Real-time prediction and anomaly detection method for sales data of electric transmission equipment

Abstract

The invention provides a real-time prediction and anomaly detection method for sales data of electric transmission equipment, and relates to the technical field of big data processing. The method comprises the steps of collecting historical periodic sales data of target equipment, and performing sales parameter correlation analysis for periodic influence to form sales change feature data; acquiring sales data of the current sales cycle, and performing prediction analysis in combination with the sales change feature data to form sales real-time prediction data; and obtaining real-time sales data, and carrying out anomaly comparison analysis in combination with the sales real-time prediction data to form sales anomaly detection result data. According to the method, the prediction and real-time early warning of the current sales condition are realized by reasonably analyzing the sales data.

Description

Technical Field

[0001] The present invention relates to the field of big data processing technology, and in particular to a real-time prediction and anomaly detection method for sales data of electric transmission equipment. Background Art

[0002] Electrical transmission equipment is categorized into various subcategories based on its purpose, performance, and other factors. Due to its capabilities and widespread application in modern industry, the demand for electrical transmission equipment is enormous. Like the sale of other products, the sales of electrical transmission equipment are influenced by market demand, resulting in fluctuations in both price and volume. For businesses in particular, sales performance is closely linked to market fluctuations.

[0003] Due to factors such as the category and sales scope of the electrical transmission equipment sold by enterprises, the sales of electrical transmission equipment have gradually formed a regularity in the enterprise's operations. In order to ensure the normal operation of the enterprise, it is necessary to reasonably control the operation and sales of the enterprise's electrical transmission equipment, which is conducive to improving the enterprise's ability to resist operational risks.

[0004] Therefore, it is an urgent problem to design a real-time prediction and anomaly detection method for electrical transmission equipment sales data, and to achieve an estimate of the current sales situation and real-time warning through reasonable analysis of sales data. Summary of the Invention

[0005] The purpose of the present invention is to provide a real-time prediction and anomaly detection method for sales data of electrical transmission equipment. By obtaining sales data of the target electrical transmission equipment in multiple historical periods and conducting correlation analysis on sales volume, sales price and sales cycle, the correlation characteristic information of sales volume and sales price with sales time characteristics is determined. In this way, when analyzing the real-time sales data, the real-time sales volume can be predicted based on the corresponding period of the acquired real-time sales data in the sales cycle, and reasonable prediction data can be obtained for comparative analysis with the actual sales volume to determine whether the current sales situation conforms to the big data law of market changes. On the one hand, the rationality of the sales data is verified and tested, and on the other hand, data reference can be provided for the company's sales policy in a timely manner, which is conducive to guiding the company to carry out more reasonable and effective sales business.

[0006] In a first aspect, the present invention provides a real-time prediction and anomaly detection method for sales data of electric transmission equipment, including: collecting historical period sales data of the target equipment, conducting correlation analysis on sales parameters affected by the period, and forming sales change characteristic data; obtaining sales data of the current sales period, and performing prediction analysis in combination with the sales change characteristic data to form real-time sales prediction data; obtaining real-time sales data, and performing anomaly comparative analysis in combination with the real-time sales prediction data to form sales anomaly detection result data.

[0007] In the present invention, the method obtains sales data of the target electrical transmission equipment over multiple historical periods to conduct correlation analysis on sales volume, sales price and sales cycle, and then determines the correlation characteristic information of sales volume and sales price with sales time characteristics. In this way, when analyzing real-time sales data, the real-time sales volume can be predicted based on the corresponding period of the acquired real-time sales data in the sales cycle, and reasonable predicted data can be obtained for comparative analysis with the actual sales volume to determine whether the current sales situation conforms to the big data law of market changes. On the one hand, the rationality of the sales data is verified and tested, and on the other hand, data reference can be provided for the company's sales policy in a timely manner, which is conducive to guiding the company to carry out more reasonable and effective sales business.

[0008] As a possible implementation method, historical period sales data of the target device is collected, and sales parameter correlation analysis for periodic impact is performed to form sales change characteristic data, including: collecting historical sales data of the target device in multiple historical periods, and performing period year-on-year parameter correlation analysis based on sensitivity to form sales parameter same period year-on-year correlation characteristic information; based on the sales parameter same period year-on-year correlation characteristic information, performing period month-on-month parameter correlation analysis based on sensitivity in combination with historical sales data to form sales parameter same period change characteristic information; and gathering sales parameter same period change characteristic information of different periods in the historical period to form sales change characteristic data.

[0009] In the present invention, in order to obtain the correlation characteristics between the sales cycle, sales volume and sales price, it is necessary to perform a regularity analysis on the collected historical sales data in the sales cycle. It should be noted here that for the extraction of the correlation characteristics between sales volume and sales price in the sales cycle, the usual way is to perform a correlation analysis on the changes in the sales volume and sales price data of each historical cycle over the entire cycle, and then obtain the change characteristic relationship between sales volume and sales price over the entire sales cycle. The results obtained by this analysis method can only predict the changing relationship between sales volume and sales price in a stable market environment within the sales cycle, and cannot achieve the prediction of the changing relationship between sales volume and sales price in an unstable market, such as sudden changes in market conditions caused by sudden policy guidance, lack or increase of upstream raw materials, etc. Based on this, the present application analyzes the correlation between the sales volume and sales price of the target equipment during the sales cycle, taking into account the parameter changes caused by the impact of sudden changes in market conditions. The correlation analysis of the three starts from two aspects. On the one hand, it is different from the conventional relationship analysis method. The correlation analysis of the change in sales volume and the change in sales price during the sales cycle is adopted. This can accurately grasp the correlation between the change in sales parameters, and then extract the correlation characteristics of the changes in sales parameters caused by various market conditions, thereby increasing the scope of application of the correlation analysis results. On the other hand, considering that the conventional correlation analysis forms a relationship between the change in sales volume and sales price over the entire sales cycle, this relationship is relatively rough. Especially for certain electrical transmission equipment with obvious cyclical change characteristics, if the entire sales cycle is used as the time reference parameter, the parameter correlation of the period with good sales will be weakened due to the large difference in sales conditions in each period within the cycle, and the parameter correlation of the period with poor sales will be enhanced. Therefore, the present application considers using different sales periods within the sales cycle as the unit time for correlation analysis, and conducts year-on-year correlation analysis of the horizontal data on the sales period and month-on-month correlation analysis of the vertical data on the sales period, thereby forming more accurate sales change characteristic data.

[0010] As a possible implementation method, historical sales data of the target device in multiple historical periods is collected, and sensitivity-based period year-on-year parameter correlation analysis is performed to form sales parameter same period year-on-year correlation characteristic information, including: according to the historical sales data in different historical periods, respectively obtaining the period historical sales volume and period historical sales price corresponding to different sales periods in the period; aggregating the period historical sales volume and period historical sales price corresponding to the same sales period in different historical periods to form historical sales data for the same period; for different historical sales data for the same period, the corresponding period historical sales prices are sorted in ascending order with reference to the period historical sales price to form corresponding historical sales sequence data for the same period; for different historical sales sequence data for the same period, a sensitivity-based change quantity characteristic analysis is performed to form corresponding sales parameter same period year-on-year correlation characteristic information.

[0011] In the present invention, the change in sales volume and the change in sales price are analyzed year-on-year in terms of correlation over the sales period. First, a reference value for the change is determined, i.e., reasonable data on the change in sales volume and sales price over the same period is collected. Here, the sales volume and sales price under the same sales period in different sales cycles are arranged in order with numerical values ​​as reference to form sequential data, and then a reasonable reference benchmark is obtained to form the change data. It should be noted that the sales period within the sales cycle can be set according to the actual sales situation of the target device to ensure a reasonable division of the sales period. As long as the period division fully considers the large changes in sales volume caused by the change in sales price, it is advisable. Of course, the correlation feature analysis performed on the obtained change data is mainly to determine the relationship between the change in sales volume and the change in sales price. Due to the characteristics of big data, it is impossible to achieve the correlation feature relationship formed to accurately connect the historical data of each period. Therefore, the extraction of the correlation feature relationship with the help of sensitivity is used to determine whether it has reached the preset accuracy to obtain reasonable feature information.

[0012] As a possible implementation method, a sensitivity-based change characteristic analysis is performed on different historical sales sequence data of the same period to form the corresponding sales parameter year-on-year correlation characteristic information of the same period, including: according to the historical sales sequence data of the same period, the smallest period historical sales price is determined as the benchmark price of the same period, and the historical sales volume of the period corresponding to the benchmark price of the same period is determined as the benchmark sales volume of the same period; the sales price difference of the historical sales prices of the remaining different periods in the historical sales sequence data of the same period relative to the benchmark price of the same period is obtained. And the sales difference between the historical sales volume of other different periods in the historical sales sequence data of the same period and the benchmark sales volume of the same period , i represents the amount sequence number of historical sales prices in the same period except the benchmark price in the same period in the historical sales sequence data; set the year-on-year change matching sensitivity , the difference in sales price during the same period Sales difference with the same period Fit the change relationship to form the sales parameter corresponding to the historical sales sequence data of the same period and the same period year-on-year correlation characteristic relationship , where the sales parameter year-on-year correlation characteristic relationship satisfies any sales price difference in the same period The sales difference determined by the characteristic relationship is the same as the corresponding sales difference in the same period The difference is not greater than the year-on-year change matching sensitivity , k represents the number of different sales periods; obtain the sales parameters corresponding to the sales period and the year-on-year correlation characteristic relationship formula And the corresponding sales price difference range for the same period Sales difference range with the same period , forming the corresponding sales parameters’ year-on-year correlation characteristic information during the same period.

[0013] In the present invention, after sorting the sales data of the same sales period in different historical cycles, the correlation characteristic analysis of the change amount is first performed with the minimum value of the formed sequence data as the benchmark data. It is advisable to select either sales volume or sales price as the sequence minimum value. This application uses sales price as a reference for sorting, so the minimum sales price is selected as the benchmark, and the sales volume corresponding to the minimum sales price is used as the benchmark for sales volume to ensure the correlation between the sales volume change data and the sales price change data. With the benchmark value as a reference, the relative change amount of sales volume and sales price corresponding to other same sales periods is obtained, and then the relationship data between the relative change amounts is formed. The relationship between the sales change amount and the sales change price in the corresponding sales period is determined by performing fitting analysis. Here, the expression form of the characteristic relationship formula and the corresponding power number can be determined according to the actual situation's demand for accurate characteristic information. As long as the unknown quantity parameter established does not exceed the data volume and a clear relationship formula can be formed, it is advisable. Furthermore, considering that the characteristic relationship is formed through big data analysis using data on sales changes over the same sales period, it is considered fitted data. Therefore, there is a degree of predictive accuracy regarding the relationship between sales change and sales price changes in the original data. This accuracy is limited here by the year-on-year change matching sensitivity. Specifically, the difference between the sales volume change data obtained after the extracted sales price change data is incorporated into the characteristic relationship, and the corresponding historical actual sales volume change data, is used to determine the accuracy of the fitted characteristic relationship. The year-on-year change matching sensitivity can be set based on actual circumstances.

[0014] As a possible implementation method, based on the year-on-year correlation characteristic information of sales parameters in the same period, sensitivity-based period-on-period parameter correlation analysis is performed in combination with historical sales data to form characteristic information of sales parameter changes in the same period, including: determining the sales period corresponding to the year-on-year correlation characteristic information of sales parameters in the same period as the month-on-month target period, obtaining the period historical sales price and period historical sales volume corresponding to the sales period that is located before the month-on-month target period in different historical periods; determining the month-on-month period sales price difference corresponding to different historical periods based on the period historical sales price and period historical sales volume corresponding to the month-on-month target period in different historical periods and the period historical sales price and period historical sales volume corresponding to the sales period before the month-on-month target period. Sales difference between the same period ; Based on the month-on-month sales price difference corresponding to different historical periods Sales difference between the same period , the correlation characteristic relationship of sales parameters in the same period is The difference between the sales price during the same period Sales difference with the same period Conduct month-on-month sensitivity analysis of the target to form characteristic information on changes in sales parameters corresponding to the sales period.

[0015] In the present invention, it is understood that the year-on-year characteristic relationship established based on sales parameter data of the same sales period in different historical cycles can accurately and reasonably reflect the correlation characteristics of the change in sales parameters of the target device during that period. It is a manifestation of the characteristic properties of a fixed period in the time parameter. However, due to factors such as equipment backlogs and the impact of previous market conditions on the current market, it is not possible to fully accurately map historical data when performing year-on-year characteristic relationship analysis. This is also the data characteristic exhibited by big data. After further refining the characteristic relationship through year-on-year change matching sensitivity, there is still a certain gap between the relationship and the accurate mapping parameter change value. This gap can be further reduced by extracting the characteristics of the sales data in adjacent sales periods. For the month-on-month characteristic analysis, it is still necessary to obtain the corresponding month-on-month change data. Here, the sales data of the adjacent previous sales period has the greatest impact on the year-on-year characteristic relationship to be optimized, and the longer the sales period, the greater this impact. After obtaining sales data from adjacent sales periods, we compare it with the current sales period's sales data to obtain the corresponding month-over-month sales change data. This data serves as the basis for month-over-month analysis to optimize the year-over-year characteristic relationship. Understandably, given the discrete nature of the collected sales data and the characteristics of big data, the degree to which month-over-month analysis optimizes the year-over-year characteristic relationship is merely a closer approximation of the sales volume change data predicted by the relationship and the actual historically mapped change data. Optimization cannot completely eliminate this discrepancy. During optimization, we limit this approximation trend by determining a reasonable sensitivity to achieve the desired optimization effect.

[0016] As a possible implementation method, the sales price difference during the corresponding period of different historical periods is Sales difference between the same period , the correlation characteristic relationship of sales parameters in the same period is The difference between the sales price during the same period Sales difference with the same period The sensitivity of the target is analyzed month-on-month to form the corresponding sales parameters of the sales period, including: for different sales periods, according to the corresponding sales price difference of all month-on-month periods Sales difference between the same period , the correlation characteristic relationship of sales parameters in the same period is Targeting the sales price difference during the same period Sales difference with the same period Fitting analysis is used to form a characteristic relationship between sales parameters during the same period , and the characteristic relationship of sales parameters changing in the same period is Satisfy: For any sales price difference during the same period The sales difference determined by the characteristic relationship is the same as the corresponding sales difference in the same period The difference is not greater than the month-on-month change matching sensitivity ,in: , It is a month-on-month difference adjustment type, and the sales price difference between any month-on-month period is adjusted. The month-on-month sales difference formed by the month-on-month difference adjustment formula is the same as the corresponding month-on-month period sales difference. The difference does not exceed the month-on-month matching sensitivity; obtain the sales parameter corresponding to the sales period and the change characteristic relationship of the same period , the corresponding sales price difference range for the same period , the corresponding sales difference range for the same period And the corresponding sales price difference range during the month-on-month period and the sales difference range during the same period , forming the corresponding sales parameter change characteristic information during the same period.

[0017] In the present invention, the month-on-month change data is used to optimize the year-on-year characteristic relationship formula, mainly by determining the influence or adjustment degree of the month-on-month change data on the relationship formula, to see whether the predicted sales change data formed by the characteristic relationship formula after adding the influence relationship formed by the month-on-month change data is closer to the actual change data collected historically. Here, the parameter quantity and parameter quantity relationship of the month-on-month difference adjustment formula can be set according to actual conditions, as long as the formed adjustment formula can further achieve the closeness between the predicted data and the actual data, it is desirable. The month-on-month change matching sensitivity can be set according to actual needs. Of course, it is clear that the month-on-month change sensitivity is a smaller value than the year-on-year change sensitivity.

[0018] As a possible implementation method, the sales data of the current sales cycle is obtained, and the sales change characteristic data is combined for forecast analysis to form real-time sales forecast data, including: obtaining the current sales volume of the current sales cycle and current sales price and early sales and pre-sale price ; According to the sales period corresponding to the data collected in the current sales cycle, determine the corresponding sales parameter change characteristic information during the same period; according to the current sales volume , current sales price , benchmark sales volume and benchmark price for the same period, respectively determine the corresponding current sales difference and current sales price difference; based on the current sales volume , current sales price , early sales volume and the initial sales price , respectively determine the current period month-on-month sales difference and the current period month-on-month sales price difference; combine the current period sales difference, the current period sales price difference, the current period month-on-month sales difference and the current period month-on-month sales price difference, according to the corresponding sales parameter change characteristic relationship formula , determine the current forecast sales change.

[0019] In the present invention, after obtaining the characteristic relationship between sales changes, the predicted sales change for the current sales period can be predicted based on the real-time data of the current sales period. It should be noted that since the characteristic relationship is a continuous relationship, the current sales data can be from the current sales period that has not yet ended or the most recent sales period that has ended. By analyzing the data information of the change, the corresponding predicted change can be obtained, and this analysis can ensure the timeliness of data analysis.

[0020] As a possible implementation method, real-time sales data is obtained and combined with real-time sales forecast data for abnormal comparative analysis to form sales abnormality detection result data, including: according to the current sales difference, current sales price difference, current month-on-month sales difference and current month-on-month sales price difference, combined with the corresponding sales price difference range for the same period , sales difference range for the same period , Sales price difference range during the month-on-month period and the sales difference range during the month-on-month period , conduct data applicability detection and analysis to form applicability detection and analysis results; based on the applicability detection and analysis results, conduct sales anomaly detection and analysis on the current sales difference to form sales volume anomaly detection results.

[0021] In the present invention, it is understood that, for the characteristic relationship formula, since it is formed based on the fitting of historical discrete data, the range of its parameters should also be the range limited by the historical discrete data. Analyzing the characteristic relationship formula with parameters outside this range may not necessarily guarantee the accuracy of the analysis results. Therefore, this application first needs to perform a suitability test on the acquired real-time variation data, and then perform an abnormality detection and analysis on the predicted variation data based on the test results to ensure that the sales changes can be controlled in real time and reasonable sales policy adjustments can be made.

[0022] As a possible implementation method, based on the current sales difference, current sales price difference, current month-on-month sales difference and current month-on-month sales price difference, combined with the corresponding sales price difference range for the same period , sales difference range for the same period , Sales price difference range during the month-on-month period and the sales difference range during the month-on-month period , the current sales difference, the current sales difference, the current sales difference and the current sales difference, if the current sales difference belongs to the same period sales price difference range , the current sales difference belongs to the same period sales difference range , the current sales difference belongs to the same period sales difference range , the current sales difference belongs to the same period sales difference range , the current sales difference belongs to the same period sales difference range

[0023] In the application, the adaptability of the data must ensure that all the obtained real-time change data is within the range defined by the characteristic relationship, so as to ensure the accuracy and reliability of the predicted change data obtained by the characteristic relationship.

[0024] As a possible implementation mode, according to the adaptability detection analysis result, the current sales difference is detected and analyzed, and the sales quantity abnormality detection result is formed, including: when the adaptability detection analysis result is data adaptation information, the corresponding current predicted sales change quantity and the current sales difference are analyzed as follows: if the difference between the current predicted sales change quantity and the current sales difference exceeds the sales quantity prediction deviation threshold, the sales quantity abnormality information is formed; if the difference between the current predicted sales change quantity and the current sales difference exceeds the sales quantity prediction deviation threshold, the sales quantity normal information is formed.

[0025] In the application, it can be understood that even the predicted change data will be affected by other small factors other than the actual sales price, sales quantity and historical period, resulting in a certain reasonable deviation of the data. Therefore, when performing abnormality detection analysis, the sales quantity prediction deviation threshold is used to control the allowable deviation value, so as to ensure the rationality and accuracy of the analysis result. The sales quantity prediction deviation threshold can be set according to the actual situation, or can be determined based on big data analysis.

[0026] The real-time prediction and abnormality detection method for the sales data of the electric drive equipment provided by the application has the following beneficial effects: This method obtains sales data of the target electrical transmission equipment over multiple historical periods to conduct correlation analysis on sales volume, sales price and sales cycle, and then determines the correlation characteristic information of sales volume and sales price with sales time characteristics. In this way, when analyzing real-time sales data, the real-time sales volume can be predicted based on the corresponding period of the acquired real-time sales data in the sales cycle, and reasonable predicted data can be obtained for comparative analysis with the actual sales volume to determine whether the current sales situation conforms to the big data law of market changes. On the one hand, the rationality of the sales data can be verified and tested, and on the other hand, data reference can be provided for the company's sales policy in a timely manner, which is conducive to guiding the company to carry out more reasonable and effective sales operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments of the present invention. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 A step diagram of a method for real-time prediction and anomaly detection of sales data of electric transmission equipment provided by an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a real-time prediction and anomaly detection system for electric transmission equipment sales data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present invention will be described below with reference to the accompanying drawings in the embodiments of the present invention.

[0030] Electrical transmission equipment is categorized into various subcategories based on its purpose, performance, and other factors. Due to its capabilities and widespread application in modern industry, the demand for electrical transmission equipment is enormous. Like the sale of other products, the sales of electrical transmission equipment are influenced by market demand, resulting in fluctuations in both price and volume. For businesses in particular, sales performance is closely linked to market fluctuations.

[0031] Due to factors such as the category and sales scope of the electrical transmission equipment sold by enterprises, the sales of electrical transmission equipment have gradually formed a regularity in the enterprise's operations. In order to ensure the normal operation of the enterprise, it is necessary to reasonably control the operation and sales of the enterprise's electrical transmission equipment, which is conducive to improving the enterprise's ability to resist operational risks.

[0032] refer to Figure 1~Figure 2 , an embodiment of the present invention provides a real-time prediction and anomaly detection method for sales data of electric transmission equipment. The method obtains sales data of target electric transmission equipment over multiple historical periods to perform correlation analysis on sales volume, sales price and sales cycle, and then determines the correlation characteristic information of sales volume and sales price with sales time characteristics. In this way, when analyzing real-time sales data, the real-time sales volume can be predicted based on the corresponding period of the acquired real-time sales data in the sales cycle, and reasonable prediction data can be obtained for comparative analysis with the actual sales volume to determine whether the current sales situation conforms to the big data law of market changes. On the one hand, the rationality of the sales data is verified and tested, and on the other hand, data reference can be provided for the company's sales policy in a timely manner, which is conducive to guiding the company to carry out more reasonable and effective sales business.

[0033] The real-time prediction and anomaly detection method for electrical transmission equipment sales data specifically includes the following steps: S1: Collect historical period sales data of the target device, conduct correlation analysis on sales parameters affected by the period, and form sales change characteristic data.

[0034] Collect historical periodic sales data of the target device, conduct correlation analysis of sales parameters for periodic impact, and form sales change characteristic data, including: collecting historical sales data of the target device in multiple historical periods, and conducting sensitivity-based period-on-year parameter correlation analysis to form sales parameter same-period year-on-year correlation characteristic information; based on the sales parameter same-period year-on-year correlation characteristic information, conduct sensitivity-based period-on-period parameter correlation analysis in combination with historical sales data to form sales parameter same-period change characteristic information; gather sales parameter same-period change characteristic information of different periods in the historical period to form sales change characteristic data.

[0035] To obtain the correlation characteristics between sales cycle, sales volume and sales price, it is necessary to analyze the regularity of the collected historical sales data in the sales cycle. It should be noted here that for the extraction of the correlation characteristics of sales volume and sales price in the sales cycle, the usual method is to perform a correlation analysis on the changes in the sales volume and sales price data of each historical cycle over the entire cycle, and then obtain the change characteristic relationship between sales volume and sales price over the entire sales cycle. The results obtained by this analysis method can only predict the changing relationship between sales volume and sales price within the sales cycle under a stable market environment, and cannot predict the changing relationship between sales volume and sales price within the sales cycle under unstable market conditions, such as sudden changes in market conditions caused by sudden policy guidance, lack or increase of upstream raw materials, etc. Based on this, the present application analyzes the correlation between the sales volume and sales price of the target equipment during the sales cycle, taking into account the parameter changes caused by the impact of sudden changes in market conditions. The correlation analysis of the three starts from two aspects. On the one hand, it is different from the conventional relationship analysis method. The correlation analysis of the change in sales volume and the change in sales price during the sales cycle is adopted. This can accurately grasp the correlation between the change in sales parameters, and then extract the correlation characteristics of the changes in sales parameters caused by various market conditions, thereby increasing the scope of application of the correlation analysis results. On the other hand, considering that the conventional correlation analysis forms a relationship between the change in sales volume and sales price over the entire sales cycle, this relationship is relatively rough. Especially for certain electrical transmission equipment with obvious cyclical change characteristics, if the entire sales cycle is used as the time reference parameter, the parameter correlation of the period with good sales will be weakened due to the large difference in sales conditions in each period within the cycle, and the parameter correlation of the period with poor sales will be enhanced. Therefore, the present application considers using different sales periods within the sales cycle as the unit time for correlation analysis, and conducts year-on-year correlation analysis of the horizontal data on the sales period and month-on-month correlation analysis of the vertical data on the sales period, thereby forming more accurate sales change characteristic data.

[0036] Collect historical sales data of target equipment in multiple historical periods, and conduct sensitivity-based period year-on-year parameter correlation analysis to form sales parameter same period year-on-year correlation characteristic information, including: according to the historical sales data in different historical periods, respectively obtain the period historical sales volume and period historical sales price corresponding to different sales periods in the period; aggregate the period historical sales volume and period historical sales price corresponding to the same sales period in different historical periods to form the historical sales data for the same period; for different historical sales data for the same period, use the period historical sales price as a reference to sort the corresponding period historical sales prices in ascending order to form the corresponding historical sales sequence data for the same period; for different historical sales sequence data for the same period, conduct sensitivity-based change quantity characteristic analysis to form the corresponding sales parameter same period year-on-year correlation characteristic information.

[0037] To conduct a year-on-year correlation analysis of sales volume changes and sales price changes over sales periods, it is first necessary to determine a reference for the changes, namely, to reasonably collect data on sales volume and sales price changes over the same period. Here, the sales volume and sales price data for the same sales period across different sales cycles are arranged in numerical order, forming sequential data. A reasonable reference benchmark is then obtained to form the change data. It should be noted that the sales periods within a sales cycle can be set based on the actual sales performance of the target device to ensure a reasonable division of sales periods. Any period division that fully considers the significant changes in sales volume caused by changes in sales price is acceptable. Of course, the correlation feature analysis performed on the acquired change data primarily aims to determine the relationship between sales volume changes and sales price changes. Due to the characteristics of big data, it is impossible to accurately link the resulting correlation feature relationships across each historical period. Therefore, sensitivity is used to determine whether the correlation feature relationship extraction achieves a predetermined level of accuracy to obtain reasonable feature information.

[0038] For different historical sales sequence data of the same period, a sensitivity-based change characteristic analysis is performed to form the corresponding sales parameter year-on-year correlation characteristic information of the same period, including: according to the historical sales sequence data of the same period, the smallest period historical sales price is determined as the benchmark price of the same period, and the historical sales volume of the period corresponding to the benchmark price of the same period is determined as the benchmark sales volume of the same period; the same period sales price difference of the historical sales prices of the remaining different periods in the historical sales sequence data of the same period relative to the benchmark price of the same period is obtained. And the sales difference between the historical sales volume of other different periods in the historical sales sequence data of the same period and the benchmark sales volume of the same period , i represents the amount sequence number of historical sales prices in the same period except the benchmark price in the same period in the historical sales sequence data; set the year-on-year change matching sensitivity , the difference in sales price during the same period Sales difference with the same period Fit the change relationship to form the sales parameter corresponding to the historical sales sequence data of the same period and the same period year-on-year correlation characteristic relationship , where the sales parameter year-on-year correlation characteristic relationship satisfies any sales price difference in the same period The sales difference determined by the characteristic relationship is the same as the corresponding sales difference in the same period The difference is not greater than the year-on-year change matching sensitivity , k represents the number of different sales periods; obtain the sales parameters corresponding to the sales period and the year-on-year correlation characteristic relationship formula And the corresponding sales price difference range for the same period Sales difference range with the same period , forming the corresponding sales parameters’ year-on-year correlation characteristic information during the same period.

[0039] After sorting the sales data of the same sales period in different historical cycles, the correlation characteristic analysis of the change amount is first performed with the minimum value of the formed sequence data as the benchmark data. It is advisable to choose either sales volume or sales price as the sequence minimum value. This application uses sales price as a reference for sorting, so the minimum sales price is selected as the benchmark, and the sales volume corresponding to the minimum sales price is used as the benchmark for sales volume to ensure the correlation between sales volume change data and sales price change data. With the benchmark value as a reference, the relative change amount of sales volume and sales price corresponding to other same sales periods is obtained, and then the relationship data between the relative change amounts is formed. The relationship between the sales change amount and the sales change price in the corresponding sales period is determined by fitting analysis. Here, the expression form of the characteristic relationship and the corresponding power number can be determined according to the actual situation's demand for accurate characteristic information. As long as the unknown quantity parameters established do not exceed the data volume and can form a clear relationship, it is advisable. Furthermore, considering that the characteristic relationship is formed through big data analysis using data on sales changes over the same sales period, it is considered fitted data. Therefore, there is a degree of predictive accuracy regarding the relationship between sales change and sales price changes in the original data. This accuracy is limited here by the year-on-year change matching sensitivity. Specifically, the difference between the sales volume change data obtained after the extracted sales price change data is incorporated into the characteristic relationship, and the corresponding historical actual sales volume change data, is used to determine the accuracy of the fitted characteristic relationship. The year-on-year change matching sensitivity can be set based on actual circumstances.

[0040] Based on the year-on-year correlation characteristic information of sales parameters in the same period, sensitivity-based period-on-period parameter correlation analysis is performed in combination with historical sales data to form characteristic information of sales parameter changes in the same period, including: determining the sales period corresponding to the year-on-year correlation characteristic information of sales parameters in the same period as the month-on-month target period, obtaining the period historical sales price and period historical sales volume corresponding to the sales period that is located before the month-on-month target period in different historical periods; determining the month-on-month period sales price difference corresponding to different historical periods based on the period historical sales price and period historical sales volume corresponding to the month-on-month target period in different historical periods and the period historical sales price and period historical sales volume corresponding to the sales period before the month-on-month target period. Sales difference between the same period ; Based on the month-on-month sales price difference corresponding to different historical periods Sales difference between the same period , the correlation characteristic relationship of sales parameters in the same period is The difference between the sales price during the same period Sales difference with the same period Conduct month-on-month sensitivity analysis of the target to form characteristic information on changes in sales parameters corresponding to the sales period.

[0041] It's understandable that the year-over-year characteristic relationship established based on sales parameter data from the same sales period across different historical cycles can accurately and reasonably reflect the correlation characteristics between the sales parameters of the target device during that period, reflecting the characteristic properties of a fixed period in the time parameter. However, due to factors such as equipment backlogs and the impact of previous market conditions on the current market, year-over-year characteristic relationship analysis cannot fully accurately map historical data. This is also a characteristic of big data. Even after further refining the characteristic relationship through year-over-year change matching sensitivity, there is still a certain gap between the relationship and the accurate mapping parameter change value. This gap can be further reduced by extracting features that influence sales data in adjacent sales periods. For the month-over-month characteristic analysis, corresponding month-over-month change data is still required. Here, the sales data from the adjacent previous sales period has the greatest impact on the optimized year-over-year characteristic relationship, and this influence increases with the length of the sales period. After obtaining sales data from adjacent sales periods, we compare it with the current sales period's sales data to obtain the corresponding month-over-month sales change data. This data serves as the basis for month-over-month analysis to optimize the year-over-year characteristic relationship. Understandably, given the discrete nature of the collected sales data and the characteristics of big data, the degree to which month-over-month analysis optimizes the year-over-year characteristic relationship is merely a closer approximation of the sales volume change data predicted by the relationship and the actual historically mapped change data. Optimization cannot completely eliminate this discrepancy. During optimization, we limit this approximation trend by determining a reasonable sensitivity to achieve the desired optimization effect.

[0042] According to the sales price difference during the corresponding period of different historical periods Sales difference between the same period , the correlation characteristic relationship of sales parameters in the same period is The difference between the sales price during the same period Sales difference with the same period The sensitivity of the target is analyzed month-on-month to form the corresponding sales parameters of the sales period, including: for different sales periods, according to the corresponding sales price difference of all month-on-month periods Sales difference between the same period , the correlation characteristic relationship of sales parameters in the same period is Targeting the sales price difference during the same period Sales difference with the same period Fitting analysis is used to form a characteristic relationship between sales parameters changing over the same period. , and the characteristic relationship of sales parameters changing in the same period is Satisfy: For any sales price difference during the same period The sales difference determined by the characteristic relationship is the same as the corresponding sales difference in the same period The difference is not greater than the month-on-month change matching sensitivity ,in: , It is a month-on-month difference adjustment type, and the sales price difference between any month-on-month period is adjusted. The month-on-month sales difference formed by the month-on-month difference adjustment formula is the same as the corresponding month-on-month period sales difference. The difference does not exceed the month-on-month matching sensitivity; obtain the sales parameter corresponding to the sales period and the change characteristic relationship of the same period , the corresponding sales price difference range for the same period , the corresponding sales difference range for the same period And the corresponding sales price difference range during the month-on-month period and the sales difference range during the same period , forming the corresponding sales parameter change characteristic information during the same period.

[0043] Optimizing the year-on-year characteristic relationship using month-on-month change data primarily involves determining its impact or degree of adjustment on the relationship. This is done to determine whether the predicted sales change data, formed by incorporating the influence of the month-on-month change data, is closer to the actual change data collected historically. The parameters and their relationships within the month-on-month difference adjustment formula can be set based on actual circumstances. Any adjustment formula that further approximates the predicted data to actual data is acceptable. The month-on-month change matching sensitivity can be set based on actual needs. Of course, it's clear that the month-on-month change sensitivity is a smaller value than the year-on-year change sensitivity.

[0044] S2: Obtain sales data for the current sales cycle, and perform forecast analysis based on sales change characteristic data to generate real-time sales forecast data.

[0045] Obtain sales data for the current sales cycle and conduct forecast analysis based on sales change characteristic data to form real-time sales forecast data, including: obtaining current sales volume for the current sales cycle and current sales price and early sales and pre-sale price ; According to the sales period corresponding to the data collected in the current sales cycle, determine the corresponding sales parameter change characteristic information during the same period; according to the current sales volume , current sales price , benchmark sales volume and benchmark price for the same period, respectively determine the corresponding current sales difference and current sales price difference; based on the current sales volume , current sales price , early sales volume and the initial sales price , respectively determine the current period month-on-month sales difference and the current period month-on-month sales price difference; combine the current period sales difference, the current period sales price difference, the current period month-on-month sales difference and the current period month-on-month sales price difference, according to the corresponding sales parameter change characteristic relationship formula , determine the current forecast sales change.

[0046] After obtaining the characteristic relationship between sales changes, the predicted sales change for the current sales period can be predicted based on the real-time data from the current sales period. It should be noted that since the characteristic relationship is continuous, the current sales data can be from the current sales period that has not yet ended or the most recent sales period that has ended. By analyzing the data information about the change, the corresponding predicted change can be obtained, ensuring the timeliness of data analysis.

[0047] S3: Obtain real-time sales data and perform anomaly comparative analysis in combination with real-time sales forecast data to generate sales anomaly detection result data.

[0048] Acquire real-time sales data and conduct anomaly comparative analysis in combination with real-time sales forecast data to generate sales anomaly detection result data, including: based on the current sales difference, current sales price difference, current month-on-month sales difference, and current month-on-month sales price difference, combined with the corresponding sales price difference range for the same period , sales difference range for the same period , Sales price difference range during the month-on-month period and the sales difference range during the month-on-month period , conduct data applicability detection and analysis to form applicability detection and analysis results; based on the applicability detection and analysis results, conduct sales anomaly detection and analysis on the current sales difference to form sales volume anomaly detection results.

[0049] It is understandable that for the characteristic relationship formula, since it is formed based on the fitting of historical discrete data, the range of its parameters should also be the range limited by the historical discrete data. Analyzing the characteristic relationship formula with parameters outside this range may not necessarily guarantee the accuracy of the analysis results. Therefore, this application first needs to perform a suitability test on the acquired real-time variation data, and then perform an abnormality detection and analysis on the predicted variation data based on the test results to ensure that the sales changes can be controlled in real time and reasonable sales policy adjustments can be made.

[0050] Based on the current sales difference, current sales price difference, current month-on-month sales difference and current month-on-month sales price difference, combined with the corresponding sales price difference range for the same period , sales difference range for the same period , Sales price difference range during the month-on-month period and the sales difference range during the month-on-month period , conduct data applicability test analysis and form applicability test analysis results, including: the current sales difference, the current sales price difference, the current month-on-month sales difference and the current month-on-month sales price difference, if the current sales difference falls within the sales price difference range of the same period , the current sales price difference falls within the sales volume range of the same period The current period's month-on-month sales difference falls within the range of the month-on-month sales price difference. The current period's month-on-month sales price difference falls within the range of the month-on-month sales difference. , then data adaptability information is formed, otherwise data non-adaptability information is formed.

[0051] The adaptability of data must ensure that all acquired real-time variation data are within the range defined by the characteristic relationship, so as to ensure the accuracy and reliability of the predicted variation data obtained through the characteristic relationship.

[0052] Based on the results of the applicability detection analysis, a sales anomaly detection analysis is performed on the current sales difference to form a sales volume anomaly detection result, including: when the applicability detection analysis result is data adaptation information, the corresponding current forecast sales change and the current sales difference are obtained to perform the following sales volume anomaly detection analysis: if the difference between the current forecast sales change and the current sales difference exceeds the sales volume forecast deviation threshold, sales volume anomaly information is formed; if the difference between the current forecast sales change and the current sales difference exceeds the sales volume forecast deviation threshold, sales volume normal information is formed.

[0053] Understandably, even predicted change data can experience reasonable deviations due to factors other than actual sales price, sales volume, and historical periods, which have less significant impact. Therefore, during anomaly detection analysis, a sales forecast deviation threshold is used to control this permissible deviation to ensure the rationality and accuracy of the analysis results. This sales forecast deviation threshold can be set based on actual conditions or determined based on big data analysis.

[0054] The application further provides a real-time prediction and abnormality detection system for sales data of an electric drive device, comprising: a data acquisition unit configured to acquire historical periodic sales data and real-time sales data of a target device; a feature extraction unit configured to perform correlation analysis on sales parameters affected by a period based on the historical periodic sales data acquired by the data acquisition unit, and form sales change feature data; and a prediction and detection unit configured to perform prediction analysis based on the real-time sales data acquired by the data acquisition unit and the sales change feature data formed by the feature extraction unit, form sales real-time prediction data, and perform abnormality comparison analysis in combination with the sales change feature data, and form sales abnormality detection result data.

[0055] In summary, the electric drive device sales data real-time prediction and abnormality detection method provided by the embodiments of the application has the following beneficial effects: The method performs correlation analysis on sales quantity, sales price and sales period based on the sales data of the target electric drive device in multiple historical periods, and further determines the correlation feature information of the sales quantity and sales price with sales time characteristics. Thus, when analyzing the real-time sales data, the real-time sales quantity can be predicted based on the corresponding period of the sales period of the acquired real-time sales data, reasonable prediction data is obtained, and comparison analysis is performed with the actual sales quantity to determine whether the current sales condition conforms to the big data rule of market changes. On the one hand, the sales data is reasonably verified, and on the other hand, data reference is provided for the sales policy of the enterprise, which is conducive to guiding the enterprise to carry out more reasonable and effective sales business.

[0056] In the embodiments of the present application, the indication can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by a certain information is referred to as to-be-indicated information, and in the specific implementation process, there are many ways to indicate the to-be-indicated information, for example but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, a protocol), thereby reducing the indication overhead to a certain extent. Meanwhile, the common part of each information can be identified and uniformly indicated, so as to reduce the indication overhead caused by separately indicating the same information.

[0057] In addition, the specific indication method can also be various existing indication methods, such as but not limited to the above-mentioned indication methods and various combinations thereof. The specific details of the various indication methods can be referred to the prior art and will not be repeated herein. As can be seen from the above, for example, when it is necessary to indicate multiple information of the same type, there may be a situation where the indication methods for different information are different. In the specific implementation process, the required indication method can be selected according to specific needs. The embodiment of the present application does not limit the selected indication method. In this way, the indication method involved in the embodiment of the present application should be understood to cover various methods that can enable the party to be indicated to obtain the information to be indicated.

[0058] It should be understood that the information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately, and the sending period and / or sending time of these sub-information can be the same or different. The specific sending method is not limited in the embodiments of this application. The sending period and / or sending time of these sub-information can be predefined, for example, predefined according to a protocol, or can be configured by the transmitting device by sending configuration information to the receiving device.

[0059] "Pre-definition" or "pre-configuration" can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in the device, and the embodiments of the present application do not limit the specific implementation method. Among them, "saving" can mean saving in one or more memories. The one or more memories can be set separately or integrated in an encoder or decoder, a processor, or a communication device. The one or more memories can also be partially set separately and partially integrated in a decoder, a processor, or a communication device. The type of memory can be any form of storage medium, and the embodiments of the present application do not limit this.

[0060] The "protocol" involved in the embodiments of the present application may refer to a protocol family in the communication field, a standard protocol with a similar protocol family frame structure, or a related protocol used in future communication systems. The embodiments of the present application do not make specific limitations on this.

[0061] In the embodiments of the present application, descriptions such as "when...", "in the case of...", "if" and "if" all mean that the device will perform corresponding processing under certain objective circumstances. It does not limit the time, nor does it require the device to perform judgment actions when implemented, nor does it mean that there are other limitations.

[0062] In the description of the embodiments of this application, unless otherwise specified, " / " indicates that the associated objects are in an "or" relationship. For example, A / B can mean A or B. "And / or" in the embodiments of this application is merely a description of the associated relationship between the associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, in the description of the embodiments of this application, unless otherwise specified, "multiple" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural. Furthermore, to facilitate the clear description of the technical solutions of the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish between identical or similar items with substantially the same function or effect. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit differences. At the same time, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or design. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0063] It should be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), but may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0064] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of random access memory (RAM) can be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0065] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0066] It should be understood that the term "and / or" as used herein simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B together, or B alone. A and B can be singular or plural. Furthermore, the character " / " as used herein generally indicates an "or" relationship between the associated objects, but it may also indicate an "and / or" relationship. For specific understanding, please refer to the context.

[0067] In this application, "at least one" means one or more, and "plurality" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, "at least one of a, b, or c" can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural.

[0068] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0069] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0070] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0071] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0072] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0073] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0074] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0075] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A real-time prediction and anomaly detection method for electrical transmission equipment sales data, characterized in that: include: Collect historical sales data of target devices, conduct correlation analysis on sales parameters affected by the cycle, and generate sales change characteristic data; Obtain sales data for the current sales cycle, and perform forecast analysis based on the sales change characteristic data to generate real-time sales forecast data; Real-time sales data is obtained, and anomaly comparison analysis is performed in combination with the real-time sales forecast data to form sales anomaly detection result data.

2. The method for real-time prediction and anomaly detection of electric transmission equipment sales data according to claim 1, characterized in that: The process of collecting historical period sales data of the target device and performing correlation analysis on sales parameters affected by the period to form sales change characteristic data includes: Collecting historical sales data of the target device within a plurality of historical periods, and performing sensitivity-based period-on-period parameter correlation analysis to form period-on-period year-on-year correlation feature information of the sales parameters; Based on the year-on-year correlation characteristic information of the sales parameters during the same period, a sensitivity-based period-on-period parameter correlation analysis is performed in combination with the historical sales data to form characteristic information of changes in the sales parameters during the same period; The sales parameter change characteristic information of different periods in the historical period is collected to form the sales change characteristic data.

3. The method for real-time prediction and anomaly detection of electric transmission equipment sales data according to claim 2, characterized in that: The collecting of historical sales data of the target device in the plurality of historical periods and performing sensitivity-based period-on-period parameter correlation analysis to form period-on-period year-on-year correlation feature information of sales parameters include: According to the historical sales data in different historical periods, respectively obtain the period historical sales volume and period historical sales price corresponding to different sales periods in the period; Gather the historical sales volumes and historical sales prices corresponding to the same sales period in different historical cycles to form historical sales data for the same period; For different historical sales data of the same period, the corresponding historical sales prices of the period are sorted in ascending order based on the historical sales prices of the period, to form the corresponding historical sales sequence data of the same period; For different historical sales sequence data of the same period, a sensitivity-based change characteristic analysis is performed to form the corresponding sales parameter year-on-year correlation characteristic information of the same period.

4. The method for real-time prediction and anomaly detection of electric transmission equipment sales data according to claim 3, characterized in that: The sensitivity-based change characteristic analysis is performed on different historical sales sequence data of the same period to form the corresponding year-on-year correlation characteristic information of the sales parameters of the same period, including: According to the historical sales sequence data of the same period, the smallest historical sales price of the period is determined as the benchmark price of the same period, and the historical sales volume of the period corresponding to the benchmark price of the same period is determined as the benchmark sales volume of the same period; Obtain the sales price difference of the other different periods in the historical sales sequence data of the same period relative to the benchmark price of the same period and the sales difference between the historical sales volume of the other different periods in the historical sales sequence data of the same period and the benchmark sales volume of the same period , i represents the amount sequence number of the historical sales price of the period other than the benchmark price of the same period in the historical sales sequence data of the same period; Set the year-on-year change matching sensitivity , the sales price difference during the same period Sales difference with the same period Fit the change relationship to form the sales parameter corresponding to the historical sales sequence data of the same period and the same period year-on-year correlation characteristic relationship , wherein the sales parameter same period year-on-year correlation characteristic relationship formula satisfies any of the same period sales price difference The sales difference determined according to the characteristic relationship is the same as the corresponding sales difference in the same period The difference is no greater than the year-on-year change matching sensitivity , k represents the number of different sales periods; Get the sales parameter corresponding to the sales period and the corresponding year-on-year correlation characteristic relationship formula And the corresponding sales price difference range for the same period Sales difference range with the same period , forming the corresponding year-on-year correlation feature information of the sales parameters in the same period.

5. The method for real-time prediction and anomaly detection of sales data of electric transmission equipment according to claim 4, characterized in that: The method of performing sensitivity-based period-on-period parameter correlation analysis based on the year-on-year correlation characteristic information of the sales parameters in the same period in combination with the historical sales data to form the change characteristic information of the sales parameters in the same period includes: Determine the sales period corresponding to the year-on-year correlation characteristic information of the sales parameter as the month-on-month target period, and obtain the period historical sales price and period historical sales volume corresponding to the sales period that precedes the month-on-month target period in different historical cycles; Determine the month-on-month sales price difference corresponding to the different historical periods based on the historical sales prices and historical sales volumes corresponding to the month-on-month target periods in different historical periods and the historical sales prices and historical sales volumes corresponding to the sales periods before the month-on-month target periods. Sales difference between the same period ; According to the sales price difference during the month-on-month period corresponding to different historical periods Sales difference between the same period , the sales parameters of the same period year-on-year correlation characteristic relationship formula The difference in sales price over the same period The difference between the sales volume and the same period A sensitivity analysis of the target is performed on a month-on-month basis to form characteristic information of changes in the sales parameters corresponding to the sales period.

6. The method for real-time prediction and anomaly detection of electric transmission equipment sales data according to claim 5, characterized in that: The sales price difference during the month-on-month period corresponding to different historical periods Sales difference between the same period , the sales parameters of the same period year-on-year correlation characteristic relationship formula The difference in sales price over the same period The difference between the sales volume and the same period The sensitivity analysis of the target is performed on a month-on-month basis to form characteristic information of the sales parameters corresponding to the sales period during the same period, including: For different sales periods, according to the corresponding sales price difference of all the corresponding period Sales difference between the same period , the sales parameters of the same period year-on-year correlation characteristic relationship formula For the sales price difference of the same period The difference between the sales volume and the same period Fitting analysis is used to form a characteristic relationship between sales parameters changing over the same period. , and the sales parameter change characteristic relationship during the same period is satisfy: For any of the above mentioned sales price differences The sales difference determined according to the characteristic relationship is the same as the corresponding sales difference in the same period The difference is not greater than the month-on-month change matching sensitivity ,in: , It is a month-on-month difference adjustment type, and the sales price difference during any of the said month-on-month periods is adjusted. The month-on-month sales difference formed according to the month-on-month difference adjustment formula is the same as the corresponding month-on-month period sales difference. The difference does not exceed the ring matching sensitivity; Obtain the sales parameter corresponding to the sales period and the corresponding period change characteristic relationship , the corresponding sales price difference range for the same period , the corresponding sales difference range for the same period And the corresponding sales price difference range during the month-on-month period and the sales difference range during the same period , forming the corresponding characteristic information of the sales parameters changing during the same period.

7. The method for real-time prediction and anomaly detection of electric transmission equipment sales data according to claim 6, characterized in that: The acquisition of sales data for the current sales cycle and the combination of the sales change characteristic data for forecast analysis to form real-time sales forecast data include: Get the current sales volume for the current sales cycle and current sales price and early sales and pre-sale price ; Determine, based on the sales period corresponding to the data collected during the current sales cycle, the corresponding sales parameter change characteristic information during the same period; According to the current sales volume , the current sales price , the benchmark sales volume for the same period and the benchmark price for the same period, respectively determining the corresponding current period sales difference and current period sales price difference; According to the current sales volume , the current sales price 、The aforementioned previous sales volume and the initial sales price , respectively determine the current period's month-on-month sales difference and the current period's month-on-month sales price difference; Combined with the current sales price difference, the current month-on-month sales difference and the current month-on-month sales price difference, according to the corresponding sales parameter change characteristic relationship formula , determine the current forecast sales change.

8. The method for real-time prediction and anomaly detection of electric transmission equipment sales data according to claim 7, characterized in that: The real-time sales data is acquired, and anomaly comparison analysis is performed in combination with the real-time sales forecast data to form sales anomaly detection result data, including: According to the current sales difference, the current sales price difference, the current month-on-month sales difference and the current month-on-month sales price difference, combined with the corresponding sales price difference range for the same period 、The sales difference range for the same period , the sales price difference range during the mentioned month-on-month period and the sales variance range for the mentioned month-over-month period , conduct data applicability detection and analysis, and form applicability detection and analysis results; Based on the applicability detection and analysis results, sales anomaly detection and analysis is performed on the current sales difference to form a sales volume anomaly detection result.

9. The method for real-time prediction and anomaly detection of electric transmission equipment sales data according to claim 8, characterized in that: According to the current sales difference, the current sales price difference, the current month-on-month sales difference and the current month-on-month sales price difference, combined with the corresponding sales price difference range for the same period 、The sales difference range for the same period , the sales price difference range during the mentioned month-on-month period and the sales variance range for the mentioned month-over-month period , conduct data applicability detection and analysis, and form applicability detection and analysis results, including: For the current sales difference, the current sales price difference, the current month-on-month sales difference and the current month-on-month sales price difference, if the current sales difference falls within the sales price difference range for the same period, The current sales price difference falls within the sales difference range of the same period The current period sales difference is within the range of the period sales difference. The current period month-on-month sales price difference falls within the sales difference range of the month-on-month period , then data adaptability information is formed, otherwise data non-adaptability information is formed.

10. The method for real-time prediction and anomaly detection of sales data of electric transmission equipment according to claim 9, characterized in that: The step of performing sales anomaly detection and analysis on the current sales difference based on the applicability detection and analysis result to form a sales volume anomaly detection result includes: When the applicability detection and analysis result is data adaptation information, the corresponding current forecast sales change and the current sales difference are obtained to perform the following sales volume anomaly detection analysis: If the difference between the current period forecast sales change and the current period sales difference exceeds the sales forecast deviation threshold, sales abnormality information is generated; If the difference between the current period predicted sales change and the current period sales difference exceeds the sales volume forecast deviation threshold, normal sales volume information is generated.

Images