Enterprise digital analysis method and system based on artificial intelligence

Abstract

The invention discloses an enterprise digital analysis method and system based on artificial intelligence, and relates to the technical field of data processing, and the enterprise digital analysis method based on artificial intelligence comprises the following steps: obtaining real-time production data in response to an enterprise digital analysis request; and inputting the customer demand content and the real-time production data in the enterprise digital analysis request into a pre-trained artificial intelligence-based analysis model, analyzing the customer demand content and the real-time production data by the artificial intelligence-based analysis model to obtain predicted order issuing information, and sending the predicted order issuing information. According to the invention, the method can automatically carry out the comprehensive analysis of the customer demands according to the data of a plurality of different departments, can obtain the related data of the current actual production condition of an enterprise in time, comprehensively and accurately, and judges whether the related data of the current actual production condition of the enterprise can meet the customer demands or not. Therefore, support is provided for work of related departments.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to an enterprise digital analysis method and system based on artificial intelligence. Background Art

[0002] Enterprise digital application refers to the practice of enterprises using digital technology to optimize business processes, improve management efficiency, and innovate products and services to enhance competitiveness and achieve sustainable development. At present, common enterprise digital application fields include: production and manufacturing, marketing, enterprise management, and product research and development. In terms of sales, production, and supply, the existing enterprise digital analysis methods and systems have the following problems: (1) An enterprise is usually composed of multiple different departments, and there are often information barriers between multiple departments. In addition, the existing enterprise digital analysis methods and systems do not realize that in the relevant analysis of enterprise digital applications, the data between different departments of the enterprise are interrelated and mutually influential, and jointly provide support for the analysis results. For example: when the sales department of an enterprise communicates with customers about order requirements, it is often unable to timely, comprehensively and accurately grasp the relevant data on the actual production situation of its own enterprise. If the relevant data on the actual production situation of its own enterprise is not clear, the order may not be delivered in time, the departments of the enterprise may not be able to arrange orders, and transaction disputes may occur.

[0003] (2) In terms of enterprise digital applications, existing enterprise digital analysis methods and systems are unable to automatically conduct a comprehensive analysis of customer needs based on data from multiple different departments, and are unable to timely, comprehensively and accurately obtain relevant data on the actual production situation of the enterprise itself, and determine whether the relevant data on the actual production situation of the enterprise itself can meet customer needs, thereby providing support for the work of relevant departments. For example: when the sales department receives customer needs, it can only obtain the actual production situation within the enterprise through repeated communication with multiple personnel from different departments. However, obtaining data from different departments through manual communication has problems such as low communication efficiency, low data accuracy and poor timeliness.

[0004] Therefore, there is an urgent need to develop a new enterprise digital analysis method and system based on artificial intelligence to solve the above problems. Summary of the invention

[0005] The purpose of this application is to provide an enterprise digital analysis method and system based on artificial intelligence, which can automatically conduct a comprehensive analysis of customer needs based on data between multiple different departments, and can timely, comprehensively and accurately obtain relevant data on the current actual production situation of its own enterprise, and judge whether the relevant data on the current actual production situation of its own enterprise can meet customer needs, thereby providing support for the work of relevant departments.

[0006] To achieve the above-mentioned purpose, the present application provides an enterprise digital analysis method based on artificial intelligence, comprising the following steps: S1: Responding to an enterprise digital analysis request, obtaining real-time production data; wherein the enterprise digital analysis request includes at least: a request account, an analysis request time, and customer demand content, wherein the customer demand content includes at least: a required product code, a required product quantity, a required arrival time, and a delivery address; wherein the real-time production data includes at least: the quantity to be produced, the current unit production efficiency of each production line to be analyzed, the current storage quantity of each raw material, and the current shipping address; S2: Inputting the customer demand content and real-time production data in the enterprise digital analysis request into a pre-trained artificial intelligence-based analysis model, and the artificial intelligence-based analysis model analyzes the customer demand content and real-time production data to obtain predicted order information and send it; wherein the predicted order information includes at least: the enterprise digital analysis result, the predicted production time, and the predicted delivery time; the enterprise digital analysis result is whether the demand is met or not.

[0007] As above, in which, in response to the enterprise's digital analysis request, the sub-steps for obtaining real-time production data are as follows: S11: Determine the production quantity to be produced based on the demand product code in the customer demand content; S12: Determine multiple production lines to be analyzed based on the demand product code in the customer demand content, and obtain the current unit production efficiency of each production line to be analyzed; S13: Determine the current storage quantity of each raw material based on the demand product code in the customer demand content; S14: Determine the current shipping address based on the demand product code in the customer demand content.

[0008] As above, the sub-steps of determining the quantity to be produced according to the demand product code in the customer demand content are as follows: S111: Traverse the to-be-produced database according to the demand product code in the customer demand content, and determine that the to-be-produced order data packet whose order product code is consistent with the demand product code is the to-be-produced order data packet to be analyzed, wherein the to-be-produced order data packet to be analyzed includes: multiple to-be-produced orders, each to-be-produced order includes at least: order time, order customer name, order product code, total order product quantity, order arrival time and order delivery address; S112: Obtain the total order product quantity in each to-be-produced order in the to-be-produced order data packet to be analyzed, and take the sum of all the total order product quantities as the to-be-produced quantity.

[0009] As above, wherein, multiple production lines to be analyzed are determined according to the demand product codes in the customer demand content, and the sub-steps of obtaining the current unit production efficiency of each production line to be analyzed are as follows: S121: Traverse the production line database according to the demand product codes in the customer demand content, and determine that the production line data packet whose production product code is consistent with the demand product code is the production line data packet to be analyzed; S122: Take the production line corresponding to the production line code of each production line data in the production line data packet to be analyzed as the production line to be analyzed; S123: Obtain the current unit production efficiency of the corresponding production line to be analyzed based on the production line data.

[0010] As above, the sub-steps of obtaining the current unit production efficiency of the corresponding production line to be analyzed based on the production line data are as follows: S1231: Obtain the current operating time and production efficiency change table of the production equipment in the production equipment data corresponding to each production node in the production line data, traverse the production efficiency change table using the current operating time of the production equipment, determine the operating time range to which the current operating time of the production equipment belongs in the production efficiency change table, use the allowable number of failures corresponding to the operating time range as the allowable number of failures to be analyzed, and use the production efficiency change value corresponding to the operating time range as the production efficiency change value to be analyzed; S1232: Calculate the current unit production efficiency of the corresponding production equipment based on the standard production efficiency of the production equipment in the production equipment data corresponding to each production node in the production line data and the current number of failures of each failure category of the production equipment, as well as the allowable number of failures to be analyzed and the production efficiency change value to be analyzed; S1233: Take the minimum value of the current unit production efficiencies of all production equipment as the current unit production efficiency of the production line to be analyzed.

[0011] As above, the expression of the current unit production efficiency of the production equipment is: ; in, For the The first of the production lines to be analyzed The current unit production efficiency of each production equipment; For the The first of the production lines to be analyzed The standard production efficiency of each production equipment; For the The first of the production lines to be analyzed The production efficiency change value to be analyzed for each production equipment; For the The first of the production lines to be analyzed The number of allowed failures to be analyzed for each production equipment; For the The first of the production lines to be analyzed Production equipment No. The current number of faults of the fault category; For the The first of the production lines to be analyzed Production equipment No. The impact weight of each fault category, , For the The first of the production lines to be analyzed The total number of types of failure categories of production equipment, is a natural number.

[0012] As above, wherein the customer demand content and real-time production data are analyzed by an analysis model based on artificial intelligence, and the sub-steps for obtaining predicted order information are as follows: S21: Obtain raw material procurement time based on customer demand content and real-time production data, and execute S22; S22: Obtain the total producible amount of the production line based on customer demand content, real-time production data and raw material procurement time, and use the total amount of demanded products in the customer demand content to analyze the total producible amount of the production line to generate an enterprise digital analysis result. If the total producible amount of the production line is greater than or equal to the total amount of demanded products, the generated enterprise digital analysis result is that the demand is met, and S23 is executed; if the total producible amount of the production line is less than the total amount of demanded products, the generated enterprise digital analysis result is that the demand is not met, and S23 is executed; S23: Obtain the predicted production time and predicted delivery time based on the customer demand content, real-time production data and raw material procurement time.

[0013] As above, the expression for predicting production time is: ; in, To predict production time; The total amount of products required in the customer's demand content; Time for purchasing raw materials; For real-time production data The current unit production efficiency of the production lines to be analyzed, , is the total number of production lines to be analyzed, is a natural number; for The minimum value of the current unit production efficiency of the production lines to be analyzed; for The maximum value of the current unit production efficiency of the production lines to be analyzed.

[0014] As above, the expression for predicting delivery time is: ; in, To predict the delivery time; To predict production time; The delivery address in the customer's demand content; The current shipping address in the real-time production data; is the transport speed per unit distance; The total amount of products required in the customer's demand content; For the packaging unit time The maximum total number of products that can be packaged within a certain period of time.

[0015] The present application also provides an enterprise digital analysis system based on artificial intelligence, including: multiple enterprise digital analysis request terminals and an artificial intelligence analysis center; wherein the enterprise digital analysis request terminal is used to send enterprise digital analysis requests; receive predicted order information; the artificial intelligence analysis center is used to execute the above-mentioned enterprise digital analysis method based on artificial intelligence.

[0016] The artificial intelligence-based enterprise digital analysis method and system of the present application can automatically conduct a comprehensive analysis of customer needs based on data between multiple different departments, and can timely, comprehensively and accurately obtain relevant data on the current actual production situation of the enterprise itself, and judge whether the relevant data on the current actual production situation of the enterprise itself can meet customer needs, thereby providing support for the work of relevant departments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0018] Figure 1 A schematic diagram of the structure of an embodiment of an enterprise digital analysis system based on artificial intelligence; Figure 2 A flowchart of an embodiment of an enterprise digital analysis method based on artificial intelligence. DETAILED DESCRIPTION

[0019] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0020] like Figure 1 As shown, the present application provides an enterprise digital analysis system based on artificial intelligence, including: multiple enterprise digital analysis request terminals 1 and an artificial intelligence analysis center 2.

[0021] Among them, the enterprise digital analysis request terminal 1 is used to send enterprise digital analysis requests and receive predicted order information.

[0022] Artificial Intelligence Analysis Center 2: Used to execute the following artificial intelligence-based enterprise digital analysis methods.

[0023] Furthermore, the artificial intelligence analysis center 2 includes at least: a data acquisition unit, an analysis unit and a storage unit.

[0024] Among them, the data acquisition unit: responds to the enterprise digital analysis request, obtains real-time production data, and sends the customer demand content and real-time production data in the enterprise digital analysis request to the analysis unit; wherein the enterprise digital analysis request at least includes: the request account, the analysis request time and the customer demand content, wherein the customer demand content at least includes: the required product code, the required product quantity, the required arrival time and the delivery address; wherein the real-time production data at least includes: the quantity to be produced, the current unit production efficiency of each production line to be analyzed, the current storage quantity of each raw material and the current shipping address.

[0025] Analysis unit: a pre-trained AI-based analysis model is provided; the AI-based analysis model analyzes customer demand content and real-time production data to obtain predicted order information, and sends the predicted order information to the enterprise digital analysis request terminal 1.

[0026] Storage unit: used to store the database to be produced, the production line database, the raw material storage database, the delivery location database and the procurement database.

[0027] Among them, the production database includes: multiple production order data packets, one production order data packet corresponds to an order product code, and each production order data packet includes: multiple production orders, and each production order includes at least: order time, order customer name, order product code, total order product quantity, order arrival time and order delivery address.

[0028] Among them, the production line database includes: multiple production line data packets, one production line data packet corresponds to a production product code, each production line data packet includes: multiple production line data, one production line data corresponds to a production line code, one production line code corresponds to a production line, each production line data includes: a production process, the production process includes multiple production nodes, each production node corresponds to a production operation sequence number, the production operation sequence number increases in sequence according to the production order of the product, each production node corresponds to a production equipment data, each production equipment data includes at least: the production equipment code, the standard operating time of the production equipment, the standard production efficiency of the production equipment, the current operating time of the production equipment, the current number of failures of each failure type of the production equipment and a production efficiency change table; the production efficiency change table includes: multiple operating time ranges, one operating time range corresponds to an allowable number of failures and a production efficiency change value.

[0029] Specifically, one piece of production equipment data corresponds to one piece of production equipment, and one piece of production equipment corresponds to one piece of production equipment code.

[0030] The standard operating time of a production device is the maximum time that the production device can be used normally.

[0031] The standard production efficiency of production equipment is the maximum amount of corresponding products that the production equipment can produce per unit time.

[0032] The current running time of the production device is the total time that the production device has been used when analyzing the request time.

[0033] The current number of faults of each fault category of the production device is the number of faults of each fault category that have occurred in the production device at the time of the analysis request.

[0034] Each runtime range is different and all lie within the range [0, standard runtime of production equipment].

[0035] The probability of failure varies in different operating time ranges. The longer the production equipment is used, the greater the probability of failure. The allowed number of failures is the maximum number of failures allowed within the operating time range. The specific value of the allowed number of failures corresponding to each operating time range is set based on multiple actual tests or actual statistics.

[0036] The specific value of the production efficiency change value is set according to multiple actual test results or multiple simulation analysis results.

[0037] Among them, the raw material storage database includes: multiple raw material storage data packets, one raw material storage data packet corresponds to an application table and a material code, each application table includes: multiple application product codes, one application product code corresponds to a production operation serial number of a production node, and each raw material storage data packet includes: real-time storage quantity.

[0038] Specifically, the real-time storage volume is the total amount of unused raw materials in inventory.

[0039] Among them, the shipping location database includes: multiple shipping location data packets, one shipping location data packet corresponds to a shipping table and an address code, each shipping table includes: multiple shipping product codes, one shipping product code corresponds to a product, and each shipping location data packet includes: a shipping location.

[0040] The procurement database at least includes: a plurality of raw material collection data packets, one raw material collection data packet corresponds to a material code, and each raw material collection data packet includes: a plurality of procurement quantity ranges, each procurement quantity range corresponds to a collection time.

[0041] Furthermore, the database for production, the production line database, the raw material storage database, the shipping location database and the procurement database are all updated in real time according to the update conditions, wherein the update conditions are: data in the database for production, the production line database, the raw material storage database, the shipping location database and / or the procurement database changes, for example: completion, addition, deletion or modification of a production order; increase or reduction of production lines or change of production equipment information in the production line data package; change of the content of the application table or the real-time storage capacity in each raw material storage data package; increase, deletion or modification of the content in the shipping location data package.

[0042] like Figure 2 As shown, the present application provides an enterprise digital analysis method based on artificial intelligence, comprising the following steps: S1: Respond to the enterprise's digital analysis request and obtain real-time production data; wherein the enterprise's digital analysis request includes at least: the request account, the analysis request time and the customer demand content, wherein the customer demand content includes at least: the required product code, the required product quantity, the required arrival time and the delivery address; wherein the real-time production data includes at least: the quantity to be produced, the current unit production efficiency of each production line to be analyzed, the current storage quantity of each raw material and the current shipping address.

[0043] Specifically, the requesting account is the account of the requester who sends the enterprise digital analysis request. One requester corresponds to one account.

[0044] The analysis request time is the time when the enterprise digital analysis request is sent.

[0045] The demand product code is the product code corresponding to the product that the customer intends to purchase. One product corresponds to one product code. Different types of products have different product codes, while the same types of products have the same product code.

[0046] The total demand for products is the total demand for products that customers intend to purchase.

[0047] The required arrival time is the latest time the customer expects to receive the product.

[0048] The delivery address is the specific address where the customer wants the product to be delivered.

[0049] Furthermore, in response to the enterprise digital analysis request, the sub-steps of obtaining real-time production data are as follows: S11: Determine the quantity to be produced according to the product code in the customer's demand content.

[0050] Specifically, the quantity to be produced is the total quantity of products that have been ordered but have not yet started production and are consistent with the required product code category.

[0051] Furthermore, the sub-steps of determining the quantity to be produced according to the required product code in the customer's demand content are as follows: S111: Traverse the to-be-produced database according to the demand product codes in the customer demand content, and determine that the to-be-produced order data package whose order product code is consistent with the demand product code is the to-be-produced order data package to be analyzed, wherein the to-be-produced order data package to be analyzed includes: multiple to-be-produced orders, each to-be-produced order includes at least: order time, ordering customer name, order product code, total order product quantity, order arrival time and order delivery address.

[0052] S112: Obtain the total quantity of ordered products in each to-be-produced order in the to-be-produced order data package to be analyzed, and take the sum of the total quantities of all ordered products as the to-be-produced quantity.

[0053] Furthermore, a pre-trained artificial intelligence-based recognition model is used to identify each pending production order in the pending production order data package to be analyzed, the total number of ordered products in each pending production order is obtained, and the pending production quantity is calculated based on the total number of all ordered products. However, it is not limited to a pre-trained artificial intelligence-based recognition model, but can also be a pre-trained neural network. The present application preferably uses a pre-trained artificial intelligence-based recognition model.

[0054] S12: Determine multiple production lines to be analyzed according to the demand product codes in the customer demand content, and obtain the current unit production efficiency of each production line to be analyzed.

[0055] Furthermore, the sub-steps of determining multiple production lines to be analyzed according to the required product codes in the customer's requirements and obtaining the current unit production efficiency of each production line to be analyzed are as follows: S121: Traverse the production line database according to the required product code in the customer demand content, and determine that the production line data package whose production product code is consistent with the required product code is the production line data package to be analyzed.

[0056] Specifically, the production line data packet to be analyzed includes: multiple production line data, one production line data corresponds to a production line code, one production line code corresponds to a production line, each production line data includes: a production process, the production process includes multiple production nodes, each production node corresponds to a production operation sequence number, the production operation sequence number increases in sequence according to the production order of the product, each production node corresponds to a production equipment data, each production equipment data includes at least: the production equipment code, the standard operating time of the production equipment, the standard production efficiency of the production equipment, the current operating time of the production equipment, the current number of failures of each failure type of the production equipment and a production efficiency change table; the production efficiency change table includes: multiple operating time ranges, one operating time range corresponds to an allowable number of failures and a production efficiency change value.

[0057] S122: The production line corresponding to the production line code of each production line data in the production line data packet to be analyzed is used as the production line to be analyzed.

[0058] S123: Acquire the current unit production efficiency of the corresponding production line to be analyzed according to the production line data.

[0059] Furthermore, the sub-steps of obtaining the current unit production efficiency of the corresponding production line to be analyzed according to the production line data are as follows: S1231: Obtain the current operating time and production efficiency change table of the production equipment in the production equipment data corresponding to each production node in the production line data, use the current operating time of the production equipment to traverse the production efficiency change table, determine the operating time range to which the current operating time of the production equipment belongs in the production efficiency change table, use the allowed number of failures corresponding to the operating time range as the allowed number of failures to be analyzed, and use the production efficiency change value corresponding to the operating time range as the production efficiency change value to be analyzed.

[0060] S1232: Calculate the current unit production efficiency of the corresponding production equipment based on the standard production efficiency of the production equipment in the production equipment data corresponding to each production node in the production line data, the current number of failures of each failure type of the production equipment, the allowable number of failures to be analyzed, and the production efficiency change value to be analyzed.

[0061] Furthermore, the expression of the current unit production efficiency of the production equipment is: ; in, For the The first of the production lines to be analyzed The current unit production efficiency of each production equipment; For the The first of the production lines to be analyzed The standard production efficiency of each production equipment; For the The first of the production lines to be analyzed The production efficiency change value to be analyzed for each production equipment; For the The first of the production lines to be analyzed The number of allowed failures to be analyzed for each production equipment; For the The first of the production lines to be analyzed Production equipment No. The current number of faults of the fault category; For the The first of the production lines to be analyzed Production equipment No. The impact weight of each fault category, , For the The first of the production lines to be analyzed The total number of types of failure categories of production equipment, is a natural number.

[0062] Specifically, The specific value of is set according to the actual situation. The greater the impact of the fault type on the operating status of the production equipment, The bigger.

[0063] S1233: The minimum value of the current unit production efficiency of all production equipment is used as the current unit production efficiency of the production line to be analyzed.

[0064] Specifically, the current unit production efficiency is the maximum value of the total number of complete products that can be produced by the production line to be analyzed within a unit time.

[0065] S13: Determine the current storage quantity of each raw material according to the demand product code in the customer demand content.

[0066] Further, the sub-steps of determining the current storage quantity of each raw material according to the required product code in the customer's demand content are as follows: S131: Traverse the application table corresponding to each raw material storage data packet in the raw material storage database according to the required product code in the customer demand content. If the application table has an application product code that is consistent with the required product code, determine that the raw material storage data packet corresponding to the application table is the raw material storage data packet to be analyzed.

[0067] S132: Read the real-time storage capacity in the raw material storage data packet to be analyzed, and use the real-time storage capacity as the current storage capacity.

[0068] S14: Determine the current shipping address according to the required product code in the customer's demand content.

[0069] Furthermore, the sub-steps of determining the current shipping address according to the required product code in the customer's demand content are as follows: S141: Traverse each shipping table in the shipping location database according to the required product code in the customer demand content. If the shipping table has a shipping product code that is consistent with the required product code, determine that the shipping location data packet corresponding to the shipping table is the shipping location data packet to be analyzed.

[0070] S142: Read the shipping location in the shipping location data packet to be analyzed, and use the shipping location as the current shipping address.

[0071] S2: Input the customer demand content and real-time production data in the enterprise digital analysis request into a pre-trained artificial intelligence-based analysis model, and use the artificial intelligence-based analysis model to analyze the customer demand content and real-time production data to obtain predicted order information and send it; wherein the predicted order information includes at least: the enterprise digital analysis result, predicted production time and predicted delivery time; the enterprise digital analysis result is whether the demand is met or not.

[0072] Furthermore, the artificial intelligence-based analysis model analyzes customer demand content and real-time production data to obtain the following sub-steps for predicting order information: S21: Obtain the raw material procurement time according to the customer demand content and real-time production data, and execute S22.

[0073] Furthermore, the sub-steps for obtaining the raw material procurement time based on customer demand content and real-time production data are as follows: S211: Calculate the quantity of intermediate products corresponding to the required product code that can be produced by each raw material according to the current storage quantity of each raw material in the real-time production data.

[0074] Further, The expression for the number of intermediate products corresponding to the required product code that can be produced by the raw materials is: ; in, For the The quantity of intermediate products corresponding to the required product code that can be produced by the raw materials at present; For real-time production data Current stocks of the raw materials; It is the quantity to be produced in the real-time production data; The first step required to produce an intermediate product corresponding to a required product code The amount of raw materials used; To produce an intermediate product corresponding to a required product code, The process loss of raw materials, , The total number of types of raw materials required to produce the product corresponding to the required product code. is a natural number.

[0075] Specifically, When producing an intermediate product corresponding to a required product code, the first The amount of raw materials, The specific value is set according to the actual production process or equipment model.

[0076] S212: Analyze the quantity of intermediate products corresponding to the demand product codes that can be currently produced by each raw material using the total quantity of demand products in the customer demand content. If the quantity of intermediate products corresponding to the demand product codes that can currently be produced by each raw material is greater than or equal to the total quantity of demand products, the raw material procurement time is 0; if there are one or more quantities of intermediate products corresponding to the demand product codes that can currently be produced by all raw materials that are less than the total quantity of demand products, the raw materials corresponding to the quantity of intermediate products corresponding to the demand product codes that can currently be produced by the raw materials that are less than the total quantity of demand products are used as the raw materials to be purchased, and the quantity of intermediate products corresponding to the demand product codes that can currently be produced by the raw materials that are less than the total quantity of demand products is used as the quantity to be purchased, and then execute S213.

[0077] S213: Traverse the procurement database according to the material code corresponding to each raw material to be purchased, and determine that the raw material collection data package whose material code is consistent with the material code corresponding to the raw material to be purchased is the raw material collection data package to be analyzed.

[0078] S214: Traverse the purchase quantity range in the raw material acquisition data package to be analyzed according to the quantity to be purchased, determine the purchase quantity range to which the quantity to be purchased belongs as the target purchase range, and use the acquisition time corresponding to the target purchase range as the target acquisition time.

[0079] S215: The maximum value of all target collection times is used as the raw material procurement time.

[0080] S22: The total production volume that the production line can produce is obtained according to the customer demand content, real-time production data and raw material procurement time, and the total production volume that the production line can produce is analyzed using the total demand product volume in the customer demand content to generate an enterprise digital analysis result. If the total production volume that the production line can produce is greater than or equal to the total demand product volume, the generated enterprise digital analysis result is that the demand is met, and S23 is executed; if the total production volume that the production line can produce is less than the total demand product volume, the generated enterprise digital analysis result is that the demand is not met, and S23 is executed.

[0081] Furthermore, the expression for the total amount of production that can be produced by the production line is: ; in, is the total production capacity of the production line; For real-time production data The current unit production efficiency of the production lines to be analyzed, , is the total number of production lines to be analyzed, is a natural number; The required arrival time for the content required by the customer; The delivery address of the customer's request content; The current shipping address in the real-time production data; is the transport speed per unit distance; The unit time corresponding to the current unit production efficiency of the production line to be analyzed; The total amount of products required in the customer's demand content; For the packaging unit time The maximum total number of products that can be packaged within a certain period of time; It is the quantity to be produced in the real-time production data; Time to purchase raw materials.

[0082] Specifically, the unit time corresponding to the current unit production efficiency of each production line to be analyzed is equal.

[0083] S23: Obtain the predicted production time and predicted delivery time based on customer demand content, real-time production data and raw material procurement time.

[0084] Furthermore, the predicted production time is the predicted time for the production line to be analyzed to complete the total amount of required products. The expression for the predicted production time is: ; in, To predict production time; The total amount of products required in the customer's demand content; Time for purchasing raw materials; For real-time production data The current unit production efficiency of the production lines to be analyzed, , is the total number of production lines to be analyzed, is a natural number; for The minimum value of the current unit production efficiency of the production lines to be analyzed; for The maximum value of the current unit production efficiency of the production lines to be analyzed.

[0085] Furthermore, the predicted delivery time is the predicted time from receiving the order to completing the order. The expression for the predicted delivery time is: ; in, To predict the delivery time; To predict production time; The delivery address in the customer's demand content; The current shipping address in the real-time production data; is the transport speed per unit distance; The total amount of products required in the customer's demand content; For the packaging unit time The maximum total number of products that can be packaged within a certain period of time.

[0086] The artificial intelligence-based enterprise digital analysis method and system of the present application can automatically conduct a comprehensive analysis of customer needs based on data between multiple different departments, and can timely, comprehensively and accurately obtain relevant data on the current actual production situation of the enterprise itself, and judge whether the relevant data on the current actual production situation of the enterprise itself can meet customer needs, thereby providing support for the work of relevant departments.

[0087] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they are aware of the basic creative concepts. Therefore, the scope of protection of the present application is intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present application. Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the protection scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. An enterprise digital analysis method based on artificial intelligence, characterized in that: The steps include: S1: Responding to the enterprise digital analysis request, obtaining real-time production data; wherein the enterprise digital analysis request at least includes: request account, analysis request time and customer demand content, wherein the customer demand content at least includes: demand product code, demand product total quantity, demand arrival time and delivery address; wherein the real-time production data at least includes: to-be-produced quantity, current unit production efficiency of each production line to be analyzed, current storage quantity of each raw material and current delivery address; S2: Input the customer demand content and real-time production data in the enterprise digital analysis request into a pre-trained artificial intelligence-based analysis model, and use the artificial intelligence-based analysis model to analyze the customer demand content and real-time production data to obtain predicted order information and send it; wherein the predicted order information includes at least: the enterprise digital analysis result, predicted production time and predicted delivery time; the enterprise digital analysis result is whether the demand is met or not.

2. The enterprise digitalization analysis method based on artificial intelligence according to claim 1 is characterized in that: In response to the enterprise digital analysis request, the sub-steps for obtaining real-time production data are as follows: S11: Determine the quantity to be produced according to the product code in the customer's demand content; S12: Determine multiple production lines to be analyzed according to the required product codes in the customer's requirements, and obtain the current unit production efficiency of each production line to be analyzed; S13: Determine the current storage quantity of each raw material according to the required product code in the customer's demand content; S14: Determine the current shipping address according to the required product code in the customer's demand content.

3. The enterprise digitalization analysis method based on artificial intelligence according to claim 2 is characterized in that: The sub-steps for determining the quantity to be produced based on the product code in the customer demand content are as follows: S111: Traverse the to-be-produced database according to the demand product code in the customer demand content, and determine that the to-be-produced order data packet whose order product code is consistent with the demand product code is the to-be-produced order data packet to be analyzed, wherein the to-be-produced order data packet to be analyzed includes: multiple to-be-produced orders, each to-be-produced order includes at least: order time, order customer name, order product code, total order product quantity, order arrival time, and order delivery address; S112: Obtain the total quantity of ordered products in each to-be-produced order in the to-be-produced order data package to be analyzed, and take the sum of the total quantities of all ordered products as the to-be-produced quantity.

4. The enterprise digitalization analysis method based on artificial intelligence according to claim 3 is characterized in that: The sub-steps of determining multiple production lines to be analyzed according to the required product codes in the customer's requirements and obtaining the current unit production efficiency of each production line to be analyzed are as follows: S121: Traverse the production line database according to the required product code in the customer demand content, and determine that the production line data package whose production product code is consistent with the required product code is the production line data package to be analyzed; S122: taking the production line corresponding to the production line code of each production line data in the production line data packet to be analyzed as the production line to be analyzed; S123: Acquire the current unit production efficiency of the corresponding production line to be analyzed according to the production line data.

5. The enterprise digitalization analysis method based on artificial intelligence according to claim 4 is characterized in that: The sub-steps for obtaining the current unit production efficiency of the corresponding production line to be analyzed based on the production line data are as follows: S1231: Obtain the current operation time and production efficiency change table of the production equipment in the production equipment data corresponding to each production node in the production line data, traverse the production efficiency change table using the current operation time of the production equipment, determine the operation time range to which the current operation time of the production equipment belongs in the production efficiency change table, use the allowed number of failures corresponding to the operation time range as the allowed number of failures to be analyzed, and use the production efficiency change value corresponding to the operation time range as the production efficiency change value to be analyzed; S1232: Calculate the current unit production efficiency of the corresponding production equipment according to the standard production efficiency of the production equipment in the production equipment data corresponding to each production node in the production line data, the current number of failures of each failure type of the production equipment, the allowable number of failures to be analyzed, and the production efficiency change value to be analyzed; S1233: The minimum value of the current unit production efficiency of all production equipment is used as the current unit production efficiency of the production line to be analyzed.

6. The enterprise digitalization analysis method based on artificial intelligence according to claim 5 is characterized in that: The expression of the current unit production efficiency of the production equipment is: ； in, For the The first of the production lines to be analyzed The current unit production efficiency of each production equipment; For the The first of the production lines to be analyzed The standard production efficiency of each production equipment; For the The first of the production lines to be analyzed The production efficiency change value to be analyzed for each production equipment; For the The first of the production lines to be analyzed The number of allowed failures to be analyzed for each production equipment; For the The first of the production lines to be analyzed Production equipment No. The current number of faults of the fault category; For the The first of the production lines to be analyzed Production equipment No. The impact weight of each fault category, , For the The first of the production lines to be analyzed The total number of types of failure categories of production equipment, is a natural number.

7. The enterprise digitalization analysis method based on artificial intelligence according to claim 5 is characterized in that: The AI-based analysis model analyzes customer demand content and real-time production data to obtain predicted order information in the following sub-steps: S21: Obtain the raw material procurement time according to the customer demand content and real-time production data, and execute S22; S22: The total amount of production that can be produced by the production line is obtained according to the customer demand content, real-time production data and raw material procurement time, and the total amount of required products in the customer demand content is used to analyze the total amount of production that can be produced by the production line to generate an enterprise digital analysis result. If the total amount of production that can be produced by the production line is greater than or equal to the total amount of required products, the generated enterprise digital analysis result is that the demand is met, and S23 is executed; if the total amount of production that can be produced by the production line is less than the total amount of required products, the generated enterprise digital analysis result is that the demand is not met, and S23 is executed; S23: Obtain the predicted production time and predicted delivery time based on customer demand content, real-time production data and raw material procurement time.

8. The enterprise digitalization analysis method based on artificial intelligence according to claim 7 is characterized in that: The expression for predicting production time is: ； in, To predict production time; The total amount of products required in the customer's demand content; Time for purchasing raw materials; For real-time production data The current unit production efficiency of the production lines to be analyzed, , is the total number of production lines to be analyzed, is a natural number; for The minimum value of the current unit production efficiency of the production lines to be analyzed; for The maximum value of the current unit production efficiency of the production lines to be analyzed.

9. The enterprise digitalization analysis method based on artificial intelligence according to claim 7 is characterized in that: The expression for predicting delivery time is: ； in, To predict the delivery time; To predict production time; The delivery address in the customer's demand content; The current shipping address in the real-time production data; is the transport speed per unit distance; The total amount of products required in the customer's demand content; For the packaging unit time The maximum total number of products that can be packaged within a certain period of time.

10. An enterprise digital analysis system based on artificial intelligence, characterized in that: include: Multiple enterprise digital analysis request terminals and artificial intelligence analysis centers; Among them, the enterprise digital analysis request end is used to send enterprise digital analysis requests and receive forecast order information; Artificial Intelligence Analysis Center: used to execute the artificial intelligence-based enterprise digital analysis method described in any one of claims 1-9.

Images