An intelligent analysis system for purchase, sales and inventory

Abstract

The present invention provides a purchase, sale and inventory intelligent analysis system, including: a data management module, an external system connection module and an inventory change operation module, and also includes: an intelligent analysis module; the intelligent analysis module includes: an analysis instruction acquisition unit, used to obtain the data analysis instructions of the staff; an instruction parsing unit, used to parse the data analysis instructions, determine the data capture rules, data analysis rules and output rules; a data capture unit, used to extract the data to be analyzed from the data management module based on the data capture rules; a data analysis unit, used to analyze the data to be analyzed based on the data analysis rules to obtain the analysis results; an analysis output unit, used to output the analysis results based on the output rules. The purchase, sale and inventory intelligent analysis system of the present invention analyzes according to the data records to generate various analysis reports, and presents them according to the presentation method set by the staff, so as to enable the staff to better manage the goods in the purchase, sale and inventory links of the enterprise.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to an intelligent analysis system for purchasing, selling and inventory. Background Art

[0002] The goods management in the purchase, inventory and sales links of an enterprise is a huge workload due to the wide variety of goods, large business volume and complex inventory management. It is also easy to make various errors based on the subjective influence of the staff if it is managed manually. The use of a purchase, sales and inventory management system can improve the work efficiency of the staff. It not only converts the original manual operation into automatic system management, but also avoids the errors based on the subjective influence of the staff in manual operation, and achieves clear purchase, sales and inventory management.

[0003] However, the existing purchase, sales and inventory management systems are simply data recording and calling, and do not have the function of analyzing based on the data records. Summary of the invention

[0004] One of the purposes of the present invention is to provide an intelligent analysis system for purchase, sales and inventory, which performs analysis based on data records to generate various analysis reports, and presents them according to the presentation method set by the staff, so as to enable the staff to better manage the goods in the purchase, sales and inventory links of the enterprise.

[0005] An intelligent analysis system for purchase, sales and inventory provided by an embodiment of the present invention includes: a data management module, an external system connection module and an inventory change operation module, and also includes: an intelligent analysis module;

[0006] Intelligent analysis modules include:

[0007] An analysis instruction acquisition unit, used to acquire data analysis instructions from staff members;

[0008] An instruction parsing unit, used to parse data analysis instructions and determine data capture rules, data analysis rules and output rules;

[0009] A data capture unit, used to extract the data to be analyzed from the data management module based on the data capture rules;

[0010] A data analysis unit, used to analyze the data to be analyzed based on the data analysis rules to obtain analysis results;

[0011] The analysis output unit is used to output the analysis results based on the output rules.

[0012] Preferably, the data management module includes:

[0013] Supplier management unit, used to manage supplier-related data;

[0014] Dealer management unit, used to manage dealer-related data;

[0015] Warehouse management unit, used to manage warehouse-related data;

[0016] Brand management unit, used to manage brand-related data;

[0017] The goods management unit is used to manage the relevant data of goods;

[0018] The cargo owner management unit is used to manage the cargo owner's related data;

[0019] Purchase price management unit, used to manage purchase price related data;

[0020] Profit management unit, used to manage profit-related data;

[0021] The permission management unit is used to manage permission-related data.

[0022] Preferably, the external system connection module includes:

[0023] OMS system access module, used to connect to the external OMS system;

[0024] ERP system access module, used to connect to external ERP system.

[0025] Preferably, the inventory change operation module includes:

[0026] The storage operation unit is used to receive the storage operation of the user;

[0027] The outbound operation unit is used to receive the outbound operation of the user;

[0028] An inventory operation unit, used for receiving an inventory operation from a user;

[0029] A warehouse transfer operation unit, used to receive a user's warehouse transfer operation;

[0030] The destroy operation unit is used to receive a destroy operation from a user.

[0031] Preferably, the purchase, sales and inventory intelligent analysis system further includes: an account management module for managing the enterprise's login account and account information;

[0032] The account management module includes:

[0033] The permission configuration unit is used to create new roles within the enterprise and configure the permissions of each role within the enterprise;

[0034] The sub-account management unit is used to create new employee accounts for the company's staff and associate the employee accounts with roles.

[0035] Preferably, the purchase, sales and inventory intelligent analysis system further includes: an inventory analysis module;

[0036] The Inventory Analysis module performs the following operations:

[0037] At preset intervals or upon receiving inventory analysis instructions from staff, obtain the current inventory information of each item in the warehouse;

[0038] Get the inventory threshold of each product;

[0039] Analyze current inventory information and determine the current inventory quantity of each item;

[0040] When the current inventory is less than the inventory threshold, the corresponding goods are added to the list to be purchased;

[0041] Output the list of items to be purchased.

[0042] Preferably, the inventory threshold is determined by the following steps:

[0043] Obtain the purchase data and historical sales data of goods;

[0044] Analyze the purchase data and determine the purchase cycle;

[0045] Using a preset first feature extraction rule to extract features from the purchase cycle and historical sales data, and obtaining multiple first feature values;

[0046] Inputting a plurality of first characteristic values ​​into a preset first neural network model to determine the purchase and sales factors;

[0047] Based on the purchase and sales factors, a comparison table of preset purchase and sales factors and the first stocking quantity is queried to determine the first stocking quantity;

[0048] Obtain hot information related to the product within a preset time and the comment information corresponding to the hot information;

[0049] Using a preset second feature extraction rule to extract features from the hot information and comment information, and obtaining a plurality of second feature values;

[0050] Inputting the plurality of second eigenvalues ​​into a preset second neural network model to determine a hot spot factor;

[0051] Based on the hotspot factor, a comparison table of preset hotspot factors and second stocking quantities is searched to determine the second stocking quantity;

[0052] Obtain browsing information of display interfaces associated with goods within a preset time;

[0053] Analyze browsing information, determine each browser and each browser's browsing behavior, and add the browser to the list for behavior analysis;

[0054] Based on historical sales data, determine whether the viewer has purchased the product after browsing;

[0055] When the viewer purchases the goods, the viewer is deleted from the list of pending behavior analysis;

[0056] Using a preset third feature extraction rule to extract features from the browsing behavior of each viewer in the behavior analysis list, and obtaining multiple behavior features corresponding to each viewer;

[0057] Inputting the plurality of behavioral characteristics into a preset third neural network model to determine the behavioral factors;

[0058] Determine the purchase probability of each viewer in the behavior analysis list based on the behavior factor and the preset comparison table of behavior factor and purchase probability;

[0059] Determine a third stock quantity based on the number of viewers in the behavior analysis list whose purchase probability is greater than a preset probability threshold;

[0060] An inventory threshold is determined based on the first stocking quantity, the second stocking quantity, and the third stocking quantity.

[0061] Preferably, obtaining hot information related to the product within a preset time includes:

[0062] Using a preset fourth feature extraction rule to extract features of the product information of the product to obtain a plurality of fourth feature values;

[0063] constructing a second signature vector based on the plurality of fourth eigenvalues;

[0064] Get all hotspot information within the preset time;

[0065] Using a preset fourth feature extraction rule to extract features from each hotspot information to obtain multiple third feature values;

[0066] constructing a first signature vector based on the plurality of third eigenvalues;

[0067] Calculate the similarity between the first labeled vector and the second labeled vector. The similarity calculation formula is as follows:

[0068]

[0069] Among them, SP represents similarity; a i represents the i-th parameter value of the first marker vector; b i represents the i-th parameter value of the second marker vector; n represents the total number of parameters of the first marker vector or the total number of parameters of the second marker vector;

[0070] When the similarity is greater than a preset similarity threshold, it is determined that the hotspot information is related to the product.

[0071] Preferably, the purchase, sales and inventory intelligent analysis system further includes:

[0072] Joint decision-making module, used to establish joint analysis groups among enterprises and share data within the group;

[0073] The joint decision module performs the following operations:

[0074] Obtain historical sales data of the same products from other companies;

[0075] Using a preset first feature extraction rule to extract features from the historical sales data of the same goods of other companies during the purchase period, and obtaining a plurality of first feature values;

[0076] Inputting a plurality of first characteristic values ​​into a preset first neural network model to determine the purchase and sales factors;

[0077] Based on the purchase and sales factors, a comparison table of preset purchase and sales factors and the first stocking quantity is queried to determine the first stocking quantity determined based on the historical sales data of each other enterprise;

[0078] The first stock quantity of the enterprise is corrected based on the following formula:

[0079]

[0080] Among them, B 1 Indicates the first stock quantity after correction; x j is the first stock quantity determined by the historical sales data of the jth other enterprise; N is the total number of other enterprises; y 1 is the first stock quantity before correction; γ 1 , γ 2 is the preset weight; F(·) is the rounding function that rounds up to an integer.

[0081] Preferably, the purchase, sales and inventory intelligent analysis system further includes:

[0082] The scheduling module is used to obtain the goods scheduling request of the enterprise and obtain the scheduling response to the goods scheduling request from other enterprises;

[0083] The scheduling module performs the following operations:

[0084] Get the goods dispatch request sent by the staff;

[0085] Output the preset template of goods dispatch request;

[0086] Receiving staff's filling of the goods dispatch request form template and generating the goods dispatch request form;

[0087] Execute the preset review process corresponding to the goods dispatch request;

[0088] When the review is passed, obtain the list of dispatchable goods of other enterprises in the preset goods dispatch coordination group;

[0089] Determine other companies that can cooperate based on the goods dispatch request and the dispatchable goods list;

[0090] Send cargo dispatch requests to other companies that can cooperate;

[0091] Receive goods dispatch negotiation documents corresponding to goods dispatch request documents from other enterprises that can cooperate;

[0092] Analyze the goods dispatch negotiation document and determine the dispatch price and dispatch time of the goods;

[0093] Obtain the credit rating of other companies that provide goods dispatch bargaining documents;

[0094] Based on the credit rating, dispatch price and dispatch time, the target enterprise is determined and a dispatch agreement is sent;

[0095] The reputation evaluation value is determined through the following steps:

[0096] Configure reputation rating values ​​for enterprises;

[0097] Get the dispatch history of the enterprise in response to other enterprises;

[0098] Analyze the dispatch history records and determine the dispatch execution status corresponding to the dispatch price document for each dispatch;

[0099] After each scheduling is executed, the reputation evaluation value is adjusted based on the scheduling execution status and the reputation evaluation value; the adjustment formula is as follows:

[0100]

[0101] Where X represents the adjusted credit rating value; T 0 is the credit evaluation value before adjustment; d represents the quantitative value of the dispatch execution. When the dispatch execution meets the dispatch negotiation agreement, d is a positive value, otherwise it is a negative value; t represents the adjustment value, t 0 Indicates the fine-tuning value. When d is a positive value, t-dt 0 >0; the value of |d| is determined by querying a preset coefficient table based on the consecutive number of historical scheduling execution situations that are the same as the current scheduling execution situation; the larger the consecutive number in the coefficient table, the larger the corresponding |d| value.

[0102] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0103] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0104] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0105] Figure 1 A schematic diagram of a purchase, sales and inventory intelligent analysis system in an embodiment of the present invention;

[0106] Figure 2 is a schematic diagram of an intelligent analysis module in an embodiment of the present invention;

[0107] Figure 3 This is an architecture diagram of a purchase, sales and inventory intelligent analysis system in an embodiment of the present invention;

[0108] Figure 4 The figure is a schematic diagram of external data import in an embodiment of the present invention. DETAILED DESCRIPTION

[0109] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0110] The embodiment of the present invention provides a purchase, sales and inventory intelligent analysis system, such as Figure 1 and 2 As shown, it includes: a data management module 1, an external system connection module 2 and an inventory change operation module 3, and also includes: an intelligent analysis module 4;

[0111] Intelligent analysis module 4 includes:

[0112] The analysis instruction acquisition unit 41 is used to acquire data analysis instructions from the staff; the data analysis instructions include: daily analysis of purchase, sales and inventory, daily analysis of purchases, daily analysis of sales, etc.;

[0113] The instruction parsing unit 42 is used to parse the data analysis instruction and determine the data capture rules, data analysis rules and output rules;

[0114] The data capture unit 43 is used to extract the data to be analyzed from the data management module based on the data capture rules; the data capture rules specify the form of the captured data, such as the date of the data analyzed in the sales daily report, and the sales data of the corresponding date can be obtained;

[0115] The data analysis unit 44 is used to analyze the data to be analyzed based on the data analysis rules to obtain analysis results; for example, the analysis results of the daily sales analysis include: sales growth, growth trend, etc.;

[0116] An analysis output unit 45 is used to output the analysis results based on the output rules. The output rules specify the output form of the analysis results, such as a pie chart, a curve chart, etc.;

[0117] Wherein, the data management module 1 includes:

[0118] The supplier management unit is used to manage supplier-related data; supplier information maintenance can import suppliers and create new suppliers according to the import template on the supplier information list. [Supplier Name] is required, and the supplier maintained in the system must be unique and cannot be repeated; [Company Name]: the name of the cooperating dealer; [Company Address]: the company address is the dealer's address; [Cooperation Time]: start time-end time, whether the current time is within the cooperation period determines whether the supplier is in the cooperation period; [Cooperation Attachment]: upload contracts, etc.; [Contact Information]: multiple supplier contact information, contacts and contact addresses can be maintained. When entering documents, you can select the maintained contact to select the address; [Account Information]: multiple account information can be maintained. This account information is used for settlement. The settlement account number is determined based on the selected bank and account during settlement; Figure 3 It is a specific system architecture diagram;

[0119] The dealer management unit is used to manage dealer-related data; dealer management; fill in dealer information according to the imported template or click Add Dealer to create dealer information. Dealer information: [Dealer Name]: unique in the system and cannot be repeated; [Company Name]: name of the cooperative dealer company; [Company Address]: the company address is the dealer company address; [Dealer Level]: no level maintenance has been done for the time being, so this version can be ignored; [Cooperation Time]: start time-end time, whether the current time is within the cooperation time period determines whether the dealer is in the cooperation period; [Cooperation Attachment]: upload contracts, etc.; [Contact Information]: multiple dealer contact information, contacts and contact addresses can be maintained. When entering documents, you can select the maintained contact to select the address; [Account Information]: multiple account information can be maintained. This account information is used for settlement. The settlement account is determined according to the selected bank and account during settlement; Level management: dealers need to set the corresponding level, which corresponds to the price (markup) of the product level, and the sales price of the product is calculated when creating a sales order.

[0120] The warehouse management unit is used to manage warehouse-related data; after configuring [Physical Warehouse] and [Consignor] for enterprise users, enterprise users can create a new cloud warehouse; fill in warehouse details; [Warehouse Name] The name of the warehouse, which will be used for various inventory operations in this system; [Warehouse Type] Physical warehouse: a warehouse with a physical warehouse and a consignor code; Virtual warehouse: a warehouse without a physical warehouse and a consignor code, and the in and out operations of this warehouse are all automatically virtual returns by the system; [Default Express] The warehouse dimension can specify the supported express. If the default express is used, the express will be used to push down when the outbound document is issued; [Provincial, municipal, and district address, zip code, contact person, contact number] The contact address here is the default sender information of the warehouse, which generally automatically brings out the default contact address and contact person of the physical warehouse; Add warehouse configuration batch rules; [Rule 1] Expiration date management; Expiration date priority refers to the expiration date as the basis, and the closer to the expiration date, the priority is given to outbound; [Rule 2] First in, first out; First in, first out refers to the entry time as the basis, and the earlier the entry time, the priority is given to outbound;

[0121] Brand management unit, used to manage brand-related data and maintain cooperative brand information;

[0122] The product management unit is used to manage product-related data. Before creating a product, you need to maintain the brand. The brand is not mandatory. To add a new product, import the product list according to the import template. To create a new product, enter it directly on the platform.

[0123] The cargo owner management unit is used to manage the cargo owner's related data;

[0124] The purchase price management unit is used to manage the purchase price related data; import purchase price; purchase price maintenance is the supplier cooperation status corresponding to the sku and the purchase price maintenance, which can be imported in batches. One sku can be supplied by multiple suppliers, and the corresponding supply price is maintained here; product supply details; product supply details are the list of suppliers supplying the product. View the pop-up window, click the drop-down, and select Add to add a supplier separately; view purchase price details; each supplier card can add a price. After adding, the status is [Created]. You need to click Submit for review. It will take effect after the review is completed.

[0125] Profit management unit, used to manage profit-related data; Profit management: The profit list pulls all product SKUs, and each product has all levels of level management; Batch set product level profits; Import profits; Product level profits can be imported in batches; All level prices must be reviewed after processing. After updating the profit data, the status will be updated to [Created]. Click [Submit for Review] to make the profit effective after the review is passed;

[0126] The permission management unit is used to manage permission-related data.

[0127] In addition, there is filing management; import filing data according to the product filing import template; after the product file maintenance is completed, the goods with a trade type of bonded must complete the filing before stock declaration and other operations can be carried out; after completing the creation of the filing data, you need to click Submit before submitting it to CCS operation (if the submission fails here, please select to confirm whether the SKU has been filed in the customs clearance system. If the old data has been filed, you need to contact the customs to delete and update the data. At this time, the filing data must be accurate, otherwise it will affect the online C-order declaration results).

[0128] In one embodiment, the external system connection module 2 includes:

[0129] OMS system access module, used to connect to the external OMS system; OMS system is an order management system;

[0130] ERP system access module is used to connect to external ERP systems. ERP (Enterprise Resource Planning) is an enterprise information management system that integrates material resources, financial resources and information resources for the manufacturing industry. Figure 4 Import diagrams for external ERP data.

[0131] Inventory change operation module 3 includes:

[0132] The incoming operation unit is used to receive incoming operations from users; import incoming orders; import incoming orders based on incoming documents on the import page; add incoming orders, for which you need to select the incoming type, associated documents, planned incoming date, receiving warehouse, and the item details are automatically filled in;

[0133] The outbound operation unit is used to receive outbound operations from users; import outbound documents; import outbound orders based on import templates; add outbound orders, Outbound Type: Sales Outbound, Transfer Outbound, Other Outbound, Destruction Outbound; Associated Documents: select associated documents, shipping warehouse and logistics, consignee information, and product details are automatically filled;

[0134] An inventory counting operation unit, used to receive inventory counting operations from users and perform inventory counting operations;

[0135] The warehouse transfer operation unit is used to receive the user's warehouse transfer operation and move the goods in the entire warehouse to the new warehouse;

[0136] The destruction operation unit is used to receive the user's destruction operation, that is, to destroy the goods and execute the warehouse sales operation.

[0137] In one embodiment, the purchase, sales and inventory intelligent analysis system further includes: an account management module for managing the login account and account information of the enterprise;

[0138] The account management module includes:

[0139] The permission configuration unit is used to create new roles within the enterprise and configure the permissions of each role within the enterprise; the main functions of the permission configuration unit are: adding new roles, that is, creating new roles required for enterprise management, including: procurement, finance, warehouse, etc.; assigning permissions such as operation menus and functions visible to the new roles.

[0140] The sub-account management unit is used to create new employee accounts for the company's staff and associate the employee accounts with roles. The main functions of sub-account management are: adding sub-accounts. The company's main account can add member sub-accounts, i.e. employee accounts; binding roles to open up available permissions for sub-accounts.

[0141] In one embodiment, the purchase, sales and inventory intelligent analysis system further includes: an inventory analysis module;

[0142] The Inventory Analysis module performs the following operations:

[0143] At preset intervals or upon receiving inventory analysis instructions from staff, obtain the current inventory information of each item in the warehouse;

[0144] Get the inventory threshold of each product;

[0145] Analyze current inventory information and determine the current inventory quantity of each item;

[0146] When the current inventory is less than the inventory threshold, the corresponding goods are added to the list to be purchased;

[0147] Output the list of items to be purchased.

[0148] Through the inventory analysis module, it is possible to analyze whether the current inventory meets sales demand in order to respond to possible sales situations and improve the company's sales response capabilities.

[0149] The inventory threshold is determined by the following steps:

[0150] Obtain the purchase data and historical sales data of goods;

[0151] Analyze the purchase data and determine the purchase cycle;

[0152] The preset first feature extraction rule is used to extract features from the purchase cycle and historical sales data to obtain multiple first feature values; the first feature values ​​include: the first sales volume of each purchase cycle, the average value of all first sales volumes, the maximum value of all first sales volumes, the variance of all first sales volumes, the first sales volume of the same period in history, the maximum value of the first sales volume of the same period in history, etc.;

[0153] Inputting a plurality of first characteristic values ​​into a preset first neural network model to determine the purchase and sales factor; the first neural network model is trained and converged based on a large amount of data in advance, and is used for analyzing historical sales data and predicting sales volume in a future purchase cycle to obtain the purchase and sales factor;

[0154] Based on the purchase and sales factors, the preset purchase and sales factors and the comparison table of the first stocking quantity are queried to determine the first stocking quantity; the preset purchase and sales factors and the comparison table of the first stocking quantity convert the prediction result of the first neural network model, that is, the purchase and sales factors, into a specific first stocking quantity; the comparison table of the purchase and sales factors and the first stocking quantity is also a statistical form obtained in advance through a large amount of data analysis;

[0155] Obtain hot information related to products within a preset time and corresponding comment information of hot information; hot information includes: popular TV series, current news, etc. For example, a piece of clothing becomes popular due to a certain movie or TV series, and its sales volume can also increase predictably. Therefore, considering the impact of hot information during inventory analysis can effectively ensure that inventory can cope with sales in the future purchase cycle;

[0156] Using a preset second feature extraction rule to extract features from hot information and comment information, and obtaining multiple second feature values; the second feature values ​​include: a feature value indicating whether it is positive hot information, a feature value indicating whether it is negative hot information, a feature value indicating the number of followers, etc.;

[0157] Inputting a plurality of second characteristic values ​​into a preset second neural network model to determine a hot spot factor; the second neural network model is trained and converged based on the impact data of a large amount of hot spot information on the goods;

[0158] Based on the hotspot factor, a comparison table of preset hotspot factors and second stocking quantities is queried to determine the second stocking quantity; the comparison table of hotspot factors and second stocking quantities is a table for quantifying hotspot factors based on a large amount of data analysis;

[0159] Obtain browsing information of display interfaces associated with goods within a preset time;

[0160] Analyze browsing information, determine each browser and each browser's browsing behavior, and add the browser to the list for behavior analysis;

[0161] Based on historical sales data, determine whether the viewer has purchased the product after browsing;

[0162] When the viewer purchases the goods, the viewer is deleted from the list of pending behavior analysis;

[0163] Using a preset third feature extraction rule to extract features from the browsing behavior of each viewer in the behavior analysis list, and obtaining multiple behavior features corresponding to each viewer;

[0164] Inputting the plurality of behavioral characteristics into a preset third neural network model to determine the behavioral factors;

[0165] Determine the purchase probability of each viewer in the behavior analysis list based on the behavior factor and the preset comparison table of behavior factor and purchase probability;

[0166] Determine a third stock quantity based on the number of viewers in the behavior analysis list whose purchase probability is greater than a preset probability threshold;

[0167] Determine the inventory threshold based on the first, second and third stocking quantities. Realize the integration of enterprise sales data, hot information and browser behavior to reasonably determine the inventory threshold to ensure that the inventory can cope with the next cycle of sales and realize rational inventory management.

[0168] Among them, obtaining hot information related to goods within a preset time includes:

[0169] The product information of the product is subjected to feature extraction using a preset fourth feature extraction rule to obtain a plurality of fourth feature values; the fourth feature value can extract keywords of description information in the product information; taking clothes as an example, feature extraction can be performed on pictures used to describe clothes in the product information to extract parameter values ​​representing information such as style, color, and pattern of the clothes;

[0170] constructing a second signature vector based on the plurality of fourth eigenvalues;

[0171] Get all hotspot information within the preset time;

[0172] Using the preset fourth feature extraction rule to extract features from each hotspot information, a plurality of third feature values ​​are obtained; taking a movie as an example, parameter values ​​such as the style, color, and pattern of the characters' clothing are extracted;

[0173] constructing a first signature vector based on the plurality of third eigenvalues;

[0174] Calculate the similarity between the first labeled vector and the second labeled vector. The similarity calculation formula is as follows:

[0175]

[0176] Among them, SP represents similarity; a i represents the i-th parameter value of the first marker vector; b i represents the i-th parameter value of the second marker vector; n represents the total number of parameters of the first marker vector or the total number of parameters of the second marker vector;

[0177] When the similarity is greater than a preset similarity threshold (eg, 0.96), it is determined that the hotspot information is related to the product.

[0178] By extracting features and calculating similarities, we can determine whether hot information is related to the product, thereby providing a data basis for analyzing the impact of hot information on inventory thresholds.

[0179] In one embodiment, the purchase, sales and inventory intelligent analysis system further includes:

[0180] Joint decision-making module, used to establish joint analysis groups among enterprises and share data within the group; for example: historical sales data, minimum inventory data, etc.;

[0181] The joint decision module performs the following operations:

[0182] Obtain historical sales data of the same products from other companies;

[0183] The preset first feature extraction rule is used to extract features from the historical sales data of the same goods of other companies in the purchase cycle to obtain multiple first feature values; the first feature values ​​include: the first sales volume of each purchase cycle, the average value of all first sales volumes, the maximum value of all first sales volumes, the variance of all first sales volumes, the first sales volume in the same historical period, the maximum value of the first sales volume in the same historical period, etc.;

[0184] Inputting a plurality of first characteristic values ​​into a preset first neural network model to determine the purchase and sales factor; the first neural network model is trained and converged based on a large amount of data in advance, and is used for analyzing historical sales data and predicting sales volume in a future purchase cycle to obtain the purchase and sales factor;

[0185] Based on the purchase and sales factors, the preset comparison table of purchase and sales factors and the first inventory quantity is queried to determine the first inventory quantity based on the historical sales data of each other enterprise; the preset comparison table of purchase and sales factors and the first inventory quantity converts the prediction result of the first neural network model, that is, the purchase and sales factors, into a specific first inventory quantity; the comparison table of purchase and sales factors and the first inventory quantity is also a statistical form obtained in advance through a large amount of data analysis.

[0186] The first inventory quantity of the enterprise is corrected based on the following formula:

[0187]

[0188] Among them, B 1 Indicates the first stock quantity after correction; x j is the first stock quantity determined by the historical sales data of the jth other enterprise; N is the total number of other enterprises; y 1is the first stock quantity before correction; γ 1 , γ 2 is the preset weight; F(·) is the rounding function that rounds up to an integer.

[0189] The first stock quantity is adjusted by referring to the sales of the same goods of other enterprises, so that the first stock quantity analyzed based on the sales data can more accurately reflect the impact of the sales environment.

[0190] In one embodiment, the purchase, sales and inventory intelligent analysis system further includes:

[0191] The scheduling module is used to obtain the goods scheduling request of the enterprise and obtain the scheduling response to the goods scheduling request from other enterprises;

[0192] The scheduling module performs the following operations:

[0193] Get the goods dispatch request sent by the staff;

[0194] Output the preset template of goods dispatch request;

[0195] Receiving staff members' filling in of the template of the goods dispatch request and generating the goods dispatch request; the goods dispatch request includes description information of the required goods, required time limit information, etc.;

[0196] Execute the preset review process corresponding to the goods dispatch request; the review is mainly for the goods dispatch request, for example: if the staff is a salesperson, it needs to be sent to the staff's superior supervisor, manager, etc. for review; when the amount is large, it also needs to be reviewed by the general manager.

[0197] When the review is passed, the dispatchable goods list of other enterprises in the preset goods dispatch coordination group is obtained; the dispatchable goods list can be pre-stored on the server, and the dispatch module can connect to the server to obtain the dispatchable goods list pre-stored by other enterprises;

[0198] Based on the goods dispatch request and the dispatchable goods list, determine other enterprises that can cooperate; other enterprises that can cooperate are enterprises that have goods corresponding to the goods dispatch request on the dispatchable goods list;

[0199] Send cargo dispatch requests to other companies that can cooperate;

[0200] Receive goods dispatch negotiation documents corresponding to goods dispatch request documents from other enterprises that can cooperate;

[0201] Analyze the goods dispatch negotiation document and determine the dispatch price and dispatch time of the goods;

[0202] Obtain the credit rating of other companies that provide goods dispatch bargaining documents;

[0203] Based on the reputation evaluation value, dispatch price and dispatch time, the target enterprise is determined and a dispatch agreement is sent; when the reputation evaluation value is greater than the preset reputation evaluation threshold, and the dispatch price is the lowest among all enterprises and the dispatch time is the fastest, other enterprises are the target enterprises; by adding the reputation evaluation value, it is determined whether the target enterprise is reliable, and by signing the dispatch agreement, the reliability of the dispatch execution is guaranteed. Among them, the reputation evaluation value is determined through the following steps:

[0204] Configure reputation rating values ​​for enterprises;

[0205] Get the dispatch history of the enterprise in response to other enterprises;

[0206] Analyze the dispatch history records and determine the dispatch execution status corresponding to the dispatch price document for each dispatch;

[0207] After each scheduling is executed, the reputation evaluation value is adjusted based on the scheduling execution status and the reputation evaluation value; the adjustment formula is as follows:

[0208]

[0209] Where X represents the adjusted credit rating value; T 0 is the credit evaluation value before adjustment; d represents the quantitative value of the dispatch execution. When the dispatch execution meets the dispatch negotiation agreement, d is a positive value, otherwise it is a negative value; t represents the adjustment value, t 0 Indicates the fine-tuning value. When d is a positive value, t-dt 0 >0; the value of |d| is determined by querying the preset coefficient table based on the continuous number of historical scheduling execution conditions that are the same as the current scheduling execution conditions; the larger the continuous number in the coefficient table, the larger the corresponding |d| value; through the coefficient table, when the enterprise scheduling execution conditions have always been in line with the scheduling bargaining book, the d value becomes larger and larger; when the enterprise scheduling execution conditions are consistently inconsistent with the scheduling bargaining book, the -|d| value becomes larger; to ensure that the adjustment range of continuously good enterprises is rewarded, and the continuous punishment is relatively increased. Urge enterprise scheduling to meet the scheduling bargaining book and ensure fair competition.

[0210] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. An intelligent purchase, sales and inventory analysis system, comprising: The data management module, the external system connection module and the inventory change operation module are characterized in that they also include: an intelligent analysis module; The intelligent analysis module includes: An analysis instruction acquisition unit, used to acquire data analysis instructions from staff members; An instruction parsing unit, used to parse the data analysis instruction and determine data capture rules, data analysis rules and output rules; A data capture unit, used to extract the data to be analyzed from the data management module based on the data capture rule; A data analysis unit, configured to analyze the data to be analyzed based on the data analysis rules to obtain an analysis result; An analysis output unit, configured to output the analysis result based on the output rule; The inventory analysis module performs the following operations: At every preset time or when receiving an inventory analysis instruction from a staff member, obtain the current inventory information of each product in the warehouse, obtain the inventory threshold of each product, parse the current inventory information, determine the current inventory quantity of each product, and when the current inventory quantity is less than the inventory threshold, add the corresponding product to a to-be-purchased list and output the to-be-purchased list; The inventory threshold is determined by the following steps: Obtain the purchase data and historical sales data of the goods, Analyze the purchase data and determine the purchase cycle, Using a preset first feature extraction rule to extract features from the purchase cycle and the historical sales data to obtain a plurality of first feature values, Input the plurality of the first characteristic values ​​into a preset first neural network model to determine the purchase and sales factor, Based on the purchase and sales factor, a comparison table of preset purchase and sales factors and the first stocking quantity is queried to determine the first stocking quantity. Obtain hot information related to the product within a preset time and comment information corresponding to the hot information, Using a preset second feature extraction rule to extract features from the hot information and the comment information to obtain a plurality of second feature values, Inputting a plurality of the second characteristic values ​​into a preset second neural network model to determine a hot spot factor, Based on the hotspot factor, a comparison table of preset hotspot factors and second stocking quantities is searched to determine the second stocking quantity. Obtain browsing information of the display interface associated with the product within a preset time, Analyze the browsing information, determine each browser and the browsing behavior of each browser and add the browser to the list for behavior analysis. Based on historical sales data, determine whether the browser has purchased the product after browsing. When the browser purchases the product, the browser is deleted from the list to be analyzed. A preset third feature extraction rule is used to extract features from the browsing behaviors of each of the viewers in the behavior analysis list to obtain a plurality of behavior features corresponding to each of the viewers. Inputting a plurality of said behavior characteristics into a preset third neural network model to determine the behavior factor, Based on the behavior factor and a comparison table of the preset behavior factor and purchase probability, determining the purchase probability of each of the viewers in the behavior analysis list, Determine a third stock quantity based on the number of viewers in the behavior analysis list whose purchase probability is greater than a preset probability threshold, The inventory threshold is determined based on the first stocking quantity, the second stocking quantity, and the third stocking quantity.

2. The intelligent analysis system for purchase, sales and inventory as claimed in claim 1, characterized in that: The data management module comprises: Supplier management unit, used to manage supplier-related data; Dealer management unit, used to manage dealer-related data; Warehouse management unit, used to manage warehouse-related data; Brand management unit, used to manage brand-related data; The goods management unit is used to manage the relevant data of goods; The cargo owner management unit is used to manage the cargo owner's related data; Purchase price management unit, used to manage purchase price related data; Profit management unit, used to manage profit-related data; The permission management unit is used to manage permission-related data.

3. The intelligent analysis system for purchase, sales and inventory as claimed in claim 1, characterized in that: The external system connection module includes: OMS system access module, used to connect to the external OMS system; ERP system access module, used to connect to external ERP system.

4. The intelligent analysis system for purchase, sales and inventory as claimed in claim 1, characterized in that: The inventory change operation module includes: The storage operation unit is used to receive the storage operation of the user; The outbound operation unit is used to receive the outbound operation of the user; An inventory operation unit, used for receiving an inventory operation from a user; A warehouse transfer operation unit, used to receive a user's warehouse transfer operation; The destroy operation unit is used to receive a destroy operation from a user.

5. The intelligent analysis system for purchase, sales and inventory as claimed in claim 1, characterized in that: Also includes: Account management module, used to manage the enterprise's login account and account information; The account management module includes: The permission configuration unit is used to create new roles within the enterprise and configure the permissions of each role within the enterprise; The sub-account management unit is used to create a new employee account for the staff of the enterprise and associate the employee account with the role.

6. The intelligent analysis system for purchase, sales and inventory as claimed in claim 1, characterized in that: The obtaining of hot spot information related to the product within a preset time includes: Using a preset fourth feature extraction rule to extract features of the product information of the product to obtain a plurality of fourth feature values; constructing a second signature vector based on the plurality of fourth eigenvalues; Get all hotspot information within the preset time; Using a preset fourth feature extraction rule to perform feature extraction on each of the hotspot information to obtain a plurality of third feature values; constructing a first signature vector based on the plurality of third eigenvalues; The similarity between the first labeled vector and the second labeled vector is calculated, and the similarity calculation formula is as follows: Wherein, SP represents the similarity; a i represents the i-th parameter value of the first marking vector; b i represents the i-th parameter value of the second marker vector; n represents the total number of parameters of the first marker vector or the total number of parameters of the second marker vector; When the similarity is greater than a preset similarity threshold, it is determined that the hot spot information is related to the product.

7. The intelligent analysis system for purchase, sales and inventory as claimed in claim 1, characterized in that: Also includes: Joint decision-making module, used to establish joint analysis groups among enterprises and share data within the group; The joint decision module performs the following operations: Obtain historical sales data of the same product from other companies; Using a preset first feature extraction rule to extract features from the purchase cycle and the historical sales data of the same product of other enterprises, to obtain a plurality of first feature values; Inputting the plurality of the first characteristic values ​​into a preset first neural network model to determine the purchase and sales factor; Based on the purchase and sales factors, a comparison table of preset purchase and sales factors and first stocking quantities is queried to determine the first stocking quantity determined based on the historical sales data of each other enterprise; The first stocking quantity of the enterprise is corrected based on the following formula, and the correction formula is as follows: Wherein, B1 represents the first stock quantity after correction; x j is the first inventory quantity determined by the historical sales data of the jth other enterprise; N is the total number of other enterprises; y1 is the first inventory quantity before correction; γ1 and γ2 are preset weights; F(·) is a rounding function that rounds upwards to an integer.

8. The intelligent analysis system for purchase, sales and inventory as claimed in claim 1, characterized in that: Also includes: A scheduling module, used to obtain a goods scheduling request from an enterprise, and obtain a scheduling response to the goods scheduling request from other enterprises; The scheduling module performs the following operations: Get the goods dispatch request sent by the staff; Output the preset template of goods dispatch request; receiving the staff's filling of the goods dispatch request form template and generating the goods dispatch request form; Execute the preset review process corresponding to the goods dispatch request; When the review is passed, obtain the list of dispatchable goods of other enterprises in the preset goods dispatch coordination group; Determine other enterprises that can cooperate based on the goods dispatch request and the dispatchable goods list; Send the above-mentioned goods dispatch request to other enterprises that can cooperate; Receive goods dispatch negotiation documents from other enterprises that can cooperate with the goods dispatch request document; Analyze the goods dispatch price negotiation document to determine the dispatch price and dispatch time of the goods; Obtain the credit rating of the other enterprise in the goods dispatch negotiation document; Based on the credit rating value, the dispatch price and the dispatch time, determine the target enterprise and send a dispatch agreement; The reputation evaluation value is determined by the following steps: Configure reputation rating values ​​for enterprises; Get the dispatch history of the enterprise in response to other enterprises; Analyze the dispatch history records to determine the dispatch execution status corresponding to the dispatch price agreement for each dispatch; After each scheduling is executed, the reputation evaluation value is adjusted based on the scheduling execution status and the reputation evaluation value; the adjustment formula is as follows: Among them, X represents the credit rating value after adjustment; T0 is the credit rating value before adjustment; D represents the quantitative value of the scheduling execution situation. When the scheduling execution situation complies with the scheduling negotiation document, d is a positive value, otherwise it is a negative value; t represents the adjustment value, t0 represents the fine-tuning value, when d is a positive value, t-dt0>0; the value of |d| is determined by querying a preset coefficient table based on the consecutive number of historical scheduling execution situations that are the same as the current scheduling execution situation; the larger the consecutive number in the coefficient table, the larger the corresponding |d| value.

Images