A Supply Chain Multi-User Docking Method and System for a Cloud Cutting Platform

Abstract

The present invention discloses a method and system for multi-user docking of a supply chain in a cloud cutting platform. The method includes: generating a first set of demand elements through collection; performing serialization adjustment based on time sequence to obtain a first adjustment result; collecting and generating a first set of production elements; performing space-time adjustment based on time sequence to obtain a second adjustment result; performing primary optimization screening on a first supply end to obtain a primary screening result; obtaining a first set of utilization rates, where the first set of utilization rates corresponds one-to-one with the primary screening result; performing secondary optimization screening based on the first set of utilization rates to obtain a secondary screening result, and performing multi-user docking based on the corresponding supply end. It solves the technical problem in the prior art that in the collaborative manufacturing of steel plate cutting, the supplier and the demander communicate and establish a cooperation on the collaborative manufacturing plan based on their actual production or demand situations respectively, resulting in poor flexibility in collaborative manufacturing and low matching degree between the supply and demand sides, and thus unable to maximize the interests of multiple parties in the supply chain.

Description

Technical Field

[0001] The present invention relates to the field of computer application technologies, and particularly to a method and system for multi-user docking of a supply chain on a cloud cutting platform. Background Art

[0002] With the rapid development of computer technologies, more and more traditional industries and fields have started to use computer technologies for industry transformation and upgrading. Among them, in order to improve the overall supply chain efficiency, the steel plate cutting industry has established an online collaborative manufacturing cooperation system based on the Internet + steel plate cutting collaborative manufacturing sharing platform. However, in the existing technologies, the collaborative manufacturing cooperation between the steel plate cutting supplier and the demander is usually established based on the subjective evaluation of the strength of both parties or the cooperation based on trust, and after the cooperation is established, the supply and demand docking process is carried out through the online collaborative manufacturing platform. Based on this, the supplier cannot match and obtain more production orders based on its actual production capacity, and the demander also cannot match a suitable supplier for the delivery deadline, cutting cost, etc. according to its actual demand situation, such as the demand for steel plate cutting volume, cutting precision requirements, etc., resulting in the overall economic benefits of the steel plate cutting collaborative manufacturing supply chain not being maximized. Research on using computer technologies to intelligently establish a connection for the supply and demand parties to be adapted has important significance for maximizing the benefits of all parties and promoting healthy competition in the industry.

[0003] However, in the existing technologies for steel plate cutting collaborative manufacturing, the supplier and the demander respectively communicate the collaborative manufacturing plan and establish cooperation based on their actual production or demand situations, resulting in technical problems such as poor flexibility in collaborative manufacturing and low matching degree between the supply and demand parties, and thus the maximization of the multi-party interests of the supply chain cannot be achieved. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for multi-user docking of a supply chain on a cloud cutting platform to solve the technical problems in the existing technologies for steel plate cutting collaborative manufacturing, where the supplier and the demander respectively communicate the collaborative manufacturing plan and establish cooperation based on their actual production or demand situations, resulting in poor flexibility in collaborative manufacturing and low matching degree between the supply and demand parties, and thus the maximization of the multi-party interests of the supply chain cannot be achieved.

[0005] In view of the above problems, the present invention provides a method and system for multi-user docking of a supply chain on a cloud cutting platform.

[0006] In a first aspect, the present invention provides a method for multi-user docking of a supply chain of a cloud cutting platform. The method is implemented through a multi-user docking system of a supply chain of a cloud cutting platform. Wherein, the method includes: collecting demand elements from a first demand side to generate a first demand element set; serially adjusting the first demand element set based on time sequence to obtain a first adjustment result; collecting production elements from a first supply side to generate a first production element set; performing space-time adjustment on the first production element set based on time sequence to obtain a second adjustment result; performing primary optimization screening on the first supply side based on the first adjustment result and the second adjustment result to obtain a primary screening result; traversing the primary screening result to extract the utilization rate to obtain a first utilization rate set, wherein the first utilization rate set and the primary screening result are in one-to-one correspondence; performing secondary optimization screening on the primary screening result based on the first utilization rate set to obtain a secondary screening result, and performing multi-user docking based on the supply side corresponding to the secondary screening result.

[0007] In another aspect, the present invention further provides a multi-user docking system for a supply chain of a cloud cutting platform, which is used to execute the method for multi-user docking of a supply chain of a cloud cutting platform as described in the first aspect. Wherein, the system includes: a first generating unit: the first generating unit is used to collect demand elements from a first demand side to generate a first demand element set; a first obtaining unit: the first obtaining unit is used to serially adjust the first demand element set based on time sequence to obtain a first adjustment result; a second generating unit: the second generating unit is used to collect production elements from a first supply side to generate a first production element set; a second obtaining unit: the second obtaining unit is used to perform space-time adjustment on the first production element set based on time sequence to obtain a second adjustment result; a third obtaining unit: the third obtaining unit is used to perform primary optimization screening on the first supply side based on the first adjustment result and the second adjustment result to obtain a primary screening result; a fourth obtaining unit: the fourth obtaining unit is used to traverse the primary screening result to extract the utilization rate to obtain a first utilization rate set, wherein the first utilization rate set and the primary screening result are in one-to-one correspondence; a first execution unit: the first execution unit is used to perform secondary optimization screening on the primary screening result based on the first utilization rate set to obtain a secondary screening result, and perform multi-user docking based on the supply side corresponding to the secondary screening result.

[0008] In a third aspect, an electronic device includes a processor and a memory;

[0009] The memory is used for storage;

[0010] The processor is used to execute the method described in any one of the first aspects by calling.

[0011] Fourthly, a computer program product for multi-user docking of the supply chain of a cloud cutting platform, including a computer program and / or instructions, which when executed by a processor implement the steps of the method described in any one of the above first aspects.

[0012] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:

[0013] 1. By means of the steel plate cutting collaborative manufacturing sharing platform, the actual situations of the supply side and the demand side are respectively collected, intelligently analyzed and adjusted, and then based on the adjustment processing results, the supply side is optimized and screened at the first level. Further, in combination with the actual production capacity index data of each supplier in the first-level optimization and screening results, the final supplier is obtained through the second-level optimization and screening, and the docking between the finally screened supplier and multiple demand users is established. Through the intelligent analysis and adjustment processing of the supply chain multi-user docking system, the supply-demand matching degree of collaborative manufacturing between the supply side and the demand side is improved, and on the basis of ensuring the basic steel plate cutting requirements of the demand side, the technical effect of improving the overall working efficiency of the supply chain and thus realizing the maximization of the interests of multiple parties is achieved.

[0014] 2. By training a first-level optimization model based on the idea of the gradient ascent decision forest algorithm, where the layer range is set in each decision tree training, overfitting of the training results is avoided, and at the same time, the training time is saved, achieving the technical effects of improving the degree of abnormal data analysis and processing and improving the model performance.

[0015] 3. By considering the time operation rate, performance operation rate data, and cutting steel plate yield rate data of each supplier, the output of each supplier is quantitatively predicted, achieving the technical effect of improving the accuracy of supplier output prediction and providing data reference for subsequent establishment of reasonable and reliable collaborative manufacturing.

[0016] The above description is only an overview of the technical solution of the present invention. In order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable, the following specific embodiments of the present invention are specifically given. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0018] Figure 1 It is a schematic flow chart of a method for multi-user docking of the supply chain of a cloud cutting platform of the present invention;

[0019] Figure 2 It is a schematic flow chart for obtaining the second adjustment result in the multi-user docking method of the supply chain of a cloud cutting platform according to the present invention;

[0020] Figure 3 It is a schematic flow chart for constructing a primary optimization model in the multi-user docking method of the supply chain of a cloud cutting platform according to the present invention;

[0021] Figure 4 It is a schematic flow chart for obtaining the secondary screening result in the multi-user docking method of the supply chain of a cloud cutting platform according to the present invention;

[0022] Figure 5 It is a schematic structural diagram of a multi-user docking system for the supply chain of a cloud cutting platform according to the present invention;

[0023] Figure 6 It is a schematic structural diagram of an exemplary electronic device according to the present invention;

[0024] Explanation of reference numerals:

[0025] The first generation unit 11, the first acquisition unit 12, the second generation unit 13, the second acquisition unit 14, the third acquisition unit 15, the fourth acquisition unit 16, the first execution unit 17, the bus 300, the receiver 301, the processor 302, the transmitter 303, the memory 304, the bus interface 305. Detailed implementation manners

[0026] By providing a multi-user docking method and system for the supply chain of a cloud cutting platform, the present invention solves the technical problem in the collaborative manufacturing of steel plate cutting in the prior art that the supplier and the demander communicate and establish cooperation on the collaborative manufacturing plan based on their actual production or demand situations respectively, resulting in poor flexibility in collaborative manufacturing and low matching degree between the supply and demand sides, and thus unable to maximize the interests of multiple parties in the supply chain. Through the intelligent analysis and adjustment processing of the multi-user docking system for the supply chain, the supply-demand matching degree of collaborative manufacturing between the supplier and the demander is improved, and on the basis of ensuring the basic steel plate cutting requirements of the demander, the technical effect of improving the overall working efficiency of the supply chain and thus maximizing the interests of multiple parties is achieved.

[0027] In the technical solution of the present invention, the acquisition, storage, use, processing, etc. of data all comply with the relevant regulations of national laws and regulations.

[0028] Next, the technical solutions in the present invention will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments of the present invention. It should be understood that the present invention is not limited by the example embodiments described herein. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention. Additionally, it should be noted that for the sake of convenience of description, only the parts related to the present invention are shown in the drawings rather than all of them.

[0029] The present invention provides a multi-user docking method for the supply chain of a cloud cutting platform. The method is applied to a multi-user docking system for the supply chain of a cloud cutting platform. Among them, the method includes: collecting demand elements from the first demand side to generate a first demand element set; serially adjusting the first demand element set based on time sequence to obtain a first adjustment result; collecting production elements from the first supply side to generate a first production element set; performing space-time adjustment on the first production element set based on time sequence to obtain a second adjustment result; performing primary optimization screening on the first supply side based on the first adjustment result and the second adjustment result to obtain a primary screening result; traversing the primary screening result to extract the utilization rate to obtain a first utilization rate set, where the first utilization rate set and the primary screening result are in one-to-one correspondence; performing secondary optimization screening on the primary screening result based on the first utilization rate set to obtain a secondary screening result, and performing multi-user docking based on the supply side corresponding to the secondary screening result.

[0030] After introducing the basic principle of the present invention, the various non-limiting embodiments of the present invention will be specifically introduced below with reference to the accompanying drawings of the specification.

[0031] Embodiment 1

[0032] Please refer to the attached Figure 1 , the present invention provides a multi-user docking method for the supply chain of a cloud cutting platform. Among them, the method is applied to a multi-user docking system for the supply chain of a cloud cutting platform. The method specifically includes the following steps:

[0033] Step S100: Collect demand elements from the first demand side to generate a first demand element set;

[0034] Specifically, the multi-user docking method for the supply chain of the cloud cutting platform is applied to the multi-user docking system for the supply chain of the cloud cutting platform, which can intelligently analyze and adjust the actual situations of the supply side and the demand side, so as to screen out the final suppliers and automatically establish the docking between each supplier and customers. The first demand side refers to all the demand user parties to be docked in the multi-user docking system for the supply chain. Based on the demand information released by the first demand side, the system automatically analyzes and extracts relevant demand elements. For example, demand information such as the type and thickness of the cut steel plate, the shape and size requirements of the steel plate cutting, the total cutting demand, the demand cutting components in each time stage, and the steel plate cutting accuracy. All the collected demand elements form the first demand element set. By collecting the first demand element set, the technical effects of providing a data basis for intelligently matching corresponding suppliers based on the specific actual demand data information of the demand side and providing a basis for improving the matching degree of suppliers are achieved.

[0035] Step S200: Serialize and adjust the first demand element set based on time sequence to obtain a first adjustment result;

[0036] Specifically, according to the demand element information in the first demand element set, perform demand adjustment in the order of time progression, and record the arrangement order of each demand element in the adjusted first demand element set as the first adjustment result. For example, the length * width * height of the steel plate size to be cut by a certain demand side is 2 * 1 * 0.1 meters. Among them, 120 pieces are required per month in the first quarter, 150 pieces are required per month in the second quarter, 180 pieces are required per month in the third quarter, and 120 pieces are required per month in the fourth quarter. To meet the production and manufacturing requirements, it is required to complete the delivery of all required steel plates for the next month at the end of each month. Then, the demand adjusted based on time sequence is 120 pieces in January, 120 pieces in February, 120 pieces in March, 150 pieces in April, 150 pieces in May, 150 pieces in June, 180 pieces in July, 180 pieces in August, 180 pieces in September, 120 pieces in October, 120 pieces in November, and 120 pieces in December.

[0037] By obtaining the first adjustment result, the technical effects of providing accurate and reliable demand information for matching corresponding suppliers based on the specific demands of the demand side in each time stage, thereby improving the reliability of the matching result and ultimately improving the matching degree between the supply and demand sides are achieved.

[0038] Step S300: Collect production elements for the first supply side to generate a first production element set;

[0039] Step S400: Perform space-time adjustment on the first production element set based on time sequence to obtain a second adjustment result;

[0040] Specifically, the first supply end refers to all suppliers in the multi-user docking system of the supply chain that can provide steel plate cutting services. Based on various intelligent devices, relevant information such as the processing production and cutting manufacturing capabilities of each supplier in the first supply end is collected. For example, parameters such as the equipment for the supplier to cut steel plates, the cutting principle and technology of the corresponding equipment, cutting accuracy, cutting cost, and cutting efficiency are collected, thereby forming the first production factor set. Further, for each production factor corresponding to the first supply end in the first production factor set, analysis and processing are performed, and based on the spatial and temporal information of steel plate cutting, the priority of each production factor is adjusted, thereby obtaining a second adjustment result.

[0041] For example, a certain supplier currently has 2 idle A-type devices and 5 idle B-type devices for steel plate cutting. In addition, based on the current order information and production capacity analysis of the supplier, it is estimated that 3 idle A-type devices and 1 idle B-type device will be added after one week, and 1 idle A-type device will be added after two weeks. Among them, the A-type device is a high-precision cutting device with a cutting production efficiency of 80 pieces per hour for steel plates, and the B-type device is a general-precision cutting device with a cutting production efficiency of 110 pieces per hour for steel plates. All cutting devices can work continuously for 24 hours. Then, based on the spatial and temporal coordination analysis of the production factors of this supplier, the sorting result of the production factors of this supplier is obtained as follows: the maximum amount of high-precision steel plate cutting that can be completed currently is 2 * 7 * 24 * 80 = 26,880 pieces, and the maximum amount of general-precision steel plate cutting that can be completed is 5 * 7 * 24 * 110 = 92,400 pieces; after one week, the maximum amount of high-precision steel plate cutting that can be completed is 5 * 7 * 24 * 80 = 67,200 pieces, and the maximum amount of general-precision steel plate cutting that can be completed is 6 * 7 * 24 * 110 = 110,880 pieces; after two weeks, the maximum amount of high-precision steel plate cutting that can be completed is 6 * 7 * 24 * 80 = 80,640 pieces, and the maximum amount of general-precision steel plate cutting that can be completed is 6 * 7 * 24 * 110 = 110,880 pieces.

[0042] By obtaining the second adjustment result, the technical effect of providing a production capacity data basis for subsequent matching of corresponding demands based on the actual production capacity of the supply end and then establishing a highly adaptable cooperation is achieved.

[0043] Step S500: Based on the first adjustment result and the second adjustment result, perform a primary optimization screening on the first supply end to obtain a primary screening result;

[0044] Specifically, according to the first adjustment result adjusted based on the actual demand factor data of each demander and the second adjustment result adjusted based on the relevant production factor data such as the actual production capacity of each supplier, the multi-user docking method for the supply chain automatically screens each supplier, and the screened suppliers form the first-level screening result. Among them, each supplier in the first-level screening result refers to all suppliers in the first supply end whose actual production capacity, etc. meet the actual steel plate cutting requirements of each demander in the first demand end.

[0045] For example, Supplier A has 1 idle Type A steel plate cutting equipment this week and can complete 13,440 high-precision steel plate cutting tasks. Supplier B has 1 idle Type B steel plate cutting equipment this week and can complete 18,480 general-precision steel plate cutting tasks. Supplier C has 1 idle Type A steel plate cutting equipment and 2 idle Type B steel plate cutting equipment this week and can complete 13,440 high-precision steel plate cutting tasks and 36,960 general-precision steel plate cutting tasks. In addition, there are currently 100,000 general-precision steel plate cutting tasks. Then, Supplier B and Supplier C are included in the optimized screening result.

[0046] By comparing and screening based on the actual production and demand factor data of the supply and demand sides to obtain the supply sides that can meet the current demand, that is, obtaining the first-level screening result, it achieves the technical effect of narrowing the matching range for the subsequent system to match and cooperate with the manufacturing supply side based on the existing actual demand, improving the efficiency of matching and establishing cooperation, and ultimately improving the overall economic benefits.

[0047] Step S600: Traverse the first-level screening result to extract the utilization rate, and obtain the first utilization rate set, where the first utilization rate set and the first-level screening result are in one-to-one correspondence;

[0048] Specifically, in the first-level screening result obtained by comparing and screening based on the current actual steel plate cutting demand and actual steel plate cutting production capacity, further extract the utilization rate of each screened supplier in the production process in turn, so as to obtain the first utilization rate set. Among them, the first utilization rate set refers to the set of production utilization rate data of each supplier in the first-level screening result. Among them, the utilization rate refers to the ratio of the value created by actually cutting steel plates by the steel plate cutting equipment within a certain period of time to the value that can be achieved by theoretically cutting steel plates. In addition, the utilization rate specifically includes the time utilization rate, the output utilization rate, etc.

[0049] For example, theoretically, equipment type A can cut 1,920 high-precision steel plates within 24 hours. If it actually cuts 1,850 high-precision steel plates, the operating rate of equipment type A is 0.96. The operating rates of each supplier calculated in sequence form the first set of operating rates. Among them, there is a one-to-one correspondence between each operating rate in the first set of operating rates and each supplier in the first-level screening result.

[0050] By calculating the operating rates of each supplier obtained through screening, it achieves the technical effect of adjusting the actual production capacity data based on the operating rate data of each supplier's equipment in the subsequent stage, that is, providing a reference for improving the accuracy of the actual production capacity of each supplier.

[0051] Step S700: Based on the first set of operating rates, perform secondary optimization screening on the first-level screening result to obtain a secondary screening result, and perform multi-user docking based on the supply end corresponding to the secondary screening result.

[0052] Specifically, according to the operating rate data of each supplier in the calculated first-level screening result, analyze and adjust the actual production capacity of each supplier again, and then perform secondary optimization screening on the first-level screening result. The suppliers obtained through screening form the secondary screening result. For example, after the system's first-level screening, the obtained suppliers are Supplier B and Supplier C. Among them, the equipment operating rate of Supplier B is 0.98, and the equipment operating rate of Supplier C is 0.88. Then, it can be calculated that the number of ordinary-precision steel plate cutting tasks that Supplier B can actually complete is 18,480 * 0.98 = 18,110, the number of high-precision steel plate cutting tasks that Supplier C can actually complete is 13,440 * 0.88 = 11,827, and the number of ordinary-precision steel plate cutting tasks that Supplier C can actually complete is 36,960 * 0.88 = 32,524. Based on the current 100,000 ordinary-precision steel plate cutting task requirements, perform secondary screening on Supplier B and Supplier C again. The obtained secondary screening result is Supplier B and Supplier C. Further, dock each supplier in the obtained secondary screening result with the demand users of the corresponding demand side. For example, dock Supplier B and Supplier C with the demand users they can satisfy respectively.

[0053] By adjusting the actual production capacity based on the operating rate data of the actual production equipment of the supplier, it achieves the technical effect of improving the accuracy of the supplier's production capacity assessment, thereby improving the matching suitability between the supply and demand sides. While ensuring the needs of the demand side, it maximizes the economic benefits of both parties and even the entire supply chain.

[0054] Further, as shown in the appendix Figure 2 It is shown that step S400 of the present invention further includes:

[0055] Step S410: Obtain first production spatio-temporal sequence information according to the first production factor set, where the first production spatio-temporal sequence information corresponds one-to-one with the first supply end;

[0056] Step S420: Match first preset production sequence information according to the first demand factor set;

[0057] Step S430: Find the intersection of the first preset production sequence information and the first production spatio-temporal sequence information to obtain first intersection sequence information;

[0058] Step S440: Set the first demand factor set corresponding to the first intersection sequence information as the second adjustment result.

[0059] Specifically, by extracting and analyzing the actual available supply data of each supplier corresponding to the supply end in the multi-user docking system of the supply chain, information such as the actual steel plate cutting and the quantity and quality of available products of each supplier in different time periods is obtained, and the first production spatio-temporal sequence information is obtained by arranging them in chronological order. In addition, each supplier corresponds to a different location, that is, corresponds to different spatial information. Further, according to the demand data of each demander, a production plan information that meets the steel plate cutting requirements of each region and each time period is automatically generated, including the detailed production information of the supplier corresponding to the product requirements of each region and each stage. According to the actual production capacity information of each supplier and the actual demand data information of each demander, through comparison and integration, the corresponding supplier that meets the requirements of the corresponding region and the corresponding stage is obtained, that is, the first intersection sequence information is formed, and the first demand factor set corresponding to the first intersection sequence information is set as the second adjustment result. By analyzing the second adjustment result based on the actual situations of each supplier and demander, the technical effects of improving the accuracy and reliability of the second adjustment result are achieved.

[0060] Further, step S500 of the present invention further includes:

[0061] Step S510: Obtain first historical data, where the first historical data includes multiple groups: demand factor set, production factor set, and matching result identification information;

[0062] Step S520: Based on the gradient ascent decision forest, construct a first-level optimization model through the multiple groups: demand factor set, production factor set, and matching result identification information;

[0063] Step S530: Input the first adjustment result and the second adjustment result into the first-level optimization model to generate the first-level screening result.

[0064] Further, as shown in the appendix Figure 3 Step S520 of the present invention further includes:

[0065] Step S521: training a first decision tree through the multiple groups: demand factor set, production factor set and matching result identification information, wherein the number of layers of the first decision tree is limited to a, 15≤a≤20;

[0066] Step S522: extracting the first historical data that does not meet the first preset accuracy rate to generate second historical data;

[0067] Step S523: training a second decision tree using the second historical data, wherein the number of layers of the first decision tree is limited to b, 15≤b≤20;

[0068] Step S524: repeat M times until the amount of the Mth historical data is less than or equal to the preset amount of data, and obtain the M-1th decision tree, wherein the number of layers of the M-1th decision tree is limited to c, 15≤c≤20;

[0069] Step S525: Merge the first decision tree, the second decision tree, and up to the M-1th decision tree to generate the first-level optimization model.

[0070] Specifically, the first historical data is obtained by collecting the historical cutting steel plates, transaction orders and other related data of each supplier in the supply chain multi-user docking method system using computer technology. The first historical data includes all relevant data information of the actual demand of the corresponding demander and the actual production, delivery and other cooperation of the corresponding supplier in any historical collaborative manufacturing order. In other words, the first historical data includes multiple groups of historical order information, specifically the demand factor set, production factor set and matching result identification information of each order.

[0071] Furthermore, according to the relevant data information of each order in the first historical data, that is, multiple sets of demand factor sets, production factor sets and matching result identification information, the gradient ascent decision forest algorithm is used to train and obtain a first-level optimization model. The gradient ascent decision forest algorithm refers to first training with initial data to obtain a base learner, and then adjusting the training data according to the performance of the base learner and training again, so that the wrong samples in the previous learner are further trained, until multiple learners are finally obtained, and a model is formed by weighted combination to achieve the effect of improving the prediction accuracy.

[0072] Specifically, first, a decision tree model, i.e., the first decision tree, is trained based on multiple groups of demand factor sets, production factor sets, and matching result identification information. Then, the historical data information in the first historical data that does not meet the first preset accuracy rate is extracted, and the extracted data forms the second historical data. Further, a second decision tree is trained based on the second historical data. By analogy, through M times of extraction and training, M decision tree models are obtained, namely the first decision tree, the second decision tree... the (M - 1)th decision tree. Finally, all the decision trees are merged to obtain the first-level optimization model. Among them, the number of layers of each decision tree is set within the range of [15, 20].

[0073] By setting the range of the number of layers for each decision tree training, overfitting of the training results is avoided, and at the same time, the training time is saved. In addition, the first-level optimization model is trained based on the idea of the gradient ascent decision forest algorithm, achieving the technical effects of improving the degree of abnormal data analysis and processing and improving the model performance.

[0074] Further, as shown in the appendix Figure 4 it is shown that step S700 of the present invention further includes:

[0075] Step S710: Obtain the first output demand information and the first time zone demand information according to the first demand factor set, where the first output demand information and the first time zone demand information are in one-to-one correspondence;

[0076] Step S720: Based on the first time zone demand information, traverse the first set of utilization rates to obtain the first set of time utilization rates and the first set of performance utilization rates;

[0077] Step S730: Traverse the first set of time utilization rates and the first set of performance utilization rates for output prediction to obtain the first set of output prediction results;

[0078] Step S740: Match the first set of output prediction results with the first output demand information to obtain the second-level screening result.

[0079] Further, step S730 of the present invention further includes:

[0080] Step S731: Obtain the first output prediction formula:

[0081]

[0082] Step S732: Among them, p 1 is the time utilization rate, p 2 is the performance utilization rate, α and β are the proportions of the time utilization rate and the performance utilization rate, and A is the preset output in the t-th time zone, is the predicted output value of the nth supply end in the tth time zone;

[0083] Step S733: Input the first set of time utilization rates and the first set of performance utilization rates into the first output prediction formula in sequence to obtain the first set of output prediction results.

[0084] Specifically, according to the demand data information of each demander in the demand end of the supply chain multi-user docking system, extract the total demand for steel plate cutting of each demander and the demand time period information corresponding to each demand quantity, so as to obtain the one-to-one correspondence between output demand and output demand time. Further, based on the data in the demand information of the first time zone, traverse the utilization rate data of the cutting equipment of each supplier in the supply end of the supply chain multi-user docking system, so as to extract the time utilization rate and performance utilization rate of the supplier in the corresponding stage. Furthermore, the time utilization rates and performance utilization rates of all suppliers in this stage respectively form the first set of time utilization rates and the first set of performance utilization rates. Among them, the time utilization rate refers to the ratio of the actual time spent by the steel plate cutting equipment of the supplier to cut a unit quantity of steel plates to the theoretically required time; the performance utilization rate refers to the ratio of the actual number of steel plates cut by the steel plate cutting equipment of the supplier per unit time to the theoretically cuttable number of steel plates. Further, based on the time utilization rate data and performance utilization rate data of each supplier, predict the actual production capacity of each supplier, that is, the output. The specific calculation algorithm is as shown in the following first output prediction formula:

[0085]

[0086] where p 1 is the time utilization rate, p 2 is the performance utilization rate, α and β are the proportions of the time utilization rate and performance utilization rate, A is the preset output in the tth time zone, is the predicted output value of the nth supply end in the tth time zone.

[0087] Finally, based on the first output prediction formula, combined with the utilization rate data of each supplier in the first set of time utilization rates and the first set of performance utilization rates, calculate in sequence to obtain the output prediction results of each supplier. The output prediction results of all suppliers form the first set of output prediction results.

[0088] By considering the time utilization rate and performance utilization rate data of each supplier, quantitatively predicting the actual output of each supplier, etc., the technical effect of improving the accuracy of the output prediction of the supplier and providing data reference for the subsequent establishment of reasonable and reliable collaborative manufacturing is achieved.

[0089] Further, the present invention further includes step S734:

[0090] Step S7341: Traverse according to the first-level screening results to obtain the first set of first-pass yields;

[0091] Step S7342: Adjust the first production prediction formula according to the first set of first-pass yields to obtain the second production prediction formula:

[0092]

[0093] Step S7343: Among them, p 1 is the time operation rate, p 2 is the performance operation rate, p 3 is the first-pass yield, α, β, and γ are the proportions of the time operation rate, performance operation rate, and first-pass yield, A is the preset production volume in the t-th time zone, is the production prediction value of the n-th supplier in the t-th time zone;

[0094] Step S7344: Input the first set of time operation rates, the first set of performance operation rates, and the first set of first-pass yields into the second production prediction formula in sequence to obtain the second set of production prediction results.

[0095] Specifically, calculate and analyze the first-pass yields of each supplier in the first-level screening results one by one. For example, based on the detection data of the historical cut steel plates of each supplier, calculate the ratio of the number of detected qualified steel plates to the total number of cut steel plates, that is, the first-pass yield data. Further, based on the set of first-pass yield data of each supplier, adjust the first production prediction formula, that is, consider the impact of the first-pass yield of the supplier on its production volume, and further predict its production volume. The specific calculation method is shown in the following formula:

[0096]

[0097] Among them, p 1 is the time operation rate, p 2 is the performance operation rate, p 3 is the first-pass yield, α, β, and γ are the proportions of the time operation rate, performance operation rate, and first-pass yield, A is the preset production volume in the t-th time zone, is the production prediction value of the n-th supplier in the t-th time zone.

[0098] Finally, based on the second production prediction formula, combined with the operation rate data of each supplier in the first set of time operation rates and the first set of performance operation rates, and the first set of first-pass yields, calculate in sequence to obtain the production prediction results of each supplier. The production prediction results of all suppliers form the second set of production prediction results. By considering the first-pass yield data of the steel plates cut by the supplier to predict its actual production volume, the technical effect of improving the accuracy of the production prediction results and further improving the matching degree between the supplier and the demander is achieved.

[0099] In summary, a multi-user docking method for the supply chain of a cloud cutting platform provided by the present invention has the following technical effects:

[0100] 1. Through the steel plate cutting collaborative manufacturing sharing platform, the actual situations of the supply side and the demand side are respectively collected, intelligently analyzed and adjusted, and then based on the adjustment results, the supply side is optimized and screened at the first level. Further, combined with the actual production capacity index data of each supplier in the first-level optimization and screening results, the final supplier is obtained through the second-level optimization and screening, and the docking between the finally selected supplier and multiple demand users is established. Through the intelligent analysis and adjustment of the multi-user docking system for the supply chain, the supply-demand matching degree of collaborative manufacturing between the supply side and the demand side is improved. On the basis of ensuring the basic steel plate cutting needs of the demand side, the technical effect of improving the overall working efficiency of the supply chain and then realizing the maximization of the interests of multiple parties is achieved.

[0101] 2. An first-level optimization model is trained through the idea of the gradient ascent decision forest algorithm, where the layer range is set in each decision tree training, avoiding overfitting of the training results and saving training time at the same time, achieving the technical effects of improving the degree of abnormal data analysis and processing and improving the model performance.

[0102] 3. By considering the time utilization rate, performance utilization rate data, and cutting steel plate yield rate data of each supplier, the output of each supplier is quantitatively predicted, achieving the technical effect of improving the accuracy of supplier output prediction and providing data reference for subsequent establishment of reasonable and reliable collaborative manufacturing.

[0103] Embodiment 2

[0104] Based on the multi-user docking method for the supply chain of a cloud cutting platform in the foregoing embodiment and the same inventive concept, the present invention further provides a multi-user docking system for the supply chain of a cloud cutting platform. Please refer to the appendix Figure 5 , the system includes:

[0105] The first generating unit 11 is used to collect demand elements of the first demand side and generate a first demand element set;

[0106] The first obtaining unit 12 is used to serially adjust the first demand element set based on time sequence to obtain a first adjustment result;

[0107] The second generating unit 13 is used to collect production elements of the first supply side and generate a first production element set;

[0108] The second obtaining unit 14 is used to perform space-time adjustment on the first production element set based on time sequence to obtain a second adjustment result;

[0109] A third acquisition unit 15, configured to perform a primary optimization screening on the first supply end based on the first adjustment result and the second adjustment result, and obtain a primary screening result;

[0110] A fourth acquisition unit 16, configured to traverse the primary screening result to extract the utilization rate and obtain a first utilization rate set, where the first utilization rate set and the primary screening result are in one-to-one correspondence;

[0111] A first execution unit 17, configured to perform a secondary optimization screening on the primary screening result based on the first utilization rate set to obtain a secondary screening result, and perform multi-user docking based on the supply end corresponding to the secondary screening result.

[0112] Furthermore, the system further includes:

[0113] A fifth acquisition unit, configured to obtain first production spatio-temporal sequence information according to the first production factor set, where the first production spatio-temporal sequence information and the first supply end are in one-to-one correspondence;

[0114] A first matching unit, configured to match first preset production sequence information according to the first demand factor set;

[0115] A sixth acquisition unit, configured to find the intersection of the first preset production sequence information and the first production spatio-temporal sequence information to obtain first intersection sequence information;

[0116] A first setting unit, configured to set the first demand factor set corresponding to the first intersection sequence information as the second adjustment result.

[0117] Furthermore, the system further includes:

[0118] A seventh acquisition unit, configured to obtain first historical data, where the first historical data includes multiple groups: demand factor set, production factor set, and matching result identification information;

[0119] A first construction unit, configured to construct a primary optimization model based on the gradient ascent decision forest through the multiple groups: demand factor set, production factor set, and matching result identification information;

[0120] A third generation unit, configured to input the first adjustment result and the second adjustment result into the primary optimization model to generate the primary screening result.

[0121] Furthermore, the system further includes:

[0122] The first training unit is configured to train a first decision tree by using the multiple groups of: requirement element sets, production element sets, and matching result identification information, where the number of layers of the first decision tree is limited to a, and 15 ≤ a ≤ 20;

[0123] The fourth generation unit is configured to extract the first historical data that does not meet the first preset accuracy rate and generate second historical data;

[0124] The second training unit is configured to train a second decision tree by using the second historical data, where the number of layers of the first decision tree is limited to b, and 15 ≤ b ≤ 20;

[0125] The eighth acquisition unit is configured to repeat M times until the data volume of the Mth historical data ≤ the preset data volume, and acquire the (M - 1)th decision tree, where the number of layers of the (M - 1)th decision tree is limited to c, and 15 ≤ c ≤ 20;

[0126] The fifth generation unit is configured to merge the first decision tree, the second decision tree, until the (M - 1)th decision tree to generate the first-level optimization model.

[0127] Further, the system further includes:

[0128] The ninth acquisition unit is configured to acquire first production demand information and first time zone demand information according to the first requirement element set, where the first production demand information and the first time zone demand information are in one-to-one correspondence;

[0129] The tenth acquisition unit is configured to traverse the first operating rate set based on the first time zone demand information to acquire a first time operating rate set and a first performance operating rate set;

[0130] The eleventh acquisition unit is configured to traverse the first time operating rate set and the first performance operating rate set for production prediction to acquire a first production prediction result set;

[0131] The twelfth acquisition unit is configured to match the first production prediction result set and the first production demand information to acquire the second-level screening result.

[0132] Further, the system further includes:

[0133] The thirteenth acquisition unit is configured to acquire a first production prediction formula:

[0134]

[0135] The second setting unit, where the second setting unit is used for where, p 1 is the time operation rate, p 2 is the performance operation rate, α and β are the proportions of the time operation rate and the performance operation rate, A is the preset output in the t-th time zone, is the predicted output value of the n-th supply end in the t-th time zone;

[0136] The fourteenth obtaining unit is configured to input the first time operation rate set and the first performance operation rate set into the first output prediction formula in sequence to obtain the first output prediction result set.

[0137] Further, the system further includes:

[0138] The fifteenth obtaining unit is configured to traverse according to the first-level screening result to obtain the first set of good product rates;

[0139] The sixteenth obtaining unit is configured to adjust the first output prediction formula according to the first set of good product rates to obtain the second output prediction formula:

[0140]

[0141] The third setting unit, where the third setting unit is used for where, p 1 is the time operation rate, p 2 is the performance operation rate, p 3 is the good product rate, α, β and γ are the proportions of the time operation rate, the performance operation rate and the good product rate, A is the preset output in the t-th time zone, is the predicted output value of the n-th supply end in the t-th time zone;

[0142] The seventeenth obtaining unit is configured to input the first time operation rate set, the first performance operation rate set and the first set of good product rates into the second output prediction formula in sequence to obtain the second output prediction result set.

[0143] The various embodiments in this specification are described in a progressive manner. The key points of each embodiment are the differences from other embodiments. The foregoing Figure 1The supply chain multi-user docking method and specific example in Embodiment 1 are equally applicable to the supply chain multi-user docking system of a cloud cutting platform in this embodiment. Through the detailed description of the supply chain multi-user docking method of a cloud cutting platform above, those skilled in the art can clearly know the supply chain multi-user docking system of a cloud cutting platform in this embodiment. Therefore, for the sake of simplicity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0144] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0145] Exemplary electronic device

[0146] Next, refer to Figure 6 to describe the electronic device of the present invention.

[0147] Figure 6 The structural schematic diagram of the electronic device according to the present invention is illustrated.

[0148] Based on the inventive concept of the supply chain multi-user docking method of a cloud cutting platform in the foregoing embodiment, the present invention further provides a supply chain multi-user docking system of a cloud cutting platform, on which a computer program is stored, and when the program is executed by a processor, the steps of any of the methods of the supply chain multi-user docking method of a cloud cutting platform described above are implemented.

[0149] Among them, in Figure 6 the bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, and bus 300 links various circuits including one or more processors represented by processor 302 and a memory represented by memory 304 together. Bus 300 may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and therefore, will not be further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, that is, a transceiver, providing a unit for communicating with various other devices on the transmission medium.

[0150] The processor 302 is responsible for managing the bus 300 and general processing, while the memory 304 can be used to store data used by the processor 302 when performing operations.

[0151] The present invention provides a method for multi-user docking of the supply chain of a cloud cutting platform. The method is applied to a multi-user docking system of the supply chain of a cloud cutting platform. Wherein, the method includes: collecting demand elements from the first demand side to generate a first demand element set; serially adjusting the first demand element set based on time sequence to obtain a first adjustment result; collecting production elements from the first supply side to generate a first production element set; performing space-time adjustment on the first production element set based on time sequence to obtain a second adjustment result; performing primary optimization screening on the first supply side based on the first adjustment result and the second adjustment result to obtain a primary screening result; traversing the primary screening result to extract the utilization rate to obtain a first utilization rate set, wherein the first utilization rate set and the primary screening result are in one-to-one correspondence; performing secondary optimization screening on the primary screening result based on the first utilization rate set to obtain a secondary screening result, and performing multi-user docking based on the supply side corresponding to the secondary screening result. It solves the technical problem in the prior art that in the collaborative manufacturing of steel plate cutting, the supplier and the demander communicate and establish a cooperation on the collaborative manufacturing plan based on their actual production or demand situations respectively, resulting in poor flexibility in collaborative manufacturing and low matching degree between the supply and demand sides, and thus unable to maximize the interests of multiple parties in the supply chain. Through the intelligent analysis and adjustment processing of the multi-user docking system of the supply chain, the supply-demand matching degree of collaborative manufacturing between the supply side and the demand side is improved. On the basis of ensuring the basic steel plate cutting requirements of the demand side, the technical effect of improving the overall working efficiency of the supply chain and thus realizing the maximization of the interests of multiple parties is achieved.

[0152] The present invention also provides an electronic device, which includes a processor and a memory;

[0153] The memory is used for storage;

[0154] The processor is used to execute the method described in any one of the above-mentioned Embodiment 1 by calling.

[0155] The present invention also provides a computer program product for multi-user docking of the supply chain of a cloud cutting platform, including a computer program and / or instructions. When the computer program and / or instructions are executed by a processor, the steps of the method described in any one of the above-mentioned Embodiment 1 are implemented.

[0156] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, an apparatus, or a computer program product. Therefore, the present invention can take the form of a complete software embodiment, a complete hardware embodiment, or an embodiment combining software and hardware aspects. In addition, the present invention is in the form of a computer program product that can be implemented on one or more computer-usable storage media containing computer-usable program code. The computer-usable storage media include, but are not limited to, various media that can store program code, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disk storage, compact disc read-only memory (CD-ROM), optical storage, etc.

[0157] The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a system for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0158] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing devices to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction system that implements the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0159] These computer program instructions can also be loaded onto a computer or other programmable data processing devices, such that a series of operation steps are executed on the computer or other programmable devices to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable devices provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks. Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications to these embodiments once they know the basic creative concepts.

[0160] Obviously, those skilled in the art can make various modifications and variations 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 present invention and its equivalent technologies, the present invention also intends to include these modifications and variations.

Claims

1. A multi-user docking method for the supply chain of a cloud cutting platform, characterized in that, the method includes: Collect demand elements from the first demand side to generate a first demand element set; Perform serialization adjustment on the first demand element set based on time sequence to obtain a first adjustment result; Collect production elements from the first supply side to generate a first production element set; Perform space-time adjustment on the first production element set based on time sequence to obtain a second adjustment result; Perform primary optimization screening on the first supply side based on the first adjustment result and the second adjustment result to obtain a primary screening result; Traverse the primary screening result to extract the utilization rate to obtain a first utilization rate set, where the first utilization rate set and the primary screening result are in one-to-one correspondence; Perform secondary optimization screening on the primary screening result based on the first utilization rate set to obtain a secondary screening result, and perform multi-user docking based on the supply side corresponding to the secondary screening result; The performing space-time adjustment on the first production element set based on time sequence to obtain a second adjustment result includes: According to the first production element set, obtain first production space-time sequence information, where the first production space-time sequence information and the first supply side are in one-to-one correspondence; Match the first preset production time sequence information according to the first demand element set; Find the intersection of the first preset production time sequence information and the first production space-time sequence information to obtain first intersection time sequence information; Set the first demand element set corresponding to the first intersection time sequence information as the second adjustment result; The performing primary optimization screening on the first supply side based on the first adjustment result and the second adjustment result to obtain a primary screening result includes: Obtain first historical data, where the first historical data includes multiple groups: demand element set, production element set, and matching result identification information; Based on the gradient ascent decision forest, construct a primary optimization model through the multiple groups: demand element set, production element set, and matching result identification information; Input the first adjustment result and the second adjustment result into the primary optimization model to generate the primary screening result; The constructing a primary optimization model based on the gradient ascent decision forest through the multiple groups: demand element set, production element set, and matching result identification information includes: Train a first decision tree through the multiple groups: demand element set, production element set, and matching result identification information, where the number of layers of the first decision tree is limited to a, 15 ≤ a ≤ 20; Extract the first historical data that does not meet the first preset accuracy rate to generate second historical data; Train a second decision tree through the second historical data, where the number of layers of the first decision tree is limited to b, 15 ≤ b ≤ 20; Repeat M times until the data volume of the Mth historical data ≤ the preset data volume to obtain the (M - 1)th decision tree, where the number of layers of the (M - 1)th decision tree is limited to c, 15 ≤ c ≤ 20; Merge the first decision tree, the second decision tree until the (M - 1)th decision tree to generate the primary optimization model; Performing secondary screening on the first-level screening result based on the first utilization rate set to obtain a secondary screening result, including: Obtaining first production demand information and first time zone demand information according to the first demand factor set, wherein the first production demand information and the first time zone demand information are in one-to-one correspondence; Based on the first time zone demand information, traversing the first utilization rate set to obtain a first time utilization rate set and a first performance utilization rate set; Traversing the first time utilization rate set and the first performance utilization rate set for production prediction to obtain a first production prediction result set; Matching the first production prediction result set with the first production demand information to obtain the secondary screening result; The traversing the first time utilization rate set and the first performance utilization rate set for production prediction to obtain a first production prediction result set includes: Obtaining a first production prediction formula; Among them, p 1 is the time operation rate, p 2 is the performance operation rate, α and β are the proportions of the time operation rate and the performance operation rate, A is the preset output in the t-th time zone, is the predicted output value of the n-th supply end in the t-th time zone; Sequentially inputting the first time utilization rate set and the first performance utilization rate set into the first production prediction formula to obtain the first production prediction result set; The method further includes: Traversing according to the first-level screening result to obtain a first yield rate set; Adjusting the first production prediction formula according to the first yield rate set to obtain a second production prediction formula; Among them, p 1 is the time operation rate, p 2 is the performance operation rate, p 3 is the yield rate, α, β, and γ are the proportions of the time operation rate, performance operation rate, and yield rate, A is the preset output in the t-th time zone, is the predicted output value of the n-th supply end in the t-th time zone; Sequentially inputting the first time utilization rate set, the first performance utilization rate set, and the first yield rate set into the second production prediction formula to obtain a second production prediction result set.

2. A multi-user docking system for the supply chain of a cloud cutting platform Characterized in that The system is applied to the method described in claim 1, and the system includes: A first generation unit: The first generation unit is used to collect demand factors from a first demand side and generate a first demand factor set; A first obtaining unit: The first obtaining unit is used to perform serialization adjustment on the first demand factor set based on time sequence to obtain a first adjustment result; A second generation unit: The second generation unit is used to collect production factors from a first supply side and generate a first production factor set; A second obtaining unit: The second obtaining unit is used to perform space-time adjustment on the first production factor set based on time sequence to obtain a second adjustment result; A third obtaining unit: The third obtaining unit is used to perform first-level optimization screening on the first supply side based on the first adjustment result and the second adjustment result to obtain a first-level screening result; A fourth obtaining unit: The fourth obtaining unit is used to traverse the first-level screening result to extract the utilization rate and obtain a first utilization rate set, wherein the first utilization rate and the first-level screening result are in one-to-one correspondence; A first execution unit: The first execution unit is used to perform secondary optimization screening on the first-level screening result based on the first utilization rate set to obtain a secondary screening result, and perform multi-user docking based on the supply side corresponding to the secondary screening result.

3. An electronic device Characterized in that It includes a processor and a memory; The memory is used for storage; The processor is used to execute the method described in claim 1 by calling.

4. A computer program product for multi-user docking of the supply chain of a cloud cutting platform, including computer programs and / or instructions, characterized in that, when the computer program and / or instructions are executed by a processor, the steps of the method described in claim 1 are implemented.

Images