and these improvements and refinements should be regarded as the protection scope of the present application.

Claims

1. A method for monitoring commodity operation strategies based on big data, characterized in that, include: Collect historical commodity supply information and historical commodity price data within a historical period, as well as information on operational changes of commodities within a future preset time period; By constructing correlation curves between the historical commodity supply information and the historical commodity price data, a dynamic price curve for each commodity within a historical period is obtained. The event time points and price fluctuation data of the price change events are determined based on the dynamic curve of the commodity price. Based on the event time points, the historical commodity supply information is retrieved to obtain commodity change information; Based on the operational change information, the price fluctuation data and the product change information are managed and predicted to obtain future product sales and future product pricing within a future time period; The step of managing and predicting the price fluctuation data and product change information based on the operational change information to obtain future product sales volume and future product pricing within a future time period includes: Based on the commodity change information, determine the price change factors that caused the price change event and the commodity sales volume at different time points after the price change event, and classify the price change factors into factor categories to obtain the change empty set of different factor categories. The price fluctuation data and the sales volume of the goods are added to the change empty set according to the time node of occurrence, respectively, to obtain the change data set of different factor categories; Based on the aforementioned set of changing data, calculate the price-representing slope and sales-representing slope for each price change event corresponding to each factor category; Supervised prediction is performed on the price-representing slope and the sales-representing slope to obtain the price-representing prediction slope and sales-representing prediction slope for each factor category of each product within a preset future time period. Based on the operational change information, determine the products to be changed in the future time period and the categories of change factors for the products to be changed, and screen the products to be changed and the products in the product change information to obtain the product price slope and product sales slope corresponding to each category of the products to be changed; The change factor category is matched with the factor category to obtain the target product price slope and target product sales slope corresponding to the change factor category; Determine whether the changed product is still on sale within the current time period. If it is still on sale, determine the current product price and the current product sales volume within the preset time period. Determine the future product pricing within a future time period based on the current product price and the target product price slope; The future sales volume of the product within a future time period is determined based on the current sales volume of the product and the slope of the target product sales volume.

2. The method for supervising commodity operation strategies based on big data according to claim 1, characterized in that, The step of constructing a correlation curve between the historical commodity supply information and the historical commodity price data to obtain the dynamic price curve of each commodity within a historical period includes: Create a dynamic coordinate system for historical products, where the X-axis represents different time points and the Y-axis represents price data for different specifications. The commodity information in the historical commodity supply information is associated with the commodity information in the historical commodity price data to obtain the dynamic price data of each commodity in the historical commodity supply information within the historical period; Import the dynamic price data of the commodities into the historical dynamic coordinates of the commodities to obtain the dynamic price curve of each commodity within the historical period.

3. The method for supervising commodity operation strategies based on big data according to claim 1, characterized in that, The calculation of the price-representative slope and sales-representative slope for each price change event corresponding to each factor category based on the changed data set includes: Create a product price change coordinate system and a product sales change coordinate system. The X-axis of the product price change coordinate system and the product sales change coordinate system are different time points. The Y-axis of the product price change coordinate system contains product price data in different units around it. The Y-axis of the product sales change coordinate system contains product sales data in different units. The commodity price data in the variable data set are imported into the commodity price change coordinate according to the time nodes to obtain multiple commodity factor price curves; The product sales data in the variable data set are imported into the product sales change coordinate according to the time nodes to obtain multiple product factor sales curves. The price curves and sales curves of the multiple product factors are analyzed to obtain the price-representative slope of each product factor price curve and the sales-representative slope of each product factor sales curve.

4. The method for supervising commodity operation strategies based on big data according to claim 2, characterized in that, The supervised prediction of the price-representing slope and the sales-representing slope to obtain the predicted price-representing slope and the predicted sales-representing slope for each factor category of each product within a preset future time period includes: Based on the time series length and the factor category, the price representative slope and the sales representative slope are organized to obtain the commodity slope matrix data; By performing basic data distribution exploration on the commodity slope matrix data, the relative periodicity of the slope corresponding to each factor category is obtained; The time period length is determined based on the relative periodicity of the slope, and the commodity slope matrix data is processed by supervised time series data based on the time period length. The processed commodity slope matrix data is then input into a preset model to perform slope data extrapolation, thereby obtaining the price-representing predicted slope and sales-representing predicted slope for each factor category of each commodity within a preset time period in the future.

5. The method for supervising commodity operation strategies based on big data according to claim 3, characterized in that, The step of performing curve waveform analysis on the price curves and sales curves of the multiple product factors to obtain the price-representative slope of each product factor price curve and the sales-representative slope of each product factor sales curve includes: Determine whether there are any abnormal points of increase or decrease in the price curve and sales curve of each commodity factor. If so, define the abnormal points of increase or decrease as interference points and determine whether the interference points in the price curve and sales curve of each commodity factor are unique. If the interference point is a unique interference point and the interference point is located on the commodity factor price curve, then determine the interference price data corresponding to the interference point, the initial price data corresponding to the initial point of the commodity factor price curve, and the termination price data corresponding to the termination point of the commodity factor price curve. Based on the interference price data and the initial price data, determine the first price fluctuation data and the first price fluctuation period. Based on the interference price data and the termination price data, determine the second price fluctuation data and the second price fluctuation period. Calculate the ratio of the first price fluctuation data to the first price fluctuation period and the ratio of the second price fluctuation data to the second price fluctuation period to obtain the first price slope corresponding to the first price fluctuation data and the second price slope corresponding to the second price fluctuation data. The first price slope and the second price slope are integrated and calculated according to the proportional relationship between the first price fluctuation period and the second price fluctuation period to obtain the price representative slope; If the interference point is a unique interference point and the interference point is located on the product factor sales curve, then determine the interference sales data corresponding to the interference point, the initial sales data corresponding to the initial point of the product factor sales curve, and the termination sales data corresponding to the termination point of the product factor sales curve. Based on the interference sales data and the initial sales data, determine the first sales fluctuation data and the first sales fluctuation period. Based on the interference sales data and the termination sales data, determine the second sales fluctuation data and the second sales fluctuation period. Calculate the ratio of the first sales fluctuation data to the first sales fluctuation period and the ratio of the second sales fluctuation data to the second sales fluctuation period to obtain the first sales slope corresponding to the first sales fluctuation data and the second sales slope corresponding to the second sales fluctuation data. The first sales slope and the second sales slope are integrated and calculated according to the proportional relationship between the first sales fluctuation period and the second sales fluctuation period to obtain the sales representative slope.

6. The method for supervising commodity operation strategies based on big data according to claim 5, characterized in that, Determining whether the interference points in the price curve and sales curve of each commodity factor are unique includes: If the interference point is not the only interference point and the interference point is located on the commodity factor price curve, then the interference points are numbered according to the time sequence, and the interference price data corresponding to each interference point, the initial price data corresponding to the initial point of the commodity factor price curve, and the termination price data corresponding to the termination point of the commodity factor price curve are determined. Based on the adjacency characteristics between interference points and the interference price data, the first price fluctuation data and the first price fluctuation period between adjacent interference points are determined. Based on the initial price data and the interference price data corresponding to the first interference point, the second price fluctuation data and the second price fluctuation period are determined. Based on the termination price data and the interference price data corresponding to the Nth interference point, the third price fluctuation data and the third price fluctuation data are determined. The ratio of the first price fluctuation data to the first price fluctuation period, the ratio of the second price fluctuation data to the second price fluctuation period, and the ratio of the third price fluctuation data to the third price fluctuation period are calculated respectively to obtain the first price slope corresponding to the first price fluctuation data, the second price slope corresponding to the second price fluctuation data, and the third price slope corresponding to the third price fluctuation data. N is the total number of interference points. The first price slope, the second price slope, and the third price slope are integrated and calculated according to the proportional relationship between the first price fluctuation period, the second price fluctuation period, and the third price fluctuation period to obtain the price representative slope; If the interference point is not the only interference point and the interference point is located on the product factor sales curve, then the interference points are numbered according to the time sequence, and the interference sales data corresponding to each interference point, the initial sales data corresponding to the initial point of the product factor sales curve, and the termination sales data corresponding to the termination point of the product factor sales curve are determined. Based on the adjacency characteristics between interference points and the interference sales data, the first sales fluctuation data and the first sales fluctuation period between adjacent interference points are determined. Based on the initial sales data and the interference sales data corresponding to the first interference point, the second sales fluctuation data and the second sales fluctuation period are determined. Based on the termination sales data and the interference sales data corresponding to the Mth interference point, the third sales fluctuation data and the third sales fluctuation data are determined. The ratio of the first sales fluctuation data to the first sales fluctuation period, the ratio of the second sales fluctuation data to the second sales fluctuation period, and the ratio of the third sales fluctuation data to the third sales fluctuation period are calculated respectively to obtain the first sales slope corresponding to the first sales fluctuation data, the second sales slope corresponding to the second sales fluctuation data, and the third sales slope corresponding to the third sales fluctuation data. M is the total number of interference points. The first sales slope, the second sales slope, and the third sales slope are integrated and calculated according to the proportional relationship between the first sales fluctuation period, the second sales fluctuation period, and the third sales fluctuation period to obtain the representative sales slope.

7. A big data-based commodity operation strategy monitoring system, characterized in that, include: The information collection module is used to collect historical commodity supply information and historical commodity price data within a historical period, as well as information on changes in commodity operations within a future preset time period. The curve construction module is used to construct a correlation curve between the historical commodity supply information and the historical commodity price data to obtain the dynamic price curve of each commodity in the historical period. The event determination module is used to determine the event time node and price fluctuation data of the price change event based on the commodity price dynamic curve. The information retrieval module is used to retrieve the historical commodity supply information based on the event time node to obtain commodity change information; The predictive analysis module is used to manage and predict the price fluctuation data and the product change information based on the operational change information, so as to obtain the future product sales volume and future product pricing within a future time period. When the predictive analysis module performs management and predictive analysis on the price fluctuation data and the product change information based on the operational change information to obtain future product sales volume and future product pricing within a future time period, it is specifically used for: Based on the commodity change information, determine the price change factors that caused the price change event and the commodity sales volume at different time points after the price change event, and classify the price change factors into factor categories to obtain the change empty set of different factor categories. The price fluctuation data and the sales volume of the goods are added to the change empty set according to the time node of occurrence, respectively, to obtain the change data set of different factor categories; Based on the aforementioned set of changing data, calculate the price-representing slope and sales-representing slope for each price change event corresponding to each factor category; Supervised prediction is performed on the price-representing slope and the sales-representing slope to obtain the price-representing prediction slope and sales-representing prediction slope for each factor category of each product within a preset future time period. Based on the operational change information, determine the products to be changed in the future time period and the categories of change factors for the products to be changed, and screen the products to be changed and the products in the product change information to obtain the product price slope and product sales slope corresponding to each category of the products to be changed; The change factor category is matched with the factor category to obtain the target product price slope and target product sales slope corresponding to the change factor category; Determine whether the changed product is still on sale within the current time period. If it is still on sale, determine the current product price and the current product sales volume within the preset time period. Determine the future product pricing within a future time period based on the current product price and the target product price slope; The future sales volume of the product within a future time period is determined based on the current sales volume of the product and the slope of the target product sales volume.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; Memory; At least one application, wherein the at least one application is stored in memory and configured to be executed by at least one processor, the at least one application being configured to: execute a big data-based commodity operation strategy monitoring method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, include: The computer program is stored and can be loaded by a processor and executed as described in any one of claims 1-6, which is a big data-based commodity operation strategy monitoring method.

Images