Smart enterprise management platform based on big data

Abstract

The invention discloses a smart enterprise management platform based on big data, and particularly relates to the technical field of enterprise management, and the platform comprises a demand making module, a sales volume adjustment module and a supplier evaluation module. According to the method, the historical sales mean value is obtained as preliminary prediction, secondary correction is carried out in combination with the sales change rate, the sales price influence ratio and the analysis result of the satisfaction degree score, that is, the correction index is calculated and estimated, and finally the correction index is mapped to the adjustment set to obtain the confidence sales. The problems that in the prior art, multi-dimensional analysis of sales volume trend, price fluctuation and user evaluation is lacked, so that prediction precision is low, and market changes cannot be adapted are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of enterprise management, more specifically, the present application relates to a wisdom enterprise management platform based on big data. BACKGROUND

[0002] In today's digital age, enterprises are facing massive amounts of data and complex management problems.

[0003] However, the existing enterprise management platform can realize some basic management functions, such as data recording and process approval, but still has the following shortcomings:

[0004] First, traditional sales forecasting relies on historical data mean, lacks multi-dimensional analysis of sales trend, price fluctuation and user evaluation, resulting in low prediction accuracy, unable to adapt to market changes, leading to difficulty in efficient response to market demand due to lack of prediction and preparation in future product sales process for enterprises;

[0005] In addition, the supplier evaluation system is single, only based on a small amount of historical cooperation data for screening, without integrating real-time pricing, delivery cycle and response speed dynamic parameters, making it difficult to quickly locate high-quality suppliers in the event of inventory shortage.

[0006] In order to solve the above problems, a wisdom enterprise management platform based on big data is put forward. SUMMARY

[0007] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present application provide a wisdom enterprise management platform based on big data.

[0008] To achieve the above-mentioned purpose, the present application provides the following technical scheme:

[0009] A wisdom enterprise management platform based on big data, comprising the following modules:

[0010] Demand setting module: extracting historical sales data of products sold by the enterprise within k set time zones before the current time point from the pre-constructed enterprise database, taking the average value of the historical sales data within k set time zones to obtain the preliminary predicted sales of the products sold by the enterprise within the next set time zone;

[0011] Sales adjustment module: combining the sales change rate, the formulated sales price of the next set time zone and the comprehensive analysis result of historical user evaluation to make secondary adjustment to the preliminary predicted sales of the products sold by the enterprise within the next set time zone to obtain the confidence sales;

[0012] The supplier evaluation module extracts the inventory of products sold by the enterprise at the current time point from the enterprise database, compares the inventory with the confidence sales volume, and if the confidence sales volume is greater than the inventory, extracts the cooperation archives of each supplier with which the enterprise cooperates at the current time point, and triggers the evaluation signal to perform corresponding steps to select the better supplier from the suppliers.

[0013] Specifically, the comprehensive analysis result of the sales growth rate is specifically:

[0014] The historical sales data in the previous k set time zones at the current time point are extracted and arranged in chronological order. After the arrangement is completed, the sales change rate between the adjacent two groups of historical sales data is calculated, that is, the sales change rate is calculated by ; wherein y1 and y2 respectively represent the historical sales data located on the left and the historical sales data located on the right in the adjacent two groups of historical sales data; if the sales change rate calculated between the adjacent two groups of historical sales data is positive, it is determined as the sales growth rate, and if it is negative, the absolute value is taken to determine the sales reduction rate;

[0015] The sum of each group of sales growth rate and sales reduction rate is obtained to obtain the total growth rate and the total reduction rate. The difference between the total growth rate and the total reduction rate is calculated. If the calculation result is positive, it is determined as the sales potential rate, and if it is negative, the absolute value is taken to determine the sales hidden danger rate. Pi is used to represent, wherein i=1 or 2, respectively representing the sales potential rate and the sales hidden danger rate.

[0016] Specifically, the comprehensive analysis result of the sales growth rate is specifically:

[0017] The product sales unit price of the products sold by the enterprise in the previous k set time zones at the current time point is obtained, and the average value of the product sales unit prices corresponding to the k set time zones is taken as the unit price reference value. The preliminary planning unit price of the products sold by the enterprise in the next set time zone is obtained from the enterprise database; the preliminary planning unit price is taken as the numerator and the unit price reference value is taken as the denominator for ratio calculation, so as to obtain the sales price influence ratio H.

[0018] Each user evaluation of the products sold by the enterprise in the previous k set time zones at the current time point is extracted; wherein the user evaluation includes evaluation time, evaluation content and product score; the product score is extracted from each user evaluation, and the average value is calculated to obtain the satisfaction score F corresponding to the products sold by the enterprise.

[0019] Specifically, the preliminary prediction sales of the products sold by the enterprise in the next set time zone is twice adjusted, which is specifically:

[0020] The sales potential rate and sales risk rate of the products sold by the enterprise in the k set time zones before the current time point are identified, and a comprehensive analysis is performed by substituting the corresponding formula (1) and (2), so as to obtain the estimated correction index E;

[0021] That is, by Wherein η1, η2, η3 represent the weight coefficients corresponding to the sales potential rate P1, the price influence ratio H and the satisfaction degree score F respectively when i = 1.

[0022] δ1, δ2, δ3 represent the weight coefficients corresponding to the sales potential rate P2, the price influence ratio H and the satisfaction degree score F respectively when i = 2.

[0023] The obtained estimated correction index E is mapped to each set of set index range for matching, and each set of set index corresponds to a set of sales adjustment set. The sales adjustment set includes sales adjustment percentage and sales adjustment direction, and the sales adjustment direction includes growth adjustment and decline adjustment. After matching, the sales adjustment set is obtained. The sales adjustment direction and the sales adjustment percentage are extracted and calculated with the preliminary predicted sales to obtain the confidence sales.

[0024] Specifically, the cooperation archives of each supplier include: the qualified rate of the supplied raw materials, the number of past cooperation orders and the on-time delivery rate.

[0025] Specifically, the trigger evaluation signaling and the corresponding steps are executed, specifically:

[0026] The qualified rate of the supplied raw materials in the past cooperation orders is extracted from the cooperation archives of each supplier, and the average value is obtained as the quality performance value of each supplier at the current time point. The number of past cooperation orders is counted from the cooperation archives of each supplier as the familiarity value of each supplier at the current time point.

[0027] The marked delivery time point and the actual delivery time point in the past cooperation orders of each supplier are identified. If the actual delivery time point in a past cooperation order is later than the marked delivery time point, it is marked as a delayed delivery order. The number of delayed delivery orders is counted as the credit performance value of each supplier at the current time point.

[0028] The quality performance value, familiarity value and credit performance value of each supplier at the current time point are marked as R1, R2 and R3 respectively, and a comprehensive calculation is performed according to the formula to obtain the archive performance value yu of each supplier; wherein μ1, μ2, μ3 represent the weight coefficients corresponding to the quality performance value, the familiarity value and the credit performance value respectively.

[0029] Specifically, the trigger evaluation signaling and the corresponding steps further include:

[0030] The archives performance value yu is sorted from large to small, and the suppliers corresponding to the top three archives performance values yu are selected as candidate suppliers from left after sorting;

[0031] The preliminary cooperation signaling is sent to each candidate supplier, each candidate supplier confirms after receiving the preliminary cooperation signaling, and feeds back the preliminary order quotation; wherein the preliminary order quotation includes the raw material unit price, the delivery time point and the promised shortest response time.

[0032] Specifically, the specific process of selecting the better supplier from the suppliers is:

[0033] The time difference between the delivery time point of each candidate supplier and the current time point is calculated, so as to obtain the delivery cycle length of each candidate supplier;

[0034] The raw material unit price, the delivery cycle length and the promised shortest response time corresponding to each candidate supplier are marked as L1, L2 and L3 respectively; and the archives performance value yu is substituted into the formula The comprehensive calculation is carried out, so as to obtain the cooperation optimal value ye of each candidate supplier; the candidate supplier with higher cooperation optimal value ye is selected as the better supplier; wherein σ1, σ2, σ3 and σ4 are weight coefficients corresponding to the raw material unit price, the delivery cycle length, the promised shortest response time and the archives performance value respectively;

[0035] The order generation module is used for generating the cooperation order with the currently selected better supplier after the audit personnel audits and passes the evaluation report generated by the enterprise at the current time point.

[0036] The technical effects and advantages of the present application are:

[0037] (1) By obtaining the historical sales average value as the preliminary prediction, and then combining the analysis results of the sales change rate, the sales price influence ratio and the satisfaction degree score for secondary correction, that is, by calculating the estimated correction index, finally mapping to the adjustment set to obtain the confidence sales, the problem that the existing technology lacks multi-dimensional analysis of sales trend, price fluctuation and user evaluation, resulting in low prediction accuracy and inability to adapt to market changes is solved;

[0038] (2) By calculating the archives performance value of each supplier through the quality performance value, the familiarity value and the credit performance value, and combining the real-time quotation parameters, that is, the raw material unit price, the delivery cycle and the response time to generate the cooperation optimal value, data support is provided for the selection of suppliers, solving the problem that the existing technology has a single supplier evaluation system, which can only be based on a small amount of historical cooperation data for screening, without integrating real-time quotation, delivery cycle and response speed dynamic parameters, and it is difficult to quickly locate high-quality suppliers when the inventory is short;

[0039] (3) By first selecting the top three candidate suppliers according to the archive performance value, and then combining the real-time bidding parameters to calculate the cooperation value, the one-sidedness of single historical data or real-time bidding is avoided. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 A schematic diagram of the intelligent enterprise management platform based on big data. DETAILED DESCRIPTION

[0041] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0042] As shown in Figure 1 A module of the intelligent enterprise management platform based on big data includes a demand formulation module, a sales volume adjustment module, a supplier evaluation module, and an order generation module.

[0043] The demand formulation module is used to extract historical sales volume data of products sold by the enterprise within the previous k set time zones at the current time point from the pre-constructed enterprise database, where k>5, and the value of k is dynamically adjusted by technical personnel. Technical personnel can dynamically modify the value of k according to business needs through the configuration interface of the module, for example, for products with large fluctuations in sales data, the value of k can be appropriately increased to smooth the data. The average value of the historical sales volume data within the k set time zones is obtained to get the preliminary forecast sales volume of the products sold by the enterprise in the next set time zone.

[0044] It is further explained that the data is extracted from the sales data table (such as sales_records) in the enterprise database, and the table structure includes fields such as sale_date (sale date), sale_volume (sale quantity), sale_region (sale region), etc.

[0045] Time range determination: based on the current time point, the historical time range that needs to be extracted is determined according to the set parameter k, for example, if the set time zone is "month", the sales volume data in the previous k months of the current time point is extracted.

[0046] The sales volume adjustment module is used to combine the sales volume change rate, the formulated sales price of the next set time zone, and the comprehensive analysis result of the historical user evaluation to make a secondary adjustment to the preliminary forecast sales volume of the products sold by the enterprise in the next set time zone, and obtain the confidence sales volume.

[0047] Specifically,

[0048] Extract the historical sales data in the k set time zone before the current time point, and arrange them in chronological order. After the arrangement is completed, calculate the sales change rate between the adjacent two groups of historical sales data, that is, through Calculation; wherein y1 and y2 represent the historical sales data on the left and the historical sales data on the right in the adjacent two groups of historical sales data respectively; if the sales change rate calculated between the adjacent two groups of historical sales data is positive, it is determined as the sales growth rate, and if it is negative, it is determined as the sales reduction rate after taking the absolute value;

[0049] Sum the sales growth rate and the sales reduction rate respectively to obtain the total growth rate and the total reduction rate. Calculate the difference between the total growth rate and the total reduction rate. If the calculation result is positive, it is determined as the sales potential rate, and if it is negative, it is determined as the sales hidden risk rate after taking the absolute value. Denoted as Pi, wherein i = 1 or 2, representing the sales potential rate and the sales hidden risk rate respectively;

[0050] It is supplemented that the difference between the total growth rate and the total reduction rate can quantify the "strength" of the trend. For example: total growth rate = 20%, total reduction rate = 5% → potential rate = 15%, indicating strong overall growth momentum; total growth rate = 8%, total reduction rate = 12% → hidden risk rate = 4%, indicating that the sales decline pressure is greater than the growth momentum;

[0051] For the product sales unit price of the products sold by the enterprise in the k set time zone before the current time point, take the average of the product sales unit prices corresponding to the k set time zones as the unit price reference value, and obtain the preliminary planning unit price of the products sold by the enterprise in the next set time zone from the enterprise database; The preliminary planning unit price is preliminarily confirmed by the enterprise internal management personnel according to the real-time time length; the ratio calculation is carried out by taking the preliminary planning unit price as the numerator and the unit price reference value as the denominator, so as to obtain the sales price influence ratio H;

[0052] It is supplemented that by calculating the sales price influence ratio H (preliminary planning unit price / unit price reference value), the deviation amplitude of the next cycle pricing from the historical average can be directly reflected:

[0053] If H > 1, it means that the planning unit price is higher than the historical average (for example, H = 1.2 represents a 20% price increase), and the corresponding sales estimation shows a downward trend;

[0054] If H < 1, it means that the planning unit price is lower than the historical average (for example, H = 0.8 represents a 20% price reduction), and the corresponding sales estimation shows an upward trend;

[0055] extracting each piece of user evaluation of the product sold by the enterprise in the k set time zones before the current time point; wherein the user evaluation includes evaluation time, evaluation content and product score; for each piece of user evaluation, eliminating repeated evaluation, non-substantial content text (such as “good” “not bad”), and garbage information (advertising, waterlogging); the product score range is set to 1-5, and is an integer, and the higher the score represents the higher the user's satisfaction with the product;

[0056] extracting the product score from each piece of user evaluation and calculating the average value to obtain the satisfaction score F of the product sold by the enterprise;

[0057] It is supplemented that the better the historical user evaluation of the product is, the higher the sales estimation of the corresponding product is, for example, the data of an e-commerce platform shows that the conversion rate of goods with a good comment rate of more than 90% is 30% higher than the industry average;

[0058] Identifying the sales potential rate and sales risk rate of the product sold by the enterprise in the k set time zones before the current time point, and corresponding to formula (1) and (2) for comprehensive analysis, so as to obtain the estimation correction index E;

[0059] that is, by wherein η1, η2, η3 represent the weight coefficients corresponding to the sales potential rate P1, the price influence ratio H and the satisfaction score F respectively when i = 1;

[0060] δ1, δ2, δ3 represent the weight coefficients corresponding to the sales potential rate P2, the price influence ratio H and the satisfaction score F respectively when i = 2;

[0061] It is supplemented that the estimation correction index E is quantified by multiple dimensions, which converts historical sales trend, pricing strategy and user evaluation into an operable correction basis, avoids the one-sidedness of a single index, and realizes the improvement of prediction accuracy;

[0062] Mapping the obtained estimation correction index E to each set of set index range for matching, and each set of set index corresponds to a set of sales adjustment set, and the sales adjustment set includes sales adjustment percentage and sales adjustment direction, and the sales adjustment direction includes growth adjustment and decline adjustment;

[0063] After matching, the sales adjustment set is obtained, and the sales adjustment direction and the sales adjustment percentage are extracted and calculated with the preliminary predicted sales to obtain the confidence sales;

[0064] If the sales adjustment direction is growth adjustment, the confidence sales is obtained by multiplying the preliminary predicted sales by (1+sales adjustment percentage);

[0065] If the sales adjustment direction is decline adjustment, the confidence sales is obtained by multiplying the preliminary predicted sales by (1-sales adjustment percentage);

[0066] According to the principle of "the smaller E is, the higher and larger the downward adjustment possibility is", E is divided into several intervals from low to high, and a typical grading method is as follows:

[0067] Low interval: E is close to the minimum value, corresponding to a serious sales risk, and a large downward adjustment, so the adjustment direction is downward adjustment, and the sales adjustment percentage is very high;

[0068] Low-middle interval: E is slightly low, there is a sales decline pressure, and a medium-sized downward adjustment, so the adjustment direction is downward adjustment, and the sales adjustment percentage is high;

[0069] Middle interval: E is moderate, and the trend is not significant, and no adjustment is made;

[0070] High-middle interval: E is slightly high, there is a growth momentum, and a medium-sized upward adjustment, so the adjustment direction is growth adjustment, and the sales adjustment percentage is high;

[0071] High interval: E is close to the maximum value, and the growth momentum is strong, and a large upward adjustment, so the adjustment direction is growth adjustment, and the sales adjustment percentage is very high;

[0072] The supplier evaluation module is used to extract the inventory of the products sold by the enterprise at the current time point from the enterprise database, compare the inventory with the confidence sales, and if the confidence sales is greater than the inventory, extract the cooperation archives of each supplier with which the enterprise cooperates at the current time point, and trigger the evaluation signal to perform the corresponding steps, select the better supplier from each supplier, generate an evaluation report and send it to the reviewer; It can be sent to the mailbox address set by the reviewer;

[0073] By comparing the confidence sales and the inventory, the supplier evaluation mechanism is automatically triggered to avoid the risk of stockout caused by insufficient inventory, and to ensure the continuity of sales, for example, when the confidence sales is higher than the inventory, the supplier screening is started in time to ensure the timeliness of replenishment;

[0074] Specifically:

[0075] The cooperation archives of each supplier include the qualified rate of the supplied raw materials, the number of past cooperation orders and the on-time delivery rate; It also includes cooperation order time, delivery time and order amount, etc.

[0076] The qualified rate of the supplied raw materials in the past cooperation orders of each supplier is extracted from the cooperation archives of each supplier, and the average value is obtained to get the quality performance value of each supplier at the current time point; The qualified rate is counted by counting after the supplier completes the supply;

[0077] The number of past cooperation orders of each supplier is counted from the cooperation archives of each supplier as the familiarity value of each supplier at the current time point;

[0078] Identify the delivery time points marked in the past cooperation orders of each supplier and the actual delivery time points. If the actual delivery time point of a past cooperation order is later than the marked delivery time point, mark it as a delayed delivery order. Count the number of delayed delivery orders as the credit performance value of each supplier at the current time point;

[0079] Based on the sales forecast (confidence sales), drive the supplier evaluation, make the supply chain management from "passive replenishment" to "active prediction", and improve the response speed of enterprises to market demand;

[0080] Multi-dimensional quantitative indicators:

[0081] Quality performance value: objectively reflect the product quality stability of the supplier through the average value of the qualified rate of raw materials;

[0082] Familiarity value: measure the cooperation experience of the supplier and the enterprise by the number of past cooperation orders, prefer to choose suppliers familiar with business processes to reduce communication costs and cooperation adaptation period risks;

[0083] Credit performance value: quantify the reliability of the supplier's performance through the number of delayed delivery orders;

[0084] Flexible weight configuration: by setting the weight coefficients of different indicators (such as quality, familiarity, credit), the evaluation focus can be dynamically adjusted according to business needs (such as quality priority or delivery speed priority), improving the adaptability of evaluation;

[0085] For the quality performance value, familiarity value and credit performance value of each supplier at the current time point, mark them as R1, R2 and R3 respectively, and calculate them comprehensively according to the formula , so as to obtain the file performance value yu of each supplier; wherein μ1, μ2 and μ3 respectively represent the weight coefficients corresponding to the quality performance value, the familiarity value and the credit performance value;

[0086] Quantitative ranking of suppliers through file performance value (comprehensive quality, familiarity, credit) to avoid subjective judgment bias and ensure the fairness of the screening results;

[0087] Sort the file performance value yu from large to small, and select the top three suppliers corresponding to the file performance value yu from left after sorting as candidate suppliers;

[0088] Send preliminary cooperation signals to each candidate supplier. Each candidate supplier confirms after receiving the preliminary cooperation signal and feeds back the preliminary order. The preliminary order includes the unit price of raw materials, the delivery time point and the promised shortest response time. The additional costs include but are not limited to transportation fees, packaging fees, tax fees and other hidden costs, which are determined according to the feedback results of the supplier;

[0089] Calculate the time difference between the delivery time point of each candidate supplier and the current time point, so as to obtain the delivery cycle length of each candidate supplier;

[0090] Mark the raw material unit price, delivery cycle length and promised shortest response time of each candidate supplier as L1, L2 and L3 respectively, and substitute them into the formula Perform comprehensive calculation to obtain the cooperation value ye of each candidate supplier; select the candidate supplier with higher cooperation value ye as the better supplier; wherein σ1, σ2, σ3 and σ4 are the weight coefficients corresponding to the raw material unit price, delivery cycle length, promised shortest response time and archive performance value respectively;

[0091] Combine the archive performance value (based on historical quality, familiarity, credit performance) and the real-time feedback of the bidding parameters (unit price, delivery cycle, response time), avoid relying only on historical data or single dimension (such as price) decision, make the evaluation more in line with the current business needs;

[0092] First, select the top three candidate suppliers and then calculate the cooperation value, form a two-layer mechanism of "pre-selection + fine evaluation", ensure that the main selected supplier can be quickly switched when there is a problem, and enhance the resilience of the supply chain;

[0093] The order generation module is used to generate a cooperation order with the currently selected better supplier after the audit personnel audits the evaluation report generated by the enterprise at the current time point; wherein the cooperation order includes the supplier name, generation date and total amount of purchased raw materials, etc.

[0094] The above formulas are all dimensionless values, and the specific dimensionless can be standardized or other means, which will not be described here. The formula is obtained by software simulation of a large amount of data to reflect the current real situation. The preset parameters in the formula are set by the person skilled in the art according to the actual situation.

[0095] The above-described embodiments can be implemented in part or in whole through software, hardware, firmware or any combination thereof. When implemented in software, the above-described embodiments can be implemented using one or more computer programs written in any suitable programming language. Such programs can be stored in one or more storage media or memory devices (e.g., a computer readable medium) associated with the computer or other suitable devices. The memory devices can include, but are not limited to, RAM, ROM, EEPROM, flash memory or other suitable memory devices. The computer programs can be loaded and / or executed on the computer or other suitable devices to produce a computer implemented process, such that the actions specified in the computer programs are performed. The computer programs can be executed on a single computer or on multiple computers.

[0096] It should be understood that the sequence of the above processes is not intended to mean the execution order of the processes, and the execution order of the processes should be determined according to the functions and inherent logic of the processes, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0097] Those skilled in the art can understand that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0098] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are merely illustrative, for example, the division of units is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed units can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0099] The units described as separate components may or may not be physically separate, and the components displayed as units may or may not be physical units, which may be located in one place or distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0100] In addition, the functional units in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit.

[0101] The functions, if realized in the form of software functional units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application or the part of the present application that essentially contributes to the prior art or the part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a 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: a U disk, a mobile ATA hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program code storage media.

[0102] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A smart enterprise management platform based on big data, characterized in that, Includes the following modules: Demand formulation module: Extracts historical sales data of the products sold by the enterprise from the pre-built enterprise database for the k set time zones before the current time, takes the average of the historical sales data for the k set time zones, and obtains the preliminary predicted sales of the products sold by the enterprise in the next set time zone. Sales Adjustment Module: Combining the sales change rate, the set sales price for the next set time zone, and the comprehensive analysis results of historical user reviews, the module performs a secondary adjustment on the initial predicted sales volume of the company's products in the next set time zone to obtain the confidence sales volume. Supplier evaluation module: Extracts the inventory of products sold by the enterprise at the current time from the enterprise database, compares the inventory with the confidence sales volume, and if the confidence sales volume is greater than the inventory, extracts the cooperation files of each supplier that the enterprise cooperates with at the current time, triggers the evaluation signaling to execute the corresponding steps, and selects the better supplier from all suppliers.

2. The intelligent enterprise management platform based on big data according to claim 1, characterized in that, The comprehensive analysis results of the obtained sales growth rate are as follows: Extract historical sales data from the k time zones prior to the current time point, arrange them in chronological order, and then calculate the sales change rate between any two adjacent sets of historical sales data. The calculation yields the following results: where y1 and y2 represent the historical sales data located on the left and right sides of two adjacent historical sales data sets, respectively. If the calculated sales change rate between two adjacent historical sales data sets is positive, it is determined to be the sales growth rate; if it is negative, the absolute value is taken and determined to be the sales decrease rate. Sum the sales growth rate and sales reduction rate of each group to obtain the total growth rate and the total reduction rate. Calculate the difference between the total growth rate and the total reduction rate. If the result is positive, it is determined as the sales potential rate. If it is negative, the absolute value is taken and determined as the sales hidden risk rate, denoted by Pi, where i = 1 or 2, representing the sales potential rate and the sales hidden risk rate, respectively.

3. The intelligent enterprise management platform based on big data according to claim 2, characterized in that, The comprehensive analysis results of obtaining the set sales price for the next time zone and historical user reviews are as follows: The unit price of the products sold by enterprises in the k set time zones before the current time point is obtained, and the average unit price of the products corresponding to the k set time zones is taken as the unit price reference value. The preliminary planned unit price of the products sold by the enterprise in the next set time zone is obtained from the enterprise database. The ratio H is calculated by using the preliminary planned unit price as the numerator and the unit price reference value as the denominator. For each user review of the products sold by the company within the k specified time zones prior to the current time, the user reviews include the review time, review content, and product rating. The product rating is extracted from each user review, and the average value is calculated to obtain the satisfaction rating F corresponding to the products sold by the company.

4. The intelligent enterprise management platform based on big data according to claim 3, characterized in that, The preliminary sales forecast for the company's products in the next set time zone is adjusted a second time, specifically as follows: Identify the sales potential rate and sales risk rate of products sold by enterprises in the k set time zones before the current time point, and substitute them into formulas (1) and (2) for comprehensive analysis to obtain the estimated correction index E; That is, through Where η1, η2, and η3 represent the weighting coefficients corresponding to the sales potential rate P1, the price influence ratio H, and the satisfaction rating F respectively when i = 1; δ1, δ2, and δ3 represent the weighting coefficients corresponding to the sales potential rate P2, the price influence ratio H, and the satisfaction rating F when i = 2. The obtained estimated correction index E is mapped to the set index range of each group for matching. Each set index corresponds to a set of sales adjustment, which includes the sales adjustment percentage and the sales adjustment direction. The sales adjustment direction includes growth adjustment and decline adjustment. After matching, the sales adjustment set is obtained. The sales adjustment direction and sales adjustment percentage are extracted and then calculated with the preliminary predicted sales to obtain the confidence sales.

5. The intelligent enterprise management platform based on big data according to claim 4, characterized in that, The cooperation files of each supplier include: the qualification rate of supplied raw materials, the number of past cooperation orders, and the on-time delivery rate.

6. The intelligent enterprise management platform based on big data according to claim 5, characterized in that, The triggering of the evaluation signaling and the execution of the corresponding steps are as follows: Extract the pass rate of raw materials supplied in past cooperation orders from each supplier's cooperation file, and take the average to obtain the quality performance value of each supplier at the current time point; count the number of past cooperation orders from each supplier's cooperation file as the familiarity value of each supplier at the current time point. Identify the delivery time and actual delivery time marked in the past cooperation orders of each supplier. If the actual delivery time in a past cooperation order is later than the marked delivery time, it is marked as a delayed delivery order. The number of delayed delivery orders is counted as the credit performance value of each supplier at the current time. For each supplier's quality performance, familiarity score, and credit performance score at the current point in time, they are labeled R1, R2, and R3, respectively, and then processed according to the formula... A comprehensive calculation is performed to obtain the performance value yu of each supplier's profile; where μ1, μ2, and μ3 represent the weighting coefficients corresponding to the quality performance value, familiarity value, and credit performance value, respectively.

7. A smart enterprise management platform based on big data according to claim 6, characterized in that, The triggering of the evaluation signaling and execution of the corresponding steps also includes: Sort the file performance values ​​yu from largest to smallest, and then select the top three file performance values ​​yu from left to right as candidate suppliers. Preliminary cooperation signals are sent to each candidate supplier. Upon receiving the preliminary cooperation signals, each candidate supplier confirms and provides a preliminary quotation order, which includes the unit price of raw materials, delivery time, and the promised shortest response time.

8. The intelligent enterprise management platform based on big data according to claim 7, characterized in that, The specific process for selecting the better supplier from among the suppliers is as follows: The time difference between the delivery time of each candidate supplier and the current time is calculated to obtain the delivery cycle length of each candidate supplier. The raw material unit price, delivery cycle length, and promised shortest response time for each candidate supplier are labeled L1, L2, and L3, respectively; and substituted into the formula along with the performance value yu from the archive. A comprehensive calculation is performed to obtain the cooperation merit value ye for each candidate supplier; the candidate supplier with the higher cooperation merit value ye is selected as the better supplier; where σ1, σ2, σ3, and σ4 are the weighting coefficients corresponding to the raw material unit price, delivery cycle length, promised shortest response time, and file performance value, respectively. The order generation module is used to generate a cooperation order with the currently selected best supplier after the reviewer approves the evaluation report generated by the company at the current time.

Images