Enterprise information management method and management system based on big data

Abstract

The present invention discloses an enterprise information management method and management system based on big data, and relates to the technical field of enterprise information management. If the sales forecast value of a target product is lower than expected, data collection is performed on the target product and related data, and consumers are classified into different consumer groups. After matching corresponding marketing strategies for consumer groups in a marketing program library, interest content is recommended; a marketing value is generated from a marketing indicator data set of the target product. If the marketing value exceeds expectations, the safety inventory of the target product is constrained based on sales speed data and the marketing value. If the inventory of the target product exceeds the safety inventory, an alarm instruction is issued to the outside; an alarm concentration is constructed based on the time node when the alarm instruction is received. If the alarm concentration exceeds expectations, the inventory management process is optimized; the frequency of the current excessive inventory is evaluated, and when the inventory is excessive for a long time, feedback is formed on the current inventory management and marketing.

Description

Technical Field

[0001] The present invention relates to the technical field of enterprise information management, and in particular to an enterprise information management method and management system based on big data. Background Art

[0002] Enterprise information management is a key driving force for optimizing product sales. It integrates, analyzes and effectively utilizes internal and external data resources of the enterprise to provide accurate insights for product strategy formulation, market positioning, customer demand forecasting, sales channel optimization and after-sales service improvement, thereby enhancing market competitiveness, improving customer satisfaction and promoting sustained growth in product sales.

[0003] From the perspective of product sales, the importance of enterprise information management is reflected in the following aspects:

[0004] Market insight and strategy formulation: By collecting and analyzing market trends, competitor dynamics and consumer behavior data, companies can more accurately grasp market demand and formulate product sales strategies that meet market changes, including pricing strategies, promotional activities and channel layout. Customer demand forecasting: Using historical sales data, customer feedback and social media sentiment analysis, companies can predict future changes in customer demand, adjust product structure in advance, develop new products that meet market expectations, reduce inventory backlogs, and improve sales efficiency.

[0005] In the Chinese invention patent application publication number CN111340538A, an enterprise information management cloud platform based on marketing big data is disclosed, which is used to solve the problems in the prior art that the enterprise information management cloud platform cannot send the marketing data corresponding to some non-sticky customers from the server to the corresponding employee mobile phone terminal for storage, and the employees are unfamiliar with the enterprise information management software, resulting in the inability to complete the enterprise information management; it includes a data acquisition module, a server, a data analysis module, a data management module, a login registration module, an information learning module, a master calculation module and a notification management module; the present invention compresses the data through the server and sends it to the corresponding employee mobile phone terminal, so that the employees can understand the customer's analysis value in time, and the information learning module enables the employees to learn the operation video of the information management software, thereby reducing the inability to complete the enterprise information management due to the employees' unfamiliarity with the enterprise information management software.

[0006] Combined with the above application and the contents of the prior art:

[0007] When selling products, the products may have poor sales due to lack of popularity or inappropriate prices. If this situation is not improved in time, the business operations will be disturbed to a certain extent. Therefore, in this case, it is necessary to timely integrate various enterprise information, such as product marketing information, inventory management information and supply chain information, etc., and form feedback on product marketing and sales through management and integration of various information.

[0008] In order to solve the problem of poor product sales, existing enterprise information management methods are usually based on big data, through more accurate content push, to increase the company's visibility and increase product sales; but the above method is difficult to solve the problem more comprehensively, especially when the current predicted sales of the product are lower than expected, and there are still risk points in various links of the product supply chain. The difficulty of product marketing management may be further increased. For example, when the sales of a product suddenly increase, if the product inventory is not constrained and managed in time, the inventory of the product may gradually become excessive with the change in sales. If the product sales speed is insufficient, resulting in product backlogs, it may result in large losses.

[0009] To this end, the present invention provides an enterprise information management method and management system based on big data. Summary of the invention

[0010] 1. Technical issues to be resolved

[0011] In view of the deficiencies in the prior art, the present invention provides an enterprise information management method and management system based on big data, which recommends content of interest after matching corresponding marketing strategies for consumer groups in a marketing program library; generates a marketing value from a set of marketing indicator data of a target product; if the marketing value exceeds expectations, constrains the safety inventory of the target product based on sales speed data and the marketing value; if the inventory of the target product exceeds the safety inventory, issues an alarm instruction to the outside; constructs an alarm concentration based on the time node when the alarm instruction is received; if the alarm concentration exceeds expectations, optimizes the inventory management process; evaluates the frequency of the current excessive inventory; and when the inventory is excessive for a long time, provides feedback to the current inventory management and marketing, thereby solving the technical problems recorded in the background technology.

[0012] (II) Technical solution

[0013] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0014] Enterprise information management methods based on big data include identifying abnormal risk points in the target product supply chain and the sales data of the target product when the abnormal risk points occur, and analyzing and obtaining the correlation coefficient between the two , if the correlation coefficient Exceeding expectations, issuing sales forecast instructions to external parties;

[0015] If the sales forecast of the target product is lower than expected, collect data on the target product and related data, and aggregate to obtain a product marketing data set; classify consumers into different consumer groups, match corresponding marketing strategies for consumer groups in the marketing plan library, and then recommend interest content;

[0016] Generate marketing value from the marketing indicator data set of the target product If the marketing value Exceeded expectations, based on sales velocity data and marketing value Constrain the safety stock of the target product. If the stock of the target product exceeds the safety stock, an alarm command will be issued to the outside.

[0017] Construct alarm aggregation based on the time node when the alarm command is received , if the alarm concentration Exceeded expectations, collected inventory management process data of target products and generated operational value , if the operating value Optimize inventory management processes without exceeding operational thresholds;

[0018] Collect sales feedback data of target products and construct a system to evaluate the improvement of marketing effect of target products If the improvement If the improvement threshold is not exceeded, the target product supply chain is optimized using a multi-objective optimization algorithm based on the target product's marketing and supply chain data.

[0019] Furthermore, the link data of the supply chain of the target product is analyzed, and the link data is used as input, and the abnormal risk points of the data abnormalities are identified using the trained abnormal data recognition model, and the time node at which the abnormal risk point is generated is used as the risk node;

[0020] By analyzing the historical sales data of the target product, the sales data of the target product at each risk node is obtained, and the relative deviation between the link data at the risk node and the preset standard value is used as the risk degree.

[0021] Furthermore, the risk degree of several consecutive risk nodes is obtained. Product sales volume with target products After that, the correlation coefficient between the two is obtained. , where: linear normalization is performed on risk and product sales, and the corresponding data values ​​are mapped to the interval Then follow the steps below:

[0022] ;

[0023] in, For the risk level at the risk node i The value on For product sales at risk nodes i The value on

[0024] , is the number of risk nodes, , is the weight coefficient, , ,and .

[0025] Furthermore, after receiving the efficiency prediction instruction, the trained product sales prediction model is used to predict the sales volume of the target product and obtain the sales prediction value; if the sales prediction value of the target product is lower than expected, data collection is performed on the target product and related data, and the product marketing data set is obtained after aggregation.

[0026] Furthermore, feature extraction is performed on product marketing data to obtain corresponding marketing features, and consumer portraits are generated after analyzing consumer consumption characteristics using data visualization tools. After obtaining several groups of portrait data, the pre-trained hierarchical clustering algorithm is used to classify the portraits of different consumers to obtain corresponding consumer groups.

[0027] Furthermore, after executing the marketing strategy on the consumer group, the marketing indicators of the marketing activities are collected in the sub-period, and the marketing indicator data set is generated after being aggregated; the marketing value is generated from the marketing indicator data set. If the marketing value If the marketing value does not exceed the marketing threshold, adjust the marketing strategy. If the marketing value exceeds the marketing threshold, issue inventory management instructions to the outside.

[0028] Furthermore, the open rate , click-through rate and conversion rate Perform linear normalization and map the corresponding data values ​​to the interval In the following way, the marketing value is generated :

[0029] ;

[0030] in, , is the number of sub-periods, and the weight coefficient is: , , ,and ;

[0031] For the i The opening rate of each sub-period, is the mean open rate, For the i The click rate of each sub-period, is the mean click rate, For the i The conversion rate of the sub-cycle, is the mean conversion rate;

[0032] Furthermore, after receiving the inventory management instruction, the inventory level of the target product is monitored in real time, and the sales speed of the target product during the observation period is Marketing value , taking the acceptable inventory as the safety stock and impose constraints;

[0033] If the current inventory of the target product does not exceed the safety inventory, a replenishment instruction is generated and issued to the outside. If the current inventory exceeds the safety inventory, an alarm instruction is issued to the outside.

[0034] Furthermore, the safety stock The constraints are as follows:

[0035] ;

[0036] Weight coefficient, , ,and ; is the number of sub-periods, It is i Sub-period to j The difference in sales velocity within the sub-periods, is the average of the sales velocity differences, The safety stock amount.

[0037] Furthermore, the time node when the alarm instruction is received is used as the alarm node, and the alarm concentration is constructed after receiving several alarm instructions continuously in the current observation period. , if the alarm concentration When the preset concentration threshold is exceeded, an inventory analysis instruction is issued to the outside;

[0038] Further, the alarm concentration is constructed The way is as follows:

[0039] ;

[0040] Where: , The value is 2.718, the weight coefficient, , ,and ;

[0041] is the radius of the observation period; No. i The weighted value of each alarm command, It is i Alarm command to j The time interval between alarm instructions. The number of alarm nodes.

[0042] Furthermore, after receiving the inventory analysis instruction, the inventory management process of the target product is monitored and data is collected in continuous sub-periods, and the operation data set of the target product is generated after aggregation; the operation value is generated from the operation data set , among which, the order delivery time and inventory turnover time Perform linear normalization and map the corresponding data values ​​to the interval In the following way:

[0043] ;

[0044] Weight coefficient, , , For the i The median value of operations within a sub-period, is the corresponding mean, is the number of sub-periods.

[0045] The enterprise information management system based on big data includes a sales forecasting unit, which identifies abnormal risk points in the target product supply chain and the sales data of the target product when abnormal risk points occur, and analyzes and obtains the correlation coefficient between the two. , if the correlation coefficient Exceeding expectations, issuing sales forecast instructions to external parties;

[0046] The marketing content push unit collects data on the target product and related data if the sales forecast value of the target product is lower than expected, and collects and obtains a collection of product marketing data; it classifies consumers into different consumer groups, matches corresponding marketing strategies for consumer groups in the marketing plan library, and recommends content of interest;

[0047] Inventory alarm unit generates marketing value from the marketing indicator data set of the target product If the marketing value Exceeded expectations, based on sales velocity data and marketing value Constrain the safety stock of the target product. If the stock of the target product exceeds the safety stock, an alarm command will be issued to the outside.

[0048] The operation analysis unit builds the alarm aggregation degree based on the time node when the alarm instruction is received , if the alarm concentration Exceeded expectations, collected inventory management process data of target products and generated operational value , if the operating value Optimize inventory management processes without exceeding operational thresholds;

[0049] Process optimization unit, collects sales feedback data of target products and builds a system to evaluate the improvement of marketing effect of target products If the improvement If the improvement threshold is not exceeded, the target product supply chain is optimized using a multi-objective optimization algorithm based on the target product's marketing and supply chain data.

[0050] (III) Beneficial effects

[0051] The present invention provides an enterprise information management method and management system based on big data, which has the following beneficial effects:

[0052] 1. By determining the correlation between the risk level of the supply chain and the sales volume of the target product, the impact of the supply chain of the target product on the sales volume can be determined. By adjusting the supply chain, the sales volume of the target product can be adjusted.

[0053] 2. By collecting and analyzing various data to build consumer portraits, different marketing strategies can be adopted to achieve targeted processing when it is necessary to market the target products; by matching corresponding marketing strategies for each consumer group in the marketing plan library and formulating targeted marketing strategies for each consumer group, better marketing effects can be achieved when marketing the target products.

[0054] 3. After pushing content to consumers, collect feedback data on the pushed content and use it as a marketing indicator to generate marketing value , based on marketing value Modify the push content to adjust the marketing effect of the target product.

[0055] 4. Constrain the current acceptable inventory level based on sales velocity data and marketing value, and dynamically adjust the acceptable inventory level to prevent excessive inventory of target products, which would lead to losses.

[0056] 5. Based on the alarm concentration constructed The frequency of the current excessive inventory can be evaluated. When the inventory is persistently excessive, feedback can be provided on the current inventory management and marketing to increase sales of target products.

[0057] 6. Collect the delivery status data of the target product and build the operational value from it , based on operating value Evaluate the current inventory delivery status of the target product. If the delivery status of the target product is poor, optimize the delivery process of the target product, improve the delivery efficiency when managing the target product, and form positive feedback when marketing the target product.

[0058] 7. Based on the identification of each risk node, use multi-objective optimization to optimize the current supply chain links. Different from the optimization of the target product marketing strategy, it can increase the target sales volume and sales speed and reduce inventory. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 It is a flow chart of the enterprise information management method based on big data of the present invention;

[0060] Figure 2 It is a schematic diagram of the structure of the enterprise information management system based on big data of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] See also Figure 1 The present invention provides an enterprise information management method based on big data, including:

[0063] Step 1: Identify the abnormal risk points in the target product supply chain and the sales data of the target product when the abnormal risk points occur, and analyze and obtain the correlation coefficient between the two , if the correlation coefficient Exceeding expectations, issuing sales forecast instructions to external parties;

[0064] The step 1 includes the following contents:

[0065] Step 101: Analyze the supply chain data of the target product, such as procurement, logistics and inventory;

[0066] The recurrent convolutional network is trained with labeled sample data to obtain a trained abnormal data recognition model. The link data is used as input, and the trained abnormal data recognition model is used to identify abnormal risk points of the data abnormalities, and the time node at which the abnormal risk point is generated is used as the risk node.

[0067] When in use, by collecting the supply chain data of the target product and identifying abnormal data, when the target product is in operation, verify whether there are abnormalities in the supply chain from the perspective of data analysis and identification. If there are abnormalities, they can be handled in a timely manner and the corresponding degree of abnormality can be determined;

[0068] Step 102: Analyze the historical sales data of the target product to obtain the sales data of the target product at each risk node; use the relative deviation between the link data at the risk node and the preset standard value as the risk degree; if there are multiple risk items, add up the multiple relative deviations to use as the risk degree;

[0069] Step 103: Obtain the risk levels of several consecutive risk nodes Product sales volume with target products After that, the correlation coefficient between the two is obtained by analysis, where: the risk level and product sales are linearly normalized and the corresponding data values ​​are mapped to the interval Then follow the steps below:

[0070] ;

[0071] in, For the risk level at the risk node i The value on For product sales at risk nodes i The value on , is the number of risk nodes, , is the weight coefficient, , ,and , the specific value is set by the user or obtained by referring to the hierarchical analysis method;

[0072] Pre-set relevant thresholds based on historical data and marketing and supply management expectations for target products;

[0073] If the correlation coefficient If the relevant threshold is exceeded, it means that the risks in the current supply chain of the target product may have certain interference and negative impact on the marketing of the target product. At this time, a sales forecast instruction is issued to the outside.

[0074] When using, combine the contents in steps 101 to 103:

[0075] By determining the correlation between the risk level of the supply chain links and the sales volume of the target product, the impact of the supply chain of the target product on the sales volume can be determined. If the impact exceeds expectations, the sales volume of the target product can be adjusted by adjusting the supply chain.

[0076] Combined with the above application and the contents of the prior art:

[0077] When selling products, the products may have poor sales due to lack of popularity or inappropriate prices. If this situation is not improved in a timely manner, the business operations will be affected to a certain extent. Therefore, in this case, it is necessary to timely integrate various enterprise information, such as product marketing information, inventory management information, and supply chain information, so as to form feedback on product marketing and sales through management and integration of various information.

[0078] In order to solve the problem of poor product sales, existing enterprise information management methods are usually based on big data, through more accurate content push, to increase the company's visibility and increase product sales; but the above method is difficult to solve the problem more comprehensively, especially when the current predicted sales of the product are lower than expected, and there are still risk points in various links of the product supply chain, the difficulty of product marketing management may be further increased. For example, when the sales of a product suddenly increase, if the product inventory is not constrained and managed in time, the inventory of the product may gradually become excessive with the change in sales. If the product sales speed is insufficient, resulting in product backlog, it may cause large losses.

[0079] Step 2: If the sales forecast value of the target product is lower than expected, collect data on the target product and related data, and obtain a product marketing data set; classify consumers into different consumer groups, match corresponding marketing strategies for consumer groups in the marketing plan library, and recommend interest content;

[0080] The step 2 includes the following contents:

[0081] Step 201: after receiving the efficiency prediction instruction, a recurrent neural network is trained with sample data including historical data to generate a trained product efficiency prediction model; the trained product sales prediction model is used to predict the sales volume of the target product and obtain a sales prediction value;

[0082] If the sales forecast of the target product is lower than expected, data collection is performed on the target product and related data, for example:

[0083] Basic information of consumers, such as name, contact information, address, etc., and interaction history, such as contact records, purchase history, etc.; collect transaction data of consumers on e-commerce platforms, and analyze the purchase frequency, category and average consumption amount of consumers;

[0084] Capture consumers’ comments, likes, shares and other interactive behaviors on brands through social media analysis tools to understand consumers’ interests and emotions; obtain direct feedback through questionnaires; collect supply chain data, manage procurement, inventory, sales and other information, and integrate data from various departments; collect transportation data, track the status and transportation routes of goods. Obtain order, delivery time and quality data; inventory levels, purchase orders, sales forecasts, etc., financial data, such as transportation costs, supplier payment records. Market data, such as market demand forecasts and competitor analysis data;

[0085] Summarize the relevant data of each target product collected above to obtain a product marketing data set;

[0086] When in use, by collecting relevant data of the target product, when the sales forecast value of the target product is lower than expected, feedback can be formed on the sales and marketing of the target product;

[0087] Step 202: extract features from product marketing data and obtain corresponding marketing features, use data visualization tools to analyze consumer consumption characteristics and generate consumer portraits, such as age, gender, geographic location, consumption preferences, etc.;

[0088] After obtaining several groups of portrait data, the pre-trained hierarchical clustering algorithm is used to classify the portraits of different consumers and obtain the corresponding consumer groups;

[0089] When in use, by collecting and analyzing various data to build consumer portraits, different marketing strategies can be adopted when it is necessary to market the target products, so as to achieve targeted processing and increase sales when the sales forecast value of the target products is lower than expected;

[0090] Step 203: Obtain several marketing strategies through online search and offline collection, including recommended content, recommended frequency, and recommended duration, and aggregate the obtained marketing plans to generate a marketing plan library;

[0091] According to the marketing characteristics of the consumer group, the corresponding marketing strategy is matched for the consumer group in the marketing plan library. According to the marketing strategy, the content of interest is recommended to the consumer group based on the collaborative filtering algorithm;

[0092] When using, combine the contents in steps 201 to 203:

[0093] Based on the marketing characteristics of each consumer group, by matching the corresponding marketing strategy in the marketing plan library for each consumer group, and using the matched marketing strategy as a reference, by formulating targeted marketing strategies for each consumer group, when marketing the target product, better marketing effects can be achieved;

[0094] Step 3: Generate marketing value from the marketing indicator data set of the target product If the marketing value Exceeded expectations, based on sales velocity data and marketing value Constrain the safety stock of the target product. If the stock of the target product exceeds the safety stock, an alarm command will be issued to the outside.

[0095] The step three includes the following contents:

[0096] Step 301: pre-set an observation period including several sub-periods, and after executing a marketing strategy on a consumer group, collect marketing indicators of the marketing activities in the sub-periods, including open rate, click rate, conversion rate, etc., and generate a marketing indicator data set after aggregation;

[0097] Generate marketing value from marketing indicator data set , among which, the open rate , click-through rate and conversion rate Perform linear normalization and map the corresponding data values ​​to the interval In the following way:

[0098] ;

[0099] in, , is the number of sub-periods, and the weight coefficient is: , , ,and ;The weight coefficient is determined by referring to the hierarchical analysis method;

[0100] For the i The opening rate of each sub-period, is the mean open rate, For the i The click rate of each sub-period, is the mean click rate, For the i The conversion rate of the sub-cycle, is the mean conversion rate;

[0101] Pre-set marketing thresholds based on historical data and expected feedback on marketing effectiveness;

[0102] If marketing value If the marketing value does not exceed the marketing threshold, it means that the current marketing effect has not met expectations and the marketing strategy needs to be adjusted, for example, by switching the recommended content, recommendation frequency, and push duration, to ensure the best marketing effect. If the marketing value exceeds the marketing threshold, an inventory management instruction is issued externally.

[0103] When in use, we implement targeted marketing strategies for each consumer group. After pushing content to consumers, we collect feedback data on the pushed content and use it as a marketing indicator to generate marketing value. , can be based on marketing value Modify the push content to adjust the marketing effect of the target product;

[0104] Step 302: After receiving the inventory management instruction, the inventory level of the target product is monitored in real time based on the sales speed of the target product during the observation period. Marketing value , taking the acceptable inventory as the safety stock And constrain it as follows:

[0105] ;

[0106] in, is the number of sub-periods, It is i Sub-period to j The difference in sales velocity within the sub-periods, is the average of the sales velocity differences, The safety stock amount. , is the weight coefficient, , ,and , the value is consistent with the previous value;

[0107] If the current inventory of the target product does not exceed the safety inventory, a replenishment instruction is generated and sent to the outside to facilitate replenishment; if the current inventory exceeds the safety inventory, it means that the current inventory of the target product is large and there may be a backlog. At this time, an alarm instruction is sent to the outside;

[0108] When using, combine the contents in steps 301 and 302:

[0109] After recording and obtaining the sales speed data of the target products in each sub-period, the current acceptable inventory level is constrained according to the sales speed data and marketing value to achieve dynamic adjustment of the acceptable inventory level. By keeping the safety stock level in a dynamic adjustment state, it is possible to prevent excessive inventory of the target product and thus incur losses.

[0110] Step 4: Build alarm aggregation based on the time node of receiving the alarm command , if the alarm concentration Exceeded expectations, collected inventory management process data of target products and generated operational value , if the operating value Optimize inventory management processes without exceeding operational thresholds;

[0111] The step 4 includes the following contents:

[0112] Step 401: The time node of receiving the alarm instruction is used as the alarm node, and the alarm concentration is constructed after receiving several alarm instructions continuously in the current observation period. ,in,

[0113] ;

[0114] Where: , The value is 2.718, the weight coefficient, , ,and ;

[0115] is the radius of the observation period; No. i The weighted value of each alarm command, It is i Alarm command to j The time interval between alarm instructions. is the number of alarm nodes;

[0116] If the alarm concentration If the concentration exceeds the preset threshold, it means that the current inventory situation of the target product may be serious and needs to be dealt with in a timely manner. At this time, an inventory analysis instruction is issued to the outside.

[0117] When in use, by recording the alarm instructions, according to the alarm concentration constructed It can evaluate the frequency of the current excessive inventory. When the inventory is excessive for a long time, it can provide feedback on the current inventory management and marketing to increase the sales of the target products.

[0118] Step 402: After receiving the inventory analysis instruction, monitor the inventory management process of the target product in consecutive sub-periods and collect data, including order delivery time, inventory turnover time, etc., and generate an operation data set for the target product after aggregation; generate an operation value from the operation data set , regularly evaluate the operational performance of the supply chain based on operational values, including:

[0119] Delivery time for orders and inventory turnover time Perform linear normalization and map the corresponding data values ​​to the interval In the following way:

[0120] ;

[0121] Weight coefficient, , , the weight coefficient can be obtained by referring to the hierarchical analysis method; For the i The median value of operations within a sub-period, is the corresponding mean, is the number of sub-periods;

[0122] Pre-set operational thresholds based on historical data and delivery management expectations for target products;

[0123] If the operating value If the preset operation threshold is not exceeded, it means that the delivery efficiency of the target product is poor after entering the delivery state, and the current inventory management needs to be optimized. At this time, a process optimization instruction is issued to the outside to optimize the delivery process of the target product orders that have generated the backlog.

[0124] When using, combine the contents in steps 401 and 402:

[0125] When there is a large amount of inventory of the target product, collect the delivery status data of the target product and build the operation value from it , evaluate the current inventory delivery status of the target product based on the operation value. If the delivery status of the target product is poor, the delivery process of the target product can be optimized, and the delivery efficiency can be improved when managing the target product, forming positive feedback when marketing the target product;

[0126] Step 5: Collect sales feedback data of target products and build a system to evaluate the improvement of marketing effect of target products If the improvement If the improvement threshold is not exceeded, the target product supply chain is optimized using a multi-objective optimization algorithm based on the target product's marketing and supply chain data;

[0127] The step five includes the following contents:

[0128] Step 501: After the preset marketing cycle ends, collect the sales data, product delivery data and inventory data of the target product in each sub-cycle, and calculate the sales speed of the target product in each sub-cycle. Arranged by timeline, by sales speed Construct an evaluation system to evaluate the improvement of the marketing effect of the target product , as follows:

[0129] ;

[0130] in, For the i The sales speed of the target product in the second sub-cycle, is the mean sales velocity, is its qualified standard value; For the i Improve the median value, is its mean value, , is the number of sub-periods,

[0131] Weight coefficient: , ,and , the weight coefficients and can be kept consistent with the previous ones;

[0132] Based on historical data and the expected improvement in the marketing effect of the target product, the improvement threshold is set in advance; if the improvement degree Failure to exceed the improvement threshold indicates that the marketing strategy for the target product has not met expectations and needs to be further optimized. At this point, a strategy optimization instruction is issued externally;

[0133] When used, in the marketing process of the target product, after optimizing the marketing strategy and inventory management, a system is constructed to evaluate the improvement of the marketing effect of the target product based on the changes in sales data. , based on the improvement Determine whether the current marketing effect of the target product has improved. If it has, the current marketing strategy can be maintained. If it has not produced the expected effect, further optimization is required.

[0134] Step 502: After receiving the strategy optimization instruction, collect consumers' feedback on personalized marketing, as well as sales data, procurement data, logistics data, inventory data and delivery data of the target product through online surveys, social media interactions, etc., and use the above data as supply feedback data; that is, marketing and supply chain data of the target product;

[0135] After feature engineering of the supply feedback data, the corresponding feedback features are extracted; based on the feedback features, a multi-objective optimization algorithm is used to optimize each link of the current supply chain of the target product, such as reducing the inventory of the target product, adjusting the purchase price, etc.; and the supply chain of the optimized target product is obtained;

[0136] When using, combine the contents in steps 501 and 502:

[0137] After collecting various feedback data, the corresponding feedback features are extracted, and based on the identification of various risk nodes, the multi-objective optimization algorithm is used to optimize the current supply chain links. Different from the optimization of the target product marketing strategy, it can increase the target sales volume and sales speed and reduce inventory.

[0138] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into levels such as goals, criteria, and plans, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for dealing with target systems with hierarchical and staggered evaluation indicators, and when the target value is difficult to describe quantitatively, the AHP is an effective decision-making tool.

[0139] The core of the hierarchical analysis method is to decompose the decision problem into multiple levels to form a hierarchical structure, which usually includes the target level, the criterion level, the sub-criterion level and the solution level. By solving the eigenvector of the judgment matrix, the priority weight of each element at each level to an element at the previous level is obtained, and the final weight of each alternative solution to the total goal is recursively merged by the weighted sum method, so as to find the optimal solution.

[0140] See also Figure 2 The present invention provides an enterprise information management system based on big data, including:

[0141] The sales forecasting unit identifies abnormal risk points in the target product supply chain and the sales data of the target product when the abnormal risk points occur, and analyzes and obtains the correlation coefficient between the two , if the correlation coefficient Exceeding expectations, issuing sales forecast instructions to external parties;

[0142] The marketing content push unit collects data on the target product and related data if the sales forecast value of the target product is lower than expected, and collects and obtains a collection of product marketing data; it classifies consumers into different consumer groups, matches corresponding marketing strategies for consumer groups in the marketing plan library, and recommends content of interest;

[0143] Inventory alarm unit generates marketing value from the marketing indicator data set of the target product If the marketing value Exceeded expectations, based on sales velocity data and marketing value Constrain the safety stock of the target product. If the stock of the target product exceeds the safety stock, an alarm command will be issued to the outside.

[0144] The operation analysis unit builds the alarm aggregation degree based on the time node when the alarm instruction is received , if the alarm concentration Exceeded expectations, collected inventory management process data of target products and generated operational value , if the operating value Optimize inventory management processes without exceeding operational thresholds;

[0145] Process optimization unit, collects sales feedback data of target products and builds a system to evaluate the improvement of marketing effect of target products If the improvement If the improvement threshold is not exceeded, the target product supply chain is optimized using a multi-objective optimization algorithm based on the target product's marketing and supply chain data.

[0146] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. 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 computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0147] Those of ordinary skill 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 to be beyond the scope of this application.

[0148] Those skilled in the art can 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.

[0149] In the several embodiments provided in the present 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 only schematic. For example, the division of the units is only for some logical functions. There may be other division methods in actual implementation, 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.

[0150] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0151] 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.

[0152] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0153] 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 who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An enterprise information management method based on big data, characterized by: include, Identify abnormal risk points in the target product supply chain and the sales data of the target product when the abnormal risk points occur, and analyze and obtain the correlation coefficient between the two , if the correlation coefficient If the sales volume exceeds expectations, a sales forecast instruction is issued to the outside. The link data of the supply chain of the target product is analyzed, and the link data is used as input. The trained abnormal data recognition model is used to identify the abnormal risk points of the data abnormalities, and the time node where the abnormal risk point is generated is used as the risk node; By analyzing the historical sales data of the target product, the sales data of the target product at each risk node is obtained, and the relative deviation between the link data at the risk node and the preset standard value is used as the risk degree; If the sales forecast of the target product is lower than expected, collect data on the target product and related data, including basic information of consumers, collect consumer transaction data, consumer feedback data, supply chain data collection, transportation data, inventory and delivery data, financial data, and market data; summarize and obtain product marketing data sets; classify consumers into different consumer groups, match corresponding marketing strategies for consumer groups in the marketing plan library, and recommend interest content; Generate marketing value from the marketing indicator data set of the target product If the marketing value Exceeded expectations, based on sales velocity data and marketing value Constrain the safety stock of the target product. If the stock of the target product exceeds the safety stock, an alarm command will be issued to the outside. Construct alarm aggregation based on the time node when the alarm command is received , if the alarm concentration Exceeded expectations, collected inventory management process data of target products and generated operational value , if the operating value Optimize inventory management processes without exceeding operational thresholds; Collect sales feedback data of target products and construct a system to evaluate the improvement of marketing effect of target products If the improvement If the improvement threshold is not exceeded, the target product supply chain is optimized using a multi-objective optimization algorithm based on the target product's marketing and supply chain data.

2. The enterprise information management method based on big data according to claim 1, characterized in that: Get the risk degree of several consecutive risk nodes Product sales volume with target products After that, the correlation coefficient between the two is obtained. , among which, the risk And product sales Perform linear normalization and map the corresponding data values ​​to the interval Then follow the steps below: ； in, For the risk level at the risk node The value on For product sales at risk nodes The value on , is the number of risk nodes, is the weight coefficient, , ,and .

3. The enterprise information management method based on big data according to claim 2 is characterized by: After receiving the sales forecast instruction, the trained product sales forecast model is used to predict the sales volume of the target product and obtain the sales forecast value; if the sales forecast value of the target product is lower than expected, data collection is performed on the target product and related data, and the product marketing data set is obtained after aggregation.

4. The enterprise information management method based on big data according to claim 3 is characterized by: Feature extraction is performed on product marketing data to obtain corresponding marketing features. Consumers’ consumption characteristics are analyzed using data visualization tools to generate consumer portraits. After obtaining several groups of portrait data, the pre-trained hierarchical clustering algorithm is used to classify the portraits of different consumers to obtain the corresponding consumer groups.

5. The enterprise information management method based on big data according to claim 4 is characterized in that: After executing the marketing strategy on the consumer group, the marketing indicators of the marketing activities are collected and summarized to generate a marketing indicator data set; the marketing value is generated from the marketing indicator data set If the marketing value If the marketing value does not exceed the marketing threshold, adjust the marketing strategy. If the marketing value exceeds the marketing threshold, issue inventory management instructions to the outside.

6. The enterprise information management method based on big data according to claim 5 is characterized by: After receiving the inventory management instruction, the inventory level of the target product is monitored in real time, and the sales speed of the target product within the observation period is calculated. Marketing value , taking the acceptable inventory as the safety stock and impose constraints; If the current inventory of the target product does not exceed the safety stock , generate replenishment instructions and send them to the outside. If the current inventory exceeds the safety inventory, an alarm instruction will be sent to the outside.

7. The enterprise information management method based on big data according to claim 6 is characterized by: Based on the sales speed of the target product Marketing value Safety Stock The constraints are as follows: ； Weight coefficient, , ,and ; is the number of sub-periods, It is Sub-period to The difference in sales velocity within the sub-periods, is the average of the sales velocity differences, The safety stock amount.

8. The enterprise information management method based on big data according to claim 7 is characterized by: The time node when the alarm command is received is used as the alarm node, and the alarm concentration is constructed after receiving several alarm commands continuously in the current observation period. , if the alarm concentration When the preset concentration threshold is exceeded, an inventory analysis instruction is issued to the outside.

9. The enterprise information management method based on big data according to claim 8, characterized in that: in, Constructing alarm aggregation The way is as follows: ； Where: , The value is 2.718, the weight coefficient, , ,and ; is the radius of the observation period; It is The weighted value of each alarm command, It is Alarm command to The time interval between alarm instructions. The number of alarm nodes.

10. The enterprise information management method based on big data according to claim 9, characterized in that: After receiving the inventory analysis instruction, the inventory management process of the target product is monitored and data is collected in continuous sub-periods. The operation data set of the target product is generated after aggregation. The operation value is generated from the operation data set. ,in, Delivery time for orders and inventory turnover time Perform linear normalization and map the corresponding data values ​​to the interval In the following way: ； Weight coefficient, , , For the The median value of operations within a sub-period, is the corresponding mean, is the number of sub-periods.

11. An enterprise information management system based on big data, applying the method according to any one of claims 1 to 10, characterized in that: include, The sales forecasting unit identifies abnormal risk points in the target product supply chain and the sales data of the target product when the abnormal risk points occur, and analyzes and obtains the correlation coefficient between the two , if the correlation coefficient Exceeding expectations, issuing sales forecast instructions to external parties; The marketing content push unit, if the sales forecast of the target product is lower than expected, collects data on the target product and related data, including basic information of consumers, consumer transaction data, consumer feedback data, supply chain data collection, transportation data, inventory and delivery data, financial data, market data, and aggregates and obtains a collection of product marketing data; Categorize consumers into different consumer groups, match corresponding marketing strategies for consumer groups in the marketing plan library, and then recommend content of interest; Inventory alarm unit generates marketing value from the marketing indicator data set of the target product If the marketing value Exceeded expectations, based on sales velocity data and marketing value Constrain the safety stock of the target product. If the stock of the target product exceeds the safety stock, an alarm command will be issued to the outside. The operation analysis unit builds the alarm aggregation degree based on the time node when the alarm instruction is received , if the alarm concentration Exceeded expectations, collected inventory management process data of target products and generated operational value , if the operating value Optimize inventory management processes without exceeding operational thresholds; Process optimization unit, collects sales feedback data of target products and builds a system to evaluate the improvement of marketing effect of target products If the improvement If the improvement threshold is not exceeded, the target product supply chain is optimized using a multi-objective optimization algorithm based on the target product's marketing and supply chain data.

Images